kernel_optimize_test/arch/x86/kernel/dumpstack_64.c

181 lines
4.1 KiB
C
Raw Normal View History

/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
*/
#include <linux/sched/debug.h>
#include <linux/kallsyms.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/hardirq.h>
#include <linux/kdebug.h>
#include <linux/export.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>
static char *exception_stack_names[N_EXCEPTION_STACKS] = {
[ DOUBLEFAULT_STACK-1 ] = "#DF",
[ NMI_STACK-1 ] = "NMI",
[ DEBUG_STACK-1 ] = "#DB",
[ MCE_STACK-1 ] = "#MC",
};
static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
[0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
[DEBUG_STACK - 1] = DEBUG_STKSZ
};
const char *stack_type_name(enum stack_type type)
{
BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
if (type == STACK_TYPE_IRQ)
return "IRQ";
if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST)
return exception_stack_names[type - STACK_TYPE_EXCEPTION];
return NULL;
}
static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
{
unsigned long *begin, *end;
struct pt_regs *regs;
unsigned k;
BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
for (k = 0; k < N_EXCEPTION_STACKS; k++) {
end = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k];
begin = end - (exception_stack_sizes[k] / sizeof(long));
regs = (struct pt_regs *)end - 1;
if (stack <= begin || stack >= end)
continue;
info->type = STACK_TYPE_EXCEPTION + k;
info->begin = begin;
info->end = end;
info->next_sp = (unsigned long *)regs->sp;
return true;
}
return false;
}
static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
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 12:34:27 +08:00
{
unsigned long *end = (unsigned long *)this_cpu_read(irq_stack_ptr);
unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
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 12:34:27 +08:00
x86/dumpstack: Add support for unwinding empty IRQ stacks When an interrupt happens in entry code while running on a software IRQ stack, and the IRQ stack was empty, regs->sp will contain the stack end address (e.g., irq_stack_ptr). If the regs are passed to dump_trace(), get_stack_info() will report STACK_TYPE_UNKNOWN, causing dump_trace() to return prematurely without trying to go to the next stack. Update the bounds checking for software interrupt stacks so that the ending address is now considered part of the stack. This means that it's now possible for the 'walk_stack' callbacks -- print_context_stack() and print_context_stack_bp() -- to be called with an empty stack. But that's fine; they're already prepared to deal with that due to their on_stack() checks. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nilay Vaish <nilayvaish@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/5a5e5de92dcf11e8dc6b6e8e50ad7639d067830b.1473905218.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-09-15 10:07:43 +08:00
/*
* This is a software stack, so 'end' can be a valid stack pointer.
* It just means the stack is empty.
*/
if (stack <= begin || stack > end)
return false;
info->type = STACK_TYPE_IRQ;
info->begin = begin;
info->end = end;
/*
* The next stack pointer is the first thing pushed by the entry code
* after switching to the irq stack.
*/
info->next_sp = (unsigned long *)*(end - 1);
return true;
}
int get_stack_info(unsigned long *stack, struct task_struct *task,
struct stack_info *info, unsigned long *visit_mask)
{
if (!stack)
goto unknown;
task = task ? : current;
if (in_task_stack(stack, task, info))
goto recursion_check;
if (task != current)
goto unknown;
if (in_exception_stack(stack, info))
goto recursion_check;
if (in_irq_stack(stack, info))
goto recursion_check;
goto unknown;
recursion_check:
/*
* Make sure we don't iterate through any given stack more than once.
* If it comes up a second time then there's something wrong going on:
* just break out and report an unknown stack type.
