From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: linux-btrfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: Re: [PATCH 09/15] btrfs: add dax mmap support
Date: Thu, 28 Mar 2019 08:45:39 -0700 [thread overview]
Message-ID: <20190328154539.GF1172@magnolia> (raw)
In-Reply-To: <20190326190301.32365-10-rgoldwyn@suse.de>
On Tue, Mar 26, 2019 at 02:02:55PM -0500, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
>
> Add a new vm_operations struct btrfs_dax_vm_ops
> specifically for dax files.
>
> Since we will be removing(nulling) readpages/writepages for dax
> return ENOEXEC only for non-dax files.
>
> dax_insert_entry() looks ugly. Do you think we should break it
> into dax_insert_cow_entry() and dax_insert_entry()?
I would (or replace the two bools with flags), but people seem not to
like my stylistic choices. :)
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
> fs/btrfs/ctree.h | 1 +
> fs/btrfs/dax.c | 11 +++++++++++
> fs/btrfs/file.c | 18 ++++++++++++++++--
> fs/dax.c | 17 ++++++++++-------
> 4 files changed, 38 insertions(+), 9 deletions(-)
>
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index 3bcd2a4959c1..0e5060933bde 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -3802,6 +3802,7 @@ int btree_readahead_hook(struct extent_buffer *eb, int err);
> /* dax.c */
> ssize_t btrfs_file_dax_read(struct kiocb *iocb, struct iov_iter *to);
> ssize_t btrfs_file_dax_write(struct kiocb *iocb, struct iov_iter *from);
> +vm_fault_t btrfs_dax_fault(struct vm_fault *vmf);
> #else
> static inline ssize_t btrfs_file_dax_write(struct kiocb *iocb, struct iov_iter *from)
> {
> diff --git a/fs/btrfs/dax.c b/fs/btrfs/dax.c
> index 49619fe3f94f..927f962d1e88 100644
> --- a/fs/btrfs/dax.c
> +++ b/fs/btrfs/dax.c
> @@ -157,4 +157,15 @@ ssize_t btrfs_file_dax_write(struct kiocb *iocb, struct iov_iter *iter)
> }
> return ret;
> }
> +
> +vm_fault_t btrfs_dax_fault(struct vm_fault *vmf)
> +{
> + vm_fault_t ret;
> + pfn_t pfn;
> + ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &pfn, NULL, &btrfs_iomap_ops);
> + if (ret & VM_FAULT_NEEDDSYNC)
> + ret = dax_finish_sync_fault(vmf, PE_SIZE_PTE, pfn);
> +
> + return ret;
> +}
> #endif /* CONFIG_FS_DAX */
> diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
> index 3b320d0ab495..196c8f37ff9d 100644
> --- a/fs/btrfs/file.c
> +++ b/fs/btrfs/file.c
> @@ -2214,15 +2214,29 @@ static const struct vm_operations_struct btrfs_file_vm_ops = {
> .page_mkwrite = btrfs_page_mkwrite,
> };
>
> +#ifdef CONFIG_FS_DAX
> +static const struct vm_operations_struct btrfs_dax_vm_ops = {
> + .fault = btrfs_dax_fault,
> + .page_mkwrite = btrfs_dax_fault,
> + .pfn_mkwrite = btrfs_dax_fault,
> +};
> +#else
> +#define btrfs_dax_vm_ops btrfs_file_vm_ops
> +#endif
> +
> static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma)
> {
> struct address_space *mapping = filp->f_mapping;
> + struct inode *inode = file_inode(filp);
>
> - if (!mapping->a_ops->readpage)
> + if (!IS_DAX(inode) && !mapping->a_ops->readpage)
> return -ENOEXEC;
>
> file_accessed(filp);
> - vma->vm_ops = &btrfs_file_vm_ops;
> + if (IS_DAX(inode))
> + vma->vm_ops = &btrfs_dax_vm_ops;
> + else
> + vma->vm_ops = &btrfs_file_vm_ops;
>
> return 0;
> }
> diff --git a/fs/dax.c b/fs/dax.c
> index 21ee3df6f02c..41061da42771 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
Whoah, waitaminute, I thought this was a "twiddle stuff inside btrfs
only" patch...
> @@ -708,14 +708,15 @@ static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
> */
> static void *dax_insert_entry(struct xa_state *xas,
> struct address_space *mapping, struct vm_fault *vmf,
> - void *entry, pfn_t pfn, unsigned long flags, bool dirty)
> + void *entry, pfn_t pfn, unsigned long flags, bool dirty,
> + bool cow)
> {
> void *new_entry = dax_make_entry(pfn, flags);
>
> if (dirty)
> __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
>
> - if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
> + if (cow || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) {
> unsigned long index = xas->xa_index;
> /* we are replacing a zero page with block mapping */
> if (dax_is_pmd_entry(entry))
> @@ -732,7 +733,7 @@ static void *dax_insert_entry(struct xa_state *xas,
> dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address);
> }
>
> - if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
> + if (cow || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
> /*
> * Only swap our new entry into the page cache if the current
> * entry is a zero page or an empty entry. If a normal PTE or
> @@ -1031,7 +1032,7 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
> vm_fault_t ret;
>
> *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
> - DAX_ZERO_PAGE, false);
> + DAX_ZERO_PAGE, false, false);
>
> ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
> trace_dax_load_hole(inode, vmf, ret);
> @@ -1408,7 +1409,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
> goto error_finish_iomap;
>
> entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
> - 0, write && !sync);
> + 0, write && !sync,
> + (iomap.flags & IOMAP_F_COW) != 0);
Assuming you stick with bool cow, you don't need the != 0 test.
