linux_dsm_epyc7002/arch/mips/kernel/process.c
Paul Burton b63e132b64
MIPS: Use async IPIs for arch_trigger_cpumask_backtrace()
The current MIPS implementation of arch_trigger_cpumask_backtrace() is
broken because it attempts to use synchronous IPIs despite the fact that
it may be run with interrupts disabled.

This means that when arch_trigger_cpumask_backtrace() is invoked, for
example by the RCU CPU stall watchdog, we may:

  - Deadlock due to use of synchronous IPIs with interrupts disabled,
    causing the CPU that's attempting to generate the backtrace output
    to hang itself.

  - Not succeed in generating the desired output from remote CPUs.

  - Produce warnings about this from smp_call_function_many(), for
    example:

    [42760.526910] INFO: rcu_sched detected stalls on CPUs/tasks:
    [42760.535755]  0-...!: (1 GPs behind) idle=ade/140000000000000/0 softirq=526944/526945 fqs=0
    [42760.547874]  1-...!: (0 ticks this GP) idle=e4a/140000000000000/0 softirq=547885/547885 fqs=0
    [42760.559869]  (detected by 2, t=2162 jiffies, g=266689, c=266688, q=33)
    [42760.568927] ------------[ cut here ]------------
    [42760.576146] WARNING: CPU: 2 PID: 1216 at kernel/smp.c:416 smp_call_function_many+0x88/0x20c
    [42760.587839] Modules linked in:
    [42760.593152] CPU: 2 PID: 1216 Comm: sh Not tainted 4.15.4-00373-gee058bb4d0c2 #2
    [42760.603767] Stack : 8e09bd20 8e09bd20 8e09bd20 fffffff0 00000007 00000006 00000000 8e09bca8
    [42760.616937]         95b2b379 95b2b379 807a0080 00000007 81944518 0000018a 00000032 00000000
    [42760.630095]         00000000 00000030 80000000 00000000 806eca74 00000009 8017e2b8 000001a0
    [42760.643169]         00000000 00000002 00000000 8e09baa4 00000008 808b8008 86d69080 8e09bca0
    [42760.656282]         8e09ad50 805e20aa 00000000 00000000 00000000 8017e2b8 00000009 801070ca
    [42760.669424]         ...
    [42760.673919] Call Trace:
    [42760.678672] [<27fde568>] show_stack+0x70/0xf0
    [42760.685417] [<84751641>] dump_stack+0xaa/0xd0
    [42760.692188] [<699d671c>] __warn+0x80/0x92
    [42760.698549] [<68915d41>] warn_slowpath_null+0x28/0x36
    [42760.705912] [<f7c76c1c>] smp_call_function_many+0x88/0x20c
    [42760.713696] [<6bbdfc2a>] arch_trigger_cpumask_backtrace+0x30/0x4a
    [42760.722216] [<f845bd33>] rcu_dump_cpu_stacks+0x6a/0x98
    [42760.729580] [<796e7629>] rcu_check_callbacks+0x672/0x6ac
    [42760.737476] [<059b3b43>] update_process_times+0x18/0x34
    [42760.744981] [<6eb94941>] tick_sched_handle.isra.5+0x26/0x38
    [42760.752793] [<478d3d70>] tick_sched_timer+0x1c/0x50
    [42760.759882] [<e56ea39f>] __hrtimer_run_queues+0xc6/0x226
    [42760.767418] [<e88bbcae>] hrtimer_interrupt+0x88/0x19a
    [42760.775031] [<6765a19e>] gic_compare_interrupt+0x2e/0x3a
    [42760.782761] [<0558bf5f>] handle_percpu_devid_irq+0x78/0x168
    [42760.790795] [<90c11ba2>] generic_handle_irq+0x1e/0x2c
    [42760.798117] [<1b6d462c>] gic_handle_local_int+0x38/0x86
    [42760.805545] [<b2ada1c7>] gic_irq_dispatch+0xa/0x14
    [42760.812534] [<90c11ba2>] generic_handle_irq+0x1e/0x2c
    [42760.820086] [<c7521934>] do_IRQ+0x16/0x20
    [42760.826274] [<9aef3ce6>] plat_irq_dispatch+0x62/0x94
    [42760.833458] [<6a94b53c>] except_vec_vi_end+0x70/0x78
    [42760.840655] [<22284043>] smp_call_function_many+0x1ba/0x20c
    [42760.848501] [<54022b58>] smp_call_function+0x1e/0x2c
    [42760.855693] [<ab9fc705>] flush_tlb_mm+0x2a/0x98
    [42760.862730] [<0844cdd0>] tlb_flush_mmu+0x1c/0x44
    [42760.869628] [<cb259b74>] arch_tlb_finish_mmu+0x26/0x3e
    [42760.877021] [<1aeaaf74>] tlb_finish_mmu+0x18/0x66
    [42760.883907] [<b3fce717>] exit_mmap+0x76/0xea
