ocfs2-devel.oss.oracle.com archive mirror
 help / color / mirror / Atom feed
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: jack@suse.cz, darrick.wong@oracle.com, david@fromorbit.com,
	ocfs2-devel@oss.oracle.com, viro@zeniv.linux.org.uk,
	dan.j.williams@intel.com, linux-btrfs@vger.kernel.org
Subject: [Ocfs2-devel] [PATCH v2 02/10] fsdax: Factor helper: dax_fault_actor()
Date: Fri, 26 Feb 2021 08:20:22 +0800	[thread overview]
Message-ID: <20210226002030.653855-3-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20210226002030.653855-1-ruansy.fnst@fujitsu.com>

The core logic in the two dax page fault functions is similar. So, move
the logic into a common helper function. Also, to facilitate the
addition of new features, such as CoW, switch-case is no longer used to
handle different iomap types.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
---
 fs/dax.c | 211 ++++++++++++++++++++++++++++++-------------------------
 1 file changed, 117 insertions(+), 94 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 7031e4302b13..9dea1572868e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1289,6 +1289,93 @@ static int dax_fault_cow_page(struct vm_fault *vmf, struct iomap *iomap,
 	return 0;
 }
 
+static vm_fault_t dax_fault_insert_pfn(struct vm_fault *vmf, pfn_t pfn,
+		bool pmd, bool write)
+{
+	vm_fault_t ret;
+
+	if (!pmd) {
+		struct vm_area_struct *vma = vmf->vma;
+		unsigned long address = vmf->address;
+
+		if (write)
+			ret = vmf_insert_mixed_mkwrite(vma, address, pfn);
+		else
+			ret = vmf_insert_mixed(vma, address, pfn);
+	} else
+		ret = vmf_insert_pfn_pmd(vmf, pfn, write);
+
+	return ret;
+}
+
+#ifdef CONFIG_FS_DAX_PMD
+static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
+		struct iomap *iomap, void **entry);
+#else
+static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
+		struct iomap *iomap, void **entry)
+{
+	return VM_FAULT_FALLBACK;
+}
+#endif
+
+/**
+ * dax_fault_actor - Common actor to handle pfn insertion in PTE/PMD fault.
+ * @vmf:	vm fault instance
+ * @pfnp:	pfn to be returned
+ * @xas:	the dax mapping tree of a file
+ * @entry:	an unlocked dax entry to be inserted
+ * @pmd:	distinguish whether it is a pmd fault
+ * @flags:	iomap flags
+ * @iomap:	from iomap_begin()
+ * @srcmap:	from iomap_begin(), not equal to iomap if it is a CoW
+ */
+static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
+		struct xa_state *xas, void *entry, bool pmd, unsigned int flags,
+		struct iomap *iomap, struct iomap *srcmap)
+{
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	size_t size = pmd ? PMD_SIZE : PAGE_SIZE;
+	loff_t pos = (loff_t)xas->xa_offset << PAGE_SHIFT;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+	bool sync = dax_fault_is_synchronous(flags, vmf->vma, iomap);
+	vm_fault_t ret = 0;
+	int err = 0;
+	pfn_t pfn;
+
+	/* if we are reading UNWRITTEN and HOLE, return a hole. */
+	if (!write &&
+	    (iomap->type == IOMAP_UNWRITTEN || iomap->type == IOMAP_HOLE)) {
+		if (!pmd)
+			return dax_load_hole(xas, mapping, &entry, vmf);
+		else
+			return dax_pmd_load_hole(xas, vmf, iomap, &entry);
+	}
+
+	if (iomap->type != IOMAP_MAPPED) {
+		WARN_ON_ONCE(1);
+		return VM_FAULT_SIGBUS;
+	}
+
+	err = dax_iomap_pfn(iomap, pos, size, &pfn);
+	if (err)
+		goto error_fault;
+
+	entry = dax_insert_entry(xas, mapping, vmf, entry, pfn, 0,
+				 write && !sync);
+
+	if (sync)
+		return dax_fault_synchronous_pfnp(pfnp, pfn);
+
+	ret = dax_fault_insert_pfn(vmf, pfn, pmd, write);
+
+error_fault:
+	if (err)
+		ret = dax_fault_return(err);
+
+	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)
 {
@@ -1296,17 +1383,14 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	XA_STATE(xas, &mapping->i_pages, vmf->pgoff);
 	struct inode *inode = mapping->host;
-	unsigned long vaddr = vmf->address;
 	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
 	struct iomap iomap = { .type = IOMAP_HOLE };
 	struct iomap srcmap = { .type = IOMAP_HOLE };
 	unsigned flags = IOMAP_FAULT;
 	int error, major = 0;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
-	bool sync;
 	vm_fault_t ret = 0;
 	void *entry;
-	pfn_t pfn;
 
