linux_dsm_epyc7002/arch/x86/kernel/dumpstack_64.c

335 lines
8.2 KiB
C
Raw Normal View History

/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
*/
#include <linux/kallsyms.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/hardirq.h>
#include <linux/kdebug.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/kexec.h>
#include <linux/sysfs.h>
#include <linux/bug.h>
#include <linux/nmi.h>
#include <asm/stacktrace.h>
#define N_EXCEPTION_STACKS_END \
(N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
static char x86_stack_ids[][8] = {
[ DEBUG_STACK-1 ] = "#DB",
[ NMI_STACK-1 ] = "NMI",
[ DOUBLEFAULT_STACK-1 ] = "#DF",
[ STACKFAULT_STACK-1 ] = "#SS",
[ MCE_STACK-1 ] = "#MC",
#if DEBUG_STKSZ > EXCEPTION_STKSZ
[ N_EXCEPTION_STACKS ...
N_EXCEPTION_STACKS_END ] = "#DB[?]"
#endif
};
static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
unsigned *usedp, char **idp)
{
unsigned k;
/*
* Iterate over all exception stacks, and figure out whether
* 'stack' is in one of them:
*/
for (k = 0; k < N_EXCEPTION_STACKS; k++) {
unsigned long end = per_cpu(orig_ist, cpu).ist[k];
/*
* Is 'stack' above this exception frame's end?
* If yes then skip to the next frame.
*/
if (stack >= end)
continue;
/*
* Is 'stack' above this exception frame's start address?
* If yes then we found the right frame.
*/
if (stack >= end - EXCEPTION_STKSZ) {
/*
* Make sure we only iterate through an exception
* stack once. If it comes up for the second time
* then there's something wrong going on - just
* break out and return NULL:
*/
if (*usedp & (1U << k))
break;
*usedp |= 1U << k;
*idp = x86_stack_ids[k];
return (unsigned long *)end;
}
/*
* If this is a debug stack, and if it has a larger size than
* the usual exception stacks, then 'stack' might still
* be within the lower portion of the debug stack:
*/
#if DEBUG_STKSZ > EXCEPTION_STKSZ
if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) {
unsigned j = N_EXCEPTION_STACKS - 1;
/*
* Black magic. A large debug stack is composed of
* multiple exception stack entries, which we
* iterate through now. Dont look:
*/
do {
++j;
end -= EXCEPTION_STKSZ;
x86_stack_ids[j][4] = '1' +
(j - N_EXCEPTION_STACKS);
} while (stack < end - EXCEPTION_STKSZ);
if (*usedp & (1U << j))
break;
*usedp |= 1U << j;
*idp = x86_stack_ids[j];
return (unsigned long *)end;
}
#endif
}
return NULL;
}
x86: Fixup wrong irq frame link in stacktraces When we enter in irq, two things can happen to preserve the link to the previous frame pointer: - If we were in an irq already, we don't switch to the irq stack as we are inside. We just need to save the previous frame pointer and to link the new one to the previous. - Otherwise we need another level of indirection. We enter the irq with the previous stack. We save the previous bp inside and make bp pointing to its saved address. Then we switch to the irq stack and push bp another time but to the new stack. This makes two levels to dereference instead of one. In the second case, the current stacktrace code omits the second level and loses the frame pointer accuracy. The stack that follows will then be considered as unreliable. Handling that makes the perf callchain happier. Before: 43.94% [k] _raw_read_lock | --- _read_lock | |--60.53%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | synaptics_process_byte | psmouse_handle_byte | psmouse_interrupt | serio_interrupt | i8042_interrupt | handle_IRQ_event | handle_edge_irq | handle_irq | __irqentry_text_start | ret_from_intr | | | |--30.43%-- __select | | | |--17.39%-- 0x454f15 | | | |--13.04%-- __read | | | |--13.04%-- vread_hpet | | | |--13.04%-- _xcb_lock_io | | | --13.04%-- 0x7f630878ce8 After: 50.00% [k] _raw_read_lock | --- _read_lock | |--98.97%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | | | |--96.88%-- synaptics_process_byte | | psmouse_handle_byte | | psmouse_interrupt | | serio_interrupt | | i8042_interrupt | | handle_IRQ_event | | handle_edge_irq | | handle_irq | | __irqentry_text_start | | ret_from_intr | | | | | |--39.78%-- __const_udelay | | | | | | | |--91.89%-- ath5k_hw_register_timeout | | | | ath5k_hw_noise_floor_calibration | | | | ath5k_hw_reset | | | | ath5k_reset | | | | ath5k_config | | | | ieee80211_hw_config | | | | | | | | | |--88.24%-- ieee80211_scan_work | | | | | worker_thread | | | | | kthread | | | | | child_rip | | | | | | | | | --11.76%-- ieee80211_scan_completed | | | | ieee80211_scan_work | | | | worker_thread | | | | kthread | | | | child_rip | | | | | | | --8.11%-- ath5k_hw_noise_floor_calibration | | | ath5k_hw_reset | | | ath5k_reset | | | ath5k_config Note: This does not only affect perf events but also x86-64 stacktraces. They were considered as unreliable once we quit the irq stack frame. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "K. Prasad" <prasad@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com>
2009-12-06 11:34:27 +07:00
static inline int
in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
unsigned long *irq_stack_end)
{
return (stack >= irq_stack && stack < irq_stack_end);
}
/*
* We are returning from the irq stack and go to the previous one.
* If the previous stack is also in the irq stack, then bp in the first
* frame of the irq stack points to the previous, interrupted one.
* Otherwise we have another level of indirection: We first save
* the bp of the previous stack, then we switch the stack to the irq one
* and save a new bp that links to the previous one.