    [42760.890428] [<c4c8a2f6>] mmput+0x80/0x11a
    [42760.896632] [<a41a08f4>] do_exit+0x1f4/0x80c
    [42760.903158] [<ee01cef6>] do_group_exit+0x20/0x7e
    [42760.909990] [<13fa8d54>] __wake_up_parent+0x0/0x1e
    [42760.917045] [<46cf89d0>] smp_call_function_many+0x1a2/0x20c
    [42760.924893] [<8c21a93b>] syscall_common+0x14/0x1c
    [42760.931765] ---[ end trace 02aa09da9dc52a60 ]---
    [42760.938342] ------------[ cut here ]------------
    [42760.945311] WARNING: CPU: 2 PID: 1216 at kernel/smp.c:291 smp_call_function_single+0xee/0xf8
    ...

This patch switches MIPS' arch_trigger_cpumask_backtrace() to use async
IPIs & smp_call_function_single_async() in order to resolve this
problem. We ensure use of the pre-allocated call_single_data_t
structures is serialized by maintaining a cpumask indicating that
they're busy, and refusing to attempt to send an IPI when a CPU's bit is
set in this mask. This should only happen if a CPU hasn't responded to a
previous backtrace IPI - ie. if it's hung - and we print a warning to
the console in this case.

I've marked this for stable branches as far back as v4.9, to which it
applies cleanly. Strictly speaking the faulty MIPS implementation can be
traced further back to commit 856839b768 ("MIPS: Add
arch_trigger_all_cpu_backtrace() function") in v3.19, but kernel
versions v3.19 through v4.8 will require further work to backport due to
the rework performed in commit 9a01c3ed5c ("nmi_backtrace: add more
trigger_*_cpu_backtrace() methods").

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19597/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: linux-mips@linux-mips.org
Cc: stable@vger.kernel.org # v4.9+
Fixes: 856839b768 ("MIPS: Add arch_trigger_all_cpu_backtrace() function")
Fixes: 9a01c3ed5c ("nmi_backtrace: add more trigger_*_cpu_backtrace() methods")
2018-06-28 14:14:41 -07:00

851 lines
20 KiB
C

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 1994 - 1999, 2000 by Ralf Baechle and others.
* Copyright (C) 2005, 2006 by Ralf Baechle (ralf@linux-mips.org)
* Copyright (C) 1999, 2000 Silicon Graphics, Inc.
* Copyright (C) 2004 Thiemo Seufer
* Copyright (C) 2013 Imagination Technologies Ltd.
*/
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/tick.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/export.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/personality.h>
#include <linux/sys.h>
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/kallsyms.h>
#include <linux/random.h>
#include <linux/prctl.h>
#include <linux/nmi.h>
#include <asm/asm.h>
#include <asm/bootinfo.h>
#include <asm/cpu.h>
#include <asm/dsemul.h>
#include <asm/dsp.h>
#include <asm/fpu.h>
#include <asm/irq.h>
#include <asm/msa.h>
#include <asm/pgtable.h>
#include <asm/mipsregs.h>
#include <asm/processor.h>
#include <asm/reg.h>
#include <linux/uaccess.h>
#include <asm/io.h>
#include <asm/elf.h>
#include <asm/isadep.h>
#include <asm/inst.h>
#include <asm/stacktrace.h>
#include <asm/irq_regs.h>
#ifdef CONFIG_HOTPLUG_CPU
void arch_cpu_idle_dead(void)
{
play_dead();
}
#endif
asmlinkage void ret_from_fork(void);
asmlinkage void ret_from_kernel_thread(void);
void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
{
unsigned long status;
/* New thread loses kernel privileges. */
status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK);
status |= KU_USER;
regs->cp0_status = status;
lose_fpu(0);
clear_thread_flag(TIF_MSA_CTX_LIVE);
clear_used_math();
atomic_set(&current->thread.bd_emu_frame, BD_EMUFRAME_NONE);
init_dsp();
regs->cp0_epc = pc;
regs->regs[29] = sp;
}
void exit_thread(struct task_struct *tsk)
{
/*
* User threads may have allocated a delay slot emulation frame.
