[PATCH 3/5] firmware: add sanity check on shutdown/suspend

From: Luis R. Rodriguez
Date: Wed Mar 29 2017 - 23:28:23 EST


The firmware API should not be used after we go to suspend
and after we reboot/halt. The suspend/resume case is a bit
complex, so this documents that so things are clearer.

We want to know about users of the API in incorrect places so
that their callers are corrected, so this also adds a warn
for those cases.

Signed-off-by: Luis R. Rodriguez <mcgrof@xxxxxxxxxx>
---
.../driver-api/firmware/request_firmware.rst | 11 +++
drivers/base/firmware_class.c | 96 ++++++++++++++++++++++
2 files changed, 107 insertions(+)

diff --git a/Documentation/driver-api/firmware/request_firmware.rst b/Documentation/driver-api/firmware/request_firmware.rst
index cc0aea880824..1c2c4967cd43 100644
--- a/Documentation/driver-api/firmware/request_firmware.rst
+++ b/Documentation/driver-api/firmware/request_firmware.rst
@@ -44,6 +44,17 @@ request_firmware_nowait
.. kernel-doc:: drivers/base/firmware_class.c
:functions: request_firmware_nowait

+Considerations for suspend and resume
+=====================================
+
+During suspend and resume only the built-in firmware and the firmware cache
+elements of the firmware API can be used. This is managed by fw_pm_notify().
+
+fw_pm_notify
+------------
+.. kernel-doc:: drivers/base/firmware_class.c
+ :functions: fw_pm_notify
+
request firmware API expected driver use
========================================

diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index e8edf22536c1..f7ac619635b4 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -260,6 +260,38 @@ static int fw_cache_piggyback_on_request(const char *name);
* guarding for corner cases a global lock should be OK */
static DEFINE_MUTEX(fw_lock);

+static bool __enable_firmware = false;
+
+static void enable_firmware(void)
+{
+ mutex_lock(&fw_lock);
+ __enable_firmware = true;
+ mutex_unlock(&fw_lock);
+}
+
+static void disable_firmware(void)
+{
+ mutex_lock(&fw_lock);
+ __enable_firmware = false;
+ mutex_unlock(&fw_lock);
+}
+
+/*
+ * When disabled only the built-in firmware and the firmware cache will be
+ * used to look for firmware.
+ */
+static bool firmware_enabled(void)
+{
+ bool enabled = false;
+
+ mutex_lock(&fw_lock);
+ if (__enable_firmware)
+ enabled = true;
+ mutex_unlock(&fw_lock);
+
+ return enabled;
+}
+
static struct firmware_cache fw_cache;

static struct firmware_buf *__allocate_fw_buf(const char *fw_name,
@@ -1165,6 +1197,12 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
if (ret <= 0) /* error or already assigned */
goto out;

+ if (!firmware_enabled()) {
+ WARN(1, "firmware request while host is not available\n");
+ ret = -EHOSTDOWN;
+ goto out;
+ }
+
ret = 0;
timeout = firmware_loading_timeout();
if (opt_flags & FW_OPT_NOWAIT) {
@@ -1697,6 +1735,59 @@ static void device_uncache_fw_images_delay(unsigned long delay)
msecs_to_jiffies(delay));
}

+/**
+ * fw_pm_notify - notifier for suspend/resume
+ *
+ * Used to modify the firmware_class state as we move in between states.
+ * The firmware_class implements a firmware cache to enable device driver
+ * to fetch firmware upon resume before the root filesystem is ready. We
+ * disable API calls which do not use the built-in firmware or the firmware
+ * cache when we know these calls will not work.
+ *
+ * The inner logic behind all this is a bit complex so it is worth summarizing
+ * the kernel's own suspend/resume process with context and focus on how this
+ * can impact the firmware API.
+ *
+ * First a review on how we go to suspend:
+ *
+ * pm_suspend() --> enter_state() -->
+ * sys_sync()
+ * suspend_prepare() -->
+ * __pm_notifier_call_chain(PM_SUSPEND_PREPARE, ...);
+ * suspend_freeze_processes() -->
+ * freeze_processes() -->
+ * __usermodehelper_set_disable_depth(UMH_DISABLED);
+ * freeze all tasks ...
+ * freeze_kernel_threads()
+ * suspend_devices_and_enter() -->
+ * dpm_suspend_start() -->
+ * dpm_prepare()
+ * dpm_suspend()
+ * suspend_enter() -->
+ * platform_suspend_prepare()
+ * dpm_suspend_late()
+ * freeze_enter()
+ * syscore_suspend()
+ *
+ * When we resume we bail out of a loop from suspend_devices_and_enter() and
+ * unwind back out to the caller enter_state() where we were before as follows:
+ *
+ * enter_state() -->
+ * suspend_devices_and_enter() --> (bail from loop)
+ * dpm_resume_end() -->
+ * dpm_resume()
+ * dpm_complete()
+ * suspend_finish() -->
+ * suspend_thaw_processes() -->
+ * thaw_processes() -->
+ * __usermodehelper_set_disable_depth(UMH_FREEZING);
+ * thaw_workqueues();
+ * thaw all processes ...
+ * usermodehelper_enable();
+ * pm_notifier_call_chain(PM_POST_SUSPEND);
+ *
+ * fw_pm_notify() works through pm_notifier_call_chain().
+ */
static int fw_pm_notify(struct notifier_block *notify_block,
unsigned long mode, void *unused)
{
@@ -1710,6 +1801,7 @@ static int fw_pm_notify(struct notifier_block *notify_block,
*/
kill_pending_fw_fallback_reqs(true);
device_cache_fw_images();
+ disable_firmware();
break;

case PM_POST_SUSPEND:
@@ -1722,6 +1814,7 @@ static int fw_pm_notify(struct notifier_block *notify_block,
mutex_lock(&fw_lock);
fw_cache.state = FW_LOADER_NO_CACHE;
mutex_unlock(&fw_lock);
+ enable_firmware();

device_uncache_fw_images_delay(10 * MSEC_PER_SEC);
break;
@@ -1770,6 +1863,7 @@ static void __init fw_cache_init(void)
static int fw_shutdown_notify(struct notifier_block *unused1,
unsigned long unused2, void *unused3)
{
+ disable_firmware();
/*
* Kill all pending fallback requests to avoid both stalling shutdown,
* and avoid a deadlock with the usermode_lock.
@@ -1785,6 +1879,7 @@ static struct notifier_block fw_shutdown_nb = {

static int __init firmware_class_init(void)
{
+ enable_firmware();
fw_cache_init();
register_reboot_notifier(&fw_shutdown_nb);
#ifdef CONFIG_FW_LOADER_USER_HELPER
@@ -1796,6 +1891,7 @@ static int __init firmware_class_init(void)

static void __exit firmware_class_exit(void)
{
+ disable_firmware();
#ifdef CONFIG_PM_SLEEP
unregister_syscore_ops(&fw_syscore_ops);
unregister_pm_notifier(&fw_cache.pm_notify);
--
2.11.0