From ce48c457b95316b9a01b5aa9d4456ce820df94b4 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 19 Dec 2018 18:23:15 +0000 Subject: cpu/hotplug: Mute hotplug lockdep during init Since we've had: commit cb538267ea1e ("jump_label/lockdep: Assert we hold the hotplug lock for _cpuslocked() operations") we've been getting some lockdep warnings during init, such as on HiKey960: [ 0.820495] WARNING: CPU: 4 PID: 0 at kernel/cpu.c:316 lockdep_assert_cpus_held+0x3c/0x48 [ 0.820498] Modules linked in: [ 0.820509] CPU: 4 PID: 0 Comm: swapper/4 Tainted: G S 4.20.0-rc5-00051-g4cae42a #34 [ 0.820511] Hardware name: HiKey960 (DT) [ 0.820516] pstate: 600001c5 (nZCv dAIF -PAN -UAO) [ 0.820520] pc : lockdep_assert_cpus_held+0x3c/0x48 [ 0.820523] lr : lockdep_assert_cpus_held+0x38/0x48 [ 0.820526] sp : ffff00000a9cbe50 [ 0.820528] x29: ffff00000a9cbe50 x28: 0000000000000000 [ 0.820533] x27: 00008000b69e5000 x26: ffff8000bff4cfe0 [ 0.820537] x25: ffff000008ba69e0 x24: 0000000000000001 [ 0.820541] x23: ffff000008fce000 x22: ffff000008ba70c8 [ 0.820545] x21: 0000000000000001 x20: 0000000000000003 [ 0.820548] x19: ffff00000a35d628 x18: ffffffffffffffff [ 0.820552] x17: 0000000000000000 x16: 0000000000000000 [ 0.820556] x15: ffff00000958f848 x14: 455f3052464d4d34 [ 0.820559] x13: 00000000769dde98 x12: ffff8000bf3f65a8 [ 0.820564] x11: 0000000000000000 x10: ffff00000958f848 [ 0.820567] x9 : ffff000009592000 x8 : ffff00000958f848 [ 0.820571] x7 : ffff00000818ffa0 x6 : 0000000000000000 [ 0.820574] x5 : 0000000000000000 x4 : 0000000000000001 [ 0.820578] x3 : 0000000000000000 x2 : 0000000000000001 [ 0.820582] x1 : 00000000ffffffff x0 : 0000000000000000 [ 0.820587] Call trace: [ 0.820591] lockdep_assert_cpus_held+0x3c/0x48 [ 0.820598] static_key_enable_cpuslocked+0x28/0xd0 [ 0.820606] arch_timer_check_ool_workaround+0xe8/0x228 [ 0.820610] arch_timer_starting_cpu+0xe4/0x2d8 [ 0.820615] cpuhp_invoke_callback+0xe8/0xd08 [ 0.820619] notify_cpu_starting+0x80/0xb8 [ 0.820625] secondary_start_kernel+0x118/0x1d0 We've also had a similar warning in sched_init_smp() for every asymmetric system that would enable the sched_asym_cpucapacity static key, although that was singled out in: commit 40fa3780bac2 ("sched/core: Take the hotplug lock in sched_init_smp()") Those warnings are actually harmless, since we cannot have hotplug operations at the time they appear. Instead of starting to sprinkle useless hotplug lock operations in the init codepaths, mute the warnings until they start warning about real problems. Suggested-by: Peter Zijlstra Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Thomas Gleixner Cc: Will Deacon Cc: cai@gmx.us Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: linux-arm-kernel@lists.infradead.org Cc: longman@redhat.com Cc: marc.zyngier@arm.com Cc: mark.rutland@arm.com Link: https://lkml.kernel.org/r/1545243796-23224-2-git-send-email-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/cpu.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 91d5c38eb7e5..34e40ef2f6e0 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -313,6 +313,15 @@ void cpus_write_unlock(void) void lockdep_assert_cpus_held(void) { + /* + * We can't have hotplug operations before userspace starts running, + * and some init codepaths will knowingly not take the hotplug lock. + * This is all valid, so mute lockdep until it makes sense to report + * unheld locks. + */ + if (system_state < SYSTEM_RUNNING) + return; + percpu_rwsem_assert_held(&cpu_hotplug_lock); } -- cgit v1.2.3 From 34d66caf251df91ff27b24a3a786810d29989eca Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Thu, 17 Jan 2019 02:10:59 -0800 Subject: x86/speculation: Remove redundant arch_smt_update() invocation With commit a74cfffb03b7 ("x86/speculation: Rework SMT state change"), arch_smt_update() is invoked from each individual CPU hotplug function. Therefore the extra arch_smt_update() call in the sysfs SMT control is redundant. Fixes: a74cfffb03b7 ("x86/speculation: Rework SMT state change") Signed-off-by: Zhenzhong Duan Signed-off-by: Thomas Gleixner Cc: Cc: Cc: Cc: Cc: Cc: Link: https://lkml.kernel.org/r/e2e064f2-e8ef-42ca-bf4f-76b612964752@default --- kernel/cpu.