linux/arch/riscv/kernel/smp.c

365 lines
7.6 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* SMP initialisation and IPI support
* Based on arch/arm64/kernel/smp.c
*
* Copyright (C) 2012 ARM Ltd.
* Copyright (C) 2015 Regents of the University of California
* Copyright (C) 2017 SiFive
*/
#include <linux/cpu.h>
#include <linux/clockchips.h>
#include <linux/interrupt.h>
#include <linux/module.h>
riscv: kexec: Fixup crash_smp_send_stop without multi cores Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv. Before this patch, test result: crash> help -r CPU 0: [OFFLINE] CPU 1: epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff2000001098b9a8 CPU 2: [OFFLINE] CPU 3: [OFFLINE] After this patch, test result: crash> help -r CPU 0: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 1: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 2: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 3: epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff200000109bb9a8 Fixes: ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()") Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Cc: Nick Kossifidis <mick@ics.forth.gr> Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-10-20 10:16:03 -04:00
#include <linux/kexec.h>
RISC-V: Implement kgdb_roundup_cpus() to enable future NMI Roundup Until now, the generic weak kgdb_roundup_cpus() has been used for kgdb on RISCV. A custom one allows to debug CPUs that are stuck with interrupts disabled with NMI support in the future. And using an IPI is better than the generic one since it avoids the potential situation described in the generic kgdb_call_nmi_hook(). As Andrew pointed out, once there is NMI support, we can easily extend this and the CPU backtrace support to use NMIs. After this patch, the kgdb test show that: # echo g > /proc/sysrq-trigger [2]kdb> btc btc: cpu status: Currently on cpu 2 Available cpus: 0-1(-), 2, 3(-) Stack traceback for pid 0 0xffffffff81c13a40 0 0 1 0 - 0xffffffff81c14510 swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-g3120273055b6-dirty #51 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006c48>] dump_backtrace+0x28/0x30 [<ffffffff80fceb38>] show_stack+0x38/0x44 [<ffffffff80fe6a04>] dump_stack_lvl+0x58/0x7a [<ffffffff80fe6a3e>] dump_stack+0x18/0x20 [<ffffffff801143fa>] kgdb_cpu_enter+0x682/0x6b2 [<ffffffff801144ca>] kgdb_nmicallback+0xa0/0xac [<ffffffff8000a392>] handle_IPI+0x9c/0x120 [<ffffffff800a2baa>] handle_percpu_devid_irq+0xa4/0x1e4 [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff800a9e5c>] ipi_mux_process+0xe8/0x110 [<ffffffff806e1e30>] imsic_handle_irq+0xf8/0x13a [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff806dff12>] riscv_intc_aia_irq+0x2e/0x40 [<ffffffff80fe6ab0>] handle_riscv_irq+0x54/0x86 [<ffffffff80ff2e4a>] call_on_irq_stack+0x32/0x40 Rebased on Ryo Takakura's "RISC-V: Enable IPI CPU Backtrace" patch. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Link: https://lore.kernel.org/r/20240727063438.886155-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-27 14:34:38 +08:00
#include <linux/kgdb.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/smp.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/irq_work.h>
RISC-V: Enable IPI CPU Backtrace Add arch_trigger_cpumask_backtrace() which is a generic infrastructure for sampling other CPUs' backtrace using IPI. The feature is used when lockups are detected or in case of oops/panic if parameters are set accordingly. Below is the case of oops with the oops_all_cpu_backtrace enabled. $ sysctl kernel.oops_all_cpu_backtrace=1 triggering oops shows: [ 212.214237] NMI backtrace for cpu 1 [ 212.214390] CPU: 1 PID: 610 Comm: in:imklog Tainted: G OE 6.10.0-rc6 #1 [ 212.214570] Hardware name: riscv-virtio,qemu (DT) [ 212.214690] epc : fallback_scalar_usercopy+0x8/0xdc [ 212.214809] ra : _copy_to_user+0x20/0x40 [ 212.214913] epc : ffffffff80c3a930 ra : ffffffff8059ba7e sp : ff20000000eabb50 [ 212.215061] gp : ffffffff82066f90 tp : ff6000008e958000 t0 : 3463303866660000 [ 212.215210] t1 : 000000000000005b t2 : 3463303866666666 s0 : ff20000000eabb60 [ 212.215358] s1 : 0000000000000386 a0 : 00007ff6e81df926 a1 : ff600000824df800 [ 212.215505] a2 : 000000000000003f a3 : 7fffffffffffffc0 a4 : 0000000000000000 [ 212.215651] a5 : 000000000000003f a6 : 0000000000000000 a7 : 0000000000000000 [ 212.215857] s2 : ff600000824df800 s3 : ffffffff82066cc0 s4 : 0000000000001c1a [ 212.216074] s5 : ffffffff8206a5a8 s6 : 00007ff6e81df926 s7 : ffffffff8206a5a0 [ 212.216278] s8 : ff600000824df800 s9 : ffffffff81e25de0 s10: 000000000000003f [ 212.216471] s11: ffffffff8206a59d t3 : ff600000824df812 t4 : ff600000824df812 [ 212.216651] t5 : ff600000824df818 t6 : 0000000000040000 [ 212.216796] status: 0000000000040120 badaddr: 0000000000000000 cause: 8000000000000001 [ 212.217035] [<ffffffff80c3a930>] fallback_scalar_usercopy+0x8/0xdc [ 212.217207] [<ffffffff80095f56>] syslog_print+0x1f4/0x2b2 [ 212.217362] [<ffffffff80096e5c>] do_syslog.part.0+0x94/0x2d8 [ 212.217502] [<ffffffff800979e8>] do_syslog+0x66/0x88 [ 212.217636] [<ffffffff803a5dda>] kmsg_read+0x44/0x5c [ 212.217764] [<ffffffff80392dbe>] proc_reg_read+0x7a/0xa8 [ 212.217952] [<ffffffff802ff726>] vfs_read+0xb0/0x24e [ 212.218090] [<ffffffff803001ba>] ksys_read+0x64/0xe4 [ 212.218264] [<ffffffff8030025a>] __riscv_sys_read+0x20/0x2c [ 212.218453] [<ffffffff80c4af9a>] do_trap_ecall_u+0x60/0x1d4 [ 212.218664] [<ffffffff80c56998>] ret_from_exception+0x0/0x64 Signed-off-by: Ryo Takakura <takakura@valinux.co.jp> Link: https://lore.kernel.org/r/20240718093659.158912-1-takakura@valinux.co.jp Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-18 18:36:59 +09:00