* (See save_args())
*/
static inline unsigned long
fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
unsigned long *irq_stack, unsigned long *irq_stack_end)
{
#ifdef CONFIG_FRAME_POINTER
struct stack_frame *frame = (struct stack_frame *)bp;
unsigned long next;
x86: Fixup wrong irq frame link in stacktraces When we enter in irq, two things can happen to preserve the link to the previous frame pointer: - If we were in an irq already, we don't switch to the irq stack as we are inside. We just need to save the previous frame pointer and to link the new one to the previous. - Otherwise we need another level of indirection. We enter the irq with the previous stack. We save the previous bp inside and make bp pointing to its saved address. Then we switch to the irq stack and push bp another time but to the new stack. This makes two levels to dereference instead of one. In the second case, the current stacktrace code omits the second level and loses the frame pointer accuracy. The stack that follows will then be considered as unreliable. Handling that makes the perf callchain happier. Before: 43.94% [k] _raw_read_lock | --- _read_lock | |--60.53%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | synaptics_process_byte | psmouse_handle_byte | psmouse_interrupt | serio_interrupt | i8042_interrupt | handle_IRQ_event | handle_edge_irq | handle_irq | __irqentry_text_start | ret_from_intr | | | |--30.43%-- __select | | | |--17.39%-- 0x454f15 | | | |--13.04%-- __read | | | |--13.04%-- vread_hpet | | | |--13.04%-- _xcb_lock_io | | | --13.04%-- 0x7f630878ce8 After: 50.00% [k] _raw_read_lock | --- _read_lock | |--98.97%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | | | |--96.88%-- synaptics_process_byte | | psmouse_handle_byte | | psmouse_interrupt | | serio_interrupt | | i8042_interrupt | | handle_IRQ_event | | handle_edge_irq | | handle_irq | | __irqentry_text_start | | ret_from_intr | | | | | |--39.78%-- __const_udelay | | | | | | | |--91.89%-- ath5k_hw_register_timeout | | | | ath5k_hw_noise_floor_calibration | | | | ath5k_hw_reset | | | | ath5k_reset | | | | ath5k_config | | | | ieee80211_hw_config | | | | | | | | | |--88.24%-- ieee80211_scan_work | | | | | worker_thread | | | | | kthread | | | | | child_rip | | | | | | | | | --11.76%-- ieee80211_scan_completed | | | | ieee80211_scan_work | | | | worker_thread | | | | kthread | | | | child_rip | | | | | | | --8.11%-- ath5k_hw_noise_floor_calibration | | | ath5k_hw_reset | | | ath5k_reset | | | ath5k_config Note: This does not only affect perf events but also x86-64 stacktraces. They were considered as unreliable once we quit the irq stack frame. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "K. Prasad" <prasad@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com>
2009-12-06 11:34:27 +07:00
if (!in_irq_stack(stack, irq_stack, irq_stack_end)) {
if (!probe_kernel_address(&frame->next_frame, next))
return next;
else
WARN_ONCE(1, "Perf: bad frame pointer = %p in "
"callchain\n", &frame->next_frame);
}
x86: Fixup wrong irq frame link in stacktraces When we enter in irq, two things can happen to preserve the link to the previous frame pointer: - If we were in an irq already, we don't switch to the irq stack as we are inside. We just need to save the previous frame pointer and to link the new one to the previous. - Otherwise we need another level of indirection. We enter the irq with the previous stack. We save the previous bp inside and make bp pointing to its saved address. Then we switch to the irq stack and push bp another time but to the new stack. This makes two levels to dereference instead of one. In the second case, the current stacktrace code omits the second level and loses the frame pointer accuracy. The stack that follows will then be considered as unreliable. Handling that makes the perf callchain happier. Before: 43.94% [k] _raw_read_lock | --- _read_lock | |--60.53%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | synaptics_process_byte | psmouse_handle_byte | psmouse_interrupt | serio_interrupt | i8042_interrupt | handle_IRQ_event | handle_edge_irq | handle_irq | __irqentry_text_start | ret_from_intr | | | |--30.43%-- __select | | | |--17.39%-- 0x454f15 | | | |--13.04%-- __read | | | |--13.04%-- vread_hpet | | | |--13.04%-- _xcb_lock_io | | | --13.04%-- 0x7f630878ce8 After: 50.00% [k] _raw_read_lock | --- _read_lock | |--98.97%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | | | |--96.88%-- synaptics_process_byte | | psmouse_handle_byte | | psmouse_interrupt | | serio_interrupt | | i8042_interrupt | | handle_IRQ_event | | handle_edge_irq | | handle_irq | | __irqentry_text_start | | ret_from_intr | | | | | |--39.78%-- __const_udelay | | | | | | | |--91.89%-- ath5k_hw_register_timeout | | | | ath5k_hw_noise_floor_calibration | | | | ath5k_hw_reset | | | | ath5k_reset | | | | ath5k_config | | | | ieee80211_hw_config | | | | | | | | | |--88.24%-- ieee80211_scan_work | | | | | worker_thread | | | | | kthread | | | | | child_rip | | | | | | | | | --11.76%-- ieee80211_scan_completed | | | | ieee80211_scan_work | | | | worker_thread | | | | kthread | | | | child_rip | | | | | | | --8.11%-- ath5k_hw_noise_floor_calibration | | | ath5k_hw_reset | | | ath5k_reset | | | ath5k_config Note: This does not only affect perf events but also x86-64 stacktraces. They were considered as unreliable once we quit the irq stack frame. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "K. Prasad" <prasad@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com>
2009-12-06 11:34:27 +07:00
#endif
return bp;
}
/*
* x86-64 can have up to three kernel stacks:
* process stack
* interrupt stack
* severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
*/
