kernel/linux.git/include/linux/cpuhotplug.h, branch v6.6.131

hrtimers: Push pending hrtimers away from outgoing CPU earlier

2023-12-13T17:44:56+00:00

[ Upstream commit 5c0930ccaad5a74d74e8b18b648c5eb21ed2fe94 ] 2b8272ff4a70 ("cpu/hotplug: Prevent self deadlock on CPU hot-unplug") solved the straight forward CPU hotplug deadlock vs. the scheduler bandwidth timer. Yu discovered a more involved variant where a task which has a bandwidth timer started on the outgoing CPU holds a lock and then gets throttled. If the lock required by one of the CPU hotplug callbacks the hotplug operation deadlocks because the unthrottling timer event is not handled on the dying CPU and can only be recovered once the control CPU reaches the hotplug state which pulls the pending hrtimers from the dead CPU. Solve this by pushing the hrtimers away from the dying CPU in the dying callbacks. Nothing can queue a hrtimer on the dying CPU at that point because all other CPUs spin in stop_machine() with interrupts disabled and once the operation is finished the CPU is marked offline. Reported-by: Yu Liao Signed-off-by: Thomas Gleixner Tested-by: Liu Tie Link: https://lore.kernel.org/r/87a5rphara.ffs@tglx Signed-off-by: Sasha Levin

arm64/arm: xen: enlighten: Fix KPTI checks

2023-11-20T10:59:12+00:00

[ Upstream commit 20f3b8eafe0ba5d3c69d5011a9b07739e9645132 ] When KPTI is in use, we cannot register a runstate region as XEN requires that this is always a valid VA, which we cannot guarantee. Due to this, xen_starting_cpu() must avoid registering each CPU's runstate region, and xen_guest_init() must avoid setting up features that depend upon it. We tried to ensure that in commit: f88af7229f6f22ce (" xen/arm: do not setup the runstate info page if kpti is enabled") ... where we added checks for xen_kernel_unmapped_at_usr(), which wraps arm64_kernel_unmapped_at_el0() on arm64 and is always false on 32-bit arm. Unfortunately, as xen_guest_init() is an early_initcall, this happens before secondary CPUs are booted and arm64 has finalized the ARM64_UNMAP_KERNEL_AT_EL0 cpucap which backs arm64_kernel_unmapped_at_el0(), and so this can subsequently be set as secondary CPUs are onlined. On a big.LITTLE system where the boot CPU does not require KPTI but some secondary CPUs do, this will result in xen_guest_init() intializing features that depend on the runstate region, and xen_starting_cpu() registering the runstate region on some CPUs before KPTI is subsequent enabled, resulting the the problems the aforementioned commit tried to avoid. Handle this more robsutly by deferring the initialization of the runstate region until secondary CPUs have been initialized and the ARM64_UNMAP_KERNEL_AT_EL0 cpucap has been finalized. The per-cpu work is moved into a new hotplug starting function which is registered later when we're certain that KPTI will not be used. Fixes: f88af7229f6f ("xen/arm: do not setup the runstate info page if kpti is enabled") Signed-off-by: Mark Rutland Cc: Bertrand Marquis Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Stefano Stabellini Cc: Suzuki K Poulose Cc: Will Deacon Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin

xfs: remove CPU hotplug infrastructure

2023-09-11T15:39:04+00:00

There are no users of the cpu hotplug hooks in xfs now, so remove it. This reverts f1653c2e2831e ("xfs: introduce CPU hotplug infrastructure"). Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner

Documentation: core-api/cpuhotplug: Fix state names

2023-08-08T08:55:58+00:00

Dynamic allocated hotplug states in documentation and the comment above cpuhp_state enum do not match the code. To not get confused by wrong documentation, change to proper state names. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230515162038.62703-1-anna-maria@linutronix.de