#include <linux/nmi.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
riscv: kexec: Fixup crash_smp_send_stop without multi cores Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv. Before this patch, test result: crash> help -r CPU 0: [OFFLINE] CPU 1: epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff2000001098b9a8 CPU 2: [OFFLINE] CPU 3: [OFFLINE] After this patch, test result: crash> help -r CPU 0: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 1: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 2: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 3: epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff200000109bb9a8 Fixes: ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()") Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Cc: Nick Kossifidis <mick@ics.forth.gr> Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-10-20 10:16:03 -04:00
#include <asm/cpu_ops.h>
enum ipi_message_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
IPI_CPU_STOP,
riscv: kexec: Fixup crash_smp_send_stop without multi cores Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv. Before this patch, test result: crash> help -r CPU 0: [OFFLINE] CPU 1: epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff2000001098b9a8 CPU 2: [OFFLINE] CPU 3: [OFFLINE] After this patch, test result: crash> help -r CPU 0: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 1: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 2: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 3: epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff200000109bb9a8 Fixes: ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()") Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Cc: Nick Kossifidis <mick@ics.forth.gr> Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-10-20 10:16:03 -04:00
IPI_CPU_CRASH_STOP,
IPI_IRQ_WORK,
IPI_TIMER,
RISC-V: Enable IPI CPU Backtrace Add arch_trigger_cpumask_backtrace() which is a generic infrastructure for sampling other CPUs' backtrace using IPI. The feature is used when lockups are detected or in case of oops/panic if parameters are set accordingly. Below is the case of oops with the oops_all_cpu_backtrace enabled. $ sysctl kernel.oops_all_cpu_backtrace=1 triggering oops shows: [ 212.214237] NMI backtrace for cpu 1 [ 212.214390] CPU: 1 PID: 610 Comm: in:imklog Tainted: G OE 6.10.0-rc6 #1 [ 212.214570] Hardware name: riscv-virtio,qemu (DT) [ 212.214690] epc : fallback_scalar_usercopy+0x8/0xdc [ 212.214809] ra : _copy_to_user+0x20/0x40 [ 212.214913] epc : ffffffff80c3a930 ra : ffffffff8059ba7e sp : ff20000000eabb50 [ 212.215061] gp : ffffffff82066f90 tp : ff6000008e958000 t0 : 3463303866660000 [ 212.215210] t1 : 000000000000005b t2 : 3463303866666666 s0 : ff20000000eabb60 [ 212.215358] s1 : 0000000000000386 a0 : 00007ff6e81df926 a1 : ff600000824df800 [ 212.215505] a2 : 000000000000003f a3 : 7fffffffffffffc0 a4 : 0000000000000000 [ 212.215651] a5 : 000000000000003f a6 : 0000000000000000 a7 : 0000000000000000 [ 212.215857] s2 : ff600000824df800 s3 : ffffffff82066cc0 s4 : 0000000000001c1a [ 212.216074] s5 : ffffffff8206a5a8 s6 : 00007ff6e81df926 s7 : ffffffff8206a5a0 [ 212.216278] s8 : ff600000824df800 s9 : ffffffff81e25de0 s10: 000000000000003f [ 212.216471] s11: ffffffff8206a59d t3 : ff600000824df812 t4 : ff600000824df812 [ 212.216651] t5 : ff600000824df818 t6 : 0000000000040000 [ 212.216796] status: 0000000000040120 badaddr: 0000000000000000 cause: 8000000000000001 [ 212.217035] [<ffffffff80c3a930>] fallback_scalar_usercopy+0x8/0xdc [ 212.217207] [<ffffffff80095f56>] syslog_print+0x1f4/0x2b2 [ 212.217362] [<ffffffff80096e5c>] do_syslog.part.0+0x94/0x2d8 [ 212.217502] [<ffffffff800979e8>] do_syslog+0x66/0x88 [ 212.217636] [<ffffffff803a5dda>] kmsg_read+0x44/0x5c [ 212.217764] [<ffffffff80392dbe>] proc_reg_read+0x7a/0xa8 [ 212.217952] [<ffffffff802ff726>] vfs_read+0xb0/0x24e [ 212.218090] [<ffffffff803001ba>] ksys_read+0x64/0xe4 [ 212.218264] [<ffffffff8030025a>] __riscv_sys_read+0x20/0x2c [ 212.218453] [<ffffffff80c4af9a>] do_trap_ecall_u+0x60/0x1d4 [ 212.218664] [<ffffffff80c56998>] ret_from_exception+0x0/0x64 Signed-off-by: Ryo Takakura <takakura@valinux.co.jp> Link: https://lore.kernel.org/r/20240718093659.158912-1-takakura@valinux.co.jp Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-18 18:36:59 +09:00
IPI_CPU_BACKTRACE,