x86, dumpstack: Correct stack dump info when frame pointer is available Current stack dump code scans entire stack and check each entry contains a pointer to kernel code. If CONFIG_FRAME_POINTER=y it could mark whether the pointer is valid or not based on value of the frame pointer. Invalid entries could be preceded by '?' sign. However this was not going to happen because scan start point was always higher than the frame pointer so that they could not meet. Commit 9c0729dc8062 ("x86: Eliminate bp argument from the stack tracing routines") delayed bp acquisition point, so the bp was read in lower frame, thus all of the entries were marked invalid. This patch fixes this by reverting above commit while retaining stack_frame() helper as suggested by Frederic Weisbecker. End result looks like below: before: [ 3.508329] Call Trace: [ 3.508551] [<ffffffff814f35c9>] ? panic+0x91/0x199 [ 3.508662] [<ffffffff814f3739>] ? printk+0x68/0x6a [ 3.508770] [<ffffffff81a981b2>] ? mount_block_root+0x257/0x26e [ 3.508876] [<ffffffff81a9821f>] ? mount_root+0x56/0x5a [ 3.508975] [<ffffffff81a98393>] ? prepare_namespace+0x170/0x1a9 [ 3.509216] [<ffffffff81a9772b>] ? kernel_init+0x1d2/0x1e2 [ 3.509335] [<ffffffff81003894>] ? kernel_thread_helper+0x4/0x10 [ 3.509442] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.509542] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.509641] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 after: [ 3.522991] Call Trace: [ 3.523351] [<ffffffff814f35b9>] panic+0x91/0x199 [ 3.523468] [<ffffffff814f3729>] ? printk+0x68/0x6a [ 3.523576] [<ffffffff81a981b2>] mount_block_root+0x257/0x26e [ 3.523681] [<ffffffff81a9821f>] mount_root+0x56/0x5a [ 3.523780] [<ffffffff81a98393>] prepare_namespace+0x170/0x1a9 [ 3.523885] [<ffffffff81a9772b>] kernel_init+0x1d2/0x1e2 [ 3.523987] [<ffffffff81003894>] kernel_thread_helper+0x4/0x10 [ 3.524228] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.524345] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.524445] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 -v5: * fix build breakage with oprofile -v4: * use 0 instead of regs->bp * separate out printk changes -v3: * apply comment from Frederic * add a couple of printk fixes Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Soren Sandmann <ssp@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <1300416006-3163-1-git-send-email-namhyung@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-03-18 09:40:06 +07:00
void dump_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
unsigned long *irq_stack_end =
(unsigned long *)per_cpu(irq_stack_ptr, cpu);
unsigned used = 0;
struct thread_info *tinfo;
int graph = 0;
unsigned long dummy;
if (!task)
task = current;
if (!stack) {
stack = &dummy;
if (task && task != current)
stack = (unsigned long *)task->thread.sp;
}
x86, dumpstack: Correct stack dump info when frame pointer is available Current stack dump code scans entire stack and check each entry contains a pointer to kernel code. If CONFIG_FRAME_POINTER=y it could mark whether the pointer is valid or not based on value of the frame pointer. Invalid entries could be preceded by '?' sign. However this was not going to happen because scan start point was always higher than the frame pointer so that they could not meet. Commit 9c0729dc8062 ("x86: Eliminate bp argument from the stack tracing routines") delayed bp acquisition point, so the bp was read in lower frame, thus all of the entries were marked invalid. This patch fixes this by reverting above commit while retaining stack_frame() helper as suggested by Frederic Weisbecker. End result looks like below: before: [ 3.508329] Call Trace: [ 3.508551] [<ffffffff814f35c9>] ? panic+0x91/0x199 [ 3.508662] [<ffffffff814f3739>] ? printk+0x68/0x6a [ 3.508770] [<ffffffff81a981b2>] ? mount_block_root+0x257/0x26e [ 3.508876] [<ffffffff81a9821f>] ? mount_root+0x56/0x5a [ 3.508975] [<ffffffff81a98393>] ? prepare_namespace+0x170/0x1a9 [ 3.509216] [<ffffffff81a9772b>] ? kernel_init+0x1d2/0x1e2 [ 3.509335] [<ffffffff81003894>] ? kernel_thread_helper+0x4/0x10 [ 3.509442] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.509542] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.509641] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 after: [ 3.522991] Call Trace: [ 3.523351] [<ffffffff814f35b9>] panic+0x91/0x199 [ 3.523468] [<ffffffff814f3729>] ? printk+0x68/0x6a [ 3.523576] [<ffffffff81a981b2>] mount_block_root+0x257/0x26e [ 3.523681] [<ffffffff81a9821f>] mount_root+0x56/0x5a [ 3.523780] [<ffffffff81a98393>] prepare_namespace+0x170/0x1a9 [ 3.523885] [<ffffffff81a9772b>] kernel_init+0x1d2/0x1e2 [ 3.523987] [<ffffffff81003894>] kernel_thread_helper+0x4/0x10 [ 3.524228] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.524345] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.524445] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 -v5: * fix build breakage with oprofile -v4: * use 0 instead of regs->bp * separate out printk changes -v3: * apply comment from Frederic * add a couple of printk fixes Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Soren Sandmann <ssp@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <1300416006-3163-1-git-send-email-namhyung@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-03-18 09:40:06 +07:00
if (!bp)
bp = stack_frame(task, regs);
/*
* Print function call entries in all stacks, starting at the
* current stack address. If the stacks consist of nested
* exceptions
*/
tinfo = task_thread_info(task);
for (;;) {
char *id;
unsigned long *estack_end;
estack_end = in_exception_stack(cpu, (unsigned long)stack,
&used, &id);
if (estack_end) {
if (ops->stack(data, id) < 0)
break;
bp = ops->walk_stack(tinfo, stack, bp, ops,
data, estack_end, &graph);