*/
if (visit_mask) {
if (*visit_mask & (1UL << info->type)) {
printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type);
goto unknown;
}
*visit_mask |= 1UL << info->type;
}
return 0;
unknown:
info->type = STACK_TYPE_UNKNOWN;
return -EINVAL;
}
void show_regs(struct pt_regs *regs)
{
int i;
dump_stack: unify debug information printed by show_regs() show_regs() is inherently arch-dependent but it does make sense to print generic debug information and some archs already do albeit in slightly different forms. This patch introduces a generic function to print debug information from show_regs() so that different archs print out the same information and it's much easier to modify what's printed. show_regs_print_info() prints out the same debug info as dump_stack() does plus task and thread_info pointers. * Archs which didn't print debug info now do. alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r, metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc, um, xtensa * Already prints debug info. Replaced with show_regs_print_info(). The printed information is superset of what used to be there. arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86 * s390 is special in that it used to print arch-specific information along with generic debug info. Heiko and Martin think that the arch-specific extra isn't worth keeping s390 specfic implementation. Converted to use the generic version. Note that now all archs print the debug info before actual register dumps. An example BUG() dump follows. kernel BUG at /work/os/work/kernel/workqueue.c:4841! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000 RIP: 0010:[<ffffffff8234a07e>] [<ffffffff8234a07e>] init_workqueues+0x4/0x6 RSP: 0000:ffff88007c861ec8 EFLAGS: 00010246 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650 0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760 Call Trace: [<ffffffff81000312>] do_one_initcall+0x122/0x170 [<ffffffff82335e5d>] kernel_init_freeable+0x9b/0x1c8 [<ffffffff81c47760>] ? rest_init+0x140/0x140 [<ffffffff81c4776e>] kernel_init+0xe/0xf0 [<ffffffff81c6be9c>] ret_from_fork+0x7c/0xb0 [<ffffffff81c47760>] ? rest_init+0x140/0x140 ... v2: Typo fix in x86-32. v3: CPU number dropped from show_regs_print_info() as dump_stack_print_info() has been updated to print it. s390 specific implementation dropped as requested by s390 maintainers. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Chris Metcalf <cmetcalf@tilera.com> [tile bits] Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:17 +08:00
show_regs_print_info(KERN_DEFAULT);
__show_regs(regs, 1);
/*
* 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;
x86/dumpstack: Remove raw stack dump For mostly historical reasons, the x86 oops dump shows the raw stack values: ... [registers] Stack: ffff880079af7350 ffff880079905400 0000000000000000 ffffc900008f3ae0 ffffffffa0196610 0000000000000001 00010000ffffffff 0000000087654321 0000000000000002 0000000000000000 0000000000000000 0000000000000000 Call Trace: ... This seems to be an artifact from long ago, and probably isn't needed anymore. It generally just adds noise to the dump, and it can be actively harmful because it leaks kernel addresses. Linus says: "The stack dump actually goes back to forever, and it used to be useful back in 1992 or so. But it used to be useful mainly because stacks were simpler and we didn't have very good call traces anyway. I definitely remember having used them - I just do not remember having used them in the last ten+ years. Of course, it's still true that if you can trigger an oops, you've likely already lost the security game, but since the stack dump is so useless, let's aim to just remove it and make games like the above harder." This also removes the related 'kstack=' cmdline option and the 'kstack_depth_to_print' sysctl. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/e83bd50df52d8fe88e94d2566426ae40d813bf8f.1477405374.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-10-25 22:51:13 +08:00
show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
bugs, x86: Fix printk levels for panic, softlockups and stack dumps rsyslog will display KERN_EMERG messages on a connected terminal. However, these messages are useless/undecipherable for a general user. For example, after a softlockup we get: Message from syslogd@intel-s3e37-04 at Jan 25 14:18:06 ... kernel:Stack: Message from syslogd@intel-s3e37-04 at Jan 25 14:18:06 ... kernel:Call Trace: Message from syslogd@intel-s3e37-04 at Jan 25 14:18:06 ... kernel:Code: ff ff a8 08 75 25 31 d2 48 8d 86 38 e0 ff ff 48 89 d1 0f 01 c8 0f ae f0 48 8b 86 38 e0 ff ff a8 08 75 08 b1 01 4c 89 e0 0f 01 c9 <e8> ea 69 dd ff 4c 29 e8 48 89 c7 e8 0f bc da ff 49 89 c4 49 89 This happens because the printk levels for these messages are incorrect. Only an informational message should be displayed on a terminal. I modified the printk levels for various messages in the kernel and tested the output by using the drivers/misc/lkdtm.c kernel modules (ie, softlockups, panics, hard lockups, etc.) and confirmed that the console output was still the same and that the output to the terminals was correct. For example, in the case of a softlockup we now see the much more informative: Message from syslogd@intel-s3e37-04 at Jan 25 10:18:06 ... BUG: soft lockup - CPU4 stuck for 60s! instead of the above confusing messages. AFAICT, the messages no longer have to be KERN_EMERG. In the most important case of a panic we set console_verbose(). As for the other less severe cases the correct data is output to the console and /var/log/messages. Successfully tested by me using the drivers/misc/lkdtm.c module. Signed-off-by: Prarit Bhargava <prarit@redhat.com> Cc: dzickus@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/1327586134-11926-1-git-send-email-prarit@redhat.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-01-26 21:55:34 +08:00
printk(KERN_DEFAULT "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)) {
pr_cont(" Bad RIP value.");
break;
}
if (ip == (u8 *)regs->ip)
pr_cont("<%02x> ", c);
else
pr_cont("%02x ", c);
}
}
pr_cont("\n");
}