On Wed, 22 Mar 2023 17:15:48 -0600 Jens Axboe <axboe@xxxxxxxxx> wrote: > On 3/22/23 5:13 PM, David Howells wrote: > > Stephen Rothwell <sfr@xxxxxxxxxxxxxxxx> wrote: > > > >> + if (unlikely(iov_iter_is_pipe(i))) { > >> + copied = copy_page_to_iter_pipe(page, offset, bytes, i); > >> + goto out; > >> + } > > > > This bit would need to be removed from copy_page_to_iter_atomic() as the two > > functions it calls should be removed by the patch in the block tree. > > Maybe it'd be better to consolidate rather than split the changes over > two trees? fyi, Lorenzo has sent out v7 of this series. I'll be pushing this in an hour or so. After which I suggest Stephen removes those (now) two lines and sends out one of his "build fix" emails which can be the basis for Linus's resolution. Or I can just steal "iov_iter: Kill ITER_PIPE"... From: Lorenzo Stoakes <lstoakes@xxxxxxxxx> Subject: iov_iter: add copy_page_to_iter_nofault() Date: Wed, 22 Mar 2023 18:57:03 +0000 Provide a means to copy a page to user space from an iterator, aborting if a page fault would occur. This supports compound pages, but may be passed a tail page with an offset extending further into the compound page, so we cannot pass a folio. This allows for this function to be called from atomic context and _try_ to user pages if they are faulted in, aborting if not. The function does not use _copy_to_iter() in order to not specify might_fault(), this is similar to copy_page_from_iter_atomic(). This is being added in order that an iteratable form of vread() can be implemented while holding spinlocks. Link: https://lkml.kernel.org/r/19734729defb0f498a76bdec1bef3ac48a3af3e8.1679511146.git.lstoakes@xxxxxxxxx Signed-off-by: Lorenzo Stoakes <lstoakes@xxxxxxxxx> Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx> Cc: Baoquan He <bhe@xxxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: Jens Axboe <axboe@xxxxxxxxx> Cc: Jiri Olsa <jolsa@xxxxxxxxxx> Cc: Liu Shixin <liushixin2@xxxxxxxxxx> Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> Cc: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- --- a/include/linux/uio.h~iov_iter-add-copy_page_to_iter_nofault +++ a/include/linux/uio.h @@ -173,6 +173,8 @@ static inline size_t copy_folio_to_iter( { return copy_page_to_iter(&folio->page, offset, bytes, i); } +size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, + size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) --- a/lib/iov_iter.c~iov_iter-add-copy_page_to_iter_nofault +++ a/lib/iov_iter.c @@ -172,6 +172,18 @@ static int copyout(void __user *to, cons return n; } +static int copyout_nofault(void __user *to, const void *from, size_t n) +{ + long res; + + if (should_fail_usercopy()) + return n; + + res = copy_to_user_nofault(to, from, n); + + return res < 0 ? n : res; +} + static int copyin(void *to, const void __user *from, size_t n) { size_t res = n; @@ -734,6 +746,42 @@ size_t copy_page_to_iter(struct page *pa } EXPORT_SYMBOL(copy_page_to_iter); +size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, + struct iov_iter *i) +{ + size_t res = 0; + + if (!page_copy_sane(page, offset, bytes)) + return 0; + if (WARN_ON_ONCE(i->data_source)) + return 0; + if (unlikely(iov_iter_is_pipe(i))) + return copy_page_to_iter_pipe(page, offset, bytes, i); + page += offset / PAGE_SIZE; // first subpage + offset %= PAGE_SIZE; + while (1) { + void *kaddr = kmap_local_page(page); + size_t n = min(bytes, (size_t)PAGE_SIZE - offset); + + iterate_and_advance(i, n, base, len, off, + copyout_nofault(base, kaddr + offset + off, len), + memcpy(base, kaddr + offset + off, len) + ) + kunmap_local(kaddr); + res += n; + bytes -= n; + if (!bytes || !n) + break; + offset += n; + if (offset == PAGE_SIZE) { + page++; + offset = 0; + } + } + return res; +} +EXPORT_SYMBOL(copy_page_to_iter_nofault); + size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { _