Select Git revision
amdgpu_fb.c
-
Rex Zhu authored
this bug happened when amdgpu load failed. [ 75.740951] BUG: unable to handle kernel paging request at 00000000000031c0 [ 75.748167] IP: [<ffffffffa064a0e0>] amdgpu_fbdev_restore_mode+0x20/0x60 [amdgpu] [ 75.755774] PGD 0 [ 75.759185] Oops: 0000 [#1] SMP [ 75.762408] Modules linked in: amdgpu(OE-) ttm(OE) drm_kms_helper(OE) drm(OE) i2c_algo_bit(E) fb_sys_fops(E) syscopyarea(E) sysfillrect(E) sysimgblt(E) rpcsec_gss_krb5(E) nfsv4(E) nfs(E) fscache(E) eeepc_wmi(E) asus_wmi(E) sparse_keymap(E) intel_rapl(E) snd_hda_codec_hdmi(E) snd_hda_codec_realtek(E) snd_hda_codec_generic(E) snd_hda_intel(E) snd_hda_codec(E) snd_hda_core(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) snd_hwdep(E) snd_pcm(E) snd_seq_midi(E) coretemp(E) kvm_intel(E) snd_seq_midi_event(E) snd_rawmidi(E) kvm(E) snd_seq(E) joydev(E) snd_seq_device(E) snd_timer(E) irqbypass(E) crct10dif_pclmul(E) crc32_pclmul(E) mei_me(E) ghash_clmulni_intel(E) snd(E) aesni_intel(E) mei(E) soundcore(E) aes_x86_64(E) shpchp(E) serio_raw(E) lrw(E) acpi_pad(E) gf128mul(E) glue_helper(E) ablk_helper(E) mac_hid(E) [ 75.835574] cryptd(E) parport_pc(E) ppdev(E) lp(E) nfsd(E) parport(E) auth_rpcgss(E) nfs_acl(E) lockd(E) grace(E) sunrpc(E) autofs4(E) hid_generic(E) usbhid(E) mxm_wmi(E) psmouse(E) e1000e(E) ptp(E) pps_core(E) ahci(E) libahci(E) wmi(E) video(E) i2c_hid(E) hid(E) [ 75.858489] CPU: 5 PID: 1603 Comm: rmmod Tainted: G OE 4.9.0-custom #2 [ 75.866183] Hardware name: System manufacturer System Product Name/Z170-A, BIOS 0901 08/31/2015 [ 75.875050] task: ffff88045d1bbb80 task.stack: ffffc90002de4000 [ 75.881094] RIP: 0010:[<ffffffffa064a0e0>] [<ffffffffa064a0e0>] amdgpu_fbdev_restore_mode+0x20/0x60 [amdgpu] [ 75.891238] RSP: 0018:ffffc90002de7d48 EFLAGS: 00010286 [ 75.896648] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000001 [ 75.903933] RDX: 0000000000000000 RSI: ffff88045d1bbb80 RDI: 0000000000000286 [ 75.911183] RBP: ffffc90002de7d50 R08: 0000000000000502 R09: 0000000000000004 [ 75.918449] R10: 0000000000000000 R11: 0000000000000001 R12: ffff880464bf0000 [ 75.925675] R13: ffffffffa0853000 R14: 0000000000000000 R15: 0000564e44f88210 [ 75.932980] FS: 00007f13d5400700(0000) GS:ffff880476540000(0000) knlGS:0000000000000000 [ 75.941238] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 75.947088] CR2: 00000000000031c0 CR3: 000000045fd0b000 CR4: 00000000003406e0 [ 75.954332] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 75.961566] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 75.968834] Stack: [ 75.970881] ffff880464bf0000 ffffc90002de7d60 ffffffffa0636592 ffffc90002de7d80 [ 75.978454] ffffffffa059015f ffff880464bf0000 ffff880464bf0000 ffffc90002de7da8 [ 75.986076] ffffffffa0595216 ffff880464bf0000 ffff880460f4d000 ffffffffa0853000 [ 75.993692] Call Trace: [ 75.996177] [<ffffffffa0636592>] amdgpu_driver_lastclose_kms+0x12/0x20 [amdgpu] [ 76.003700] [<ffffffffa059015f>] drm_lastclose+0x2f/0xd0 [drm] [ 76.009777] [<ffffffffa0595216>] drm_dev_unregister+0x16/0xd0 [drm] [ 76.016255] [<ffffffffa0595944>] drm_put_dev+0x34/0x70 [drm] [ 76.022139] [<ffffffffa062f365>] amdgpu_pci_remove+0x15/0x20 [amdgpu] [ 76.028800] [<ffffffff81416499>] pci_device_remove+0x39/0xc0 [ 76.034661] [<ffffffff81531caa>] __device_release_driver+0x9a/0x140 [ 76.041121] [<ffffffff81531e58>] driver_detach+0xb8/0xc0 [ 76.046575] [<ffffffff81530c95>] bus_remove_driver+0x55/0xd0 [ 76.052401] [<ffffffff815325fc>] driver_unregister+0x2c/0x50 [ 76.058244] [<ffffffff81416289>] pci_unregister_driver+0x29/0x90 [ 76.064466] [<ffffffffa0596c5e>] drm_pci_exit+0x9e/0xb0 [drm] [ 76.070507] [<ffffffffa0796d71>] amdgpu_exit+0x1c/0x32 [amdgpu] [ 76.076609] [<ffffffff81104810>] SyS_delete_module+0x1a0/0x200 [ 76.082627] [<ffffffff810e2b1a>] ? rcu_eqs_enter.isra.36+0x4a/0x50 [ 76.089001] [<ffffffff8100392e>] do_syscall_64+0x6e/0x180 [ 76.094583] [<ffffffff817e1d2f>] entry_SYSCALL64_slow_path+0x25/0x25 [ 76.101114] Code: 94 c0 c3 31 c0 5d c3 0f 1f 40 00 0f 1f 44 00 00 55 31 c0 48 89 e5 53 48 89 fb 48 c7 c7 1d 21 84 a0 e8 ab 77 b3 e0 e8 fc 8b d7 e0 <48> 8b bb c0 31 00 00 48 85 ff 74 09 e8 ff eb fc ff 85 c0 75 03 [ 76.121432] RIP [<ffffffffa064a0e0>] amdgpu_fbdev_restore_mode+0x20/0x60 [amdgpu] Signed-off-by:
Rex Zhu <Rex.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
Rex Zhu authoredthis bug happened when amdgpu load failed. [ 75.740951] BUG: unable to handle kernel paging request at 00000000000031c0 [ 75.748167] IP: [<ffffffffa064a0e0>] amdgpu_fbdev_restore_mode+0x20/0x60 [amdgpu] [ 75.755774] PGD 0 [ 75.759185] Oops: 0000 [#1] SMP [ 75.762408] Modules linked in: amdgpu(OE-) ttm(OE) drm_kms_helper(OE) drm(OE) i2c_algo_bit(E) fb_sys_fops(E) syscopyarea(E) sysfillrect(E) sysimgblt(E) rpcsec_gss_krb5(E) nfsv4(E) nfs(E) fscache(E) eeepc_wmi(E) asus_wmi(E) sparse_keymap(E) intel_rapl(E) snd_hda_codec_hdmi(E) snd_hda_codec_realtek(E) snd_hda_codec_generic(E) snd_hda_intel(E) snd_hda_codec(E) snd_hda_core(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) snd_hwdep(E) snd_pcm(E) snd_seq_midi(E) coretemp(E) kvm_intel(E) snd_seq_midi_event(E) snd_rawmidi(E) kvm(E) snd_seq(E) joydev(E) snd_seq_device(E) snd_timer(E) irqbypass(E) crct10dif_pclmul(E) crc32_pclmul(E) mei_me(E) ghash_clmulni_intel(E) snd(E) aesni_intel(E) mei(E) soundcore(E) aes_x86_64(E) shpchp(E) serio_raw(E) lrw(E) acpi_pad(E) gf128mul(E) glue_helper(E) ablk_helper(E) mac_hid(E) [ 75.835574] cryptd(E) parport_pc(E) ppdev(E) lp(E) nfsd(E) parport(E) auth_rpcgss(E) nfs_acl(E) lockd(E) grace(E) sunrpc(E) autofs4(E) hid_generic(E) usbhid(E) mxm_wmi(E) psmouse(E) e1000e(E) ptp(E) pps_core(E) ahci(E) libahci(E) wmi(E) video(E) i2c_hid(E) hid(E) [ 75.858489] CPU: 5 PID: 1603 Comm: rmmod Tainted: G OE 4.9.0-custom #2 [ 75.866183] Hardware name: System manufacturer System Product Name/Z170-A, BIOS 0901 08/31/2015 [ 75.875050] task: ffff88045d1bbb80 task.stack: ffffc90002de4000 [ 75.881094] RIP: 0010:[<ffffffffa064a0e0>] [<ffffffffa064a0e0>] amdgpu_fbdev_restore_mode+0x20/0x60 [amdgpu] [ 75.891238] RSP: 0018:ffffc90002de7d48 EFLAGS: 00010286 [ 75.896648] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000001 [ 75.903933] RDX: 0000000000000000 