>
> /*
> * If we are doing synchronous page fault and inode needs fsync,
> @@ -1487,7 +1489,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
>
> pfn = page_to_pfn_t(zero_page);
> *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
> - DAX_PMD | DAX_ZERO_PAGE, false);
> + DAX_PMD | DAX_ZERO_PAGE, false, false);
>
> ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
> if (!pmd_none(*(vmf->pmd))) {
> @@ -1610,7 +1612,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
> goto finish_iomap;
>
> entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
> - DAX_PMD, write && !sync);
> + DAX_PMD, write && !sync,
> + false);
Why don't PMD faults support COW?
--D
>
> /*
> * If we are doing synchronous page fault and inode needs fsync,
> --
> 2.16.4
>
next prev parent reply other threads:[~2019-03-28 15:46 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20190326190301.32365-1-rgoldwyn@suse.de>
2019-03-26 19:02 ` [PATCH 01/15] btrfs: create a mount option for dax Goldwyn Rodrigues
2019-03-26 19:10 ` Matthew Wilcox
2019-03-27 11:00 ` Goldwyn Rodrigues
2019-03-27 12:00 ` Matthew Wilcox
2019-03-27 12:26 ` Goldwyn Rodrigues
2019-03-27 23:31 ` Goldwyn Rodrigues
2019-03-27 17:38 ` Adam Borowski
2019-03-28 14:49 ` David Sterba
2019-03-28 17:28 ` David Sterba
2019-03-28 17:57 ` Darrick J. Wong
2019-04-01 20:43 ` Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 02/15] btrfs: Carve out btrfs_get_extent_map_write() out of btrfs_get_blocks_write() Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 03/15] btrfs: basic dax read Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 04/15] dax: Introduce IOMAP_F_COW for copy-on-write Goldwyn Rodrigues
2019-03-27 17:54 ` Darrick J. Wong
2019-03-27 18:58 ` Goldwyn Rodrigues
2019-03-28 14:45 ` Darrick J. Wong
2019-04-01 4:38 ` Dave Chinner
2019-04-01 21:41 ` Goldwyn Rodrigues
2019-04-01 23:06 ` Dave Chinner
2019-04-03 1:56 ` Goldwyn Rodrigues
2019-04-03 3:20 ` Dave Chinner
2019-04-07 7:26 ` Christoph Hellwig
2019-03-26 19:02 ` [PATCH 05/15] btrfs: return whether extent is nocow or not Goldwyn Rodrigues
2019-03-31 18:42 ` Nikolay Borisov
2019-03-26 19:02 ` [PATCH 06/15] btrfs: Rename __endio_write_update_ordered() to btrfs_update_ordered_extent() Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 07/15] btrfs: add dax write support Goldwyn Rodrigues
2019-03-28 14:53 ` Darrick J. Wong
2019-04-01 20:39 ` Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 08/15] dax: add dax_iomap_cow to copy a mmap page before writing Goldwyn Rodrigues
2019-03-28 15:41 ` Darrick J. Wong
2019-03-26 19:02 ` [PATCH 09/15] btrfs: add dax mmap support Goldwyn Rodrigues
2019-03-28 15:45 ` Darrick J. Wong [this message]
2019-03-26 19:02 ` [PATCH 10/15] btrfs: Add dax specific address_space_operations Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 11/15] fs: dedup file range to use a compare function Goldwyn Rodrigues
2019-03-28 17:04 ` Darrick J. Wong
2019-04-01 20:36 ` Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 12/15] btrfs: trace functions for btrfs_iomap_begin/end Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 13/15] btrfs: handle dax page zeroing Goldwyn Rodrigues
2019-03-26 19:03 ` [PATCH 14/15] btrfs: Disable dax-based defrag and send Goldwyn Rodrigues
2019-03-26 19:03 ` [PATCH 15/15] btrfs: Writeprotect mmap pages on snapshot Goldwyn Rodrigues
2019-03-28 15:48 ` Darrick J. Wong
2019-03-26 19:09 ` [PATCH v2 00/15] btrfs dax support Goldwyn Rodrigues
2019-03-27 20:14 ` Adam Borowski
2019-03-27 23:26 ` Goldwyn Rodrigues
2019-03-28 10:24 ` [PATCH] btrfs: allow MAP_SYNC mmap Adam Borowski
2019-03-28 10:42 ` Adam Borowski
2019-04-01 20:08 ` Goldwyn Rodrigues
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190328154539.GF1172@magnolia \
--to=darrick.wong@oracle.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=rgoldwyn@suse.com \
--cc=rgoldwyn@suse.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).