Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
IronPort-Data: =?us-ascii?q?A9a23=3AdrKY66lxJy/djcXz809Uttvo5gzqJ0RdPkR7XQ2?=
 =?us-ascii?q?eYbTBsI5bpzQHyWVJCGyDPf2JYGDxeox3O42x9kwEvpSHmtEwSQZk+CA2RRqmi?=
 =?us-ascii?q?+KfW43BcR2Y0wB+jyH7ZBs+qZ1YM7EsFehsJpPnjkrrYuiJQUVUj/nSHOKlUrG?=
 =?us-ascii?q?cY0ideCc/IMsfoUM68wIGqt4w6TSJK1vlVeLa+6UzCnf8s9JHGj58B5a4lf9al?=
 =?us-ascii?q?K+aVAX0EbAJTasjUFf2zxH5BX+ETE27ByOQroJ8RoZWSwtfpYxV8F81/z91Yj+?=
 =?us-ascii?q?kur39NEMXQL/OJhXIgX1TM0SgqkEa4HVsjeBgb7xBAatUo2zhc9RZ0shEs4ehD?=
 =?us-ascii?q?wkvJbHklvkfUgVDDmd1OqguFLrveCLn4JXIlRCWG5fr67A0ZK0sBqUU8/h2DUl?=
 =?us-ascii?q?A7/sdLyoHbwzFjOWzqJq7QelEh8ItNsDnMYoT/HZ6wlnxAf8gB5KFXKTO4d5R2?=
 =?us-ascii?q?SwYh8ZSEPKYbM0cARJjbgvHZRJnOVoNDp862uCyiRHXdzxetULQoK8f4Hbaxw8?=
 =?us-ascii?q?316LiWPLTZNCLQMB9mkeDunmA+2X/HwFcONGBoRKH+3ShwOTPgAv8QosZELD+/?=
 =?us-ascii?q?flv6HWXx2oOGFgYTle2v/S9olCxVsgZKEEO/Ccq668o+ySDStj7Qg39o3OeuBM?=
 =?us-ascii?q?Yc8RfHvd86wyXzKfQpQGDCQAsSj9HdcxjpMEtbSIl20XPnN7zAzFr9rqPRhqgG?=
 =?us-ascii?q?h28xd+pEXFNazZcOmlfFk1Yi+QPabob1nrnJuuP2obu5jEtJQzN/g=3D=3D?=
IronPort-HdrOrdr: =?us-ascii?q?A9a23=3A1pPOm6Ba9tCzMfHlHemQ55DYdb4zR+YMi2TD?=
 =?us-ascii?q?tnoBLSC9F/b0qynAppomPGDP4gr5NEtApTniAtjkfZq/z+8X3WB5B97LMzUO01?=
 =?us-ascii?q?HYTr2Kg7GD/xTQXwX69sN4kZxrarVCDrTLZmRSvILX5xaZHr8brOW6zA=3D=3D?=
From:   Shiyang Ruan <ruansy.fnst@fujitsu.com>
To:     <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
        <nvdimm@lists.linux.dev>, <linux-mm@kvack.org>,
        <linux-fsdevel@vger.kernel.org>
CC:     <djwong@kernel.org>, <dan.j.williams@intel.com>,
        <david@fromorbit.com>, <hch@infradead.org>, <jane.chu@oracle.com>
Subject: [PATCH v10 1/9] dax: Introduce holder for dax_device
Date:   Thu, 27 Jan 2022 20:40:50 +0800
Message-ID: <20220127124058.1172422-2-ruansy.fnst@fujitsu.com>
In-Reply-To: <20220127124058.1172422-1-ruansy.fnst@fujitsu.com>
References: <20220127124058.1172422-1-ruansy.fnst@fujitsu.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

To easily track filesystem from a pmem device, we introduce a holder for
dax_device structure, and also its operation.  This holder is used to
remember who is using this dax_device:
 - When it is the backend of a filesystem, the holder will be the
   instance of this filesystem.
 - When this pmem device is one of the targets in a mapped device, the
   holder will be this mapped device.  In this case, the mapped device
   has its own dax_device and it will follow the first rule.  So that we
   can finally track to the filesystem we needed.