RSI: ffff88045d1bbb80 RDI: 0000000000000286 [ 75.911183] RBP: ffffc90002de7d50 R08: 0000000000000502 R09: 0000000000000004 [ 75.918449] R10: 0000000000000000 R11: 0000000000000001 R12: ffff880464bf0000 [ 75.925675] R13: ffffffffa0853000 R14: 0000000000000000 R15: 0000564e44f88210 [ 75.932980] FS: 00007f13d5400700(0000) GS:ffff880476540000(0000) knlGS:0000000000000000 [ 75.941238] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 75.947088] CR2: 00000000000031c0 CR3: 000000045fd0b000 CR4: 00000000003406e0 [ 75.954332] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 75.961566] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 75.968834] Stack: [ 75.970881] ffff880464bf0000 ffffc90002de7d60 ffffffffa0636592 ffffc90002de7d80 [ 75.978454] ffffffffa059015f ffff880464bf0000 ffff880464bf0000 ffffc90002de7da8 [ 75.986076] ffffffffa0595216 ffff880464bf0000 ffff880460f4d000 ffffffffa0853000 [ 75.993692] Call Trace: [ 75.996177] [<ffffffffa0636592>] amdgpu_driver_lastclose_kms+0x12/0x20 [amdgpu] [ 76.003700] [<ffffffffa059015f>] drm_lastclose+0x2f/0xd0 [drm] [ 76.009777] [<ffffffffa0595216>] drm_dev_unregister+0x16/0xd0 [drm] [ 76.016255] [<ffffffffa0595944>] drm_put_dev+0x34/0x70 [drm] [ 76.022139] [<ffffffffa062f365>] amdgpu_pci_remove+0x15/0x20 [amdgpu] [ 76.028800] [<ffffffff81416499>] pci_device_remove+0x39/0xc0 [ 76.034661] [<ffffffff81531caa>] __device_release_driver+0x9a/0x140 [ 76.041121] [<ffffffff81531e58>] driver_detach+0xb8/0xc0 [ 76.046575] [<ffffffff81530c95>] bus_remove_driver+0x55/0xd0 [ 76.052401] [<ffffffff815325fc>] driver_unregister+0x2c/0x50 [ 76.058244] [<ffffffff81416289>] pci_unregister_driver+0x29/0x90 [ 76.064466] [<ffffffffa0596c5e>] drm_pci_exit+0x9e/0xb0 [drm] [ 76.070507] [<ffffffffa0796d71>] amdgpu_exit+0x1c/0x32 [amdgpu] [ 76.076609] [<ffffffff81104810>] SyS_delete_module+0x1a0/0x200 [ 76.082627] [<ffffffff810e2b1a>] ? rcu_eqs_enter.isra.36+0x4a/0x50 [ 76.089001] [<ffffffff8100392e>] do_syscall_64+0x6e/0x180 [ 76.094583] [<ffffffff817e1d2f>] entry_SYSCALL64_slow_path+0x25/0x25 [ 76.101114] Code: 94 c0 c3 31 c0 5d c3 0f 1f 40 00 0f 1f 44 00 00 55 31 c0 48 89 e5 53 48 89 fb 48 c7 c7 1d 21 84 a0 e8 ab 77 b3 e0 e8 fc 8b d7 e0 <48> 8b bb c0 31 00 00 48 85 ff 74 09 e8 ff eb fc ff 85 c0 75 03 [ 76.121432] RIP [<ffffffffa064a0e0>] amdgpu_fbdev_restore_mode+0x20/0x60 [amdgpu] Signed-off-by:
Rex Zhu <Rex.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
trace_stack.c 7.33 KiB
/*
* Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
*
*/
#include <linux/stacktrace.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/uaccess.h>
#include <linux/debugfs.h>
#include <linux/ftrace.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/init.h>
#include <linux/fs.h>
#include "trace.h"
#define STACK_TRACE_ENTRIES 500
static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
{ [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
static struct stack_trace max_stack_trace = {
.max_entries = STACK_TRACE_ENTRIES,
.entries = stack_dump_trace,
};
static unsigned long max_stack_size;
static raw_spinlock_t max_stack_lock =
