unwind_user/deferred: Make unwind deferral requests NMI-safe

Make unwind_deferred_request() NMI-safe so tracers in NMI context can
call it and safely request a user space stacktrace when the task exits.

Note, this is only allowed for architectures that implement a safe
cmpxchg. If an architecture requests a deferred stack trace from NMI
context that does not support a safe NMI cmpxchg, it will get an -EINVAL
and trigger a warning. For those architectures, they would need another
method (perhaps an irqwork), to request a deferred user space stack trace.
That can be dealt with later if one of theses architectures require this
feature.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Jens Remus <jremus@linux.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182405.657072238@kernel.org
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
This commit is contained in:
Steven Rostedt 2025-07-29 14:23:09 -04:00 committed by Steven Rostedt (Google)
parent 2dffa355f6
commit 055c7060e7

View file

@ -12,6 +12,31 @@
#include <linux/slab.h>
#include <linux/mm.h>
/*
* For requesting a deferred user space stack trace from NMI context
* the architecture must support a safe cmpxchg in NMI context.
* For those architectures that do not have that, then it cannot ask
* for a deferred user space stack trace from an NMI context. If it
* does, then it will get -EINVAL.
*/
#if defined(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG)
# define CAN_USE_IN_NMI 1
static inline bool try_assign_cnt(struct unwind_task_info *info, u32 cnt)
{
u32 old = 0;
return try_cmpxchg(&info->id.cnt, &old, cnt);
}
#else
# define CAN_USE_IN_NMI 0
/* When NMIs are not allowed, this always succeeds */
static inline bool try_assign_cnt(struct unwind_task_info *info, u32 cnt)
{
info->id.cnt = cnt;
return true;
}
#endif
/* Make the cache fit in a 4K page */
#define UNWIND_MAX_ENTRIES \
((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long))
@ -42,14 +67,13 @@ static DEFINE_PER_CPU(u32, unwind_ctx_ctr);
static u64 get_cookie(struct unwind_task_info *info)
{
u32 cnt = 1;
u32 old = 0;
if (info->id.cpu)
return info->id.id;
/* LSB is always set to ensure 0 is an invalid value */
cnt |= __this_cpu_read(unwind_ctx_ctr) + 2;
if (try_cmpxchg(&info->id.cnt, &old, cnt)) {
if (try_assign_cnt(info, cnt)) {
/* Update the per cpu counter */
__this_cpu_write(unwind_ctx_ctr, cnt);
}
@ -167,31 +191,43 @@ static void unwind_deferred_task_work(struct callback_head *head)
int unwind_deferred_request(struct unwind_work *work, u64 *cookie)
{
struct unwind_task_info *info = &current->unwind_info;
long pending;
int ret;
*cookie = 0;
if (WARN_ON_ONCE(in_nmi()))
return -EINVAL;
if ((current->flags & (PF_KTHREAD | PF_EXITING)) ||
!user_mode(task_pt_regs(current)))
return -EINVAL;
/*
* NMI requires having safe cmpxchg operations.
* Trigger a warning to make it obvious that an architecture
* is using this in NMI when it should not be.
*/
if (WARN_ON_ONCE(!CAN_USE_IN_NMI && in_nmi()))
return -EINVAL;
guard(irqsave)();
*cookie = get_cookie(info);
/* callback already pending? */
if (info->pending)
pending = READ_ONCE(info->pending);
if (pending)
return 1;
/* Claim the work unless an NMI just now swooped in to do so. */
if (!try_cmpxchg(&info->pending, &pending, 1))
return 1;
/* The work has been claimed, now schedule it. */
ret = task_work_add(current, &info->work, TWA_RESUME);
if (WARN_ON_ONCE(ret))
if (WARN_ON_ONCE(ret)) {
WRITE_ONCE(info->pending, 0);
return ret;
}
info->pending = 1;
return 0;
}