From 581b2027af0018944ba301d68e7af45c6d1128b5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 1 Sep 2021 09:15:21 +0100 Subject: afs: Fix page leak There's a loop in afs_extend_writeback() that adds extra pages to a write we want to make to improve the efficiency of the writeback by making it larger. This loop stops, however, if we hit a page we can't write back from immediately, but it doesn't get rid of the page ref we speculatively acquired. This was caused by the removal of the cleanup loop when the code switched from using find_get_pages_contig() to xarray scanning as the latter only gets a single page at a time, not a batch. Fix this by putting the page on a ref on an early break from the loop. Unfortunately, we can't just add that page to the pagevec we're employing as we'll go through that and add those pages to the RPC call. This was found by the generic/074 test. It leaks ~4GiB of RAM each time it is run - which can be observed with "top". Fixes: e87b03f5830e ("afs: Prepare for use of THPs") Reported-by: Marc Dionne Signed-off-by: David Howells Reviewed-and-tested-by: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111666635.283156.177701903478910460.stgit@warthog.procyon.org.uk/ --- fs/afs/write.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'fs/afs/write.c') diff --git a/fs/afs/write.c b/fs/afs/write.c index c0534697268e..66b235266893 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -471,13 +471,18 @@ static void afs_extend_writeback(struct address_space *mapping, } /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) + if (unlikely(page != xas_reload(&xas))) { + put_page(page); break; + } - if (!trylock_page(page)) + if (!trylock_page(page)) { + put_page(page); break; + } if (!PageDirty(page) || PageWriteback(page)) { unlock_page(page); + put_page(page); break; } @@ -487,6 +492,7 @@ static void afs_extend_writeback(struct address_space *mapping, t = afs_page_dirty_to(page, priv); if (f != 0 && !new_content) { unlock_page(page); + put_page(page); break; } -- cgit v1.2.3 From 3978d816523991dd86cf9aae88c295230a5ea3b2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 1 Sep 2021 19:22:50 +0100 Subject: afs: Add missing vnode validation checks afs_d_revalidate() should only be validating the directory entry it is given and the directory to which that belongs; it shouldn't be validating the inode/vnode to which that dentry points. Besides, validation need to be done even if we don't call afs_d_revalidate() - which might be the case if we're starting from a file descriptor. In order for afs_d_revalidate() to be fixed, validation points must be added in some other places. Certain directory operations, such as afs_unlink(), already check this, but not all and not all file operations either. Note that the validation of a vnode not only checks to see if the attributes we have are correct, but also gets a promise from the server to notify us if that file gets changed by a third party. Add the following checks: - Check the vnode we're going to make a hard link to. - Check the vnode we're going to move/rename. - Check the vnode we're going to read from. - Check the vnode we're going to write to. - Check the vnode we're going to sync. - Check the vnode we're going to make a mapped page writable for. Some of these aren't strictly necessary as we're going to perform a server operation that might get the attributes anyway from which we can determine if something changed - though it might not get us a callback promise. Signed-off-by: David Howells Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111667354.283156.12720698333342917516.stgit@warthog.procyon.org.uk/ --- fs/afs/write.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'fs/afs/write.c') diff --git a/fs/afs/write.c b/fs/afs/write.c index 66b235266893..32a764c24284 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -807,6 +807,7 @@ int afs_writepages(struct address_space *mapping, ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) { struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp)); + struct afs_file *af = iocb->ki_filp->private_data; ssize_t result; size_t count = iov_iter_count(from); @@ -822,6 +823,10 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) if (!count) return 0; + result = afs_validate(vnode, af->key); + if (result < 0) + return result; + result = generic_file_write_iter(iocb, from); _leave(" = %zd", result); @@ -835,13 +840,18 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) */ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct inode *inode = file_inode(file); - struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); + struct afs_file *af = file->private_data; + int ret; _enter("{%llx:%llu},{n=%pD},%d", vnode->fid.vid, vnode->fid.vnode, file, datasync); + ret = afs_validate(vnode, af->key); + if (ret < 0) + return ret; + return file_write_and_wait_range(file, start, end); } @@ -855,11 +865,14 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) struct file *file = vmf->vma->vm_file; struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_file *af = file->private_data; unsigned long priv; vm_fault_t ret = VM_FAULT_RETRY; _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + afs_validate(vnode, af->key); + sb_start_pagefault(inode->i_sb); /* Wait for the page to be written to the cache before we allow it to -- cgit v1.2.3 From 9d37e1cab2a9d2cee2737973fa455e6f89eee46a Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Sep 2021 21:55:19 +0100 Subject: afs: Fix updating of i_blocks on file/dir extension When an afs file or directory is modified locally such that the total file size is extended, i_blocks needs to be recalculated too. Fix this by making afs_write_end() and afs_edit_dir_add() call afs_set_i_size() rather than setting inode->i_size directly as that also recalculates inode->i_blocks. This can be tested by creating and writing into directories and files and then examining them with du. Without this change, directories show a 4 blocks (they start out at 2048 bytes) and files show 0 blocks; with this change, they should show a number of blocks proportional to the file size rounded up to 1024. Fixes: 31143d5d515e ("AFS: implement basic file write support") Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") Reported-by: Markus Suvanto Signed-off-by: David Howells Reviewed-by: Marc Dionne Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163113612442.352844.11162345591911691150.stgit@warthog.procyon.org.uk/ --- fs/afs/write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/afs/write.c') diff --git a/fs/afs/write.c b/fs/afs/write.c index 32a764c24284..2dfe3b3a53d6 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -137,7 +137,7 @@ int afs_write_end(struct file *file, struct address_space *mapping, write_seqlock(&vnode->cb_lock); i_size = i_size_read(&vnode->vfs_inode); if (maybe_i_size > i_size) - i_size_write(&vnode->vfs_inode, maybe_i_size); + afs_set_i_size(vnode, maybe_i_size); write_sequnlock(&vnode->cb_lock); } -- cgit v1.2.3