ops->stack(data, "<EOE>");
/*
* We link to the next stack via the
* second-to-last pointer (index -2 to end) in the
* exception stack:
*/
stack = (unsigned long *) estack_end[-2];
continue;
}
if (irq_stack_end) {
unsigned long *irq_stack;
irq_stack = irq_stack_end -
(IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
x86: Fixup wrong irq frame link in stacktraces When we enter in irq, two things can happen to preserve the link to the previous frame pointer: - If we were in an irq already, we don't switch to the irq stack as we are inside. We just need to save the previous frame pointer and to link the new one to the previous. - Otherwise we need another level of indirection. We enter the irq with the previous stack. We save the previous bp inside and make bp pointing to its saved address. Then we switch to the irq stack and push bp another time but to the new stack. This makes two levels to dereference instead of one. In the second case, the current stacktrace code omits the second level and loses the frame pointer accuracy. The stack that follows will then be considered as unreliable. Handling that makes the perf callchain happier. Before: 43.94% [k] _raw_read_lock | --- _read_lock | |--60.53%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | synaptics_process_byte | psmouse_handle_byte | psmouse_interrupt | serio_interrupt | i8042_interrupt | handle_IRQ_event | handle_edge_irq | handle_irq | __irqentry_text_start | ret_from_intr | | | |--30.43%-- __select | | | |--17.39%-- 0x454f15 | | | |--13.04%-- __read | | | |--13.04%-- vread_hpet | | | |--13.04%-- _xcb_lock_io | | | --13.04%-- 0x7f630878ce8 After: 50.00% [k] _raw_read_lock | --- _read_lock | |--98.97%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | | | |--96.88%-- synaptics_process_byte | | psmouse_handle_byte | | psmouse_interrupt | | serio_interrupt | | i8042_interrupt | | handle_IRQ_event | | handle_edge_irq | | handle_irq | | __irqentry_text_start | | ret_from_intr | | | | | |--39.78%-- __const_udelay | | | | | | | |--91.89%-- ath5k_hw_register_timeout | | | | ath5k_hw_noise_floor_calibration | | | | ath5k_hw_reset | | | | ath5k_reset | | | | ath5k_config | | | | ieee80211_hw_config | | | | | | | | | |--88.24%-- ieee80211_scan_work | | | | | worker_thread | | | | | kthread | | | | | child_rip | | | | | | | | | --11.76%-- ieee80211_scan_completed | | | | ieee80211_scan_work | | | | worker_thread | | | | kthread | | | | child_rip | | | | | | | --8.11%-- ath5k_hw_noise_floor_calibration | | | ath5k_hw_reset | | | ath5k_reset | | | ath5k_config Note: This does not only affect perf events but also x86-64 stacktraces. They were considered as unreliable once we quit the irq stack frame. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "K. Prasad" <prasad@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com>
2009-12-06 11:34:27 +07:00
if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
if (ops->stack(data, "IRQ") < 0)
break;
bp = ops->walk_stack(tinfo, stack, bp,
ops, data, irq_stack_end, &graph);
/*
* We link to the next stack (which would be
* the process stack normally) the last
* pointer (index -1 to end) in the IRQ stack:
*/
stack = (unsigned long *) (irq_stack_end[-1]);
x86: Fixup wrong irq frame link in stacktraces When we enter in irq, two things can happen to preserve the link to the previous frame pointer: - If we were in an irq already, we don't switch to the irq stack as we are inside. We just need to save the previous frame pointer and to link the new one to the previous. - Otherwise we need another level of indirection. We enter the irq with the previous stack. We save the previous bp inside and make bp pointing to its saved address. Then we switch to the irq stack and push bp another time but to the new stack. This makes two levels to dereference instead of one. In the second case, the current stacktrace code omits the second level and loses the frame pointer accuracy. The stack that follows will then be considered as unreliable. Handling that makes the perf callchain happier. Before: 43.94% [k] _raw_read_lock | --- _read_lock | |--60.53%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | synaptics_process_byte | psmouse_handle_byte | psmouse_interrupt | serio_interrupt | i8042_interrupt | handle_IRQ_event | handle_edge_irq | handle_irq | __irqentry_text_start | ret_from_intr | | | |--30.43%-- __select | | | |--17.39%-- 0x454f15 | | | |--13.04%-- __read | | | |--13.04%-- vread_hpet | | | |--13.04%-- _xcb_lock_io | | | --13.04%-- 0x7f630878ce8 After: 50.00% [k] _raw_read_lock | --- _read_lock | |--98.97%-- send_sigio | __kill_fasync | kill_fasync | evdev_pass_event | evdev_event | input_pass_event | input_handle_event | input_event | | | |--96.88%-- synaptics_process_byte | | psmouse_handle_byte | | psmouse_interrupt | | serio_interrupt | | i8042_interrupt | | handle_IRQ_event | | handle_edge_irq | | handle_irq | | __irqentry_text_start | | ret_from_intr | | | | | |--39.78%-- __const_udelay | | | | | | | |--91.89%-- ath5k_hw_register_timeout | | | | ath5k_hw_noise_floor_calibration | | | | ath5k_hw_reset | | | | ath5k_reset | | | | ath5k_config | | | | ieee80211_hw_config | | | | | | | | | |--88.24%-- ieee80211_scan_work | | | | | worker_thread | | | | | kthread | | | | | child_rip | | | | | | | | | --11.76%-- ieee80211_scan_completed | | | | ieee80211_scan_work | | | | worker_thread | | | | kthread | | | | child_rip | | | | | | | --8.11%-- ath5k_hw_noise_floor_calibration | | | ath5k_hw_reset | | | ath5k_reset | | | ath5k_config Note: This does not only affect perf events but also x86-64 stacktraces. They were considered as unreliable once we quit the irq stack frame. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "K. Prasad" <prasad@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com>
