From 225a05043cd87a37455bfbff8c35d4e276519387 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 8 Feb 2023 14:56:11 +0000 Subject: filemap: Remove lock_page_killable() There are no more callers; remove this function before any more appear. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells Signed-off-by: Steve French --- include/linux/pagemap.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 29e1f9e76eb6..2f5b36f446cc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -977,16 +977,6 @@ static inline int folio_lock_killable(struct folio *folio) return 0; } -/* - * lock_page_killable is like lock_page but can be interrupted by fatal - * signals. It returns 0 if it locked the page and -EINTR if it was - * killed while waiting. - */ -static inline int lock_page_killable(struct page *page) -{ - return folio_lock_killable(page_folio(page)); -} - /* * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. -- cgit v1.3.1 From 07073eb01c5f630344bc1c3e56b0e0d94aedf919 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Feb 2023 15:01:42 +0000 Subject: splice: Add a func to do a splice from a buffered file without ITER_PIPE Provide a function to do splice read from a buffered file, pulling the folios out of the pagecache directly by calling filemap_get_pages() to do any required reading and then pasting the returned folios into the pipe. A helper function is provided to do the actual folio pasting and will handle multipage folios by splicing as many of the relevant subpages as will fit into the pipe. The code is loosely based on filemap_read() and might belong in mm/filemap.c with that as it needs to use filemap_get_pages(). Signed-off-by: David Howells Reviewed-by: Jens Axboe cc: Christoph Hellwig cc: Al Viro cc: David Hildenbrand cc: John Hubbard cc: linux-mm@kvack.org cc: linux-block@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- include/linux/fs.h | 3 ++ include/linux/pipe_fs_i.h | 20 +++++++ lib/iov_iter.c | 6 --- mm/filemap.c | 129 ++++++++++++++++++++++++++++++++++++++++++++++ mm/internal.h | 6 +++ 5 files changed, 158 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c1769a2c5d70..28743e38df91 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3163,6 +3163,9 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ +ssize_t filemap_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 6cb65df3e3ba..d2c3f16cf6b1 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -156,6 +156,26 @@ static inline bool pipe_full(unsigned int head, unsigned int tail, return pipe_occupancy(head, tail) >= limit; } +/** + * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring + * @pipe: The pipe to access + * @slot: The slot of interest + */ +static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe, + unsigned int slot) +{ + return &pipe->bufs[slot & (pipe->ring_size - 1)]; +} + +/** + * pipe_head_buf - Return the pipe buffer at the head of the pipe ring + * @pipe: The pipe to access + */ +static inline struct pipe_buffer *pipe_head_buf(const struct pipe_inode_info *pipe) +{ + return pipe_buf(pipe, pipe->head); +} + /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f9a3ff37ecd1..47c484551c59 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -186,12 +186,6 @@ static int copyin(void *to, const void __user *from, size_t n) return res; } -static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe, - unsigned int slot) -{ - return &pipe->bufs[slot & (pipe->ring_size - 1)]; -} - #ifdef PIPE_PARANOIA static bool sanity(const struct iov_iter *i) { diff --git a/mm/filemap.c b/mm/filemap.c index 2d5377012284..162b4daaeb99 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -42,6 +42,8 @@ #include #include #include +#include +#include #include #include #include "internal.h" @@ -2843,6 +2845,133 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) } EXPORT_SYMBOL(generic_file_read_iter); +/* + * Splice subpages from a folio into a pipe. + */ +size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, + struct folio *folio, loff_t fpos, size_t size) +{ + struct page *page; + size_t spliced = 0, offset = offset_in_folio(folio, fpos); + + page = folio_page(folio, offset / PAGE_SIZE); + size = min(size, folio_size(folio) - offset); + offset %= PAGE_SIZE; + + while (spliced < size && + !