(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
static int stack_trace_disabled __read_mostly;
static DEFINE_PER_CPU(int, trace_active);
static DEFINE_MUTEX(stack_sysctl_mutex);
int stack_tracer_enabled;
static int last_stack_tracer_enabled;
static inline void check_stack(void)
{
unsigned long this_size, flags;
unsigned long *p, *top, *start;
int i;
this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
this_size = THREAD_SIZE - this_size;
if (this_size <= max_stack_size)
return;
/* we do not handle interrupt stacks yet */
if (!object_is_on_stack(&this_size))
return;
local_irq_save(flags);
__raw_spin_lock(&max_stack_lock);
/* a race could have already updated it */
if (this_size <= max_stack_size)
goto out;
max_stack_size = this_size;
max_stack_trace.nr_entries = 0;
max_stack_trace.skip = 3;
save_stack_trace(&max_stack_trace);
/*
* Now find where in the stack these are.
*/
i = 0;
start = &this_size;
top = (unsigned long *)
(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
/*
* Loop through all the entries. One of the entries may
* for some reason be missed on the stack, so we may
* have to account for them. If they are all there, this
* loop will only happen once. This code only takes place
* on a new max, so it is far from a fast path.
*/
while (i < max_stack_trace.nr_entries) {
int found = 0;
stack_dump_index[i] = this_size;
p = start;
for (; p < top && i < max_stack_trace.nr_entries; p++) {
if (*p == stack_dump_trace[i]) {
this_size = stack_dump_index[i++] =
(top - p) * sizeof(unsigned long);
found = 1;
/* Start the search from here */
start = p + 1;
}
}
if (!found)
i++;
}
out:
__raw_spin_unlock(&max_stack_lock);
local_irq_restore(flags);
}
static void
stack_trace_call(unsigned long ip, unsigned long parent_ip)
{
int cpu, resched;
if (unlikely(!ftrace_enabled || stack_trace_disabled))
return;
resched = ftrace_preempt_disable();
cpu = raw_smp_processor_id();
/* no atomic needed, we only modify this variable by this cpu */
if (per_cpu(trace_active, cpu)++ != 0)
goto out;
check_stack();
out:
per_cpu(trace_active, cpu)--;
/* prevent recursion in schedule */
ftrace_preempt_enable(resched);
}
static struct ftrace_ops trace_ops __read_mostly =
{
.func = stack_trace_call,
};
static ssize_t
stack_max_size_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
unsigned long *ptr = filp->private_data;
char buf[64];
int r;
r = snprintf(buf, sizeof(buf), "%ld\n", *ptr);
if (r > sizeof(buf))
r = sizeof(buf);
return simple_read_from_buffer(ubuf, count, ppos, buf, r);
}
static ssize_t
stack_max_size_write(struct file *filp, const char __user *ubuf,
size_t count, loff_t *ppos)
{
long *ptr = filp->private_data;
unsigned long val, flags;
char buf[64];
int ret;
if (count >= sizeof(buf))
return -EINVAL;
if (copy_from_user(&buf, ubuf, count))
return -EFAULT;
buf[count] = 0;
ret = strict_strtoul(buf, 10, &val);
if (ret < 0)
return ret;
local_irq_save(flags);
__raw_spin_lock(&max_stack_lock);
*ptr = val;
__raw_spin_unlock(&max_stack_lock);
local_irq_restore(flags);
return count;
}
static const struct file_operations stack_max_size_fops = {