RISC-V: Implement kgdb_roundup_cpus() to enable future NMI Roundup Until now, the generic weak kgdb_roundup_cpus() has been used for kgdb on RISCV. A custom one allows to debug CPUs that are stuck with interrupts disabled with NMI support in the future. And using an IPI is better than the generic one since it avoids the potential situation described in the generic kgdb_call_nmi_hook(). As Andrew pointed out, once there is NMI support, we can easily extend this and the CPU backtrace support to use NMIs. After this patch, the kgdb test show that: # echo g > /proc/sysrq-trigger [2]kdb> btc btc: cpu status: Currently on cpu 2 Available cpus: 0-1(-), 2, 3(-) Stack traceback for pid 0 0xffffffff81c13a40 0 0 1 0 - 0xffffffff81c14510 swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-g3120273055b6-dirty #51 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006c48>] dump_backtrace+0x28/0x30 [<ffffffff80fceb38>] show_stack+0x38/0x44 [<ffffffff80fe6a04>] dump_stack_lvl+0x58/0x7a [<ffffffff80fe6a3e>] dump_stack+0x18/0x20 [<ffffffff801143fa>] kgdb_cpu_enter+0x682/0x6b2 [<ffffffff801144ca>] kgdb_nmicallback+0xa0/0xac [<ffffffff8000a392>] handle_IPI+0x9c/0x120 [<ffffffff800a2baa>] handle_percpu_devid_irq+0xa4/0x1e4 [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff800a9e5c>] ipi_mux_process+0xe8/0x110 [<ffffffff806e1e30>] imsic_handle_irq+0xf8/0x13a [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff806dff12>] riscv_intc_aia_irq+0x2e/0x40 [<ffffffff80fe6ab0>] handle_riscv_irq+0x54/0x86 [<ffffffff80ff2e4a>] call_on_irq_stack+0x32/0x40 Rebased on Ryo Takakura's "RISC-V: Enable IPI CPU Backtrace" patch. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Link: https://lore.kernel.org/r/20240727063438.886155-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-27 14:34:38 +08:00
IPI_KGDB_ROUNDUP,
IPI_MAX
};
unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = {
[0 ... NR_CPUS-1] = INVALID_HARTID
};
void __init smp_setup_processor_id(void)
{
cpuid_to_hartid_map(0) = boot_cpu_hartid;
}
static DEFINE_PER_CPU_READ_MOSTLY(int, ipi_dummy_dev);
static int ipi_virq_base __ro_after_init;
static int nr_ipi __ro_after_init = IPI_MAX;
static struct irq_desc *ipi_desc[IPI_MAX] __read_mostly;
int riscv_hartid_to_cpuid(unsigned long hartid)
{
int i;
for (i = 0; i < NR_CPUS; i++)
if (cpuid_to_hartid_map(i) == hartid)
return i;
return -ENOENT;
}
static void ipi_stop(void)
{
set_cpu_online(smp_processor_id(), false);
while (1)
wait_for_interrupt();
}
riscv: kexec: Fixup crash_smp_send_stop without multi cores Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv. Before this patch, test result: crash> help -r CPU 0: [OFFLINE] CPU 1: epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff2000001098b9a8 CPU 2: [OFFLINE] CPU 3: [OFFLINE] After this patch, test result: crash> help -r CPU 0: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 1: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 2: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 3: epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff200000109bb9a8 Fixes: ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()") Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Cc: Nick Kossifidis <mick@ics.forth.gr> Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-10-20 10:16:03 -04:00
#ifdef CONFIG_KEXEC_CORE
static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
{
crash_save_cpu(regs, cpu);
atomic_dec(&waiting_for_crash_ipi);
local_irq_disable();
#ifdef CONFIG_HOTPLUG_CPU
if (cpu_has_hotplug(cpu))
cpu_ops->cpu_stop();
riscv: kexec: Fixup crash_smp_send_stop without multi cores Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv. Before this patch, test result: crash> help -r CPU 0: [OFFLINE] CPU 1: epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff2000001098b9a8 CPU 2: [OFFLINE] CPU 3: [OFFLINE] After this patch, test result: crash> help -r CPU 0: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 1: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 2: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 3: epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff200000109bb9a8 Fixes: ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()") Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Cc: Nick Kossifidis <mick@ics.forth.gr> Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-10-20 10:16:03 -04:00
#endif
for(;;)
wait_for_interrupt();
}
#else
static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
{
unreachable();
}
#endif
static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
{
__ipi_send_mask(ipi_desc[op], mask);
}
static void send_ipi_single(int cpu, enum ipi_message_type op)
{
__ipi_send_mask(ipi_desc[op], cpumask_of(cpu));
}
#ifdef CONFIG_IRQ_WORK
void arch_irq_work_raise(void)
{
send_ipi_single(smp_processor_id(), IPI_IRQ_WORK);
}
#endif
static irqreturn_t handle_IPI(int irq, void *data)
{
RISC-V: Implement kgdb_roundup_cpus() to enable future NMI Roundup Until now, the generic weak kgdb_roundup_cpus() has been used for kgdb on RISCV. A custom one allows to debug CPUs that are stuck with interrupts disabled with NMI support in the future. And using an IPI is better than the generic one since it avoids the potential situation described in the generic kgdb_call_nmi_hook(). As Andrew pointed out, once there is NMI support, we can easily extend this and the CPU backtrace support to use NMIs. After this patch, the kgdb test show that: # echo g > /proc/sysrq-trigger [2]kdb> btc btc: cpu status: Currently on cpu 2 Available cpus: 0-1(-), 2, 3(-) Stack traceback for pid 0 0xffffffff81c13a40 0 0 1 0 - 0xffffffff81c14510 swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-g3120273055b6-dirty #51 