Merge tag 'pm-5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These rework the system-wide PM driver flags, make runtime switching
  of cpuidle governors easier, improve the user space hibernation
  interface code, add intel-speed-select interface documentation, add
  more debug messages to the ACPI code handling suspend to idle, update
  the cpufreq core and drivers, fix a minor issue in the cpuidle core
  and update two cpuidle drivers, improve the PM-runtime framework,
  update the Intel RAPL power capping driver, update devfreq core and
  drivers, and clean up the cpupower utility.

  Specifics:

   - Rework the system-wide PM driver flags to make them easier to
     understand and use and update their documentation (Rafael Wysocki,
     Alan Stern).

   - Allow cpuidle governors to be switched at run time regardless of
     the kernel configuration and update the related documentation
     accordingly (Hanjun Guo).

   - Improve the resume device handling in the user space hibernarion
     interface code (Domenico Andreoli).

   - Document the intel-speed-select sysfs interface (Srinivas
     Pandruvada).

   - Make the ACPI code handing suspend to idle print more debug
     messages to help diagnose issues with it (Rafael Wysocki).

   - Fix a helper routine in the cpufreq core and correct a typo in the
     struct cpufreq_driver kerneldoc comment (Rafael Wysocki, Wang
     Wenhu).

   - Update cpufreq drivers:

      - Make the intel_pstate driver start in the passive mode by
        default on systems without HWP (Rafael Wysocki).

      - Add i.MX7ULP support to the imx-cpufreq-dt driver and add
        i.MX7ULP to the cpufreq-dt-platdev blacklist (Peng Fan).

      - Convert the qoriq cpufreq driver to a platform one, make the
        platform code create a suitable device object for it and add
        platform dependencies to it (Mian Yousaf Kaukab, Geert
        Uytterhoeven).

      - Fix wrong compatible binding in the qcom driver (Ansuel Smith).

      - Build the omap driver by default for ARCH_OMAP2PLUS (Anders
        Roxell).

      - Add r8a7742 SoC support to the dt cpufreq driver (Lad
        Prabhakar).

   - Update cpuidle core and drivers:

      - Fix three reference count leaks in error code paths in the
        cpuidle core (Qiushi Wu).

      - Convert Qualcomm SPM to a generic cpuidle driver (Stephan
        Gerhold).

      - Fix up the execution order when entering a domain idle state in
        the PSCI driver (Ulf Hansson).

   - Fix a reference counting issue related to clock management and
     clean up two oddities in the PM-runtime framework (Rafael Wysocki,
     Andy Shevchenko).

   - Add ElkhartLake support to the Intel RAPL power capping driver and
     remove an unused local MSR definition from it (Jacob Pan, Sumeet
     Pawnikar).

   - Update devfreq core and drivers:

      - Replace strncpy() with strscpy() in the devfreq core and use
        lockdep asserts instead of manual checks for a locked mutex in
        it (Dmitry Osipenko, Krzysztof Kozlowski).

      - Add a generic imx bus scaling driver and make it register an
        interconnect device (Leonard Crestez, Gustavo A. R. Silva).

      - Make the cpufreq notifier in the tegra30 driver take boosting
        into account and delete an unuseful error message from that
        driver (Dmitry Osipenko, Markus Elfring).

   - Remove unneeded semicolon from the cpupower code (Zou Wei)"

* tag 'pm-5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (51 commits)
  cpuidle: Fix three reference count leaks
  PM: runtime: Replace pm_runtime_callbacks_present()
  PM / devfreq: Use lockdep asserts instead of manual checks for locked mutex
  PM / devfreq: imx-bus: Fix inconsistent IS_ERR and PTR_ERR
  PM / devfreq: Replace strncpy with strscpy
  PM / devfreq: imx: Register interconnect device
  PM / devfreq: Add generic imx bus scaling driver
  PM / devfreq: tegra30: Delete an error message in tegra_devfreq_probe()
  PM / devfreq: tegra30: Make CPUFreq notifier to take into account boosting
  PM: hibernate: Restrict writes to the resume device
  PM: runtime: clk: Fix clk_pm_runtime_get() error path
  cpuidle: Convert Qualcomm SPM driver to a generic CPUidle driver
  ACPI: EC: PM: s2idle: Extend GPE dispatching debug message
  ACPI: PM: s2idle: Print type of wakeup debug messages
  powercap: RAPL: remove unused local MSR define
  PM: runtime: Make clear what we do when conditions are wrong in rpm_suspend()
  Documentation: admin-guide: pm: Document intel-speed-select
  PM: hibernate: Split off snapshot dev option
  PM: hibernate: Incorporate concurrency handling
  Documentation: ABI: make current_governer_ro as a candidate for removal
  ...

5 files changed, 48 insertions, 13 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index c208566c844b..4d0e6e815a2b 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -80,6 +80,18 @@ config HIBERNATION
 
 	  For more information take a look at <file:Documentation/power/swsusp.rst>.
 