.open = tracing_open_generic,
.read = stack_max_size_read,
.write = stack_max_size_write,
};
static void *
__next(struct seq_file *m, loff_t *pos)
{
long n = *pos - 1;
if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
return NULL;
m->private = (void *)n;
return &m->private;
}
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
(*pos)++;
return __next(m, pos);
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
local_irq_disable();
__raw_spin_lock(&max_stack_lock);
if (*pos == 0)
return SEQ_START_TOKEN;
return __next(m, pos);
}
static void t_stop(struct seq_file *m, void *p)
{
__raw_spin_unlock(&max_stack_lock);
local_irq_enable();
}
static int trace_lookup_stack(struct seq_file *m, long i)
{
unsigned long addr = stack_dump_trace[i];
return seq_printf(m, "%pF\n", (void *)addr);
}
static void print_disabled(struct seq_file *m)
{
seq_puts(m, "#\n"
"# Stack tracer disabled\n"
"#\n"
"# To enable the stack tracer, either add 'stacktrace' to the\n"
"# kernel command line\n"
"# or 'echo 1 > /proc/sys/kernel/stack_tracer_enabled'\n"
"#\n");
}
static int t_show(struct seq_file *m, void *v)
{
long i;
int size;
if (v == SEQ_START_TOKEN) {
seq_printf(m, " Depth Size Location"
" (%d entries)\n"
" ----- ---- --------\n",
max_stack_trace.nr_entries - 1);
if (!stack_tracer_enabled && !max_stack_size)
print_disabled(m);
return 0;
}
i = *(long *)v;
if (i >= max_stack_trace.nr_entries ||
stack_dump_trace[i] == ULONG_MAX)
return 0;
if (i+1 == max_stack_trace.nr_entries ||
stack_dump_trace[i+1] == ULONG_MAX)
size = stack_dump_index[i];
else
size = stack_dump_index[i] - stack_dump_index[i+1];
seq_printf(m, "%3ld) %8d %5d ", i, stack_dump_index[i], size);
trace_lookup_stack(m, i);
return 0;
}
static const struct seq_operations stack_trace_seq_ops = {
.start = t_start,
.next = t_next,
.stop = t_stop,
.show = t_show,
};
static int stack_trace_open(struct inode *inode, struct file *file)
{
return seq_open(file, &stack_trace_seq_ops);
}
static const struct file_operations stack_trace_fops = {
.open = stack_trace_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
int
stack_trace_sysctl(struct ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
mutex_lock(&stack_sysctl_mutex);
ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
if (ret || !write ||
(last_stack_tracer_enabled == !!stack_tracer_enabled))
goto out;
last_stack_tracer_enabled = !!stack_tracer_enabled;
if (stack_tracer_enabled)
register_ftrace_function(&trace_ops);
else
unregister_ftrace_function(&trace_ops);
out:
mutex_unlock(&stack_sysctl_mutex);
return ret;
}
static __init int enable_stacktrace(char *str)
{
stack_tracer_enabled = 1;
last_stack_tracer_enabled = 1;
return 1;
}
__setup("stacktrace", enable_stacktrace);
static __init int stack_trace_init(void)
{
struct dentry *d_tracer;
d_tracer = tracing_init_dentry();
trace_create_file("stack_max_size", 0644, d_tracer,
&max_stack_size, &stack_max_size_fops);
trace_create_file("stack_trace", 0444, d_tracer,
NULL, &stack_trace_fops);
if (stack_tracer_enabled)
register_ftrace_function(&trace_ops);
return 0;
}
device_initcall(stack_trace_init);