Merge tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip

2023-06-26T20:59:56+00:00

Pull SMP updates from Thomas Gleixner: "A large update for SMP management: - Parallel CPU bringup The reason why people are interested in parallel bringup is to shorten the (kexec) reboot time of cloud servers to reduce the downtime of the VM tenants. The current fully serialized bringup does the following per AP: 1) Prepare callbacks (allocate, intialize, create threads) 2) Kick the AP alive (e.g. INIT/SIPI on x86) 3) Wait for the AP to report alive state 4) Let the AP continue through the atomic bringup 5) Let the AP run the threaded bringup to full online state There are two significant delays: #3 The time for an AP to report alive state in start_secondary() on x86 has been measured in the range between 350us and 3.5ms depending on vendor and CPU type, BIOS microcode size etc. #4 The atomic bringup does the microcode update. This has been measured to take up to ~8ms on the primary threads depending on the microcode patch size to apply. On a two socket SKL server with 56 cores (112 threads) the boot CPU spends on current mainline about 800ms busy waiting for the APs to come up and apply microcode. That's more than 80% of the actual onlining procedure. This can be reduced significantly by splitting the bringup mechanism into two parts: 1) Run the prepare callbacks and kick the AP alive for each AP which needs to be brought up. The APs wake up, do their firmware initialization and run the low level kernel startup code including microcode loading in parallel up to the first synchronization point. (#1 and #2 above) 2) Run the rest of the bringup code strictly serialized per CPU (#3 - #5 above) as it's done today. Parallelizing that stage of the CPU bringup might be possible in theory, but it's questionable whether required surgery would be justified for a pretty small gain. If the system is large enough the first AP is already waiting at the first synchronization point when the boot CPU finished the wake-up of the last AP. That reduces the AP bringup time on that SKL from ~800ms to ~80ms, i.e. by a factor ~10x. The actual gain varies wildly depending on the system, CPU, microcode patch size and other factors. There are some opportunities to reduce the overhead further, but that needs some deep surgery in the x86 CPU bringup code. For now this is only enabled on x86, but the core functionality obviously works for all SMP capable architectures. - Enhancements for SMP function call tracing so it is possible to locate the scheduling and the actual execution points. That allows to measure IPI delivery time precisely" * tag 'smp-core-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits) trace,smp: Add tracepoints for scheduling remotelly called functions trace,smp: Add tracepoints around remotelly called functions MAINTAINERS: Add CPU HOTPLUG entry x86/smpboot: Fix the parallel bringup decision x86/realmode: Make stack lock work in trampoline_compat() x86/smp: Initialize cpu_primary_thread_mask late cpu/hotplug: Fix off by one in cpuhp_bringup_mask() x86/apic: Fix use of X{,2}APIC_ENABLE in asm with older binutils x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it x86/smpboot: Support parallel startup of secondary CPUs x86/smpboot: Implement a bit spinlock to protect the realmode stack x86/apic: Save the APIC virtual base address cpu/hotplug: Allow "parallel" bringup up to CPUHP_BP_KICK_AP_STATE x86/apic: Provide cpu_primary_thread mask x86/smpboot: Enable split CPU startup cpu/hotplug: Provide a split up CPUHP_BRINGUP mechanism cpu/hotplug: Reset task stack state in _cpu_up() cpu/hotplug: Remove unused state functions riscv: Switch to hotplug core state synchronization parisc: Switch to hotplug core state synchronization ...

x86/hyperv: Fix hyperv_pcpu_input_arg handling when CPUs go online/offline

2023-06-17T23:09:47+00:00

These commits a494aef23dfc ("PCI: hv: Replace retarget_msi_interrupt_params with hyperv_pcpu_input_arg") 2c6ba4216844 ("PCI: hv: Enable PCI pass-thru devices in Confidential VMs") update the Hyper-V virtual PCI driver to use the hyperv_pcpu_input_arg because that memory will be correctly marked as decrypted or encrypted for all VM types (CoCo or normal). But problems ensue when CPUs in the VM go online or offline after virtual PCI devices have been configured. When a CPU is brought online, the hyperv_pcpu_input_arg for that CPU is initialized by hv_cpu_init() running under state CPUHP_AP_ONLINE_DYN. But this state occurs after state CPUHP_AP_IRQ_AFFINITY_ONLINE, which may call the virtual PCI driver and fault trying to use the as yet uninitialized hyperv_pcpu_input_arg. A similar problem occurs in a CoCo VM if the MMIO read and write hypercalls are used from state CPUHP_AP_IRQ_AFFINITY_ONLINE. When a CPU is taken offline, IRQs may be reassigned in state CPUHP_TEARDOWN_CPU. Again, the virtual PCI driver may fault trying to use the hyperv_pcpu_input_arg that has already been freed by a higher state. Fix the onlining problem by adding state CPUHP_AP_HYPERV_ONLINE immediately after CPUHP_AP_ONLINE_IDLE (similar to CPUHP_AP_KVM_ONLINE) and before CPUHP_AP_IRQ_AFFINITY_ONLINE. Use this new state for Hyper-V initialization so that hyperv_pcpu_input_arg is allocated early enough. Fix the offlining problem by not freeing hyperv_pcpu_input_arg when a CPU goes offline. Retain the allocated memory, and reuse it if the CPU comes back online later. Signed-off-by: Michael Kelley Reviewed-by: Vitaly Kuznetsov Acked-by: Borislav Petkov (AMD) Reviewed-by: Dexuan Cui Link: https://lore.kernel.org/r/1684862062-51576-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu

cpu/hotplug: Allow "parallel" bringup up to CPUHP_BP_KICK_AP_STATE

2023-05-15T11:45:02+00:00

There is often significant latency in the early stages of CPU bringup, and time is wasted by waking each CPU (e.g. with SIPI/INIT/INIT on x86) and then waiting for it to respond before moving on to the next. Allow a platform to enable parallel setup which brings all to be onlined CPUs up to the CPUHP_BP_KICK_AP state. While this state advancement on the control CPU (BP) is single-threaded the important part is the last state CPUHP_BP_KICK_AP which wakes the to be onlined CPUs up. This allows the CPUs to run up to the first sychronization point cpuhp_ap_sync_alive() where they wait for the control CPU to release them one by one for the full onlining procedure. This parallelism depends on the CPU hotplug core sync mechanism which ensures that the parallel brought up CPUs wait for release before touching any state which would make the CPU visible to anything outside the hotplug control mechanism. To handle the SMT constraints of X86 correctly the bringup happens in two iterations when CONFIG_HOTPLUG_SMT is enabled. The control CPU brings up the primary SMT threads of each core first, which can load the microcode without the need to rendevouz with the thread siblings. Once that's completed it brings up the secondary SMT threads. Co-developed-by: David Woodhouse Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205257.240231377@linutronix.de

cpu/hotplug: Provide a split up CPUHP_BRINGUP mechanism

2023-05-15T11:45:01+00:00

The bring up logic of a to be onlined CPU consists of several parts, which are considered to be a single hotplug state: 1) Control CPU issues the wake-up 2) To be onlined CPU starts up, does the minimal initialization, reports to be alive and waits for release into the complete bring-up. 3) Control CPU waits for the alive report and releases the upcoming CPU for the complete bring-up. Allow to split this into two states: 1) Control CPU issues the wake-up After that the to be onlined CPU starts up, does the minimal initialization, reports to be alive and waits for release into the full bring-up. As this can run after the control CPU dropped the hotplug locks the code which is executed on the AP before it reports alive has to be carefully audited to not violate any of the hotplug constraints, especially not modifying any of the various cpumasks. This is really only meant to avoid waiting for the AP to react on the wake-up. Of course an architecture can move strict CPU related setup functionality, e.g. microcode loading, with care before the synchronization point to save further pointless waiting time. 2) Control CPU waits for the alive report and releases the upcoming CPU for the complete bring-up. This allows that the two states can be split up to run all to be onlined CPUs up to state #1 on the control CPU and then at a later point run state #2. This spares some of the latencies of the full serialized per CPU bringup by avoiding the per CPU wakeup/wait serialization. The assumption is that the first AP already waits when the last AP has been woken up. This obvioulsy depends on the hardware latencies and depending on the timings this might still not completely eliminate all wait scenarios. This split is just a preparatory step for enabling the parallel bringup later. The boot time bringup is still fully serialized. It has a separate config switch so that architectures which want to support parallel bringup can test the split of the CPUHP_BRINGUG step separately. To enable this the architecture must support the CPU hotplug core sync mechanism and has to be audited that there are no implicit hotplug state dependencies which require a fully serialized bringup. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205257.080801387@linutronix.de

