From: Christoph Hellwig <hch@lst.de>
To: "Darrick J. Wong" <djwong@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>,
Matthew Wilcox <willy@infradead.org>,
Andreas Gruenbacher <agruenba@redhat.com>,
Shiyang Ruan <ruansy.fnst@fujitsu.com>,
linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-btrfs@vger.kernel.org, nvdimm@lists.linux.dev,
cluster-devel@redhat.com, Ritesh Harjani <riteshh@linux.ibm.com>
Subject: [PATCH 24/27] fsdax: factor out helpers to simplify the dax fault code
Date: Mon, 19 Jul 2021 12:35:17 +0200 [thread overview]
Message-ID: <20210719103520.495450-25-hch@lst.de> (raw)
In-Reply-To: <20210719103520.495450-1-hch@lst.de>
From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
The dax page fault code is too long and a bit difficult to read. And it
is hard to understand when we trying to add new features. Some of the
PTE/PMD codes have similar logic. So, factor out helper functions to
simplify the code.
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
[hch: minor cleanups]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/dax.c | 153 ++++++++++++++++++++++++++++++-------------------------
1 file changed, 84 insertions(+), 69 deletions(-)
diff --git a/fs/dax.c b/fs/dax.c
index 51da45301350a6..c09d721629d167 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1255,6 +1255,53 @@ static bool dax_fault_is_synchronous(unsigned long flags,
&& (iomap->flags & IOMAP_F_DIRTY);
}
+/*
+ * When handling a synchronous page fault and the inode need a fsync, we can
+ * insert the PTE/PMD into page tables only after that fsync happened. Skip
+ * insertion for now and return the pfn so that caller can insert it after the
+ * fsync is done.
+ */
+static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
+{
+ if (WARN_ON_ONCE(!pfnp))
+ return VM_FAULT_SIGBUS;
+ *pfnp = pfn;
+ return VM_FAULT_NEEDDSYNC;
+}
+
+static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf, struct iomap *iomap,
+ loff_t pos)
+{
+ sector_t sector = dax_iomap_sector(iomap, pos);
+ unsigned long vaddr = vmf->address;
+ vm_fault_t ret;
+ int error = 0;
+
+ switch (iomap->type) {
+ case IOMAP_HOLE:
+ case IOMAP_UNWRITTEN:
+ clear_user_highpage(vmf->cow_page, vaddr);
+ break;
+ case IOMAP_MAPPED:
+ error = copy_cow_page_dax(iomap->bdev, iomap->dax_dev, sector,
+ vmf->cow_page, vaddr);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ error = -EIO;
+ break;
+ }
+
+ if (error)
+ return dax_fault_return(error);
+
+ __SetPageUptodate(vmf->cow_page);
+ ret = finish_fault(vmf);
+ if (!ret)
+ return VM_FAULT_DONE_COW;
+ return ret;
+}
+
static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
int *iomap_errp, const struct iomap_ops *ops)
{
@@ -1323,30 +1370,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
}
if (vmf->cow_page) {
- sector_t sector = dax_iomap_sector(&iomap, pos);
-
- switch (iomap.type) {
- case IOMAP_HOLE:
- case IOMAP_UNWRITTEN:
- clear_user_highpage(vmf->cow_page, vaddr);
- break;
- case IOMAP_MAPPED:
- error = copy_cow_page_dax(iomap.bdev, iomap.dax_dev,
- sector, vmf->cow_page, vaddr);
- break;
- default:
- WARN_ON_ONCE(1);
- error = -EIO;
- break;
- }
-
- if (error)
- goto error_finish_iomap;
-
- __SetPageUptodate(vmf->cow_page);
- ret = finish_fault(vmf);
- if (!ret)
- ret = VM_FAULT_DONE_COW;
+ ret = dax_fault_cow_page(vmf, &iomap, pos);
goto finish_iomap;
}
@@ -1366,19 +1390,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
0, write && !sync);
- /*
- * If we are doing synchronous page fault and inode needs fsync,
- * we can insert PTE into page tables only after that happens.
- * Skip insertion for now and return the pfn so that caller can
- * insert it after fsync is done.