The holder and holder_ops will be set when filesystem is being mounted,
or an target device is being activated.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
---
 drivers/dax/super.c | 62 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/dax.h | 29 +++++++++++++++++++++
 2 files changed, 91 insertions(+)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index e3029389d809..8e2733b78437 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -21,6 +21,9 @@
  * @cdev: optional character interface for "device dax"
  * @private: dax driver private data
  * @flags: state and boolean properties
+ * @ops: operations for dax_device
+ * @holder_data: holder of a dax_device: could be filesystem or mapped device
+ * @holder_ops: operations for the inner holder
  */
 struct dax_device {
 	struct inode inode;
@@ -28,6 +31,8 @@ struct dax_device {
 	void *private;
 	unsigned long flags;
 	const struct dax_operations *ops;
+	void *holder_data;
+	const struct dax_holder_operations *holder_ops;
 };
 
 static dev_t dax_devt;
@@ -193,6 +198,29 @@ int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 EXPORT_SYMBOL_GPL(dax_zero_page_range);
 
+int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off,
+			      u64 len, int mf_flags)
+{
+	int rc, id;
+
+	id = dax_read_lock();
+	if (!dax_alive(dax_dev)) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	if (!dax_dev->holder_ops) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	rc = dax_dev->holder_ops->notify_failure(dax_dev, off, len, mf_flags);
+out:
+	dax_read_unlock(id);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(dax_holder_notify_failure);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
@@ -268,6 +296,10 @@ void kill_dax(struct dax_device *dax_dev)
 
 	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
 	synchronize_srcu(&dax_srcu);
+
+	/* clear holder data */
+	dax_dev->holder_ops = NULL;
+	dax_dev->holder_data = NULL;
 }
 EXPORT_SYMBOL_GPL(kill_dax);
 
@@ -409,6 +441,36 @@ void put_dax(struct dax_device *dax_dev)
 }
 EXPORT_SYMBOL_GPL(put_dax);
 
+void dax_register_holder(struct dax_device *dax_dev, void *holder,
+		const struct dax_holder_operations *ops)
+{
+	if (!dax_alive(dax_dev))
+		return;
+
+	dax_dev->holder_data = holder;
+	dax_dev->holder_ops = ops;
+}
+EXPORT_SYMBOL_GPL(dax_register_holder);
+
+void dax_unregister_holder(struct dax_device *dax_dev)
+{
+	if (!dax_alive(dax_dev))
+		return;
+
+	dax_dev->holder_data = NULL;
+	dax_dev->holder_ops = NULL;
+}
+EXPORT_SYMBOL_GPL(dax_unregister_holder);
+
+void *dax_get_holder(struct dax_device *dax_dev)
+{
+	if (!dax_alive(dax_dev))
+		return NULL;
+
+	return dax_dev->holder_data;
+}
+EXPORT_SYMBOL_GPL(dax_get_holder);
+
 /**
  * inode_dax: convert a public inode into its dax_dev
  * @inode: An inode with i_cdev pointing to a dax_dev
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9fc5f99a0ae2..96cfc63b12fd 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -34,6 +34,22 @@ struct dax_operations {
 
 #if IS_ENABLED(CONFIG_DAX)
 struct dax_device *alloc_dax(void *private, const struct dax_operations *ops);
+struct dax_holder_operations {
+	/*
+	 * notify_failure - notify memory failure into inner holder device
+	 * @dax_dev: the dax device which contains the holder
+	 * @offset: offset on this dax device where memory failure occurs
+	 * @len: length of this memory failure event
+	 * @flags: action flags for memory failure handler
+	 */
+	int (*notify_failure)(struct dax_device *dax_dev, u64 offset,
+			u64 len, int mf_flags);
+};
+
+void dax_register_holder(struct dax_device *dax_dev, void *holder,
+		const struct dax_holder_operations *ops);
+void dax_unregister_holder(struct dax_device *dax_dev);
+void *dax_get_holder(struct dax_device *dax_dev);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
@@ -53,6 +69,17 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 	return dax_synchronous(dax_dev);
 }
 #else
+static inline void dax_register_holder(struct dax_device *dax_dev, void *holder,
+		const struct dax_holder_operations *ops)
+{
+}
+static inline void dax_unregister_holder(struct dax_device *dax_dev)
+{
+}
+static inline void *dax_get_holder(struct dax_device *dax_dev)
+{
+	return NULL;
+}
 static inline struct dax_device *alloc_dax(void *private,
 		const struct dax_operations *ops)
 {
@@ -185,6 +212,8 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 			size_t nr_pages);
+int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len,
+		int mf_flags);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
-- 
2.34.1