From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
To: <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
<linux-nvdimm@lists.01.org>, <linux-fsdevel@vger.kernel.org>
Cc: <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>, <ocfs2-devel@oss.oracle.com>,
<david@fromorbit.com>, <hch@lst.de>, <rgoldwyn@suse.de>
Subject: [PATCH v3 01/10] fsdax: Factor helpers to simplify dax fault code
Date: Fri, 19 Mar 2021 09:52:28 +0800 [thread overview]
Message-ID: <20210319015237.993880-2-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20210319015237.993880-1-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 them as helper functions to
simplify the code.
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/dax.c | 152 ++++++++++++++++++++++++++++++-------------------------
1 file changed, 84 insertions(+), 68 deletions(-)
diff --git a/fs/dax.c b/fs/dax.c
index 26d5dcd2d69e..7031e4302b13 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1243,6 +1243,52 @@ static bool dax_fault_is_synchronous(unsigned long flags,
&& (iomap->flags & IOMAP_F_DIRTY);
}
+/*
+ * If we are doing synchronous page fault and inode needs fsync, we can insert
+ * PTE/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.
+ */
+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 int dax_fault_cow_page(struct vm_fault *vmf, struct iomap *iomap,
+ loff_t pos, vm_fault_t *ret)
+{
+ int error = 0;
+ unsigned long vaddr = vmf->address;
+ 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)
+ return error;
+
+ __SetPageUptodate(vmf->cow_page);
+ *ret = finish_fault(vmf);
+ if (!*ret)
+ *ret = VM_FAULT_DONE_COW;
+ return 0;
+}
+
static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
int *iomap_errp, const struct iomap_ops *ops)
{
@@ -1311,30 +1357,9 @@ 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;
- }
-
+ error = dax_fault_cow_page(vmf, &iomap, pos, &ret);
if (error)
- goto error_finish_iomap;
-
- __SetPageUptodate(vmf->cow_page);
- ret = finish_fault(vmf);
- if (!ret)
- ret = VM_FAULT_DONE_COW;
+ ret = dax_fault_return(error);
goto finish_iomap;
}
@@ -1354,19 +1379,8 @@ 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);
@@ -1465,13 +1479,45 @@ 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;
@@ -1494,33 +1540,12 @@ 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;
/*
@@ -1572,17 +1597,8 @@ 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;
}
--
2.30.1
next prev parent reply other threads:[~2021-03-19 1:53 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-19 1:52 [PATCH v3 00/10] fsdax,xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-03-19 1:52 ` Shiyang Ruan [this message]
2021-03-23 15:33 ` [PATCH v3 01/10] fsdax: Factor helpers to simplify dax fault code Ritesh Harjani
2021-03-19 1:52 ` [PATCH v3 02/10] fsdax: Factor helper: dax_fault_actor() Shiyang Ruan
2021-03-23 15:48 ` Ritesh Harjani
2021-03-31 3:57 ` ruansy.fnst
2021-04-02 7:47 ` Christoph Hellwig
2021-03-19 1:52 ` [PATCH v3 03/10] fsdax: Output address in dax_iomap_pfn() and rename it Shiyang Ruan
2021-03-23 15:54 ` Ritesh Harjani
2021-03-19 1:52 ` [PATCH v3 04/10] fsdax: Introduce dax_iomap_cow_copy() Shiyang Ruan
2021-03-23 16:08 ` Ritesh Harjani
2021-03-19 1:52 ` [PATCH v3 05/10] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-04-01 6:39 ` Ritesh Harjani
2021-04-01 7:03 ` ruansy.fnst
2021-03-19 1:52 ` [PATCH v3 06/10] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Shiyang Ruan
2021-04-01 6:45 ` Ritesh Harjani
2021-04-01 7:00 ` ruansy.fnst
2021-03-19 1:52 ` [PATCH v3 07/10] iomap: Introduce iomap_apply2() for operations on two files Shiyang Ruan
2021-04-01 7:12 ` Ritesh Harjani
2021-03-19 1:52 ` [PATCH v3 08/10] fsdax: Dedup file range to use a compare function Shiyang Ruan
2021-04-01 11:11 ` Ritesh Harjani
2021-04-08 3:21 ` ruansy.fnst
2021-03-19 1:52 ` [PATCH v3 09/10] fs/xfs: Handle CoW for fsdax write() path Shiyang Ruan
2021-03-19 1:52 ` [PATCH v3 10/10] fs/xfs: Add dedupe support for fsdax Shiyang Ruan
2021-03-23 15:27 ` [PATCH v3 00/10] fsdax,xfs: Add reflink&dedupe " Ritesh Harjani
2021-04-02 7:49 ` Christoph Hellwig
2021-04-02 8:18 ` ruansy.fnst
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=20210319015237.993880-2-ruansy.fnst@fujitsu.com \
--to=ruansy.fnst@fujitsu.com \
--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=ocfs2-devel@oss.oracle.com \
--cc=rgoldwyn@suse.de \
--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).