[for-next][PATCH 00/40] tracing: Updates for 5.16

[for-next][PATCH 00/40] tracing: Updates for 5.16

[Steven Rostedt]

Finally, this code now passes all my tests!

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
for-next

Head SHA1: fed240d9c9743815fcbc0ca5c0913292ce1f25e2


Arnd Bergmann (1):
      tracing: use %ps format string to print symbols

Carles Pey (1):
      ftrace: Add unit test for removing trace function

Changbin Du (1):
      tracing: in_irq() cleanup

Jiri Olsa (6):
      x86/ftrace: Remove extra orig rax move
      tracing: Add trampoline/graph selftest
      ftrace: Add ftrace_add_rec_direct function
      ftrace: Add multi direct register/unregister interface
      ftrace: Add multi direct modify interface
      ftrace/samples: Add multi direct interface test module

Kalesh Singh (1):
      tracing/cfi: Fix cmp_entries_* functions signature mismatch

Masami Hiramatsu (16):
      bootconfig: Allocate xbc_data inside xbc_init()
      bootconfig: Add xbc_get_info() for the node information
      tools/bootconfig: Run test script when build all
      bootconfig: Rename xbc_destroy_all() to xbc_exit()
      bootconfig: Split parse-tree part from xbc_init
      bootconfig: Remove unused debug function
      tools/bootconfig: Print all error message in stderr
      bootconfig: Replace u16 and u32 with uint16_t and uint32_t
      bootconfig: Cleanup dummy headers in tools/bootconfig
      x86/unwind: Compile kretprobe fixup code only if CONFIG_KRETPROBES=y
      arm64: kprobes: Record frame pointer with kretprobe instance
      arm64: kprobes: Make a frame pointer on __kretprobe_trampoline
      arm64: Recover kretprobe modified return address in stacktrace
      ARM: clang: Do not rely on lr register for stacktrace
      ARM: kprobes: Make a frame pointer on __kretprobe_trampoline
      ARM: Recover kretprobe modified return address in stacktrace

Steven Rostedt (VMware) (12):
      tracing: Initialize upper and lower vars in pid_list_refill_irq()
      tracefs: Have tracefs directories not set OTH permission bits by default
      tracing: Disable "other" permission bits in the tracefs files
      tracing: Use linker magic instead of recasting ftrace_ops_list_func()
      tracing: Reuse logic from perf's get_recursion_context()
      tracing/perf: Add interrupt_context_level() helper
      x86/ftrace: Remove fault protection code in prepare_ftrace_return
      ftrace/x86_64: Have function graph tracer depend on DYNAMIC_FTRACE
      x86/ftrace: Make function graph use ftrace directly
      tracing: Fix selftest config check for function graph start up test
      ftrace/direct: Do not disable when switching direct callers
      tracing: Explain the trace recursion transition bit better

Sven Schnelle (1):
      kprobes: convert tests to kunit

Weizhao Ouyang (1):
      ftrace: Cleanup ftrace_dyn_arch_init()

----
 arch/arm/Kconfig                              |   1 +
 arch/arm/include/asm/stacktrace.h             |   9 +
 arch/arm/kernel/ftrace.c                      |   5 -
 arch/arm/kernel/return_address.c              |   4 +
 arch/arm/kernel/stacktrace.c                  |  17 +-
 arch/arm/probes/kprobes/core.c                |  28 ++-
 arch/arm64/Kconfig                            |   1 +
 arch/arm64/include/asm/stacktrace.h           |   4 +
 arch/arm64/kernel/ftrace.c                    |   5 -
 arch/arm64/kernel/probes/kprobes.c            |   4 +-
 arch/arm64/kernel/probes/kprobes_trampoline.S |   4 +
 arch/arm64/kernel/stacktrace.c                |   7 +
 arch/csky/kernel/ftrace.c                     |   5 -
 arch/ia64/kernel/ftrace.c                     |   6 -
 arch/microblaze/kernel/ftrace.c               |   5 -
 arch/nds32/kernel/ftrace.c                    |   5 -
 arch/parisc/kernel/ftrace.c                   |   5 -
 arch/riscv/kernel/ftrace.c                    |   5 -
 arch/s390/kernel/ftrace.c                     |   5 -
 arch/sh/kernel/ftrace.c                       |   5 -
 arch/sparc/kernel/ftrace.c                    |   5 -
 arch/x86/Kconfig                              |   2 +-
 arch/x86/include/asm/ftrace.h                 |   9 +-
 arch/x86/include/asm/unwind.h                 |   6 +
 arch/x86/kernel/ftrace.c                      |  76 +++---
 arch/x86/kernel/ftrace_64.S                   |  30 +--
 fs/tracefs/inode.c                            |   3 +-
 include/asm-generic/vmlinux.lds.h             |  10 +-
 include/linux/bootconfig.h                    |  31 ++-
 include/linux/ftrace.h                        |  38 ++-
 include/linux/preempt.h                       |  21 ++
 include/linux/trace_recursion.h               |  16 +-
 init/main.c                                   |  16 +-
 kernel/events/internal.h                      |   7 +-
 kernel/kprobes.c                              |   3 -
 kernel/test_kprobes.c                         | 222 +++++-------------
 kernel/trace/fgraph.c                         |   6 +-
 kernel/trace/ftrace.c                         | 325 ++++++++++++++++++++++----
 kernel/trace/pid_list.c                       |   4 +-
 kernel/trace/ring_buffer.c                    |   9 +-
 kernel/trace/trace.c                          |  73 +++---
 kernel/trace/trace.h                          |   5 +-
 kernel/trace/trace_dynevent.c                 |   2 +-
 kernel/trace/trace_events.c                   |  42 ++--
 kernel/trace/trace_events_hist.c              |  15 +-
 kernel/trace/trace_events_synth.c             |   4 +-
 kernel/trace/trace_functions_graph.c          |   4 +-
 kernel/trace/trace_hwlat.c                    |   6 +-
 kernel/trace/trace_kprobe.c                   |   8 +-
 kernel/trace/trace_osnoise.c                  |  14 +-
 kernel/trace/trace_printk.c                   |   2 +-
 kernel/trace/trace_recursion_record.c         |   4 +-
 kernel/trace/trace_selftest.c                 |  92 +++++++-
 kernel/trace/trace_stack.c                    |   6 +-
 kernel/trace/trace_stat.c                     |   6 +-
 kernel/trace/trace_uprobe.c                   |   4 +-
 kernel/trace/tracing_map.c                    |  40 ++--
 lib/Kconfig.debug                             |   3 +-
 lib/bootconfig.c                              | 231 +++++++++++-------
 samples/ftrace/Makefile                       |   1 +
 samples/ftrace/ftrace-direct-multi.c          |  52 +++++
 tools/bootconfig/Makefile                     |   4 +-
 tools/bootconfig/include/linux/bootconfig.h   |  45 +++-
 tools/bootconfig/include/linux/bug.h          |  12 -
 tools/bootconfig/include/linux/ctype.h        |   7 -
 tools/bootconfig/include/linux/errno.h        |   7 -
 tools/bootconfig/include/linux/kernel.h       |  18 --
 tools/bootconfig/include/linux/memblock.h     |  11 -
 tools/bootconfig/include/linux/printk.h       |  14 --
 tools/bootconfig/include/linux/string.h       |  32 ---
 tools/bootconfig/main.c                       |  32 +--
 71 files changed, 1033 insertions(+), 732 deletions(-)
 create mode 100644 samples/ftrace/ftrace-direct-multi.c
 delete mode 100644 tools/bootconfig/include/linux/bug.h
 delete mode 100644 tools/bootconfig/include/linux/ctype.h
 delete mode 100644 tools/bootconfig/include/linux/errno.h
 delete mode 100644 tools/bootconfig/include/linux/kernel.h
 delete mode 100644 tools/bootconfig/include/linux/memblock.h
 delete mode 100644 tools/bootconfig/include/linux/printk.h
 delete mode 100644 tools/bootconfig/include/linux/string.h

[for-next][PATCH 01/40] tracing: Initialize upper and lower vars in pid_list_refill_irq()

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

The upper and lower variables are set as link lists to add into the sparse
array. If they are NULL, after the needed allocations are done, then there
is nothing to add. But they need to be initialized to NULL for this to
work.

Link: https://lore.kernel.org/all/221bc7ba-a475-1cb9-1bbe-730bb9c2d448@canonical.com/

Fixes: 8d6e90983ade ("tracing: Create a sparse bitmask for pid filtering")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/pid_list.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c
index cbf8031b2b99..a2ef1d18126a 100644
--- a/kernel/trace/pid_list.c
+++ b/kernel/trace/pid_list.c
@@ -333,8 +333,8 @@ static void pid_list_refill_irq(struct irq_work *iwork)
 {
 	struct trace_pid_list *pid_list = container_of(iwork, struct trace_pid_list,
 						       refill_irqwork);
-	union upper_chunk *upper;
-	union lower_chunk *lower;
+	union upper_chunk *upper = NULL;
+	union lower_chunk *lower = NULL;
 	union upper_chunk **upper_next = &upper;
 	union lower_chunk **lower_next = &lower;
 	int upper_count;
-- 
2.33.0

[for-next][PATCH 02/40] tracefs: Have tracefs directories not set OTH permission bits by default

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

The tracefs file system is by default mounted such that only root user can
access it. But there are legitimate reasons to create a group and allow
those added to the group to have access to tracing. By changing the
permissions of the tracefs mount point to allow access, it will allow
group access to the tracefs directory.

There should not be any real reason to allow all access to the tracefs
directory as it contains sensitive information. Have the default
permission of directories being created not have any OTH (other) bits set,
such that an admin that wants to give permission to a group has to first
disable all OTH bits in the file system.

Link: https://lkml.kernel.org/r/20210818153038.664127804@goodmis.org

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 fs/tracefs/inode.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 1261e8b41edb..925a621b432e 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -432,7 +432,8 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent,
 	if (unlikely(!inode))
 		return failed_creating(dentry);
 
-	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	/* Do not set bits for OTH */
+	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP;
 	inode->i_op = ops;
 	inode->i_fop = &simple_dir_operations;
 
-- 
2.33.0

[for-next][PATCH 03/40] tracing: Disable "other" permission bits in the tracefs files

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

When building the files in the tracefs file system, do not by default set
any permissions for OTH (other). This will make it easier for admins who
want to define a group for accessing tracefs and not having to first
disable all the permission bits for "other" in the file system.

As tracing can leak sensitive information, it should never by default
allowing all users access. An admin can still set the permission bits for
others to have access, which may be useful for creating a honeypot and
seeing who takes advantage of it and roots the machine.

Link: https://lkml.kernel.org/r/20210818153038.864149276@goodmis.org

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c                 | 23 +++++----
 kernel/trace/trace.c                  | 73 ++++++++++++++-------------
 kernel/trace/trace.h                  |  3 ++
 kernel/trace/trace_dynevent.c         |  2 +-
 kernel/trace/trace_events.c           | 42 +++++++--------
 kernel/trace/trace_events_synth.c     |  4 +-
 kernel/trace/trace_functions_graph.c  |  2 +-
 kernel/trace/trace_hwlat.c            |  6 +--
 kernel/trace/trace_kprobe.c           |  8 +--
 kernel/trace/trace_osnoise.c          | 14 ++---
 kernel/trace/trace_printk.c           |  2 +-
 kernel/trace/trace_recursion_record.c |  4 +-
 kernel/trace/trace_stack.c            |  6 +--
 kernel/trace/trace_stat.c             |  6 +--
 kernel/trace/trace_uprobe.c           |  4 +-
 15 files changed, 103 insertions(+), 96 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3eec6792f115..0a0dbc2d411b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -988,8 +988,9 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
 		}
 	}
 
-	entry = tracefs_create_file("function_profile_enabled", 0644,
-				    d_tracer, NULL, &ftrace_profile_fops);
+	entry = tracefs_create_file("function_profile_enabled",
+				    TRACE_MODE_WRITE, d_tracer, NULL,
+				    &ftrace_profile_fops);
 	if (!entry)
 		pr_warn("Could not create tracefs 'function_profile_enabled' entry\n");
 }
@@ -6109,10 +6110,10 @@ void ftrace_create_filter_files(struct ftrace_ops *ops,
 				struct dentry *parent)
 {
 
-	trace_create_file("set_ftrace_filter", 0644, parent,
+	trace_create_file("set_ftrace_filter", TRACE_MODE_WRITE, parent,
 			  ops, &ftrace_filter_fops);
 
-	trace_create_file("set_ftrace_notrace", 0644, parent,
+	trace_create_file("set_ftrace_notrace", TRACE_MODE_WRITE, parent,
 			  ops, &ftrace_notrace_fops);
 }
 
@@ -6139,19 +6140,19 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops)
 static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
 {
 
-	trace_create_file("available_filter_functions", 0444,
+	trace_create_file("available_filter_functions", TRACE_MODE_READ,
 			d_tracer, NULL, &ftrace_avail_fops);
 
-	trace_create_file("enabled_functions", 0444,
+	trace_create_file("enabled_functions", TRACE_MODE_READ,
 			d_tracer, NULL, &ftrace_enabled_fops);
 
 	ftrace_create_filter_files(&global_ops, d_tracer);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	trace_create_file("set_graph_function", 0644, d_tracer,
+	trace_create_file("set_graph_function", TRACE_MODE_WRITE, d_tracer,
 				    NULL,
 				    &ftrace_graph_fops);
-	trace_create_file("set_graph_notrace", 0644, d_tracer,
+	trace_create_file("set_graph_notrace", TRACE_MODE_WRITE, d_tracer,
 				    NULL,
 				    &ftrace_graph_notrace_fops);
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -7494,10 +7495,10 @@ static const struct file_operations ftrace_no_pid_fops = {
 
 void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 {
-	trace_create_file("set_ftrace_pid", 0644, d_tracer,
+	trace_create_file("set_ftrace_pid", TRACE_MODE_WRITE, d_tracer,
 			    tr, &ftrace_pid_fops);
-	trace_create_file("set_ftrace_notrace_pid", 0644, d_tracer,
-			    tr, &ftrace_no_pid_fops);
+	trace_create_file("set_ftrace_notrace_pid", TRACE_MODE_WRITE,
+			  d_tracer, tr, &ftrace_no_pid_fops);
 }
 
 void __init ftrace_init_tracefs_toplevel(struct trace_array *tr,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dcced07a45e6..985390cb8441 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1690,7 +1690,8 @@ static void trace_create_maxlat_file(struct trace_array *tr,
 {
 	INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn);
 	init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq);
-	tr->d_max_latency = trace_create_file("tracing_max_latency", 0644,
+	tr->d_max_latency = trace_create_file("tracing_max_latency",
+					      TRACE_MODE_WRITE,
 					      d_tracer, &tr->max_latency,
 					      &tracing_max_lat_fops);
 }
@@ -1727,8 +1728,8 @@ void latency_fsnotify(struct trace_array *tr)
 #else
 
 #define trace_create_maxlat_file(tr, d_tracer)				\
-	trace_create_file("tracing_max_latency", 0644, d_tracer,	\
-			  &tr->max_latency, &tracing_max_lat_fops)
+	trace_create_file("tracing_max_latency", TRACE_MODE_WRITE,	\
+			  d_tracer, &tr->max_latency, &tracing_max_lat_fops)
 
 #endif
 
@@ -6054,7 +6055,7 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start,
 
 static void trace_create_eval_file(struct dentry *d_tracer)
 {
-	trace_create_file("eval_map", 0444, d_tracer,
+	trace_create_file("eval_map", TRACE_MODE_READ, d_tracer,
 			  NULL, &tracing_eval_map_fops);
 }
 
@@ -8567,27 +8568,27 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu)
 	}
 
 	/* per cpu trace_pipe */
-	trace_create_cpu_file("trace_pipe", 0444, d_cpu,
+	trace_create_cpu_file("trace_pipe", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_pipe_fops);
 
 	/* per cpu trace */
-	trace_create_cpu_file("trace", 0644, d_cpu,
+	trace_create_cpu_file("trace", TRACE_MODE_WRITE, d_cpu,
 				tr, cpu, &tracing_fops);
 
-	trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu,
+	trace_create_cpu_file("trace_pipe_raw", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_buffers_fops);
 
-	trace_create_cpu_file("stats", 0444, d_cpu,
+	trace_create_cpu_file("stats", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_stats_fops);
 
-	trace_create_cpu_file("buffer_size_kb", 0444, d_cpu,
+	trace_create_cpu_file("buffer_size_kb", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_entries_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_cpu_file("snapshot", 0644, d_cpu,
+	trace_create_cpu_file("snapshot", TRACE_MODE_WRITE, d_cpu,
 				tr, cpu, &snapshot_fops);
 
-	trace_create_cpu_file("snapshot_raw", 0444, d_cpu,
+	trace_create_cpu_file("snapshot_raw", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &snapshot_raw_fops);
 #endif
 }
@@ -8793,8 +8794,8 @@ create_trace_option_file(struct trace_array *tr,
 	topt->opt = opt;
 	topt->tr = tr;
 
-	topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
-				    &trace_options_fops);
+	topt->entry = trace_create_file(opt->name, TRACE_MODE_WRITE,
+					t_options, topt, &trace_options_fops);
 
 }
 
@@ -8869,7 +8870,7 @@ create_trace_option_core_file(struct trace_array *tr,
 	if (!t_options)
 		return NULL;
 
