mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2025-08-18 19:18:57 +00:00
2b29be967a
Since commit6b9f29b81b("riscv: Enable pcpu page first chunk allocator"), if NUMA is enabled, the page percpu allocator may be used on very sparse configurations, or when requested on boot with percpu_alloc=page. In that case, percpu data gets put in the vmalloc area. However, sbi_hsm_hart_start() needs the physical address of a sbi_hart_boot_data, and simply assumes that __pa() would work. This causes the just started hart to immediately access an invalid address and hang. Fortunately, struct sbi_hart_boot_data is not too large, so we can simply allocate an array for boot_data statically, putting it in the kernel image. This fixes NUMA=y SMP boot on Sophgo SG2042. To reproduce on QEMU: Set CONFIG_NUMA=y and CONFIG_DEBUG_VIRTUAL=y, then run with: qemu-system-riscv64 -M virt -smp 2 -nographic \ -kernel arch/riscv/boot/Image \ -append "percpu_alloc=page" Kernel output: [ 0.000000] Booting Linux on hartid 0 [ 0.000000] Linux version 6.16.0-rc1 (dram@sakuya) (riscv64-unknown-linux-gnu-gcc (GCC) 14.2.1 20250322, GNU ld (GNU Binutils) 2.44) #11 SMP Tue Jun 24 14:56:22 CST 2025 ... [ 0.000000] percpu: 28 4K pages/cpu s85784 r8192 d20712 ... [ 0.083192] smp: Bringing up secondary CPUs ... [ 0.086722] ------------[ cut here ]------------ [ 0.086849] virt_to_phys used for non-linear address: (____ptrval____) (0xff2000000001d080) [ 0.088001] WARNING: CPU: 0 PID: 1 at arch/riscv/mm/physaddr.c:14 __virt_to_phys+0xae/0xe8 [ 0.088376] Modules linked in: [ 0.088656] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.16.0-rc1 #11 NONE [ 0.088833] Hardware name: riscv-virtio,qemu (DT) [ 0.088948] epc : __virt_to_phys+0xae/0xe8 [ 0.089001] ra : __virt_to_phys+0xae/0xe8 [ 0.089037] epc : ffffffff80021eaa ra : ffffffff80021eaa sp : ff2000000004bbc0 [ 0.089057] gp : ffffffff817f49c0 tp : ff60000001d60000 t0 : 5f6f745f74726976 [ 0.089076] t1 : 0000000000000076 t2 : 705f6f745f747269 s0 : ff2000000004bbe0 [ 0.089095] s1 : ff2000000001d080 a0 : 0000000000000000 a1 : 0000000000000000 [ 0.089113] a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 [ 0.089131] a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000 [ 0.089155] s2 : ffffffff8130dc00 s3 : 0000000000000001 s4 : 0000000000000001 [ 0.089174] s5 : ffffffff8185eff8 s6 : ff2000007f1eb000 s7 : ffffffff8002a2ec [ 0.089193] s8 : 0000000000000001 s9 : 0000000000000001 s10: 0000000000000000 [ 0.089211] s11: 0000000000000000 t3 : ffffffff8180a9f7 t4 : ffffffff8180a9f7 [ 0.089960] t5 : ffffffff8180a9f8 t6 : ff2000000004b9d8 [ 0.089984] status: 0000000200000120 badaddr: ffffffff80021eaa cause: 0000000000000003 [ 0.090101] [<ffffffff80021eaa>] __virt_to_phys+0xae/0xe8 [ 0.090228] [<ffffffff8001d796>] sbi_cpu_start+0x6e/0xe8 [ 0.090247] [<ffffffff8001a5da>] __cpu_up+0x1e/0x8c [ 0.090260] [<ffffffff8002a32e>] bringup_cpu+0x42/0x258 [ 0.090277] [<ffffffff8002914c>] cpuhp_invoke_callback+0xe0/0x40c [ 0.090292] [<ffffffff800294e0>] __cpuhp_invoke_callback_range+0x68/0xfc [ 0.090320] [<ffffffff8002a96a>] _cpu_up+0x11a/0x244 [ 0.090334] [<ffffffff8002aae6>] cpu_up+0x52/0x90 [ 0.090384] [<ffffffff80c09350>] bringup_nonboot_cpus+0x78/0x118 [ 0.090411] [<ffffffff80c11060>] smp_init+0x34/0xb8 [ 0.090425] [<ffffffff80c01220>] kernel_init_freeable+0x148/0x2e4 [ 0.090442] [<ffffffff80b83802>] kernel_init+0x1e/0x14c [ 0.090455] [<ffffffff800124ca>] ret_from_fork_kernel+0xe/0xf0 [ 0.090471] [<ffffffff80b8d9c2>] ret_from_fork_kernel_asm+0x16/0x18 [ 0.090560] ---[ end trace 0000000000000000 ]--- [ 1.179875] CPU1: failed to come online [ 1.190324] smp: Brought up 1 node, 1 CPU Cc: stable@vger.kernel.org Reported-by: Han Gao <rabenda.cn@gmail.com> Fixes:6b9f29b81b("riscv: Enable pcpu page first chunk allocator") Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com> Tested-by: Alexandre Ghiti <alexghiti@rivosinc.com> Signed-off-by: Vivian Wang <wangruikang@iscas.ac.cn> Link: https://lore.kernel.org/r/20250624-riscv-hsm-boot-data-array-v1-1-50b5eeafbe61@iscas.ac.cn Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
111 lines
2.5 KiB
C
111 lines
2.5 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* HSM extension and cpu_ops implementation.