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006c48>] dump_backtrace+0x28/0x30 [<ffffffff80fceb38>] show_stack+0x38/0x44 [<ffffffff80fe6a04>] dump_stack_lvl+0x58/0x7a [<ffffffff80fe6a3e>] dump_stack+0x18/0x20 [<ffffffff801143fa>] kgdb_cpu_enter+0x682/0x6b2 [<ffffffff801144ca>] kgdb_nmicallback+0xa0/0xac [<ffffffff8000a392>] handle_IPI+0x9c/0x120 [<ffffffff800a2baa>] handle_percpu_devid_irq+0xa4/0x1e4 [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff800a9e5c>] ipi_mux_process+0xe8/0x110 [<ffffffff806e1e30>] imsic_handle_irq+0xf8/0x13a [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff806dff12>] riscv_intc_aia_irq+0x2e/0x40 [<ffffffff80fe6ab0>] handle_riscv_irq+0x54/0x86 [<ffffffff80ff2e4a>] call_on_irq_stack+0x32/0x40 Rebased on Ryo Takakura's "RISC-V: Enable IPI CPU Backtrace" patch. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Link: https://lore.kernel.org/r/20240727063438.886155-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-27 14:34:38 +08:00
unsigned int cpu = smp_processor_id();
int ipi = irq - ipi_virq_base;
switch (ipi) {
case IPI_RESCHEDULE:
scheduler_ipi();
break;
case IPI_CALL_FUNC:
generic_smp_call_function_interrupt();
break;
case IPI_CPU_STOP:
ipi_stop();
break;
case IPI_CPU_CRASH_STOP:
RISC-V: Implement kgdb_roundup_cpus() to enable future NMI Roundup Until now, the generic weak kgdb_roundup_cpus() has been used for kgdb on RISCV. A custom one allows to debug CPUs that are stuck with interrupts disabled with NMI support in the future. And using an IPI is better than the generic one since it avoids the potential situation described in the generic kgdb_call_nmi_hook(). As Andrew pointed out, once there is NMI support, we can easily extend this and the CPU backtrace support to use NMIs. After this patch, the kgdb test show that: # echo g > /proc/sysrq-trigger [2]kdb> btc btc: cpu status: Currently on cpu 2 Available cpus: 0-1(-), 2, 3(-) Stack traceback for pid 0 0xffffffff81c13a40 0 0 1 0 - 0xffffffff81c14510 swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-g3120273055b6-dirty #51 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006c48>] dump_backtrace+0x28/0x30 [<ffffffff80fceb38>] show_stack+0x38/0x44 [<ffffffff80fe6a04>] dump_stack_lvl+0x58/0x7a [<ffffffff80fe6a3e>] dump_stack+0x18/0x20 [<ffffffff801143fa>] kgdb_cpu_enter+0x682/0x6b2 [<ffffffff801144ca>] kgdb_nmicallback+0xa0/0xac [<ffffffff8000a392>] handle_IPI+0x9c/0x120 [<ffffffff800a2baa>] handle_percpu_devid_irq+0xa4/0x1e4 [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff800a9e5c>] ipi_mux_process+0xe8/0x110 [<ffffffff806e1e30>] imsic_handle_irq+0xf8/0x13a [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff806dff12>] riscv_intc_aia_irq+0x2e/0x40 [<ffffffff80fe6ab0>] handle_riscv_irq+0x54/0x86 [<ffffffff80ff2e4a>] call_on_irq_stack+0x32/0x40 Rebased on Ryo Takakura's "RISC-V: Enable IPI CPU Backtrace" patch. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Link: https://lore.kernel.org/r/20240727063438.886155-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-27 14:34:38 +08:00
ipi_cpu_crash_stop(cpu, get_irq_regs());
break;
case IPI_IRQ_WORK:
irq_work_run();
break;
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
case IPI_TIMER:
tick_receive_broadcast();
break;
#endif
RISC-V: Enable IPI CPU Backtrace Add arch_trigger_cpumask_backtrace() which is a generic infrastructure for sampling other CPUs' backtrace using IPI. The feature is used when lockups are detected or in case of oops/panic if parameters are set accordingly. Below is the case of oops with the oops_all_cpu_backtrace enabled. $ sysctl kernel.oops_all_cpu_backtrace=1 triggering oops shows: [ 212.214237] NMI backtrace for cpu 1 [ 212.214390] CPU: 1 PID: 610 Comm: in:imklog Tainted: G OE 6.10.0-rc6 #1 [ 212.214570] Hardware name: riscv-virtio,qemu (DT) [ 212.214690] epc : fallback_scalar_usercopy+0x8/0xdc [ 212.214809] ra : _copy_to_user+0x20/0x40 [ 212.214913] epc : ffffffff80c3a930 ra : ffffffff8059ba7e sp : ff20000000eabb50 [ 212.215061] gp : ffffffff82066f90 tp : ff6000008e958000 t0 : 3463303866660000 [ 212.215210] t1 : 000000000000005b t2 : 3463303866666666 s0 : ff20000000eabb60 [ 212.215358] s1 : 0000000000000386 a0 : 00007ff6e81df926 a1 : ff600000824df800 [ 212.215505] a2 : 000000000000003f a3 : 7fffffffffffffc0 a4 : 0000000000000000 [ 212.215651] a5 : 000000000000003f a6 : 0000000000000000 a7 : 0000000000000000 [ 212.215857] s2 : ff600000824df800 s3 : ffffffff82066cc0 s4 : 0000000000001c1a [ 212.216074] s5 : ffffffff8206a5a8 s6 : 00007ff6e81df926 s7 : ffffffff8206a5a0 [ 212.216278] s8 : ff600000824df800 s9 : ffffffff81e25de0 s10: 000000000000003f [ 212.216471] s11: ffffffff8206a59d t3 : ff600000824df812 t4 : ff600000824df812 [ 212.216651] t5 : ff600000824df818 t6 : 0000000000040000 [ 212.216796] status: 0000000000040120 badaddr: 0000000000000000 cause: 8000000000000001 [ 212.217035] [<ffffffff80c3a930>] fallback_scalar_usercopy+0x8/0xdc [ 212.217207] [<ffffffff80095f56>] syslog_print+0x1f4/0x2b2 [ 212.217362] [<ffffffff80096e5c>] do_syslog.part.0+0x94/0x2d8 [ 212.217502] [<ffffffff800979e8>] do_syslog+0x66/0x88 [ 212.217636] [<ffffffff803a5dda>] kmsg_read+0x44/0x5c [ 212.217764] [<ffffffff80392dbe>] proc_reg_read+0x7a/0xa8 [ 212.217952] [<ffffffff802ff726>] vfs_read+0xb0/0x24e [ 212.218090] [<ffffffff803001ba>] ksys_read+0x64/0xe4 [ 212.218264] [<ffffffff8030025a>] __riscv_sys_read+0x20/0x2c [ 212.218453] [<ffffffff80c4af9a>] do_trap_ecall_u+0x60/0x1d4 [ 212.218664] [<ffffffff80c56998>] ret_from_exception+0x0/0x64 Signed-off-by: Ryo Takakura <takakura@valinux.co.jp> Link: https://lore.kernel.org/r/20240718093659.158912-1-takakura@valinux.co.jp Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-18 18:36:59 +09:00