-	return trace_create_file(option, 0644, t_options,
+	return trace_create_file(option, TRACE_MODE_WRITE, t_options,
 				 (void *)&tr->trace_flags_index[index],
 				 &trace_options_core_fops);
 }
@@ -9394,28 +9395,28 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	struct trace_event_file *file;
 	int cpu;
 
-	trace_create_file("available_tracers", 0444, d_tracer,
+	trace_create_file("available_tracers", TRACE_MODE_READ, d_tracer,
 			tr, &show_traces_fops);
 
-	trace_create_file("current_tracer", 0644, d_tracer,
+	trace_create_file("current_tracer", TRACE_MODE_WRITE, d_tracer,
 			tr, &set_tracer_fops);
 
-	trace_create_file("tracing_cpumask", 0644, d_tracer,
+	trace_create_file("tracing_cpumask", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_cpumask_fops);
 
-	trace_create_file("trace_options", 0644, d_tracer,
+	trace_create_file("trace_options", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_iter_fops);
 
-	trace_create_file("trace", 0644, d_tracer,
+	trace_create_file("trace", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_fops);
 
-	trace_create_file("trace_pipe", 0444, d_tracer,
+	trace_create_file("trace_pipe", TRACE_MODE_READ, d_tracer,
 			  tr, &tracing_pipe_fops);
 
-	trace_create_file("buffer_size_kb", 0644, d_tracer,
+	trace_create_file("buffer_size_kb", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_entries_fops);
 
-	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
+	trace_create_file("buffer_total_size_kb", TRACE_MODE_READ, d_tracer,
 			  tr, &tracing_total_entries_fops);
 
 	trace_create_file("free_buffer", 0200, d_tracer,
@@ -9426,25 +9427,25 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 
 	file = __find_event_file(tr, "ftrace", "print");
 	if (file && file->dir)
-		trace_create_file("trigger", 0644, file->dir, file,
-				  &event_trigger_fops);
+		trace_create_file("trigger", TRACE_MODE_WRITE, file->dir,
+				  file, &event_trigger_fops);
 	tr->trace_marker_file = file;
 
 	trace_create_file("trace_marker_raw", 0220, d_tracer,
 			  tr, &tracing_mark_raw_fops);
 
-	trace_create_file("trace_clock", 0644, d_tracer, tr,
+	trace_create_file("trace_clock", TRACE_MODE_WRITE, d_tracer, tr,
 			  &trace_clock_fops);
 
-	trace_create_file("tracing_on", 0644, d_tracer,
+	trace_create_file("tracing_on", TRACE_MODE_WRITE, d_tracer,
 			  tr, &rb_simple_fops);
 
-	trace_create_file("timestamp_mode", 0444, d_tracer, tr,
+	trace_create_file("timestamp_mode", TRACE_MODE_READ, d_tracer, tr,
 			  &trace_time_stamp_mode_fops);
 
 	tr->buffer_percent = 50;
 
-	trace_create_file("buffer_percent", 0444, d_tracer,
+	trace_create_file("buffer_percent", TRACE_MODE_READ, d_tracer,
 			tr, &buffer_percent_fops);
 
 	create_trace_options_dir(tr);
@@ -9457,11 +9458,11 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 		MEM_FAIL(1, "Could not allocate function filter files");
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_file("snapshot", 0644, d_tracer,
+	trace_create_file("snapshot", TRACE_MODE_WRITE, d_tracer,
 			  tr, &snapshot_fops);
 #endif
 
-	trace_create_file("error_log", 0644, d_tracer,
+	trace_create_file("error_log", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_err_log_fops);
 
 	for_each_tracing_cpu(cpu)
@@ -9654,19 +9655,19 @@ static __init int tracer_init_tracefs(void)
 	init_tracer_tracefs(&global_trace, NULL);
 	ftrace_init_tracefs_toplevel(&global_trace, NULL);
 
-	trace_create_file("tracing_thresh", 0644, NULL,
+	trace_create_file("tracing_thresh", TRACE_MODE_WRITE, NULL,
 			&global_trace, &tracing_thresh_fops);
 
-	trace_create_file("README", 0444, NULL,
+	trace_create_file("README", TRACE_MODE_READ, NULL,
 			NULL, &tracing_readme_fops);
 
-	trace_create_file("saved_cmdlines", 0444, NULL,
+	trace_create_file("saved_cmdlines", TRACE_MODE_READ, NULL,
 			NULL, &tracing_saved_cmdlines_fops);
 
-	trace_create_file("saved_cmdlines_size", 0644, NULL,
+	trace_create_file("saved_cmdlines_size", TRACE_MODE_WRITE, NULL,
 			  NULL, &tracing_saved_cmdlines_size_fops);
 
-	trace_create_file("saved_tgids", 0444, NULL,
+	trace_create_file("saved_tgids", TRACE_MODE_READ, NULL,
 			NULL, &tracing_saved_tgids_fops);
 
 	trace_eval_init();
@@ -9678,7 +9679,7 @@ static __init int tracer_init_tracefs(void)
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	trace_create_file("dyn_ftrace_total_info", 0444, NULL,
+	trace_create_file("dyn_ftrace_total_info", TRACE_MODE_READ, NULL,
 			NULL, &tracing_dyn_info_fops);
 #endif
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2ec500186992..6c3808132b16 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -29,6 +29,9 @@
 #include <asm/syscall.h>	/* some archs define it here */
 #endif
 
+#define TRACE_MODE_WRITE	0640
+#define TRACE_MODE_READ		0440
+
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
 
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index 1110112e55bd..e34e8182ee4b 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -262,7 +262,7 @@ static __init int init_dynamic_event(void)
 	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("dynamic_events", 0644, NULL,
+	entry = tracefs_create_file("dynamic_events", TRACE_MODE_WRITE, NULL,
 				    NULL, &dynamic_events_ops);
 
 	/* Event list interface */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index bf54d2803261..4021b9a79f93 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2312,7 +2312,8 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	/* the ftrace system is special, do not create enable or filter files */
 	if (strcmp(name, "ftrace") != 0) {
 
-		entry = tracefs_create_file("filter", 0644, dir->entry, dir,
+		entry = tracefs_create_file("filter", TRACE_MODE_WRITE,
+					    dir->entry, dir,
 					    &ftrace_subsystem_filter_fops);
 		if (!entry) {
 			kfree(system->filter);
@@ -2320,7 +2321,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 			pr_warn("Could not create tracefs '%s/filter' entry\n", name);
 		}
 
-		trace_create_file("enable", 0644, dir->entry, dir,
+		trace_create_file("enable", TRACE_MODE_WRITE, dir->entry, dir,
 				  &ftrace_system_enable_fops);
 	}
 
@@ -2402,12 +2403,12 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	}
 
 	if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
-		trace_create_file("enable", 0644, file->dir, file,
+		trace_create_file("enable", TRACE_MODE_WRITE, file->dir, file,
 				  &ftrace_enable_fops);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (call->event.type && call->class->reg)
-		trace_create_file("id", 0444, file->dir,
+		trace_create_file("id", TRACE_MODE_READ, file->dir,
 				  (void *)(long)call->event.type,
 				  &ftrace_event_id_fops);
 #endif
@@ -2423,22 +2424,22 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	 * triggers or filters.
 	 */
 	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
-		trace_create_file("filter", 0644, file->dir, file,
-				  &ftrace_event_filter_fops);
+		trace_create_file("filter", TRACE_MODE_WRITE, file->dir,
+				  file, &ftrace_event_filter_fops);
 
-		trace_create_file("trigger", 0644, file->dir, file,
-				  &event_trigger_fops);
+		trace_create_file("trigger", TRACE_MODE_WRITE, file->dir,
+				  file, &event_trigger_fops);
 	}
 
 #ifdef CONFIG_HIST_TRIGGERS
-	trace_create_file("hist", 0444, file->dir, file,
+	trace_create_file("hist", TRACE_MODE_READ, file->dir, file,
 			  &event_hist_fops);
 #endif
 #ifdef CONFIG_HIST_TRIGGERS_DEBUG
-	trace_create_file("hist_debug", 0444, file->dir, file,
+	trace_create_file("hist_debug", TRACE_MODE_READ, file->dir, file,
 			  &event_hist_debug_fops);
 #endif
-	trace_create_file("format", 0444, file->dir, call,
+	trace_create_file("format", TRACE_MODE_READ, file->dir, call,
 			  &ftrace_event_format_fops);
 
 #ifdef CONFIG_TRACE_EVENT_INJECT
@@ -3433,7 +3434,7 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 	struct dentry *d_events;
 	struct dentry *entry;
 
-	entry = tracefs_create_file("set_event", 0644, parent,
+	entry = tracefs_create_file("set_event", TRACE_MODE_WRITE, parent,
 				    tr, &ftrace_set_event_fops);
 	if (!entry) {
 		pr_warn("Could not create tracefs 'set_event' entry\n");
@@ -3446,7 +3447,7 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 		return -ENOMEM;
 	}
 
-	entry = trace_create_file("enable", 0644, d_events,
+	entry = trace_create_file("enable", TRACE_MODE_WRITE, d_events,
 				  tr, &ftrace_tr_enable_fops);
 	if (!entry) {
 		pr_warn("Could not create tracefs 'enable' entry\n");
@@ -3455,24 +3456,25 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 
 	/* There are not as crucial, just warn if they are not created */
 
-	entry = tracefs_create_file("set_event_pid", 0644, parent,
+	entry = tracefs_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
 				    tr, &ftrace_set_event_pid_fops);
 	if (!entry)
 		pr_warn("Could not create tracefs 'set_event_pid' entry\n");
 
-	entry = tracefs_create_file("set_event_notrace_pid", 0644, parent,
-				    tr, &ftrace_set_event_notrace_pid_fops);
+	entry = tracefs_create_file("set_event_notrace_pid",
+				    TRACE_MODE_WRITE, parent, tr,
+				    &ftrace_set_event_notrace_pid_fops);
 	if (!entry)
 		pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n");
 
 	/* ring buffer internal formats */
-	entry = trace_create_file("header_page", 0444, d_events,
+	entry = trace_create_file("header_page", TRACE_MODE_READ, d_events,
 				  ring_buffer_print_page_header,
 				  &ftrace_show_header_fops);
 	if (!entry)
 		pr_warn("Could not create tracefs 'header_page' entry\n");
 
-	entry = trace_create_file("header_event", 0444, d_events,
+	entry = trace_create_file("header_event", TRACE_MODE_READ, d_events,
 				  ring_buffer_print_entry_header,
 				  &ftrace_show_header_fops);
 	if (!entry)
@@ -3689,8 +3691,8 @@ __init int event_trace_init(void)
 	if (!tr)
 		return -ENODEV;
 
-	entry = tracefs_create_file("available_events", 0444, NULL,
-				    tr, &ftrace_avail_fops);
+	entry = tracefs_create_file("available_events", TRACE_MODE_READ,
+				    NULL, tr, &ftrace_avail_fops);
 	if (!entry)
 		pr_warn("Could not create tracefs 'available_events' entry\n");
 
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index d54094b7a9d7..22db3ce95e74 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -2227,8 +2227,8 @@ static __init int trace_events_synth_init(void)
 	if (err)
 		goto err;
 
-	entry = tracefs_create_file("synthetic_events", 0644, NULL,
-				    NULL, &synth_events_fops);
+	entry = tracefs_create_file("synthetic_events", TRACE_MODE_WRITE,
+				    NULL, NULL, &synth_events_fops);
 	if (!entry) {
 		err = -ENODEV;
 		goto err;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 0de6837722da..6b5ff3ba4251 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1340,7 +1340,7 @@ static __init int init_graph_tracefs(void)
 	if (ret)
 		return 0;
 
-	trace_create_file("max_graph_depth", 0644, NULL,
+	trace_create_file("max_graph_depth", TRACE_MODE_WRITE, NULL,
 			  NULL, &graph_depth_fops);
 
 	return 0;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 1b83d75eb103..d0a730d99a33 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -782,21 +782,21 @@ static int init_tracefs(void)
 	if (!top_dir)
 		return -ENOMEM;
 
-	hwlat_sample_window = tracefs_create_file("window", 0640,
+	hwlat_sample_window = tracefs_create_file("window", TRACE_MODE_WRITE,
 						  top_dir,
 						  &hwlat_window,
 						  &trace_min_max_fops);
 	if (!hwlat_sample_window)
 		goto err;
 
-	hwlat_sample_width = tracefs_create_file("width", 0644,
+	hwlat_sample_width = tracefs_create_file("width", TRACE_MODE_WRITE,
 						 top_dir,
 						 &hwlat_width,
 						 &trace_min_max_fops);
 	if (!hwlat_sample_width)
 		goto err;
 
-	hwlat_thread_mode = trace_create_file("mode", 0644,
+	hwlat_thread_mode = trace_create_file("mode", TRACE_MODE_WRITE,
 					      top_dir,
 					      NULL,
 					      &thread_mode_fops);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 0e1e7ce5f7ed..33272a7b6912 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1925,16 +1925,16 @@ static __init int init_kprobe_trace(void)
 	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("kprobe_events", 0644, NULL,
-				    NULL, &kprobe_events_ops);
+	entry = tracefs_create_file("kprobe_events", TRACE_MODE_WRITE,
+				    NULL, NULL, &kprobe_events_ops);
 
 	/* Event list interface */
 	if (!entry)
 		pr_warn("Could not create tracefs 'kprobe_events' entry\n");
 
 	/* Profile interface */
-	entry = tracefs_create_file("kprobe_profile", 0444, NULL,
-				    NULL, &kprobe_profile_ops);
+	entry = tracefs_create_file("kprobe_profile", TRACE_MODE_READ,
+				    NULL, NULL, &kprobe_profile_ops);
 
 	if (!entry)
 		pr_warn("Could not create tracefs 'kprobe_profile' entry\n");
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index ce053619f289..c4f14fb98aaa 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1856,38 +1856,38 @@ static int init_tracefs(void)
 	if (!top_dir)
 		return 0;
 
-	tmp = tracefs_create_file("period_us", 0640, top_dir,
+	tmp = tracefs_create_file("period_us", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_period, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 
-	tmp = tracefs_create_file("runtime_us", 0644, top_dir,
+	tmp = tracefs_create_file("runtime_us", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_runtime, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 
-	tmp = tracefs_create_file("stop_tracing_us", 0640, top_dir,
+	tmp = tracefs_create_file("stop_tracing_us", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_stop_tracing_in, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 
-	tmp = tracefs_create_file("stop_tracing_total_us", 0640, top_dir,
+	tmp = tracefs_create_file("stop_tracing_total_us", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_stop_tracing_total, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 
-	tmp = trace_create_file("cpus", 0644, top_dir, NULL, &cpus_fops);
+	tmp = trace_create_file("cpus", TRACE_MODE_WRITE, top_dir, NULL, &cpus_fops);
 	if (!tmp)
 		goto err;
 #ifdef CONFIG_TIMERLAT_TRACER
 #ifdef CONFIG_STACKTRACE
-	tmp = tracefs_create_file("print_stack", 0640, top_dir,
+	tmp = tracefs_create_file("print_stack", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_print_stack, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 #endif
 
-	tmp = tracefs_create_file("timerlat_period_us", 0640, top_dir,
+	tmp = tracefs_create_file("timerlat_period_us", TRACE_MODE_WRITE, top_dir,
 				  &timerlat_period, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 4b320fe7df70..29f6e95439b6 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -384,7 +384,7 @@ static __init int init_trace_printk_function_export(void)
 	if (ret)
 		return 0;
 
-	trace_create_file("printk_formats", 0444, NULL,
+	trace_create_file("printk_formats", TRACE_MODE_READ, NULL,
 				    NULL, &ftrace_formats_fops);
 
 	return 0;
diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c
index b2edac1fe156..4d4b78c8ca25 100644
--- a/kernel/trace/trace_recursion_record.c
+++ b/kernel/trace/trace_recursion_record.c
@@ -226,8 +226,8 @@ __init static int create_recursed_functions(void)
 {
 	struct dentry *dentry;
 
-	dentry = trace_create_file("recursed_functions", 0644, NULL, NULL,
-				   &recursed_functions_fops);
+	dentry = trace_create_file("recursed_functions", TRACE_MODE_WRITE,
+				   NULL, NULL, &recursed_functions_fops);
 	if (!dentry)
 		pr_warn("WARNING: Failed to create recursed_functions\n");
 	return 0;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 63c285042051..5a48dba912ea 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -559,14 +559,14 @@ static __init int stack_trace_init(void)
 	if (ret)
 		return 0;
 
-	trace_create_file("stack_max_size", 0644, NULL,
+	trace_create_file("stack_max_size", TRACE_MODE_WRITE, NULL,
 			&stack_trace_max_size, &stack_max_size_fops);
 
-	trace_create_file("stack_trace", 0444, NULL,
+	trace_create_file("stack_trace", TRACE_MODE_READ, NULL,
 			NULL, &stack_trace_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	trace_create_file("stack_trace_filter", 0644, NULL,
+	trace_create_file("stack_trace_filter", TRACE_MODE_WRITE, NULL,
 			  &trace_ops, &stack_trace_filter_fops);
 #endif
 
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 8d141c3825a9..bb247beec447 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -297,9 +297,9 @@ static int init_stat_file(struct stat_session *session)
 	if (!stat_dir && (ret = tracing_stat_init()))
 		return ret;
 
-	session->file = tracefs_create_file(session->ts->name, 0644,
-					    stat_dir,
-					    session, &tracing_stat_fops);
+	session->file = tracefs_create_file(session->ts->name, TRACE_MODE_WRITE,
+					    stat_dir, session,
+					    &tracing_stat_fops);
 	if (!session->file)
 		return -ENOMEM;
 	return 0;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 225ce569bf8f..0a5c0db3137e 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1655,10 +1655,10 @@ static __init int init_uprobe_trace(void)
 	if (ret)
 		return 0;
 
-	trace_create_file("uprobe_events", 0644, NULL,
+	trace_create_file("uprobe_events", TRACE_MODE_WRITE, NULL,
 				    NULL, &uprobe_events_ops);
 	/* Profile interface */
-	trace_create_file("uprobe_profile", 0444, NULL,
+	trace_create_file("uprobe_profile", TRACE_MODE_READ, NULL,
 				    NULL, &uprobe_profile_ops);
 	return 0;
 }
-- 
2.33.0

[for-next][PATCH 04/40] ftrace: Cleanup ftrace_dyn_arch_init()

[Steven Rostedt]

From: Weizhao Ouyang <o451686892@gmail.com>

Most of ARCHs use empty ftrace_dyn_arch_init(), introduce a weak common
ftrace_dyn_arch_init() to cleanup them.

