Merge tag 'trace-deferred-unwind-v6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull initial deferred unwind infrastructure from Steven Rostedt:
 "This is the core infrastructure for the deferred unwinder that is
  required for sframes[1]. Several other patch series are based on this
  work although those patch series are not dependent on each other. In
  order to simplify the development, having this core series upstream
  will allow the other series to be worked on in parallel. The other
  series are:

    - The two patches to implement x86 support [2] [3]

    - The s390 work [4]

    - The perf work [5]

    - The ftrace work [6]

    - The sframe work [7]

  And more is on the way.

  The core infrastructure adds the following in kernel APIs:

    - int unwind_user_faultable(struct unwind_stacktrace *trace);

        Performs a user space stack trace that may fault user pages in.

    - int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func);

        Allows a tracer to register with the unwind deferred
        infrastructure.

    - int unwind_deferred_request(struct unwind_work *work, u64 *cookie);

        Used when a tracer request a deferred trace. Can be called from
        interrupt or NMI context.

    - void unwind_deferred_cancel(struct unwind_work *work);

        Called by a tracer to unregister from the deferred unwind
        infrastructure.

    - void unwind_deferred_task_exit(struct task_struct *task);

        Called by task exit code to flush any pending unwind requests.

    - void unwind_task_init(struct task_struct *task);

        Called by do_fork() to initialize the task struct for the
        deferred unwinder.

    - void unwind_task_free(struct task_struct *task);

        Called by do_exit() to free up any resources used by the
        deferred unwinder.

    None of the above is actually compiled unless an architecture enables it,
    which none currently do"

Link: https://sourceware.org/binutils/wiki/sframe [1]
Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/ [2]
Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/ [3]
Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/ [4]
Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/ [5]
Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/ [6]
Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/ [7]

* tag 'trace-deferred-unwind-v6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  unwind: Finish up unwind when a task exits
  unwind deferred: Use SRCU unwind_deferred_task_work()
  unwind: Add USED bit to only have one conditional on way back to user space
  unwind deferred: Add unwind_completed mask to stop spurious callbacks
  unwind deferred: Use bitmask to determine which callbacks to call
  unwind_user/deferred: Make unwind deferral requests NMI-safe
  unwind_user/deferred: Add deferred unwinding interface
  unwind_user/deferred: Add unwind cache
  unwind_user/deferred: Add unwind_user_faultable()
  unwind_user: Add user space unwinding API with frame pointer support

Author: torvalds

MAINTAINERS

@@ -26253,6 +26253,13 @@ F:	Documentation/driver-api/uio-howto.rst
 F:	drivers/uio/
 F:	include/linux/uio_driver.h
 
+USERSPACE STACK UNWINDING
+M:	Josh Poimboeuf <[email protected]>
+M:	Steven Rostedt <[email protected]>
+S:	Maintained
+F:	include/linux/unwind*.h
+F:	kernel/unwind/
+
 UTIL-LINUX PACKAGE
 M:	Karel Zak <[email protected]>
 L:	[email protected]

arch/Kconfig

@@ -444,6 +444,13 @@ config HAVE_HARDLOCKUP_DETECTOR_ARCH
 	  It uses the same command line parameters, and sysctl interface,
 	  as the generic hardlockup detectors.
 
+config UNWIND_USER
+	bool
+
+config HAVE_UNWIND_USER_FP
+	bool
+	select UNWIND_USER
+
 config HAVE_PERF_REGS
 	bool
 	help

include/asm-generic/Kbuild

@@ -59,6 +59,7 @@ mandatory-y += tlbflush.h
 mandatory-y += topology.h
 mandatory-y += trace_clock.h
 mandatory-y += uaccess.h
+mandatory-y += unwind_user.h
 mandatory-y += vermagic.h
 mandatory-y += vga.h
 mandatory-y += video.h

include/asm-generic/unwind_user.h

@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_UNWIND_USER_H
+#define _ASM_GENERIC_UNWIND_USER_H
+
+#endif /* _ASM_GENERIC_UNWIND_USER_H */

include/linux/irq-entry-common.h

@@ -7,6 +7,7 @@
 #include <linux/context_tracking.h>
 #include <linux/tick.h>
 #include <linux/kmsan.h>
+#include <linux/unwind_deferred.h>
 
 #include <asm/entry-common.h>
 
@@ -256,6 +257,7 @@ static __always_inline void exit_to_user_mode(void)
 	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
+	unwind_reset_info();
 	user_enter_irqoff();
 	arch_exit_to_user_mode();
 	lockdep_hardirqs_on(CALLER_ADDR0);

include/linux/sched.h

@@ -47,6 +47,7 @@
 #include <linux/rv.h>
 #include <linux/uidgid_types.h>
 #include <linux/tracepoint-defs.h>
+#include <linux/unwind_deferred_types.h>
 #include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
@@ -1646,6 +1647,10 @@ struct task_struct {
 	struct user_event_mm		*user_event_mm;
 #endif
 