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 91d5c38eb7e5..c0c7f64573ed 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2090,10 +2090,8 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) */ cpuhp_offline_cpu_device(cpu); } - if (!ret) { + if (!ret) cpu_smt_control = ctrlval; - arch_smt_update(); - } cpu_maps_update_done(); return ret; } @@ -2104,7 +2102,6 @@ static int cpuhp_smt_enable(void) cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; - arch_smt_update(); for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) -- cgit v1.2.3 From b284909abad48b07d3071a9fc9b5692b3e64914b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 30 Jan 2019 07:13:58 -0600 Subject: cpu/hotplug: Fix "SMT disabled by BIOS" detection for KVM With the following commit: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") ... the hotplug code attempted to detect when SMT was disabled by BIOS, in which case it reported SMT as permanently disabled. However, that code broke a virt hotplug scenario, where the guest is booted with only primary CPU threads, and a sibling is brought online later. The problem is that there doesn't seem to be a way to reliably distinguish between the HW "SMT disabled by BIOS" case and the virt "sibling not yet brought online" case. So the above-mentioned commit was a bit misguided, as it permanently disabled SMT for both cases, preventing future virt sibling hotplugs. Going back and reviewing the original problems which were attempted to be solved by that commit, when SMT was disabled in BIOS: 1) /sys/devices/system/cpu/smt/control showed "on" instead of "notsupported"; and 2) vmx_vm_init() was incorrectly showing the L1TF_MSG_SMT warning. I'd propose that we instead consider #1 above to not actually be a problem. Because, at least in the virt case, it's possible that SMT wasn't disabled by BIOS and a sibling thread could be brought online later. So it makes sense to just always default the smt control to "on" to allow for that possibility (assuming cpuid indicates that the CPU supports SMT). The real problem is #2, which has a simple fix: change vmx_vm_init() to query the actual current SMT state -- i.e., whether any siblings are currently online -- instead of looking at the SMT "control" sysfs value. So fix it by: a) reverting the original "fix" and its followup fix: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") bc2d8d262cba ("cpu/hotplug: Fix SMT supported evaluation") and b) changing vmx_vm_init() to query the actual current SMT state -- instead of the sysfs control value -- to determine whether the L1TF warning is needed. This also requires the 'sched_smt_present' variable to exported, instead of 'cpu_smt_control'. Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by: Igor Mammedov Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Joe Mario Cc: Jiri Kosina Cc: Peter Zijlstra Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/e3a85d585da28cc333ecbc1e78ee9216e6da9396.1548794349.git.jpoimboe@redhat.com --- kernel/cpu.c | 33 ++++----------------------------- 1 file changed, 4 insertions(+), 29 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index c0c7f64573ed..d1c6d152da89 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -376,9 +376,6 @@ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; -EXPORT_SYMBOL_GPL(cpu_smt_control); - -static bool cpu_smt_available __read_mostly; void __init cpu_smt_disable(bool force) { @@ -397,25 +394,11 @@ void __init cpu_smt_disable(bool force) /* * The decision whether SMT is supported can only be done after the full - * CPU identification. Called from architecture code before non boot CPUs - * are brought up. - */ -void __init cpu_smt_check_topology_early(void) -{ - if (!topology_smt_supported()) - cpu_smt_control = CPU_SMT_NOT_SUPPORTED; -} - -/* - * If SMT was disabled by BIOS, detect it here, after the CPUs have been - * brought online. This ensures the smt/l1tf sysfs entries are consistent - * with reality. cpu_smt_available is set to true during the bringup of non - * boot CPUs when a SMT sibling is detected. Note, this may overwrite - * cpu_smt_control's previous setting. + * CPU identification. Called from architecture code. */ void __init cpu_smt_check_topology(void) { - if (!cpu_smt_available) + if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } @@ -428,18 +411,10 @@ early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { - if (topology_is_primary_thread(cpu)) + if (cpu_smt_control == CPU_SMT_ENABLED) return true; - /* - * If the CPU is not a 'primary' thread and the booted_once bit is - * set then the processor has SMT support. Store this information - * for the late check of SMT support in cpu_smt_check_topology(). - */ - if (per_cpu(cpuhp_state, cpu).booted_once) - cpu_smt_available = true; - - if (cpu_smt_control == CPU_SMT_ENABLED) + if (topology_is_primary_thread(cpu)) return true; /* -- cgit v1.2.3 From 206b92353c839c0b27a0b9bec24195f93fd6cf7a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 26 Mar 2019 17:36:05 +0100 Subject: cpu/hotplug: Prevent crash when CPU bringup fails on CONFIG_HOTPLUG_CPU=n Tianyu reported a crash in a CPU hotplug teardown callback when booting a