Received-SPF: pass (google.com: domain of linux-kernel+bounces-206665-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
From: =?UTF-8?q?Jos=C3=A9=20Roberto=20de=20Souza?= <jose.souza@intel.com>
To: linux-kernel@vger.kernel.org,
	intel-xe@lists.freedesktop.org
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>,
	Mukesh Ojha <quic_mojha@quicinc.com>,
	Johannes Berg <johannes@sipsolutions.net>,
	Jonathan Cavitt <jonathan.cavitt@intel.com>,
	=?UTF-8?q?Jos=C3=A9=20Roberto=20de=20Souza?= <jose.souza@intel.com>
Subject: [PATCH v4 1/2] devcoredump: Add dev_coredumpm_timeout()
Date: Fri,  7 Jun 2024 12:32:19 -0700
Message-ID: <20240607193220.229760-1-jose.souza@intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add function to set a custom coredump timeout.

For Xe driver usage, current 5 minutes timeout may be too short for
users to search and understand what needs to be done to capture
coredump to report bugs.

We have plans to automate(distribute a udev script) it but at the end
will be up to distros and users to pack it so having a option to
increase the timeout is a safer option.

v2:
- replace dev_coredump_timeout_set() by dev_coredumpm_timeout() (Mukesh)

v3:
- make dev_coredumpm() static inline (Johannes)

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Mukesh Ojha <quic_mojha@quicinc.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Acked-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/base/devcoredump.c  | 23 ++++++++--------
 include/linux/devcoredump.h | 54 ++++++++++++++++++++++++++++---------
 2 files changed, 54 insertions(+), 23 deletions(-)

diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c
index 82aeb09b3d1b5..c795edad1b969 100644
--- a/drivers/base/devcoredump.c
+++ b/drivers/base/devcoredump.c
@@ -18,9 +18,6 @@ static struct class devcd_class;
 /* global disable flag, for security purposes */
 static bool devcd_disabled;
 
-/* if data isn't read by userspace after 5 minutes then delete it */
-#define DEVCD_TIMEOUT	(HZ * 60 * 5)
-
 struct devcd_entry {
 	struct device devcd_dev;
 	void *data;
@@ -328,7 +325,8 @@ void dev_coredump_put(struct device *dev)
 EXPORT_SYMBOL_GPL(dev_coredump_put);
 
 /**
- * dev_coredumpm - create device coredump with read/free methods
+ * dev_coredumpm_timeout - create device coredump with read/free methods with a
+ * custom timeout.
  * @dev: the struct device for the crashed device
  * @owner: the module that contains the read/free functions, use %THIS_MODULE
  * @data: data cookie for the @read/@free functions
@@ -336,17 +334,20 @@ EXPORT_SYMBOL_GPL(dev_coredump_put);
  * @gfp: allocation flags
  * @read: function to read from the given buffer
  * @free: function to free the given buffer
+ * @timeout: time in jiffies to remove coredump
  *
  * Creates a new device coredump for the given device. If a previous one hasn't
  * been read yet, the new coredump is discarded. The data lifetime is determined
  * by the device coredump framework and when it is no longer needed the @free
  * function will be called to free the data.
  */
-void dev_coredumpm(struct device *dev, struct module *owner,
-		   void *data, size_t datalen, gfp_t gfp,
-		   ssize_t (*read)(char *buffer, loff_t offset, size_t count,
-				   void *data, size_t datalen),
-		   void (*free)(void *data))
+void dev_coredumpm_timeout(struct device *dev, struct module *owner,
+			   void *data, size_t datalen, gfp_t gfp,
+			   ssize_t (*read)(char *buffer, loff_t offset,
+					   size_t count, void *data,
+					   size_t datalen),
+			   void (*free)(void *data),
+			   unsigned long timeout)
 {
 	static atomic_t devcd_count = ATOMIC_INIT(0);
 	struct devcd_entry *devcd;
@@ -403,7 +404,7 @@ void dev_coredumpm(struct device *dev, struct module *owner,
 	dev_set_uevent_suppress(&devcd->devcd_dev, false);
 	kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD);
 	INIT_DELAYED_WORK(&devcd->del_wk, devcd_del);
-	schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT);
+	schedule_delayed_work(&devcd->del_wk, timeout);
 	mutex_unlock(&devcd->mutex);
 	return;
  put_device:
@@ -414,7 +415,7 @@ void dev_coredumpm(struct device *dev, struct module *owner,
  free:
 	free(data);
 }
-EXPORT_SYMBOL_GPL(dev_coredumpm);
+EXPORT_SYMBOL_GPL(dev_coredumpm_timeout);
 