2009-12-06 11:34:27 +07:00
bp = fixup_bp_irq_link(bp, stack, irq_stack,
irq_stack_end);
irq_stack_end = NULL;
ops->stack(data, "EOI");
continue;
}
}
break;
}
/*
* This handles the process stack:
*/
bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
put_cpu();
}
EXPORT_SYMBOL(dump_trace);
void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
x86, dumpstack: Correct stack dump info when frame pointer is available Current stack dump code scans entire stack and check each entry contains a pointer to kernel code. If CONFIG_FRAME_POINTER=y it could mark whether the pointer is valid or not based on value of the frame pointer. Invalid entries could be preceded by '?' sign. However this was not going to happen because scan start point was always higher than the frame pointer so that they could not meet. Commit 9c0729dc8062 ("x86: Eliminate bp argument from the stack tracing routines") delayed bp acquisition point, so the bp was read in lower frame, thus all of the entries were marked invalid. This patch fixes this by reverting above commit while retaining stack_frame() helper as suggested by Frederic Weisbecker. End result looks like below: before: [ 3.508329] Call Trace: [ 3.508551] [<ffffffff814f35c9>] ? panic+0x91/0x199 [ 3.508662] [<ffffffff814f3739>] ? printk+0x68/0x6a [ 3.508770] [<ffffffff81a981b2>] ? mount_block_root+0x257/0x26e [ 3.508876] [<ffffffff81a9821f>] ? mount_root+0x56/0x5a [ 3.508975] [<ffffffff81a98393>] ? prepare_namespace+0x170/0x1a9 [ 3.509216] [<ffffffff81a9772b>] ? kernel_init+0x1d2/0x1e2 [ 3.509335] [<ffffffff81003894>] ? kernel_thread_helper+0x4/0x10 [ 3.509442] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.509542] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.509641] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 after: [ 3.522991] Call Trace: [ 3.523351] [<ffffffff814f35b9>] panic+0x91/0x199 [ 3.523468] [<ffffffff814f3729>] ? printk+0x68/0x6a [ 3.523576] [<ffffffff81a981b2>] mount_block_root+0x257/0x26e [ 3.523681] [<ffffffff81a9821f>] mount_root+0x56/0x5a [ 3.523780] [<ffffffff81a98393>] prepare_namespace+0x170/0x1a9 [ 3.523885] [<ffffffff81a9772b>] kernel_init+0x1d2/0x1e2 [ 3.523987] [<ffffffff81003894>] kernel_thread_helper+0x4/0x10 [ 3.524228] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.524345] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.524445] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 -v5: * fix build breakage with oprofile -v4: * use 0 instead of regs->bp * separate out printk changes -v3: * apply comment from Frederic * add a couple of printk fixes Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Soren Sandmann <ssp@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <1300416006-3163-1-git-send-email-namhyung@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-03-18 09:40:06 +07:00
unsigned long *sp, unsigned long bp, char *log_lvl)
{
x86: dumpstack, 64-bit: Disable preemption when walking the IRQ/exception stacks This warning: [ 847.140022] rb_producer D 0000000000000000 5928 519 2 0x00000000 [ 847.203627] BUG: using smp_processor_id() in preemptible [00000000] code: khungtaskd/517 [ 847.207360] caller is show_stack_log_lvl+0x2e/0x241 [ 847.210364] Pid: 517, comm: khungtaskd Not tainted 2.6.32-rc8-tip+ #13761 [ 847.213395] Call Trace: [ 847.215847] [<ffffffff81413bde>] debug_smp_processor_id+0x1f0/0x20a [ 847.216809] [<ffffffff81015eae>] show_stack_log_lvl+0x2e/0x241 [ 847.220027] [<ffffffff81018512>] show_stack+0x1c/0x1e [ 847.223365] [<ffffffff8107b7db>] sched_show_task+0xe4/0xe9 [ 847.226694] [<ffffffff8112f21f>] check_hung_task+0x140/0x199 [ 847.230261] [<ffffffff8112f4a8>] check_hung_uninterruptible_tasks+0x1b7/0x20f [ 847.233371] [<ffffffff8112f500>] ? watchdog+0x0/0x50 [ 847.236683] [<ffffffff8112f54e>] watchdog+0x4e/0x50 [ 847.240034] [<ffffffff810cee56>] kthread+0x97/0x9f [ 847.243372] [<ffffffff81012aea>] child_rip+0xa/0x20 [ 847.246690] [<ffffffff81e43494>] ? restore_args+0x0/0x30 [ 847.250019] [<ffffffff81e43083>] ? _spin_lock+0xe/0x10 [ 847.253351] [<ffffffff810cedbf>] ? kthread+0x0/0x9f [ 847.256833] [<ffffffff81012ae0>] ? child_rip+0x0/0x20 Happens because on preempt-RCU, khungd calls show_stack() with preemption enabled. Make sure we are not preemptible while walking the IRQ and exception stacks on 64-bit. (32-bit stack dumping is preemption safe.) Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-26 14:29:10 +07:00
unsigned long *irq_stack_end;
unsigned long *irq_stack;
unsigned long *stack;
x86: dumpstack, 64-bit: Disable preemption when walking the IRQ/exception stacks This warning: [ 847.140022] rb_producer D 0000000000000000 5928 519 2 0x00000000 [ 847.203627] BUG: using smp_processor_id() in preemptible [00000000] code: khungtaskd/517 [ 847.207360] caller is show_stack_log_lvl+0x2e/0x241 [ 847.210364] Pid: 517, comm: khungtaskd Not tainted 2.6.32-rc8-tip+ #13761 [ 847.213395] Call Trace: [ 847.215847] [<ffffffff81413bde>] debug_smp_processor_id+0x1f0/0x20a [ 847.216809] [<ffffffff81015eae>] show_stack_log_lvl+0x2e/0x241 [ 847.220027] [<ffffffff81018512>] show_stack+0x1c/0x1e [ 847.223365] [<ffffffff8107b7db>] sched_show_task+0xe4/0xe9 [ 847.226694] [<ffffffff8112f21f>] check_hung_task+0x140/0x199 [ 847.230261] [<ffffffff8112f4a8>] check_hung_uninterruptible_tasks+0x1b7/0x20f [ 847.233371] [<ffffffff8112f500>] ? watchdog+0x0/0x50 [ 847.236683] [<ffffffff8112f54e>] watchdog+0x4e/0x50 [ 847.240034] [<ffffffff810cee56>] kthread+0x97/0x9f [ 847.243372] [<ffffffff81012aea>] child_rip+0xa/0x20 [ 847.246690] [<ffffffff81e43494>] ? restore_args+0x0/0x30 [ 847.250019] [<ffffffff81e43083>] ? _spin_lock+0xe/0x10 [ 847.253351] [<ffffffff810cedbf>] ? kthread+0x0/0x9f [ 847.256833] [<ffffffff81012ae0>] ? child_rip+0x0/0x20 Happens because on preempt-RCU, khungd calls show_stack() with preemption enabled. Make sure we are not preemptible while walking the IRQ and exception stacks on 64-bit. (32-bit stack dumping is preemption safe.) Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-26 14:29:10 +07:00
