1
0
Fork 0
alistair23-linux/arch/arm64/kernel/smp.c

1055 lines
23 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* SMP initialisation and IPI support
* Based on arch/arm/kernel/smp.c
*
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/acpi.h>
arm64: kernel: Add arch-specific SDEI entry code and CPU masking The Software Delegated Exception Interface (SDEI) is an ARM standard for registering callbacks from the platform firmware into the OS. This is typically used to implement RAS notifications. Such notifications enter the kernel at the registered entry-point with the register values of the interrupted CPU context. Because this is not a CPU exception, it cannot reuse the existing entry code. (crucially we don't implicitly know which exception level we interrupted), Add the entry point to entry.S to set us up for calling into C code. If the event interrupted code that had interrupts masked, we always return to that location. Otherwise we pretend this was an IRQ, and use SDEI's complete_and_resume call to return to vbar_el1 + offset. This allows the kernel to deliver signals to user space processes. For KVM this triggers the world switch, a quick spin round vcpu_run, then back into the guest, unless there are pending signals. Add sdei_mask_local_cpu() calls to the smp_send_stop() code, this covers the panic() code-path, which doesn't invoke cpuhotplug notifiers. Because we can interrupt entry-from/exit-to another EL, we can't trust the value in sp_el0 or x29, even if we interrupted the kernel, in this case the code in entry.S will save/restore sp_el0 and use the value in __entry_task. When we have VMAP stacks we can interrupt the stack-overflow test, which stirs x0 into sp, meaning we have to have our own VMAP stacks. For now these are allocated when we probe the interface. Future patches will add refcounting hooks to allow the arch code to allocate them lazily. Signed-off-by: James Morse <james.morse@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-01-08 08:38:12 -07:00
#include <linux/arm_sdei.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
sched/headers: Move task->mm handling methods to <linux/sched/mm.h> Move the following task->mm helper APIs into a new header file, <linux/sched/mm.h>, to further reduce the size and complexity of <linux/sched.h>. Here are how the APIs are used in various kernel files: # mm_alloc(): arch/arm/mach-rpc/ecard.c fs/exec.c include/linux/sched/mm.h kernel/fork.c # __mmdrop(): arch/arc/include/asm/mmu_context.h include/linux/sched/mm.h kernel/fork.c # mmdrop(): arch/arm/mach-rpc/ecard.c arch/m68k/sun3/mmu_emu.c arch/x86/mm/tlb.c drivers/gpu/drm/amd/amdkfd/kfd_process.c drivers/gpu/drm/i915/i915_gem_userptr.c drivers/infiniband/hw/hfi1/file_ops.c drivers/vfio/vfio_iommu_spapr_tce.c fs/exec.c fs/proc/base.c fs/proc/task_mmu.c fs/proc/task_nommu.c fs/userfaultfd.c include/linux/mmu_notifier.h include/linux/sched/mm.h kernel/fork.c kernel/futex.c kernel/sched/core.c mm/khugepaged.c mm/ksm.c mm/mmu_context.c mm/mmu_notifier.c mm/oom_kill.c virt/kvm/kvm_main.c # mmdrop_async_fn(): include/linux/sched/mm.h # mmdrop_async(): include/linux/sched/mm.h kernel/fork.c # mmget_not_zero(): fs/userfaultfd.c include/linux/sched/mm.h mm/oom_kill.c # mmput(): arch/arc/include/asm/mmu_context.h arch/arc/kernel/troubleshoot.c arch/frv/mm/mmu-context.c arch/powerpc/platforms/cell/spufs/context.c arch/sparc/include/asm/mmu_context_32.h drivers/android/binder.c drivers/gpu/drm/etnaviv/etnaviv_gem.c drivers/gpu/drm/i915/i915_gem_userptr.c drivers/infiniband/core/umem.c drivers/infiniband/core/umem_odp.c drivers/infiniband/core/uverbs_main.c drivers/infiniband/hw/mlx4/main.c drivers/infiniband/hw/mlx5/main.c drivers/infiniband/hw/usnic/usnic_uiom.c drivers/iommu/amd_iommu_v2.c drivers/iommu/intel-svm.c drivers/lguest/lguest_user.c drivers/misc/cxl/fault.c drivers/misc/mic/scif/scif_rma.c drivers/oprofile/buffer_sync.c drivers/vfio/vfio_iommu_type1.c drivers/vhost/vhost.c drivers/xen/gntdev.c fs/exec.c fs/proc/array.c fs/proc/base.c fs/proc/task_mmu.c fs/proc/task_nommu.c fs/userfaultfd.c include/linux/sched/mm.h kernel/cpuset.c kernel/events/core.c kernel/events/uprobes.c kernel/exit.c kernel/fork.c kernel/ptrace.c kernel/sys.c kernel/trace/trace_output.c kernel/tsacct.c mm/memcontrol.c mm/memory.c mm/mempolicy.c mm/migrate.c mm/mmu_notifier.c mm/nommu.c mm/oom_kill.c mm/process_vm_access.c mm/rmap.c mm/swapfile.c mm/util.c virt/kvm/async_pf.c # mmput_async(): include/linux/sched/mm.h kernel/fork.c mm/oom_kill.c # get_task_mm(): arch/arc/kernel/troubleshoot.c arch/powerpc/platforms/cell/spufs/context.c drivers/android/binder.c drivers/gpu/drm/etnaviv/etnaviv_gem.c drivers/infiniband/core/umem.c drivers/infiniband/core/umem_odp.c drivers/infiniband/hw/mlx4/main.c drivers/infiniband/hw/mlx5/main.c drivers/infiniband/hw/usnic/usnic_uiom.c drivers/iommu/amd_iommu_v2.c drivers/iommu/intel-svm.c drivers/lguest/lguest_user.c drivers/misc/cxl/fault.c drivers/misc/mic/scif/scif_rma.c drivers/oprofile/buffer_sync.c drivers/vfio/vfio_iommu_type1.c drivers/vhost/vhost.c drivers/xen/gntdev.c fs/proc/array.c fs/proc/base.c fs/proc/task_mmu.c include/linux/sched/mm.h kernel/cpuset.c kernel/events/core.c kernel/exit.c kernel/fork.c kernel/ptrace.c kernel/sys.c kernel/trace/trace_output.c kernel/tsacct.c mm/memcontrol.c mm/memory.c mm/mempolicy.c mm/migrate.c mm/mmu_notifier.c mm/nommu.c mm/util.c # mm_access(): fs/proc/base.c include/linux/sched/mm.h kernel/fork.c mm/process_vm_access.c # mm_release(): arch/arc/include/asm/mmu_context.h fs/exec.c include/linux/sched/mm.h include/uapi/linux/sched.h kernel/exit.c kernel/fork.c Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-02-01 11:08:20 -07:00
#include <linux/sched/mm.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task_stack.h>
#include <linux/interrupt.h>
#include <linux/cache.h>
#include <linux/profile.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/seq_file.h>
#include <linux/irq.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <linux/percpu.h>
#include <linux/clockchips.h>
#include <linux/completion.h>
#include <linux/of.h>
#include <linux/irq_work.h>
#include <linux/kexec.h>
#include <asm/alternative.h>
#include <asm/atomic.h>
#include <asm/cacheflush.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/cpu_ops.h>
#include <asm/daifflags.h>
#include <asm/mmu_context.h>
#include <asm/numa.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/processor.h>
#include <asm/smp_plat.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/ptrace.h>
#include <asm/virt.h>
#define CREATE_TRACE_POINTS
#include <trace/events/ipi.h>
DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
EXPORT_PER_CPU_SYMBOL(cpu_number);
/*
* as from 2.5, kernels no longer have an init_tasks structure
* so we need some other way of telling a new secondary core
* where to place its SVC stack
*/
struct secondary_data secondary_data;
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
/* Number of CPUs which aren't online, but looping in kernel text. */
int cpus_stuck_in_kernel;
enum ipi_msg_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
IPI_CPU_STOP,
IPI_CPU_CRASH_STOP,
IPI_TIMER,
IPI_IRQ_WORK,
arm64: kernel: implement ACPI parking protocol The SBBR and ACPI specifications allow ACPI based systems that do not implement PSCI (eg systems with no EL3) to boot through the ACPI parking protocol specification[1]. This patch implements the ACPI parking protocol CPU operations, and adds code that eases parsing the parking protocol data structures to the ARM64 SMP initializion carried out at the same time as cpus enumeration. To wake-up the CPUs from the parked state, this patch implements a wakeup IPI for ARM64 (ie arch_send_wakeup_ipi_mask()) that mirrors the ARM one, so that a specific IPI is sent for wake-up purpose in order to distinguish it from other IPI sources. Given the current ACPI MADT parsing API, the patch implements a glue layer that helps passing MADT GICC data structure from SMP initialization code to the parking protocol implementation somewhat overriding the CPU operations interfaces. This to avoid creating a completely trasparent DT/ACPI CPU operations layer that would require creating opaque structure handling for CPUs data (DT represents CPU through DT nodes, ACPI through static MADT table entries), which seems overkill given that ACPI on ARM64 mandates only two booting protocols (PSCI and parking protocol), so there is no need for further protocol additions. Based on the original work by Mark Salter <msalter@redhat.com> [1] https://acpica.org/sites/acpica/files/MP%20Startup%20for%20ARM%20platforms.docx Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Loc Ho <lho@apm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Hanjun Guo <hanjun.guo@linaro.org> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mark Salter <msalter@redhat.com> Cc: Al Stone <ahs3@redhat.com> [catalin.marinas@arm.com: Added WARN_ONCE(!acpi_parking_protocol_valid() on the IPI] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-01-26 04:10:38 -07:00
IPI_WAKEUP
};
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
#ifdef CONFIG_HOTPLUG_CPU
static int op_cpu_kill(unsigned int cpu);
#else
static inline int op_cpu_kill(unsigned int cpu)
{
return -ENOSYS;
}
#endif
/*
* Boot a secondary CPU, and assign it the specified idle task.
* This also gives us the initial stack to use for this CPU.
*/
2013-06-18 08:18:31 -06:00
static int boot_secondary(unsigned int cpu, struct task_struct *idle)
{
if (cpu_ops[cpu]->cpu_boot)
return cpu_ops[cpu]->cpu_boot(cpu);
return -EOPNOTSUPP;
}
static DECLARE_COMPLETION(cpu_running);
2013-06-18 08:18:31 -06:00
int __cpu_up(unsigned int cpu, struct task_struct *idle)
{
int ret;
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
long status;
/*
* We need to tell the secondary core where to find its stack and the
* page tables.
*/
arm64: split thread_info from task stack This patch moves arm64's struct thread_info from the task stack into task_struct. This protects thread_info from corruption in the case of stack overflows, and makes its address harder to determine if stack addresses are leaked, making a number of attacks more difficult. Precise detection and handling of overflow is left for subsequent patches. Largely, this involves changing code to store the task_struct in sp_el0, and acquire the thread_info from the task struct. Core code now implements current_thread_info(), and as noted in <linux/sched.h> this relies on offsetof(task_struct, thread_info) == 0, enforced by core code. This change means that the 'tsk' register used in entry.S now points to a task_struct, rather than a thread_info as it used to. To make this clear, the TI_* field offsets are renamed to TSK_TI_*, with asm-offsets appropriately updated to account for the structural change. Userspace clobbers sp_el0, and we can no longer restore this from the stack. Instead, the current task is cached in a per-cpu variable that we can safely access from early assembly as interrupts are disabled (and we are thus not preemptible). Both secondary entry and idle are updated to stash the sp and task pointer separately. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Laura Abbott <labbott@redhat.com> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: James Morse <james.morse@arm.com> Cc: Kees Cook <keescook@chromium.org> Cc: Suzuki K Poulose <suzuki.poulose@arm.com> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-11-03 14:23:13 -06:00
secondary_data.task = idle;
arm64: kernel: remove {THREAD,IRQ_STACK}_START_SP For historical reasons, we leave the top 16 bytes of our task and IRQ stacks unused, a practice used to ensure that the SP can always be masked to find the base of the current stack (historically, where thread_info could be found). However, this is not necessary, as: * When an exception is taken from a task stack, we decrement the SP by S_FRAME_SIZE and stash the exception registers before we compare the SP against the task stack. In such cases, the SP must be at least S_FRAME_SIZE below the limit, and can be safely masked to determine whether the task stack is in use. * When transitioning to an IRQ stack, we'll place a dummy frame onto the IRQ stack before enabling asynchronous exceptions, or executing code we expect to trigger faults. Thus, if an exception is taken from the IRQ stack, the SP must be at least 16 bytes below the limit. * We no longer mask the SP to find the thread_info, which is now found via sp_el0. Note that historically, the offset was critical to ensure that cpu_switch_to() found the correct stack for new threads that hadn't yet executed ret_from_fork(). Given that, this initial offset serves no purpose, and can be removed. This brings us in-line with other architectures (e.g. x86) which do not rely on this masking. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> [Mark: rebase, kill THREAD_START_SP, commit msg additions] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Will Deacon <will.deacon@arm.com> Tested-by: Laura Abbott <labbott@redhat.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: James Morse <james.morse@arm.com>
2017-07-20 10:15:45 -06:00
secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
update_cpu_boot_status(CPU_MMU_OFF);
__flush_dcache_area(&secondary_data, sizeof(secondary_data));
/*
* Now bring the CPU into our world.