case IPI_CPU_BACKTRACE:
nmi_cpu_backtrace(get_irq_regs());
break;
RISC-V: Implement kgdb_roundup_cpus() to enable future NMI Roundup Until now, the generic weak kgdb_roundup_cpus() has been used for kgdb on RISCV. A custom one allows to debug CPUs that are stuck with interrupts disabled with NMI support in the future. And using an IPI is better than the generic one since it avoids the potential situation described in the generic kgdb_call_nmi_hook(). As Andrew pointed out, once there is NMI support, we can easily extend this and the CPU backtrace support to use NMIs. After this patch, the kgdb test show that: # echo g > /proc/sysrq-trigger [2]kdb> btc btc: cpu status: Currently on cpu 2 Available cpus: 0-1(-), 2, 3(-) Stack traceback for pid 0 0xffffffff81c13a40 0 0 1 0 - 0xffffffff81c14510 swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-g3120273055b6-dirty #51 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006c48>] dump_backtrace+0x28/0x30 [<ffffffff80fceb38>] show_stack+0x38/0x44 [<ffffffff80fe6a04>] dump_stack_lvl+0x58/0x7a [<ffffffff80fe6a3e>] dump_stack+0x18/0x20 [<ffffffff801143fa>] kgdb_cpu_enter+0x682/0x6b2 [<ffffffff801144ca>] kgdb_nmicallback+0xa0/0xac [<ffffffff8000a392>] handle_IPI+0x9c/0x120 [<ffffffff800a2baa>] handle_percpu_devid_irq+0xa4/0x1e4 [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff800a9e5c>] ipi_mux_process+0xe8/0x110 [<ffffffff806e1e30>] imsic_handle_irq+0xf8/0x13a [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff806dff12>] riscv_intc_aia_irq+0x2e/0x40 [<ffffffff80fe6ab0>] handle_riscv_irq+0x54/0x86 [<ffffffff80ff2e4a>] call_on_irq_stack+0x32/0x40 Rebased on Ryo Takakura's "RISC-V: Enable IPI CPU Backtrace" patch. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Link: https://lore.kernel.org/r/20240727063438.886155-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-27 14:34:38 +08:00
case IPI_KGDB_ROUNDUP:
kgdb_nmicallback(cpu, get_irq_regs());
break;
default:
RISC-V: Implement kgdb_roundup_cpus() to enable future NMI Roundup Until now, the generic weak kgdb_roundup_cpus() has been used for kgdb on RISCV. A custom one allows to debug CPUs that are stuck with interrupts disabled with NMI support in the future. And using an IPI is better than the generic one since it avoids the potential situation described in the generic kgdb_call_nmi_hook(). As Andrew pointed out, once there is NMI support, we can easily extend this and the CPU backtrace support to use NMIs. After this patch, the kgdb test show that: # echo g > /proc/sysrq-trigger [2]kdb> btc btc: cpu status: Currently on cpu 2 Available cpus: 0-1(-), 2, 3(-) Stack traceback for pid 0 0xffffffff81c13a40 0 0 1 0 - 0xffffffff81c14510 swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-g3120273055b6-dirty #51 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006c48>] dump_backtrace+0x28/0x30 [<ffffffff80fceb38>] show_stack+0x38/0x44 [<ffffffff80fe6a04>] dump_stack_lvl+0x58/0x7a [<ffffffff80fe6a3e>] dump_stack+0x18/0x20 [<ffffffff801143fa>] kgdb_cpu_enter+0x682/0x6b2 [<ffffffff801144ca>] kgdb_nmicallback+0xa0/0xac [<ffffffff8000a392>] handle_IPI+0x9c/0x120 [<ffffffff800a2baa>] handle_percpu_devid_irq+0xa4/0x1e4 [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff800a9e5c>] ipi_mux_process+0xe8/0x110 [<ffffffff806e1e30>] imsic_handle_irq+0xf8/0x13a [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff806dff12>] riscv_intc_aia_irq+0x2e/0x40 [<ffffffff80fe6ab0>] handle_riscv_irq+0x54/0x86 [<ffffffff80ff2e4a>] call_on_irq_stack+0x32/0x40 Rebased on Ryo Takakura's "RISC-V: Enable IPI CPU Backtrace" patch. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Link: https://lore.kernel.org/r/20240727063438.886155-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-27 14:34:38 +08:00
pr_warn("CPU%d: unhandled IPI%d\n", cpu, ipi);
break;
}
return IRQ_HANDLED;
}
void riscv_ipi_enable(void)
{
int i;
if (WARN_ON_ONCE(!ipi_virq_base))
return;
for (i = 0; i < nr_ipi; i++)
enable_percpu_irq(ipi_virq_base + i, 0);
}
void riscv_ipi_disable(void)
{
int i;
if (WARN_ON_ONCE(!ipi_virq_base))
return;
for (i = 0; i < nr_ipi; i++)
disable_percpu_irq(ipi_virq_base + i);
}
bool riscv_ipi_have_virq_range(void)
{
return (ipi_virq_base) ? true : false;
}
