linux_dsm_epyc7002/arch/x86/kernel/stacktrace.c

244 lines
5.4 KiB
C
Raw Normal View History

/*
* Stack trace management functions
*
* Copyright (C) 2006-2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*/
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
#include <linux/export.h>
#include <linux/uaccess.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
static int save_stack_address(struct stack_trace *trace, unsigned long addr,
bool nosched)
{
if (nosched && in_sched_functions(addr))
return 0;
if (trace->skip > 0) {
trace->skip--;
return 0;
}
if (trace->nr_entries >= trace->max_entries)
return -1;
trace->entries[trace->nr_entries++] = addr;
return 0;
}
static void noinline __save_stack_trace(struct stack_trace *trace,
struct task_struct *task, struct pt_regs *regs,
bool nosched)
{
struct unwind_state state;
unsigned long addr;
if (regs)
save_stack_address(trace, regs->ip, nosched);
for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
if (!addr || save_stack_address(trace, addr, nosched))
break;
}
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
/*
* Save stack-backtrace addresses into a stack_trace buffer.
*/
void save_stack_trace(struct stack_trace *trace)
{
trace->skip++;
__save_stack_trace(trace, current, NULL, false);
}
EXPORT_SYMBOL_GPL(save_stack_trace);
void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
{
__save_stack_trace(trace, current, regs, false);
}
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
if (!try_get_task_stack(tsk))
return;
if (tsk == current)
trace->skip++;
__save_stack_trace(trace, tsk, NULL, true);
put_task_stack(tsk);
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
stacktrace/x86: add function for detecting reliable stack traces For live patching and possibly other use cases, a stack trace is only useful if it can be assured that it's completely reliable. Add a new save_stack_trace_tsk_reliable() function to achieve that. Note that if the target task isn't the current task, and the target task is allowed to run, then it could be writing the stack while the unwinder is reading it, resulting in possible corruption. So the caller of save_stack_trace_tsk_reliable() must ensure that the task is either 'current' or inactive. save_stack_trace_tsk_reliable() relies on the x86 unwinder's detection of pt_regs on the stack. If the pt_regs are not user-mode registers from a syscall, then they indicate an in-kernel interrupt or exception (e.g. preemption or a page fault), in which case the stack is considered unreliable due to the nature of frame pointers. It also relies on the x86 unwinder's detection of other issues, such as: - corrupted stack data - stack grows the wrong way - stack walk doesn't reach the bottom - user didn't provide a large enough entries array Such issues are reported by checking unwind_error() and !unwind_done(). Also add CONFIG_HAVE_RELIABLE_STACKTRACE so arch-independent code can determine at build time whether the function is implemented. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Ingo Molnar <mingo@kernel.org> # for the x86 changes Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2017-02-14 08:42:28 +07:00
#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
#define STACKTRACE_DUMP_ONCE(task) ({ \
static bool __section(.data.unlikely) __dumped; \
\
if (!__dumped) { \
__dumped = true; \
WARN_ON(1); \
show_stack(task, NULL); \
} \
})
static int __always_inline
__save_stack_trace_reliable(struct stack_trace *trace,
struct task_struct *task)
stacktrace/x86: add function for detecting reliable stack traces For live patching and possibly other use cases, a stack trace is only useful if it can be assured that it's completely reliable. Add a new save_stack_trace_tsk_reliable() function to achieve that. Note that if the target task isn't the current task, and the target task is allowed to run, then it could be writing the stack while the unwinder is reading it, resulting in possible corruption. So the caller of save_stack_trace_tsk_reliable() must ensure that the task is either 'current' or inactive. save_stack_trace_tsk_reliable() relies on the x86 unwinder's detection of pt_regs on the stack. If the pt_regs are not user-mode registers from a syscall, then they indicate an in-kernel interrupt or exception (e.g. preemption or a page fault), in which case the stack is considered unreliable due to the nature of frame pointers. It also relies on the x86 unwinder's detection of other issues, such as: - corrupted stack data - stack grows the wrong way - stack walk doesn't reach the bottom - user didn't provide a large enough entries array Such issues are reported by checking unwind_error() and !unwind_done(). Also add CONFIG_HAVE_RELIABLE_STACKTRACE so arch-independent code can determine at build time whether the function is implemented. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Ingo Molnar <mingo@kernel.org> # for the x86 changes Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2017-02-14 08:42:28 +07:00
{
struct unwind_state state;
struct pt_regs *regs;
unsigned long addr;
for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
regs = unwind_get_entry_regs(&state, NULL);
stacktrace/x86: add function for detecting reliable stack traces For live patching and possibly other use cases, a stack trace is only useful if it can be assured that it's completely reliable. Add a new save_stack_trace_tsk_reliable() function to achieve that. Note that if the target task isn't the current task, and the target task is allowed to run, then it could be writing the stack while the unwinder is reading it, resulting in possible corruption. So the caller of save_stack_trace_tsk_reliable() must ensure that the task is either 'current' or inactive. save_stack_trace_tsk_reliable() relies on the x86 unwinder's detection of pt_regs on the stack. If the pt_regs are not user-mode registers from a syscall, then they indicate an in-kernel interrupt or exception (e.g. preemption or a page fault), in which case the stack is considered unreliable due to the nature of frame pointers. It also relies on the x86 unwinder's detection of other issues, such as: - corrupted stack data - stack grows the wrong way - stack walk doesn't reach the bottom - user didn't provide a large enough entries array Such issues are reported by checking unwind_error() and !unwind_done(). Also add CONFIG_HAVE_RELIABLE_STACKTRACE so arch-independent code can determine at build time whether the function is implemented. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Ingo Molnar <mingo@kernel.org> # for the x86 changes Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2017-02-14 08:42:28 +07:00
if (regs) {
/*
* Kernel mode registers on the stack indicate an
* in-kernel interrupt or exception (e.g., preemption
* or a page fault), which can make frame pointers
* unreliable.