*/
ret = boot_secondary(cpu, idle);
if (ret == 0) {
/*
* CPU was successfully started, wait for it to come online or
* time out.
*/
wait_for_completion_timeout(&cpu_running,
msecs_to_jiffies(1000));
if (!cpu_online(cpu)) {
pr_crit("CPU%u: failed to come online\n", cpu);
ret = -EIO;
}
} else {
pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
return ret;
}
arm64: split thread_info from task stack This patch moves arm64's struct thread_info from the task stack into task_struct. This protects thread_info from corruption in the case of stack overflows, and makes its address harder to determine if stack addresses are leaked, making a number of attacks more difficult. Precise detection and handling of overflow is left for subsequent patches. Largely, this involves changing code to store the task_struct in sp_el0, and acquire the thread_info from the task struct. Core code now implements current_thread_info(), and as noted in <linux/sched.h> this relies on offsetof(task_struct, thread_info) == 0, enforced by core code. This change means that the 'tsk' register used in entry.S now points to a task_struct, rather than a thread_info as it used to. To make this clear, the TI_* field offsets are renamed to TSK_TI_*, with asm-offsets appropriately updated to account for the structural change. Userspace clobbers sp_el0, and we can no longer restore this from the stack. Instead, the current task is cached in a per-cpu variable that we can safely access from early assembly as interrupts are disabled (and we are thus not preemptible). Both secondary entry and idle are updated to stash the sp and task pointer separately. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Laura Abbott <labbott@redhat.com> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: James Morse <james.morse@arm.com> Cc: Kees Cook <keescook@chromium.org> Cc: Suzuki K Poulose <suzuki.poulose@arm.com> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-11-03 14:23:13 -06:00
secondary_data.task = NULL;
secondary_data.stack = NULL;
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
status = READ_ONCE(secondary_data.status);
if (ret && status) {
if (status == CPU_MMU_OFF)
status = READ_ONCE(__early_cpu_boot_status);
switch (status & CPU_BOOT_STATUS_MASK) {
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
default:
pr_err("CPU%u: failed in unknown state : 0x%lx\n",
cpu, status);
break;
case CPU_KILL_ME:
if (!op_cpu_kill(cpu)) {
pr_crit("CPU%u: died during early boot\n", cpu);
break;
}
/* Fall through */
pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
case CPU_STUCK_IN_KERNEL:
pr_crit("CPU%u: is stuck in kernel\n", cpu);
if (status & CPU_STUCK_REASON_52_BIT_VA)
pr_crit("CPU%u: does not support 52-bit VAs\n", cpu);
if (status & CPU_STUCK_REASON_NO_GRAN)
pr_crit("CPU%u: does not support %luK granule \n", cpu, PAGE_SIZE / SZ_1K);
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
cpus_stuck_in_kernel++;
break;
case CPU_PANIC_KERNEL:
panic("CPU%u detected unsupported configuration\n", cpu);
}
}
return ret;
}
static void init_gic_priority_masking(void)
{
u32 cpuflags;
if (WARN_ON(!gic_enable_sre()))
return;
cpuflags = read_sysreg(daif);
WARN_ON(!(cpuflags & PSR_I_BIT));
arm64: fix kernel stack overflow in kdump capture kernel When enabling ARM64_PSEUDO_NMI feature in kdump capture kernel, it will report a kernel stack overflow exception: [ 0.000000] CPU features: detected: IRQ priority masking [ 0.000000] alternatives: patching kernel code [ 0.000000] Insufficient stack space to handle exception! [ 0.000000] ESR: 0x96000044 -- DABT (current EL) [ 0.000000] FAR: 0x0000000000000040 [ 0.000000] Task stack: [0xffff0000097f0000..0xffff0000097f4000] [ 0.000000] IRQ stack: [0x0000000000000000..0x0000000000004000] [ 0.000000] Overflow stack: [0xffff80002b7cf290..0xffff80002b7d0290] [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 4.19.34-lw+ #3 [ 0.000000] pstate: 400003c5 (nZcv DAIF -PAN -UAO) [ 0.000000] pc : el1_sync+0x0/0xb8 [ 0.000000] lr : el1_irq+0xb8/0x140 [ 0.000000] sp : 0000000000000040 [ 0.000000] pmr_save: 00000070 [ 0.000000] x29: ffff0000097f3f60 x28: ffff000009806240 [ 0.000000] x27: 0000000080000000 x26: 0000000000004000 [ 0.000000] x25: 0000000000000000 x24: ffff000009329028 [ 0.000000] x23: 0000000040000005 x22: ffff000008095c6c [ 0.000000] x21: ffff0000097f3f70 x20: 0000000000000070 [ 0.000000] x19: ffff0000097f3e30 x18: ffffffffffffffff [ 0.000000] x17: 0000000000000000 x16: 0000000000000000 [ 0.000000] x15: ffff0000097f9708 x14: ffff000089a382ef [ 0.000000] x13: ffff000009a382fd x12: ffff000009824000 [ 0.000000] x11: ffff0000097fb7b0 x10: ffff000008730028 [ 0.000000] x9 : ffff000009440018 x8 : 000000000000000d [ 0.000000] x7 : 6b20676e69686374 x6 : 000000000000003b [ 0.000000] x5 : 0000000000000000 x4 : ffff000008093600 [ 0.000000] x3 : 0000000400000008 x2 : 7db2e689fc2b8e00 [ 0.000000] x1 : 0000000000000000 x0 : ffff0000097f3e30 [ 0.000000] Kernel panic - not syncing: kernel stack overflow [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 4.19.34-lw+ #3 [ 0.000000] Call trace: [ 0.000000] dump_backtrace+0x0/0x1b8 [ 0.000000] show_stack+0x24/0x30 [ 0.000000] dump_stack+0xa8/0xcc [ 0.000000] panic+0x134/0x30c [ 0.000000] __stack_chk_fail+0x0/0x28 [ 0.000000] handle_bad_stack+0xfc/0x108 [ 0.000000] __bad_stack+0x90/0x94 [ 0.000000] el1_sync+0x0/0xb8 [ 0.000000] init_gic_priority_masking+0x4c/0x70 [ 0.000000] smp_prepare_boot_cpu+0x60/0x68 [ 0.000000] start_kernel+0x1e8/0x53c [ 0.000000] ---[ end Kernel panic - not syncing: kernel stack overflow ]--- The reason is init_gic_priority_masking() may unmask PSR.I while the irq stacks are not inited yet. Some "NMI" could be raised unfortunately and it will just go into this exception. In this patch, we just write the PMR in smp_prepare_boot_cpu(), and delay unmasking PSR.I after irq stacks inited in init_IRQ(). Fixes: e79321883842 ("arm64: Switch to PMR masking when starting CPUs") Cc: Will Deacon <will.deacon@arm.com> Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Wei Li <liwei391@huawei.com> [JT: make init_gic_priority_masking() not modify daif, rebase on other priority masking fixes] Signed-off-by: Julien Thierry <julien.thierry@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-06-11 03:38:12 -06:00
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
}
/*
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
*/
asmlinkage notrace void secondary_start_kernel(void)
{
u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
struct mm_struct *mm = &init_mm;
unsigned int cpu;
cpu = task_cpu(current);
set_my_cpu_offset(per_cpu_offset(cpu));
/*
* All kernel threads share the same mm context; grab a
* reference and switch to it.
*/
mmgrab(mm);
current->active_mm = mm;
/*
* TTBR0 is only used for the identity mapping at this stage. Make it
* point to zero page to avoid speculatively fetching new entries.
*/
cpu_uninstall_idmap();
if (system_uses_irq_prio_masking())
init_gic_priority_masking();
preempt_disable();
trace_hardirqs_off();
arm64: Delay cpu feature capability checks At the moment we run through the arm64_features capability list for each CPU and set the capability if one of the CPU supports it. This could be problematic in a heterogeneous system with differing capabilities. Delay the CPU feature checks until all the enabled CPUs are up(i.e, smp_cpus_done(), so that we can make better decisions based on the overall system capability. Once we decide and advertise the capabilities the alternatives can be applied. From this state, we cannot roll back a feature to disabled based on the values from a new hotplugged CPU, due to the runtime patching and other reasons. So, for all new CPUs, we need to make sure that they have the established system capabilities. Failing which, we bring the CPU down, preventing it from turning online. Once the capabilities are decided, any new CPU booting up goes through verification to ensure that it has all the enabled capabilities and also invokes the respective enable() method on the CPU. The CPU errata checks are not delayed and is still executed per-CPU to detect the respective capabilities. If we ever come across a non-errata capability that needs to be checked on each-CPU, we could introduce them via a new capability table(or introduce a flag), which can be processed per CPU. The next patch will make the feature checks use the system wide safe value of a feature register. NOTE: The enable() methods associated with the capability is scheduled on all the CPUs (which is the only use case at the moment). If we need a different type of 'enable()' which only needs to be run once on any CPU, we should be able to handle that when needed. Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com> Tested-by: Dave Martin <Dave.Martin@arm.com> [catalin.marinas@arm.com: static variable and coding style fixes] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-10-19 07:24:50 -06:00
/*
* If the system has established the capabilities, make sure
* this CPU ticks all of those. If it doesn't, the CPU will
* fail to come online.
*/
arm64: Rearrange CPU errata workaround checks Right now we run through the work around checks on a CPU from __cpuinfo_store_cpu. There are some problems with that: 1) We initialise the system wide CPU feature registers only after the Boot CPU updates its cpuinfo. Now, if a work around depends on the variance of a CPU ID feature (e.g, check for Cache Line size mismatch), we have no way of performing it cleanly for the boot CPU. 2) It is out of place, invoked from __cpuinfo_store_cpu() in cpuinfo.c. It is not an obvious place for that. This patch rearranges the CPU specific capability(aka work around) checks. 1) At the moment we use verify_local_cpu_capabilities() to check if a new CPU has all the system advertised features. Use this for the secondary CPUs to perform the work around check. For that we rename verify_local_cpu_capabilities() => check_local_cpu_capabilities() which: If the system wide capabilities haven't been initialised (i.e, the CPU is activated at the boot), update the system wide detected work arounds. Otherwise (i.e a CPU hotplugged in later) verify that this CPU conforms to the system wide capabilities. 2) Boot CPU updates the work arounds from smp_prepare_boot_cpu() after we have initialised the system wide CPU feature values. Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andre Przywara <andre.przywara@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-09-09 07:07:10 -06:00
check_local_cpu_capabilities();
arm64: Delay cpu feature capability checks At the moment we run through the arm64_features capability list for each CPU and set the capability if one of the CPU supports it. This could be problematic in a heterogeneous system with differing capabilities. Delay the CPU feature checks until all the enabled CPUs are up(i.e, smp_cpus_done(), so that we can make better decisions based on the overall system capability. Once we decide and advertise the capabilities the alternatives can be applied. From this state, we cannot roll back a feature to disabled based on the values from a new hotplugged CPU, due to the runtime patching and other reasons. So, for all new CPUs, we need to make sure that they have the established system capabilities. Failing which, we bring the CPU down, preventing it from turning online. Once the capabilities are decided, any new CPU booting up goes through verification to ensure that it has all the enabled capabilities and also invokes the respective enable() method on the CPU. The CPU errata checks are not delayed and is still executed per-CPU to detect the respective capabilities. If we ever come across a non-errata capability that needs to be checked on each-CPU, we could introduce them via a new capability table(or introduce a flag), which can be processed per CPU. The next patch will make the feature checks use the system wide safe value of a feature register. NOTE: The enable() methods associated with the capability is scheduled on all the CPUs (which is the only use case at the moment). If we need a different type of 'enable()' which only needs to be run once on any CPU, we should be able to handle that when needed. Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com> Tested-by: Dave Martin <Dave.Martin@arm.com> [catalin.marinas@arm.com: static variable and coding style fixes] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-10-19 07:24:50 -06:00
if (cpu_ops[cpu]->cpu_postboot)
cpu_ops[cpu]->cpu_postboot();
/*
* Log the CPU info before it is marked online and might get read.
*/
cpuinfo_store_cpu();
/*
* Enable GIC and timers.