int cpu;
int i;
x86: dumpstack, 64-bit: Disable preemption when walking the IRQ/exception stacks This warning: [ 847.140022] rb_producer D 0000000000000000 5928 519 2 0x00000000 [ 847.203627] BUG: using smp_processor_id() in preemptible [00000000] code: khungtaskd/517 [ 847.207360] caller is show_stack_log_lvl+0x2e/0x241 [ 847.210364] Pid: 517, comm: khungtaskd Not tainted 2.6.32-rc8-tip+ #13761 [ 847.213395] Call Trace: [ 847.215847] [<ffffffff81413bde>] debug_smp_processor_id+0x1f0/0x20a [ 847.216809] [<ffffffff81015eae>] show_stack_log_lvl+0x2e/0x241 [ 847.220027] [<ffffffff81018512>] show_stack+0x1c/0x1e [ 847.223365] [<ffffffff8107b7db>] sched_show_task+0xe4/0xe9 [ 847.226694] [<ffffffff8112f21f>] check_hung_task+0x140/0x199 [ 847.230261] [<ffffffff8112f4a8>] check_hung_uninterruptible_tasks+0x1b7/0x20f [ 847.233371] [<ffffffff8112f500>] ? watchdog+0x0/0x50 [ 847.236683] [<ffffffff8112f54e>] watchdog+0x4e/0x50 [ 847.240034] [<ffffffff810cee56>] kthread+0x97/0x9f [ 847.243372] [<ffffffff81012aea>] child_rip+0xa/0x20 [ 847.246690] [<ffffffff81e43494>] ? restore_args+0x0/0x30 [ 847.250019] [<ffffffff81e43083>] ? _spin_lock+0xe/0x10 [ 847.253351] [<ffffffff810cedbf>] ? kthread+0x0/0x9f [ 847.256833] [<ffffffff81012ae0>] ? child_rip+0x0/0x20 Happens because on preempt-RCU, khungd calls show_stack() with preemption enabled. Make sure we are not preemptible while walking the IRQ and exception stacks on 64-bit. (32-bit stack dumping is preemption safe.) Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-26 14:29:10 +07:00
preempt_disable();
cpu = smp_processor_id();
irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
irq_stack = (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
/*
x86: dumpstack, 64-bit: Disable preemption when walking the IRQ/exception stacks This warning: [ 847.140022] rb_producer D 0000000000000000 5928 519 2 0x00000000 [ 847.203627] BUG: using smp_processor_id() in preemptible [00000000] code: khungtaskd/517 [ 847.207360] caller is show_stack_log_lvl+0x2e/0x241 [ 847.210364] Pid: 517, comm: khungtaskd Not tainted 2.6.32-rc8-tip+ #13761 [ 847.213395] Call Trace: [ 847.215847] [<ffffffff81413bde>] debug_smp_processor_id+0x1f0/0x20a [ 847.216809] [<ffffffff81015eae>] show_stack_log_lvl+0x2e/0x241 [ 847.220027] [<ffffffff81018512>] show_stack+0x1c/0x1e [ 847.223365] [<ffffffff8107b7db>] sched_show_task+0xe4/0xe9 [ 847.226694] [<ffffffff8112f21f>] check_hung_task+0x140/0x199 [ 847.230261] [<ffffffff8112f4a8>] check_hung_uninterruptible_tasks+0x1b7/0x20f [ 847.233371] [<ffffffff8112f500>] ? watchdog+0x0/0x50 [ 847.236683] [<ffffffff8112f54e>] watchdog+0x4e/0x50 [ 847.240034] [<ffffffff810cee56>] kthread+0x97/0x9f [ 847.243372] [<ffffffff81012aea>] child_rip+0xa/0x20 [ 847.246690] [<ffffffff81e43494>] ? restore_args+0x0/0x30 [ 847.250019] [<ffffffff81e43083>] ? _spin_lock+0xe/0x10 [ 847.253351] [<ffffffff810cedbf>] ? kthread+0x0/0x9f [ 847.256833] [<ffffffff81012ae0>] ? child_rip+0x0/0x20 Happens because on preempt-RCU, khungd calls show_stack() with preemption enabled. Make sure we are not preemptible while walking the IRQ and exception stacks on 64-bit. (32-bit stack dumping is preemption safe.) Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-26 14:29:10 +07:00
* Debugging aid: "show_stack(NULL, NULL);" prints the
* back trace for this cpu:
*/
if (sp == NULL) {
if (task)
sp = (unsigned long *)task->thread.sp;
else
sp = (unsigned long *)&sp;
}
stack = sp;
for (i = 0; i < kstack_depth_to_print; i++) {
if (stack >= irq_stack && stack <= irq_stack_end) {
if (stack == irq_stack_end) {
stack = (unsigned long *) (irq_stack_end[-1]);
x86, printk: Get rid of <0> from stack output The stack output currently looks like this: 7fffffffffffffff 0000000a00000000 ffffffff81093341 0000000000000046 <0> ffff88003a545fd8 0000000000000000 0000000000000000 00007fffa39769c0 <0> ffff88003e403f58 ffffffff8102fc4c ffff88003e403f58 ffff88003e403f78 The superfluous <0> are caused by recent printk KERN_CONT change. <*> is now ignored in printk unless some text follows the level and even then it still has to be the first in the format message. Note that the log_lvl parameter is now completely ignored in show_stack_log_lvl and the stack is dumped with the default level (like for quite some time already). It behaves the same as the rest of the dump, function traces are dumped in the very same manner. Only Code and maybe some lines are printed with EMERG level. Unfortunately I see no way how to fix this conceptually to have the whole oops/BUG/panic output with the same level, so this removed only the superfluous characters for the time being. Just for illustration: <4>Process kworker/0:0 (pid: 0, threadinfo ffff88003c8a6000, task ffff88003c85c100) <0>Stack: <4> ffffffff818022c0 0000000a00000001 0000000000000001 0000000000000046 <4> ffff88003c8a7fd8 0000000000000001 ffff88003c8a7e58 0000000000000000 <4> ffff88003e503f48 ffffffff8102fc4c ffff88003e503f48 ffff88003e503f68 <0>Call Trace: <0> <IRQ> <4> [<ffffffff8102fc4c>] ? call_softirq+0x1c/0x30 ... <0>Code: 00 01 00 00 65 8b 04 25 80 c5 00 00 c7 45 ... Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: jirislaby@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1287586131-16222-1-git-send-email-jslaby@suse.cz> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-10-20 21:48:51 +07:00
printk(KERN_CONT " <EOI> ");