Link: https://lkml.kernel.org/r/20210909090216.1955240-1-o451686892@gmail.com

Acked-by: Heiko Carstens <hca@linux.ibm.com> (s390)
Acked-by: Helge Deller <deller@gmx.de> (parisc)
Signed-off-by: Weizhao Ouyang <o451686892@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/arm/kernel/ftrace.c        | 5 -----
 arch/arm64/kernel/ftrace.c      | 5 -----
 arch/csky/kernel/ftrace.c       | 5 -----
 arch/ia64/kernel/ftrace.c       | 6 ------
 arch/microblaze/kernel/ftrace.c | 5 -----
 arch/nds32/kernel/ftrace.c      | 5 -----
 arch/parisc/kernel/ftrace.c     | 5 -----
 arch/riscv/kernel/ftrace.c      | 5 -----
 arch/s390/kernel/ftrace.c       | 5 -----
 arch/sh/kernel/ftrace.c         | 5 -----
 arch/sparc/kernel/ftrace.c      | 5 -----
 arch/x86/kernel/ftrace.c        | 5 -----
 kernel/trace/ftrace.c           | 5 +++++
 13 files changed, 5 insertions(+), 61 deletions(-)

diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 3c83b5d29697..a006585e1c09 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -193,11 +193,6 @@ int ftrace_make_nop(struct module *mod,
 
 	return ret;
 }
-
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 7f467bd9db7a..fc62dfe73f93 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -236,11 +236,6 @@ void arch_ftrace_update_code(int command)
 	command |= FTRACE_MAY_SLEEP;
 	ftrace_modify_all_code(command);
 }
-
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c
index b4a7ec1517ff..50bfcf129078 100644
--- a/arch/csky/kernel/ftrace.c
+++ b/arch/csky/kernel/ftrace.c
@@ -133,11 +133,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 				(unsigned long)func, true, true);
 	return ret;
 }
-
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c
index b2ab2d58fb30..d6360fd404ab 100644
--- a/arch/ia64/kernel/ftrace.c
+++ b/arch/ia64/kernel/ftrace.c
@@ -194,9 +194,3 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	flush_icache_range(addr, addr + 16);
 	return 0;
 }
-
-/* run from kstop_machine */
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c
index 224eea40e1ee..188749d62709 100644
--- a/arch/microblaze/kernel/ftrace.c
+++ b/arch/microblaze/kernel/ftrace.c
@@ -163,11 +163,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ret;
 }
 
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
-
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c
index 0e23e3a8df6b..f0ef4842d191 100644
--- a/arch/nds32/kernel/ftrace.c
+++ b/arch/nds32/kernel/ftrace.c
@@ -84,11 +84,6 @@ void _ftrace_caller(unsigned long parent_ip)
 	/* restore all state needed by the compiler epilogue */
 }
 
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
-
 static unsigned long gen_sethi_insn(unsigned long addr)
 {
 	unsigned long opcode = 0x46000000;
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 0a1e75af5382..01581f715737 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -94,11 +94,6 @@ int ftrace_disable_ftrace_graph_caller(void)
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	return 0;
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 7f1e5203de88..4716f4cdc038 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -154,11 +154,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 	return ret;
 }
-
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 1d94ffdf347b..5165bf344f95 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -262,11 +262,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return 0;
 }
 
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
-
 void arch_ftrace_update_code(int command)
 {
 	if (ftrace_shared_hotpatch_trampoline(NULL))
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 295c43315bbe..930001bb8c6a 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -252,11 +252,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	return ftrace_modify_code(rec->ip, old, new);
 }
-
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c
index 684b84ce397f..eaead3da8e03 100644
--- a/arch/sparc/kernel/ftrace.c
+++ b/arch/sparc/kernel/ftrace.c
@@ -82,11 +82,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	new = ftrace_call_replace(ip, (unsigned long)func);
 	return ftrace_modify_code(ip, old, new);
 }
-
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
 #endif
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1b3ce3b4a2a2..23d221a9a3cd 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -252,11 +252,6 @@ void arch_ftrace_update_code(int command)
 	ftrace_modify_all_code(command);
 }
 
-int __init ftrace_dyn_arch_init(void)
-{
-	return 0;
-}
-
 /* Currently only x86_64 supports dynamic trampolines */
 #ifdef CONFIG_X86_64
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0a0dbc2d411b..2c3e9760df7f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6847,6 +6847,11 @@ void __init ftrace_free_init_mem(void)
 	ftrace_free_mem(NULL, start, end);
 }
 
+int __init __weak ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+
 void __init ftrace_init(void)
 {
 	extern unsigned long __start_mcount_loc[];
-- 
2.33.0

[for-next][PATCH 05/40] bootconfig: Allocate xbc_data inside xbc_init()

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Allocate 'xbc_data' in the xbc_init() so that it does
not need to care about the ownership of the copied
data.

Link: https://lkml.kernel.org/r/163177339986.682366.898762699429769117.stgit@devnote2

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/bootconfig.h |  2 +-
 init/main.c                | 13 ++-----------
 lib/bootconfig.c           | 33 +++++++++++++++++++++------------
 tools/bootconfig/main.c    |  6 +++---
 4 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 537e1b991f11..62e09b788172 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -271,7 +271,7 @@ static inline int __init xbc_node_compose_key(struct xbc_node *node,
 }
 
 /* XBC node initializer */
-int __init xbc_init(char *buf, const char **emsg, int *epos);
+int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos);
 
 
 /* XBC cleanup data structures */
diff --git a/init/main.c b/init/main.c
index 81a79a77db46..d894989d86bc 100644
--- a/init/main.c
+++ b/init/main.c
@@ -409,7 +409,7 @@ static void __init setup_boot_config(void)
 	const char *msg;
 	int pos;
 	u32 size, csum;
-	char *data, *copy, *err;
+	char *data, *err;
 	int ret;
 
 	/* Cut out the bootconfig data even if we have no bootconfig option */
@@ -442,16 +442,7 @@ static void __init setup_boot_config(void)
 		return;
 	}
 
-	copy = memblock_alloc(size + 1, SMP_CACHE_BYTES);
-	if (!copy) {
-		pr_err("Failed to allocate memory for bootconfig\n");
-		return;
-	}
-
-	memcpy(copy, data, size);
-	copy[size] = '\0';
-
-	ret = xbc_init(copy, &msg, &pos);
+	ret = xbc_init(data, size, &msg, &pos);
 	if (ret < 0) {
 		if (pos < 0)
 			pr_err("Failed to init bootconfig: %s.\n", msg);
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 5ae248b29373..66b02fddfea8 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -789,6 +789,7 @@ static int __init xbc_verify_tree(void)
  */
 void __init xbc_destroy_all(void)
 {
+	memblock_free_ptr(xbc_data, xbc_data_size);
 	xbc_data = NULL;
 	xbc_data_size = 0;
 	xbc_node_num = 0;
@@ -799,19 +800,20 @@ void __init xbc_destroy_all(void)
 
 /**
  * xbc_init() - Parse given XBC file and build XBC internal tree
- * @buf: boot config text
+ * @data: The boot config text original data
+ * @size: The size of @data
  * @emsg: A pointer of const char * to store the error message
  * @epos: A pointer of int to store the error position
  *
- * This parses the boot config text in @buf. @buf must be a
- * null terminated string and smaller than XBC_DATA_MAX.
+ * This parses the boot config text in @data. @size must be smaller
+ * than XBC_DATA_MAX.
  * Return the number of stored nodes (>0) if succeeded, or -errno
  * if there is any error.
  * In error cases, @emsg will be updated with an error message and
  * @epos will be updated with the error position which is the byte offset
  * of @buf. If the error is not a parser error, @epos will be -1.
  */
-int __init xbc_init(char *buf, const char **emsg, int *epos)
+int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos)
 {
 	char *p, *q;
 	int ret, c;
@@ -824,28 +826,35 @@ int __init xbc_init(char *buf, const char **emsg, int *epos)
 			*emsg = "Bootconfig is already initialized";
 		return -EBUSY;
 	}
-
-	ret = strlen(buf);
-	if (ret > XBC_DATA_MAX - 1 || ret == 0) {
+	if (size > XBC_DATA_MAX || size == 0) {
 		if (emsg)
-			*emsg = ret ? "Config data is too big" :
+			*emsg = size ? "Config data is too big" :
 				"Config data is empty";
 		return -ERANGE;
 	}
 
+	xbc_data = memblock_alloc(size + 1, SMP_CACHE_BYTES);
+	if (!xbc_data) {
+		if (emsg)
+			*emsg = "Failed to allocate bootconfig data";
+		return -ENOMEM;
+	}
+	memcpy(xbc_data, data, size);
+	xbc_data[size] = '\0';
+	xbc_data_size = size + 1;
+
 	xbc_nodes = memblock_alloc(sizeof(struct xbc_node) * XBC_NODE_MAX,
 				   SMP_CACHE_BYTES);
 	if (!xbc_nodes) {
 		if (emsg)
 			*emsg = "Failed to allocate bootconfig nodes";
+		xbc_destroy_all();
 		return -ENOMEM;
 	}
 	memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX);
-	xbc_data = buf;
-	xbc_data_size = ret + 1;
-	last_parent = NULL;
 
-	p = buf;
+	last_parent = NULL;
+	p = xbc_data;
 	do {
 		q = strpbrk(p, "{}=+;:\n#");
 		if (!q) {
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index fd67496a947f..7269c9e35335 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -229,7 +229,7 @@ static int load_xbc_from_initrd(int fd, char **buf)
 		return -EINVAL;
 	}
 
-	ret = xbc_init(*buf, &msg, NULL);
+	ret = xbc_init(*buf, size, &msg, NULL);
 	/* Wrong data */
 	if (ret < 0) {
 		pr_err("parse error: %s.\n", msg);
@@ -269,7 +269,7 @@ static int init_xbc_with_error(char *buf, int len)
 	if (!copy)
 		return -ENOMEM;
 
-	ret = xbc_init(buf, &msg, &pos);
+	ret = xbc_init(buf, len, &msg, &pos);
 	if (ret < 0)
 		show_xbc_error(copy, msg, pos);
 	free(copy);
@@ -382,7 +382,7 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	memcpy(data, buf, size);
 
 	/* Check the data format */
-	ret = xbc_init(buf, &msg, &pos);
+	ret = xbc_init(buf, size, &msg, &pos);
 	if (ret < 0) {
 		show_xbc_error(data, msg, pos);
 		free(data);
-- 
2.33.0

[for-next][PATCH 06/40] bootconfig: Add xbc_get_info() for the node information

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Add xbc_get_info() API which allows user to get the
number of used xbc_nodes and the size of bootconfig
data. This is also useful for checking the bootconfig
is initialized or not.

Link: https://lkml.kernel.org/r/163177340877.682366.4360676589783197627.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/bootconfig.h |  2 ++
 init/main.c                |  1 +
 lib/bootconfig.c           | 21 +++++++++++++++++++++
 tools/bootconfig/main.c    |  1 +
 4 files changed, 25 insertions(+)

diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 62e09b788172..f955bb7eabbb 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -273,6 +273,8 @@ static inline int __init xbc_node_compose_key(struct xbc_node *node,
 /* XBC node initializer */
 int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos);
 
+/* XBC node and size information */
+int __init xbc_get_info(int *node_size, size_t *data_size);
 
 /* XBC cleanup data structures */
 void __init xbc_destroy_all(void);
diff --git a/init/main.c b/init/main.c
index d894989d86bc..afaed805de19 100644
--- a/init/main.c
+++ b/init/main.c
@@ -450,6 +450,7 @@ static void __init setup_boot_config(void)
 			pr_err("Failed to parse bootconfig: %s at %d.\n",
 				msg, pos);
 	} else {
+		xbc_get_info(&ret, NULL);
 		pr_info("Load bootconfig: %d bytes %d nodes\n", size, ret);
 		/* keys starting with "kernel." are passed via cmdline */
 		extra_command_line = xbc_make_cmdline("kernel");
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 66b02fddfea8..b088fe5c0001 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -34,6 +34,27 @@ static int xbc_err_pos __initdata;
 static int open_brace[XBC_DEPTH_MAX] __initdata;
 static int brace_index __initdata;
 
+/**
+ * xbc_get_info() - Get the information of loaded boot config
+ * node_size: A pointer to store the number of nodes.
+ * data_size: A pointer to store the size of bootconfig data.
+ *
+ * Get the number of used nodes in @node_size if it is not NULL,
+ * and the size of bootconfig data in @data_size if it is not NULL.
+ * Return 0 if the boot config is initialized, or return -ENODEV.
+ */
+int __init xbc_get_info(int *node_size, size_t *data_size)
+{
+	if (!xbc_data)
+		return -ENODEV;
+
+	if (node_size)
+		*node_size = xbc_node_num;
+	if (data_size)
+		*data_size = xbc_data_size;
+	return 0;
+}
+
 static int __init xbc_parse_error(const char *msg, const char *p)
 {
 	xbc_err_msg = msg;
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 7269c9e35335..4f2a8d884745 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -391,6 +391,7 @@ static int apply_xbc(const char *path, const char *xbc_path)
 		return ret;
 	}
 	printf("Apply %s to %s\n", xbc_path, path);
+	xbc_get_info(&ret, NULL);
 	printf("\tNumber of nodes: %d\n", ret);
 	printf("\tSize: %u bytes\n", (unsigned int)size);
 	printf("\tChecksum: %d\n", (unsigned int)csum);
-- 
2.33.0

[for-next][PATCH 07/40] tools/bootconfig: Run test script when build all

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Run the bootconfig test script when build all target
so that user can notice any issue when build it.

Link: https://lkml.kernel.org/r/163187295173.2366983.18295281097397499118.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/bootconfig/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bootconfig/Makefile b/tools/bootconfig/Makefile
index da5975775337..f1eec3ccbe18 100644
--- a/tools/bootconfig/Makefile
+++ b/tools/bootconfig/Makefile
@@ -15,7 +15,7 @@ CFLAGS = -Wall -g -I$(CURDIR)/include
 ALL_TARGETS := bootconfig
 ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
 
-all: $(ALL_PROGRAMS)
+all: $(ALL_PROGRAMS) test
 
 $(OUTPUT)bootconfig: main.c $(LIBSRC)
 	$(CC) $(filter %.c,$^) $(CFLAGS) -o $@
-- 
2.33.0

[for-next][PATCH 08/40] bootconfig: Rename xbc_destroy_all() to xbc_exit()

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Avoid using this noisy name and use more calm one.
This is just a name change. No functional change.

Link: https://lkml.kernel.org/r/163187295918.2366983.5231840238429996027.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/bootconfig.h | 2 +-
 init/main.c                | 2 +-
 lib/bootconfig.c           | 8 ++++----
 tools/bootconfig/main.c    | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index f955bb7eabbb..7eb7a7f8ade7 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -277,7 +277,7 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos);
 int __init xbc_get_info(int *node_size, size_t *data_size);
 
 /* XBC cleanup data structures */
-void __init xbc_destroy_all(void);
+void __init xbc_exit(void);
 
 /* Debug dump functions */
 void __init xbc_debug_dump(void);
diff --git a/init/main.c b/init/main.c
index afaed805de19..f1428234e1e4 100644
--- a/init/main.c
+++ b/init/main.c
@@ -462,7 +462,7 @@ static void __init setup_boot_config(void)
 
 static void __init exit_boot_config(void)
 {
-	xbc_destroy_all();
+	xbc_exit();
 }
 
 #else	/* !CONFIG_BOOT_CONFIG */
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index b088fe5c0001..a3ce5a0c3ca4 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -802,13 +802,13 @@ static int __init xbc_verify_tree(void)
 }
 
 /**
- * xbc_destroy_all() - Clean up all parsed bootconfig
+ * xbc_exit() - Clean up all parsed bootconfig
  *
  * This clears all data structures of parsed bootconfig on memory.
  * If you need to reuse xbc_init() with new boot config, you can
  * use this.
  */
-void __init xbc_destroy_all(void)
+void __init xbc_exit(void)
 {
 	memblock_free_ptr(xbc_data, xbc_data_size);
 	xbc_data = NULL;
@@ -869,7 +869,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos)
 	if (!xbc_nodes) {
 		if (emsg)
 			*emsg = "Failed to allocate bootconfig nodes";
-		xbc_destroy_all();
+		xbc_exit();
 		return -ENOMEM;
 	}
 	memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX);
@@ -925,7 +925,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos)
 			*epos = xbc_err_pos;
 		if (emsg)
 			*emsg = xbc_err_msg;
-		xbc_destroy_all();
+		xbc_exit();
 	} else
 		ret = xbc_node_num;
 
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 4f2a8d884745..4252c23bd35d 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -397,7 +397,7 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	printf("\tChecksum: %d\n", (unsigned int)csum);
 
 	/* TODO: Check the options by schema */
-	xbc_destroy_all();
+	xbc_exit();
 	free(buf);
 
 	/* Remove old boot config if exists */
-- 
2.33.0

[for-next][PATCH 09/40] bootconfig: Split parse-tree part from xbc_init

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Split bootconfig data parser to build tree code from
xbc_init(). This is an internal cosmetic change.