 	trace_dax_pte_fault(inode, vmf, ret);
 	/*
@@ -1352,8 +1436,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		goto unlock_entry;
 	}
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		error = -EIO;	/* fs corruption? */
-		goto error_finish_iomap;
+		ret = VM_FAULT_SIGBUS;	/* fs corruption? */
+		goto finish_iomap;
 	}
 
 	if (vmf->cow_page) {
@@ -1363,49 +1447,19 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		goto finish_iomap;
 	}
 
-	sync = dax_fault_is_synchronous(flags, vma, &iomap);
-
-	switch (iomap.type) {
-	case IOMAP_MAPPED:
-		if (iomap.flags & IOMAP_F_NEW) {
-			count_vm_event(PGMAJFAULT);
-			count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
-			major = VM_FAULT_MAJOR;
-		}
-		error = dax_iomap_pfn(&iomap, pos, PAGE_SIZE, &pfn);
-		if (error < 0)
-			goto error_finish_iomap;
-
-		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
-						 0, write && !sync);
-
-		if (sync) {
-			ret = dax_fault_synchronous_pfnp(pfnp, pfn);
-			goto finish_iomap;
-		}
-		trace_dax_insert_mapping(inode, vmf, entry);
-		if (write)
-			ret = vmf_insert_mixed_mkwrite(vma, vaddr, pfn);
-		else
-			ret = vmf_insert_mixed(vma, vaddr, pfn);
-
+	ret = dax_fault_actor(vmf, pfnp, &xas, entry, false, flags,
+			      &iomap, &srcmap);
+	if (ret == VM_FAULT_SIGBUS)
 		goto finish_iomap;
-	case IOMAP_UNWRITTEN:
-	case IOMAP_HOLE:
-		if (!write) {
-			ret = dax_load_hole(&xas, mapping, &entry, vmf);
-			goto finish_iomap;
-		}
-		fallthrough;
-	default:
-		WARN_ON_ONCE(1);
-		error = -EIO;
-		break;
+
+	/* read/write MAPPED, CoW UNWRITTEN */
+	if (iomap.flags & IOMAP_F_NEW) {
+		count_vm_event(PGMAJFAULT);
+		count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
+		major = VM_FAULT_MAJOR;
 	}
 
- error_finish_iomap:
-	ret = dax_fault_return(error);
- finish_iomap:
+finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PAGE_SIZE;
 
@@ -1419,9 +1473,9 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		 */
 		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
- unlock_entry:
+unlock_entry:
 	dax_unlock_entry(&xas, entry);
- out:
+out:
 	trace_dax_pte_fault_done(inode, vmf, ret);
 	return ret | major;
 }
@@ -1519,17 +1573,15 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER);
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
-	bool sync;
-	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
+	unsigned int flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
 	struct inode *inode = mapping->host;
-	vm_fault_t result = VM_FAULT_FALLBACK;
+	vm_fault_t ret = VM_FAULT_FALLBACK;
 	struct iomap iomap = { .type = IOMAP_HOLE };
 	struct iomap srcmap = { .type = IOMAP_HOLE };
 	pgoff_t max_pgoff;
 	void *entry;
 	loff_t pos;
 	int error;
-	pfn_t pfn;
 
 	/*
 	 * Check whether offset isn't beyond end of file now. Caller is
@@ -1541,7 +1593,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
 
 	if (xas.xa_index >= max_pgoff) {
-		result = VM_FAULT_SIGBUS;
+		ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
@@ -1556,7 +1608,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 */
 	entry = grab_mapping_entry(&xas, mapping, PMD_ORDER);
 	if (xa_is_internal(entry)) {
-		result = xa_to_internal(entry);
+		ret = xa_to_internal(entry);
 		goto fallback;
 	}
 