+#ifdef CONFIG_UNWIND_USER
+	struct unwind_task_info		unwind_info;
+#endif
+
 	/* CPU-specific state of this task: */
 	struct thread_struct		thread;
 

include/linux/unwind_deferred.h

@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNWIND_USER_DEFERRED_H
+#define _LINUX_UNWIND_USER_DEFERRED_H
+
+#include <linux/task_work.h>
+#include <linux/unwind_user.h>
+#include <linux/unwind_deferred_types.h>
+
+struct unwind_work;
+
+typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stacktrace *trace, u64 cookie);
+
+struct unwind_work {
+	struct list_head		list;
+	unwind_callback_t		func;
+	int				bit;
+};
+
+#ifdef CONFIG_UNWIND_USER
+
+enum {
+	UNWIND_PENDING_BIT = 0,
+	UNWIND_USED_BIT,
+};
+
+enum {
+	UNWIND_PENDING		= BIT(UNWIND_PENDING_BIT),
+
+	/* Set if the unwinding was used (directly or deferred) */
+	UNWIND_USED		= BIT(UNWIND_USED_BIT)
+};
+
+void unwind_task_init(struct task_struct *task);
+void unwind_task_free(struct task_struct *task);
+
+int unwind_user_faultable(struct unwind_stacktrace *trace);
+
+int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func);
+int unwind_deferred_request(struct unwind_work *work, u64 *cookie);
+void unwind_deferred_cancel(struct unwind_work *work);
+
+void unwind_deferred_task_exit(struct task_struct *task);
+
+static __always_inline void unwind_reset_info(void)
+{
+	struct unwind_task_info *info = &current->unwind_info;
+	unsigned long bits;
+
+	/* Was there any unwinding? */
+	if (unlikely(info->unwind_mask)) {
+		bits = info->unwind_mask;
+		do {
+			/* Is a task_work going to run again before going back */
+			if (bits & UNWIND_PENDING)
+				return;
+		} while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL));
+		current->unwind_info.id.id = 0;
+
+		if (unlikely(info->cache)) {
+			info->cache->nr_entries = 0;
+			info->cache->unwind_completed = 0;
+		}
+	}
+}
+
+#else /* !CONFIG_UNWIND_USER */
+
+static inline void unwind_task_init(struct task_struct *task) {}
+static inline void unwind_task_free(struct task_struct *task) {}
+
+static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; }
+static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) { return -ENOSYS; }
+static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; }
+static inline void unwind_deferred_cancel(struct unwind_work *work) {}
+
+static inline void unwind_deferred_task_exit(struct task_struct *task) {}
+static inline void unwind_reset_info(void) {}
+
+#endif /* !CONFIG_UNWIND_USER */
+
+#endif /* _LINUX_UNWIND_USER_DEFERRED_H */

include/linux/unwind_deferred_types.h

@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H
+#define _LINUX_UNWIND_USER_DEFERRED_TYPES_H
+
+struct unwind_cache {
+	unsigned long		unwind_completed;
+	unsigned int		nr_entries;
+	unsigned long		entries[];
+};
+
+/*
+ * The unwind_task_id is a unique identifier that maps to a user space
+ * stacktrace. It is generated the first time a deferred user space
+ * stacktrace is requested after a task has entered the kerenl and
+ * is cleared to zero when it exits. The mapped id will be a non-zero
+ * number.
+ *
+ * To simplify the generation of the 64 bit number, 32 bits will be
+ * the CPU it was generated on, and the other 32 bits will be a per
+ * cpu counter that gets incremented by two every time a new identifier
+ * is generated. The LSB will always be set to keep the value
+ * from being zero.
+ */
+union unwind_task_id {
+	struct {
+		u32		cpu;
+		u32		cnt;
+	};
+	u64			id;
+};
+
+struct unwind_task_info {
+	unsigned long		unwind_mask;
+	struct unwind_cache	*cache;
+	struct callback_head	work;
+	union unwind_task_id	id;
+};
+
+#endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */

include/linux/unwind_user.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNWIND_USER_H
+#define _LINUX_UNWIND_USER_H
+
+#include <linux/unwind_user_types.h>
+#include <asm/unwind_user.h>
+
+#ifndef ARCH_INIT_USER_FP_FRAME
+ #define ARCH_INIT_USER_FP_FRAME
+#endif
+
+int unwind_user(struct unwind_stacktrace *trace, unsigned int max_entries);
+
+#endif /* _LINUX_UNWIND_USER_H */

include/linux/unwind_user_types.h

@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNWIND_USER_TYPES_H
+#define _LINUX_UNWIND_USER_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * Unwind types, listed in priority order: lower numbers are attempted first if
+ * available.
+ */
+enum unwind_user_type_bits {
+	UNWIND_USER_TYPE_FP_BIT =		0,
+
+	NR_UNWIND_USER_TYPE_BITS,
+};
+
+enum unwind_user_type {
+	/* Type "none" for the start of stack walk iteration. */
+	UNWIND_USER_TYPE_NONE =			0,
+	UNWIND_USER_TYPE_FP =			BIT(UNWIND_USER_TYPE_FP_BIT),
+};
+
+struct unwind_stacktrace {
+	unsigned int	nr;
+	unsigned long	*entries;
+};
+
+struct unwind_user_frame {
+	s32 cfa_off;
+	s32 ra_off;
+	s32 fp_off;
+	bool use_fp;
+};
+
+struct unwind_user_state {
+	unsigned long				ip;
+	unsigned long				sp;
+	unsigned long				fp;
+	enum unwind_user_type			current_type;
+	unsigned int				available_types;
+	bool					done;
+};
+
+#endif /* _LINUX_UNWIND_USER_TYPES_H */