Link: https://lkml.kernel.org/r/163187296647.2366983.15590065167920474865.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 lib/bootconfig.c | 99 ++++++++++++++++++++++++++----------------------
 1 file changed, 54 insertions(+), 45 deletions(-)

diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index a3ce5a0c3ca4..b7e5a32b30d3 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -801,6 +801,58 @@ static int __init xbc_verify_tree(void)
 	return 0;
 }
 
+/* Need to setup xbc_data and xbc_nodes before call this. */
+static int __init xbc_parse_tree(void)
+{
+	char *p, *q;
+	int ret, c;
+
+	last_parent = NULL;
+	p = xbc_data;
+	do {
+		q = strpbrk(p, "{}=+;:\n#");
+		if (!q) {
+			p = skip_spaces(p);
+			if (*p != '\0')
+				ret = xbc_parse_error("No delimiter", p);
+			break;
+		}
+
+		c = *q;
+		*q++ = '\0';
+		switch (c) {
+		case ':':
+		case '+':
+			if (*q++ != '=') {
+				ret = xbc_parse_error(c == '+' ?
+						"Wrong '+' operator" :
+						"Wrong ':' operator",
+							q - 2);
+				break;
+			}
+			fallthrough;
+		case '=':
+			ret = xbc_parse_kv(&p, q, c);
+			break;
+		case '{':
+			ret = xbc_open_brace(&p, q);
+			break;
+		case '#':
+			q = skip_comment(q);
+			fallthrough;
+		case ';':
+		case '\n':
+			ret = xbc_parse_key(&p, q);
+			break;
+		case '}':
+			ret = xbc_close_brace(&p, q);
+			break;
+		}
+	} while (!ret);
+
+	return ret;
+}
+
 /**
  * xbc_exit() - Clean up all parsed bootconfig
  *
@@ -836,8 +888,7 @@ void __init xbc_exit(void)
  */
 int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos)
 {
-	char *p, *q;
-	int ret, c;
+	int ret;
 
 	if (epos)
 		*epos = -1;
@@ -874,49 +925,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos)
 	}
 	memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX);
 
-	last_parent = NULL;
-	p = xbc_data;
-	do {
-		q = strpbrk(p, "{}=+;:\n#");
-		if (!q) {
-			p = skip_spaces(p);
-			if (*p != '\0')
-				ret = xbc_parse_error("No delimiter", p);
-			break;
-		}
-
-		c = *q;
-		*q++ = '\0';
-		switch (c) {
-		case ':':
-		case '+':
-			if (*q++ != '=') {
-				ret = xbc_parse_error(c == '+' ?
-						"Wrong '+' operator" :
-						"Wrong ':' operator",
-							q - 2);
-				break;
-			}
-			fallthrough;
-		case '=':
-			ret = xbc_parse_kv(&p, q, c);
-			break;
-		case '{':
-			ret = xbc_open_brace(&p, q);
-			break;
-		case '#':
-			q = skip_comment(q);
-			fallthrough;
-		case ';':
-		case '\n':
-			ret = xbc_parse_key(&p, q);
-			break;
-		case '}':
-			ret = xbc_close_brace(&p, q);
-			break;
-		}
-	} while (!ret);
-
+	ret = xbc_parse_tree();
 	if (!ret)
 		ret = xbc_verify_tree();
 
-- 
2.33.0

[for-next][PATCH 10/40] bootconfig: Remove unused debug function

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Remove unused xbc_debug_dump() from bootconfig for clean up
the code.

Link: https://lkml.kernel.org/r/163187297371.2366983.12943349701785875450.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/bootconfig.h |  3 ---
 lib/bootconfig.c           | 21 ---------------------
 2 files changed, 24 deletions(-)

diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 7eb7a7f8ade7..85cdfd381877 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -279,7 +279,4 @@ int __init xbc_get_info(int *node_size, size_t *data_size);
 /* XBC cleanup data structures */
 void __init xbc_exit(void);
 
-/* Debug dump functions */
-void __init xbc_debug_dump(void);
-
 #endif
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index b7e5a32b30d3..953789171858 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -4,15 +4,12 @@
  * Masami Hiramatsu <mhiramat@kernel.org>
  */
 
-#define pr_fmt(fmt)    "bootconfig: " fmt
-
 #include <linux/bootconfig.h>
 #include <linux/bug.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/memblock.h>
-#include <linux/printk.h>
 #include <linux/string.h>
 
 /*
@@ -940,21 +937,3 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos)
 
 	return ret;
 }
-
-/**
- * xbc_debug_dump() - Dump current XBC node list
- *
- * Dump the current XBC node list on printk buffer for debug.
- */
-void __init xbc_debug_dump(void)
-{
-	int i;
-
-	for (i = 0; i < xbc_node_num; i++) {
-		pr_debug("[%d] %s (%s) .next=%d, .child=%d .parent=%d\n", i,
-			xbc_node_get_data(xbc_nodes + i),
-			xbc_node_is_value(xbc_nodes + i) ? "value" : "key",
-			xbc_nodes[i].next, xbc_nodes[i].child,
-			xbc_nodes[i].parent);
-	}
-}
-- 
2.33.0

[for-next][PATCH 11/40] tools/bootconfig: Print all error message in stderr

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Print all error message in stderr. This also removes
unneeded tools/bootconfig/include/linux/printk.h.

Link: https://lkml.kernel.org/r/163187298106.2366983.15210300267326257397.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/bootconfig/include/linux/kernel.h |  2 --
 tools/bootconfig/include/linux/printk.h | 14 --------------
 tools/bootconfig/main.c                 |  2 ++
 3 files changed, 2 insertions(+), 16 deletions(-)
 delete mode 100644 tools/bootconfig/include/linux/printk.h

diff --git a/tools/bootconfig/include/linux/kernel.h b/tools/bootconfig/include/linux/kernel.h
index 2d93320aa374..c4854b8e7023 100644
--- a/tools/bootconfig/include/linux/kernel.h
+++ b/tools/bootconfig/include/linux/kernel.h
@@ -5,8 +5,6 @@
 #include <stdlib.h>
 #include <stdbool.h>
 
-#include <linux/printk.h>
-
 typedef unsigned short u16;
 typedef unsigned int   u32;
 
diff --git a/tools/bootconfig/include/linux/printk.h b/tools/bootconfig/include/linux/printk.h
deleted file mode 100644
index 036e667596eb..000000000000
--- a/tools/bootconfig/include/linux/printk.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _SKC_LINUX_PRINTK_H
-#define _SKC_LINUX_PRINTK_H
-
-#include <stdio.h>
-
-#define printk(fmt, ...) printf(fmt, ##__VA_ARGS__)
-
-#define pr_err printk
-#define pr_warn	printk
-#define pr_info	printk
-#define pr_debug printk
-
-#endif
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 4252c23bd35d..adc6c6e73fa9 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -15,6 +15,8 @@
 #include <linux/kernel.h>
 #include <linux/bootconfig.h>
 
+#define pr_err(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__)
+
 static int xbc_show_value(struct xbc_node *node, bool semicolon)
 {
 	const char *val, *eol;
-- 
2.33.0

[for-next][PATCH 12/40] bootconfig: Replace u16 and u32 with uint16_t and uint32_t

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Replace u16 and u32 with uint16_t and uint32_t so
that the tools/bootconfig only needs <stdint.h>.

Link: https://lkml.kernel.org/r/163187298835.2366983.9838262576854319669.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/bootconfig.h              | 12 ++++++------
 lib/bootconfig.c                        | 16 ++++++++--------
 tools/bootconfig/include/linux/kernel.h |  4 +---
 tools/bootconfig/main.c                 | 20 ++++++++++----------
 4 files changed, 25 insertions(+), 27 deletions(-)

diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 85cdfd381877..a6f8dc51f168 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -25,10 +25,10 @@
  * The checksum will be used with the BOOTCONFIG_MAGIC and the size for
  * embedding the bootconfig in the initrd image.
  */
-static inline __init u32 xbc_calc_checksum(void *data, u32 size)
+static inline __init uint32_t xbc_calc_checksum(void *data, uint32_t size)
 {
 	unsigned char *p = data;
-	u32 ret = 0;
+	uint32_t ret = 0;
 
 	while (size--)
 		ret += *p++;
@@ -38,10 +38,10 @@ static inline __init u32 xbc_calc_checksum(void *data, u32 size)
 
 /* XBC tree node */
 struct xbc_node {
-	u16 next;
-	u16 child;
-	u16 parent;
-	u16 data;
+	uint16_t next;
+	uint16_t child;
+	uint16_t parent;
+	uint16_t data;
 } __attribute__ ((__packed__));
 
 #define XBC_KEY		0
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 953789171858..a2f5f582181d 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -244,7 +244,7 @@ int __init xbc_node_compose_key_after(struct xbc_node *root,
 				      struct xbc_node *node,
 				      char *buf, size_t size)
 {
-	u16 keys[XBC_DEPTH_MAX];
+	uint16_t keys[XBC_DEPTH_MAX];
 	int depth = 0, ret = 0, total = 0;
 
 	if (!node || node == root)
@@ -359,21 +359,21 @@ const char * __init xbc_node_find_next_key_value(struct xbc_node *root,
 
 /* XBC parse and tree build */
 
-static int __init xbc_init_node(struct xbc_node *node, char *data, u32 flag)
+static int __init xbc_init_node(struct xbc_node *node, char *data, uint32_t flag)
 {
 	unsigned long offset = data - xbc_data;
 
 	if (WARN_ON(offset >= XBC_DATA_MAX))
 		return -EINVAL;
 
-	node->data = (u16)offset | flag;
+	node->data = (uint16_t)offset | flag;
 	node->child = 0;
 	node->next = 0;
 
 	return 0;
 }
 
-static struct xbc_node * __init xbc_add_node(char *data, u32 flag)
+static struct xbc_node * __init xbc_add_node(char *data, uint32_t flag)
 {
 	struct xbc_node *node;
 
@@ -403,7 +403,7 @@ static inline __init struct xbc_node *xbc_last_child(struct xbc_node *node)
 	return node;
 }
 
-static struct xbc_node * __init __xbc_add_sibling(char *data, u32 flag, bool head)
+static struct xbc_node * __init __xbc_add_sibling(char *data, uint32_t flag, bool head)
 {
 	struct xbc_node *sib, *node = xbc_add_node(data, flag);
 
@@ -430,17 +430,17 @@ static struct xbc_node * __init __xbc_add_sibling(char *data, u32 flag, bool hea
 	return node;
 }
 
-static inline struct xbc_node * __init xbc_add_sibling(char *data, u32 flag)
+static inline struct xbc_node * __init xbc_add_sibling(char *data, uint32_t flag)
 {
 	return __xbc_add_sibling(data, flag, false);
 }
 
-static inline struct xbc_node * __init xbc_add_head_sibling(char *data, u32 flag)
+static inline struct xbc_node * __init xbc_add_head_sibling(char *data, uint32_t flag)
 {
 	return __xbc_add_sibling(data, flag, true);
 }
 
-static inline __init struct xbc_node *xbc_add_child(char *data, u32 flag)
+static inline __init struct xbc_node *xbc_add_child(char *data, uint32_t flag)
 {
 	struct xbc_node *node = xbc_add_sibling(data, flag);
 
diff --git a/tools/bootconfig/include/linux/kernel.h b/tools/bootconfig/include/linux/kernel.h
index c4854b8e7023..39f306c18dd0 100644
--- a/tools/bootconfig/include/linux/kernel.h
+++ b/tools/bootconfig/include/linux/kernel.h
@@ -3,11 +3,9 @@
 #define _SKC_LINUX_KERNEL_H
 
 #include <stdlib.h>
+#include <stdint.h>
 #include <stdbool.h>
 
-typedef unsigned short u16;
-typedef unsigned int   u32;
-
 #define unlikely(cond)	(cond)
 
 #define __init
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index adc6c6e73fa9..fb7c9fb953d7 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -178,7 +178,7 @@ static int load_xbc_from_initrd(int fd, char **buf)
 {
 	struct stat stat;
 	int ret;
-	u32 size = 0, csum = 0, rcsum;
+	uint32_t size = 0, csum = 0, rcsum;
 	char magic[BOOTCONFIG_MAGIC_LEN];
 	const char *msg;
 
@@ -202,11 +202,11 @@ static int load_xbc_from_initrd(int fd, char **buf)
 	if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0)
 		return pr_errno("Failed to lseek for size", -errno);
 
-	if (read(fd, &size, sizeof(u32)) < 0)
+	if (read(fd, &size, sizeof(uint32_t)) < 0)
 		return pr_errno("Failed to read size", -errno);
 	size = le32toh(size);
 
-	if (read(fd, &csum, sizeof(u32)) < 0)
+	if (read(fd, &csum, sizeof(uint32_t)) < 0)
 		return pr_errno("Failed to read checksum", -errno);
 	csum = le32toh(csum);
 
@@ -364,7 +364,7 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	size_t total_size;
 	struct stat stat;
 	const char *msg;
-	u32 size, csum;
+	uint32_t size, csum;
 	int pos, pad;
 	int ret, fd;
 
@@ -378,7 +378,7 @@ static int apply_xbc(const char *path, const char *xbc_path)
 
 	/* Backup the bootconfig data */
 	data = calloc(size + BOOTCONFIG_ALIGN +
-		      sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1);
+		      sizeof(uint32_t) + sizeof(uint32_t) + BOOTCONFIG_MAGIC_LEN, 1);
 	if (!data)
 		return -ENOMEM;
 	memcpy(data, buf, size);
@@ -426,17 +426,17 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	}
 
 	/* To align up the total size to BOOTCONFIG_ALIGN, get padding size */
-	total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN;
+	total_size = stat.st_size + size + sizeof(uint32_t) * 2 + BOOTCONFIG_MAGIC_LEN;
 	pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size;
 	size += pad;
 
 	/* Add a footer */
 	p = data + size;
-	*(u32 *)p = htole32(size);
-	p += sizeof(u32);
+	*(uint32_t *)p = htole32(size);
+	p += sizeof(uint32_t);
 
-	*(u32 *)p = htole32(csum);
-	p += sizeof(u32);
+	*(uint32_t *)p = htole32(csum);
+	p += sizeof(uint32_t);
 
 	memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
 	p += BOOTCONFIG_MAGIC_LEN;
-- 
2.33.0

[for-next][PATCH 13/40] bootconfig: Cleanup dummy headers in tools/bootconfig

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Cleanup dummy headers in tools/bootconfig/include except
for tools/bootconfig/include/linux/bootconfig.h.
For this change, I use __KERNEL__ macro to split kernel
header #include and introduce xbc_alloc_mem() and
xbc_free_mem().