@@ -1568,7 +1620,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 */
 	if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) &&
 			!pmd_devmap(*vmf->pmd)) {
-		result = 0;
+		ret = 0;
 		goto unlock_entry;
 	}
 
@@ -1578,49 +1630,21 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * to look up our filesystem block.
 	 */
 	pos = (loff_t)xas.xa_index << PAGE_SHIFT;
-	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap,
-			&srcmap);
+	error = ops->iomap_begin(inode, pos, PMD_SIZE, flags, &iomap, &srcmap);
 	if (error)
 		goto unlock_entry;
 
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
-	sync = dax_fault_is_synchronous(iomap_flags, vma, &iomap);
-
-	switch (iomap.type) {
-	case IOMAP_MAPPED:
-		error = dax_iomap_pfn(&iomap, pos, PMD_SIZE, &pfn);
-		if (error < 0)
-			goto finish_iomap;
+	ret = dax_fault_actor(vmf, pfnp, &xas, entry, true, flags,
+			      &iomap, &srcmap);
 
-		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
-						DAX_PMD, write && !sync);
-
-		if (sync) {
-			result = dax_fault_synchronous_pfnp(pfnp, pfn);
-			goto finish_iomap;
-		}
-
-		trace_dax_pmd_insert_mapping(inode, vmf, PMD_SIZE, pfn, entry);
-		result = vmf_insert_pfn_pmd(vmf, pfn, write);
-		break;
-	case IOMAP_UNWRITTEN:
-	case IOMAP_HOLE:
-		if (WARN_ON_ONCE(write))
-			break;
-		result = dax_pmd_load_hole(&xas, vmf, &iomap, &entry);
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		break;
-	}
-
- finish_iomap:
+finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PMD_SIZE;
 
-		if (result == VM_FAULT_FALLBACK)
+		if (ret == VM_FAULT_FALLBACK)
 			copied = 0;
 		/*
 		 * The fault is done by now and there's no way back (other
@@ -1628,19 +1652,18 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		 * Just ignore error from ->iomap_end since we cannot do much
 		 * with it.
 		 */
-		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
-				&iomap);
+		ops->iomap_end(inode, pos, PMD_SIZE, copied, flags, &iomap);
 	}
- unlock_entry:
+unlock_entry:
 	dax_unlock_entry(&xas, entry);
- fallback:
-	if (result == VM_FAULT_FALLBACK) {
+fallback:
+	if (ret == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		count_vm_event(THP_FAULT_FALLBACK);
 	}
 out:
-	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
-	return result;
+	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, ret);
+	return ret;
 }
 #else
 static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
-- 
2.30.1




_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel@oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel

  parent reply	other threads:[~2021-02-26 16:55 UTC|newest]