*/
notify_cpu_starting(cpu);
arm64: Call numa_store_cpu_info() earlier. The wq_numa_init() function makes a private CPU to node map by calling cpu_to_node() early in the boot process, before the non-boot CPUs are brought online. Since the default implementation of cpu_to_node() returns zero for CPUs that have never been brought online, the workqueue system's view is that *all* CPUs are on node zero. When the unbound workqueue for a non-zero node is created, the tsk_cpus_allowed() for the worker threads is the empty set because there are, in the view of the workqueue system, no CPUs on non-zero nodes. The code in try_to_wake_up() using this empty cpumask ends up using the cpumask empty set value of NR_CPUS as an index into the per-CPU area pointer array, and gets garbage as it is one past the end of the array. This results in: [ 0.881970] Unable to handle kernel paging request at virtual address fffffb1008b926a4 [ 1.970095] pgd = fffffc00094b0000 [ 1.973530] [fffffb1008b926a4] *pgd=0000000000000000, *pud=0000000000000000, *pmd=0000000000000000 [ 1.982610] Internal error: Oops: 96000004 [#1] SMP [ 1.987541] Modules linked in: [ 1.990631] CPU: 48 PID: 295 Comm: cpuhp/48 Tainted: G W 4.8.0-rc6-preempt-vol+ #9 [ 1.999435] Hardware name: Cavium ThunderX CN88XX board (DT) [ 2.005159] task: fffffe0fe89cc300 task.stack: fffffe0fe8b8c000 [ 2.011158] PC is at try_to_wake_up+0x194/0x34c [ 2.015737] LR is at try_to_wake_up+0x150/0x34c [ 2.020318] pc : [<fffffc00080e7468>] lr : [<fffffc00080e7424>] pstate: 600000c5 [ 2.027803] sp : fffffe0fe8b8fb10 [ 2.031149] x29: fffffe0fe8b8fb10 x28: 0000000000000000 [ 2.036522] x27: fffffc0008c63bc8 x26: 0000000000001000 [ 2.041896] x25: fffffc0008c63c80 x24: fffffc0008bfb200 [ 2.047270] x23: 00000000000000c0 x22: 0000000000000004 [ 2.052642] x21: fffffe0fe89d25bc x20: 0000000000001000 [ 2.058014] x19: fffffe0fe89d1d00 x18: 0000000000000000 [ 2.063386] x17: 0000000000000000 x16: 0000000000000000 [ 2.068760] x15: 0000000000000018 x14: 0000000000000000 [ 2.074133] x13: 0000000000000000 x12: 0000000000000000 [ 2.079505] x11: 0000000000000000 x10: 0000000000000000 [ 2.084879] x9 : 0000000000000000 x8 : 0000000000000000 [ 2.090251] x7 : 0000000000000040 x6 : 0000000000000000 [ 2.095621] x5 : ffffffffffffffff x4 : 0000000000000000 [ 2.100991] x3 : 0000000000000000 x2 : 0000000000000000 [ 2.106364] x1 : fffffc0008be4c24 x0 : ffffff0ffffada80 [ 2.111737] [ 2.113236] Process cpuhp/48 (pid: 295, stack limit = 0xfffffe0fe8b8c020) [ 2.120102] Stack: (0xfffffe0fe8b8fb10 to 0xfffffe0fe8b90000) [ 2.125914] fb00: fffffe0fe8b8fb80 fffffc00080e7648 . . . [ 2.442859] Call trace: [ 2.445327] Exception stack(0xfffffe0fe8b8f940 to 0xfffffe0fe8b8fa70) [ 2.451843] f940: fffffe0fe89d1d00 0000040000000000 fffffe0fe8b8fb10 fffffc00080e7468 [ 2.459767] f960: fffffe0fe8b8f980 fffffc00080e4958 ffffff0ff91ab200 fffffc00080e4b64 [ 2.467690] f980: fffffe0fe8b8f9d0 fffffc00080e515c fffffe0fe8b8fa80 0000000000000000 [ 2.475614] f9a0: fffffe0fe8b8f9d0 fffffc00080e58e4 fffffe0fe8b8fa80 0000000000000000 [ 2.483540] f9c0: fffffe0fe8d10000 0000000000000040 fffffe0fe8b8fa50 fffffc00080e5ac4 [ 2.491465] f9e0: ffffff0ffffada80 fffffc0008be4c24 0000000000000000 0000000000000000 [ 2.499387] fa00: 0000000000000000 ffffffffffffffff 0000000000000000 0000000000000040 [ 2.507309] fa20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 2.515233] fa40: 0000000000000000 0000000000000000 0000000000000000 0000000000000018 [ 2.523156] fa60: 0000000000000000 0000000000000000 [ 2.528089] [<fffffc00080e7468>] try_to_wake_up+0x194/0x34c [ 2.533723] [<fffffc00080e7648>] wake_up_process+0x28/0x34 [ 2.539275] [<fffffc00080d3764>] create_worker+0x110/0x19c [ 2.544824] [<fffffc00080d69dc>] alloc_unbound_pwq+0x3cc/0x4b0 [ 2.550724] [<fffffc00080d6bcc>] wq_update_unbound_numa+0x10c/0x1e4 [ 2.557066] [<fffffc00080d7d78>] workqueue_online_cpu+0x220/0x28c [ 2.563234] [<fffffc00080bd288>] cpuhp_invoke_callback+0x6c/0x168 [ 2.569398] [<fffffc00080bdf74>] cpuhp_up_callbacks+0x44/0xe4 [ 2.575210] [<fffffc00080be194>] cpuhp_thread_fun+0x13c/0x148 [ 2.581027] [<fffffc00080dfbac>] smpboot_thread_fn+0x19c/0x1a8 [ 2.586929] [<fffffc00080dbd64>] kthread+0xdc/0xf0 [ 2.591776] [<fffffc0008083380>] ret_from_fork+0x10/0x50 [ 2.597147] Code: b00057e1 91304021 91005021 b8626822 (b8606821) [ 2.603464] ---[ end trace 58c0cd36b88802bc ]--- [ 2.608138] Kernel panic - not syncing: Fatal exception Fix by moving call to numa_store_cpu_info() for all CPUs into smp_prepare_cpus(), which happens before wq_numa_init(). Since smp_store_cpu_info() now contains only a single function call, simplify by removing the function and out-lining its contents. Suggested-by: Robert Richter <rric@kernel.org> Fixes: 1a2db300348b ("arm64, numa: Add NUMA support for arm64 platforms.") Cc: <stable@vger.kernel.org> # 4.7.x- Signed-off-by: David Daney <david.daney@cavium.com> Reviewed-by: Robert Richter <rrichter@cavium.com> Tested-by: Yisheng Xie <xieyisheng1@huawei.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-09-20 12:46:35 -06:00
store_cpu_topology(cpu);
numa_add_cpu(cpu);
/*
* OK, now it's safe to let the boot CPU continue. Wait for
* the CPU migration code to notice that the CPU is online
* before we continue.
*/
pr_info("CPU%u: Booted secondary processor 0x%010lx [0x%08x]\n",
cpu, (unsigned long)mpidr,
read_cpuid_id());
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
update_cpu_boot_status(CPU_BOOT_SUCCESS);
set_cpu_online(cpu, true);
complete(&cpu_running);
local_daif_restore(DAIF_PROCCTX);
/*
* OK, it's off to the idle thread for us
*/
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
#ifdef CONFIG_HOTPLUG_CPU
static int op_cpu_disable(unsigned int cpu)
{
/*
* If we don't have a cpu_die method, abort before we reach the point
* of no return. CPU0 may not have an cpu_ops, so test for it.
*/
if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die)
return -EOPNOTSUPP;
/*
* We may need to abort a hot unplug for some other mechanism-specific
* reason.
*/
if (cpu_ops[cpu]->cpu_disable)
return cpu_ops[cpu]->cpu_disable(cpu);
return 0;
}
/*
* __cpu_disable runs on the processor to be shutdown.
*/
int __cpu_disable(void)
{
unsigned int cpu = smp_processor_id();
int ret;
ret = op_cpu_disable(cpu);
if (ret)
return ret;
remove_cpu_topology(cpu);
numa_remove_cpu(cpu);
/*
* Take this CPU offline. Once we clear this, we can't return,
* and we must not schedule until we're ready to give up the cpu.
*/
set_cpu_online(cpu, false);
/*
* OK - migrate IRQs away from this CPU
*/
irq_migrate_all_off_this_cpu();
return 0;
}
static int op_cpu_kill(unsigned int cpu)
{
/*
* If we have no means of synchronising with the dying CPU, then assume
* that it is really dead. We can only wait for an arbitrary length of
* time and hope that it's dead, so let's skip the wait and just hope.
*/
if (!cpu_ops[cpu]->cpu_kill)
return 0;
return cpu_ops[cpu]->cpu_kill(cpu);
}
/*
* called on the thread which is asking for a CPU to be shutdown -
* waits until shutdown has completed, or it is timed out.
*/
void __cpu_die(unsigned int cpu)
{
int err;
if (!cpu_wait_death(cpu, 5)) {
pr_crit("CPU%u: cpu didn't die\n", cpu);
return;
}
pr_notice("CPU%u: shutdown\n", cpu);
/*
* Now that the dying CPU is beyond the point of no return w.r.t.
* in-kernel synchronisation, try to get the firwmare to help us to
* verify that it has really left the kernel before we consider
* clobbering anything it might still be using.
*/
err = op_cpu_kill(cpu);
if (err)
pr_warn("CPU%d may not have shut down cleanly: %d\n",
cpu, err);
}
/*
* Called from the idle thread for the CPU which has been shutdown.
*
*/
void cpu_die(void)
{
unsigned int cpu = smp_processor_id();
idle_task_exit();
local_daif_mask();
/* Tell __cpu_die() that this CPU is now safe to dispose of */
(void)cpu_report_death();
/*
* Actually shutdown the CPU. This must never fail. The specific hotplug
* mechanism must perform all required cache maintenance to ensure that
* no dirty lines are lost in the process of shutting down the CPU.
*/
cpu_ops[cpu]->cpu_die(cpu);
BUG();
}
#endif
/*
* Kill the calling secondary CPU, early in bringup before it is turned
* online.
*/
void cpu_die_early(void)
{
int cpu = smp_processor_id();
pr_crit("CPU%d: will not boot\n", cpu);
/* Mark this CPU absent */
set_cpu_present(cpu, 0);
#ifdef CONFIG_HOTPLUG_CPU
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
update_cpu_boot_status(CPU_KILL_ME);
/* Check if we can park ourselves */
if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
cpu_ops[cpu]->cpu_die(cpu);
#endif
arm64: Handle early CPU boot failures A secondary CPU could fail to come online due to insufficient capabilities and could simply die or loop in the kernel. e.g, a CPU with no support for the selected kernel PAGE_SIZE loops in kernel with MMU turned off. or a hotplugged CPU which doesn't have one of the advertised system capability will die during the activation. There is no way to synchronise the status of the failing CPU back to the master. This patch solves the issue by adding a field to the secondary_data which can be updated by the failing CPU. If the secondary CPU fails even before turning the MMU on, it updates the status in a special variable reserved in the head.txt section to make sure that the update can be cache invalidated safely without possible sharing of cache write back granule. Here are the possible states : -1. CPU_MMU_OFF - Initial value set by the master CPU, this value indicates that the CPU could not turn the MMU on, hence the status could not be reliably updated in the secondary_data. Instead, the CPU has updated the status @ __early_cpu_boot_status. 0. CPU_BOOT_SUCCESS - CPU has booted successfully. 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the master CPU to synchronise by issuing a cpu_ops->cpu_kill. 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is looping in the kernel. This information could be used by say, kexec to check if it is really safe to do a kexec reboot. 3. CPU_PANIC_KERNEL - CPU detected some serious issues which requires kernel to crash immediately. The secondary CPU cannot call panic() until it has initialised the GIC. This flag can be used to instruct the master to do so. Cc: Mark Rutland <mark.rutland@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com> [catalin.marinas@arm.com: conflict resolution] [catalin.marinas@arm.com: converted "status" from int to long] [catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-02-23 03:31:42 -07:00
update_cpu_boot_status(CPU_STUCK_IN_KERNEL);
cpu_park_loop();
}
static void __init hyp_mode_check(void)
{
if (is_hyp_mode_available())
pr_info("CPU: All CPU(s) started at EL2\n");
else if (is_hyp_mode_mismatched())
WARN_TAINT(1, TAINT_CPU_OUT_OF_SPEC,
"CPU: CPUs started in inconsistent modes");
else
pr_info("CPU: All CPU(s) started at EL1\n");
}
void __init smp_cpus_done(unsigned int max_cpus)
{
pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
setup_cpu_features();
hyp_mode_check();
apply_alternatives_all();
mark_linear_text_alias_ro();
}
void __init smp_prepare_boot_cpu(void)
{
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
cpuinfo_store_boot_cpu();
/*
* We now know enough about the boot CPU to apply the
* alternatives that cannot wait until interrupt handling
* and/or scheduling is enabled.
*/
apply_boot_alternatives();
/* Conditionally switch to GIC PMR for interrupt masking */
if (system_uses_irq_prio_masking())
init_gic_priority_masking();
}
static u64 __init of_get_cpu_mpidr(struct device_node *dn)
{
const __be32 *cell;
u64 hwid;
/*
* A cpu node with missing "reg" property is
* considered invalid to build a cpu_logical_map
* entry.
*/
cell = of_get_property(dn, "reg", NULL);
if (!cell) {
pr_err("%pOF: missing reg property\n", dn);
return INVALID_HWID;
}
hwid = of_read_number(cell, of_n_addr_cells(dn));
/*
* Non affinity bits must be set to 0 in the DT
*/
if (hwid & ~MPIDR_HWID_BITMASK) {
pr_err("%pOF: invalid reg property\n", dn);
return INVALID_HWID;
}
return hwid;
}
/*
* Duplicate MPIDRs are a recipe for disaster. Scan all initialized
* entries and check for duplicates. If any is found just ignore the
* cpu. cpu_logical_map was initialized to INVALID_HWID to avoid
* matching valid MPIDR values.