Link: https://lkml.kernel.org/r/163187299574.2366983.18371329724128746091.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/bootconfig.h                  | 10 +++++
 lib/bootconfig.c                            | 43 +++++++++++++++++---
 tools/bootconfig/Makefile                   |  2 +-
 tools/bootconfig/include/linux/bootconfig.h | 45 ++++++++++++++++++++-
 tools/bootconfig/include/linux/bug.h        | 12 ------
 tools/bootconfig/include/linux/ctype.h      |  7 ----
 tools/bootconfig/include/linux/errno.h      |  7 ----
 tools/bootconfig/include/linux/kernel.h     | 14 -------
 tools/bootconfig/include/linux/memblock.h   | 11 -----
 tools/bootconfig/include/linux/string.h     | 32 ---------------
 tools/bootconfig/main.c                     |  1 -
 11 files changed, 93 insertions(+), 91 deletions(-)
 delete mode 100644 tools/bootconfig/include/linux/bug.h
 delete mode 100644 tools/bootconfig/include/linux/ctype.h
 delete mode 100644 tools/bootconfig/include/linux/errno.h
 delete mode 100644 tools/bootconfig/include/linux/kernel.h
 delete mode 100644 tools/bootconfig/include/linux/memblock.h
 delete mode 100644 tools/bootconfig/include/linux/string.h

diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index a6f8dc51f168..a4665c7ab07c 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -7,8 +7,18 @@
  * Author: Masami Hiramatsu <mhiramat@kernel.org>
  */
 
+#ifdef __KERNEL__
 #include <linux/kernel.h>
 #include <linux/types.h>
+#else /* !__KERNEL__ */
+/*
+ * NOTE: This is only for tools/bootconfig, because tools/bootconfig will
+ * run the parser sanity test.
+ * This does NOT mean linux/bootconfig.h is available in the user space.
+ * However, if you change this file, please make sure the tools/bootconfig
+ * has no issue on building and running.
+ */
+#endif
 
 #define BOOTCONFIG_MAGIC	"#BOOTCONFIG\n"
 #define BOOTCONFIG_MAGIC_LEN	12
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index a2f5f582181d..a056ae137750 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -4,6 +4,7 @@
  * Masami Hiramatsu <mhiramat@kernel.org>
  */
 
+#ifdef __KERNEL__
 #include <linux/bootconfig.h>
 #include <linux/bug.h>
 #include <linux/ctype.h>
@@ -11,6 +12,16 @@
 #include <linux/kernel.h>
 #include <linux/memblock.h>
 #include <linux/string.h>
+#else /* !__KERNEL__ */
+/*
+ * NOTE: This is only for tools/bootconfig, because tools/bootconfig will
+ * run the parser sanity test.
+ * This does NOT mean lib/bootconfig.c is available in the user space.
+ * However, if you change this file, please make sure the tools/bootconfig
+ * has no issue on building and running.
+ */
+#include <linux/bootconfig.h>
+#endif
 
 /*
  * Extra Boot Config (XBC) is given as tree-structured ascii text of
@@ -31,6 +42,29 @@ static int xbc_err_pos __initdata;
 static int open_brace[XBC_DEPTH_MAX] __initdata;
 static int brace_index __initdata;
 
+#ifdef __KERNEL__
+static inline void *xbc_alloc_mem(size_t size)
+{
+	return memblock_alloc(size, SMP_CACHE_BYTES);
+}
+
+static inline void xbc_free_mem(void *addr, size_t size)
+{
+	memblock_free_ptr(addr, size);
+}
+
+#else /* !__KERNEL__ */
+
+static inline void *xbc_alloc_mem(size_t size)
+{
+	return malloc(size);
+}
+
+static inline void xbc_free_mem(void *addr, size_t size)
+{
+	free(addr);
+}
+#endif
 /**
  * xbc_get_info() - Get the information of loaded boot config
  * node_size: A pointer to store the number of nodes.
@@ -859,11 +893,11 @@ static int __init xbc_parse_tree(void)
  */
 void __init xbc_exit(void)
 {
-	memblock_free_ptr(xbc_data, xbc_data_size);
+	xbc_free_mem(xbc_data, xbc_data_size);
 	xbc_data = NULL;
 	xbc_data_size = 0;
 	xbc_node_num = 0;
-	memblock_free_ptr(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX);
+	xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX);
 	xbc_nodes = NULL;
 	brace_index = 0;
 }
@@ -902,7 +936,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos)
 		return -ERANGE;
 	}
 
-	xbc_data = memblock_alloc(size + 1, SMP_CACHE_BYTES);
+	xbc_data = xbc_alloc_mem(size + 1);
 	if (!xbc_data) {
 		if (emsg)
 			*emsg = "Failed to allocate bootconfig data";
@@ -912,8 +946,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos)
 	xbc_data[size] = '\0';
 	xbc_data_size = size + 1;
 
-	xbc_nodes = memblock_alloc(sizeof(struct xbc_node) * XBC_NODE_MAX,
-				   SMP_CACHE_BYTES);
+	xbc_nodes = xbc_alloc_mem(sizeof(struct xbc_node) * XBC_NODE_MAX);
 	if (!xbc_nodes) {
 		if (emsg)
 			*emsg = "Failed to allocate bootconfig nodes";
diff --git a/tools/bootconfig/Makefile b/tools/bootconfig/Makefile
index f1eec3ccbe18..566c3e0ee561 100644
--- a/tools/bootconfig/Makefile
+++ b/tools/bootconfig/Makefile
@@ -17,7 +17,7 @@ ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
 
 all: $(ALL_PROGRAMS) test
 
-$(OUTPUT)bootconfig: main.c $(LIBSRC)
+$(OUTPUT)bootconfig: main.c include/linux/bootconfig.h $(LIBSRC)
 	$(CC) $(filter %.c,$^) $(CFLAGS) -o $@
 
 test: $(ALL_PROGRAMS) test-bootconfig.sh
diff --git a/tools/bootconfig/include/linux/bootconfig.h b/tools/bootconfig/include/linux/bootconfig.h
index de7f30f99af3..6784296a0692 100644
--- a/tools/bootconfig/include/linux/bootconfig.h
+++ b/tools/bootconfig/include/linux/bootconfig.h
@@ -2,10 +2,53 @@
 #ifndef _BOOTCONFIG_LINUX_BOOTCONFIG_H
 #define _BOOTCONFIG_LINUX_BOOTCONFIG_H
 
-#include "../../../../include/linux/bootconfig.h"
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <ctype.h>
+#include <errno.h>
+#include <string.h>
+
 
 #ifndef fallthrough
 # define fallthrough
 #endif
 
+#define WARN_ON(cond)	\
+	((cond) ? printf("Internal warning(%s:%d, %s): %s\n",	\
+			__FILE__, __LINE__, __func__, #cond) : 0)
+
+#define unlikely(cond)	(cond)
+
+/* Copied from lib/string.c */
+static inline char *skip_spaces(const char *str)
+{
+	while (isspace(*str))
+		++str;
+	return (char *)str;
+}
+
+static inline char *strim(char *s)
+{
+	size_t size;
+	char *end;
+
+	size = strlen(s);
+	if (!size)
+		return s;
+
+	end = s + size - 1;
+	while (end >= s && isspace(*end))
+		end--;
+	*(end + 1) = '\0';
+
+	return skip_spaces(s);
+}
+
+#define __init
+#define __initdata
+
+#include "../../../../include/linux/bootconfig.h"
+
 #endif
diff --git a/tools/bootconfig/include/linux/bug.h b/tools/bootconfig/include/linux/bug.h
deleted file mode 100644
index 7b65a389c0dd..000000000000
--- a/tools/bootconfig/include/linux/bug.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _SKC_LINUX_BUG_H
-#define _SKC_LINUX_BUG_H
-
-#include <stdio.h>
-#include <stdlib.h>
-
-#define WARN_ON(cond)	\
-	((cond) ? printf("Internal warning(%s:%d, %s): %s\n",	\
-			__FILE__, __LINE__, __func__, #cond) : 0)
-
-#endif
diff --git a/tools/bootconfig/include/linux/ctype.h b/tools/bootconfig/include/linux/ctype.h
deleted file mode 100644
index c56ecc136448..000000000000
--- a/tools/bootconfig/include/linux/ctype.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _SKC_LINUX_CTYPE_H
-#define _SKC_LINUX_CTYPE_H
-
-#include <ctype.h>
-
-#endif
diff --git a/tools/bootconfig/include/linux/errno.h b/tools/bootconfig/include/linux/errno.h
deleted file mode 100644
index 5d9f91ec2fda..000000000000
--- a/tools/bootconfig/include/linux/errno.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _SKC_LINUX_ERRNO_H
-#define _SKC_LINUX_ERRNO_H
-
-#include <asm/errno.h>
-
-#endif
diff --git a/tools/bootconfig/include/linux/kernel.h b/tools/bootconfig/include/linux/kernel.h
deleted file mode 100644
index 39f306c18dd0..000000000000
--- a/tools/bootconfig/include/linux/kernel.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _SKC_LINUX_KERNEL_H
-#define _SKC_LINUX_KERNEL_H
-
-#include <stdlib.h>
-#include <stdint.h>
-#include <stdbool.h>
-
-#define unlikely(cond)	(cond)
-
-#define __init
-#define __initdata
-
-#endif
diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h
deleted file mode 100644
index f2e506f7d57f..000000000000
--- a/tools/bootconfig/include/linux/memblock.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XBC_LINUX_MEMBLOCK_H
-#define _XBC_LINUX_MEMBLOCK_H
-
-#include <stdlib.h>
-
-#define SMP_CACHE_BYTES	0
-#define memblock_alloc(size, align)	malloc(size)
-#define memblock_free_ptr(paddr, size)	free(paddr)
-
-#endif
diff --git a/tools/bootconfig/include/linux/string.h b/tools/bootconfig/include/linux/string.h
deleted file mode 100644
index 8267af75153a..000000000000
--- a/tools/bootconfig/include/linux/string.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _SKC_LINUX_STRING_H
-#define _SKC_LINUX_STRING_H
-
-#include <string.h>
-
-/* Copied from lib/string.c */
-static inline char *skip_spaces(const char *str)
-{
-	while (isspace(*str))
-		++str;
-	return (char *)str;
-}
-
-static inline char *strim(char *s)
-{
-	size_t size;
-	char *end;
-
-	size = strlen(s);
-	if (!size)
-		return s;
-
-	end = s + size - 1;
-	while (end >= s && isspace(*end))
-		end--;
-	*(end + 1) = '\0';
-
-	return skip_spaces(s);
-}
-
-#endif
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index fb7c9fb953d7..156b62a163c5 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -12,7 +12,6 @@
 #include <errno.h>
 #include <endian.h>
 
-#include <linux/kernel.h>
 #include <linux/bootconfig.h>
 
 #define pr_err(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__)
-- 
2.33.0

[for-next][PATCH 14/40] ftrace: Add unit test for removing trace function

[Steven Rostedt]

From: Carles Pey <carles.pey@gmail.com>

A self test is provided for the trace function removal functionality.

Link: https://lkml.kernel.org/r/20210918153043.318016-2-carles.pey@gmail.com

Signed-off-by: Carles Pey <carles.pey@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_selftest.c | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index adf7ef194005..875b4f1a0476 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -287,6 +287,40 @@ static int trace_selftest_ops(struct trace_array *tr, int cnt)
 	if (trace_selftest_test_probe3_cnt != 4)
 		goto out_free;
 
+	/* Remove trace function from probe 3 */
+	func1_name = "!" __stringify(DYN_FTRACE_TEST_NAME);
+	len1 = strlen(func1_name);
+
+	ftrace_set_filter(&test_probe3, func1_name, len1, 0);
+
+	DYN_FTRACE_TEST_NAME();
+
+	print_counts();
+
+	if (trace_selftest_test_probe1_cnt != 3)
+		goto out_free;
+	if (trace_selftest_test_probe2_cnt != 2)
+		goto out_free;
+	if (trace_selftest_test_probe3_cnt != 4)
+		goto out_free;
+	if (cnt > 1) {
+		if (trace_selftest_test_global_cnt == 0)
+			goto out_free;
+	}
+	if (trace_selftest_test_dyn_cnt == 0)
+		goto out_free;
+
+	DYN_FTRACE_TEST_NAME2();
+
+	print_counts();
+
+	if (trace_selftest_test_probe1_cnt != 3)
+		goto out_free;
+	if (trace_selftest_test_probe2_cnt != 3)
+		goto out_free;
+	if (trace_selftest_test_probe3_cnt != 5)
+		goto out_free;
+
 	ret = 0;
  out_free:
 	unregister_ftrace_function(dyn_ops);
-- 
2.33.0

[for-next][PATCH 15/40] tracing: in_irq() cleanup

[Steven Rostedt]

From: Changbin Du <changbin.du@gmail.com>

Replace the obsolete and ambiguos macro in_irq() with new
macro in_hardirq().

Link: https://lkml.kernel.org/r/20210930000342.6016-1-changbin.du@gmail.com

Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Changbin Du <changbin.du@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.h                 | 2 +-
 kernel/trace/trace_functions_graph.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6c3808132b16..6b60ab9475ed 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -890,7 +890,7 @@ static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
 		 * is set, and called by an interrupt handler, we still
 		 * want to trace it.
 		 */
-		if (in_irq())
+		if (in_hardirq())
 			trace_recursion_set(TRACE_IRQ_BIT);
 		else
 			trace_recursion_clear(TRACE_IRQ_BIT);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6b5ff3ba4251..203204cadf92 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -120,7 +120,7 @@ static inline int ftrace_graph_ignore_irqs(void)
 	if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
 		return 0;
 
-	return in_irq();
+	return in_hardirq();
 }
 
 int trace_graph_entry(struct ftrace_graph_ent *trace)
-- 
2.33.0

[for-next][PATCH 16/40] tracing: Use linker magic instead of recasting ftrace_ops_list_func()

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

In an effort to enable -Wcast-function-type in the top-level Makefile to
support Control Flow Integrity builds, all function casts need to be
removed.

This means that ftrace_ops_list_func() can no longer be defined as
ftrace_ops_no_ops(). The reason for ftrace_ops_no_ops() is to use that when
an architecture calls ftrace_ops_list_func() with only two parameters
(called from assembly). And to make sure there's no C side-effects, those
archs call ftrace_ops_no_ops() which only has two parameters, as
ftrace_ops_list_func() has four parameters.

Instead of a typecast, use vmlinux.lds.h to define ftrace_ops_list_func() to
arch_ftrace_ops_list_func() that will define the proper set of parameters.

Link: https://lore.kernel.org/r/20200614070154.6039-1-oscar.carter@gmx.com
Link: https://lkml.kernel.org/r/20200617165616.52241bde@oasis.local.home
Link: https://lore.kernel.org/all/20211005053922.GA702049@embeddedor/

Requested-by: Oscar Carter <oscar.carter@gmx.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/asm-generic/vmlinux.lds.h | 10 ++++++++--
 include/linux/ftrace.h            | 12 ++++++++++--
 kernel/trace/ftrace.c             | 23 ++++++++++-------------
 3 files changed, 28 insertions(+), 17 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f2984af2b85b..8771c435f34b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -164,16 +164,22 @@
  * Need to also make ftrace_stub_graph point to ftrace_stub
  * so that the same stub location may have different protocols
  * and not mess up with C verifiers.
+ *
+ * ftrace_ops_list_func will be defined as arch_ftrace_ops_list_func
+ * as some archs will have a different prototype for that function
+ * but ftrace_ops_list_func() will have a single prototype.
  */
 #define MCOUNT_REC()	. = ALIGN(8);				\
 			__start_mcount_loc = .;			\
 			KEEP(*(__mcount_loc))			\
 			KEEP(*(__patchable_function_entries))	\
 			__stop_mcount_loc = .;			\
-			ftrace_stub_graph = ftrace_stub;
+			ftrace_stub_graph = ftrace_stub;	\
+			ftrace_ops_list_func = arch_ftrace_ops_list_func;
 #else
 # ifdef CONFIG_FUNCTION_TRACER
-#  define MCOUNT_REC()	ftrace_stub_graph = ftrace_stub;
+#  define MCOUNT_REC()	ftrace_stub_graph = ftrace_stub;	\
+			ftrace_ops_list_func = arch_ftrace_ops_list_func;
 # else
 #  define MCOUNT_REC()
 # endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 832e65f06754..12fcfa2d23ea 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -30,16 +30,26 @@
 #define ARCH_SUPPORTS_FTRACE_OPS 0
 #endif
 
+#ifdef CONFIG_FUNCTION_TRACER
+struct ftrace_ops;
+struct ftrace_regs;
 /*
  * If the arch's mcount caller does not support all of ftrace's
  * features, then it must call an indirect function that
  * does. Or at least does enough to prevent any unwelcome side effects.
+ *
+ * Also define the function prototype that these architectures use
+ * to call the ftrace_ops_list_func().
  */
 #if !ARCH_SUPPORTS_FTRACE_OPS
 # define FTRACE_FORCE_LIST_FUNC 1
+void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
 #else
 # define FTRACE_FORCE_LIST_FUNC 0
+void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+			       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #endif
+#endif /* CONFIG_FUNCTION_TRACER */
 
 /* Main tracing buffer and events set up */
 #ifdef CONFIG_TRACING
@@ -88,8 +98,6 @@ extern int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos);
 
-struct ftrace_ops;
-
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
 struct ftrace_regs {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2c3e9760df7f..8b5801881271 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -119,14 +119,9 @@ struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 struct ftrace_ops global_ops;
 
-#if ARCH_SUPPORTS_FTRACE_OPS
-static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op, struct ftrace_regs *fregs);
-#else
-/* See comment below, where ftrace_ops_list_func is defined */
-static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
-#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
-#endif
+/* Defined by vmlinux.lds.h see the commment above arch_ftrace_ops_list_func for details */
+void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+			  struct ftrace_ops *op, struct ftrace_regs *fregs);
 
 static inline void ftrace_ops_init(struct ftrace_ops *ops)
 {
@@ -7032,21 +7027,23 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
  * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved.
  * An architecture can pass partial regs with ftrace_ops and still
  * set the ARCH_SUPPORTS_FTRACE_OPS.
+ *
+ * In vmlinux.lds.h, ftrace_ops_list_func() is defined to be
+ * arch_ftrace_ops_list_func.
  */
 #if ARCH_SUPPORTS_FTRACE_OPS
-static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op, struct ftrace_regs *fregs)
+void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+			       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, fregs);
 }
-NOKPROBE_SYMBOL(ftrace_ops_list_func);
 #else
-static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
+void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
 }
-NOKPROBE_SYMBOL(ftrace_ops_no_ops);
 #endif
+NOKPROBE_SYMBOL(arch_ftrace_ops_list_func);
 
 /*
  * If there's only one function registered but it does not support
-- 
2.33.0

[for-next][PATCH 17/40] tracing/cfi: Fix cmp_entries_* functions signature mismatch

[Steven Rostedt]

From: Kalesh Singh <kaleshsingh@google.com>

If CONFIG_CFI_CLANG=y, attempting to read an event histogram will cause
the kernel to panic due to failed CFI check.

