From: Mario Limonciello Date: Fri, 13 Jun 2025 21:43:44 +0000 (-0500) Subject: PM: Restrict swap use to later in the suspend sequence X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=12ffc3b1513ebc1f11ae77d053948504a94a68a6;p=linux-block.git PM: Restrict swap use to later in the suspend sequence Currently swap is restricted before drivers have had a chance to do their prepare() PM callbacks. Restricting swap this early means that if a driver needs to evict some content from memory into sawp in it's prepare callback, it won't be able to. On AMD dGPUs this can lead to failed suspends under memory pressure situations as all VRAM must be evicted to system memory or swap. Move the swap restriction to right after all devices have had a chance to do the prepare() callback. If there is any problem with the sequence, restore swap in the appropriate dpm resume callbacks or error handling paths. Closes: https://github.com/ROCm/ROCK-Kernel-Driver/issues/174 Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2362 Signed-off-by: Mario Limonciello Tested-by: Nat Wittstock Tested-by: Lucian Langa Link: https://patch.msgid.link/20250613214413.4127087-1-superm1@kernel.org Signed-off-by: Rafael J. Wysocki --- diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index eebe699fdf4f..bf77d28e959f 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1236,6 +1236,7 @@ void dpm_complete(pm_message_t state) */ void dpm_resume_end(pm_message_t state) { + pm_restore_gfp_mask(); dpm_resume(state); dpm_complete(state); } @@ -2176,8 +2177,10 @@ int dpm_suspend_start(pm_message_t state) error = dpm_prepare(state); if (error) dpm_save_failed_step(SUSPEND_PREPARE); - else + else { + pm_restrict_gfp_mask(); error = dpm_suspend(state); + } dpm_show_time(starttime, state, error, "start"); return error; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index b1c76c8f2c82..6a3f92098872 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -446,6 +446,8 @@ extern int unregister_pm_notifier(struct notifier_block *nb); extern void ksys_sync_helper(void); extern void pm_report_hw_sleep_time(u64 t); extern void pm_report_max_hw_sleep(u64 t); +void pm_restrict_gfp_mask(void); +void pm_restore_gfp_mask(void); #define pm_notifier(fn, pri) { \ static struct notifier_block fn##_nb = \ @@ -492,6 +494,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) static inline void pm_report_hw_sleep_time(u64 t) {}; static inline void pm_report_max_hw_sleep(u64 t) {}; +static inline void pm_restrict_gfp_mask(void) {} +static inline void pm_restore_gfp_mask(void) {} + static inline void ksys_sync_helper(void) {} #define pm_notifier(fn, pri) do { (void)(fn); } while (0) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 9c59fa480b0b..3a9a9f240dbc 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1136,6 +1136,7 @@ int kernel_kexec(void) Resume_devices: dpm_resume_end(PMSG_RESTORE); Resume_console: + pm_restore_gfp_mask(); console_resume_all(); thaw_processes(); Restore_console: diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 519fb09de5e0..9216e3b91d3b 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -423,7 +423,6 @@ int hibernation_snapshot(int platform_mode) } console_suspend_all(); - pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); @@ -559,7 +558,6 @@ int hibernation_restore(int platform_mode) pm_prepare_console(); console_suspend_all(); - pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); @@ -571,7 +569,6 @@ int hibernation_restore(int platform_mode) BUG_ON(!error); } dpm_resume_end(PMSG_RECOVER); - pm_restore_gfp_mask(); console_resume_all(); pm_restore_console(); return error; diff --git a/kernel/power/power.h b/kernel/power/power.h index cb1d71562002..7ccd709af93f 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -239,11 +239,6 @@ static inline void suspend_test_finish(const char *label) {} /* kernel/power/main.c */ extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down); extern int pm_notifier_call_chain(unsigned long val); -void pm_restrict_gfp_mask(void); -void pm_restore_gfp_mask(void); -#else -static inline void pm_restrict_gfp_mask(void) {} -static inline void pm_restore_gfp_mask(void) {} #endif #ifdef CONFIG_HIGHMEM diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 76b141b9aac0..bb608b68fb30 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -540,6 +540,7 @@ int suspend_devices_and_enter(suspend_state_t state) return error; Recover_platform: + pm_restore_gfp_mask(); platform_recover(state); goto Resume_devices; } @@ -606,9 +607,7 @@ static int enter_state(suspend_state_t state) trace_suspend_resume(TPS("suspend_enter"), state, false); pm_pr_dbg("Suspending system (%s)\n", mem_sleep_labels[state]); - pm_restrict_gfp_mask(); error = suspend_devices_and_enter(state); - pm_restore_gfp_mask(); Finish: events_check_enabled = false;