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { + struct pipe_buffer *buf = pipe_head_buf(pipe); + size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); + + *buf = (struct pipe_buffer) { + .ops = &page_cache_pipe_buf_ops, + .page = page, + .offset = offset, + .len = part, + }; + folio_get(folio); + pipe->head++; + page++; + spliced += part; + offset = 0; + } + + return spliced; +} + +/* + * Splice folios from the pagecache of a buffered (ie. non-O_DIRECT) file into + * a pipe. + */ +ssize_t filemap_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct folio_batch fbatch; + struct kiocb iocb; + size_t total_spliced = 0, used, npages; + loff_t isize, end_offset; + bool writably_mapped; + int i, error = 0; + + init_sync_kiocb(&iocb, in); + iocb.ki_pos = *ppos; + + /* Work out how much data we can actually add into the pipe */ + used = pipe_occupancy(pipe->head, pipe->tail); + npages = max_t(ssize_t, pipe->max_usage - used, 0); + len = min_t(size_t, len, npages * PAGE_SIZE); + + folio_batch_init(&fbatch); + + do { + cond_resched(); + + if (*ppos >= i_size_read(file_inode(in))) + break; + + iocb.ki_pos = *ppos; + error = filemap_get_pages(&iocb, len, &fbatch, true); + if (error < 0) + break; + + /* + * i_size must be checked after we know the pages are Uptodate. + * + * Checking i_size after the check allows us to calculate + * the correct value for "nr", which means the zero-filled + * part of the page is not copied back to userspace (unless + * another truncate extends the file - this is desired though). + */ + isize = i_size_read(file_inode(in)); + if (unlikely(*ppos >= isize)) + break; + end_offset = min_t(loff_t, isize, *ppos + len); + + /* + * Once we start copying data, we don't want to be touching any + * cachelines that might be contended: + */ + writably_mapped = mapping_writably_mapped(in->f_mapping); + + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; + size_t n; + + if (folio_pos(folio) >= end_offset) + goto out; + folio_mark_accessed(folio); + + /* + * If users can be writing to this folio using arbitrary + * virtual addresses, take care of potential aliasing + * before reading the folio on the kernel side. + */ + if (writably_mapped) + flush_dcache_folio(folio); + + n = min_t(loff_t, len, isize - *ppos); + n = splice_folio_into_pipe(pipe, folio, *ppos, n); + if (!n) + goto out; + len -= n; + total_spliced += n; + *ppos += n; + in->f_ra.prev_pos = *ppos; + if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + goto out; + } + + folio_batch_release(&fbatch); + } while (len); + +out: + folio_batch_release(&fbatch); + file_accessed(in); + + return total_spliced ? total_spliced : error; +} + static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) diff --git a/mm/internal.h b/mm/internal.h index bcf75a8b032d..6d4ca98f3844 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -794,6 +794,12 @@ struct migration_target_control { gfp_t gfp_mask; }; +/* + * mm/filemap.c + */ +size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, + struct folio *folio, loff_t fpos, size_t size); + /* * mm/vmalloc.c */ -- cgit v1.3.1 From 33b3b041543e8b3abf9a692d0f8c2ab0e07c50cd Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 7 Feb 2023 10:45:40 +0000 Subject: splice: Add a func to do a splice from an O_DIRECT file without ITER_PIPE Implement a function, direct_file_splice(), that deals with this by using an ITER_BVEC iterator instead of an ITER_PIPE iterator as the former won't free its buffers when reverted. The function bulk allocates all the buffers it thinks it is going to use in advance, does the read synchronously and only then trims the buffer down. The pages we did use get pushed into the pipe. This fixes a problem with the upcoming iov_iter_extract_pages() function, whereby pages extracted from a non-user-backed iterator such as ITER_PIPE aren't pinned. __iomap_dio_rw(), however, calls iov_iter_revert() to shorten the iterator to just the bufferage it is going to use - which has the side-effect of freeing the excess pipe buffers, even though they're attached to a bio and may get written to by DMA (thanks to Hillf Danton for spotting this[1]). This then causes memory corruption that is particularly noticeable when the syzbot test[2] is run. The test boils down to: out = creat(argv[1], 0666); ftruncate(out, 0x800); lseek(out, 0x200, SEEK_SET); in = open(argv[1], O_RDONLY | O_DIRECT | O_NOFOLLOW); sendfile(out, in, NULL, 0x1dd00); run repeatedly in parallel. What I think is happening is that ftruncate() occasionally shortens the DIO read that's about to be made by sendfile's splice core by reducing i_size. This should be more efficient for DIO read by virtue of doing a bulk page allocation, but slightly less efficient by ignoring any partial page in the pipe. Reported-by: syzbot+a440341a59e3b7142895@syzkaller.appspotmail.com Signed-off-by: David Howells Reviewed-by: Jens Axboe cc: Christoph Hellwig cc: Al Viro cc: David Hildenbrand cc: John Hubbard cc: linux-mm@kvack.org cc: linux-block@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20230207094731.1390-1-hdanton@sina.com/ [1] Link: https://lore.kernel.org/r/000000000000b0b3c005f3a09383@google.com/ [2] Signed-off-by: Steve French --- fs/splice.