From: Andrew Morton Date: Tue, 16 Oct 2007 08:24:54 +0000 (-0700) Subject: Revert "[PATCH] generic_file_buffered_write(): deadlock on vectored write" X-Git-Tag: v2.6.24-rc1~1208 X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=6814d7a91289ceb143285975e244a8f00fd3a830;p=linux-2.6 Revert "[PATCH] generic_file_buffered_write(): deadlock on vectored write" This reverts commit 6527c2bdf1f833cc18e8f42bd97973d583e4aa83, which fixed the following bug: When prefaulting in the pages in generic_file_buffered_write(), we only faulted in the pages for the firts segment of the iovec. If the second of successive segment described a mmapping of the page into which we're write()ing, and that page is not up-to-date, the fault handler tries to lock the already-locked page (to bring it up to date) and deadlocks. An exploit for this bug is in writev-deadlock-demo.c, in http://www.zip.com.au/~akpm/linux/patches/stuff/ext3-tools.tar.gz. (These demos assume blocksize < PAGE_CACHE_SIZE). The problem with this fix is that it takes the kernel back to doing a single prepare_write()/commit_write() per iovec segment. So in the worst case we'll run prepare_write+commit_write 1024 times where we previously would have run it once. The other problem with the fix is that it fix all the locking problems. And apparently this change killed NFS overwrite performance, because, I suppose, it talks to the server for each prepare_write+commit_write. So just back that patch out - we'll be fixing the deadlock by other means. Nick says: also it only ever actually papered over the bug, because after faulting in the pages, they might be unmapped or reclaimed. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/mm/filemap.c b/mm/filemap.c index caaaa7adfd..4bf7d1ab6c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1865,21 +1865,14 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, do { unsigned long index; unsigned long offset; + unsigned long maxlen; size_t copied; offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */ index = pos >> PAGE_CACHE_SHIFT; bytes = PAGE_CACHE_SIZE - offset; - - /* Limit the size of the copy to the caller's write size */ - bytes = min(bytes, count); - - /* - * Limit the size of the copy to that of the current segment, - * because fault_in_pages_readable() doesn't know how to walk - * segments. - */ - bytes = min(bytes, cur_iov->iov_len - iov_base); + if (bytes > count) + bytes = count; /* * Bring in the user page that we will copy from _first_. @@ -1887,7 +1880,10 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, * same page as we're writing to, without it being marked * up-to-date. */ - fault_in_pages_readable(buf, bytes); + maxlen = cur_iov->iov_len - iov_base; + if (maxlen > bytes) + maxlen = bytes; + fault_in_pages_readable(buf, maxlen); page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec); if (!page) {