*/
static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
{
unsigned int i;
for (i = 1; (i < cpu) && (i < NR_CPUS); i++)
if (cpu_logical_map(i) == hwid)
return true;
return false;
}
ARM64: kernel: make cpu_ops hooks DT agnostic ARM64 CPU operations such as cpu_init and cpu_init_idle take a struct device_node pointer as a parameter, which corresponds to the device tree node of the logical cpu on which the operation has to be applied. With the advent of ACPI on arm64, where MADT static table entries are used to initialize cpus, the device tree node parameter in cpu_ops hooks become useless when booting with ACPI, since in that case cpu device tree nodes are not present and can not be used for cpu initialization. The current cpu_init hook requires a struct device_node pointer parameter because it is called while parsing the device tree to initialize CPUs, when the cpu_logical_map (that is used to match a cpu node reg property to a device tree node) for a given logical cpu id is not set up yet. This means that the cpu_init hook cannot rely on the of_get_cpu_node function to retrieve the device tree node corresponding to the logical cpu id passed in as parameter, so the cpu device tree node must be passed in as a parameter to fix this catch-22 dependency cycle. This patch reshuffles the cpu_logical_map initialization code so that the cpu_init cpu_ops hook can safely use the of_get_cpu_node function to retrieve the cpu device tree node, removing the need for the device tree node pointer parameter. In the process, the patch removes device tree node parameters from all cpu_ops hooks, in preparation for SMP DT/ACPI cpus initialization consolidation. Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Acked-by: Hanjun Guo <hanjun.guo@linaro.org> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Hanjun Guo <hanjun.guo@linaro.org> Tested-by: Mark Rutland <mark.rutland@arm.com> [DT] Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-05-13 07:12:46 -06:00
/*
* Initialize cpu operations for a logical cpu and
* set it in the possible mask on success
*/
static int __init smp_cpu_setup(int cpu)
{
if (cpu_read_ops(cpu))
return -ENODEV;
if (cpu_ops[cpu]->cpu_init(cpu))
return -ENODEV;
set_cpu_possible(cpu, true);
return 0;
}
static bool bootcpu_valid __initdata;
static unsigned int cpu_count = 1;
#ifdef CONFIG_ACPI
static struct acpi_madt_generic_interrupt cpu_madt_gicc[NR_CPUS];
struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu)
{
return &cpu_madt_gicc[cpu];
}
/*
* acpi_map_gic_cpu_interface - parse processor MADT entry
*
* Carry out sanity checks on MADT processor entry and initialize
* cpu_logical_map on success
*/
static void __init
acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
{
u64 hwid = processor->arm_mpidr;
if (!(processor->flags & ACPI_MADT_ENABLED)) {
pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
return;
}
if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
return;
}
if (is_mpidr_duplicate(cpu_count, hwid)) {
pr_err("duplicate CPU MPIDR 0x%llx in MADT\n", hwid);
return;
}
/* Check if GICC structure of boot CPU is available in the MADT */
if (cpu_logical_map(0) == hwid) {
if (bootcpu_valid) {
pr_err("duplicate boot CPU MPIDR: 0x%llx in MADT\n",
hwid);
return;
}
bootcpu_valid = true;
cpu_madt_gicc[0] = *processor;
return;
}
if (cpu_count >= NR_CPUS)
return;
/* map the logical cpu id to cpu MPIDR */
cpu_logical_map(cpu_count) = hwid;
cpu_madt_gicc[cpu_count] = *processor;
arm64: kernel: implement ACPI parking protocol The SBBR and ACPI specifications allow ACPI based systems that do not implement PSCI (eg systems with no EL3) to boot through the ACPI parking protocol specification[1]. This patch implements the ACPI parking protocol CPU operations, and adds code that eases parsing the parking protocol data structures to the ARM64 SMP initializion carried out at the same time as cpus enumeration. To wake-up the CPUs from the parked state, this patch implements a wakeup IPI for ARM64 (ie arch_send_wakeup_ipi_mask()) that mirrors the ARM one, so that a specific IPI is sent for wake-up purpose in order to distinguish it from other IPI sources. Given the current ACPI MADT parsing API, the patch implements a glue layer that helps passing MADT GICC data structure from SMP initialization code to the parking protocol implementation somewhat overriding the CPU operations interfaces. This to avoid creating a completely trasparent DT/ACPI CPU operations layer that would require creating opaque structure handling for CPUs data (DT represents CPU through DT nodes, ACPI through static MADT table entries), which seems overkill given that ACPI on ARM64 mandates only two booting protocols (PSCI and parking protocol), so there is no need for further protocol additions. Based on the original work by Mark Salter <msalter@redhat.com> [1] https://acpica.org/sites/acpica/files/MP%20Startup%20for%20ARM%20platforms.docx Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Loc Ho <lho@apm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Hanjun Guo <hanjun.guo@linaro.org> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mark Salter <msalter@redhat.com> Cc: Al Stone <ahs3@redhat.com> [catalin.marinas@arm.com: Added WARN_ONCE(!acpi_parking_protocol_valid() on the IPI] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-01-26 04:10:38 -07:00
/*
* Set-up the ACPI parking protocol cpu entries
* while initializing the cpu_logical_map to
* avoid parsing MADT entries multiple times for
* nothing (ie a valid cpu_logical_map entry should
* contain a valid parking protocol data set to
* initialize the cpu if the parking protocol is
* the only available enable method).
*/
acpi_set_mailbox_entry(cpu_count, processor);
cpu_count++;
}
static int __init
acpi_parse_gic_cpu_interface(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *processor;
processor = (struct acpi_madt_generic_interrupt *)header;
if (BAD_MADT_GICC_ENTRY(processor, end))
return -EINVAL;
acpi_table_print_madt_entry(&header->common);
acpi_map_gic_cpu_interface(processor);
return 0;
}
arm64: numa: rework ACPI NUMA initialization Current ACPI ARM64 NUMA initialization code in acpi_numa_gicc_affinity_init() carries out NUMA nodes creation and cpu<->node mappings at the same time in the arch backend so that a single SRAT walk is needed to parse both pieces of information. This implies that the cpu<->node mappings must be stashed in an array (sized NR_CPUS) so that SMP code can later use the stashed values to avoid another SRAT table walk to set-up the early cpu<->node mappings. If the kernel is configured with a NR_CPUS value less than the actual processor entries in the SRAT (and MADT), the logic in acpi_numa_gicc_affinity_init() is broken in that the cpu<->node mapping is only carried out (and stashed for future use) only for a number of SRAT entries up to NR_CPUS, which do not necessarily correspond to the possible cpus detected at SMP initialization in acpi_map_gic_cpu_interface() (ie MADT and SRAT processor entries order is not enforced), which leaves the kernel with broken cpu<->node mappings. Furthermore, given the current ACPI NUMA code parsing logic in acpi_numa_gicc_affinity_init(), PXM domains for CPUs that are not parsed because they exceed NR_CPUS entries are not mapped to NUMA nodes (ie the PXM corresponding node is not created in the kernel) leaving the system with a broken NUMA topology. Rework the ACPI ARM64 NUMA initialization process so that the NUMA nodes creation and cpu<->node mappings are decoupled. cpu<->node mappings are moved to SMP initialization code (where they are needed), at the cost of an extra SRAT walk so that ACPI NUMA mappings can be batched before being applied, fixing current parsing pitfalls. Acked-by: Hanjun Guo <hanjun.guo@linaro.org> Tested-by: John Garry <john.garry@huawei.com> Fixes: d8b47fca8c23 ("arm64, ACPI, NUMA: NUMA support based on SRAT and SLIT") Link: http://lkml.kernel.org/r/1527768879-88161-2-git-send-email-xiexiuqi@huawei.com Reported-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Jonathan Cameron <jonathan.cameron@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Ganapatrao Kulkarni <gkulkarni@caviumnetworks.com> Cc: Jeremy Linton <jeremy.linton@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-06-25 07:05:52 -06:00
static void __init acpi_parse_and_init_cpus(void)
{
int i;
/*
* do a walk of MADT to determine how many CPUs
* we have including disabled CPUs, and get information
* we need for SMP init.
*/
acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
acpi_parse_gic_cpu_interface, 0);
/*
* In ACPI, SMP and CPU NUMA information is provided in separate
* static tables, namely the MADT and the SRAT.
*
* Thus, it is simpler to first create the cpu logical map through
* an MADT walk and then map the logical cpus to their node ids
* as separate steps.
*/
acpi_map_cpus_to_nodes();
for (i = 0; i < nr_cpu_ids; i++)
early_map_cpu_to_node(i, acpi_numa_get_nid(i));
}
#else
arm64: numa: rework ACPI NUMA initialization Current ACPI ARM64 NUMA initialization code in acpi_numa_gicc_affinity_init() carries out NUMA nodes creation and cpu<->node mappings at the same time in the arch backend so that a single SRAT walk is needed to parse both pieces of information. This implies that the cpu<->node mappings must be stashed in an array (sized NR_CPUS) so that SMP code can later use the stashed values to avoid another SRAT table walk to set-up the early cpu<->node mappings. If the kernel is configured with a NR_CPUS value less than the actual processor entries in the SRAT (and MADT), the logic in acpi_numa_gicc_affinity_init() is broken in that the cpu<->node mapping is only carried out (and stashed for future use) only for a number of SRAT entries up to NR_CPUS, which do not necessarily correspond to the possible cpus detected at SMP initialization in acpi_map_gic_cpu_interface() (ie MADT and SRAT processor entries order is not enforced), which leaves the kernel with broken cpu<->node mappings. Furthermore, given the current ACPI NUMA code parsing logic in acpi_numa_gicc_affinity_init(), PXM domains for CPUs that are not parsed because they exceed NR_CPUS entries are not mapped to NUMA nodes (ie the PXM corresponding node is not created in the kernel) leaving the system with a broken NUMA topology. Rework the ACPI ARM64 NUMA initialization process so that the NUMA nodes creation and cpu<->node mappings are decoupled. cpu<->node mappings are moved to SMP initialization code (where they are needed), at the cost of an extra SRAT walk so that ACPI NUMA mappings can be batched before being applied, fixing current parsing pitfalls. Acked-by: Hanjun Guo <hanjun.guo@linaro.org> Tested-by: John Garry <john.garry@huawei.com> Fixes: d8b47fca8c23 ("arm64, ACPI, NUMA: NUMA support based on SRAT and SLIT") Link: http://lkml.kernel.org/r/1527768879-88161-2-git-send-email-xiexiuqi@huawei.com Reported-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Jonathan Cameron <jonathan.cameron@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Ganapatrao Kulkarni <gkulkarni@caviumnetworks.com> Cc: Jeremy Linton <jeremy.linton@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-06-25 07:05:52 -06:00
#define acpi_parse_and_init_cpus(...) do { } while (0)
#endif
/*
* Enumerate the possible CPU set from the device tree and build the
* cpu logical map array containing MPIDR values related to logical
* cpus. Assumes that cpu_logical_map(0) has already been initialized.
*/
static void __init of_parse_and_init_cpus(void)
{
struct device_node *dn;
for_each_of_cpu_node(dn) {
u64 hwid = of_get_cpu_mpidr(dn);
if (hwid == INVALID_HWID)
goto next;
if (is_mpidr_duplicate(cpu_count, hwid)) {
pr_err("%pOF: duplicate cpu reg properties in the DT\n",
dn);
goto next;
}
/*
* The numbering scheme requires that the boot CPU
* must be assigned logical id 0. Record it so that
* the logical map built from DT is validated and can
* be used.
*/
if (hwid == cpu_logical_map(0)) {
if (bootcpu_valid) {
pr_err("%pOF: duplicate boot cpu reg property in DT\n",
dn);
goto next;
}
bootcpu_valid = true;
early_map_cpu_to_node(0, of_node_to_nid(dn));
/*
* cpu_logical_map has already been
* initialized and the boot cpu doesn't need
* the enable-method so continue without
* incrementing cpu.
*/
continue;
}
if (cpu_count >= NR_CPUS)
goto next;
pr_debug("cpu logical map 0x%llx\n", hwid);
cpu_logical_map(cpu_count) = hwid;
early_map_cpu_to_node(cpu_count, of_node_to_nid(dn));
next:
cpu_count++;
}
}
/*
* Enumerate the possible CPU set from the device tree or ACPI and build the
* cpu logical map array containing MPIDR values related to logical
* cpus. Assumes that cpu_logical_map(0) has already been initialized.