riscv: Use IPIs for remote cache/TLB flushes by default An IPI backend is always required in an SMP configuration, but an SBI implementation is not. For example, SBI will be unavailable when the kernel runs in M mode. For this reason, consider IPI delivery of cache and TLB flushes to be the base case, and any other implementation (such as the SBI remote fence extension) to be an optimization. Generally, if IPIs can be delivered without firmware assistance, they are assumed to be faster than SBI calls due to the SBI context switch overhead. However, when SBI is used as the IPI backend, then the context switch cost must be paid anyway, and performing the cache/TLB flush directly in the SBI implementation is more efficient than injecting an interrupt to S-mode. This is the only existing scenario where riscv_ipi_set_virq_range() is called with use_for_rfence set to false. sbi_ipi_init() already checks riscv_ipi_have_virq_range(), so it only calls riscv_ipi_set_virq_range() when no other IPI device is available. This allows moving the static key and dropping the use_for_rfence parameter. This decouples the static key from the irqchip driver probe order. Furthermore, the static branch only makes sense when CONFIG_RISCV_SBI is enabled. Optherwise, IPIs must be used. Add a fallback definition of riscv_use_sbi_for_rfence() which handles this case and removes the need to check CONFIG_RISCV_SBI elsewhere, such as in cacheflush.c. Reviewed-by: Anup Patel <anup@brainfault.org> Signed-off-by: Samuel Holland <samuel.holland@sifive.com> Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com> Link: https://lore.kernel.org/r/20240327045035.368512-4-samuel.holland@sifive.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-03-26 21:49:44 -07:00
void riscv_ipi_set_virq_range(int virq, int nr)
{
int i, err;
if (WARN_ON(ipi_virq_base))
return;
riscv: kexec: Fixup crash_smp_send_stop without multi cores Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv. Before this patch, test result: crash> help -r CPU 0: [OFFLINE] CPU 1: epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff2000001098b9a8 CPU 2: [OFFLINE] CPU 3: [OFFLINE] After this patch, test result: crash> help -r CPU 0: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 1: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 2: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 3: epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff200000109bb9a8 Fixes: ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()") Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Cc: Nick Kossifidis <mick@ics.forth.gr> Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-10-20 10:16:03 -04:00
WARN_ON(nr < IPI_MAX);
nr_ipi = min(nr, IPI_MAX);
ipi_virq_base = virq;
/* Request IPIs */
for (i = 0; i < nr_ipi; i++) {
err = request_percpu_irq(ipi_virq_base + i, handle_IPI,
"IPI", &ipi_dummy_dev);
WARN_ON(err);
ipi_desc[i] = irq_to_desc(ipi_virq_base + i);
irq_set_status_flags(ipi_virq_base + i, IRQ_HIDDEN);
}
/* Enabled IPIs for boot CPU immediately */
riscv_ipi_enable();
}
static const char * const ipi_names[] = {
[IPI_RESCHEDULE] = "Rescheduling interrupts",
[IPI_CALL_FUNC] = "Function call interrupts",
[IPI_CPU_STOP] = "CPU stop interrupts",
riscv: kexec: Fixup crash_smp_send_stop without multi cores Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv. Before this patch, test result: crash> help -r CPU 0: [OFFLINE] CPU 1: epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff2000001098b9a8 CPU 2: [OFFLINE] CPU 3: [OFFLINE] After this patch, test result: crash> help -r CPU 0: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 1: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 2: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 3: epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff200000109bb9a8 Fixes: ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()") Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Cc: Nick Kossifidis <mick@ics.forth.gr> Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-10-20 10:16:03 -04:00
[IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts",
[IPI_IRQ_WORK] = "IRQ work interrupts",
[IPI_TIMER] = "Timer broadcast interrupts",
RISC-V: Enable IPI CPU Backtrace Add arch_trigger_cpumask_backtrace() which is a generic infrastructure for sampling other CPUs' backtrace using IPI. The feature is used when lockups are detected or in case of oops/panic if parameters are set accordingly. Below is the case of oops with the oops_all_cpu_backtrace enabled. $ sysctl kernel.oops_all_cpu_backtrace=1 triggering oops shows: [ 212.214237] NMI backtrace for cpu 1 [ 212.214390] CPU: 1 PID: 610 Comm: in:imklog Tainted: G OE 6.10.0-rc6 #1 [ 212.214570] Hardware name: riscv-virtio,qemu (DT) [ 212.214690] epc : fallback_scalar_usercopy+0x8/0xdc [ 212.214809] ra : _copy_to_user+0x20/0x40 [ 212.214913] epc : ffffffff80c3a930 ra : ffffffff8059ba7e sp : ff20000000eabb50 [ 212.215061] gp : ffffffff82066f90 tp : ff6000008e958000 t0 : 3463303866660000 [ 212.215210] t1 : 000000000000005b t2 : 3463303866666666 s0 : ff20000000eabb60 [ 212.215358] s1 : 0000000000000386 a0 : 00007ff6e81df926 a1 : ff600000824df800 [ 212.215505] a2 : 000000000000003f a3 : 7fffffffffffffc0 a4 : 0000000000000000 [ 212.215651] a5 : 000000000000003f a6 : 0000000000000000 a7 : 0000000000000000 [ 212.215857] s2 : ff600000824df800 s3 : ffffffff82066cc0 s4 : 0000000000001c1a [ 212.216074] s5 : ffffffff8206a5a8 s6 : 00007ff6e81df926 s7 : ffffffff8206a5a0 [ 212.216278] s8 : ff600000824df800 s9 : ffffffff81e25de0 s10: 000000000000003f [ 212.216471] s11: ffffffff8206a59d t3 : ff600000824df812 t4 : ff600000824df812 [ 212.216651] t5 : ff600000824df818 t6 : 0000000000040000 [ 212.216796] status: 0000000000040120 badaddr: 0000000000000000 