Thread overview: 73+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-26  0:20 [Ocfs2-devel] [PATCH v2 00/10] fsdax, xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-02-26  0:20 ` [Ocfs2-devel] [PATCH v2 01/10] fsdax: Factor helpers to simplify dax fault code Shiyang Ruan
2021-03-03  9:13   ` Christoph Hellwig
2021-02-26  0:20 ` Shiyang Ruan [this message]
2021-03-03  9:28   ` [Ocfs2-devel] [PATCH v2 02/10] fsdax: Factor helper: dax_fault_actor() Christoph Hellwig
2021-03-12  9:01     ` ruansy.fnst
2021-02-26  0:20 ` [Ocfs2-devel] [PATCH v2 03/10] fsdax: Output address in dax_iomap_pfn() and rename it Shiyang Ruan
2021-02-26  0:20 ` [Ocfs2-devel] [PATCH v2 05/10] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-03-03  9:30   ` Christoph Hellwig
2021-03-03  9:41     ` ruansy.fnst
2021-03-03  9:44       ` Christoph Hellwig
2021-03-03  9:48   ` Christoph Hellwig
2021-02-26  0:20 ` [Ocfs2-devel] [PATCH v2 08/10] fsdax: Dedup file range to use a compare function Shiyang Ruan
2021-02-26  8:28   ` Shiyang Ruan
2021-03-03  8:20   ` Joe Perches
2021-03-03  8:45     ` ruansy.fnst
2021-03-03  9:04       ` Joe Perches
2021-03-03  9:39       ` hch
2021-03-03  9:46         ` ruansy.fnst
2021-03-04  5:42   ` [Ocfs2-devel] [RESEND PATCH v2.1 " Shiyang Ruan
2021-02-26  0:20 ` [Ocfs2-devel] [PATCH v2 09/10] fs/xfs: Handle CoW for fsdax write() path Shiyang Ruan
2021-03-03  9:43   ` Christoph Hellwig
2021-03-03  9:57     ` ruansy.fnst
2021-03-03 10:43       ` Christoph Hellwig
2021-03-04  1:35         ` ruansy.fnst
2021-02-26  0:20 ` [Ocfs2-devel] [PATCH v2 10/10] fs/xfs: Add dedupe support for fsdax Shiyang Ruan
2021-02-26  9:45 ` [Ocfs2-devel] Question about the "EXPERIMENTAL" tag for dax in XFS ruansy.fnst
2021-02-26 19:04   ` Darrick J. Wong
2021-02-26 19:24     ` Dan Williams
2021-02-26 20:51       ` Dave Chinner
2021-02-26 20:59         ` Dan Williams
2021-02-26 21:27           ` Dave Chinner
2021-02-26 22:41             ` Dan Williams
2021-02-27 22:36               ` Dave Chinner
2021-02-27 23:40                 ` Dan Williams
2021-02-28 22:38                   ` Dave Chinner
2021-03-01 20:55                     ` Dan Williams
2021-03-01 22:46                       ` Dave Chinner
2021-03-02  0:32                         ` Dan Williams
2021-03-02  2:42                           ` Dave Chinner
2021-03-02  3:33                             ` Dan Williams
2021-03-02  5:38                               ` Dave Chinner
2021-03-02  5:50                                 ` Dan Williams
2021-03-02  3:28                       ` Darrick J. Wong
2021-03-02  5:41                         ` Dan Williams
2021-03-02  7:57                           ` Dave Chinner
2021-03-02 17:49                             ` Dan Williams
2021-03-04 23:40                               ` Darrick J. Wong
2021-03-01  7:26       ` Yasunori Goto
2021-03-01 21:34         ` Dan Williams
     [not found] ` <20210226002030.653855-5-ruansy.fnst@fujitsu.com>
2021-03-03  9:29   ` [Ocfs2-devel] [PATCH v2 04/10] fsdax: Introduce dax_iomap_cow_copy() Christoph Hellwig
     [not found] ` <20210226002030.653855-7-ruansy.fnst@fujitsu.com>
2021-03-03  9:31   ` [Ocfs2-devel] [PATCH v2 06/10] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Christoph Hellwig
     [not found] ` <20210226002030.653855-8-ruansy.fnst@fujitsu.com>
2021-02-26  4:14   ` [Ocfs2-devel] [PATCH v2 07/10] iomap: Introduce iomap_apply2() for operations on two files Darrick J. Wong
2021-02-26  8:11     ` ruansy.fnst
2021-02-26  8:25   ` Shiyang Ruan
2021-03-04  5:41   ` [Ocfs2-devel] [RESEND PATCH v2.1 " Shiyang Ruan
2021-03-11 12:30     ` Christoph Hellwig
2021-03-09  6:36 ` [Ocfs2-devel] [PATCH v2 00/10] fsdax, xfs: Add reflink&dedupe support for fsdax Xiaoguang Wang
2021-03-10  1:32   ` ruansy.fnst
2021-03-09 16:19 ` Goldwyn Rodrigues
2021-03-10  1:26   ` ruansy.fnst
2021-03-10 12:30 ` Neal Gompa
2021-03-10 13:02   ` Matthew Wilcox
2021-03-10 13:36     ` Neal Gompa
2021-03-10 13:55       ` Matthew Wilcox
2021-03-10 14:21     ` Goldwyn Rodrigues
2021-03-10 14:26       ` Matthew Wilcox
2021-03-10 17:04         ` Goldwyn Rodrigues
2021-03-11  0:53         ` Dan Williams
2021-03-11  8:26           ` Neal Gompa
2021-03-13 13:07         ` Adam Borowski
2021-03-13 16:24           ` Neal Gompa
2021-03-13 22:00             ` Adam Borowski

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=20210226002030.653855-3-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=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=viro@zeniv.linux.org.uk \
    --subject='Re: [Ocfs2-devel] [PATCH v2 02/10] fsdax: Factor helper: dax_fault_actor()' \
    /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

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).