* If so, clean up that allocation.
*/
if (!(current->flags & PF_KTHREAD))
dsemul_thread_cleanup(tsk);
}
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
/*
* Save any process state which is live in hardware registers to the
* parent context prior to duplication. This prevents the new child
* state becoming stale if the parent is preempted before copy_thread()
* gets a chance to save the parent's live hardware registers to the
* child context.
*/
preempt_disable();
if (is_msa_enabled())
save_msa(current);
else if (is_fpu_owner())
_save_fp(current);
save_dsp(current);
preempt_enable();
*dst = *src;
return 0;
}
/*
* Copy architecture-specific thread state
*/
int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
{
struct thread_info *ti = task_thread_info(p);
struct pt_regs *childregs, *regs = current_pt_regs();
unsigned long childksp;
childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
/* set up new TSS. */
childregs = (struct pt_regs *) childksp - 1;
/* Put the stack after the struct pt_regs. */
childksp = (unsigned long) childregs;
p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1);
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
unsigned long status = p->thread.cp0_status;
memset(childregs, 0, sizeof(struct pt_regs));
ti->addr_limit = KERNEL_DS;
p->thread.reg16 = usp; /* fn */
p->thread.reg17 = kthread_arg;
p->thread.reg29 = childksp;
p->thread.reg31 = (unsigned long) ret_from_kernel_thread;
#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
status = (status & ~(ST0_KUP | ST0_IEP | ST0_IEC)) |
((status & (ST0_KUC | ST0_IEC)) << 2);
#else
status |= ST0_EXL;
#endif
childregs->cp0_status = status;
return 0;
}
/* user thread */
*childregs = *regs;
childregs->regs[7] = 0; /* Clear error flag */
childregs->regs[2] = 0; /* Child gets zero as return value */
if (usp)
childregs->regs[29] = usp;
ti->addr_limit = USER_DS;
p->thread.reg29 = (unsigned long) childregs;
p->thread.reg31 = (unsigned long) ret_from_fork;
/*
* New tasks lose permission to use the fpu. This accelerates context
* switching for most programs since they don't use the fpu.
*/
childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
clear_tsk_thread_flag(p, TIF_USEDFPU);
clear_tsk_thread_flag(p, TIF_USEDMSA);
clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE);
#ifdef CONFIG_MIPS_MT_FPAFF
clear_tsk_thread_flag(p, TIF_FPUBOUND);
#endif /* CONFIG_MIPS_MT_FPAFF */
atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE);
if (clone_flags & CLONE_SETTLS)
ti->tp_value = tls;
return 0;
}
#ifdef CONFIG_STACKPROTECTOR
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
EXPORT_SYMBOL(__stack_chk_guard);
#endif
struct mips_frame_info {
void *func;
unsigned long func_size;
int frame_size;
int pc_offset;
};
#define J_TARGET(pc,target) \
(((unsigned long)(pc) & 0xf0000000) | ((target) << 2))
static inline int is_ra_save_ins(union mips_instruction *ip, int *poff)
{
#ifdef CONFIG_CPU_MICROMIPS
/*
* swsp ra,offset
* swm16 reglist,offset(sp)
* swm32 reglist,offset(sp)
* sw32 ra,offset(sp)
* jradiussp - NOT SUPPORTED
*
* microMIPS is way more fun...