cause: 8000000000000001 [ 212.217035] [<ffffffff80c3a930>] fallback_scalar_usercopy+0x8/0xdc [ 212.217207] [<ffffffff80095f56>] syslog_print+0x1f4/0x2b2 [ 212.217362] [<ffffffff80096e5c>] do_syslog.part.0+0x94/0x2d8 [ 212.217502] [<ffffffff800979e8>] do_syslog+0x66/0x88 [ 212.217636] [<ffffffff803a5dda>] kmsg_read+0x44/0x5c [ 212.217764] [<ffffffff80392dbe>] proc_reg_read+0x7a/0xa8 [ 212.217952] [<ffffffff802ff726>] vfs_read+0xb0/0x24e [ 212.218090] [<ffffffff803001ba>] ksys_read+0x64/0xe4 [ 212.218264] [<ffffffff8030025a>] __riscv_sys_read+0x20/0x2c [ 212.218453] [<ffffffff80c4af9a>] do_trap_ecall_u+0x60/0x1d4 [ 212.218664] [<ffffffff80c56998>] ret_from_exception+0x0/0x64 Signed-off-by: Ryo Takakura <takakura@valinux.co.jp> Link: https://lore.kernel.org/r/20240718093659.158912-1-takakura@valinux.co.jp Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-18 18:36:59 +09:00
[IPI_CPU_BACKTRACE] = "CPU backtrace interrupts",
RISC-V: Implement kgdb_roundup_cpus() to enable future NMI Roundup Until now, the generic weak kgdb_roundup_cpus() has been used for kgdb on RISCV. A custom one allows to debug CPUs that are stuck with interrupts disabled with NMI support in the future. And using an IPI is better than the generic one since it avoids the potential situation described in the generic kgdb_call_nmi_hook(). As Andrew pointed out, once there is NMI support, we can easily extend this and the CPU backtrace support to use NMIs. After this patch, the kgdb test show that: # echo g > /proc/sysrq-trigger [2]kdb> btc btc: cpu status: Currently on cpu 2 Available cpus: 0-1(-), 2, 3(-) Stack traceback for pid 0 0xffffffff81c13a40 0 0 1 0 - 0xffffffff81c14510 swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-g3120273055b6-dirty #51 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006c48>] dump_backtrace+0x28/0x30 [<ffffffff80fceb38>] show_stack+0x38/0x44 [<ffffffff80fe6a04>] dump_stack_lvl+0x58/0x7a [<ffffffff80fe6a3e>] dump_stack+0x18/0x20 [<ffffffff801143fa>] kgdb_cpu_enter+0x682/0x6b2 [<ffffffff801144ca>] kgdb_nmicallback+0xa0/0xac [<ffffffff8000a392>] handle_IPI+0x9c/0x120 [<ffffffff800a2baa>] handle_percpu_devid_irq+0xa4/0x1e4 [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff800a9e5c>] ipi_mux_process+0xe8/0x110 [<ffffffff806e1e30>] imsic_handle_irq+0xf8/0x13a [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff806dff12>] riscv_intc_aia_irq+0x2e/0x40 [<ffffffff80fe6ab0>] handle_riscv_irq+0x54/0x86 [<ffffffff80ff2e4a>] call_on_irq_stack+0x32/0x40 Rebased on Ryo Takakura's "RISC-V: Enable IPI CPU Backtrace" patch. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Link: https://lore.kernel.org/r/20240727063438.886155-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-27 14:34:38 +08:00
[IPI_KGDB_ROUNDUP] = "KGDB roundup interrupts",
};
void show_ipi_stats(struct seq_file *p, int prec)
{
unsigned int cpu, i;
for (i = 0; i < IPI_MAX; i++) {
seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
prec >= 4 ? " " : "");
for_each_online_cpu(cpu)
seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
seq_printf(p, " %s\n", ipi_names[i]);
}
}
void arch_send_call_function_ipi_mask(struct cpumask *mask)
{
send_ipi_mask(mask, IPI_CALL_FUNC);
}
void arch_send_call_function_single_ipi(int cpu)
{
send_ipi_single(cpu, IPI_CALL_FUNC);
}
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
void tick_broadcast(const struct cpumask *mask)
{
send_ipi_mask(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");
send_ipi_mask(&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_warn("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(cpu_online_mask));
}
riscv: kexec: Fixup crash_smp_send_stop without multi cores Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv. Before this patch, test result: crash> help -r CPU 0: [OFFLINE] CPU 1: epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff2000001098b9a8 CPU 2: [OFFLINE] CPU 3: [OFFLINE] After this patch, test result: crash> help -r CPU 0: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 1: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 2: epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000 t5 : 0000000000000000 t6 : 0000000000000000 CPU 3: epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097 t5 : ffffffff819a8098 t6 : ff200000109bb9a8 Fixes: ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()") Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Cc: Nick Kossifidis <mick@ics.forth.gr> Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-10-20 10:16:03 -04:00
#ifdef CONFIG_KEXEC_CORE
/*
* The number of CPUs online, not counting this CPU (which may not be
* fully online and so not counted in num_online_cpus()).
*/
static inline unsigned int num_other_online_cpus(void)
{
unsigned int this_cpu_online = cpu_online(smp_processor_id());
return num_online_cpus() - this_cpu_online;
}
void crash_smp_send_stop(void)
{
static int cpus_stopped;
cpumask_t mask;
unsigned long timeout;
/*
* This function can be called twice in panic path, but obviously
* we execute this only once.
*/
if (cpus_stopped)
return;
cpus_stopped = 1;
/*
* If this cpu is the only one alive at this point in time, online or
* not, there are no stop messages to be sent around, so just back out.