    1. echo 'hist:keys=common_pid' >> events/sched/sched_switch/trigger
    2. cat events/sched/sched_switch/hist
    3. kernel panics on attempting to read hist

This happens because the sort() function expects a generic
int (*)(const void *, const void *) pointer for the compare function.
To prevent this CFI failure, change tracing map cmp_entries_* function
signatures to match this.

Also, fix the build error reported by the kernel test robot [1].

[1] https://lore.kernel.org/r/202110141140.zzi4dRh4-lkp@intel.com/

Link: https://lkml.kernel.org/r/20211014045217.3265162-1-kaleshsingh@google.com

Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/tracing_map.c | 40 ++++++++++++++++++++++----------------
 1 file changed, 23 insertions(+), 17 deletions(-)

diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index d6bddb157ef2..39bb56d2dcbe 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -834,29 +834,35 @@ int tracing_map_init(struct tracing_map *map)
 	return err;
 }
 
-static int cmp_entries_dup(const struct tracing_map_sort_entry **a,
-			   const struct tracing_map_sort_entry **b)
+static int cmp_entries_dup(const void *A, const void *B)
 {
+	const struct tracing_map_sort_entry *a, *b;
 	int ret = 0;
 
-	if (memcmp((*a)->key, (*b)->key, (*a)->elt->map->key_size))
+	a = *(const struct tracing_map_sort_entry **)A;
+	b = *(const struct tracing_map_sort_entry **)B;
+
+	if (memcmp(a->key, b->key, a->elt->map->key_size))
 		ret = 1;
 
 	return ret;
 }
 
-static int cmp_entries_sum(const struct tracing_map_sort_entry **a,
-			   const struct tracing_map_sort_entry **b)
+static int cmp_entries_sum(const void *A, const void *B)
 {
 	const struct tracing_map_elt *elt_a, *elt_b;
+	const struct tracing_map_sort_entry *a, *b;
 	struct tracing_map_sort_key *sort_key;
 	struct tracing_map_field *field;
 	tracing_map_cmp_fn_t cmp_fn;
 	void *val_a, *val_b;
 	int ret = 0;
 
-	elt_a = (*a)->elt;
-	elt_b = (*b)->elt;
+	a = *(const struct tracing_map_sort_entry **)A;
+	b = *(const struct tracing_map_sort_entry **)B;
+
+	elt_a = a->elt;
+	elt_b = b->elt;
 
 	sort_key = &elt_a->map->sort_key;
 
@@ -873,18 +879,21 @@ static int cmp_entries_sum(const struct tracing_map_sort_entry **a,
 	return ret;
 }
 
-static int cmp_entries_key(const struct tracing_map_sort_entry **a,
-			   const struct tracing_map_sort_entry **b)
+static int cmp_entries_key(const void *A, const void *B)
 {
 	const struct tracing_map_elt *elt_a, *elt_b;
+	const struct tracing_map_sort_entry *a, *b;
 	struct tracing_map_sort_key *sort_key;
 	struct tracing_map_field *field;
 	tracing_map_cmp_fn_t cmp_fn;
 	void *val_a, *val_b;
 	int ret = 0;
 
-	elt_a = (*a)->elt;
-	elt_b = (*b)->elt;
+	a = *(const struct tracing_map_sort_entry **)A;
+	b = *(const struct tracing_map_sort_entry **)B;
+
+	elt_a = a->elt;
+	elt_b = b->elt;
 
 	sort_key = &elt_a->map->sort_key;
 
@@ -989,10 +998,8 @@ static void sort_secondary(struct tracing_map *map,
 			   struct tracing_map_sort_key *primary_key,
 			   struct tracing_map_sort_key *secondary_key)
 {
-	int (*primary_fn)(const struct tracing_map_sort_entry **,
-			  const struct tracing_map_sort_entry **);
-	int (*secondary_fn)(const struct tracing_map_sort_entry **,
-			    const struct tracing_map_sort_entry **);
+	int (*primary_fn)(const void *, const void *);
+	int (*secondary_fn)(const void *, const void *);
 	unsigned i, start = 0, n_sub = 1;
 
 	if (is_key(map, primary_key->field_idx))
@@ -1061,8 +1068,7 @@ int tracing_map_sort_entries(struct tracing_map *map,
 			     unsigned int n_sort_keys,
 			     struct tracing_map_sort_entry ***sort_entries)
 {
-	int (*cmp_entries_fn)(const struct tracing_map_sort_entry **,
-			      const struct tracing_map_sort_entry **);
+	int (*cmp_entries_fn)(const void *, const void *);
 	struct tracing_map_sort_entry *sort_entry, **entries;
 	int i, n_entries, ret;
 
-- 
2.33.0

[for-next][PATCH 18/40] tracing: Reuse logic from perfs get_recursion_context()

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Instead of having branches that adds noise to the branch prediction, use
the addition logic to set the bit for the level of interrupt context that
the state is currently in. This copies the logic from perf's
get_recursion_context() function.

Link: https://lore.kernel.org/all/20211015161702.GF174703@worktop.programming.kicks-ass.net/

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace_recursion.h | 11 ++++++-----
 kernel/trace/ring_buffer.c      | 12 ++++++------
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index a9f9c5714e65..f6da7a03bff0 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -137,12 +137,13 @@ enum {
 static __always_inline int trace_get_context_bit(void)
 {
 	unsigned long pc = preempt_count();
+	unsigned char bit = 0;
 
-	if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
-		return TRACE_CTX_NORMAL;
-	else
-		return pc & NMI_MASK ? TRACE_CTX_NMI :
-			pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ;
+	bit += !!(pc & (NMI_MASK));
+	bit += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+	bit += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
+
+	return TRACE_CTX_NORMAL - bit;
 }
 
 #ifdef CONFIG_FTRACE_RECORD_RECURSION
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c5a3fbf19617..15d4380006e3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3168,13 +3168,13 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	unsigned int val = cpu_buffer->current_context;
 	unsigned long pc = preempt_count();
-	int bit;
+	int bit = 0;
 
-	if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
-		bit = RB_CTX_NORMAL;
-	else
-		bit = pc & NMI_MASK ? RB_CTX_NMI :
-			pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
+	bit += !!(pc & (NMI_MASK));
+	bit += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+	bit += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
+
+	bit = RB_CTX_NORMAL - bit;
 
 	if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) {
 		/*
-- 
2.33.0

[for-next][PATCH 19/40] tracing/perf: Add interrupt_context_level() helper

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Now that there are three different instances of doing the addition trick
to the preempt_count() and NMI_MASK, HARDIRQ_MASK and SOFTIRQ_OFFSET
macros, it deserves a helper function defined in the preempt.h header.

Add the interrupt_context_level() helper and replace the three instances
that do that logic with it.

Link: https://lore.kernel.org/all/20211015142541.4badd8a9@gandalf.local.home/

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/preempt.h         | 21 +++++++++++++++++++++
 include/linux/trace_recursion.h |  7 +------
 kernel/events/internal.h        |  7 +------
 kernel/trace/ring_buffer.c      |  7 +------
 4 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 4d244e295e85..b32e3dabe28b 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -77,6 +77,27 @@
 /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
 #include <asm/preempt.h>
 
+/**
+ * interrupt_context_level - return interrupt context level
+ *
+ * Returns the current interrupt context level.
+ *  0 - normal context
+ *  1 - softirq context
+ *  2 - hardirq context
+ *  3 - NMI context
+ */
+static __always_inline unsigned char interrupt_context_level(void)
+{
+	unsigned long pc = preempt_count();
+	unsigned char level = 0;
+
+	level += !!(pc & (NMI_MASK));
+	level += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+	level += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
+
+	return level;
+}
+
 #define nmi_count()	(preempt_count() & NMI_MASK)
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
 #ifdef CONFIG_PREEMPT_RT
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index f6da7a03bff0..1d8cce02c3fb 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -136,12 +136,7 @@ enum {
 
 static __always_inline int trace_get_context_bit(void)
 {
-	unsigned long pc = preempt_count();
-	unsigned char bit = 0;
-
-	bit += !!(pc & (NMI_MASK));
-	bit += !!(pc & (NMI_MASK | HARDIRQ_MASK));
-	bit += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
+	unsigned char bit = interrupt_context_level();
 
 	return TRACE_CTX_NORMAL - bit;
 }
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 228801e20788..082832738c8f 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -205,12 +205,7 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
 
 static inline int get_recursion_context(int *recursion)
 {
-	unsigned int pc = preempt_count();
-	unsigned char rctx = 0;
-
-	rctx += !!(pc & (NMI_MASK));
-	rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK));
-	rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
+	unsigned char rctx = interrupt_context_level();
 
 	if (recursion[rctx])
 		return -1;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 15d4380006e3..f6520d0a4c8c 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3167,12 +3167,7 @@ static __always_inline int
 trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	unsigned int val = cpu_buffer->current_context;
-	unsigned long pc = preempt_count();
-	int bit = 0;
-
-	bit += !!(pc & (NMI_MASK));
-	bit += !!(pc & (NMI_MASK | HARDIRQ_MASK));
-	bit += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
+	int bit = interrupt_context_level();
 
 	bit = RB_CTX_NORMAL - bit;
 
-- 
2.33.0

[for-next][PATCH 20/40] x86/ftrace: Remove extra orig rax move

[Steven Rostedt]

From: Jiri Olsa <jolsa@redhat.com>

There's identical move 2 lines earlier.

Link: https://lkml.kernel.org/r/20211008091336.33616-2-jolsa@kernel.org

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/x86/kernel/ftrace_64.S | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 7c273846c687..a8eb084a7a9a 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -251,7 +251,6 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	 * If ORIG_RAX is anything but zero, make this a call to that.
 	 * See arch_ftrace_set_direct_caller().
 	 */
-	movq ORIG_RAX(%rsp), %rax
 	testq	%rax, %rax
 SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL)
 	jnz	1f
-- 
2.33.0

[for-next][PATCH 21/40] x86/ftrace: Remove fault protection code in prepare_ftrace_return

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Removing the fault protection code when writing return_hooker
to stack. As Steven noted:

> That protection was there from the beginning due to being "paranoid",
> considering ftrace was bricking network cards. But that protection
> would not have even protected against that.

Link: https://lkml.kernel.org/r/20211008091336.33616-3-jolsa@kernel.org

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/x86/kernel/ftrace.c | 38 +++-----------------------------------
 1 file changed, 3 insertions(+), 35 deletions(-)

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 23d221a9a3cd..7f12eacdf1ae 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -620,12 +620,10 @@ int ftrace_disable_ftrace_graph_caller(void)
  * Hook the return address and push it in the stack of return addrs
  * in current thread info.
  */
-void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
+void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer)
 {
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
-	unsigned long old;
-	int faulted;
 
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly
@@ -645,37 +643,7 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
-	/*
-	 * Protect against fault, even if it shouldn't
-	 * happen. This tool is too much intrusive to
-	 * ignore such a protection.
-	 */
-	asm volatile(
-		"1: " _ASM_MOV " (%[parent]), %[old]\n"
-		"2: " _ASM_MOV " %[return_hooker], (%[parent])\n"
-		"   movl $0, %[faulted]\n"
-		"3:\n"
-
-		".section .fixup, \"ax\"\n"
-		"4: movl $1, %[faulted]\n"
-		"   jmp 3b\n"
-		".previous\n"
-
-		_ASM_EXTABLE(1b, 4b)
-		_ASM_EXTABLE(2b, 4b)
-
-		: [old] "=&r" (old), [faulted] "=r" (faulted)
-		: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
-		: "memory"
-	);
-
-	if (unlikely(faulted)) {
-		ftrace_graph_stop();
-		WARN_ON(1);
-		return;
-	}
-
-	if (function_graph_enter(old, self_addr, frame_pointer, parent))
-		*parent = old;
+	if (!function_graph_enter(*parent, ip, frame_pointer, parent))
+		*parent = return_hooker;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-- 
2.33.0

[for-next][PATCH 22/40] ftrace/x86_64: Have function graph tracer depend on DYNAMIC_FTRACE

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

The function graph tracer is going to now depend on
ARCH_SUPPORTS_FTRACE_OPS, as that also means that it can support ftrace
args. Since ARCH_SUPPORTS_FTRACE_OPS depends on DYNAMIC_FTRACE, this
means that the function graph tracer for x86_64 will need to depend on
DYNAMIC_FTRACE.

Link: https://lkml.kernel.org/r/20211020233555.16b0dbf2@rorschach.local.home

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/x86/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ab83c22d274e..e39e2bd6acc5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -197,7 +197,7 @@ config X86
 	select HAVE_FAST_GUP
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER	if X86_32 || (X86_64 && DYNAMIC_FTRACE)
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT
-- 
2.33.0

[for-next][PATCH 23/40] x86/ftrace: Make function graph use ftrace directly

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

We don't need special hook for graph tracer entry point,
but instead we can use graph_ops::func function to install
the return_hooker.

This moves the graph tracing setup _before_ the direct
trampoline prepares the stack, so the return_hooker will
be called when the direct trampoline is finished.

This simplifies the code, because we don't need to take into
account the direct trampoline setup when preparing the graph
tracer hooker and we can allow function graph tracer on entries
registered with direct trampoline.

Link: https://lkml.kernel.org/r/20211008091336.33616-4-jolsa@kernel.org

[fixed compile error reported by kernel test robot <lkp@intel.com>]
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/x86/include/asm/ftrace.h |  9 +++++++--
 arch/x86/kernel/ftrace.c      | 37 ++++++++++++++++++++++++++++++++---
 arch/x86/kernel/ftrace_64.S   | 29 +--------------------------
 include/linux/ftrace.h        |  9 +++++++++
 kernel/trace/fgraph.c         |  6 ++++--
 5 files changed, 55 insertions(+), 35 deletions(-)

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 9f3130f40807..024d9797646e 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -57,6 +57,13 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
 
 #define ftrace_instruction_pointer_set(fregs, _ip)	\
 	do { (fregs)->regs.ip = (_ip); } while (0)
+
+struct ftrace_ops;
+#define ftrace_graph_func ftrace_graph_func
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#else
+#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -65,8 +72,6 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
-#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
-
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 7f12eacdf1ae..c39f906cdc4e 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -522,7 +522,7 @@ static void *addr_from_call(void *ptr)
 	return ptr + CALL_INSN_SIZE + call.disp;
 }
 
-void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
+void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer);
 
 /*
@@ -536,7 +536,8 @@ static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec)
 	void *ptr;
 
 	if (ops && ops->trampoline) {
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) && \
+	defined(CONFIG_FUNCTION_GRAPH_TRACER)
 		/*
 		 * We only know about function graph tracer setting as static
 		 * trampoline.
@@ -584,8 +585,9 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-extern void ftrace_graph_call(void);
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+extern void ftrace_graph_call(void);
 static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
 	return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr);
@@ -613,7 +615,17 @@ int ftrace_disable_ftrace_graph_caller(void)
 
 	return ftrace_mod_jmp(ip, &ftrace_stub);
 }
+#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return 0;
+}
 
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return 0;
+}
+#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 #endif /* !CONFIG_DYNAMIC_FTRACE */
 
 /*
@@ -624,6 +636,7 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer)
 {
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	int bit;
 
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly
@@ -643,7 +656,25 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
+	bit = ftrace_test_recursion_trylock(ip, *parent);
+	if (bit < 0)
+		return;
+
 	if (!function_graph_enter(*parent, ip, frame_pointer, parent))
 		*parent = return_hooker;
+
+	ftrace_test_recursion_unlock(bit);
+}
+
+#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	struct pt_regs *regs = &fregs->regs;
+	unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs);
+
+	prepare_ftrace_return(ip, (unsigned long *)stack, 0);
 }
+#endif
+
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index a8eb084a7a9a..7a879901f103 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -174,11 +174,6 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
 SYM_FUNC_END(ftrace_caller);
 
 SYM_FUNC_START(ftrace_epilogue)
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
-	jmp ftrace_stub
-#endif
-
 /*
  * This is weak to keep gas from relaxing the jumps.
  * It is also used to copy the retq for trampolines.
@@ -288,15 +283,6 @@ SYM_FUNC_START(__fentry__)
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
 
-fgraph_trace:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	cmpq $ftrace_stub, ftrace_graph_return
-	jnz ftrace_graph_caller
-
-	cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
-	jnz ftrace_graph_caller
-#endif
-
 SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
 	retq
 
@@ -314,25 +300,12 @@ trace:
 	CALL_NOSPEC r8
 	restore_mcount_regs
 
-	jmp fgraph_trace
+	jmp ftrace_stub
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_FUNC_START(ftrace_graph_caller)
-	/* Saves rbp into %rdx and fills first parameter  */
-	save_mcount_regs
-
-	leaq MCOUNT_REG_SIZE+8(%rsp), %rsi
-	movq $0, %rdx	/* No framepointers needed */
-	call	prepare_ftrace_return
-
-	restore_mcount_regs
-
-	retq
-SYM_FUNC_END(ftrace_graph_caller)
-
 SYM_FUNC_START(return_to_handler)
 	subq  $24, %rsp
 
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 12fcfa2d23ea..16a7baaba702 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -803,6 +803,15 @@ static inline bool is_ftrace_trampoline(unsigned long addr)
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#ifndef ftrace_graph_func
+#define ftrace_graph_func ftrace_stub
+#define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB
+#else
+#define FTRACE_OPS_GRAPH_STUB 0
+#endif
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /* totally disable ftrace - can not re-enable after this */
 void ftrace_kill(void);
 
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index b8a0d1d564fb..22061d38fc00 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -115,6 +115,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 {
 	struct ftrace_graph_ent trace;
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	/*
 	 * Skip graph tracing if the return location is served by direct trampoline,
 	 * since call sequence and return addresses are unpredictable anyway.
@@ -124,6 +125,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	if (ftrace_direct_func_count &&
 	    ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE))
 		return -EBUSY;
+#endif
 	trace.func = func;
 	trace.depth = ++current->curr_ret_depth;
 
@@ -333,10 +335,10 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 #endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
 
 static struct ftrace_ops graph_ops = {
-	.func			= ftrace_stub,
+	.func			= ftrace_graph_func,
 	.flags			= FTRACE_OPS_FL_INITIALIZED |
 				   FTRACE_OPS_FL_PID |
-				   FTRACE_OPS_FL_STUB,
+				   FTRACE_OPS_GRAPH_STUB,
 #ifdef FTRACE_GRAPH_TRAMP_ADDR
 	.trampoline		= FTRACE_GRAPH_TRAMP_ADDR,
 	/* trampoline_size is only needed for dynamically allocated tramps */
-- 
2.33.0

[for-next][PATCH 24/40] tracing: Add trampoline/graph selftest

[Steven Rostedt]

From: Jiri Olsa <jolsa@redhat.com>

Adding selftest for checking that direct trampoline can
co-exist together with graph tracer on same function.