*/
if (!user_mode(regs))
return -EINVAL;
/*
* The last frame contains the user mode syscall
* pt_regs. Skip it and finish the unwind.
*/
unwind_next_frame(&state);
if (!unwind_done(&state)) {
STACKTRACE_DUMP_ONCE(task);
return -EINVAL;
}
break;
}
addr = unwind_get_return_address(&state);
/*
* A NULL or invalid return address probably means there's some
* generated code which __kernel_text_address() doesn't know
* about.
*/
if (!addr) {
STACKTRACE_DUMP_ONCE(task);
return -EINVAL;
}
if (save_stack_address(trace, addr, false))
return -EINVAL;
}
/* Check for stack corruption */
if (unwind_error(&state)) {
STACKTRACE_DUMP_ONCE(task);
return -EINVAL;
}
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
return 0;
}
/*
* This function returns an error if it detects any unreliable features of the
* stack. Otherwise it guarantees that the stack trace is reliable.
*
* If the task is not 'current', the caller *must* ensure the task is inactive.
*/
int save_stack_trace_tsk_reliable(struct task_struct *tsk,
struct stack_trace *trace)
{
int ret;
x86/stacktrace: Make zombie stack traces reliable Commit: 1959a60182f4 ("x86/dumpstack: Pin the target stack when dumping it") changed the behavior of stack traces for zombies. Before that commit, /proc/<pid>/stack reported the last execution path of the zombie before it died: [<ffffffff8105b877>] do_exit+0x6f7/0xa80 [<ffffffff8105bc79>] do_group_exit+0x39/0xa0 [<ffffffff8105bcf0>] __wake_up_parent+0x0/0x30 [<ffffffff8152dd09>] system_call_fastpath+0x16/0x1b [<00007fd128f9c4f9>] 0x7fd128f9c4f9 [<ffffffffffffffff>] 0xffffffffffffffff After the commit, it just reports an empty stack trace. The new behavior is actually probably more correct. If the stack refcount has gone down to zero, then the task has already gone through do_exit() and isn't going to run anymore. The stack could be freed at any time and is basically gone, so reporting an empty stack makes sense. However, save_stack_trace_tsk_reliable() treats such a missing stack condition as an error. That can cause livepatch transition stalls if there are any unreaped zombies. Instead, just treat it as a reliable, empty stack. Reported-and-tested-by: Miroslav Benes <mbenes@suse.cz> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: live-patching@vger.kernel.org Fixes: af085d9084b4 ("stacktrace/x86: add function for detecting reliable stack traces") Link: http://lkml.kernel.org/r/e4b09e630e99d0c1080528f0821fc9d9dbaeea82.1513631620.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-19 04:13:44 +07:00
/*
* If the task doesn't have a stack (e.g., a zombie), the stack is
* "reliably" empty.