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 3 ++ 2 files changed, 95 insertions(+) (limited to 'include/linux') diff --git a/fs/splice.c b/fs/splice.c index 5969b7a1d353..4c6332854b63 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -282,6 +282,98 @@ void splice_shrink_spd(struct splice_pipe_desc *spd) kfree(spd->partial); } +/* + * Splice data from an O_DIRECT file into pages and then add them to the output + * pipe. + */ +ssize_t direct_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct iov_iter to; + struct bio_vec *bv; + struct kiocb kiocb; + struct page **pages; + ssize_t ret; + size_t used, npages, chunk, remain, reclaim; + int i; + + /* Work out how much data we can actually add into the pipe */ + used = pipe_occupancy(pipe->head, pipe->tail); + npages = max_t(ssize_t, pipe->max_usage - used, 0); + len = min_t(size_t, len, npages * PAGE_SIZE); + npages = DIV_ROUND_UP(len, PAGE_SIZE); + + bv = kzalloc(array_size(npages, sizeof(bv[0])) + + array_size(npages, sizeof(struct page *)), GFP_KERNEL); + if (!bv) + return -ENOMEM; + + pages = (void *)(bv + npages); + npages = alloc_pages_bulk_array(GFP_USER, npages, pages); + if (!npages) { + kfree(bv); + return -ENOMEM; + } + + remain = len = min_t(size_t, len, npages * PAGE_SIZE); + + for (i = 0; i < npages; i++) { + chunk = min_t(size_t, PAGE_SIZE, remain); + bv[i].bv_page = pages[i]; + bv[i].bv_offset = 0; + bv[i].bv_len = chunk; + remain -= chunk; + } + + /* Do the I/O */ + iov_iter_bvec(&to, ITER_DEST, bv, npages, len); + init_sync_kiocb(&kiocb, in); + kiocb.ki_pos = *ppos; + ret = call_read_iter(in, &kiocb, &to); + + reclaim = npages * PAGE_SIZE; + remain = 0; + if (ret > 0) { + reclaim -= ret; + remain = ret; + *ppos = kiocb.ki_pos; + file_accessed(in); + } else if (ret < 0) { + /* + * callers of ->splice_read() expect -EAGAIN on + * "can't put anything in there", rather than -EFAULT. + */ + if (ret == -EFAULT) + ret = -EAGAIN; + } + + /* Free any pages that didn't get touched at all. */ + reclaim /= PAGE_SIZE; + if (reclaim) { + npages -= reclaim; + release_pages(pages + npages, reclaim); + } + + /* Push the remaining pages into the pipe. */ + for (i = 0; i < npages; i++) { + struct pipe_buffer *buf = pipe_head_buf(pipe); + + chunk = min_t(size_t, remain, PAGE_SIZE); + *buf = (struct pipe_buffer) { + .ops = &default_pipe_buf_ops, + .page = bv[i].bv_page, + .offset = 0, + .len = chunk, + }; + pipe->head++; + remain -= chunk; + } + + kfree(bv); + return ret; +} + /** * generic_file_splice_read - splice data from file to a pipe * @in: file to splice from diff --git a/include/linux/fs.h b/include/linux/fs.h index 28743e38df91..551c9403f9b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3166,6 +3166,9 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +ssize_t direct_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, -- cgit v1.3.1 From f62e52d1276b6cd329fe72d36bdf912b2ce4caaf Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 19 Jan 2023 12:47:23 +0000 Subject: iov_iter: Define flags to qualify page extraction. Define flags to qualify page extraction to pass into iov_iter_*_pages*() rather than passing in FOLL_* flags. For now only a flag to allow peer-to-peer DMA is supported. Signed-off-by: David Howells Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jens Axboe cc: Al Viro cc: Logan Gunthorpe cc: linux-fsdevel@vger.kernel.org cc: linux-block@vger.kernel.org Signed-off-by: Steve French --- block/bio.c | 6 +++--- block/blk-map.c | 8 ++++---- include/linux/uio.h | 10 ++++++++-- lib/iov_iter.c | 14 ++++++++------ 4 files changed, 23 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index ab59a491a883..b97f3991c904 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1245,11 +1245,11 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page, */ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { + iov_iter_extraction_t extraction_flags = 0; unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; - unsigned int gup_flags = 0; ssize_t size, left; unsigned len, i = 0; size_t offset, trim; @@ -1264,7 +1264,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue)) - gup_flags |= FOLL_PCI_P2PDMA; + extraction_flags |= ITER_ALLOW_P2PDMA; /* * Each segment in the iov is required to be a block size multiple. @@ -1275,7 +1275,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) */ size = iov_iter_get_pages(iter, pages, UINT_MAX - bio->bi_iter.bi_size, - nr_pages, &offset, gup_flags); + nr_pages, &offset, extraction_flags); if (unlikely(size <= 0)) return size ? size : -EFAULT; diff --git a/block/blk-map.c b/block/blk-map.c index 19940c978c73..080dd60485be 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -265,9 +265,9 @@ static struct bio *blk_rq_map_bio_alloc(struct request *rq, static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { + iov_iter_extraction_t extraction_flags = 0; unsigned int max_sectors = queue_max_hw_sectors(rq->q); unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS); - unsigned