*/
if (mm_insn_16bit(ip->word >> 16)) {
switch (ip->mm16_r5_format.opcode) {
case mm_swsp16_op:
if (ip->mm16_r5_format.rt != 31)
return 0;
*poff = ip->mm16_r5_format.imm;
*poff = (*poff << 2) / sizeof(ulong);
return 1;
case mm_pool16c_op:
switch (ip->mm16_m_format.func) {
case mm_swm16_op:
*poff = ip->mm16_m_format.imm;
*poff += 1 + ip->mm16_m_format.rlist;
*poff = (*poff << 2) / sizeof(ulong);
return 1;
default:
return 0;
}
default:
return 0;
}
}
switch (ip->i_format.opcode) {
case mm_sw32_op:
if (ip->i_format.rs != 29)
return 0;
if (ip->i_format.rt != 31)
return 0;
*poff = ip->i_format.simmediate / sizeof(ulong);
return 1;
case mm_pool32b_op:
switch (ip->mm_m_format.func) {
case mm_swm32_func:
if (ip->mm_m_format.rd < 0x10)
return 0;
if (ip->mm_m_format.base != 29)
return 0;
*poff = ip->mm_m_format.simmediate;
*poff += (ip->mm_m_format.rd & 0xf) * sizeof(u32);
*poff /= sizeof(ulong);
return 1;
default:
return 0;
}
default:
return 0;
}
#else
/* sw / sd $ra, offset($sp) */
if ((ip->i_format.opcode == sw_op || ip->i_format.opcode == sd_op) &&
ip->i_format.rs == 29 && ip->i_format.rt == 31) {
*poff = ip->i_format.simmediate / sizeof(ulong);
return 1;
}
return 0;
#endif
}
static inline int is_jump_ins(union mips_instruction *ip)
{
#ifdef CONFIG_CPU_MICROMIPS
/*
* jr16,jrc,jalr16,jalr16
* jal
* jalr/jr,jalr.hb/jr.hb,jalrs,jalrs.hb
* jraddiusp - NOT SUPPORTED
*
* microMIPS is kind of more fun...
*/
if (mm_insn_16bit(ip->word >> 16)) {
if ((ip->mm16_r5_format.opcode == mm_pool16c_op &&
(ip->mm16_r5_format.rt & mm_jr16_op) == mm_jr16_op))
return 1;
return 0;
}
if (ip->j_format.opcode == mm_j32_op)
return 1;
if (ip->j_format.opcode == mm_jal32_op)
return 1;
if (ip->r_format.opcode != mm_pool32a_op ||
ip->r_format.func != mm_pool32axf_op)
return 0;
return ((ip->u_format.uimmediate >> 6) & mm_jalr_op) == mm_jalr_op;
#else
if (ip->j_format.opcode == j_op)
return 1;
if (ip->j_format.opcode == jal_op)
return 1;
if (ip->r_format.opcode != spec_op)
return 0;
return ip->r_format.func == jalr_op || ip->r_format.func == jr_op;
#endif
}
static inline int is_sp_move_ins(union mips_instruction *ip, int *frame_size)
{
#ifdef CONFIG_CPU_MICROMIPS
unsigned short tmp;
/*
* addiusp -imm
* addius5 sp,-imm
* addiu32 sp,sp,-imm
* jradiussp - NOT SUPPORTED
*
* microMIPS is not more fun...
*/
if (mm_insn_16bit(ip->word >> 16)) {
if (ip->mm16_r3_format.opcode == mm_pool16d_op &&
ip->mm16_r3_format.simmediate & mm_addiusp_func) {
tmp = ip->mm_b0_format.simmediate >> 1;
tmp = ((tmp & 0x1ff) ^ 0x100) - 0x100;
if ((tmp + 2) < 4) /* 0x0,0x1,0x1fe,0x1ff are special */
tmp ^= 0x100;
*frame_size = -(signed short)(tmp << 2);
return 1;
}
if (ip->mm16_r5_format.opcode == mm_pool16d_op &&
ip->mm16_r5_format.rt == 29) {
tmp = ip->mm16_r5_format.imm >> 1;
*frame_size = -(signed short)(tmp & 0xf);
return 1;
}
return 0;
}
if (ip->mm_i_format.opcode == mm_addiu32_op &&
ip->mm_i_format.rt == 29 && ip->mm_i_format.rs == 29) {
*frame_size = -ip->i_format.simmediate;
return 1;
}
#else
/* addiu/daddiu sp,sp,-imm */
if (ip->i_format.rs != 29 || ip->i_format.rt != 29)
return 0;
if (ip->i_format.opcode == addiu_op ||
ip->i_format.opcode == daddiu_op) {
*frame_size = -ip->i_format.simmediate;
return 1;
}
#endif
return 0;
}
static int get_frame_info(struct mips_frame_info *info)
{
bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS);
union mips_instruction insn, *ip, *ip_end;
const unsigned int max_insns = 128;
unsigned int last_insn_size = 0;
unsigned int i;
bool saw_jump = false;
info->pc_offset = -1;
info->frame_size = 0;
ip = (void *)msk_isa16_mode((ulong)info->func);
if (!ip)
goto err;
ip_end = (void *)ip + info->func_size;
for (i = 0; i < max_insns && ip < ip_end; i++) {
ip = (void *)ip + last_insn_size;
if (is_mmips && mm_insn_16bit(ip->halfword[0])) {
insn.word = ip->halfword[0] << 16;
last_insn_size = 2;
} else if (is_mmips) {
insn.word = ip->halfword[0] << 16 | ip->halfword[1];
last_insn_size = 4;
} else {
insn.word = ip->word;
last_insn_size = 4;
}
if (!info->frame_size) {
is_sp_move_ins(&insn, &info->frame_size);
continue;
} else if (!saw_jump && is_jump_ins(ip)) {
/*
* If we see a jump instruction, we are finished
* with the frame save.
