diff mbox series

[v14,04/07] fsdax: Introduce dax_lock_mapping_entry()

Message ID 20220508143620.1775214-5-ruansy.fnst@fujitsu.com (mailing list archive)
State New
Headers show
Series None | expand

Commit Message

Shiyang Ruan May 8, 2022, 2:36 p.m. UTC
The current dax_lock_page() locks dax entry by obtaining mapping and
index in page.  To support 1-to-N RMAP in NVDIMM, we need a new function
to lock a specific dax entry corresponding to this file's mapping,index.
And output the page corresponding to the specific dax entry for caller
use.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/dax.c            | 63 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/dax.h | 15 +++++++++++
 2 files changed, 78 insertions(+)
diff mbox series

Patch

diff --git a/fs/dax.c b/fs/dax.c
index 1ac12e877f4f..57efd3f73655 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -455,6 +455,69 @@  void dax_unlock_page(struct page *page, dax_entry_t cookie)
 	dax_unlock_entry(&xas, (void *)cookie);
 }
 
+/*
+ * dax_lock_mapping_entry - Lock the DAX entry corresponding to a mapping
+ * @mapping: the file's mapping whose entry we want to lock
+ * @index: the offset within this file
+ * @page: output the dax page corresponding to this dax entry
+ *
+ * Return: A cookie to pass to dax_unlock_mapping_entry() or 0 if the entry
+ * could not be locked.
+ */
+dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, pgoff_t index,
+		struct page **page)
+{
+	XA_STATE(xas, NULL, 0);
+	void *entry;
+
+	rcu_read_lock();
+	for (;;) {
+		entry = NULL;
+		if (!dax_mapping(mapping))
+			break;
+
+		xas.xa = &mapping->i_pages;
+		xas_lock_irq(&xas);
+		xas_set(&xas, index);
+		entry = xas_load(&xas);
+		if (dax_is_locked(entry)) {
+			rcu_read_unlock();
+			wait_entry_unlocked(&xas, entry);
+			rcu_read_lock();
+			continue;
+		}
+		if (!entry ||
+		    dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
+			/*
+			 * Because we are looking for entry from file's mapping
+			 * and index, so the entry may not be inserted for now,
+			 * or even a zero/empty entry.  We don't think this is
+			 * an error case.  So, return a special value and do
+			 * not output @page.
+			 */
+			entry = (void *)~0UL;
+		} else {
+			*page = pfn_to_page(dax_to_pfn(entry));
+			dax_lock_entry(&xas, entry);
+		}
+		xas_unlock_irq(&xas);
+		break;
+	}
+	rcu_read_unlock();
+	return (dax_entry_t)entry;
+}
+
+void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index,
+		dax_entry_t cookie)
+{
+	XA_STATE(xas, &mapping->i_pages, index);
+
+	if (cookie == ~0UL)
+		return;
+
+	dax_unlock_entry(&xas, (void *)cookie);
+}
+
 /*
  * Find page cache entry at given index. If it is a DAX entry, return it
  * with the entry locked. If the page cache doesn't contain an entry at
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9c426a207ba8..c152f315d1c9 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -143,6 +143,10 @@  struct page *dax_layout_busy_page(struct address_space *mapping);
 struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
 dax_entry_t dax_lock_page(struct page *page);
 void dax_unlock_page(struct page *page, dax_entry_t cookie);
+dax_entry_t dax_lock_mapping_entry(struct address_space *mapping,
+		unsigned long index, struct page **page);
+void dax_unlock_mapping_entry(struct address_space *mapping,
+		unsigned long index, dax_entry_t cookie);
 #else
 static inline struct page *dax_layout_busy_page(struct address_space *mapping)
 {
@@ -170,6 +174,17 @@  static inline dax_entry_t dax_lock_page(struct page *page)
 static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
 {
 }
+
+static inline dax_entry_t dax_lock_mapping_entry(struct address_space *mapping,
+		unsigned long index, struct page **page)
+{
+	return 0;
+}
+
+static inline void dax_unlock_mapping_entry(struct address_space *mapping,
+		unsigned long index, dax_entry_t cookie)
+{
+}
 #endif
 
 int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,