*/
void __init smp_init_cpus(void)
{
int i;
if (acpi_disabled)
of_parse_and_init_cpus();
else
arm64: numa: rework ACPI NUMA initialization Current ACPI ARM64 NUMA initialization code in acpi_numa_gicc_affinity_init() carries out NUMA nodes creation and cpu<->node mappings at the same time in the arch backend so that a single SRAT walk is needed to parse both pieces of information. This implies that the cpu<->node mappings must be stashed in an array (sized NR_CPUS) so that SMP code can later use the stashed values to avoid another SRAT table walk to set-up the early cpu<->node mappings. If the kernel is configured with a NR_CPUS value less than the actual processor entries in the SRAT (and MADT), the logic in acpi_numa_gicc_affinity_init() is broken in that the cpu<->node mapping is only carried out (and stashed for future use) only for a number of SRAT entries up to NR_CPUS, which do not necessarily correspond to the possible cpus detected at SMP initialization in acpi_map_gic_cpu_interface() (ie MADT and SRAT processor entries order is not enforced), which leaves the kernel with broken cpu<->node mappings. Furthermore, given the current ACPI NUMA code parsing logic in acpi_numa_gicc_affinity_init(), PXM domains for CPUs that are not parsed because they exceed NR_CPUS entries are not mapped to NUMA nodes (ie the PXM corresponding node is not created in the kernel) leaving the system with a broken NUMA topology. Rework the ACPI ARM64 NUMA initialization process so that the NUMA nodes creation and cpu<->node mappings are decoupled. cpu<->node mappings are moved to SMP initialization code (where they are needed), at the cost of an extra SRAT walk so that ACPI NUMA mappings can be batched before being applied, fixing current parsing pitfalls. Acked-by: Hanjun Guo <hanjun.guo@linaro.org> Tested-by: John Garry <john.garry@huawei.com> Fixes: d8b47fca8c23 ("arm64, ACPI, NUMA: NUMA support based on SRAT and SLIT") Link: http://lkml.kernel.org/r/1527768879-88161-2-git-send-email-xiexiuqi@huawei.com Reported-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Jonathan Cameron <jonathan.cameron@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Ganapatrao Kulkarni <gkulkarni@caviumnetworks.com> Cc: Jeremy Linton <jeremy.linton@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-06-25 07:05:52 -06:00
acpi_parse_and_init_cpus();
if (cpu_count > nr_cpu_ids)
pr_warn("Number of cores (%d) exceeds configured maximum of %u - clipping\n",
cpu_count, nr_cpu_ids);
if (!bootcpu_valid) {
pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
return;
}
/*
ARM64: kernel: make cpu_ops hooks DT agnostic ARM64 CPU operations such as cpu_init and cpu_init_idle take a struct device_node pointer as a parameter, which corresponds to the device tree node of the logical cpu on which the operation has to be applied. With the advent of ACPI on arm64, where MADT static table entries are used to initialize cpus, the device tree node parameter in cpu_ops hooks become useless when booting with ACPI, since in that case cpu device tree nodes are not present and can not be used for cpu initialization. The current cpu_init hook requires a struct device_node pointer parameter because it is called while parsing the device tree to initialize CPUs, when the cpu_logical_map (that is used to match a cpu node reg property to a device tree node) for a given logical cpu id is not set up yet. This means that the cpu_init hook cannot rely on the of_get_cpu_node function to retrieve the device tree node corresponding to the logical cpu id passed in as parameter, so the cpu device tree node must be passed in as a parameter to fix this catch-22 dependency cycle. This patch reshuffles the cpu_logical_map initialization code so that the cpu_init cpu_ops hook can safely use the of_get_cpu_node function to retrieve the cpu device tree node, removing the need for the device tree node pointer parameter. In the process, the patch removes device tree node parameters from all cpu_ops hooks, in preparation for SMP DT/ACPI cpus initialization consolidation. Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Acked-by: Hanjun Guo <hanjun.guo@linaro.org> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Hanjun Guo <hanjun.guo@linaro.org> Tested-by: Mark Rutland <mark.rutland@arm.com> [DT] Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-05-13 07:12:46 -06:00
* We need to set the cpu_logical_map entries before enabling
* the cpus so that cpu processor description entries (DT cpu nodes
* and ACPI MADT entries) can be retrieved by matching the cpu hwid
* with entries in cpu_logical_map while initializing the cpus.
* If the cpu set-up fails, invalidate the cpu_logical_map entry.
*/
for (i = 1; i < nr_cpu_ids; i++) {
ARM64: kernel: make cpu_ops hooks DT agnostic ARM64 CPU operations such as cpu_init and cpu_init_idle take a struct device_node pointer as a parameter, which corresponds to the device tree node of the logical cpu on which the operation has to be applied. With the advent of ACPI on arm64, where MADT static table entries are used to initialize cpus, the device tree node parameter in cpu_ops hooks become useless when booting with ACPI, since in that case cpu device tree nodes are not present and can not be used for cpu initialization. The current cpu_init hook requires a struct device_node pointer parameter because it is called while parsing the device tree to initialize CPUs, when the cpu_logical_map (that is used to match a cpu node reg property to a device tree node) for a given logical cpu id is not set up yet. This means that the cpu_init hook cannot rely on the of_get_cpu_node function to retrieve the device tree node corresponding to the logical cpu id passed in as parameter, so the cpu device tree node must be passed in as a parameter to fix this catch-22 dependency cycle. This patch reshuffles the cpu_logical_map initialization code so that the cpu_init cpu_ops hook can safely use the of_get_cpu_node function to retrieve the cpu device tree node, removing the need for the device tree node pointer parameter. In the process, the patch removes device tree node parameters from all cpu_ops hooks, in preparation for SMP DT/ACPI cpus initialization consolidation. Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Acked-by: Hanjun Guo <hanjun.guo@linaro.org> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Tested-by: Hanjun Guo <hanjun.guo@linaro.org> Tested-by: Mark Rutland <mark.rutland@arm.com> [DT] Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-05-13 07:12:46 -06:00
if (cpu_logical_map(i) != INVALID_HWID) {
if (smp_cpu_setup(i))
cpu_logical_map(i) = INVALID_HWID;
}
}
}
void __init smp_prepare_cpus(unsigned int max_cpus)
{
int err;
unsigned int cpu;
arm64: Call numa_store_cpu_info() earlier. The wq_numa_init() function makes a private CPU to node map by calling cpu_to_node() early in the boot process, before the non-boot CPUs are brought online. Since the default implementation of cpu_to_node() returns zero for CPUs that have never been brought online, the workqueue system's view is that *all* CPUs are on node zero. When the unbound workqueue for a non-zero node is created, the tsk_cpus_allowed() for the worker threads is the empty set because there are, in the view of the workqueue system, no CPUs on non-zero nodes. The code in try_to_wake_up() using this empty cpumask ends up using the cpumask empty set value of NR_CPUS as an index into the per-CPU area pointer array, and gets garbage as it is one past the end of the array. This results in: [ 0.881970] Unable to handle kernel paging request at virtual address fffffb1008b926a4 [ 1.970095] pgd = fffffc00094b0000 [ 1.973530] [fffffb1008b926a4] *pgd=0000000000000000, *pud=0000000000000000, *pmd=0000000000000000 [ 1.982610] Internal error: Oops: 96000004 [#1] SMP [ 1.987541] Modules linked in: [ 1.990631] CPU: 48 PID: 295 Comm: cpuhp/48 Tainted: G W 4.8.0-rc6-preempt-vol+ #9 [ 1.999435] Hardware name: Cavium ThunderX CN88XX board (DT) [ 2.005159] task: fffffe0fe89cc300 task.stack: fffffe0fe8b8c000 [ 2.011158] PC is at try_to_wake_up+0x194/0x34c [ 2.015737] LR is at try_to_wake_up+0x150/0x34c [ 2.020318] pc : [<fffffc00080e7468>] lr : [<fffffc00080e7424>] pstate: 600000c5 [ 2.027803] sp : fffffe0fe8b8fb10 [ 2.031149] x29: fffffe0fe8b8fb10 x28: 0000000000000000 [ 2.036522] x27: fffffc0008c63bc8 x26: 0000000000001000 [ 2.041896] x25: fffffc0008c63c80 x24: fffffc0008bfb200 [ 2.047270] x23: 00000000000000c0 x22: 0000000000000004 [ 2.052642] x21: fffffe0fe89d25bc x20: 0000000000001000 [ 2.058014] x19: fffffe0fe89d1d00 x18: 0000000000000000 [ 2.063386] x17: 0000000000000000 x16: 0000000000000000 [ 2.068760] x15: 0000000000000018 x14: 0000000000000000 [ 2.074133] x13: 0000000000000000 x12: 0000000000000000 [ 2.079505] x11: 0000000000000000 x10: 0000000000000000 [ 2.084879] x9 : 0000000000000000 x8 : 0000000000000000 [ 2.090251] x7 : 0000000000000040 x6 : 0000000000000000 [ 2.095621] x5 : ffffffffffffffff x4 : 0000000000000000 [ 2.100991] x3 : 0000000000000000 x2 : 0000000000000000 [ 2.106364] x1 : fffffc0008be4c24 x0 : ffffff0ffffada80 [ 2.111737] [ 2.113236] Process cpuhp/48 (pid: 295, stack limit = 0xfffffe0fe8b8c020) [ 2.120102] Stack: (0xfffffe0fe8b8fb10 to 0xfffffe0fe8b90000) [ 2.125914] fb00: fffffe0fe8b8fb80 fffffc00080e7648 . . . [ 2.442859] Call trace: [ 2.445327] Exception stack(0xfffffe0fe8b8f940 to 0xfffffe0fe8b8fa70) [ 2.451843] f940: fffffe0fe89d1d00 0000040000000000 fffffe0fe8b8fb10 fffffc00080e7468 [ 2.459767] f960: fffffe0fe8b8f980 fffffc00080e4958 ffffff0ff91ab200 fffffc00080e4b64 [ 2.467690] f980: fffffe0fe8b8f9d0 fffffc00080e515c fffffe0fe8b8fa80 0000000000000000 [ 2.475614] f9a0: fffffe0fe8b8f9d0 fffffc00080e58e4 fffffe0fe8b8fa80 0000000000000000 [ 2.483540] f9c0: fffffe0fe8d10000 0000000000000040 fffffe0fe8b8fa50 fffffc00080e5ac4 [ 2.491465] f9e0: ffffff0ffffada80 fffffc0008be4c24 0000000000000000 0000000000000000 [ 2.499387] fa00: 0000000000000000 ffffffffffffffff 0000000000000000 0000000000000040 [ 2.507309] fa20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 2.515233] fa40: 0000000000000000 0000000000000000 0000000000000000 0000000000000018 [ 2.523156] fa60: 0000000000000000 0000000000000000 [ 2.528089] [<fffffc00080e7468>] try_to_wake_up+0x194/0x34c [ 2.533723] [<fffffc00080e7648>] wake_up_process+0x28/0x34 [ 2.539275] [<fffffc00080d3764>] create_worker+0x110/0x19c [ 2.544824] [<fffffc00080d69dc>] alloc_unbound_pwq+0x3cc/0x4b0 [ 2.550724] [<fffffc00080d6bcc>] wq_update_unbound_numa+0x10c/0x1e4 [ 2.557066] [<fffffc00080d7d78>] workqueue_online_cpu+0x220/0x28c [ 2.563234] [<fffffc00080bd288>] cpuhp_invoke_callback+0x6c/0x168 [ 2.569398] [<fffffc00080bdf74>] cpuhp_up_callbacks+0x44/0xe4 [ 2.575210] [<fffffc00080be194>] cpuhp_thread_fun+0x13c/0x148 [ 2.581027] [<fffffc00080dfbac>] smpboot_thread_fn+0x19c/0x1a8 [ 2.586929] [<fffffc00080dbd64>] kthread+0xdc/0xf0 [ 2.591776] [<fffffc0008083380>] ret_from_fork+0x10/0x50 [ 2.597147] Code: b00057e1 91304021 91005021 b8626822 (b8606821) [ 2.603464] ---[ end trace 58c0cd36b88802bc ]--- [ 2.608138] Kernel panic - not syncing: Fatal exception Fix by moving call to numa_store_cpu_info() for all CPUs into smp_prepare_cpus(), which happens before wq_numa_init(). Since smp_store_cpu_info() now contains only a single function call, simplify by removing the function and out-lining its contents. Suggested-by: Robert Richter <rric@kernel.org> Fixes: 1a2db300348b ("arm64, numa: Add NUMA support for arm64 platforms.") Cc: <stable@vger.kernel.org> # 4.7.x- Signed-off-by: David Daney <david.daney@cavium.com> Reviewed-by: Robert Richter <rrichter@cavium.com> Tested-by: Yisheng Xie <xieyisheng1@huawei.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-09-20 12:46:35 -06:00
unsigned int this_cpu;
init_cpu_topology();