+config HIBERNATION_SNAPSHOT_DEV
+	bool "Userspace snapshot device"
+	depends on HIBERNATION
+	default y
+	---help---
+	  Device used by the uswsusp tools.
+
+	  Say N if no snapshotting from userspace is needed, this also
+	  reduces the attack surface of the kernel.
+
+	  If in doubt, say Y.
+
 config PM_STD_PARTITION
 	string "Default resume partition"
 	depends on HIBERNATION
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index e7e47d9be1e5..5899260a8bef 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -10,7 +10,8 @@ obj-$(CONFIG_VT_CONSOLE_SLEEP)	+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
-obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o
+obj-$(CONFIG_HIBERNATION_SNAPSHOT_DEV) += user.o
 obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
 obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 30bd28d1d418..02ec716a4927 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -67,6 +67,18 @@ bool freezer_test_done;
 
 static const struct platform_hibernation_ops *hibernation_ops;
 
+static atomic_t hibernate_atomic = ATOMIC_INIT(1);
+
+bool hibernate_acquire(void)
+{
+	return atomic_add_unless(&hibernate_atomic, -1, 0);
+}
+
+void hibernate_release(void)
+{
+	atomic_inc(&hibernate_atomic);
+}
+
 bool hibernation_available(void)
 {
 	return nohibernate == 0 && !security_locked_down(LOCKDOWN_HIBERNATION);
@@ -704,7 +716,7 @@ int hibernate(void)
 
 	lock_system_sleep();
 	/* The snapshot device should not be opened while we're running */
-	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+	if (!hibernate_acquire()) {
 		error = -EBUSY;
 		goto Unlock;
 	}
@@ -775,7 +787,7 @@ int hibernate(void)
  Exit:
 	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
 	pm_restore_console();
-	atomic_inc(&snapshot_device_available);
+	hibernate_release();
  Unlock:
 	unlock_system_sleep();
 	pr_info("hibernation exit\n");
@@ -880,7 +892,7 @@ static int software_resume(void)
 		goto Unlock;
 
 	/* The snapshot device should not be opened while we're running */
-	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+	if (!hibernate_acquire()) {
 		error = -EBUSY;
 		swsusp_close(FMODE_READ);
 		goto Unlock;
@@ -911,7 +923,7 @@ static int software_resume(void)
 	__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
 	pm_restore_console();
 	pr_info("resume failed (%d)\n", error);
-	atomic_inc(&snapshot_device_available);
+	hibernate_release();
 	/* For success case, the suspend path will release the lock */
  Unlock:
 	mutex_unlock(&system_transition_mutex);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 7cdc64dc2373..ba2094db6294 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -154,8 +154,8 @@ extern int snapshot_write_next(struct snapshot_handle *handle);
 extern void snapshot_write_finalize(struct snapshot_handle *handle);
 extern int snapshot_image_loaded(struct snapshot_handle *handle);
 
-/* If unset, the snapshot device cannot be open. */
-extern atomic_t snapshot_device_available;
+extern bool hibernate_acquire(void);
+extern void hibernate_release(void);
 
 extern sector_t alloc_swapdev_block(int swap);
 extern void free_all_swap_pages(int swap);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 7959449765d9..d5eedc2baa2a 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -35,9 +35,13 @@ static struct snapshot_data {
 	bool ready;
 	bool platform_support;
 	bool free_bitmaps;
+	struct inode *bd_inode;
 } snapshot_state;
 
-atomic_t snapshot_device_available = ATOMIC_INIT(1);
+int is_hibernate_resume_dev(const struct inode *bd_inode)
+{
+	return hibernation_available() && snapshot_state.bd_inode == bd_inode;
+}
 
 static int snapshot_open(struct inode *inode, struct file *filp)
 {
@@ -49,13 +53,13 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 
 	lock_system_sleep();
 
-	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+	if (!hibernate_acquire()) {
 		error = -EBUSY;
 		goto Unlock;
 	}
 
 	if ((filp->f_flags & O_ACCMODE) == O_RDWR) {
-		atomic_inc(&snapshot_device_available);
+		hibernate_release();
 		error = -ENOSYS;
 		goto Unlock;
 	}
@@ -92,11 +96,12 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 			__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
 	}
 	if (error)
-		atomic_inc(&snapshot_device_available);
+		hibernate_release();
 
 	data->frozen = false;
 	data->ready = false;
 	data->platform_support = false;
+	data->bd_inode = NULL;
 
  Unlock:
 	unlock_system_sleep();
@@ -112,6 +117,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 
 	swsusp_free();
 	data = filp->private_data;
+	data->bd_inode = NULL;
 	free_all_swap_pages(data->swap);
 	if (data->frozen) {
 		pm_restore_gfp_mask();
@@ -122,7 +128,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 	}
 	pm_notifier_call_chain(data->mode == O_RDONLY ?
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
-	atomic_inc(&snapshot_device_available);
+	hibernate_release();
 
 	unlock_system_sleep();
 
@@ -204,6 +210,7 @@ struct compat_resume_swap_area {
 static int snapshot_set_swap_area(struct snapshot_data *data,
 		void __user *argp)
 {
+	struct block_device *bdev;
 	sector_t offset;
 	dev_t swdev;
 
@@ -234,9 +241,12 @@ static int snapshot_set_swap_area(struct snapshot_data *data,
 		data->swap = -1;
 		return -EINVAL;
 	}
-	data->swap = swap_type_of(swdev, offset, NULL);
+	data->swap = swap_type_of(swdev, offset, &bdev);
 	if (data->swap < 0)
 		return -ENODEV;
+
+	data->bd_inode = bdev->bd_inode;
+	bdput(bdev);
 	return 0;
 }