}
} else {
if (((long) stack & (THREAD_SIZE-1)) == 0)
break;
}
if (i && ((i % STACKSLOTS_PER_LINE) == 0))
x86, printk: Get rid of <0> from stack output The stack output currently looks like this: 7fffffffffffffff 0000000a00000000 ffffffff81093341 0000000000000046 <0> ffff88003a545fd8 0000000000000000 0000000000000000 00007fffa39769c0 <0> ffff88003e403f58 ffffffff8102fc4c ffff88003e403f58 ffff88003e403f78 The superfluous <0> are caused by recent printk KERN_CONT change. <*> is now ignored in printk unless some text follows the level and even then it still has to be the first in the format message. Note that the log_lvl parameter is now completely ignored in show_stack_log_lvl and the stack is dumped with the default level (like for quite some time already). It behaves the same as the rest of the dump, function traces are dumped in the very same manner. Only Code and maybe some lines are printed with EMERG level. Unfortunately I see no way how to fix this conceptually to have the whole oops/BUG/panic output with the same level, so this removed only the superfluous characters for the time being. Just for illustration: <4>Process kworker/0:0 (pid: 0, threadinfo ffff88003c8a6000, task ffff88003c85c100) <0>Stack: <4> ffffffff818022c0 0000000a00000001 0000000000000001 0000000000000046 <4> ffff88003c8a7fd8 0000000000000001 ffff88003c8a7e58 0000000000000000 <4> ffff88003e503f48 ffffffff8102fc4c ffff88003e503f48 ffff88003e503f68 <0>Call Trace: <0> <IRQ> <4> [<ffffffff8102fc4c>] ? call_softirq+0x1c/0x30 ... <0>Code: 00 01 00 00 65 8b 04 25 80 c5 00 00 c7 45 ... Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: jirislaby@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1287586131-16222-1-git-send-email-jslaby@suse.cz> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-10-20 21:48:51 +07:00
printk(KERN_CONT "\n");
printk(KERN_CONT " %016lx", *stack++);
touch_nmi_watchdog();
}
x86: dumpstack, 64-bit: Disable preemption when walking the IRQ/exception stacks This warning: [ 847.140022] rb_producer D 0000000000000000 5928 519 2 0x00000000 [ 847.203627] BUG: using smp_processor_id() in preemptible [00000000] code: khungtaskd/517 [ 847.207360] caller is show_stack_log_lvl+0x2e/0x241 [ 847.210364] Pid: 517, comm: khungtaskd Not tainted 2.6.32-rc8-tip+ #13761 [ 847.213395] Call Trace: [ 847.215847] [<ffffffff81413bde>] debug_smp_processor_id+0x1f0/0x20a [ 847.216809] [<ffffffff81015eae>] show_stack_log_lvl+0x2e/0x241 [ 847.220027] [<ffffffff81018512>] show_stack+0x1c/0x1e [ 847.223365] [<ffffffff8107b7db>] sched_show_task+0xe4/0xe9 [ 847.226694] [<ffffffff8112f21f>] check_hung_task+0x140/0x199 [ 847.230261] [<ffffffff8112f4a8>] check_hung_uninterruptible_tasks+0x1b7/0x20f [ 847.233371] [<ffffffff8112f500>] ? watchdog+0x0/0x50 [ 847.236683] [<ffffffff8112f54e>] watchdog+0x4e/0x50 [ 847.240034] [<ffffffff810cee56>] kthread+0x97/0x9f [ 847.243372] [<ffffffff81012aea>] child_rip+0xa/0x20 [ 847.246690] [<ffffffff81e43494>] ? restore_args+0x0/0x30 [ 847.250019] [<ffffffff81e43083>] ? _spin_lock+0xe/0x10 [ 847.253351] [<ffffffff810cedbf>] ? kthread+0x0/0x9f [ 847.256833] [<ffffffff81012ae0>] ? child_rip+0x0/0x20 Happens because on preempt-RCU, khungd calls show_stack() with preemption enabled. Make sure we are not preemptible while walking the IRQ and exception stacks on 64-bit. (32-bit stack dumping is preemption safe.) Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-26 14:29:10 +07:00
preempt_enable();
x86, printk: Get rid of <0> from stack output The stack output currently looks like this: 7fffffffffffffff 0000000a00000000 ffffffff81093341 0000000000000046 <0> ffff88003a545fd8 0000000000000000 0000000000000000 00007fffa39769c0 <0> ffff88003e403f58 ffffffff8102fc4c ffff88003e403f58 ffff88003e403f78 The superfluous <0> are caused by recent printk KERN_CONT change. <*> is now ignored in printk unless some text follows the level and even then it still has to be the first in the format message. Note that the log_lvl parameter is now completely ignored in show_stack_log_lvl and the stack is dumped with the default level (like for quite some time already). It behaves the same as the rest of the dump, function traces are dumped in the very same manner. Only Code and maybe some lines are printed with EMERG level. Unfortunately I see no way how to fix this conceptually to have the whole oops/BUG/panic output with the same level, so this removed only the superfluous characters for the time being. Just for illustration: <4>Process kworker/0:0 (pid: 0, threadinfo ffff88003c8a6000, task ffff88003c85c100) <0>Stack: <4> ffffffff818022c0 0000000a00000001 0000000000000001 0000000000000046 <4> ffff88003c8a7fd8 0000000000000001 ffff88003c8a7e58 0000000000000000 <4> ffff88003e503f48 ffffffff8102fc4c ffff88003e503f48 ffff88003e503f68 <0>Call Trace: <0> <IRQ> <4> [<ffffffff8102fc4c>] ? call_softirq+0x1c/0x30 ... <0>Code: 00 01 00 00 65 8b 04 25 80 c5 00 00 c7 45 ... Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: jirislaby@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1287586131-16222-1-git-send-email-jslaby@suse.cz> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-10-20 21:48:51 +07:00
printk(KERN_CONT "\n");