arm64: Call numa_store_cpu_info() earlier. The wq_numa_init() function makes a private CPU to node map by calling cpu_to_node() early in the boot process, before the non-boot CPUs are brought online. Since the default implementation of cpu_to_node() returns zero for CPUs that have never been brought online, the workqueue system's view is that *all* CPUs are on node zero. When the unbound workqueue for a non-zero node is created, the tsk_cpus_allowed() for the worker threads is the empty set because there are, in the view of the workqueue system, no CPUs on non-zero nodes. The code in try_to_wake_up() using this empty cpumask ends up using the cpumask empty set value of NR_CPUS as an index into the per-CPU area pointer array, and gets garbage as it is one past the end of the array. This results in: [ 0.881970] Unable to handle kernel paging request at virtual address fffffb1008b926a4 [ 1.970095] pgd = fffffc00094b0000 [ 1.973530] [fffffb1008b926a4] *pgd=0000000000000000, *pud=0000000000000000, *pmd=0000000000000000 [ 1.982610] Internal error: Oops: 96000004 [#1] SMP [ 1.987541] Modules linked in: [ 1.990631] CPU: 48 PID: 295 Comm: cpuhp/48 Tainted: G W 4.8.0-rc6-preempt-vol+ #9 [ 1.999435] Hardware name: Cavium ThunderX CN88XX board (DT) [ 2.005159] task: fffffe0fe89cc300 task.stack: fffffe0fe8b8c000 [ 2.011158] PC is at try_to_wake_up+0x194/0x34c [ 2.015737] LR is at try_to_wake_up+0x150/0x34c [ 2.020318] pc : [<fffffc00080e7468>] lr : [<fffffc00080e7424>] pstate: 600000c5 [ 2.027803] sp : fffffe0fe8b8fb10 [ 2.031149] x29: fffffe0fe8b8fb10 x28: 0000000000000000 [ 2.036522] x27: fffffc0008c63bc8 x26: 0000000000001000 [ 2.041896] x25: fffffc0008c63c80 x24: fffffc0008bfb200 [ 2.047270] x23: 00000000000000c0 x22: 0000000000000004 [ 2.052642] x21: fffffe0fe89d25bc x20: 0000000000001000 [ 2.058014] x19: fffffe0fe89d1d00 x18: 0000000000000000 [ 2.063386] x17: 0000000000000000 x16: 0000000000000000 [ 2.068760] x15: 0000000000000018 x14: 0000000000000000 [ 2.074133] x13: 0000000000000000 x12: 0000000000000000 [ 2.079505] x11: 0000000000000000 x10: 0000000000000000 [ 2.084879] x9 : 0000000000000000 x8 : 0000000000000000 [ 2.090251] x7 : 0000000000000040 x6 : 0000000000000000 [ 2.095621] x5 : ffffffffffffffff x4 : 0000000000000000 [ 2.100991] x3 : 0000000000000000 x2 : 0000000000000000 [ 2.106364] x1 : fffffc0008be4c24 x0 : ffffff0ffffada80 [ 2.111737] [ 2.113236] Process cpuhp/48 (pid: 295, stack limit = 0xfffffe0fe8b8c020) [ 2.120102] Stack: (0xfffffe0fe8b8fb10 to 0xfffffe0fe8b90000) [ 2.125914] fb00: fffffe0fe8b8fb80 fffffc00080e7648 . . . [ 2.442859] Call trace: [ 2.445327] Exception stack(0xfffffe0fe8b8f940 to 0xfffffe0fe8b8fa70) [ 2.451843] f940: fffffe0fe89d1d00 0000040000000000 fffffe0fe8b8fb10 fffffc00080e7468 [ 2.459767] f960: fffffe0fe8b8f980 fffffc00080e4958 ffffff0ff91ab200 fffffc00080e4b64 [ 2.467690] f980: fffffe0fe8b8f9d0 fffffc00080e515c fffffe0fe8b8fa80 0000000000000000 [ 2.475614] f9a0: fffffe0fe8b8f9d0 fffffc00080e58e4 fffffe0fe8b8fa80 0000000000000000 [ 2.483540] f9c0: fffffe0fe8d10000 0000000000000040 fffffe0fe8b8fa50 fffffc00080e5ac4 [ 2.491465] f9e0: ffffff0ffffada80 fffffc0008be4c24 0000000000000000 0000000000000000 [ 2.499387] fa00: 0000000000000000 ffffffffffffffff 0000000000000000 0000000000000040 [ 2.507309] fa20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 2.515233] fa40: 0000000000000000 0000000000000000 0000000000000000 0000000000000018 [ 2.523156] fa60: 0000000000000000 0000000000000000 [ 2.528089] [<fffffc00080e7468>] try_to_wake_up+0x194/0x34c [ 2.533723] [<fffffc00080e7648>] wake_up_process+0x28/0x34 [ 2.539275] [<fffffc00080d3764>] create_worker+0x110/0x19c [ 2.544824] [<fffffc00080d69dc>] alloc_unbound_pwq+0x3cc/0x4b0 [ 2.550724] [<fffffc00080d6bcc>] wq_update_unbound_numa+0x10c/0x1e4 [ 2.557066] [<fffffc00080d7d78>] workqueue_online_cpu+0x220/0x28c [ 2.563234] [<fffffc00080bd288>] cpuhp_invoke_callback+0x6c/0x168 [ 2.569398] [<fffffc00080bdf74>] cpuhp_up_callbacks+0x44/0xe4 [ 2.575210] [<fffffc00080be194>] cpuhp_thread_fun+0x13c/0x148 [ 2.581027] [<fffffc00080dfbac>] smpboot_thread_fn+0x19c/0x1a8 [ 2.586929] [<fffffc00080dbd64>] kthread+0xdc/0xf0 [ 2.591776] [<fffffc0008083380>] ret_from_fork+0x10/0x50 [ 2.597147] Code: b00057e1 91304021 91005021 b8626822 (b8606821) [ 2.603464] ---[ end trace 58c0cd36b88802bc ]--- [ 2.608138] Kernel panic - not syncing: Fatal exception Fix by moving call to numa_store_cpu_info() for all CPUs into smp_prepare_cpus(), which happens before wq_numa_init(). Since smp_store_cpu_info() now contains only a single function call, simplify by removing the function and out-lining its contents. Suggested-by: Robert Richter <rric@kernel.org> Fixes: 1a2db300348b ("arm64, numa: Add NUMA support for arm64 platforms.") Cc: <stable@vger.kernel.org> # 4.7.x- Signed-off-by: David Daney <david.daney@cavium.com> Reviewed-by: Robert Richter <rrichter@cavium.com> Tested-by: Yisheng Xie <xieyisheng1@huawei.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-09-20 12:46:35 -06:00
this_cpu = smp_processor_id();
store_cpu_topology(this_cpu);
numa_store_cpu_info(this_cpu);
numa_add_cpu(this_cpu);
/*
* If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set
* secondary CPUs present.
*/
if (max_cpus == 0)
return;
/*
* Initialise the present map (which describes the set of CPUs
* actually populated at the present time) and release the
* secondaries from the bootloader.
*/
for_each_possible_cpu(cpu) {
per_cpu(cpu_number, cpu) = cpu;
if (cpu == smp_processor_id())
continue;
if (!cpu_ops[cpu])
continue;
err = cpu_ops[cpu]->cpu_prepare(cpu);
if (err)
continue;
set_cpu_present(cpu, true);
arm64: Call numa_store_cpu_info() earlier. The wq_numa_init() function makes a private CPU to node map by calling cpu_to_node() early in the boot process, before the non-boot CPUs are brought online. Since the default implementation of cpu_to_node() returns zero for CPUs that have never been brought online, the workqueue system's view is that *all* CPUs are on node zero. When the unbound workqueue for a non-zero node is created, the tsk_cpus_allowed() for the worker threads is the empty set because there are, in the view of the workqueue system, no CPUs on non-zero nodes. The code in try_to_wake_up() using this empty cpumask ends up using the cpumask empty set value of NR_CPUS as an index into the per-CPU area pointer array, and gets garbage as it is one past the end of the array. This results in: [ 0.881970] Unable to handle kernel paging request at virtual address fffffb1008b926a4 [ 1.970095] pgd = fffffc00094b0000 [ 1.973530] [fffffb1008b926a4] *pgd=0000000000000000, *pud=0000000000000000, *pmd=0000000000000000 [ 1.982610] Internal error: Oops: 96000004 [#1] SMP [ 1.987541] Modules linked in: [ 1.990631] CPU: 48 PID: 295 Comm: cpuhp/48 Tainted: G W 4.8.0-rc6-preempt-vol+ #9 [ 1.999435] Hardware name: Cavium ThunderX CN88XX board (DT) [ 2.005159] task: fffffe0fe89cc300 task.stack: fffffe0fe8b8c000 [ 2.011158] PC is at try_to_wake_up+0x194/0x34c [ 2.015737] LR is at try_to_wake_up+0x150/0x34c [ 2.020318] pc : [<fffffc00080e7468>] lr : [<fffffc00080e7424>] pstate: 600000c5 [ 2.027803] sp : fffffe0fe8b8fb10 [ 2.031149] x29: fffffe0fe8b8fb10 x28: 0000000000000000 [ 2.036522] x27: fffffc0008c63bc8 x26: 0000000000001000 [ 2.041896] x25: fffffc0008c63c80 x24: fffffc0008bfb200 [ 2.047270] x23: 00000000000000c0 x22: 0000000000000004 [ 2.052642] x21: fffffe0fe89d25bc x20: 0000000000001000 [ 2.058014] x19: fffffe0fe89d1d00 x18: 0000000000000000 [ 2.063386] x17: 0000000000000000 x16: 0000000000000000 [ 2.068760] x15: 0000000000000018 x14: 0000000000000000 [ 2.074133] x13: 0000000000000000 x12: 0000000000000000 [ 2.079505] x11: 0000000000000000 x10: 0000000000000000 [ 2.084879] x9 : 0000000000000000 x8 : 0000000000000000 [ 2.090251] x7 : 0000000000000040 x6 : 0000000000000000 [ 2.095621] x5 : ffffffffffffffff x4 : 0000000000000000 [ 2.100991] x3 : 0000000000000000 x2 : 0000000000000000 [ 2.106364] x1 : fffffc0008be4c24 x0 : ffffff0ffffada80 [ 2.111737] [ 2.113236] Process cpuhp/48 (pid: 295, stack limit = 0xfffffe0fe8b8c020) [ 2.120102] Stack: (0xfffffe0fe8b8fb10 to 0xfffffe0fe8b90000) [ 2.125914] fb00: fffffe0fe8b8fb80 fffffc00080e7648 . . . [ 2.442859] Call trace: [ 2.445327] Exception stack(0xfffffe0fe8b8f940 to 0xfffffe0fe8b8fa70) [ 2.451843] f940: fffffe0fe89d1d00 0000040000000000 fffffe0fe8b8fb10 fffffc00080e7468 [ 2.459767] f960: fffffe0fe8b8f980 fffffc00080e4958 ffffff0ff91ab200 fffffc00080e4b64 [ 2.467690] f980: fffffe0fe8b8f9d0 fffffc00080e515c fffffe0fe8b8fa80 0000000000000000 [ 2.475614] f9a0: fffffe0fe8b8f9d0 fffffc00080e58e4 fffffe0fe8b8fa80 0000000000000000 [ 2.483540] f9c0: fffffe0fe8d10000 0000000000000040 fffffe0fe8b8fa50 fffffc00080e5ac4 [ 2.491465] f9e0: ffffff0ffffada80 fffffc0008be4c24 0000000000000000 0000000000000000 [ 2.499387] fa00: 0000000000000000 ffffffffffffffff 0000000000000000 0000000000000040 [ 2.507309] fa20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 2.515233] fa40: 0000000000000000 0000000000000000 0000000000000000 0000000000000018 [ 2.523156] fa60: 0000000000000000 0000000000000000 [ 2.528089] [<fffffc00080e7468>] try_to_wake_up+0x194/0x34c [ 2.533723] [<fffffc00080e7648>] wake_up_process+0x28/0x34 [ 2.539275] [<fffffc00080d3764>] create_worker+0x110/0x19c [ 2.544824] [<fffffc00080d69dc>] alloc_unbound_pwq+0x3cc/0x4b0 [ 2.550724] [<fffffc00080d6bcc>] wq_update_unbound_numa+0x10c/0x1e4 [ 2.557066] [<fffffc00080d7d78>] workqueue_online_cpu+0x220/0x28c [ 2.563234] [<fffffc00080bd288>] cpuhp_invoke_callback+0x6c/0x168 [ 2.569398] [<fffffc00080bdf74>] cpuhp_up_callbacks+0x44/0xe4 [ 2.575210] [<fffffc00080be194>] cpuhp_thread_fun+0x13c/0x148 [ 2.581027] [<fffffc00080dfbac>] smpboot_thread_fn+0x19c/0x1a8 [ 2.586929] [<fffffc00080dbd64>] kthread+0xdc/0xf0 [ 2.591776] [<fffffc0008083380>] ret_from_fork+0x10/0x50 [ 2.597147] Code: b00057e1 91304021 91005021 b8626822 (b8606821) [ 2.603464] ---[ end trace 58c0cd36b88802bc ]--- [ 2.608138] Kernel panic - not syncing: Fatal exception Fix by moving call to numa_store_cpu_info() for all CPUs into smp_prepare_cpus(), which happens before wq_numa_init(). Since smp_store_cpu_info() now contains only a single function call, simplify by removing the function and out-lining its contents. Suggested-by: Robert Richter <rric@kernel.org> Fixes: 1a2db300348b ("arm64, numa: Add NUMA support for arm64 platforms.") Cc: <stable@vger.kernel.org> # 4.7.x- Signed-off-by: David Daney <david.daney@cavium.com> Reviewed-by: Robert Richter <rrichter@cavium.com> Tested-by: Yisheng Xie <xieyisheng1@huawei.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-09-20 12:46:35 -06:00
numa_store_cpu_info(cpu);
}
}
void (*__smp_cross_call)(const struct cpumask *, unsigned int);
void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
{
__smp_cross_call = fn;
}
static const char *ipi_types[NR_IPI] __tracepoint_string = {
#define S(x,s) [x] = s
S(IPI_RESCHEDULE, "Rescheduling interrupts"),
S(IPI_CALL_FUNC, "Function call interrupts"),
S(IPI_CPU_STOP, "CPU stop interrupts"),
S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"),
S(IPI_TIMER, "Timer broadcast interrupts"),
S(IPI_IRQ_WORK, "IRQ work interrupts"),
arm64: kernel: implement ACPI parking protocol The SBBR and ACPI specifications allow ACPI based systems that do not implement PSCI (eg systems with no EL3) to boot through the ACPI parking protocol specification[1]. This patch implements the ACPI parking protocol CPU operations, and adds code that eases parsing the parking protocol data structures to the ARM64 SMP initializion carried out at the same time as cpus enumeration. To wake-up the CPUs from the parked state, this patch implements a wakeup IPI for ARM64 (ie arch_send_wakeup_ipi_mask()) that mirrors the ARM one, so that a specific IPI is sent for wake-up purpose in order to distinguish it from other IPI sources. Given the current ACPI MADT parsing API, the patch implements a glue layer that helps passing MADT GICC data structure from SMP initialization code to the parking protocol implementation somewhat overriding the CPU operations interfaces. This to avoid creating a completely trasparent DT/ACPI CPU operations layer that would require creating opaque structure handling for CPUs data (DT represents CPU through DT nodes, ACPI through static MADT table entries), which seems overkill given that ACPI on ARM64 mandates only two booting protocols (PSCI and parking protocol), so there is no need for further protocol additions. Based on the original work by Mark Salter <msalter@redhat.com> [1] https://acpica.org/sites/acpica/files/MP%20Startup%20for%20ARM%20platforms.docx Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Loc Ho <lho@apm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Hanjun Guo <hanjun.guo@linaro.org> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mark Salter <msalter@redhat.com> Cc: Al Stone <ahs3@redhat.com> [catalin.marinas@arm.com: Added WARN_ONCE(!acpi_parking_protocol_valid() on the IPI] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-01-26 04:10:38 -07:00
S(IPI_WAKEUP, "CPU wake-up interrupts"),
};
static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
{
trace_ipi_raise(target, ipi_types[ipinr]);
__smp_cross_call(target, ipinr);
}
void show_ipi_list(struct seq_file *p, int prec)
{
unsigned int cpu, i;
for (i = 0; i < NR_IPI; i++) {
seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
prec >= 4 ? " " : "");
for_each_online_cpu(cpu)
seq_printf(p, "%10u ",
__get_irq_stat(cpu, ipi_irqs[i]));
seq_printf(p, " %s\n", ipi_types[i]);
}
}
u64 smp_irq_stat_cpu(unsigned int cpu)
{
u64 sum = 0;
int i;
for (i = 0; i < NR_IPI; i++)
sum += __get_irq_stat(cpu, ipi_irqs[i]);
return sum;
}
void arch_send_call_function_ipi_mask(const struct cpumask *mask)
{
smp_cross_call(mask, IPI_CALL_FUNC);
}
void arch_send_call_function_single_ipi(int cpu)
{
smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC);
}
arm64: kernel: implement ACPI parking protocol The SBBR and ACPI specifications allow ACPI based systems that do not implement PSCI (eg systems with no EL3) to boot through the ACPI parking protocol specification[1]. This patch implements the ACPI parking protocol CPU operations, and adds code that eases parsing the parking protocol data structures to the ARM64 SMP initializion carried out at the same time as cpus enumeration. To wake-up the CPUs from the parked state, this patch implements a wakeup IPI for ARM64 (ie arch_send_wakeup_ipi_mask()) that mirrors the ARM one, so that a specific IPI is sent for wake-up purpose in order to distinguish it from other IPI sources. Given the current ACPI MADT parsing API, the patch implements a glue layer that helps passing MADT GICC data structure from SMP initialization code to the parking protocol implementation somewhat overriding the CPU operations interfaces. This to avoid creating a completely trasparent DT/ACPI CPU operations layer that would require creating opaque structure handling for CPUs data (DT represents CPU through DT nodes, ACPI through static MADT table entries), which seems overkill given that ACPI on ARM64 mandates only two booting protocols (PSCI and parking protocol), so there is no need for further protocol additions. Based on the original work by Mark Salter <msalter@redhat.com> [1] https://acpica.org/sites/acpica/files/MP%20Startup%20for%20ARM%20platforms.docx Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Loc Ho <lho@apm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Hanjun Guo <hanjun.guo@linaro.org> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mark Salter <msalter@redhat.com> Cc: Al Stone <ahs3@redhat.com> [catalin.marinas@arm.com: Added WARN_ONCE(!acpi_parking_protocol_valid() on the IPI] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-01-26 04:10:38 -07:00
#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
{
smp_cross_call(mask, IPI_WAKEUP);
}
#endif
#ifdef CONFIG_IRQ_WORK
void arch_irq_work_raise(void)
{
if (__smp_cross_call)
smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
}
#endif
static void local_cpu_stop(void)
{
set_cpu_online(smp_processor_id(), false);
local_daif_mask();
arm64: kernel: Add arch-specific SDEI entry code and CPU masking The Software Delegated Exception Interface (SDEI) is an ARM standard for registering callbacks from the platform firmware into the OS. This is typically used to implement RAS notifications. Such notifications enter the kernel at the registered entry-point with the register values of the interrupted CPU context. Because this is not a CPU exception, it cannot reuse the existing entry code. (crucially we don't implicitly know which exception level we interrupted), Add the entry point to entry.S to set us up for calling into C code. If the event interrupted code that had interrupts masked, we always return to that location. Otherwise we pretend this was an IRQ, and use SDEI's complete_and_resume call to return to vbar_el1 + offset. This allows the kernel to deliver signals to user space processes. For KVM this triggers the world switch, a quick spin round vcpu_run, then back into the guest, unless there are pending signals. Add sdei_mask_local_cpu() calls to the smp_send_stop() code, this covers the panic() code-path, which doesn't invoke cpuhotplug notifiers. Because we can interrupt entry-from/exit-to another EL, we can't trust the value in sp_el0 or x29, even if we interrupted the kernel, in this case the code in entry.S will save/restore sp_el0 and use the value in __entry_task. When we have VMAP stacks we can interrupt the stack-overflow test, which stirs x0 into sp, meaning we have to have our own VMAP stacks. For now these are allocated when we probe the interface. Future patches will add refcounting hooks to allow the arch code to allocate them lazily. Signed-off-by: James Morse <james.morse@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-01-08 08:38:12 -07:00
sdei_mask_local_cpu();
cpu_park_loop();
}
/*
* We need to implement panic_smp_self_stop() for parallel panic() calls, so
* that cpu_online_mask gets correctly updated and smp_send_stop() can skip
* CPUs that have already stopped themselves.
*/
void panic_smp_self_stop(void)
{
local_cpu_stop();
}
#ifdef CONFIG_KEXEC_CORE
static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
#endif
static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
{
#ifdef CONFIG_KEXEC_CORE
crash_save_cpu(regs, cpu);
atomic_dec(&waiting_for_crash_ipi);
local_irq_disable();
arm64: kernel: Add arch-specific SDEI entry code and CPU masking The Software Delegated Exception Interface (SDEI) is an ARM standard for registering callbacks from the platform firmware into the OS. This is typically used to implement RAS notifications. Such notifications enter the kernel at the registered entry-point with the register values of the interrupted CPU context. Because this is not a CPU exception, it cannot reuse the existing entry code. (crucially we don't implicitly know which exception level we interrupted), Add the entry point to entry.S to set us up for calling into C code. If the event interrupted code that had interrupts masked, we always return to that location. Otherwise we pretend this was an IRQ, and use SDEI's complete_and_resume call to return to vbar_el1 + offset. This allows the kernel to deliver signals to user space processes. For KVM this triggers the world switch, a quick spin round vcpu_run, then back into the guest, unless there are pending signals. Add sdei_mask_local_cpu() calls to the smp_send_stop() code, this covers the panic() code-path, which doesn't invoke cpuhotplug notifiers. Because we can interrupt entry-from/exit-to another EL, we can't trust the value in sp_el0 or x29, even if we interrupted the kernel, in this case the code in entry.S will save/restore sp_el0 and use the value in __entry_task. When we have VMAP stacks we can interrupt the stack-overflow test, which stirs x0 into sp, meaning we have to have our own VMAP stacks. For now these are allocated when we probe the interface. Future patches will add refcounting hooks to allow the arch code to allocate them lazily. Signed-off-by: James Morse <james.morse@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-01-08 08:38:12 -07:00
sdei_mask_local_cpu();
#ifdef CONFIG_HOTPLUG_CPU
if (cpu_ops[cpu]->cpu_die)
cpu_ops[cpu]->cpu_die(cpu);
#endif
/* just in case */
cpu_park_loop();
#endif
}
/*
* Main handler for inter-processor interrupts
*/
void handle_IPI(int ipinr, struct pt_regs *regs)
{
unsigned int cpu = smp_processor_id();
struct pt_regs *old_regs = set_irq_regs(regs);
if ((unsigned)ipinr < NR_IPI) {
trace_ipi_entry_rcuidle(ipi_types[ipinr]);
__inc_irq_stat(cpu, ipi_irqs[ipinr]);
}
switch (ipinr) {
case IPI_RESCHEDULE:
scheduler_ipi();
break;
case IPI_CALL_FUNC:
irq_enter();
generic_smp_call_function_interrupt();
irq_exit();
break;
case IPI_CPU_STOP:
irq_enter();
local_cpu_stop();
irq_exit();
break;
case IPI_CPU_CRASH_STOP:
if (IS_ENABLED(CONFIG_KEXEC_CORE)) {
irq_enter();
ipi_cpu_crash_stop(cpu, regs);
unreachable();
}
break;
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
case IPI_TIMER:
irq_enter();
tick_receive_broadcast();
irq_exit();
break;
#endif
#ifdef CONFIG_IRQ_WORK
case IPI_IRQ_WORK:
irq_enter();
irq_work_run();
irq_exit();
break;
#endif
arm64: kernel: implement ACPI parking protocol The SBBR and ACPI specifications allow ACPI based systems that do not implement PSCI (eg systems with no EL3) to boot through the ACPI parking protocol specification[1]. This patch implements the ACPI parking protocol CPU operations, and adds code that eases parsing the parking protocol data structures to the ARM64 SMP initializion carried out at the same time as cpus enumeration. To wake-up the CPUs from the parked state, this patch implements a wakeup IPI for ARM64 (ie arch_send_wakeup_ipi_mask()) that mirrors the ARM one, so that a specific IPI is sent for wake-up purpose in order to distinguish it from other IPI sources. Given the current ACPI MADT parsing API, the patch implements a glue layer that helps passing MADT GICC data structure from SMP initialization code to the parking protocol implementation somewhat overriding the CPU operations interfaces. This to avoid creating a completely trasparent DT/ACPI CPU operations layer that would require creating opaque structure handling for CPUs data (DT represents CPU through DT nodes, ACPI through static MADT table entries), which seems overkill given that ACPI on ARM64 mandates only two booting protocols (PSCI and parking protocol), so there is no need for further protocol additions. Based on the original work by Mark Salter <msalter@redhat.com> [1] https://acpica.org/sites/acpica/files/MP%20Startup%20for%20ARM%20platforms.docx Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Loc Ho <lho@apm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Hanjun Guo <hanjun.guo@linaro.org> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mark Salter <msalter@redhat.com> Cc: Al Stone <ahs3@redhat.com> [catalin.marinas@arm.com: Added WARN_ONCE(!acpi_parking_protocol_valid() on the IPI] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-01-26 04:10:38 -07:00
#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
case IPI_WAKEUP:
WARN_ONCE(!acpi_parking_protocol_valid(cpu),
"CPU%u: Wake-up IPI outside the ACPI parking protocol\n",
cpu);
break;
#endif
default:
pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
break;
}
if ((unsigned)ipinr < NR_IPI)
trace_ipi_exit_rcuidle(ipi_types[ipinr]);
set_irq_regs(old_regs);
}
void smp_send_reschedule(int cpu)
{
smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
}
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
void tick_broadcast(const struct cpumask *mask)
{
smp_cross_call(mask, IPI_TIMER);
}
#endif
void smp_send_stop(void)
{
unsigned long timeout;
if (num_online_cpus() > 1) {
cpumask_t mask;
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
if (system_state <= SYSTEM_RUNNING)
pr_crit("SMP: stopping secondary CPUs\n");
smp_cross_call(&mask, IPI_CPU_STOP);
}
/* Wait up to one second for other CPUs to stop */
timeout = USEC_PER_SEC;
while (num_online_cpus() > 1 && timeout--)
udelay(1);
if (num_online_cpus() > 1)
pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(cpu_online_mask));
arm64: kernel: Add arch-specific SDEI entry code and CPU masking The Software Delegated Exception Interface (SDEI) is an ARM standard for registering callbacks from the platform firmware into the OS. This is typically used to implement RAS notifications. Such notifications enter the kernel at the registered entry-point with the register values of the interrupted CPU context. Because this is not a CPU exception, it cannot reuse the existing entry code. (crucially we don't implicitly know which exception level we interrupted), Add the entry point to entry.S to set us up for calling into C code. If the event interrupted code that had interrupts masked, we always return to that location. Otherwise we pretend this was an IRQ, and use SDEI's complete_and_resume call to return to vbar_el1 + offset. This allows the kernel to deliver signals to user space processes. For KVM this triggers the world switch, a quick spin round vcpu_run, then back into the guest, unless there are pending signals. Add sdei_mask_local_cpu() calls to the smp_send_stop() code, this covers the panic() code-path, which doesn't invoke cpuhotplug notifiers. Because we can interrupt entry-from/exit-to another EL, we can't trust the value in sp_el0 or x29, even if we interrupted the kernel, in this case the code in entry.S will save/restore sp_el0 and use the value in __entry_task. When we have VMAP stacks we can interrupt the stack-overflow test, which stirs x0 into sp, meaning we have to have our own VMAP stacks. For now these are allocated when we probe the interface. Future patches will add refcounting hooks to allow the arch code to allocate them lazily. Signed-off-by: James Morse <james.morse@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-01-08 08:38:12 -07:00
