From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
bpf@vger.kernel.org, x86@kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Josh Poimboeuf <jpoimboe@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Andrii Nakryiko <andrii@kernel.org>,
Indu Bhagat <indu.bhagat@oracle.com>,
"Jose E. Marchesi" <jemarch@gnu.org>,
Beau Belgrave <beaub@linux.microsoft.com>,
Jens Remus <jremus@linux.ibm.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
Jens Axboe <axboe@kernel.dk>, Florian Weimer <fweimer@redhat.com>
Subject: [PATCH v12 11/14] unwind: Add USED bit to only have one conditional on way back to user space
Date: Mon, 30 Jun 2025 20:53:32 -0400 [thread overview]
Message-ID: <20250701005452.410928589@goodmis.org> (raw)
In-Reply-To: 20250701005321.942306427@goodmis.org
From: Steven Rostedt <rostedt@goodmis.org>
On the way back to user space, the function unwind_reset_info() is called
unconditionally (but always inlined). It currently has two conditionals.
One that checks the unwind_mask which is set whenever a deferred trace is
called and is used to know that the mask needs to be cleared. The other
checks if the cache has been allocated, and if so, it resets the
nr_entries so that the unwinder knows it needs to do the work to get a new
user space stack trace again (it only does it once per entering the
kernel).
Use one of the bits in the unwind mask as a "USED" bit that gets set
whenever a trace is created. This will make it possible to only check the
unwind_mask in the unwind_reset_info() to know if it needs to do work or
not and eliminates a conditional that happens every time the task goes
back to user space.
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
include/linux/unwind_deferred.h | 14 +++++++-------
kernel/unwind/deferred.c | 5 ++++-
2 files changed, 11 insertions(+), 8 deletions(-)
diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index d25a72fb21ef..a1c62097f142 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -21,6 +21,10 @@ struct unwind_work {
#define UNWIND_PENDING_BIT (BITS_PER_LONG - 1)
#define UNWIND_PENDING BIT(UNWIND_PENDING_BIT)
+/* Set if the unwinding was used (directly or deferred) */
+#define UNWIND_USED_BIT (UNWIND_PENDING_BIT - 1)
+#define UNWIND_USED BIT(UNWIND_USED_BIT)
+
enum {
UNWIND_ALREADY_PENDING = 1,
UNWIND_ALREADY_EXECUTED = 2,
@@ -49,14 +53,10 @@ static __always_inline void unwind_reset_info(void)
return;
} while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL));
local64_set(¤t->unwind_info.timestamp, 0);
+
+ if (unlikely(info->cache))
+ info->cache->nr_entries = 0;
}
- /*
- * As unwind_user_faultable() can be called directly and
- * depends on nr_entries being cleared on exit to user,
- * this needs to be a separate conditional.
- */
- if (unlikely(info->cache))
- info->cache->nr_entries = 0;
}
#else /* !CONFIG_UNWIND_USER */
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index e7e4442926d3..5ab9b9045ae5 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -131,6 +131,9 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
cache->nr_entries = trace->nr;
+ /* Clear nr_entries on way back to user space */
+ set_bit(UNWIND_USED_BIT, &info->unwind_mask);
+
return 0;
}
@@ -308,7 +311,7 @@ int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func)
guard(mutex)(&callback_mutex);
/* See if there's a bit in the mask available */
- if (unwind_mask == ~(UNWIND_PENDING))
+ if (unwind_mask == ~(UNWIND_PENDING|UNWIND_USED))
return -EBUSY;
work->bit = ffz(unwind_mask);
--
2.47.2
next prev parent reply other threads:[~2025-07-01 0:54 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-01 0:53 [PATCH v12 00/14] unwind_user: x86: Deferred unwinding infrastructure Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 01/14] unwind_user: Add user space unwinding API Steven Rostedt
2025-07-04 17:58 ` Mathieu Desnoyers
2025-07-04 18:20 ` Mathieu Desnoyers
2025-07-07 19:42 ` Steven Rostedt
2025-07-07 21:01 ` Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 02/14] unwind_user: Add frame pointer support Steven Rostedt
2025-07-01 2:10 ` Linus Torvalds
2025-07-01 2:56 ` Steven Rostedt
2025-07-01 3:05 ` Steven Rostedt
2025-07-01 15:36 ` Jens Remus
2025-07-02 23:50 ` Steven Rostedt
2025-07-03 16:21 ` Jens Remus
2025-07-07 21:28 ` Steven Rostedt
2025-07-01 4:46 ` Florian Weimer
2025-07-01 12:14 ` Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 03/14] unwind_user: Add compat mode " Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 04/14] unwind_user/deferred: Add unwind_user_faultable() Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 05/14] unwind_user/deferred: Add unwind cache Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 06/14] unwind_user/deferred: Add deferred unwinding interface Steven Rostedt
2025-07-02 16:36 ` Peter Zijlstra
2025-07-02 16:42 ` Steven Rostedt
2025-07-02 16:56 ` Linus Torvalds
2025-07-02 17:26 ` Steven Rostedt
2025-07-02 17:48 ` Steven Rostedt
2025-07-02 18:21 ` Linus Torvalds
2025-07-02 18:47 ` Mathieu Desnoyers
2025-07-02 19:05 ` Steven Rostedt
2025-07-02 19:12 ` Mathieu Desnoyers
2025-07-02 19:21 ` Steven Rostedt
2025-07-02 19:36 ` Steven Rostedt
2025-07-02 19:40 ` Steven Rostedt
2025-07-02 19:48 ` Mathieu Desnoyers
2025-07-02 20:10 ` Steven Rostedt
2025-07-02 19:43 ` Mathieu Desnoyers
2025-07-02 19:51 ` Steven Rostedt
2025-07-02 18:57 ` Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 07/14] unwind_user/deferred: Make unwind deferral requests NMI-safe Steven Rostedt
2025-07-02 15:53 ` Jens Remus
2025-07-02 19:11 ` Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 08/14] unwind deferred: Use bitmask to determine which callbacks to call Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 09/14] unwind deferred: Use SRCU unwind_deferred_task_work() Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 10/14] unwind: Clear unwind_mask on exit back to user space Steven Rostedt
2025-07-01 0:53 ` Steven Rostedt [this message]
2025-07-01 0:53 ` [PATCH v12 12/14] unwind: Finish up unwind when a task exits Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 13/14] unwind_user/x86: Enable frame pointer unwinding on x86 Steven Rostedt
2025-07-01 0:53 ` [PATCH v12 14/14] unwind_user/x86: Enable compat mode " Steven Rostedt
2025-07-01 2:06 ` [PATCH v12 00/14] unwind_user: x86: Deferred unwinding infrastructure Linus Torvalds
2025-07-01 2:45 ` Steven Rostedt
2025-07-01 22:49 ` Kees Cook
2025-07-01 23:26 ` Steven Rostedt
2025-07-02 14:56 ` Kees Cook
2025-07-02 16:20 ` Mathieu Desnoyers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250701005452.410928589@goodmis.org \
--to=rostedt@goodmis.org \
--cc=akpm@linux-foundation.org \
--cc=andrii@kernel.org \
--cc=axboe@kernel.dk \
--cc=beaub@linux.microsoft.com \
--cc=bpf@vger.kernel.org \
--cc=fweimer@redhat.com \
--cc=indu.bhagat@oracle.com \
--cc=jemarch@gnu.org \
--cc=jolsa@kernel.org \
--cc=jpoimboe@kernel.org \
--cc=jremus@linux.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.