From: Dan Williams Subject: [PATCH v6 00/15] dax: fix dma vs truncate/hole-punch Date: Thu, 15 Mar 2018 08:51:22 -0700 Message-ID: <152112908134.24669.10222746224538377035.stgit@dwillia2-desk3.amr.corp.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Michal Hocko , jack-AlSwsSmVLrQ@public.gmane.org, Matthew Wilcox , "Darrick J. Wong" , Dave Hansen , Dave Chinner , =?utf-8?b?SsOpcsO0bWU=?= Glisse , Andrew Morton , linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-xfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Andreas Dilger , Alexander Viro , Jan Kara , linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Theodore Ts'o , linux-ext4-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, hch-jcswGhMUV9g@public.gmane.org To: linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org Return-path: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: linux-nvdimm-bounces-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org Sender: "Linux-nvdimm" List-Id: linux-ext4.vger.kernel.org Changes since v5 [1]: * Split the introduction of dax-specific address_space_operations into its own patch, and place them in fs/libfs.c (Christoph) * Kill some more straggling dead code implementing dax support for block devices. * Mark devm_memremap_pages EXPORT_SYMBOL_GPL (Christoph) * Introduce {xfs,ext4,ext2}_dax_writepages() and kill the dynamic check for IS_DAX() in the typical _writepages() implementations in these filesystems. (Christoph) * Rework xfs_break_layouts() to assume the XFS_MMAPLOCK_EXCL is held at entry. (Christoph) * Replace the XFS_BREAK_WRITE and XFS_BREAK_MAPS flags with the BREAK_WRITE and BREAK_TRUNCATE enum values since BREAK_WRITE is a subset of BREAK_TRUNCATE. (Christoph) * Replace wait_for_atomic_one() with Peter's new wait_var_event() facility [2]. (Peter) [1]: https://lists.01.org/pipermail/linux-nvdimm/2018-March/014585.html [2]: https://patchwork.kernel.org/patch/10284383/ --- Background: get_user_pages() in the filesystem pins file backed memory pages for access by devices performing dma. However, it only pins the memory pages not the page-to-file offset association. If a file is truncated the pages are mapped out of the file and dma may continue indefinitely into a page that is owned by a device driver. This breaks coherency of the file vs dma, but the assumption is that if userspace wants the file-space truncated it does not matter what data is inbound from the device, it is not relevant anymore. The only expectation is that dma can safely continue while the filesystem reallocates the block(s). Problem: This expectation that dma can safely continue while the filesystem changes the block map is broken by dax. With dax the target dma page *is* the filesystem block. The model of leaving the page pinned for dma, but truncating the file block out of the file, means that the filesytem is free to reallocate a block under active dma to another file and now the expected data-incoherency situation has turned into active data-corruption. Solution: Defer all filesystem operations (fallocate(), truncate()) on a dax mode file while any page/block in the file is under active dma. This solution assumes that dma is transient. Cases where dma operations are known to not be transient, like RDMA, have been explicitly disabled via commits like 5f1d43de5416 "IB/core: disable memory registration of filesystem-dax vmas". The dax_layout_busy_page() routine is called by filesystems with a lock held against mm faults (i_mmap_lock) to find pinned / busy dax pages. The process of looking up a busy page invalidates all mappings to trigger any subsequent get_user_pages() to block on i_mmap_lock. The filesystem continues to call dax_layout_busy_page() until it finally returns no more active pages. This approach assumes that the page pinning is transient, if that assumption is violated the system would have likely hung from the uncompleted I/O. --- Dan Williams (15): dax: store pfns in the radix fs, dax: prepare for dax-specific address_space_operations block, dax: remove dead code in blkdev_writepages() xfs, dax: introduce xfs_dax_aops ext4, dax: introduce ext4_dax_aops ext2, dax: introduce ext2_dax_aops fs, dax: use page->mapping to warn if truncate collides with a busy page mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks mm, dev_pagemap: introduce CONFIG_DEV_PAGEMAP_OPS memremap: mark devm_memremap_pages() EXPORT_SYMBOL_GPL mm, fs, dax: handle layout changes to pinned dax mappings xfs: require mmap lock for xfs_break_layouts() xfs: communicate lock drop events from xfs_break_layouts() xfs: prepare xfs_break_layouts() for another layout type xfs, dax: introduce xfs_break_dax_layouts() drivers/dax/super.c | 96 ++++++++++++++++--- drivers/nvdimm/pmem.c | 3 - fs/Kconfig | 1 fs/block_dev.c | 5 - fs/dax.c | 232 ++++++++++++++++++++++++++++++++++++---------- fs/ext2/ext2.h | 1 fs/ext2/inode.c | 43 +++++---- fs/ext2/namei.c | 18 ---- fs/ext2/super.c | 6 + fs/ext4/inode.c | 38 ++++++-- fs/ext4/super.c | 6 + fs/libfs.c | 27 +++++ fs/xfs/xfs_aops.c | 21 +++- fs/xfs/xfs_aops.h | 1 fs/xfs/xfs_file.c | 87 ++++++++++++++++- fs/xfs/xfs_inode.h | 16 +++ fs/xfs/xfs_ioctl.c | 8 -- fs/xfs/xfs_iops.c | 21 +++- fs/xfs/xfs_pnfs.c | 17 ++- fs/xfs/xfs_pnfs.h | 4 - fs/xfs/xfs_super.c | 20 ++-- include/linux/dax.h | 51 +++++++++- include/linux/fs.h | 3 + include/linux/memremap.h | 28 ++---- include/linux/mm.h | 61 +++++++++--- kernel/memremap.c | 32 +++++- mm/Kconfig | 5 + mm/gup.c | 5 + mm/hmm.c | 13 --- mm/swap.c | 3 - 30 files changed, 653 insertions(+), 219 deletions(-)