Re: [f2fs-dev] [PATCH 1/3] f2fs:dax: fix races between page faults and fallocate

Hi Qiuyang, When I checked i_mmap_sem in ext4, do we also check it in: f2fs_vm_page_mkwrite filemap_fault f2fs_setattr f2fs_add_inline_entries It needs to think about how to reduce lock coverage below as well. Thanks, On 05/04, sunqiuyang wrote: > Currently in F2FS, page faults and

Re: [f2fs-dev] [PATCH 1/3] f2fs:dax: fix races between page faults and fallocate

Hi Qiuyang, When I checked i_mmap_sem in ext4, do we also check it in: f2fs_vm_page_mkwrite filemap_fault f2fs_setattr f2fs_add_inline_entries It needs to think about how to reduce lock coverage below as well. Thanks, On 05/04, sunqiuyang wrote: > Currently in F2FS, page faults and

[PATCH 1/3] f2fs:dax: fix races between page faults and fallocate

Currently in F2FS, page faults and fallocate operations, like punch_hole and collapse/insert/zero_range, are completely unsynchronized. This can result in page fault faulting in a page into a range that we are changing after truncating pagecache, and thus we can end up with a page mapped to

[PATCH 1/3] f2fs:dax: fix races between page faults and fallocate

Currently in F2FS, page faults and fallocate operations, like punch_hole and collapse/insert/zero_range, are completely unsynchronized. This can result in page fault faulting in a page into a range that we are changing after truncating pagecache, and thus we can end up with a page mapped to