*/
stacktrace/x86: add function for detecting reliable stack traces For live patching and possibly other use cases, a stack trace is only useful if it can be assured that it's completely reliable. Add a new save_stack_trace_tsk_reliable() function to achieve that. Note that if the target task isn't the current task, and the target task is allowed to run, then it could be writing the stack while the unwinder is reading it, resulting in possible corruption. So the caller of save_stack_trace_tsk_reliable() must ensure that the task is either 'current' or inactive. save_stack_trace_tsk_reliable() relies on the x86 unwinder's detection of pt_regs on the stack. If the pt_regs are not user-mode registers from a syscall, then they indicate an in-kernel interrupt or exception (e.g. preemption or a page fault), in which case the stack is considered unreliable due to the nature of frame pointers. It also relies on the x86 unwinder's detection of other issues, such as: - corrupted stack data - stack grows the wrong way - stack walk doesn't reach the bottom - user didn't provide a large enough entries array Such issues are reported by checking unwind_error() and !unwind_done(). Also add CONFIG_HAVE_RELIABLE_STACKTRACE so arch-independent code can determine at build time whether the function is implemented. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Ingo Molnar <mingo@kernel.org> # for the x86 changes Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2017-02-14 08:42:28 +07:00
if (!try_get_task_stack(tsk))
x86/stacktrace: Make zombie stack traces reliable Commit: 1959a60182f4 ("x86/dumpstack: Pin the target stack when dumping it") changed the behavior of stack traces for zombies. Before that commit, /proc/<pid>/stack reported the last execution path of the zombie before it died: [<ffffffff8105b877>] do_exit+0x6f7/0xa80 [<ffffffff8105bc79>] do_group_exit+0x39/0xa0 [<ffffffff8105bcf0>] __wake_up_parent+0x0/0x30 [<ffffffff8152dd09>] system_call_fastpath+0x16/0x1b [<00007fd128f9c4f9>] 0x7fd128f9c4f9 [<ffffffffffffffff>] 0xffffffffffffffff After the commit, it just reports an empty stack trace. The new behavior is actually probably more correct. If the stack refcount has gone down to zero, then the task has already gone through do_exit() and isn't going to run anymore. The stack could be freed at any time and is basically gone, so reporting an empty stack makes sense. However, save_stack_trace_tsk_reliable() treats such a missing stack condition as an error. That can cause livepatch transition stalls if there are any unreaped zombies. Instead, just treat it as a reliable, empty stack. Reported-and-tested-by: Miroslav Benes <mbenes@suse.cz> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: live-patching@vger.kernel.org Fixes: af085d9084b4 ("stacktrace/x86: add function for detecting reliable stack traces") Link: http://lkml.kernel.org/r/e4b09e630e99d0c1080528f0821fc9d9dbaeea82.1513631620.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-19 04:13:44 +07:00
return 0;
stacktrace/x86: add function for detecting reliable stack traces For live patching and possibly other use cases, a stack trace is only useful if it can be assured that it's completely reliable. Add a new save_stack_trace_tsk_reliable() function to achieve that. Note that if the target task isn't the current task, and the target task is allowed to run, then it could be writing the stack while the unwinder is reading it, resulting in possible corruption. So the caller of save_stack_trace_tsk_reliable() must ensure that the task is either 'current' or inactive. save_stack_trace_tsk_reliable() relies on the x86 unwinder's detection of pt_regs on the stack. If the pt_regs are not user-mode registers from a syscall, then they indicate an in-kernel interrupt or exception (e.g. preemption or a page fault), in which case the stack is considered unreliable due to the nature of frame pointers. It also relies on the x86 unwinder's detection of other issues, such as: - corrupted stack data - stack grows the wrong way - stack walk doesn't reach the bottom - user didn't provide a large enough entries array Such issues are reported by checking unwind_error() and !unwind_done(). Also add CONFIG_HAVE_RELIABLE_STACKTRACE so arch-independent code can determine at build time whether the function is implemented. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Ingo Molnar <mingo@kernel.org> # for the x86 changes Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2017-02-14 08:42:28 +07:00
ret = __save_stack_trace_reliable(trace, tsk);
put_task_stack(tsk);
return ret;
}
#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
struct stack_frame_user {
const void __user *next_fp;
unsigned long ret_addr;
};
static int
copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
{
int ret;
if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
return 0;
ret = 1;
pagefault_disable();
if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
ret = 0;
pagefault_enable();
return ret;
}
static inline void __save_stack_trace_user(struct stack_trace *trace)
{
const struct pt_regs *regs = task_pt_regs(current);
const void __user *fp = (const void __user *)regs->bp;
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = regs->ip;
while (trace->nr_entries < trace->max_entries) {
struct stack_frame_user frame;
frame.next_fp = NULL;
frame.ret_addr = 0;
if (!copy_stack_frame(fp, &frame))
break;
if ((unsigned long)fp < regs->sp)
break;
if (frame.ret_addr) {
trace->entries[trace->nr_entries++] =
frame.ret_addr;
}
if (fp == frame.next_fp)
break;
fp = frame.next_fp;
}
}
void save_stack_trace_user(struct stack_trace *trace)
{
/*
* Trace user stack if we are not a kernel thread
*/
if (current->mm) {
__save_stack_trace_user(trace);
}
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}