This is supported for CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
config option, which is defined only for x86_64 for now.

Link: https://lkml.kernel.org/r/20211008091336.33616-5-jolsa@kernel.org

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_selftest.c | 54 ++++++++++++++++++++++++++++++++++-
 1 file changed, 53 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 875b4f1a0476..3404a245417e 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -784,6 +784,8 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 	.retfunc		= &trace_graph_return,
 };
 
+noinline __noclone static void trace_direct_tramp(void) { }
+
 /*
  * Pretty much the same than for the function tracer from which the selftest
  * has been borrowed.
@@ -794,6 +796,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 {
 	int ret;
 	unsigned long count;
+	char *func_name __maybe_unused;
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 	if (ftrace_filter_param) {
@@ -842,8 +845,57 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 		goto out;
 	}
 
-	/* Don't test dynamic tracing, the function tracer already did */
+#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+	tracing_reset_online_cpus(&tr->array_buffer);
+	set_graph_array(tr);
+
+	/*
+	 * Some archs *cough*PowerPC*cough* add characters to the
+	 * start of the function names. We simply put a '*' to
+	 * accommodate them.
+	 */
+	func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+	ftrace_set_global_filter(func_name, strlen(func_name), 1);
+
+	/*
+	 * Register direct function together with graph tracer
+	 * and make sure we get graph trace.
+	 */
+	ret = register_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
+				     (unsigned long) trace_direct_tramp);
+	if (ret)
+		goto out;
+
+	ret = register_ftrace_graph(&fgraph_ops);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
+
+	DYN_FTRACE_TEST_NAME();
+
+	count = 0;
+
+	tracing_stop();
+	/* check the trace buffer */
+	ret = trace_test_buffer(&tr->array_buffer, &count);
+
+	unregister_ftrace_graph(&fgraph_ops);
+
+	ret = unregister_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
+				       (unsigned long) trace_direct_tramp);
+	if (ret)
+		goto out;
+
+	tracing_start();
 
+	if (!ret && !count) {
+		ret = -1;
+		goto out;
+	}
+#endif
+
+	/* Don't test dynamic tracing, the function tracer already did */
 out:
 	/* Stop it if we failed */
 	if (ret)
-- 
2.33.0

[for-next][PATCH 25/40] tracing: Fix selftest config check for function graph start up test

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

There's a new test in trace_selftest_startup_function_graph() that
requires the use of ftrace args being supported as well does some tricks
with dynamic tracing. Although this code checks HAVE_DYNAMIC_FTRACE_WITH_ARGS
it fails to check DYNAMIC_FTRACE, and the kernel fails to build due to
that dependency.

Also only define the prototype of trace_direct_tramp() if it is used.

Link: https://lkml.kernel.org/r/20211021134357.7f48e173@gandalf.local.home

Acked-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_selftest.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 3404a245417e..afd937a46496 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -784,7 +784,11 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 	.retfunc		= &trace_graph_return,
 };
 
+#if defined(CONFIG_DYNAMIC_FTRACE) && \
+    defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)
+#define TEST_DIRECT_TRAMP
 noinline __noclone static void trace_direct_tramp(void) { }
+#endif
 
 /*
  * Pretty much the same than for the function tracer from which the selftest
@@ -845,7 +849,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 		goto out;
 	}
 
-#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+#ifdef TEST_DIRECT_TRAMP
 	tracing_reset_online_cpus(&tr->array_buffer);
 	set_graph_array(tr);
 
-- 
2.33.0

[for-next][PATCH 26/40] ftrace: Add ftrace_add_rec_direct function

[Steven Rostedt]

From: Jiri Olsa <jolsa@redhat.com>

Factor out the code that adds (ip, addr) tuple to direct_functions
hash in new ftrace_add_rec_direct function. It will be used in
following patches.

Link: https://lkml.kernel.org/r/20211008091336.33616-6-jolsa@kernel.org

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 64 +++++++++++++++++++++++++------------------
 1 file changed, 37 insertions(+), 27 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8b5801881271..ccbd8377e580 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2390,6 +2390,39 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
 	return entry->direct;
 }
 
+static struct ftrace_func_entry*
+ftrace_add_rec_direct(unsigned long ip, unsigned long addr,
+		      struct ftrace_hash **free_hash)
+{
+	struct ftrace_func_entry *entry;
+
+	if (ftrace_hash_empty(direct_functions) ||
+	    direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
+		struct ftrace_hash *new_hash;
+		int size = ftrace_hash_empty(direct_functions) ? 0 :
+			direct_functions->count + 1;
+
+		if (size < 32)
+			size = 32;
+
+		new_hash = dup_hash(direct_functions, size);
+		if (!new_hash)
+			return NULL;
+
+		*free_hash = direct_functions;
+		direct_functions = new_hash;
+	}
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return NULL;
+
+	entry->ip = ip;
+	entry->direct = addr;
+	__add_hash_entry(direct_functions, entry);
+	return entry;
+}
+
 static void call_direct_funcs(unsigned long ip, unsigned long pip,
 			      struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
@@ -5106,39 +5139,16 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 	}
 
 	ret = -ENOMEM;
-	if (ftrace_hash_empty(direct_functions) ||
-	    direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
-		struct ftrace_hash *new_hash;
-		int size = ftrace_hash_empty(direct_functions) ? 0 :
-			direct_functions->count + 1;
-
-		if (size < 32)
-			size = 32;
-
-		new_hash = dup_hash(direct_functions, size);
-		if (!new_hash)
-			goto out_unlock;
-
-		free_hash = direct_functions;
-		direct_functions = new_hash;
-	}
-
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		goto out_unlock;
-
 	direct = ftrace_find_direct_func(addr);
 	if (!direct) {
 		direct = ftrace_alloc_direct_func(addr);
-		if (!direct) {
-			kfree(entry);
+		if (!direct)
 			goto out_unlock;
-		}
 	}
 
-	entry->ip = ip;
-	entry->direct = addr;
-	__add_hash_entry(direct_functions, entry);
+	entry = ftrace_add_rec_direct(ip, addr, &free_hash);
+	if (!entry)
+		goto out_unlock;
 
 	ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0);
 	if (ret)
-- 
2.33.0

[for-next][PATCH 27/40] ftrace: Add multi direct register/unregister interface

[Steven Rostedt]

From: Jiri Olsa <jolsa@redhat.com>

Adding interface to register multiple direct functions
within single call. Adding following functions:

  register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
  unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)

The register_ftrace_direct_multi registers direct function (addr)
with all functions in ops filter. The ops filter can be updated
before with ftrace_set_filter_ip calls.

All requested functions must not have direct function currently
registered, otherwise register_ftrace_direct_multi will fail.

The unregister_ftrace_direct_multi unregisters ops related direct
functions.

Link: https://lkml.kernel.org/r/20211008091336.33616-7-jolsa@kernel.org

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  11 ++++
 kernel/trace/ftrace.c  | 142 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 153 insertions(+)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 16a7baaba702..0158261cac9f 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -324,7 +324,10 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 				unsigned long old_addr,
 				unsigned long new_addr);
 unsigned long ftrace_find_rec_direct(unsigned long ip);
+int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
+int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
 #else
+struct ftrace_ops;
 # define ftrace_direct_func_count 0
 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr)
 {
@@ -354,6 +357,14 @@ static inline unsigned long ftrace_find_rec_direct(unsigned long ip)
 {
 	return 0;
 }
+static inline int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	return -ENODEV;
+}
+static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	return -ENODEV;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ccbd8377e580..a05b25fb77d8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5401,6 +5401,148 @@ int modify_ftrace_direct(unsigned long ip,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(modify_ftrace_direct);
+
+#define MULTI_FLAGS (FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_DIRECT | \
+		     FTRACE_OPS_FL_SAVE_REGS)
+
+static int check_direct_multi(struct ftrace_ops *ops)
+{
+	if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED))
+		return -EINVAL;
+	if ((ops->flags & MULTI_FLAGS) != MULTI_FLAGS)
+		return -EINVAL;
+	return 0;
+}
+
+static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long addr)
+{
+	struct ftrace_func_entry *entry, *del;
+	int size, i;
+
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			del = __ftrace_lookup_ip(direct_functions, entry->ip);
+			if (del && del->direct == addr) {
+				remove_hash_entry(direct_functions, del);
+				kfree(del);
+			}
+		}
+	}
+}
+
+/**
+ * register_ftrace_direct_multi - Call a custom trampoline directly
+ * for multiple functions registered in @ops
+ * @ops: The address of the struct ftrace_ops object
+ * @addr: The address of the trampoline to call at @ops functions
+ *
+ * This is used to connect a direct calls to @addr from the nop locations
+ * of the functions registered in @ops (with by ftrace_set_filter_ip
+ * function).
+ *
+ * The location that it calls (@addr) must be able to handle a direct call,
+ * and save the parameters of the function being traced, and restore them
+ * (or inject new ones if needed), before returning.
+ *
+ * Returns:
+ *  0 on success
+ *  -EINVAL  - The @ops object was already registered with this call or
+ *             when there are no functions in @ops object.
+ *  -EBUSY   - Another direct function is already attached (there can be only one)
+ *  -ENODEV  - @ip does not point to a ftrace nop location (or not supported)
+ *  -ENOMEM  - There was an allocation failure.
+ */
+int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash, *free_hash = NULL;
+	struct ftrace_func_entry *entry, *new;
+	int err = -EBUSY, size, i;
+
+	if (ops->func || ops->trampoline)
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED))
+		return -EINVAL;
+	if (ops->flags & FTRACE_OPS_FL_ENABLED)
+		return -EINVAL;
+
+	hash = ops->func_hash->filter_hash;
+	if (ftrace_hash_empty(hash))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+
+	/* Make sure requested entries are not already registered.. */
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			if (ftrace_find_rec_direct(entry->ip))
+				goto out_unlock;
+		}
+	}
+
+	/* ... and insert them to direct_functions hash. */
+	err = -ENOMEM;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			new = ftrace_add_rec_direct(entry->ip, addr, &free_hash);
+			if (!new)
+				goto out_remove;
+			entry->direct = addr;
+		}
+	}
+
+	ops->func = call_direct_funcs;
+	ops->flags = MULTI_FLAGS;
+	ops->trampoline = FTRACE_REGS_ADDR;
+
+	err = register_ftrace_function(ops);
+
+ out_remove:
+	if (err)
+		remove_direct_functions_hash(hash, addr);
+
+ out_unlock:
+	mutex_unlock(&direct_mutex);
+
+	if (free_hash) {
+		synchronize_rcu_tasks();
+		free_ftrace_hash(free_hash);
+	}
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_ftrace_direct_multi);
+
+/**
+ * unregister_ftrace_direct_multi - Remove calls to custom trampoline
+ * previously registered by register_ftrace_direct_multi for @ops object.
+ * @ops: The address of the struct ftrace_ops object
+ *
+ * This is used to remove a direct calls to @addr from the nop locations
+ * of the functions registered in @ops (with by ftrace_set_filter_ip
+ * function).
+ *
+ * Returns:
+ *  0 on success
+ *  -EINVAL - The @ops object was not properly registered.
+ */
+int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+	int err;
+
+	if (check_direct_multi(ops))
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+	err = unregister_ftrace_function(ops);
+	remove_direct_functions_hash(hash, addr);
+	mutex_unlock(&direct_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 /**
-- 
2.33.0

[for-next][PATCH 28/40] ftrace: Add multi direct modify interface

[Steven Rostedt]

From: Jiri Olsa <jolsa@redhat.com>

Adding interface to modify registered direct function
for ftrace_ops. Adding following function:

   modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)

The function changes the currently registered direct
function for all attached functions.

Link: https://lkml.kernel.org/r/20211008091336.33616-8-jolsa@kernel.org

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  6 ++++
 kernel/trace/ftrace.c  | 62 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 68 insertions(+)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 0158261cac9f..9999e29187de 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -326,6 +326,8 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 unsigned long ftrace_find_rec_direct(unsigned long ip);
 int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
 int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
+int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
+
 #else
 struct ftrace_ops;
 # define ftrace_direct_func_count 0
@@ -365,6 +367,10 @@ static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigne
 {
 	return -ENODEV;
 }
+static inline int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	return -ENODEV;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a05b25fb77d8..30120342176e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5543,6 +5543,68 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	return err;
 }
 EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
+
+/**
+ * modify_ftrace_direct_multi - Modify an existing direct 'multi' call
+ * to call something else
+ * @ops: The address of the struct ftrace_ops object
+ * @addr: The address of the new trampoline to call at @ops functions
+ *
+ * This is used to unregister currently registered direct caller and
+ * register new one @addr on functions registered in @ops object.
+ *
+ * Note there's window between ftrace_shutdown and ftrace_startup calls
+ * where there will be no callbacks called.
+ *
+ * Returns: zero on success. Non zero on error, which includes:
+ *  -EINVAL - The @ops object was not properly registered.
+ */
+int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+	struct ftrace_func_entry *entry, *iter;
+	int i, size;
+	int err;
+
+	if (check_direct_multi(ops))
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+	mutex_lock(&ftrace_lock);
+
+	/*
+	 * Shutdown the ops, change 'direct' pointer for each
+	 * ops entry in direct_functions hash and startup the
+	 * ops back again.
+	 *
+	 * Note there is no callback called for @ops object after
+	 * this ftrace_shutdown call until ftrace_startup is called
+	 * later on.
+	 */
+	err = ftrace_shutdown(ops, 0);
+	if (err)
+		goto out_unlock;
+
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(iter, &hash->buckets[i], hlist) {
+			entry = __ftrace_lookup_ip(direct_functions, iter->ip);
+			if (!entry)
+				continue;
+			entry->direct = addr;
+		}
+	}
+
+	err = ftrace_startup(ops, 0);
+
+ out_unlock:
+	mutex_unlock(&ftrace_lock);
+	mutex_unlock(&direct_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi);
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 /**
-- 
2.33.0

[for-next][PATCH 29/40] ftrace/samples: Add multi direct interface test module

[Steven Rostedt]

From: Jiri Olsa <jolsa@redhat.com>

Adding simple module that uses multi direct interface:

  register_ftrace_direct_multi
  unregister_ftrace_direct_multi

The init function registers trampoline for 2 functions,
and exit function unregisters them.

Link: https://lkml.kernel.org/r/20211008091336.33616-9-jolsa@kernel.org

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 samples/ftrace/Makefile              |  1 +
 samples/ftrace/ftrace-direct-multi.c | 52 ++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)
 create mode 100644 samples/ftrace/ftrace-direct-multi.c

diff --git a/samples/ftrace/Makefile b/samples/ftrace/Makefile
index 4ce896e10b2e..ab1d1c05c288 100644
--- a/samples/ftrace/Makefile
+++ b/samples/ftrace/Makefile
@@ -3,6 +3,7 @@
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct.o
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-too.o
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-modify.o
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-multi.o
 
 CFLAGS_sample-trace-array.o := -I$(src)
 obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += sample-trace-array.o
diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c
new file mode 100644
index 000000000000..2a5b1fb7ac14
--- /dev/null
+++ b/samples/ftrace/ftrace-direct-multi.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+
+#include <linux/mm.h> /* for handle_mm_fault() */
+#include <linux/ftrace.h>
+#include <linux/sched/stat.h>
+
+void my_direct_func(unsigned long ip)
+{
+	trace_printk("ip %lx\n", ip);
+}
+
+extern void my_tramp(void *);
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	pushq %rbp\n"
+"	movq %rsp, %rbp\n"
+"	pushq %rdi\n"
+"	movq 8(%rbp), %rdi\n"
+"	call my_direct_func\n"
+"	popq %rdi\n"
+"	leave\n"
+"	ret\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+static struct ftrace_ops direct;
+
+static int __init ftrace_direct_multi_init(void)
+{
+	ftrace_set_filter_ip(&direct, (unsigned long) wake_up_process, 0, 0);
+	ftrace_set_filter_ip(&direct, (unsigned long) schedule, 0, 0);
+
+	return register_ftrace_direct_multi(&direct, (unsigned long) my_tramp);
+}
+
+static void __exit ftrace_direct_multi_exit(void)
+{
+	unregister_ftrace_direct_multi(&direct, (unsigned long) my_tramp);
+}
+
+module_init(ftrace_direct_multi_init);
+module_exit(ftrace_direct_multi_exit);
+
+MODULE_AUTHOR("Jiri Olsa");
+MODULE_DESCRIPTION("Example use case of using register_ftrace_direct_multi()");
+MODULE_LICENSE("GPL");
-- 
2.33.0

[for-next][PATCH 30/40] ftrace/direct: Do not disable when switching direct callers

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Currently to switch a set of "multi" direct trampolines from one
trampoline to another, a full shutdown of the current set needs to be
done, followed by an update to what trampoline the direct callers would
call, and then re-enabling the callers. This leaves a time when the
functions will not be calling anything, and events may be missed.