x86, dumpstack: Correct stack dump info when frame pointer is available Current stack dump code scans entire stack and check each entry contains a pointer to kernel code. If CONFIG_FRAME_POINTER=y it could mark whether the pointer is valid or not based on value of the frame pointer. Invalid entries could be preceded by '?' sign. However this was not going to happen because scan start point was always higher than the frame pointer so that they could not meet. Commit 9c0729dc8062 ("x86: Eliminate bp argument from the stack tracing routines") delayed bp acquisition point, so the bp was read in lower frame, thus all of the entries were marked invalid. This patch fixes this by reverting above commit while retaining stack_frame() helper as suggested by Frederic Weisbecker. End result looks like below: before: [ 3.508329] Call Trace: [ 3.508551] [<ffffffff814f35c9>] ? panic+0x91/0x199 [ 3.508662] [<ffffffff814f3739>] ? printk+0x68/0x6a [ 3.508770] [<ffffffff81a981b2>] ? mount_block_root+0x257/0x26e [ 3.508876] [<ffffffff81a9821f>] ? mount_root+0x56/0x5a [ 3.508975] [<ffffffff81a98393>] ? prepare_namespace+0x170/0x1a9 [ 3.509216] [<ffffffff81a9772b>] ? kernel_init+0x1d2/0x1e2 [ 3.509335] [<ffffffff81003894>] ? kernel_thread_helper+0x4/0x10 [ 3.509442] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.509542] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.509641] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 after: [ 3.522991] Call Trace: [ 3.523351] [<ffffffff814f35b9>] panic+0x91/0x199 [ 3.523468] [<ffffffff814f3729>] ? printk+0x68/0x6a [ 3.523576] [<ffffffff81a981b2>] mount_block_root+0x257/0x26e [ 3.523681] [<ffffffff81a9821f>] mount_root+0x56/0x5a [ 3.523780] [<ffffffff81a98393>] prepare_namespace+0x170/0x1a9 [ 3.523885] [<ffffffff81a9772b>] kernel_init+0x1d2/0x1e2 [ 3.523987] [<ffffffff81003894>] kernel_thread_helper+0x4/0x10 [ 3.524228] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.524345] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.524445] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 -v5: * fix build breakage with oprofile -v4: * use 0 instead of regs->bp * separate out printk changes -v3: * apply comment from Frederic * add a couple of printk fixes Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Soren Sandmann <ssp@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <1300416006-3163-1-git-send-email-namhyung@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-03-18 09:40:06 +07:00
show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
void show_registers(struct pt_regs *regs)
{
int i;
unsigned long sp;
const int cpu = smp_processor_id();
struct task_struct *cur = current;
sp = regs->sp;
printk("CPU %d ", cpu);
print_modules();
__show_regs(regs, 1);
printk("Process %s (pid: %d, threadinfo %p, task %p)\n",
cur->comm, cur->pid, task_thread_info(cur), cur);
/*
* When in-kernel, we also print out the stack and code at the
* time of the fault..
*/
if (!user_mode(regs)) {
unsigned int code_prologue = code_bytes * 43 / 64;
unsigned int code_len = code_bytes;
unsigned char c;
u8 *ip;
printk(KERN_EMERG "Stack:\n");
show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
x86, dumpstack: Correct stack dump info when frame pointer is available Current stack dump code scans entire stack and check each entry contains a pointer to kernel code. If CONFIG_FRAME_POINTER=y it could mark whether the pointer is valid or not based on value of the frame pointer. Invalid entries could be preceded by '?' sign. However this was not going to happen because scan start point was always higher than the frame pointer so that they could not meet. Commit 9c0729dc8062 ("x86: Eliminate bp argument from the stack tracing routines") delayed bp acquisition point, so the bp was read in lower frame, thus all of the entries were marked invalid. This patch fixes this by reverting above commit while retaining stack_frame() helper as suggested by Frederic Weisbecker. End result looks like below: before: [ 3.508329] Call Trace: [ 3.508551] [<ffffffff814f35c9>] ? panic+0x91/0x199 [ 3.508662] [<ffffffff814f3739>] ? printk+0x68/0x6a [ 3.508770] [<ffffffff81a981b2>] ? mount_block_root+0x257/0x26e [ 3.508876] [<ffffffff81a9821f>] ? mount_root+0x56/0x5a [ 3.508975] [<ffffffff81a98393>] ? prepare_namespace+0x170/0x1a9 [ 3.509216] [<ffffffff81a9772b>] ? kernel_init+0x1d2/0x1e2 [ 3.509335] [<ffffffff81003894>] ? kernel_thread_helper+0x4/0x10 [ 3.509442] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.509542] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.509641] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 after: [ 3.522991] Call Trace: [ 3.523351] [<ffffffff814f35b9>] panic+0x91/0x199 [ 3.523468] [<ffffffff814f3729>] ? printk+0x68/0x6a [ 3.523576] [<ffffffff81a981b2>] mount_block_root+0x257/0x26e [ 3.523681] [<ffffffff81a9821f>] mount_root+0x56/0x5a [ 3.523780] [<ffffffff81a98393>] prepare_namespace+0x170/0x1a9 [ 3.523885] [<ffffffff81a9772b>] kernel_init+0x1d2/0x1e2 [ 3.523987] [<ffffffff81003894>] kernel_thread_helper+0x4/0x10 [ 3.524228] [<ffffffff814f6880>] ? restore_args+0x0/0x30 [ 3.524345] [<ffffffff81a97559>] ? kernel_init+0x0/0x1e2 [ 3.524445] [<ffffffff81003890>] ? kernel_thread_helper+0x0/0x10 -v5: * fix build breakage with oprofile -v4: * use 0 instead of regs->bp * separate out printk changes -v3: * apply comment from Frederic * add a couple of printk fixes Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Soren Sandmann <ssp@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <1300416006-3163-1-git-send-email-namhyung@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-03-18 09:40:06 +07:00
0, KERN_EMERG);
printk(KERN_EMERG "Code: ");
ip = (u8 *)regs->ip - code_prologue;
if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
/* try starting at IP */
ip = (u8 *)regs->ip;
code_len = code_len - code_prologue + 1;
}
for (i = 0; i < code_len; i++, ip++) {
if (ip < (u8 *)PAGE_OFFSET ||
probe_kernel_address(ip, c)) {
printk(" Bad RIP value.");
break;
}
if (ip == (u8 *)regs->ip)
printk("<%02x> ", c);
else
printk("%02x ", c);
}
}
printk("\n");
}
int is_valid_bugaddr(unsigned long ip)
{
unsigned short ud2;
if (__copy_from_user(&ud2, (const void __user *) ip, sizeof(ud2)))
return 0;
return ud2 == 0x0b0f;
}