sdei_mask_local_cpu();
}
#ifdef CONFIG_KEXEC_CORE
arm64: kexec: have own crash_smp_send_stop() for crash dump for nonpanic cores Commit 0ee5941 : (x86/panic: replace smp_send_stop() with kdump friendly version in panic path) introduced crash_smp_send_stop() which is a weak function and can be overridden by architecture codes to fix the side effect caused by commit f06e515 : (kernel/panic.c: add "crash_kexec_post_ notifiers" option). ARM64 architecture uses the weak version function and the problem is that the weak function simply calls smp_send_stop() which makes other CPUs offline and takes away the chance to save crash information for nonpanic CPUs in machine_crash_shutdown() when crash_kexec_post_notifiers kernel option is enabled. Calling smp_send_crash_stop() in machine_crash_shutdown() is useless because all nonpanic CPUs are already offline by smp_send_stop() in this case and smp_send_crash_stop() only works against online CPUs. The result is that secondary CPUs registers are not saved by crash_save_cpu() and the vmcore file misreports these CPUs as being offline. crash_smp_send_stop() is implemented to fix this problem by replacing the existing smp_send_crash_stop() and adding a check for multiple calling to the function. The function (strong symbol version) saves crash information for nonpanic CPUs and machine_crash_shutdown() tries to save crash information for nonpanic CPUs only when crash_kexec_post_notifiers kernel option is disabled. * crash_kexec_post_notifiers : false panic() __crash_kexec() machine_crash_shutdown() crash_smp_send_stop() <= save crash dump for nonpanic cores * crash_kexec_post_notifiers : true panic() crash_smp_send_stop() <= save crash dump for nonpanic cores __crash_kexec() machine_crash_shutdown() crash_smp_send_stop() <= just return. Signed-off-by: Hoeun Ryu <hoeun.ryu@gmail.com> Reviewed-by: James Morse <james.morse@arm.com> Tested-by: James Morse <james.morse@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2017-08-16 20:24:27 -06:00
void crash_smp_send_stop(void)
{
arm64: kexec: have own crash_smp_send_stop() for crash dump for nonpanic cores Commit 0ee5941 : (x86/panic: replace smp_send_stop() with kdump friendly version in panic path) introduced crash_smp_send_stop() which is a weak function and can be overridden by architecture codes to fix the side effect caused by commit f06e515 : (kernel/panic.c: add "crash_kexec_post_ notifiers" option). ARM64 architecture uses the weak version function and the problem is that the weak function simply calls smp_send_stop() which makes other CPUs offline and takes away the chance to save crash information for nonpanic CPUs in machine_crash_shutdown() when crash_kexec_post_notifiers kernel option is enabled. Calling smp_send_crash_stop() in machine_crash_shutdown() is useless because all nonpanic CPUs are already offline by smp_send_stop() in this case and smp_send_crash_stop() only works against online CPUs. The result is that secondary CPUs registers are not saved by crash_save_cpu() and the vmcore file misreports these CPUs as being offline. crash_smp_send_stop() is implemented to fix this problem by replacing the existing smp_send_crash_stop() and adding a check for multiple calling to the function. The function (strong symbol version) saves crash information for nonpanic CPUs and machine_crash_shutdown() tries to save crash information for nonpanic CPUs only when crash_kexec_post_notifiers kernel option is disabled. * crash_kexec_post_notifiers : false panic() __crash_kexec() machine_crash_shutdown() crash_smp_send_stop() <= save crash dump for nonpanic cores * crash_kexec_post_notifiers : true panic() crash_smp_send_stop() <= save crash dump for nonpanic cores __crash_kexec() machine_crash_shutdown() crash_smp_send_stop() <= just return. Signed-off-by: Hoeun Ryu <hoeun.ryu@gmail.com> Reviewed-by: James Morse <james.morse@arm.com> Tested-by: James Morse <james.morse@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2017-08-16 20:24:27 -06:00
static int cpus_stopped;
cpumask_t mask;
unsigned long timeout;
arm64: kexec: have own crash_smp_send_stop() for crash dump for nonpanic cores Commit 0ee5941 : (x86/panic: replace smp_send_stop() with kdump friendly version in panic path) introduced crash_smp_send_stop() which is a weak function and can be overridden by architecture codes to fix the side effect caused by commit f06e515 : (kernel/panic.c: add "crash_kexec_post_ notifiers" option). ARM64 architecture uses the weak version function and the problem is that the weak function simply calls smp_send_stop() which makes other CPUs offline and takes away the chance to save crash information for nonpanic CPUs in machine_crash_shutdown() when crash_kexec_post_notifiers kernel option is enabled. Calling smp_send_crash_stop() in machine_crash_shutdown() is useless because all nonpanic CPUs are already offline by smp_send_stop() in this case and smp_send_crash_stop() only works against online CPUs. The result is that secondary CPUs registers are not saved by crash_save_cpu() and the vmcore file misreports these CPUs as being offline. crash_smp_send_stop() is implemented to fix this problem by replacing the existing smp_send_crash_stop() and adding a check for multiple calling to the function. The function (strong symbol version) saves crash information for nonpanic CPUs and machine_crash_shutdown() tries to save crash information for nonpanic CPUs only when crash_kexec_post_notifiers kernel option is disabled. * crash_kexec_post_notifiers : false panic() __crash_kexec() machine_crash_shutdown() crash_smp_send_stop() <= save crash dump for nonpanic cores * crash_kexec_post_notifiers : true panic() crash_smp_send_stop() <= save crash dump for nonpanic cores __crash_kexec() machine_crash_shutdown() crash_smp_send_stop() <= just return. Signed-off-by: Hoeun Ryu <hoeun.ryu@gmail.com> Reviewed-by: James Morse <james.morse@arm.com> Tested-by: James Morse <james.morse@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2017-08-16 20:24:27 -06:00
/*
* This function can be called twice in panic path, but obviously
* we execute this only once.
*/
if (cpus_stopped)
return;
cpus_stopped = 1;
arm64: kernel: Add arch-specific SDEI entry code and CPU masking The Software Delegated Exception Interface (SDEI) is an ARM standard for registering callbacks from the platform firmware into the OS. This is typically used to implement RAS notifications. Such notifications enter the kernel at the registered entry-point with the register values of the interrupted CPU context. Because this is not a CPU exception, it cannot reuse the existing entry code. (crucially we don't implicitly know which exception level we interrupted), Add the entry point to entry.S to set us up for calling into C code. If the event interrupted code that had interrupts masked, we always return to that location. Otherwise we pretend this was an IRQ, and use SDEI's complete_and_resume call to return to vbar_el1 + offset. This allows the kernel to deliver signals to user space processes. For KVM this triggers the world switch, a quick spin round vcpu_run, then back into the guest, unless there are pending signals. Add sdei_mask_local_cpu() calls to the smp_send_stop() code, this covers the panic() code-path, which doesn't invoke cpuhotplug notifiers. Because we can interrupt entry-from/exit-to another EL, we can't trust the value in sp_el0 or x29, even if we interrupted the kernel, in this case the code in entry.S will save/restore sp_el0 and use the value in __entry_task. When we have VMAP stacks we can interrupt the stack-overflow test, which stirs x0 into sp, meaning we have to have our own VMAP stacks. For now these are allocated when we probe the interface. Future patches will add refcounting hooks to allow the arch code to allocate them lazily. Signed-off-by: James Morse <james.morse@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-01-08 08:38:12 -07:00
if (num_online_cpus() == 1) {
sdei_mask_local_cpu();
return;
arm64: kernel: Add arch-specific SDEI entry code and CPU masking The Software Delegated Exception Interface (SDEI) is an ARM standard for registering callbacks from the platform firmware into the OS. This is typically used to implement RAS notifications. Such notifications enter the kernel at the registered entry-point with the register values of the interrupted CPU context. Because this is not a CPU exception, it cannot reuse the existing entry code. (crucially we don't implicitly know which exception level we interrupted), Add the entry point to entry.S to set us up for calling into C code. If the event interrupted code that had interrupts masked, we always return to that location. Otherwise we pretend this was an IRQ, and use SDEI's complete_and_resume call to return to vbar_el1 + offset. This allows the kernel to deliver signals to user space processes. For KVM this triggers the world switch, a quick spin round vcpu_run, then back into the guest, unless there are pending signals. Add sdei_mask_local_cpu() calls to the smp_send_stop() code, this covers the panic() code-path, which doesn't invoke cpuhotplug notifiers. Because we can interrupt entry-from/exit-to another EL, we can't trust the value in sp_el0 or x29, even if we interrupted the kernel, in this case the code in entry.S will save/restore sp_el0 and use the value in __entry_task. When we have VMAP stacks we can interrupt the stack-overflow test, which stirs x0 into sp, meaning we have to have our own VMAP stacks. For now these are allocated when we probe the interface. Future patches will add refcounting hooks to allow the arch code to allocate them lazily. Signed-off-by: James Morse <james.morse@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-01-08 08:38:12 -07:00
}
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
pr_crit("SMP: stopping secondary CPUs\n");
smp_cross_call(&mask, IPI_CPU_CRASH_STOP);
/* Wait up to one second for other CPUs to stop */
timeout = USEC_PER_SEC;
while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--)
udelay(1);
if (atomic_read(&waiting_for_crash_ipi) > 0)
pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(&mask));
arm64: kernel: Add arch-specific SDEI entry code and CPU masking The Software Delegated Exception Interface (SDEI) is an ARM standard for registering callbacks from the platform firmware into the OS. This is typically used to implement RAS notifications. Such notifications enter the kernel at the registered entry-point with the register values of the interrupted CPU context. Because this is not a CPU exception, it cannot reuse the existing entry code. (crucially we don't implicitly know which exception level we interrupted), Add the entry point to entry.S to set us up for calling into C code. If the event interrupted code that had interrupts masked, we always return to that location. Otherwise we pretend this was an IRQ, and use SDEI's complete_and_resume call to return to vbar_el1 + offset. This allows the kernel to deliver signals to user space processes. For KVM this triggers the world switch, a quick spin round vcpu_run, then back into the guest, unless there are pending signals. Add sdei_mask_local_cpu() calls to the smp_send_stop() code, this covers the panic() code-path, which doesn't invoke cpuhotplug notifiers. Because we can interrupt entry-from/exit-to another EL, we can't trust the value in sp_el0 or x29, even if we interrupted the kernel, in this case the code in entry.S will save/restore sp_el0 and use the value in __entry_task. When we have VMAP stacks we can interrupt the stack-overflow test, which stirs x0 into sp, meaning we have to have our own VMAP stacks. For now these are allocated when we probe the interface. Future patches will add refcounting hooks to allow the arch code to allocate them lazily. Signed-off-by: James Morse <james.morse@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-01-08 08:38:12 -07:00
sdei_mask_local_cpu();
}
bool smp_crash_stop_failed(void)
{
return (atomic_read(&waiting_for_crash_ipi) > 0);
}
#endif
/*
* not supported here
*/
int setup_profiling_timer(unsigned int multiplier)
{
return -EINVAL;
}
static bool have_cpu_die(void)
{
#ifdef CONFIG_HOTPLUG_CPU
int any_cpu = raw_smp_processor_id();
if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die)
return true;
#endif
return false;
}
bool cpus_are_stuck_in_kernel(void)
{
bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
return !!cpus_stuck_in_kernel || smp_spin_tables;
}