*
* Some functions can have a shortcut return at
* the beginning of the function, so don't start
* looking for jump instruction until we see the
* frame setup.
*
* The RA save instruction can get put into the
* delay slot of the jump instruction, so look
* at the next instruction, too.
*/
saw_jump = true;
continue;
}
if (info->pc_offset == -1 &&
is_ra_save_ins(&insn, &info->pc_offset))
break;
if (saw_jump)
break;
}
if (info->frame_size && info->pc_offset >= 0) /* nested */
return 0;
if (info->pc_offset < 0) /* leaf */
return 1;
/* prologue seems bogus... */
err:
return -1;
}
static struct mips_frame_info schedule_mfi __read_mostly;
#ifdef CONFIG_KALLSYMS
static unsigned long get___schedule_addr(void)
{
return kallsyms_lookup_name("__schedule");
}
#else
static unsigned long get___schedule_addr(void)
{
union mips_instruction *ip = (void *)schedule;
int max_insns = 8;
int i;
for (i = 0; i < max_insns; i++, ip++) {
if (ip->j_format.opcode == j_op)
return J_TARGET(ip, ip->j_format.target);
}
return 0;
}
#endif
static int __init frame_info_init(void)
{
unsigned long size = 0;
#ifdef CONFIG_KALLSYMS
unsigned long ofs;
#endif
unsigned long addr;
addr = get___schedule_addr();
if (!addr)
addr = (unsigned long)schedule;
#ifdef CONFIG_KALLSYMS
kallsyms_lookup_size_offset(addr, &size, &ofs);
#endif
schedule_mfi.func = (void *)addr;
schedule_mfi.func_size = size;
get_frame_info(&schedule_mfi);
/*
* Without schedule() frame info, result given by
* thread_saved_pc() and get_wchan() are not reliable.
*/
if (schedule_mfi.pc_offset < 0)
printk("Can't analyze schedule() prologue at %p\n", schedule);
return 0;
}
arch_initcall(frame_info_init);
/*
* Return saved PC of a blocked thread.
*/
static unsigned long thread_saved_pc(struct task_struct *tsk)
{
struct thread_struct *t = &tsk->thread;
/* New born processes are a special case */
if (t->reg31 == (unsigned long) ret_from_fork)
return t->reg31;
if (schedule_mfi.pc_offset < 0)
return 0;
return ((unsigned long *)t->reg29)[schedule_mfi.pc_offset];
}
#ifdef CONFIG_KALLSYMS
/* generic stack unwinding function */
unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
unsigned long *sp,
unsigned long pc,
unsigned long *ra)
{
unsigned long low, high, irq_stack_high;
struct mips_frame_info info;
unsigned long size, ofs;
struct pt_regs *regs;
int leaf;
if (!stack_page)
return 0;
/*
* IRQ stacks start at IRQ_STACK_START
* task stacks at THREAD_SIZE - 32
*/
low = stack_page;
if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) {
high = stack_page + IRQ_STACK_START;
irq_stack_high = high;
} else {
high = stack_page + THREAD_SIZE - 32;
irq_stack_high = 0;
}
/*
* If we reached the top of the interrupt stack, start unwinding
* the interrupted task stack.
*/
if (unlikely(*sp == irq_stack_high)) {
unsigned long task_sp = *(unsigned long *)*sp;
/*
* Check that the pointer saved in the IRQ stack head points to
* something within the stack of the current task
*/
if (!object_is_on_stack((void *)task_sp))
return 0;
/*
* Follow pointer to tasks kernel stack frame where interrupted
* state was saved.