 /**
  * dev_coredumpsg - create device coredump that uses scatterlist as data
diff --git a/include/linux/devcoredump.h b/include/linux/devcoredump.h
index c8f7eb6cc1915..56e606eb4640b 100644
--- a/include/linux/devcoredump.h
+++ b/include/linux/devcoredump.h
@@ -12,6 +12,9 @@
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 
+/* if data isn't read by userspace after 5 minutes then delete it */
+#define DEVCOREDUMP_TIMEOUT	(HZ * 60 * 5)
+
 /*
  * _devcd_free_sgtable - free all the memory of the given scatterlist table
  * (i.e. both pages and scatterlist instances)
@@ -50,16 +53,17 @@ static inline void _devcd_free_sgtable(struct scatterlist *table)
 	kfree(delete_iter);
 }
 
-
 #ifdef CONFIG_DEV_COREDUMP
 void dev_coredumpv(struct device *dev, void *data, size_t datalen,
 		   gfp_t gfp);
 
-void dev_coredumpm(struct device *dev, struct module *owner,
-		   void *data, size_t datalen, gfp_t gfp,
-		   ssize_t (*read)(char *buffer, loff_t offset, size_t count,
-				   void *data, size_t datalen),
-		   void (*free)(void *data));
+void dev_coredumpm_timeout(struct device *dev, struct module *owner,
+			   void *data, size_t datalen, gfp_t gfp,
+			   ssize_t (*read)(char *buffer, loff_t offset,
+					   size_t count, void *data,
+					   size_t datalen),
+			   void (*free)(void *data),
+			   unsigned long timeout);
 
 void dev_coredumpsg(struct device *dev, struct scatterlist *table,
 		    size_t datalen, gfp_t gfp);
@@ -72,12 +76,13 @@ static inline void dev_coredumpv(struct device *dev, void *data,
 	vfree(data);
 }
 
-static inline void
-dev_coredumpm(struct device *dev, struct module *owner,
-	      void *data, size_t datalen, gfp_t gfp,
-	      ssize_t (*read)(char *buffer, loff_t offset, size_t count,
-			      void *data, size_t datalen),
-	      void (*free)(void *data))
+void dev_coredumpm_timeout(struct device *dev, struct module *owner,
+			   void *data, size_t datalen, gfp_t gfp,
+			   ssize_t (*read)(char *buffer, loff_t offset,
+					   size_t count, void *data,
+					   size_t datalen),
+			   void (*free)(void *data),
+			   unsigned long timeout)
 {
 	free(data);
 }
@@ -92,4 +97,29 @@ static inline void dev_coredump_put(struct device *dev)
 }
 #endif /* CONFIG_DEV_COREDUMP */
 
+/**
+ * dev_coredumpm - create device coredump with read/free methods
+ * @dev: the struct device for the crashed device
+ * @owner: the module that contains the read/free functions, use %THIS_MODULE
+ * @data: data cookie for the @read/@free functions
+ * @datalen: length of the data
+ * @gfp: allocation flags
+ * @read: function to read from the given buffer
+ * @free: function to free the given buffer
+ *
+ * Creates a new device coredump for the given device. If a previous one hasn't
+ * been read yet, the new coredump is discarded. The data lifetime is determined
+ * by the device coredump framework and when it is no longer needed the @free
+ * function will be called to free the data.
+ */
+static inline void dev_coredumpm(struct device *dev, struct module *owner,
+				 void *data, size_t datalen, gfp_t gfp,
+				 ssize_t (*read)(char *buffer, loff_t offset, size_t count,
+						 void *data, size_t datalen),
+				void (*free)(void *data))
+{
+	dev_coredumpm_timeout(dev, owner, data, datalen, gfp, read, free,
+			      DEVCOREDUMP_TIMEOUT);
+}
+
 #endif /* __DEVCOREDUMP_H */
-- 
2.45.2