unwind_user: Add user space unwinding API with frame pointer support

Introduce a generic API for unwinding user stacks.

In order to expand user space unwinding to be able to handle more complex
scenarios, such as deferred unwinding and reading user space information,
create a generic interface that all architectures can use that support the
various unwinding methods.

This is an alternative method for handling user space stack traces from
the simple stack_trace_save_user() API. This does not replace that
interface, but this interface will be used to expand the functionality of
user space stack walking.

None of the structures introduced will be exposed to user space tooling.

Support for frame pointer unwinding is added. For an architecture to
support frame pointer unwinding it needs to enable
CONFIG_HAVE_UNWIND_USER_FP and define ARCH_INIT_USER_FP_FRAME.

By encoding the frame offsets in struct unwind_user_frame, much of this
code can also be reused for future unwinder implementations like sframe.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.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: 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/20250729182404.975790139@kernel.org
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Co-developed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/all/20250710164301.3094-2-mathieu.desnoyers@efficios.com/
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Co-developed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

3 files changed, 130 insertions, 0 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 32e80dd626af..541186050251 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -55,6 +55,7 @@ obj-y += rcu/
 obj-y += livepatch/
 obj-y += dma/
 obj-y += entry/
+obj-y += unwind/
 obj-$(CONFIG_MODULES) += module/
 
 obj-$(CONFIG_KCMP) += kcmp.o
diff --git a/kernel/unwind/Makefile b/kernel/unwind/Makefile
new file mode 100644
index 000000000000..349ce3677526
--- /dev/null
+++ b/kernel/unwind/Makefile
@@ -0,0 +1 @@
+ obj-$(CONFIG_UNWIND_USER) += user.o
diff --git a/kernel/unwind/user.c b/kernel/unwind/user.c
new file mode 100644
index 000000000000..97a8415e3216
--- /dev/null
+++ b/kernel/unwind/user.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+* Generic interfaces for unwinding user space
+*/
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/unwind_user.h>
+#include <linux/uaccess.h>
+
+static const struct unwind_user_frame fp_frame = {
+	ARCH_INIT_USER_FP_FRAME
+};
+
+#define for_each_user_frame(state) \
+	for (unwind_user_start(state); !(state)->done; unwind_user_next(state))
+
+static int unwind_user_next_fp(struct unwind_user_state *state)
+{
+	const struct unwind_user_frame *frame = &fp_frame;
+	unsigned long cfa, fp, ra;
+	unsigned int shift;
+
+	if (frame->use_fp) {
+		if (state->fp < state->sp)
+			return -EINVAL;
+		cfa = state->fp;
+	} else {
+		cfa = state->sp;
+	}
+
+	/* Get the Canonical Frame Address (CFA) */
+	cfa += frame->cfa_off;
+
+	/* stack going in wrong direction? */
+	if (cfa <= state->sp)
+		return -EINVAL;
+
+	/* Make sure that the address is word aligned */
+	shift = sizeof(long) == 4 ? 2 : 3;
+	if (cfa & ((1 << shift) - 1))
+		return -EINVAL;
+
+	/* Find the Return Address (RA) */
+	if (get_user(ra, (unsigned long *)(cfa + frame->ra_off)))
+		return -EINVAL;
+
+	if (frame->fp_off && get_user(fp, (unsigned long __user *)(cfa + frame->fp_off)))
+		return -EINVAL;
+
+	state->ip = ra;
+	state->sp = cfa;
+	if (frame->fp_off)
+		state->fp = fp;
+	return 0;
+}
+
+static int unwind_user_next(struct unwind_user_state *state)
+{
+	unsigned long iter_mask = state->available_types;
+	unsigned int bit;
+
+	if (state->done)
+		return -EINVAL;
+
+	for_each_set_bit(bit, &iter_mask, NR_UNWIND_USER_TYPE_BITS) {
+		enum unwind_user_type type = BIT(bit);
+
+		state->current_type = type;
+		switch (type) {
+		case UNWIND_USER_TYPE_FP:
+			if (!unwind_user_next_fp(state))
+				return 0;
+			continue;
+		default:
+			WARN_ONCE(1, "Undefined unwind bit %d", bit);
+			break;
+		}
+		break;
+	}
+
+	/* No successful unwind method. */
+	state->current_type = UNWIND_USER_TYPE_NONE;
+	state->done = true;
+	return -EINVAL;
+}
+
+static int unwind_user_start(struct unwind_user_state *state)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+
+	memset(state, 0, sizeof(*state));
+
+	if ((current->flags & PF_KTHREAD) || !user_mode(regs)) {
+		state->done = true;
+		return -EINVAL;
+	}
+
+	if (IS_ENABLED(CONFIG_HAVE_UNWIND_USER_FP))
+		state->available_types |= UNWIND_USER_TYPE_FP;
+
+	state->ip = instruction_pointer(regs);
+	state->sp = user_stack_pointer(regs);
+	state->fp = frame_pointer(regs);
+
+	return 0;
+}
+
+int unwind_user(struct unwind_stacktrace *trace, unsigned int max_entries)
+{
+	struct unwind_user_state state;
+
+	trace->nr = 0;
+
+	if (!max_entries)
+		return -EINVAL;
+
+	if (current->flags & PF_KTHREAD)
+		return 0;
+
+	for_each_user_frame(&state) {
+		trace->entries[trace->nr++] = state.ip;
+		if (trace->nr >= max_entries)
+			break;
+	}
+
+	return 0;
+}