From 39cdf87a97fdab067e82138ad4611b764f3eae15 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 27 May 2025 08:45:21 +0300 Subject: [PATCH 1/2] cpuidle: psci: Fix uninitialized variable in dt_idle_state_present() If the first cpu_node = of_cpu_device_node_get() fails then the cleanup.h code will try to free "state_node" but it hasn't been initialized yet. Declare the device_nodes where they are initialized to fix this. Fixes: 5836ebeb4a2b ("cpuidle: psci: Avoid initializing faux device if no DT idle states are present") Signed-off-by: Dan Carpenter Link: https://patch.msgid.link/aDVRcfU8O8sez1x7@stanley.mountain Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle-psci.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index 40f378c1dc9f..eef70b5259bc 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -440,14 +440,13 @@ static struct faux_device_ops psci_cpuidle_ops = { static bool __init dt_idle_state_present(void) { - struct device_node *cpu_node __free(device_node); - struct device_node *state_node __free(device_node); - - cpu_node = of_cpu_device_node_get(cpumask_first(cpu_possible_mask)); + struct device_node *cpu_node __free(device_node) = + of_cpu_device_node_get(cpumask_first(cpu_possible_mask)); if (!cpu_node) return false; - state_node = of_get_cpu_state_node(cpu_node, 0); + struct device_node *state_node __free(device_node) = + of_get_cpu_state_node(cpu_node, 0); if (!state_node) return false; From 70523f335734b0b42f97647556d331edf684c7dc Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 29 May 2025 15:40:43 +0200 Subject: [PATCH 2/2] Revert "x86/smp: Eliminate mwait_play_dead_cpuid_hint()" Revert commit 96040f7273e2 ("x86/smp: Eliminate mwait_play_dead_cpuid_hint()") because it introduced a significant power regression on systems that start with "nosmt" in the kernel command line. Namely, on such systems, SMT siblings permanently go offline early, when cpuidle has not been initialized yet, so after the above commit, hlt_play_dead() is called for them. Later on, when the processor attempts to enter a deep package C-state, including PC10 which is requisite for reaching minimum power in suspend-to-idle, it is not able to do that because of the SMT siblings staying in C1 (which they have been put into by HLT). As a result, the idle power (including power in suspend-to-idle) rises quite dramatically on those systems with all of the possible consequences, which (needless to say) may not be expected by their users. This issue is hard to debug and potentially dangerous, so it needs to be addressed as soon as possible in a way that will work for 6.15.y, hence the revert. Of course, after this revert, the issue that commit 96040f7273e2 attempted to address will be back and it will need to be fixed again later. Fixes: 96040f7273e2 ("x86/smp: Eliminate mwait_play_dead_cpuid_hint()") Reported-by: Todd Brandt Tested-by: Todd Brandt Cc: 6.15+ # 6.15+ Signed-off-by: Rafael J. Wysocki Acked-by: Dave Hansen Link: https://patch.msgid.link/12674167.O9o76ZdvQC@rjwysocki.net --- arch/x86/kernel/smpboot.c | 54 ++++++++++++++++++++++++++++++++++----- 1 file changed, 47 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index d6cf1e23c2a3..96355ab9aed9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1238,10 +1238,6 @@ void play_dead_common(void) local_irq_disable(); } -/* - * We need to flush the caches before going to sleep, lest we have - * dirty data in our caches when we come back up. - */ void __noreturn mwait_play_dead(unsigned int eax_hint) { struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead); @@ -1287,6 +1283,50 @@ void __noreturn mwait_play_dead(unsigned int eax_hint) } } +/* + * We need to flush the caches before going to sleep, lest we have + * dirty data in our caches when we come back up. + */ +static inline void mwait_play_dead_cpuid_hint(void) +{ + unsigned int eax, ebx, ecx, edx; + unsigned int highest_cstate = 0; + unsigned int highest_subcstate = 0; + int i; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) + return; + if (!this_cpu_has(X86_FEATURE_MWAIT)) + return; + if (!this_cpu_has(X86_FEATURE_CLFLUSH)) + return; + + eax = CPUID_LEAF_MWAIT; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + + /* + * eax will be 0 if EDX enumeration is not valid. + * Initialized below to cstate, sub_cstate value when EDX is valid. + */ + if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) { + eax = 0; + } else { + edx >>= MWAIT_SUBSTATE_SIZE; + for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) { + if (edx & MWAIT_SUBSTATE_MASK) { + highest_cstate = i; + highest_subcstate = edx & MWAIT_SUBSTATE_MASK; + } + } + eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) | + (highest_subcstate - 1); + } + + mwait_play_dead(eax); +} + /* * Kick all "offline" CPUs out of mwait on kexec(). See comment in * mwait_play_dead(). @@ -1337,9 +1377,9 @@ void native_play_dead(void) play_dead_common(); tboot_shutdown(TB_SHUTDOWN_WFS); - /* Below returns only on error. */ - cpuidle_play_dead(); - hlt_play_dead(); + mwait_play_dead_cpuid_hint(); + if (cpuidle_play_dead()) + hlt_play_dead(); } #else /* ... !CONFIG_HOTPLUG_CPU */