- */
if (sync) {
- if (WARN_ON_ONCE(!pfnp)) {
- error = -EIO;
- goto error_finish_iomap;
- }
- *pfnp = pfn;
- ret = VM_FAULT_NEEDDSYNC | major;
+ ret = dax_fault_synchronous_pfnp(pfnp, pfn);
goto finish_iomap;
}
trace_dax_insert_mapping(inode, vmf, entry);
@@ -1477,13 +1490,45 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
return VM_FAULT_FALLBACK;
}
+static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state *xas,
+ pgoff_t max_pgoff)
+{
+ unsigned long pmd_addr = vmf->address & PMD_MASK;
+ bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+ /*
+ * Make sure that the faulting address's PMD offset (color) matches
+ * the PMD offset from the start of the file. This is necessary so
+ * that a PMD range in the page table overlaps exactly with a PMD
+ * range in the page cache.
+ */
+ if ((vmf->pgoff & PG_PMD_COLOUR) !=
+ ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
+ return true;
+
+ /* Fall back to PTEs if we're going to COW */
+ if (write && !(vmf->vma->vm_flags & VM_SHARED))
+ return true;
+
+ /* If the PMD would extend outside the VMA */
+ if (pmd_addr < vmf->vma->vm_start)
+ return true;
+ if ((pmd_addr + PMD_SIZE) > vmf->vma->vm_end)
+ return true;
+
+ /* If the PMD would extend beyond the file size */
+ if ((xas->xa_index | PG_PMD_COLOUR) >= max_pgoff)
+ return true;
+
+ return false;
+}
+
static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
const struct iomap_ops *ops)
{
struct vm_area_struct *vma = vmf->vma;
struct address_space *mapping = vma->vm_file->f_mapping;
XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER);
- unsigned long pmd_addr = vmf->address & PMD_MASK;
bool write = vmf->flags & FAULT_FLAG_WRITE;
bool sync;
unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
@@ -1506,33 +1551,12 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
- /*
- * Make sure that the faulting address's PMD offset (color) matches
- * the PMD offset from the start of the file. This is necessary so
- * that a PMD range in the page table overlaps exactly with a PMD
- * range in the page cache.
- */
- if ((vmf->pgoff & PG_PMD_COLOUR) !=
- ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
- goto fallback;
-
- /* Fall back to PTEs if we're going to COW */
- if (write && !(vma->vm_flags & VM_SHARED))
- goto fallback;
-
- /* If the PMD would extend outside the VMA */
- if (pmd_addr < vma->vm_start)
- goto fallback;
- if ((pmd_addr + PMD_SIZE) > vma->vm_end)
- goto fallback;
-
if (xas.xa_index >= max_pgoff) {
result = VM_FAULT_SIGBUS;
goto out;
}
- /* If the PMD would extend beyond the file size */
- if ((xas.xa_index | PG_PMD_COLOUR) >= max_pgoff)
+ if (dax_fault_check_fallback(vmf, &xas, max_pgoff))
goto fallback;
/*
@@ -1584,17 +1608,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
DAX_PMD, write && !sync);
- /*
- * If we are doing synchronous page fault and inode needs fsync,
- * we can insert PMD into page tables only after that happens.
- * Skip insertion for now and return the pfn so that caller can
- * insert it after fsync is done.
- */
if (sync) {
- if (WARN_ON_ONCE(!pfnp))
- goto finish_iomap;
- *pfnp = pfn;
- result = VM_FAULT_NEEDDSYNC;
+ result = dax_fault_synchronous_pfnp(pfnp, pfn);
goto finish_iomap;
}
--
2.30.2
next prev parent reply other threads:[~2021-07-19 11:04 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-19 10:34 RFC: switch iomap to an iterator model Christoph Hellwig
2021-07-19 10:34 ` [PATCH 01/27] iomap: fix a trivial comment typo in trace.h Christoph Hellwig
2021-07-19 16:00 ` Darrick J. Wong
2021-07-19 10:34 ` [PATCH 02/27] iomap: remove the iomap arguments to ->page_{prepare,done} Christoph Hellwig
2021-07-19 16:04 ` Darrick J. Wong