int gup_flags = 0; struct bio *bio; int ret; int j; @@ -280,7 +280,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, return -ENOMEM; if (blk_queue_pci_p2pdma(rq->q)) - gup_flags |= FOLL_PCI_P2PDMA; + extraction_flags |= ITER_ALLOW_P2PDMA; while (iov_iter_count(iter)) { struct page **pages, *stack_pages[UIO_FASTIOV]; @@ -291,10 +291,10 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (nr_vecs <= ARRAY_SIZE(stack_pages)) { pages = stack_pages; bytes = iov_iter_get_pages(iter, pages, LONG_MAX, - nr_vecs, &offs, gup_flags); + nr_vecs, &offs, extraction_flags); } else { bytes = iov_iter_get_pages_alloc(iter, &pages, - LONG_MAX, &offs, gup_flags); + LONG_MAX, &offs, extraction_flags); } if (unlikely(bytes <= 0)) { ret = bytes ? bytes : -EFAULT; diff --git a/include/linux/uio.h b/include/linux/uio.h index 9f158238edba..eec6ed8a627a 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -13,6 +13,8 @@ struct page; struct pipe_inode_info; +typedef unsigned int __bitwise iov_iter_extraction_t; + struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; @@ -252,12 +254,12 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray * loff_t start, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start, - unsigned gup_flags); + iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start, - unsigned gup_flags); + iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); @@ -360,4 +362,8 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, }; } +/* Flags for iov_iter_get/extract_pages*() */ +/* Allow P2PDMA on the extracted pages */ +#define ITER_ALLOW_P2PDMA ((__force iov_iter_extraction_t)0x01) + #endif diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 47c484551c59..9d4949ea9b27 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1426,9 +1426,9 @@ static struct page *first_bvec_segment(const struct iov_iter *i, static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, size_t *start, - unsigned int gup_flags) + iov_iter_extraction_t extraction_flags) { - unsigned int n; + unsigned int n, gup_flags = 0; if (maxsize > i->count) maxsize = i->count; @@ -1436,6 +1436,8 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, return 0; if (maxsize > MAX_RW_COUNT) maxsize = MAX_RW_COUNT; + if (extraction_flags & ITER_ALLOW_P2PDMA) + gup_flags |= FOLL_PCI_P2PDMA; if (likely(user_backed_iter(i))) { unsigned long addr; @@ -1489,14 +1491,14 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start, unsigned gup_flags) + size_t *start, iov_iter_extraction_t extraction_flags) { if (!maxpages) return 0; BUG_ON(!pages); return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, - start, gup_flags); + start, extraction_flags); } EXPORT_SYMBOL_GPL(iov_iter_get_pages); @@ -1509,14 +1511,14 @@ EXPORT_SYMBOL(iov_iter_get_pages2); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, - size_t *start, unsigned gup_flags) + size_t *start, iov_iter_extraction_t extraction_flags) { ssize_t len; *pages = NULL; len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start, - gup_flags); + extraction_flags); if (len <= 0) { kvfree(*pages); *pages = NULL; -- cgit v1.3.1 From 7d58fe731028128f3a7e20b9c492be48aae133ee Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 28 Oct 2022 21:50:30 +0100 Subject: iov_iter: Add a function to extract a page list from an iterator Add a function, iov_iter_extract_pages(), to extract a list of pages from an iterator. The pages may be returned with a pin added or nothing, depending on the type of iterator. Add a second function, iov_iter_extract_will_pin(), to determine how the cleanup should be done. There are two cases: (1) ITER_IOVEC or ITER_UBUF iterator. Extracted pages will have pins (FOLL_PIN) obtained on them so that a concurrent fork() will forcibly copy the page so that DMA is done to/from the parent's buffer and is unavailable to/unaffected by the child process. iov_iter_extract_will_pin() will return true for this case. The caller should use something like unpin_user_page() to dispose of the page. (2) Any other sort of iterator. No refs or pins are obtained on the page, the assumption is made that the caller will manage page retention. iov_iter_extract_will_pin() will return false. The pages don't need additional disposal. Signed-off-by: David Howells Reviewed-by: Christoph Hellwig Reviewed-by: Jens Axboe cc: Al Viro cc: John Hubbard cc: David Hildenbrand cc: Matthew Wilcox cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org Signed-off-by: Steve French --- include/linux/uio.h | 27 +++++- lib/iov_iter.c | 264 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 290 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index eec6ed8a627a..514e3b7b06b8 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -361,9 +361,34 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, .count = count }; } - /* Flags for iov_iter_get/extract_pages*() */ /* Allow P2PDMA on the extracted pages */ #define ITER_ALLOW_P2PDMA ((__force iov_iter_extraction_t)0x01) +ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages, + size_t maxsize, unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0); + +/** + * iov_iter_extract_will_pin - Indicate how pages from the iterator will be retained + * @iter: The iterator + * + * Examine the iterator and indicate by returning true or false as to how, if + * at all, pages extracted from the iterator will be retained by the extraction + * function. + * + * %true indicates that the pages will have a pin placed in them that the + * caller must unpin. This is must be done for DMA/async DIO to force fork() + * to forcibly copy a page for the child (the parent must retain the original + * page). + * + * %false indicates that no measures are taken and that it's up to the caller + * to retain the pages. + */ +static inline bool iov_iter_extract_will_pin(const struct iov_iter *iter) +{ + return user_backed_iter(iter); +} + #endif diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9d4949ea9b27..e53b16235385 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1910,3 +1910,267 @@ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) i->iov -= state->nr_segs - i->nr_segs; i->nr_segs = state->nr_segs; } + +/* + * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not + * get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + struct page *page, **p; + unsigned int nr = 0, offset; + loff_t pos = i->xarray_start + i->iov_offset; + pgoff_t index = pos >> PAGE_SHIFT; + XA_STATE(xas, i->xarray, index); + + offset = pos & ~PAGE_MASK; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + + rcu_read_lock(); + for (page = xas_load(&xas); page; page = xas_next(&xas)) { + if (xas_retry(&xas, page)) + continue; + + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(&xas))) { + xas_reset(&xas); + continue; + } + + p[nr++] = find_subpage(page, xas.xa_index); + if (nr == maxpages) + break; + } + rcu_read_unlock(); + + maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); + iov_iter_advance(i, maxsize); + return maxsize; +} + +/* + * Extract a list of contiguous pages from an ITER_BVEC iterator. This does + * not get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + struct page **p, *page; + size_t skip = i->iov_offset, offset; + int k; + + for (;;) { + if (i->nr_segs == 0) + return 0; + maxsize = min(maxsize, i->bvec->bv_len - skip); + if (maxsize) + break; + i->iov_offset = 0; + i->nr_segs--; + i->bvec++; + skip = 0; + } + + skip += i->bvec->bv_offset; + page = i->bvec->bv_page + skip / PAGE_SIZE; + offset = skip % PAGE_SIZE; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + for (k = 0; k < maxpages; k++) + p[k] = page + k; + + maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset); + iov_iter_advance(i, maxsize); + return maxsize; +} + +/* + * Extract a list of virtually contiguous pages from an ITER_KVEC iterator. + * This does not get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + struct page **p, *page; + const void *kaddr; + size_t skip = i->iov_offset, offset, len; + int k; + + for (;;) { + if (i->nr_segs == 0) + return 0; + maxsize = min(maxsize, i->kvec->iov_len - skip); + if (maxsize) + break; + i->iov_offset = 0; + i->nr_segs--; + i->kvec++; + skip = 0; + } + + kaddr = i->kvec->iov_base + skip; + offset = (unsigned long)kaddr & ~PAGE_MASK; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + + kaddr -= offset; + len = offset + maxsize; + for (k = 0; k < maxpages; k++) { + size_t seg = min_t(size_t, len, PAGE_SIZE); + + if (is_vmalloc_or_module_addr(kaddr)) + page = vmalloc_to_page(kaddr); + else + page = virt_to_page(kaddr); + + p[k] = page; + len -= seg; + kaddr += PAGE_SIZE; + } + + maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset); + iov_iter_advance(i, maxsize); + return maxsize; +} + +/* + * Extract a list of contiguous pages from a user iterator and get a pin on + * each of them. This should only be used if the iterator is user-backed + * (IOBUF/UBUF). + * + * It does not get refs on the pages, but the pages must be unpinned by the + * caller once the transfer is complete. + * + * This is safe to be used where background IO/DMA *is* going to be modifying + * the buffer; using a pin rather than a ref makes forces fork() to give the + * child a copy of the page. + */ +static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, + struct page ***pages, + size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + unsigned long addr; + unsigned int gup_flags = 0; + size_t offset; + int res; + + if (i->data_source == ITER_DEST) + gup_flags |= FOLL_WRITE; + if (extraction_flags & ITER_ALLOW_P2PDMA) + gup_flags |= FOLL_PCI_P2PDMA; + if (i->nofault) + gup_flags |= FOLL_NOFAULT; + + addr = first_iovec_segment(i, &maxsize); + *offset0 = offset = addr % PAGE_SIZE; + addr &= PAGE_MASK; + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + res = pin_user_pages_fast(addr, maxpages, gup_flags, *pages); + if (unlikely(res <= 0)) + return res; + maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - offset); + iov_iter_advance(i, maxsize); + return maxsize; +} + +/** + * iov_iter_extract_pages - Extract a list of contiguous pages from an iterator + * @i: The iterator to extract from + * @pages: Where to return the list of pages + * @maxsize: The maximum amount of iterator to extract + * @maxpages: The maximum size of the list of pages + * @extraction_flags: Flags to qualify request + * @offset0: Where to return the starting offset into (*@pages)[0] + * + * Extract a list of contiguous pages from the current point of the iterator, + * advancing the iterator. The maximum number of pages and the maximum amount + * of page contents can be set. + * + * If *@pages is NULL, a page list will be allocated to the required size and + * *@pages will be set to its base. If *@pages is not NULL, it will be assumed + * that the caller allocated a page list at least @maxpages in size and this + * will be filled in. + * + * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA + * be allowed on the pages extracted. + * + * The iov_iter_extract_will_pin() function can be used to query how cleanup + * should be performed. + * + * Extra refs or pins on the pages may be obtained as follows: + * + * (*) If the iterator is user-backed (ITER_IOVEC/ITER_UBUF), pins will be + * added to the pages, but refs will not be taken. + * iov_iter_extract_will_pin() will return true. + * + * (*) If the iterator is ITER_KVEC, ITER_BVEC or ITER_XARRAY, the pages are + * merely listed; no extra refs or pins are obtained. + * iov_iter_extract_will_pin() will return 0. + * + * Note also: + * + * (*) Use with ITER_DISCARD is not supported as that has no content. + * + * On success, the function sets *@pages to the new pagelist, if allocated, and + * sets *offset0 to the offset into the first page. + * + * It may also return -ENOMEM and -EFAULT. + */ +ssize_t iov_iter_extract_pages(struct iov_iter *i, + struct page ***pages, + size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + maxsize = min_t(size_t, min_t(size_t, maxsize, i->count), MAX_RW_COUNT); + if (!maxsize) + return 0; + + if (likely(user_backed_iter(i))) + return iov_iter_extract_user_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); + if (iov_iter_is_kvec(i)) + return iov_iter_extract_kvec_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); + if (iov_iter_is_bvec(i)) + return iov_iter_extract_bvec_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); + if (iov_iter_is_xarray(i)) + return iov_iter_extract_xarray_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); + return -EFAULT; +} +EXPORT_SYMBOL_GPL(iov_iter_extract_pages); -- cgit v1.3.1 From 85dd2c8ff368b1446be9febde84afe1d7aec4261 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 16:16:32 +0100 Subject: netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator Add a function to extract the pages from a user-space supplied iterator (UBUF- or IOVEC-type) into a BVEC-type iterator, retaining the pages by getting a pin on them (as FOLL_PIN) as we go. This is useful in three situations: (1) A userspace thread may have a sibling that unmaps or remaps the process's VM during the operation, changing the assignment of the pages and potentially causing an error. Retaining the pages keeps some pages around, even if this occurs; futher, we find out at the point of extraction if EFAULT is going to be incurred. (2) Pages might get swapped out/discarded if not retained, so we want to retain them to avoid the reload causing a deadlock due to a DIO from/to an mmapped region on the same file. (3) The iterator may get passed to sendmsg() by the filesystem. If a fault occurs, we may get a short write to a TCP stream that's then tricky to recover from. We don't deal with other types of iterator here, leaving it to other mechanisms to retain the pages (eg. PG_locked, PG_writeback and the pipe lock). Signed-off-by: David Howells cc: Jeff Layton cc: Steve French cc: Shyam Prasad N cc: Rohith Surabattula cc: linux-cachefs@redhat.com cc: linux-cifs@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- fs/netfs/Makefile | 1 + fs/netfs/iterator.