cpu/hotplug: Add CPU state tracking and synchronization

2023-05-15T11:44:55+00:00

The CPU state tracking and synchronization mechanism in smpboot.c is completely independent of the hotplug code and all logic around it is implemented in architecture specific code. Except for the state reporting of the AP there is absolutely nothing architecture specific and the sychronization and decision functions can be moved into the generic hotplug core code. Provide an integrated variant and add the core synchronization and decision points. This comes in two flavours: 1) DEAD state synchronization Updated by the architecture code once the AP reaches the point where it is ready to be torn down by the control CPU, e.g. by removing power or clocks or tear down via the hypervisor. The control CPU waits for this state to be reached with a timeout. If the state is reached an architecture specific cleanup function is invoked. 2) Full state synchronization This extends #1 with AP alive synchronization. This is new functionality, which allows to replace architecture specific wait mechanims, e.g. cpumasks, completely. It also prevents that an AP which is in a limbo state can be brought up again. This can happen when an AP failed to report dead state during a previous off-line operation. The dead synchronization is what most architectures use. Only x86 makes a bringup decision based on that state at the moment. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205256.476305035@linutronix.de

Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

2023-04-25T19:39:01+00:00

Pull arm64 updates from Will Deacon: "ACPI: - Improve error reporting when failing to manage SDEI on AGDI device removal Assembly routines: - Improve register constraints so that the compiler can make use of the zero register instead of moving an immediate #0 into a GPR - Allow the compiler to allocate the registers used for CAS instructions CPU features and system registers: - Cleanups to the way in which CPU features are identified from the ID register fields - Extend system register definition generation to handle Enum types when defining shared register fields - Generate definitions for new _EL2 registers and add new fields for ID_AA64PFR1_EL1 - Allow SVE to be disabled separately from SME on the kernel command-line Tracing: - Support for "direct calls" in ftrace, which enables BPF tracing for arm64 Kdump: - Don't bother unmapping the crashkernel from the linear mapping, which then allows us to use huge (block) mappings and reduce TLB pressure when a crashkernel is loaded. Memory management: - Try again to remove data cache invalidation from the coherent DMA allocation path - Simplify the fixmap code by mapping at page granularity - Allow the kfence pool to be allocated early, preventing the rest of the linear mapping from being forced to page granularity Perf and PMU: - Move CPU PMU code out to drivers/perf/ where it can be reused by the 32-bit ARM architecture when running on ARMv8 CPUs - Fix race between CPU PMU probing and pKVM host de-privilege - Add support for Apple M2 CPU PMU - Adjust the generic PERF_COUNT_HW_BRANCH_INSTRUCTIONS event dynamically, depending on what the CPU actually supports - Minor fixes and cleanups to system PMU drivers Stack tracing: - Use the XPACLRI instruction to strip PAC from pointers, rather than rolling our own function in C - Remove redundant PAC removal for toolchains that handle this in their builtins - Make backtracing more resilient in the face of instrumentation Miscellaneous: - Fix single-step with KGDB - Remove harmless warning when 'nokaslr' is passed on the kernel command-line - Minor fixes and cleanups across the board" * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (72 commits) KVM: arm64: Ensure CPU PMU probes before pKVM host de-privilege arm64: kexec: include reboot.h arm64: delete dead code in this_cpu_set_vectors() arm64/cpufeature: Use helper macro to specify ID register for capabilites drivers/perf: hisi: add NULL check for name drivers/perf: hisi: Remove redundant initialized of pmu->name arm64/cpufeature: Consistently use symbolic constants for min_field_value arm64/cpufeature: Pull out helper for CPUID register definitions arm64/sysreg: Convert HFGITR_EL2 to automatic generation ACPI: AGDI: Improve error reporting for problems during .remove() arm64: kernel: Fix kernel warning when nokaslr is passed to commandline perf/arm-cmn: Fix port detection for CMN-700 arm64: kgdb: Set PSTATE.SS to 1 to re-enable single-step arm64: move PAC masks to arm64: use XPACLRI to strip PAC arm64: avoid redundant PAC stripping in __builtin_return_address() arm64/sme: Fix some comments of ARM SME arm64/signal: Alloc tpidr2 sigframe after checking system_supports_tpidr2() arm64/signal: Use system_supports_tpidr2() to check TPIDR2 arm64/idreg: Don't disable SME when disabling SVE ...