2021-07-19 10:34 ` [PATCH 03/27] iomap: mark the iomap argument to iomap_sector const Christoph Hellwig
2021-07-19 16:08 ` Darrick J. Wong
2021-07-20 9:52 ` Nikolay Borisov
2021-07-26 8:12 ` Christoph Hellwig
2021-07-19 10:34 ` [PATCH 04/27] fs: mark the iomap argument to __block_write_begin_int const Christoph Hellwig
2021-07-19 17:35 ` Darrick J. Wong
2021-07-19 10:34 ` [PATCH 05/27] fsdax: mark the iomap argument to dax_iomap_sector as const Christoph Hellwig
2021-07-19 17:35 ` Darrick J. Wong
2021-07-19 10:34 ` [PATCH 06/27] iomap: mark the iomap argument to iomap_read_inline_data const Christoph Hellwig
2021-07-19 17:35 ` Darrick J. Wong
2021-07-19 10:35 ` [PATCH 07/27] iomap: mark the iomap argument to iomap_read_page_sync const Christoph Hellwig
2021-07-19 17:35 ` Darrick J. Wong
2021-07-19 10:35 ` [PATCH 08/27] iomap: add the new iomap_iter model Christoph Hellwig
2021-07-19 16:56 ` Darrick J. Wong
2021-07-26 8:15 ` Christoph Hellwig
2021-07-19 21:48 ` Dave Chinner
2021-07-26 8:17 ` Christoph Hellwig
2021-07-19 10:35 ` [PATCH 09/27] iomap: switch readahead and readpage to use iomap_iter Christoph Hellwig
2021-07-19 10:35 ` [PATCH 10/27] iomap: switch iomap_file_buffered_write " Christoph Hellwig
2021-07-19 10:35 ` [PATCH 11/27] iomap: switch iomap_file_unshare " Christoph Hellwig
2021-07-19 10:35 ` [PATCH 12/27] iomap: switch iomap_zero_range " Christoph Hellwig
2021-07-19 10:35 ` [PATCH 13/27] iomap: switch iomap_page_mkwrite " Christoph Hellwig
2021-07-19 10:35 ` [PATCH 14/27] iomap: switch __iomap_dio_rw " Christoph Hellwig
2021-07-19 10:35 ` [PATCH 15/27] iomap: switch iomap_fiemap " Christoph Hellwig
2021-07-19 10:35 ` [PATCH 16/27] iomap: switch iomap_bmap " Christoph Hellwig
2021-07-19 17:05 ` Darrick J. Wong
2021-07-26 8:19 ` Christoph Hellwig
2021-07-26 16:39 ` Darrick J. Wong
2021-07-27 6:31 ` Christoph Hellwig
2021-07-27 14:32 ` Darrick J. Wong
2021-07-19 10:35 ` [PATCH 17/27] iomap: switch iomap_seek_hole " Christoph Hellwig
2021-07-19 17:22 ` Darrick J. Wong
2021-07-26 8:22 ` Christoph Hellwig
2021-07-26 16:41 ` Darrick J. Wong
2021-07-19 10:35 ` [PATCH 18/27] iomap: switch iomap_seek_data " Christoph Hellwig
2021-07-19 10:35 ` [PATCH 19/27] iomap: switch iomap_swapfile_activate " Christoph Hellwig
2021-07-19 10:35 ` [PATCH 20/27] fsdax: switch dax_iomap_rw " Christoph Hellwig
2021-07-19 22:10 ` Dave Chinner
2021-07-26 8:25 ` Christoph Hellwig
2021-07-19 10:35 ` [PATCH 21/27] iomap: remove iomap_apply Christoph Hellwig
2021-07-19 17:48 ` Darrick J. Wong
2021-07-19 10:35 ` [PATCH 22/27] iomap: pass an iomap_iter to various buffered I/O helpers Christoph Hellwig
2021-07-19 17:48 ` Darrick J. Wong
2021-07-19 10:35 ` [PATCH 23/27] iomap: rework unshare flag Christoph Hellwig
2021-07-19 17:44 ` Darrick J. Wong
2021-07-19 10:35 ` Christoph Hellwig [this message]
2021-07-19 10:35 ` [PATCH 25/27] fsdax: factor out a dax_fault_actor() helper Christoph Hellwig
2021-07-19 10:35 ` [PATCH 26/27] fsdax: switch the fault handlers to use iomap_iter Christoph Hellwig
2021-07-19 17:35 ` Darrick J. Wong
2021-07-19 10:35 ` [PATCH 27/27] iomap: constify iomap_iter_srcmap Christoph Hellwig
2021-07-19 17:44 ` Darrick J. Wong
2021-07-19 17:57 ` RFC: switch iomap to an iterator model Darrick J. Wong
2021-07-27 8:07 ` DAX setup pains, was " Christoph Hellwig
2021-07-29 20:33 ` 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=20210719103520.495450-25-hch@lst.de \
--to=hch@lst.de \
--cc=agruenba@redhat.com \
--cc=cluster-devel@redhat.com \
--cc=dan.j.williams@intel.com \
--cc=djwong@kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=nvdimm@lists.linux.dev \
--cc=riteshh@linux.ibm.com \
--cc=ruansy.fnst@fujitsu.com \
--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).