*/
regs = (struct pt_regs *)task_sp;
pc = regs->cp0_epc;
if (!user_mode(regs) && __kernel_text_address(pc)) {
*sp = regs->regs[29];
*ra = regs->regs[31];
return pc;
}
return 0;
}
if (!kallsyms_lookup_size_offset(pc, &size, &ofs))
return 0;
/*
* Return ra if an exception occurred at the first instruction
*/
if (unlikely(ofs == 0)) {
pc = *ra;
*ra = 0;
return pc;
}
info.func = (void *)(pc - ofs);
info.func_size = ofs; /* analyze from start to ofs */
leaf = get_frame_info(&info);
if (leaf < 0)
return 0;
if (*sp < low || *sp + info.frame_size > high)
return 0;
if (leaf)
/*
* For some extreme cases, get_frame_info() can
* consider wrongly a nested function as a leaf
* one. In that cases avoid to return always the
* same value.
*/
pc = pc != *ra ? *ra : 0;
else
pc = ((unsigned long *)(*sp))[info.pc_offset];
*sp += info.frame_size;
*ra = 0;
return __kernel_text_address(pc) ? pc : 0;
}
EXPORT_SYMBOL(unwind_stack_by_address);
/* used by show_backtrace() */
unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
unsigned long pc, unsigned long *ra)
{
unsigned long stack_page = 0;
int cpu;
for_each_possible_cpu(cpu) {
if (on_irq_stack(cpu, *sp)) {
stack_page = (unsigned long)irq_stack[cpu];
break;
}
}
if (!stack_page)
stack_page = (unsigned long)task_stack_page(task);
return unwind_stack_by_address(stack_page, sp, pc, ra);
}
#endif
/*
* get_wchan - a maintenance nightmare^W^Wpain in the ass ...
*/
unsigned long get_wchan(struct task_struct *task)
{
unsigned long pc = 0;
#ifdef CONFIG_KALLSYMS
unsigned long sp;
unsigned long ra = 0;
#endif
if (!task || task == current || task->state == TASK_RUNNING)
goto out;
if (!task_stack_page(task))
goto out;
pc = thread_saved_pc(task);
#ifdef CONFIG_KALLSYMS
sp = task->thread.reg29 + schedule_mfi.frame_size;
while (in_sched_functions(pc))
pc = unwind_stack(task, &sp, pc, &ra);
#endif
out:
return pc;
}
/*
* Don't forget that the stack pointer must be aligned on a 8 bytes
* boundary for 32-bits ABI and 16 bytes for 64-bits ABI.
*/
unsigned long arch_align_stack(unsigned long sp)
{
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
sp -= get_random_int() & ~PAGE_MASK;
return sp & ALMASK;
}
static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
static struct cpumask backtrace_csd_busy;
static void handle_backtrace(void *info)
{
nmi_cpu_backtrace(get_irq_regs());
cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
}
static void raise_backtrace(cpumask_t *mask)
{
call_single_data_t *csd;
int cpu;
for_each_cpu(cpu, mask) {
/*
* If we previously sent an IPI to the target CPU & it hasn't
* cleared its bit in the busy cpumask then it didn't handle
* our previous IPI & it's not safe for us to reuse the
* call_single_data_t.
