From: "Darrick J. Wong" <djwong@kernel.org>
To: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Cc: linux-kernel@vger.kernel.org, linux-xfs@vger.kernel.org,
linux-nvdimm@lists.01.org, linux-fsdevel@vger.kernel.org,
darrick.wong@oracle.com, dan.j.williams@intel.com,
willy@infradead.org, jack@suse.cz, viro@zeniv.linux.org.uk,
linux-btrfs@vger.kernel.org, david@fromorbit.com, hch@lst.de,
rgoldwyn@suse.de, Goldwyn Rodrigues <rgoldwyn@suse.com>,
Ritesh Harjani <riteshh@linux.ibm.com>
Subject: Re: [PATCH v4 2/7] fsdax: Replace mmap entry in case of CoW
Date: Thu, 8 Apr 2021 15:11:31 -0700 [thread overview]
Message-ID: <20210408221131.GZ3957620@magnolia> (raw)
In-Reply-To: <20210408120432.1063608-3-ruansy.fnst@fujitsu.com>
On Thu, Apr 08, 2021 at 08:04:27PM +0800, Shiyang Ruan wrote:
> We replace the existing entry to the newly allocated one in case of CoW.
> Also, we mark the entry as PAGECACHE_TAG_TOWRITE so writeback marks this
> entry as writeprotected. This helps us snapshots so new write
> pagefaults after snapshots trigger a CoW.
>
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
> ---
> fs/dax.c | 39 ++++++++++++++++++++++++++++-----------
> 1 file changed, 28 insertions(+), 11 deletions(-)
>
> diff --git a/fs/dax.c b/fs/dax.c
> index b4fd3813457a..e6c1354b27a8 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -722,6 +722,10 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d
> return 0;
> }
>
> +/* DAX Insert Flag for the entry we insert */
Might be worth mentioning that these are xarray marks for the inserted
entry, since this comment didn't help much.
> +#define DAX_IF_DIRTY (1 << 0)
> +#define DAX_IF_COW (1 << 1)
> +
> /*
> * By this point grab_mapping_entry() has ensured that we have a locked entry
> * of the appropriate size so we don't have to worry about downgrading PMDs to
> @@ -729,16 +733,19 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d
> * already in the tree, we will skip the insertion and just dirty the PMD as
> * appropriate.
> */
> -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)
> +static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf,
> + void *entry, pfn_t pfn, unsigned long flags,
> + unsigned int insert_flags)
Urk, two flags arguments. Oh, I see. We insert (shifted) pfn_t values
into the mapping as xarray values, so @flags determines the state flags
of the new entry value, whereas @insert_flags determines what xarray
mark we're going to attach (if any) to the inserted value.
--D
> {
> + struct address_space *mapping = vmf->vma->vm_file->f_mapping;
> void *new_entry = dax_make_entry(pfn, flags);
> + bool dirty = insert_flags & DAX_IF_DIRTY;
> + bool cow = insert_flags & DAX_IF_COW;
>
> 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))
> @@ -750,7 +757,7 @@ static void *dax_insert_entry(struct xa_state *xas,
>
> xas_reset(xas);
> xas_lock_irq(xas);
> - if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
> + if (cow || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
> void *old;
>
> dax_disassociate_entry(entry, mapping, false);
> @@ -774,6 +781,9 @@ static void *dax_insert_entry(struct xa_state *xas,
> if (dirty)
> xas_set_mark(xas, PAGECACHE_TAG_DIRTY);
>
> + if (cow)
> + xas_set_mark(xas, PAGECACHE_TAG_TOWRITE);
> +
> xas_unlock_irq(xas);
> return entry;
> }
> @@ -1109,8 +1119,7 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
> pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
> vm_fault_t ret;
>
> - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
> - DAX_ZERO_PAGE, false);
> + *entry = dax_insert_entry(xas, vmf, *entry, pfn, DAX_ZERO_PAGE, 0);
>
> ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
> trace_dax_load_hole(inode, vmf, ret);
> @@ -1137,8 +1146,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
> goto fallback;
>
> pfn = page_to_pfn_t(zero_page);
> - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
> - DAX_PMD | DAX_ZERO_PAGE, false);
> + *entry = dax_insert_entry(xas, vmf, *entry, pfn,
> + DAX_PMD | DAX_ZERO_PAGE, 0);
>
> if (arch_needs_pgtable_deposit()) {
> pgtable = pte_alloc_one(vma->vm_mm);
> @@ -1444,6 +1453,7 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
> bool write = vmf->flags & FAULT_FLAG_WRITE;
> bool sync = dax_fault_is_synchronous(flags, vmf->vma, iomap);
> unsigned long entry_flags = pmd ? DAX_PMD : 0;
> + unsigned int insert_flags = 0;
> int err = 0;
> pfn_t pfn;
> void *kaddr;
> @@ -1466,8 +1476,15 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
> if (err)
> return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err);
>
> - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, entry_flags,
> - write && !sync);
> + if (write) {
> + if (!sync)
> + insert_flags |= DAX_IF_DIRTY;
> + if (iomap->flags & IOMAP_F_SHARED)
> + insert_flags |= DAX_IF_COW;
> + }
> +
> + *entry = dax_insert_entry(xas, vmf, *entry, pfn, entry_flags,
> + insert_flags);
>
> if (write &&
> srcmap->addr != IOMAP_HOLE && srcmap->addr != iomap->addr) {
> --
> 2.31.0
>
>
>
next prev parent reply other threads:[~2021-04-08 22:11 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-08 12:04 [PATCH v4 0/7] fsdax,xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-04-08 12:04 ` [PATCH v4 1/7] fsdax: Introduce dax_iomap_cow_copy() Shiyang Ruan
2021-04-08 21:53 ` Darrick J. Wong
2021-04-09 2:30 ` ruansy.fnst
2021-04-08 12:04 ` [PATCH v4 2/7] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-04-08 22:11 ` Darrick J. Wong [this message]
2021-04-08 12:04 ` [PATCH v4 3/7] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Shiyang Ruan
2021-04-08 12:04 ` [PATCH v4 4/7] iomap: Introduce iomap_apply2() for operations on two files Shiyang Ruan
2021-04-08 22:26 ` Darrick J. Wong
2021-04-08 12:04 ` [PATCH v4 5/7] fsdax: Dedup file range to use a compare function Shiyang Ruan
2021-04-08 22:33 ` Darrick J. Wong
2021-04-08 12:04 ` [PATCH v4 6/7] fs/xfs: Handle CoW for fsdax write() path Shiyang Ruan
2021-04-08 22:40 ` Darrick J. Wong
2021-04-08 12:04 ` [PATCH v4 7/7] fs/xfs: Add dedupe support for fsdax Shiyang Ruan
2021-04-08 13:12 ` Su Yue
2021-04-09 1:56 ` ruansy.fnst
2021-04-08 23:04 ` Darrick J. Wong
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=20210408221131.GZ3957620@magnolia \
--to=djwong@kernel.org \
--cc=dan.j.williams@intel.com \
--cc=darrick.wong@oracle.com \
--cc=david@fromorbit.com \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=linux-xfs@vger.kernel.org \
--cc=rgoldwyn@suse.com \
--cc=rgoldwyn@suse.de \
--cc=riteshh@linux.ibm.com \
--cc=ruansy.fnst@fujitsu.com \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/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).