*/
if (num_other_online_cpus() == 0)
return;
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
atomic_set(&waiting_for_crash_ipi, num_other_online_cpus());
pr_crit("SMP: stopping secondary CPUs\n");
send_ipi_mask(&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_warn("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(&mask));
}
bool smp_crash_stop_failed(void)
{
return (atomic_read(&waiting_for_crash_ipi) > 0);
}
#endif
void arch_smp_send_reschedule(int cpu)
{
send_ipi_single(cpu, IPI_RESCHEDULE);
}
EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);
RISC-V: Enable IPI CPU Backtrace Add arch_trigger_cpumask_backtrace() which is a generic infrastructure for sampling other CPUs' backtrace using IPI. The feature is used when lockups are detected or in case of oops/panic if parameters are set accordingly. Below is the case of oops with the oops_all_cpu_backtrace enabled. $ sysctl kernel.oops_all_cpu_backtrace=1 triggering oops shows: [ 212.214237] NMI backtrace for cpu 1 [ 212.214390] CPU: 1 PID: 610 Comm: in:imklog Tainted: G OE 6.10.0-rc6 #1 [ 212.214570] Hardware name: riscv-virtio,qemu (DT) [ 212.214690] epc : fallback_scalar_usercopy+0x8/0xdc [ 212.214809] ra : _copy_to_user+0x20/0x40 [ 212.214913] epc : ffffffff80c3a930 ra : ffffffff8059ba7e sp : ff20000000eabb50 [ 212.215061] gp : ffffffff82066f90 tp : ff6000008e958000 t0 : 3463303866660000 [ 212.215210] t1 : 000000000000005b t2 : 3463303866666666 s0 : ff20000000eabb60 [ 212.215358] s1 : 0000000000000386 a0 : 00007ff6e81df926 a1 : ff600000824df800 [ 212.215505] a2 : 000000000000003f a3 : 7fffffffffffffc0 a4 : 0000000000000000 [ 212.215651] a5 : 000000000000003f a6 : 0000000000000000 a7 : 0000000000000000 [ 212.215857] s2 : ff600000824df800 s3 : ffffffff82066cc0 s4 : 0000000000001c1a [ 212.216074] s5 : ffffffff8206a5a8 s6 : 00007ff6e81df926 s7 : ffffffff8206a5a0 [ 212.216278] s8 : ff600000824df800 s9 : ffffffff81e25de0 s10: 000000000000003f [ 212.216471] s11: ffffffff8206a59d t3 : ff600000824df812 t4 : ff600000824df812 [ 212.216651] t5 : ff600000824df818 t6 : 0000000000040000 [ 212.216796] status: 0000000000040120 badaddr: 0000000000000000 cause: 8000000000000001 [ 212.217035] [<ffffffff80c3a930>] fallback_scalar_usercopy+0x8/0xdc [ 212.217207] [<ffffffff80095f56>] syslog_print+0x1f4/0x2b2 [ 212.217362] [<ffffffff80096e5c>] do_syslog.part.0+0x94/0x2d8 [ 212.217502] [<ffffffff800979e8>] do_syslog+0x66/0x88 [ 212.217636] [<ffffffff803a5dda>] kmsg_read+0x44/0x5c [ 212.217764] [<ffffffff80392dbe>] proc_reg_read+0x7a/0xa8 [ 212.217952] [<ffffffff802ff726>] vfs_read+0xb0/0x24e [ 212.218090] [<ffffffff803001ba>] ksys_read+0x64/0xe4 [ 212.218264] [<ffffffff8030025a>] __riscv_sys_read+0x20/0x2c [ 212.218453] [<ffffffff80c4af9a>] do_trap_ecall_u+0x60/0x1d4 [ 212.218664] [<ffffffff80c56998>] ret_from_exception+0x0/0x64 Signed-off-by: Ryo Takakura <takakura@valinux.co.jp> Link: https://lore.kernel.org/r/20240718093659.158912-1-takakura@valinux.co.jp Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-18 18:36:59 +09:00
static void riscv_backtrace_ipi(cpumask_t *mask)
{
send_ipi_mask(mask, IPI_CPU_BACKTRACE);
}
void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu)
{
nmi_trigger_cpumask_backtrace(mask, exclude_cpu, riscv_backtrace_ipi);
}
RISC-V: Implement kgdb_roundup_cpus() to enable future NMI Roundup Until now, the generic weak kgdb_roundup_cpus() has been used for kgdb on RISCV. A custom one allows to debug CPUs that are stuck with interrupts disabled with NMI support in the future. And using an IPI is better than the generic one since it avoids the potential situation described in the generic kgdb_call_nmi_hook(). As Andrew pointed out, once there is NMI support, we can easily extend this and the CPU backtrace support to use NMIs. After this patch, the kgdb test show that: # echo g > /proc/sysrq-trigger [2]kdb> btc btc: cpu status: Currently on cpu 2 Available cpus: 0-1(-), 2, 3(-) Stack traceback for pid 0 0xffffffff81c13a40 0 0 1 0 - 0xffffffff81c14510 swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-g3120273055b6-dirty #51 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006c48>] dump_backtrace+0x28/0x30 [<ffffffff80fceb38>] show_stack+0x38/0x44 [<ffffffff80fe6a04>] dump_stack_lvl+0x58/0x7a [<ffffffff80fe6a3e>] dump_stack+0x18/0x20 [<ffffffff801143fa>] kgdb_cpu_enter+0x682/0x6b2 [<ffffffff801144ca>] kgdb_nmicallback+0xa0/0xac [<ffffffff8000a392>] handle_IPI+0x9c/0x120 [<ffffffff800a2baa>] handle_percpu_devid_irq+0xa4/0x1e4 [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff800a9e5c>] ipi_mux_process+0xe8/0x110 [<ffffffff806e1e30>] imsic_handle_irq+0xf8/0x13a [<ffffffff8009cca8>] generic_handle_domain_irq+0x28/0x36 [<ffffffff806dff12>] riscv_intc_aia_irq+0x2e/0x40 [<ffffffff80fe6ab0>] handle_riscv_irq+0x54/0x86 [<ffffffff80ff2e4a>] call_on_irq_stack+0x32/0x40 Rebased on Ryo Takakura's "RISC-V: Enable IPI CPU Backtrace" patch. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Link: https://lore.kernel.org/r/20240727063438.886155-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-07-27 14:34:38 +08:00
#ifdef CONFIG_KGDB
void kgdb_roundup_cpus(void)
{
int this_cpu = raw_smp_processor_id();
int cpu;
for_each_online_cpu(cpu) {
/* No need to roundup ourselves */
if (cpu == this_cpu)
continue;
send_ipi_single(cpu, IPI_KGDB_ROUNDUP);
}
}
#endif