*/
if (cpumask_test_and_set_cpu(cpu, &backtrace_csd_busy)) {
pr_warn("Unable to send backtrace IPI to CPU%u - perhaps it hung?\n",
cpu);
continue;
}
csd = &per_cpu(backtrace_csd, cpu);
csd->func = handle_backtrace;
smp_call_function_single_async(cpu, csd);
}
}
void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
{
nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace);
}
int mips_get_process_fp_mode(struct task_struct *task)
{
int value = 0;
if (!test_tsk_thread_flag(task, TIF_32BIT_FPREGS))
value |= PR_FP_MODE_FR;
if (test_tsk_thread_flag(task, TIF_HYBRID_FPREGS))
value |= PR_FP_MODE_FRE;
return value;
}
static void prepare_for_fp_mode_switch(void *info)
{
struct mm_struct *mm = info;
if (current->mm == mm)
lose_fpu(1);
}
int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
{
const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE;
struct task_struct *t;
int max_users;
/* If nothing to change, return right away, successfully. */
if (value == mips_get_process_fp_mode(task))
return 0;
/* Only accept a mode change if 64-bit FP enabled for o32. */
if (!IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT))
return -EOPNOTSUPP;
/* And only for o32 tasks. */
if (IS_ENABLED(CONFIG_64BIT) && !test_thread_flag(TIF_32BIT_REGS))
return -EOPNOTSUPP;
/* Check the value is valid */
if (value & ~known_bits)
return -EOPNOTSUPP;
/* Setting FRE without FR is not supported. */
if ((value & (PR_FP_MODE_FR | PR_FP_MODE_FRE)) == PR_FP_MODE_FRE)
return -EOPNOTSUPP;
/* Avoid inadvertently triggering emulation */
if ((value & PR_FP_MODE_FR) && raw_cpu_has_fpu &&
!(raw_current_cpu_data.fpu_id & MIPS_FPIR_F64))
return -EOPNOTSUPP;
if ((value & PR_FP_MODE_FRE) && raw_cpu_has_fpu && !cpu_has_fre)
return -EOPNOTSUPP;
/* FR = 0 not supported in MIPS R6 */
if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
return -EOPNOTSUPP;
/* Proceed with the mode switch */
preempt_disable();
/* Save FP & vector context, then disable FPU & MSA */
if (task->signal == current->signal)
lose_fpu(1);
/* Prevent any threads from obtaining live FP context */
atomic_set(&task->mm->context.fp_mode_switching, 1);
smp_mb__after_atomic();
/*
* If there are multiple online CPUs then force any which are running
* threads in this process to lose their FPU context, which they can't
* regain until fp_mode_switching is cleared later.
*/
if (num_online_cpus() > 1) {
/* No need to send an IPI for the local CPU */
max_users = (task->mm == current->mm) ? 1 : 0;
if (atomic_read(&current->mm->mm_users) > max_users)
smp_call_function(prepare_for_fp_mode_switch,
(void *)current->mm, 1);
}
/*
* There are now no threads of the process with live FP context, so it
* is safe to proceed with the FP mode switch.
*/
for_each_thread(task, t) {
/* Update desired FP register width */
if (value & PR_FP_MODE_FR) {
clear_tsk_thread_flag(t, TIF_32BIT_FPREGS);
} else {
set_tsk_thread_flag(t, TIF_32BIT_FPREGS);
clear_tsk_thread_flag(t, TIF_MSA_CTX_LIVE);
}
/* Update desired FP single layout */
if (value & PR_FP_MODE_FRE)
set_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
else
clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
}
/* Allow threads to use FP again */
atomic_set(&task->mm->context.fp_mode_switching, 0);
preempt_enable();
wake_up_var(&task->mm->context.fp_mode_switching);
return 0;
}
#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
void mips_dump_regs32(u32 *uregs, const struct pt_regs *regs)
{
unsigned int i;
for (i = MIPS32_EF_R1; i <= MIPS32_EF_R31; i++) {
/* k0/k1 are copied as zero. */
if (i == MIPS32_EF_R26 || i == MIPS32_EF_R27)
uregs[i] = 0;
else
uregs[i] = regs->regs[i - MIPS32_EF_R0];
}
uregs[MIPS32_EF_LO] = regs->lo;
uregs[MIPS32_EF_HI] = regs->hi;
uregs[MIPS32_EF_CP0_EPC] = regs->cp0_epc;
uregs[MIPS32_EF_CP0_BADVADDR] = regs->cp0_badvaddr;
uregs[MIPS32_EF_CP0_STATUS] = regs->cp0_status;
uregs[MIPS32_EF_CP0_CAUSE] = regs->cp0_cause;
}
#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
#ifdef CONFIG_64BIT
void mips_dump_regs64(u64 *uregs, const struct pt_regs *regs)
{
unsigned int i;
for (i = MIPS64_EF_R1; i <= MIPS64_EF_R31; i++) {
/* k0/k1 are copied as zero. */
if (i == MIPS64_EF_R26 || i == MIPS64_EF_R27)
uregs[i] = 0;
else
uregs[i] = regs->regs[i - MIPS64_EF_R0];
}
uregs[MIPS64_EF_LO] = regs->lo;
uregs[MIPS64_EF_HI] = regs->hi;
uregs[MIPS64_EF_CP0_EPC] = regs->cp0_epc;
uregs[MIPS64_EF_CP0_BADVADDR] = regs->cp0_badvaddr;
uregs[MIPS64_EF_CP0_STATUS] = regs->cp0_status;
uregs[MIPS64_EF_CP0_CAUSE] = regs->cp0_cause;
}
#endif /* CONFIG_64BIT */