From 37f49e37ab4cb5d0bc4c60eb5c6d4dd57db767bb Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:44:59 +0000
Subject: [PATCH] gmac get mac form eeprom
---
kernel/drivers/base/devcoredump.c | 98 ++++++++++++++++++++++++++++++++++++++++++-------
1 files changed, 84 insertions(+), 14 deletions(-)
diff --git a/kernel/drivers/base/devcoredump.c b/kernel/drivers/base/devcoredump.c
index f1a3353..ef23c1c 100644
--- a/kernel/drivers/base/devcoredump.c
+++ b/kernel/drivers/base/devcoredump.c
@@ -29,6 +29,47 @@
struct device devcd_dev;
void *data;
size_t datalen;
+ /*
+ * Here, mutex is required to serialize the calls to del_wk work between
+ * user/kernel space which happens when devcd is added with device_add()
+ * and that sends uevent to user space. User space reads the uevents,
+ * and calls to devcd_data_write() which try to modify the work which is
+ * not even initialized/queued from devcoredump.
+ *
+ *
+ *
+ * cpu0(X) cpu1(Y)
+ *
+ * dev_coredump() uevent sent to user space
+ * device_add() ======================> user space process Y reads the
+ * uevents writes to devcd fd
+ * which results into writes to
+ *
+ * devcd_data_write()
+ * mod_delayed_work()
+ * try_to_grab_pending()
+ * del_timer()
+ * debug_assert_init()
+ * INIT_DELAYED_WORK()
+ * schedule_delayed_work()
+ *
+ *
+ * Also, mutex alone would not be enough to avoid scheduling of
+ * del_wk work after it get flush from a call to devcd_free()
+ * mentioned as below.
+ *
+ * disabled_store()
+ * devcd_free()
+ * mutex_lock() devcd_data_write()
+ * flush_delayed_work()
+ * mutex_unlock()
+ * mutex_lock()
+ * mod_delayed_work()
+ * mutex_unlock()
+ * So, delete_work flag is required.
+ */
+ struct mutex mutex;
+ bool delete_work;
struct module *owner;
ssize_t (*read)(char *buffer, loff_t offset, size_t count,
void *data, size_t datalen);
@@ -88,7 +129,12 @@
struct device *dev = kobj_to_dev(kobj);
struct devcd_entry *devcd = dev_to_devcd(dev);
- mod_delayed_work(system_wq, &devcd->del_wk, 0);
+ mutex_lock(&devcd->mutex);
+ if (!devcd->delete_work) {
+ devcd->delete_work = true;
+ mod_delayed_work(system_wq, &devcd->del_wk, 0);
+ }
+ mutex_unlock(&devcd->mutex);
return count;
}
@@ -116,15 +162,44 @@
{
struct devcd_entry *devcd = dev_to_devcd(dev);
+ mutex_lock(&devcd->mutex);
+ if (!devcd->delete_work)
+ devcd->delete_work = true;
+
flush_delayed_work(&devcd->del_wk);
+ mutex_unlock(&devcd->mutex);
return 0;
}
static ssize_t disabled_show(struct class *class, struct class_attribute *attr,
char *buf)
{
- return sprintf(buf, "%d\n", devcd_disabled);
+ return sysfs_emit(buf, "%d\n", devcd_disabled);
}
+
+/*
+ *
+ * disabled_store() worker()
+ * class_for_each_device(&devcd_class,
+ * NULL, NULL, devcd_free)
+ * ...
+ * ...
+ * while ((dev = class_dev_iter_next(&iter))
+ * devcd_del()
+ * device_del()
+ * put_device() <- last reference
+ * error = fn(dev, data) devcd_dev_release()
+ * devcd_free(dev, data) kfree(devcd)
+ * mutex_lock(&devcd->mutex);
+ *
+ *
+ * In the above diagram, It looks like disabled_store() would be racing with parallely
+ * running devcd_del() and result in memory abort while acquiring devcd->mutex which
+ * is called after kfree of devcd memory after dropping its last reference with
+ * put_device(). However, this will not happens as fn(dev, data) runs
+ * with its own reference to device via klist_node so it is not its last reference.
+ * so, above situation would not occur.
+ */
static ssize_t disabled_store(struct class *class, struct class_attribute *attr,
const char *buf, size_t count)
@@ -164,16 +239,7 @@
static ssize_t devcd_readv(char *buffer, loff_t offset, size_t count,
void *data, size_t datalen)
{
- if (offset > datalen)
- return -EINVAL;
-
- if (offset + count > datalen)
- count = datalen - offset;
-
- if (count)
- memcpy(buffer, ((u8 *)data) + offset, count);
-
- return count;
+ return memory_read_from_buffer(buffer, count, &offset, data, datalen);
}
static void devcd_freev(void *data)
@@ -291,13 +357,16 @@
devcd->read = read;
devcd->free = free;
devcd->failing_dev = get_device(dev);
+ devcd->delete_work = false;
+ mutex_init(&devcd->mutex);
device_initialize(&devcd->devcd_dev);
dev_set_name(&devcd->devcd_dev, "devcd%d",
atomic_inc_return(&devcd_count));
devcd->devcd_dev.class = &devcd_class;
+ mutex_lock(&devcd->mutex);
if (device_add(&devcd->devcd_dev))
goto put_device;
@@ -311,10 +380,11 @@
INIT_DELAYED_WORK(&devcd->del_wk, devcd_del);
schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT);
-
+ mutex_unlock(&devcd->mutex);
return;
put_device:
put_device(&devcd->devcd_dev);
+ mutex_unlock(&devcd->mutex);
put_module:
module_put(owner);
free:
@@ -323,7 +393,7 @@
EXPORT_SYMBOL_GPL(dev_coredumpm);
/**
- * dev_coredumpmsg - create device coredump that uses scatterlist as data
+ * dev_coredumpsg - create device coredump that uses scatterlist as data
* parameter
* @dev: the struct device for the crashed device
* @table: the dump data
--
Gitblit v1.6.2