|
|
*
|
|
* Copyright (c) 2020 Western Digital Corporation or its affiliates.
|
|
*/
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/sched/task_stack.h>
|
|
#include <asm/cpu_ops.h>
|
|
#include <asm/cpu_ops_sbi.h>
|
|
#include <asm/sbi.h>
|
|
#include <asm/smp.h>
|
|
|
|
extern char secondary_start_sbi[];
|
|
const struct cpu_operations cpu_ops_sbi;
|
|
|
|
/*
|
|
* Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
|
|
* be invoked from multiple threads in parallel. Define an array of boot data
|
|
* to handle that.
|
|
*/
|
|
static struct sbi_hart_boot_data boot_data[NR_CPUS];
|
|
|
|
static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
|
|
unsigned long priv)
|
|
{
|
|
struct sbiret ret;
|
|
|
|
ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_START,
|
|
hartid, saddr, priv, 0, 0, 0);
|
|
if (ret.error)
|
|
return sbi_err_map_linux_errno(ret.error);
|
|
else
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
static int sbi_hsm_hart_stop(void)
|
|
{
|
|
struct sbiret ret;
|
|
|
|
ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STOP, 0, 0, 0, 0, 0, 0);
|
|
|
|
if (ret.error)
|
|
return sbi_err_map_linux_errno(ret.error);
|
|
else
|
|
return 0;
|
|
}
|
|
|
|
static int sbi_hsm_hart_get_status(unsigned long hartid)
|
|
{
|
|
struct sbiret ret;
|
|
|
|
ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STATUS,
|
|
hartid, 0, 0, 0, 0, 0);
|
|
if (ret.error)
|
|
return sbi_err_map_linux_errno(ret.error);
|
|
else
|
|
return ret.value;
|
|
}
|
|
#endif
|
|
|
|
static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
|
|
{
|
|
unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
|
|
unsigned long hartid = cpuid_to_hartid_map(cpuid);
|
|
unsigned long hsm_data;
|
|
struct sbi_hart_boot_data *bdata = &boot_data[cpuid];
|
|
|
|
/* Make sure tidle is updated */
|
|
smp_mb();
|
|
bdata->task_ptr = tidle;
|
|
bdata->stack_ptr = task_pt_regs(tidle);
|
|
/* Make sure boot data is updated */
|
|
smp_mb();
|
|
hsm_data = __pa(bdata);
|
|
return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
|
|
}
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
static void sbi_cpu_stop(void)
|
|
{
|
|
int ret;
|
|
|
|
ret = sbi_hsm_hart_stop();
|
|
pr_crit("Unable to stop the cpu %u (%d)\n", smp_processor_id(), ret);
|
|
}
|
|
|
|
static int sbi_cpu_is_stopped(unsigned int cpuid)
|
|
{
|
|
int rc;
|
|
unsigned long hartid = cpuid_to_hartid_map(cpuid);
|
|
|
|
rc = sbi_hsm_hart_get_status(hartid);
|
|
|
|
if (rc == SBI_HSM_STATE_STOPPED)
|
|
return 0;
|
|
return rc;
|
|
}
|
|
#endif
|
|
|
|
const struct cpu_operations cpu_ops_sbi = {
|
|
.cpu_start = sbi_cpu_start,
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
.cpu_stop = sbi_cpu_stop,
|
|
.cpu_is_stopped = sbi_cpu_is_stopped,
|
|
#endif
|
|
};
|