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/netfs.h | 4 ++ 3 files changed, 108 insertions(+) create mode 100644 fs/netfs/iterator.c (limited to 'include/linux') diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index f684c0cd1ec5..386d6fb92793 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -3,6 +3,7 @@ netfs-y := \ buffered_read.o \ io.o \ + iterator.o \ main.o \ objects.o diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c new file mode 100644 index 000000000000..6f0d79080abc --- /dev/null +++ b/fs/netfs/iterator.c @@ -0,0 +1,103 @@ +// 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 +#include +#include +#include +#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; + bv[npages + i].bv_page = *pages++; + bv[npages + i].bv_offset = offset; + bv[npages + i].bv_len = len - 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); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 4c76ddfb6a67..b11a84f6c32b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -17,6 +17,7 @@ #include #include #include +#include enum netfs_sreq_ref_trace; @@ -296,6 +297,9 @@ void netfs_get_subrequest(struct netfs_io_subrequest *subreq, void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, enum netfs_sreq_ref_trace what); void netfs_stats_show(struct seq_file *); +ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, + struct iov_iter *new, + iov_iter_extraction_t extraction_flags); /** * netfs_inode - Get the netfs inode context from the inode -- cgit v1.3.1 From 0185846975339a5c348373aa450a977f5242366b Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Oct 2022 16:19:44 +0100 Subject: netfs: Add a function to extract an iterator into a scatterlist Provide a function for filling in a scatterlist from the list of pages contained in an iterator. If the iterator is UBUF- or IOBUF-type, the pages have a pin taken on them (as FOLL_PIN). If the iterator is BVEC-, KVEC- or XARRAY-type, no pin is taken on the pages and it is left to the caller to manage their lifetime. It cannot be assumed that a ref can be validly taken, particularly in the case of a KVEC iterator. Signed-off-by: David Howells cc: Jeff Layton cc: Steve French cc: Shyam Prasad N cc: Rohith Surabattula cc: linux-cachefs@redhat.com cc: linux-cifs@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- fs/netfs/iterator.c | 268 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/netfs.h | 4 + mm/vmalloc.c | 1 + 3 files changed, 273 insertions(+) (limited to 'include/linux') diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 6f0d79080abc..80d7ff440cac 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -7,7 +7,9 @@ #include #include +#include #include +#include #include #include "internal.h" @@ -101,3 +103,269 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, return npages; } EXPORT_SYMBOL_GPL(netfs_extract_user_iter); + +/* + * Extract and pin a list of up to sg_max pages from UBUF- or IOVEC-class + * iterators, and add them to the scatterlist. + */ +static ssize_t netfs_extract_user_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + struct page **pages; + unsigned int npages; + ssize_t ret = 0, res; + size_t len, off; + + /* We decant the page list into the tail of the scatterlist */ + pages = (void *)sgtable->sgl + array_size(sg_max, sizeof(struct scatterlist)); + pages -= sg_max; + + do { + res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, + extraction_flags, &off); + if (res < 0) + goto failed; + + len = res; + maxsize -= len; + ret += len; + npages = DIV_ROUND_UP(off + len, PAGE_SIZE); + sg_max -= npages; + + for (; npages < 0; npages--) { + struct page *page = *pages; + size_t seg = min_t(size_t, PAGE_SIZE - off, len); + + *pages++ = NULL; + sg_set_page(sg, page, len, off); + sgtable->nents++; + sg++; + len -= seg; + off = 0; + } + } while (maxsize > 0 && sg_max > 0); + + return ret; + +failed: + while (sgtable->nents > sgtable->orig_nents) + put_page(sg_page(&sgtable->sgl[--sgtable->nents])); + return res; +} + +/* + * Extract up to sg_max pages from a BVEC-type iterator and add them to the + * scatterlist. The pages are not pinned. + */ +static ssize_t netfs_extract_bvec_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + const struct bio_vec *bv = iter->bvec; + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + unsigned long start = iter->iov_offset; + unsigned int i; + ssize_t ret = 0; + + for (i = 0; i < iter->nr_segs; i++) { + size_t off, len; + + len = bv[i].bv_len; + if (start >= len) { + start -= len; + continue; + } + + len = min_t(size_t, maxsize, len - start); + off = bv[i].bv_offset + start; + + sg_set_page(sg, bv[i].bv_page, len, off); + sgtable->nents++; + sg++; + sg_max--; + + ret += len; + maxsize -= len; + if (maxsize <= 0 || sg_max == 0) + break; + start = 0; + } + + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/* + * Extract up to sg_max pages from a KVEC-type iterator and add them to the + * scatterlist. This can deal with vmalloc'd buffers as well as kmalloc'd or + * static buffers. The pages are not pinned. + */ +static ssize_t netfs_extract_kvec_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + const struct kvec *kv = iter->kvec; + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + unsigned long start = iter->iov_offset; + unsigned int i; + ssize_t ret = 0; + + for (i = 0; i < iter->nr_segs; i++) { + struct page *page; + unsigned long kaddr; + size_t off, len, seg; + + len = kv[i].iov_len; + if (start >= len) { + start -= len; + continue; + } + + kaddr = (unsigned long)kv[i].iov_base + start; + off = kaddr & ~PAGE_MASK; + len = min_t(size_t, maxsize, len - start); + kaddr &= PAGE_MASK; + + maxsize -= len; + ret += len; + do { + seg = min_t(size_t, len, PAGE_SIZE - off); + if (is_vmalloc_or_module_addr((void *)kaddr)) + page = vmalloc_to_page((void *)kaddr); + else + page = virt_to_page(kaddr); + + sg_set_page(sg, page, len, off); + sgtable->nents++; + sg++; + sg_max--; + + len -= seg; + kaddr += PAGE_SIZE; + off = 0; + } while (len > 0 && sg_max > 0); + + if (maxsize <= 0 || sg_max == 0) + break; + start = 0; + } + + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/* + * Extract up to sg_max folios from an XARRAY-type iterator and add them to + * the scatterlist. The pages are not pinned. + */ +static ssize_t netfs_extract_xarray_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + struct xarray *xa = iter->xarray; + struct folio *folio; + loff_t start = iter->xarray_start + iter->iov_offset; + pgoff_t index = start / PAGE_SIZE; + ssize_t ret = 0; + size_t offset, len; + XA_STATE(xas, xa, index); + + rcu_read_lock(); + + xas_for_each(&xas, folio, ULONG_MAX) { + if (xas_retry(&xas, folio)) + continue; + if (WARN_ON(xa_is_value(folio))) + break; + if (WARN_ON(folio_test_hugetlb(folio))) + break; + + offset = offset_in_folio(folio, start); + len = min_t(size_t, maxsize, folio_size(folio) - offset); + + sg_set_page(sg, folio_page(folio, 0), len, offset); + sgtable->nents++; + sg++; + sg_max--; + + maxsize -= len; + ret += len; + if (maxsize <= 0 || sg_max == 0) + break; + } + + rcu_read_unlock(); + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/** + * netfs_extract_iter_to_sg - Extract pages from an iterator and add ot an sglist + * @iter: The iterator to extract from + * @maxsize: The amount of iterator to copy + * @sgtable: The scatterlist table to fill in + * @sg_max: Maximum number of elements in @sgtable that may be filled + * @extraction_flags: Flags to qualify the request + * + * Extract the page fragments from the given amount of the source iterator and + * add them to a scatterlist that refers to all of those bits, to a maximum + * addition of @sg_max elements. + * + * The pages referred to by UBUF- and IOVEC-type iterators are extracted and + * pinned; BVEC-, KVEC- and XARRAY-type are extracted but aren't pinned; PIPE- + * and DISCARD-type are not supported. + * + * No end mark is placed on the scatterlist; that's left to the caller. + * + * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA + * be allowed on the pages extracted. + * + * If successul, @sgtable->nents is updated to include the number of elements + * added and the number of bytes added is returned. @sgtable->orig_nents is + * left unaltered. + * + * The iov_iter_extract_mode() function should be used to query how cleanup + * should be performed. + */ +ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t maxsize, + struct sg_table *sgtable, unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + if (maxsize == 0) + return 0; + + switch (iov_iter_type(iter)) { + case ITER_UBUF: + case ITER_IOVEC: + return netfs_extract_user_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_BVEC: + return netfs_extract_bvec_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_KVEC: + return netfs_extract_kvec_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_XARRAY: + return netfs_extract_xarray_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + default: + pr_err("%s(%u) unsupported\n", __func__, iov_iter_type(iter)); + WARN_ON_ONCE(1); + return -EIO; + } +} +EXPORT_SYMBOL_GPL(netfs_extract_iter_to_sg); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index b11a84f6c32b..a1f3522daa69 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -300,6 +300,10 @@ void netfs_stats_show(struct seq_file *); 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 sg_table; +ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t len, + struct sg_table *sgtable, unsigned int sg_max, + iov_iter_extraction_t extraction_flags); /** * netfs_inode - Get the netfs inode context from the inode diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ca71de7c9d77..61f5bec0f2b6 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -656,6 +656,7 @@ int is_vmalloc_or_module_addr(const void *x) #endif return is_vmalloc_addr(x); } +EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr); /* * Walk a vmap address to the struct page it maps. Huge vmap mappings will -- cgit v1.3.1