From 56a76f8275c379ed73c8a43cfa1dfa2f5e9cfa19 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 31 Mar 2009 15:23:23 -0700 Subject: fs: fix page_mkwrite error cases in core code and btrfs page_mkwrite is called with neither the page lock nor the ptl held. This means a page can be concurrently truncated or invalidated out from underneath it. Callers are supposed to prevent truncate races themselves, however previously the only thing they can do in case they hit one is to raise a SIGBUS. A sigbus is wrong for the case that the page has been invalidated or truncated within i_size (eg. hole punched). Callers may also have to perform memory allocations in this path, where again, SIGBUS would be wrong. The previous patch ("mm: page_mkwrite change prototype to match fault") made it possible to properly specify errors. Convert the generic buffer.c code and btrfs to return sane error values (in the case of page removed from pagecache, VM_FAULT_NOPAGE will cause the fault handler to exit without doing anything, and the fault will be retried properly). This fixes core code, and converts btrfs as a template/example. All other filesystems defining their own page_mkwrite should be fixed in a similar manner. Acked-by: Chris Mason Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/inode.c | 11 +++++++---- fs/buffer.c | 12 ++++++++---- 2 files changed, 15 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ec5423790bb..17e608c4dc7 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4307,10 +4307,15 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) u64 page_end; ret = btrfs_check_data_free_space(root, inode, PAGE_CACHE_SIZE); - if (ret) + if (ret) { + if (ret == -ENOMEM) + ret = VM_FAULT_OOM; + else /* -ENOSPC, -EIO, etc */ + ret = VM_FAULT_SIGBUS; goto out; + } - ret = -EINVAL; + ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */ again: lock_page(page); size = i_size_read(inode); @@ -4363,8 +4368,6 @@ again: out_unlock: unlock_page(page); out: - if (ret) - ret = VM_FAULT_SIGBUS; return ret; } diff --git a/fs/buffer.c b/fs/buffer.c index 6d51a3da362..0c14f8d52ee 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2320,7 +2320,7 @@ block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, struct inode *inode = vma->vm_file->f_path.dentry->d_inode; unsigned long end; loff_t size; - int ret = -EINVAL; + int ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */ lock_page(page); size = i_size_read(inode); @@ -2340,10 +2340,14 @@ block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, if (!ret) ret = block_commit_write(page, 0, end); -out_unlock: - if (ret) - ret = VM_FAULT_SIGBUS; + if (unlikely(ret)) { + if (ret == -ENOMEM) + ret = VM_FAULT_OOM; + else /* -ENOSPC, -EIO, etc */ + ret = VM_FAULT_SIGBUS; + } +out_unlock: unlock_page(page); return ret; } -- cgit v1.2.3