kernel which has CONFIG_HOTPLUG_CPU disabled with the 'nosmt' boot parameter. It turns out that the SMP=y CONFIG_HOTPLUG_CPU=n case has been broken forever in case that a bringup callback fails. Unfortunately this issue was not recognized when the CPU hotplug code was reworked, so the shortcoming just stayed in place. When a bringup callback fails, the CPU hotplug code rolls back the operation and takes the CPU offline. The 'nosmt' command line argument uses a bringup failure to abort the bringup of SMT sibling CPUs. This partial bringup is required due to the MCE misdesign on Intel CPUs. With CONFIG_HOTPLUG_CPU=y the rollback works perfectly fine, but CONFIG_HOTPLUG_CPU=n lacks essential mechanisms to exercise the low level teardown of a CPU including the synchronizations in various facilities like RCU, NOHZ and others. As a consequence the teardown callbacks which must be executed on the outgoing CPU within stop machine with interrupts disabled are executed on the control CPU in interrupt enabled and preemptible context causing the kernel to crash and burn. The pre state machine code has a different failure mode which is more subtle and resulting in a less obvious use after free crash because the control side frees resources which are still in use by the undead CPU. But this is not a x86 only problem. Any architecture which supports the SMP=y HOTPLUG_CPU=n combination suffers from the same issue. It's just less likely to be triggered because in 99.99999% of the cases all bringup callbacks succeed. The easy solution of making HOTPLUG_CPU mandatory for SMP is not working on all architectures as the following architectures have either no hotplug support at all or not all subarchitectures support it: alpha, arc, hexagon, openrisc, riscv, sparc (32bit), mips (partial). Crashing the kernel in such a situation is not an acceptable state either. Implement a minimal rollback variant by limiting the teardown to the point where all regular teardown callbacks have been invoked and leave the CPU in the 'dead' idle state. This has the following consequences: - the CPU is brought down to the point where the stop_machine takedown would happen. - the CPU stays there forever and is idle - The CPU is cleared in the CPU active mask, but not in the CPU online mask which is a legit state. - Interrupts are not forced away from the CPU - All facilities which only look at online mask would still see it, but that is the case during normal hotplug/unplug operations as well. It's just a (way) longer time frame. This will expose issues, which haven't been exposed before or only seldom, because now the normally transient state of being non active but online is a permanent state. In testing this exposed already an issue vs. work queues where the vmstat code schedules work on the almost dead CPU which ends up in an unbound workqueue and triggers 'preemtible context' warnings. This is not a problem of this change, it merily exposes an already existing issue. Still this is better than crashing fully without a chance to debug it. This is mainly thought as workaround for those architectures which do not support HOTPLUG_CPU. All others should enforce HOTPLUG_CPU for SMP. Fixes: 2e1a3483ce74 ("cpu/hotplug: Split out the state walk into functions") Reported-by: Tianyu Lan Signed-off-by: Thomas Gleixner Tested-by: Tianyu Lan Acked-by: Greg Kroah-Hartman Cc: Konrad Wilk Cc: Josh Poimboeuf Cc: Mukesh Ojha Cc: Peter Zijlstra Cc: Jiri Kosina Cc: Rik van Riel Cc: Andy Lutomirski Cc: Micheal Kelley Cc: "K. Y. Srinivasan" Cc: Linus Torvalds Cc: Borislav Petkov Cc: K. Y. Srinivasan Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190326163811.503390616@linutronix.de --- kernel/cpu.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 025f419d16f6..6754f3ecfd94 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -564,6 +564,20 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } +static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) +{ + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return true; + /* + * When CPU hotplug is disabled, then taking the CPU down is not + * possible because takedown_cpu() and the architecture and + * subsystem specific mechanisms are not available. So the CPU + * which would be completely unplugged again needs to stay around + * in the current state. + */ + return st->state <= CPUHP_BRINGUP_CPU; +} + static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { @@ -574,8 +588,10 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { - st->target = prev_state; - undo_cpu_up(cpu, st); + if (can_rollback_cpu(st)) { + st->target = prev_state; + undo_cpu_up(cpu, st); + } break; } } -- cgit v1.2.3