Instead, use a trick to allow all the functions with direct trampolines
attached will always call either the new or old trampoline while the
switch is happening. To do this, first attach a "dummy" callback via
ftrace to all the functions that the current direct trampoline is attached
to. This will cause the functions to call the "list func" instead of the
direct trampoline. The list function will call the direct trampoline
"helper" that will set the function it should call as it returns back to
the ftrace trampoline.

At this moment, the direct caller descriptor can safely update the direct
call trampoline. The list function will pick either the new or old
function (depending on the memory coherency model of the architecture).

Now removing the dummy function from each of the locations of the direct
trampoline caller, will put back the direct call, but now to the new
trampoline.

A better visual is:

[ Changing direct call from my_direct_1 to my_direct_2 ]

  <traced_func>:
     call my_direct_1

 ||||||||||||||||||||
 vvvvvvvvvvvvvvvvvvvv

  <traced_func>:
     call ftrace_caller

  <ftrace_caller>:
    [..]
    call ftrace_ops_list_func

	ftrace_ops_list_func()
	{
		ops->func() -> direct_helper -> set rax to my_direct_1 or my_direct_2
	}

   call rax (to either my_direct_1 or my_direct_2

 ||||||||||||||||||||
 vvvvvvvvvvvvvvvvvvvv

  <traced_func>:
     call my_direct_2

Link: https://lore.kernel.org/all/20211014162819.5c85618b@gandalf.local.home/

Acked-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 30120342176e..f90ed00a6d5b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5561,8 +5561,12 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
  */
 int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 {
-	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+	struct ftrace_hash *hash;
 	struct ftrace_func_entry *entry, *iter;
+	static struct ftrace_ops tmp_ops = {
+		.func		= ftrace_stub,
+		.flags		= FTRACE_OPS_FL_STUB,
+	};
 	int i, size;
 	int err;
 
@@ -5572,21 +5576,22 @@ int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 		return -EINVAL;
 
 	mutex_lock(&direct_mutex);
-	mutex_lock(&ftrace_lock);
+
+	/* Enable the tmp_ops to have the same functions as the direct ops */
+	ftrace_ops_init(&tmp_ops);
+	tmp_ops.func_hash = ops->func_hash;
+
+	err = register_ftrace_function(&tmp_ops);
+	if (err)
+		goto out_direct;
 
 	/*
-	 * Shutdown the ops, change 'direct' pointer for each
-	 * ops entry in direct_functions hash and startup the
-	 * ops back again.
-	 *
-	 * Note there is no callback called for @ops object after
-	 * this ftrace_shutdown call until ftrace_startup is called
-	 * later on.
+	 * Now the ftrace_ops_list_func() is called to do the direct callers.
+	 * We can safely change the direct functions attached to each entry.
 	 */
-	err = ftrace_shutdown(ops, 0);
-	if (err)
-		goto out_unlock;
+	mutex_lock(&ftrace_lock);
 
+	hash = ops->func_hash->filter_hash;
 	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(iter, &hash->buckets[i], hlist) {
@@ -5597,10 +5602,11 @@ int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 		}
 	}
 
-	err = ftrace_startup(ops, 0);
+	/* Removing the tmp_ops will add the updated direct callers to the functions */
+	unregister_ftrace_function(&tmp_ops);
 
- out_unlock:
 	mutex_unlock(&ftrace_lock);
+ out_direct:
 	mutex_unlock(&direct_mutex);
 	return err;
 }
-- 
2.33.0

[for-next][PATCH 31/40] tracing: Explain the trace recursion transition bit better

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

The current text of the explanation of the transition bit in the trace
recursion protection is not very clear. Improve the text, so that when all
the archs no longer have the issue of tracing between a start of a new
(interrupt) context and updating the preempt_count to reflect the new
context, that it may be removed.

Link: https://lore.kernel.org/all/20211018220203.064a42ed@gandalf.local.home/

Suggested-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace_recursion.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index 1d8cce02c3fb..24f284eb55a7 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -168,8 +168,12 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign
 	bit = trace_get_context_bit() + start;
 	if (unlikely(val & (1 << bit))) {
 		/*
-		 * It could be that preempt_count has not been updated during
-		 * a switch between contexts. Allow for a single recursion.
+		 * If an interrupt occurs during a trace, and another trace
+		 * happens in that interrupt but before the preempt_count is
+		 * updated to reflect the new interrupt context, then this
+		 * will think a recursion occurred, and the event will be dropped.
+		 * Let a single instance happen via the TRANSITION_BIT to
+		 * not drop those events.
 		 */
 		bit = TRACE_TRANSITION_BIT;
 		if (val & (1 << bit)) {
-- 
2.33.0

[for-next][PATCH 32/40] tracing: use %ps format string to print symbols

[Steven Rostedt]

From: Arnd Bergmann <arnd@arndb.de>

clang started warning about excessive stack usage in
hist_trigger_print_key()

kernel/trace/trace_events_hist.c:4723:13: error: stack frame size (1336) exceeds limit (1024) in function 'hist_trigger_print_key' [-Werror,-Wframe-larger-than]

The problem is that there are two 512-byte arrays on the stack if
hist_trigger_stacktrace_print() gets inlined. I don't think this has
changed in the past five years, but something probably changed the
inlining decisions made by the compiler, so the problem is now made
more obvious.

Rather than printing the symbol names into separate buffers, it
seems we can simply use the special %ps format string modifier
to print the pointers symbolically and get rid of both buffers.

Marking hist_trigger_stacktrace_print() would be a simpler
way of avoiding the warning, but that would not address the
excessive stack usage.

Link: https://lkml.kernel.org/r/20211019153337.294790-1-arnd@kernel.org

Fixes: 69a0200c2e25 ("tracing: Add hist trigger support for stacktraces as keys")
Link: https://lore.kernel.org/all/20211015095704.49a99859@gandalf.local.home/
Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Tested-by: Tom Zanussi <zanussi@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index a6061a69aa84..b64aed538628 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4706,7 +4706,6 @@ static void hist_trigger_stacktrace_print(struct seq_file *m,
 					  unsigned long *stacktrace_entries,
 					  unsigned int max_entries)
 {
-	char str[KSYM_SYMBOL_LEN];
 	unsigned int spaces = 8;
 	unsigned int i;
 
@@ -4715,8 +4714,7 @@ static void hist_trigger_stacktrace_print(struct seq_file *m,
 			return;
 
 		seq_printf(m, "%*c", 1 + spaces, ' ');
-		sprint_symbol(str, stacktrace_entries[i]);
-		seq_printf(m, "%s\n", str);
+		seq_printf(m, "%pS\n", (void*)stacktrace_entries[i]);
 	}
 }
 
@@ -4726,7 +4724,6 @@ static void hist_trigger_print_key(struct seq_file *m,
 				   struct tracing_map_elt *elt)
 {
 	struct hist_field *key_field;
-	char str[KSYM_SYMBOL_LEN];
 	bool multiline = false;
 	const char *field_name;
 	unsigned int i;
@@ -4747,14 +4744,12 @@ static void hist_trigger_print_key(struct seq_file *m,
 			seq_printf(m, "%s: %llx", field_name, uval);
 		} else if (key_field->flags & HIST_FIELD_FL_SYM) {
 			uval = *(u64 *)(key + key_field->offset);
-			sprint_symbol_no_offset(str, uval);
-			seq_printf(m, "%s: [%llx] %-45s", field_name,
-				   uval, str);
+			seq_printf(m, "%s: [%llx] %-45ps", field_name,
+				   uval, (void *)(uintptr_t)uval);
 		} else if (key_field->flags & HIST_FIELD_FL_SYM_OFFSET) {
 			uval = *(u64 *)(key + key_field->offset);
-			sprint_symbol(str, uval);
-			seq_printf(m, "%s: [%llx] %-55s", field_name,
-				   uval, str);
+			seq_printf(m, "%s: [%llx] %-55pS", field_name,
+				   uval, (void *)(uintptr_t)uval);
 		} else if (key_field->flags & HIST_FIELD_FL_EXECNAME) {
 			struct hist_elt_data *elt_data = elt->private_data;
 			char *comm;
-- 
2.33.0

[for-next][PATCH 33/40] kprobes: convert tests to kunit

[Steven Rostedt]

From: Sven Schnelle <svens@linux.ibm.com>

This converts the kprobes testcases to use the kunit framework.
It adds a dependency on CONFIG_KUNIT, and the output will change
to TAP:

TAP version 14
1..1
    # Subtest: kprobes_test
    1..4
random: crng init done
    ok 1 - test_kprobe
    ok 2 - test_kprobes
    ok 3 - test_kretprobe
    ok 4 - test_kretprobes
ok 1 - kprobes_test

Note that the kprobes testcases are no longer run immediately after
kprobes initialization, but as a late initcall when kunit is
initialized. kprobes itself is initialized with an early initcall,
so the order is still correct.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/kprobes.c      |   3 -
 kernel/test_kprobes.c | 222 +++++++++++-------------------------------
 lib/Kconfig.debug     |   3 +-
 3 files changed, 61 insertions(+), 167 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index b62af9fc3607..4676627cb066 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2581,9 +2581,6 @@ static int __init init_kprobes(void)
 		err = register_module_notifier(&kprobe_module_nb);
 
 	kprobes_initialized = (err == 0);
-
-	if (!err)
-		init_test_probes();
 	return err;
 }
 early_initcall(init_kprobes);
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index 76c997fdbc9d..e78f18144145 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -5,18 +5,17 @@
  * Copyright IBM Corp. 2008
  */
 
-#define pr_fmt(fmt) "Kprobe smoke test: " fmt
-
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/random.h>
+#include <kunit/test.h>
 
 #define div_factor 3
 
 static u32 rand1, preh_val, posth_val;
-static int errors, handler_errors, num_tests;
 static u32 (*target)(u32 value);
 static u32 (*target2)(u32 value);
+static struct kunit *current_test;
 
 static noinline u32 kprobe_target(u32 value)
 {
@@ -25,10 +24,7 @@ static noinline u32 kprobe_target(u32 value)
 
 static int kp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	if (preemptible()) {
-		handler_errors++;
-		pr_err("pre-handler is preemptible\n");
-	}
+	KUNIT_EXPECT_FALSE(current_test, preemptible());
 	preh_val = (rand1 / div_factor);
 	return 0;
 }
@@ -36,14 +32,8 @@ static int kp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 static void kp_post_handler(struct kprobe *p, struct pt_regs *regs,
 		unsigned long flags)
 {
-	if (preemptible()) {
-		handler_errors++;
-		pr_err("post-handler is preemptible\n");
-	}
-	if (preh_val != (rand1 / div_factor)) {
-		handler_errors++;
-		pr_err("incorrect value in post_handler\n");
-	}
+	KUNIT_EXPECT_FALSE(current_test, preemptible());
+	KUNIT_EXPECT_EQ(current_test, preh_val, (rand1 / div_factor));
 	posth_val = preh_val + div_factor;
 }
 
@@ -53,30 +43,14 @@ static struct kprobe kp = {
 	.post_handler = kp_post_handler
 };
 
-static int test_kprobe(void)
+static void test_kprobe(struct kunit *test)
 {
-	int ret;
-
-	ret = register_kprobe(&kp);
-	if (ret < 0) {
-		pr_err("register_kprobe returned %d\n", ret);
-		return ret;
-	}
-
-	ret = target(rand1);
+	current_test = test;
+	KUNIT_EXPECT_EQ(test, 0, register_kprobe(&kp));
+	target(rand1);
 	unregister_kprobe(&kp);
-
-	if (preh_val == 0) {
-		pr_err("kprobe pre_handler not called\n");
-		handler_errors++;
-	}
-
-	if (posth_val == 0) {
-		pr_err("kprobe post_handler not called\n");
-		handler_errors++;
-	}
-
-	return 0;
+	KUNIT_EXPECT_NE(test, 0, preh_val);
+	KUNIT_EXPECT_NE(test, 0, posth_val);
 }
 
 static noinline u32 kprobe_target2(u32 value)
@@ -93,10 +67,7 @@ static int kp_pre_handler2(struct kprobe *p, struct pt_regs *regs)
 static void kp_post_handler2(struct kprobe *p, struct pt_regs *regs,
 		unsigned long flags)
 {
-	if (preh_val != (rand1 / div_factor) + 1) {
-		handler_errors++;
-		pr_err("incorrect value in post_handler2\n");
-	}
+	KUNIT_EXPECT_EQ(current_test, preh_val, (rand1 / div_factor) + 1);
 	posth_val = preh_val + div_factor;
 }
 
@@ -106,51 +77,31 @@ static struct kprobe kp2 = {
 	.post_handler = kp_post_handler2
 };
 
-static int test_kprobes(void)
+static void test_kprobes(struct kunit *test)
 {
-	int ret;
 	struct kprobe *kps[2] = {&kp, &kp2};
 
+	current_test = test;
+
 	/* addr and flags should be cleard for reusing kprobe. */
 	kp.addr = NULL;
 	kp.flags = 0;
-	ret = register_kprobes(kps, 2);
-	if (ret < 0) {
-		pr_err("register_kprobes returned %d\n", ret);
-		return ret;
-	}
 
+	KUNIT_EXPECT_EQ(test, 0, register_kprobes(kps, 2));
 	preh_val = 0;
 	posth_val = 0;
-	ret = target(rand1);
+	target(rand1);
 
-	if (preh_val == 0) {
-		pr_err("kprobe pre_handler not called\n");
-		handler_errors++;
-	}
-
-	if (posth_val == 0) {
-		pr_err("kprobe post_handler not called\n");
-		handler_errors++;
-	}
+	KUNIT_EXPECT_NE(test, 0, preh_val);
+	KUNIT_EXPECT_NE(test, 0, posth_val);
 
 	preh_val = 0;
 	posth_val = 0;
-	ret = target2(rand1);
-
-	if (preh_val == 0) {
-		pr_err("kprobe pre_handler2 not called\n");
-		handler_errors++;
-	}
-
-	if (posth_val == 0) {
-		pr_err("kprobe post_handler2 not called\n");
-		handler_errors++;
-	}
+	target2(rand1);
 
+	KUNIT_EXPECT_NE(test, 0, preh_val);
+	KUNIT_EXPECT_NE(test, 0, posth_val);
 	unregister_kprobes(kps, 2);
-	return 0;
-
 }
 
 #ifdef CONFIG_KRETPROBES
@@ -158,10 +109,7 @@ static u32 krph_val;
 
 static int entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
-	if (preemptible()) {
-		handler_errors++;
-		pr_err("kretprobe entry handler is preemptible\n");
-	}
+	KUNIT_EXPECT_FALSE(current_test, preemptible());
 	krph_val = (rand1 / div_factor);
 	return 0;
 }
@@ -170,19 +118,9 @@ static int return_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	unsigned long ret = regs_return_value(regs);
 
-	if (preemptible()) {
-		handler_errors++;
-		pr_err("kretprobe return handler is preemptible\n");
-	}
-	if (ret != (rand1 / div_factor)) {
-		handler_errors++;
-		pr_err("incorrect value in kretprobe handler\n");
-	}
-	if (krph_val == 0) {
-		handler_errors++;
-		pr_err("call to kretprobe entry handler failed\n");
-	}
-
+	KUNIT_EXPECT_FALSE(current_test, preemptible());
+	KUNIT_EXPECT_EQ(current_test, ret, rand1 / div_factor);
+	KUNIT_EXPECT_NE(current_test, krph_val, 0);
 	krph_val = rand1;
 	return 0;
 }
@@ -193,39 +131,21 @@ static struct kretprobe rp = {
 	.kp.symbol_name = "kprobe_target"
 };
 
-static int test_kretprobe(void)
+static void test_kretprobe(struct kunit *test)
 {
-	int ret;
-
-	ret = register_kretprobe(&rp);
-	if (ret < 0) {
-		pr_err("register_kretprobe returned %d\n", ret);
-		return ret;
-	}
-
-	ret = target(rand1);
+	current_test = test;
+	KUNIT_EXPECT_EQ(test, 0, register_kretprobe(&rp));
+	target(rand1);
 	unregister_kretprobe(&rp);
-	if (krph_val != rand1) {
-		pr_err("kretprobe handler not called\n");
-		handler_errors++;
-	}
-
-	return 0;
+	KUNIT_EXPECT_EQ(test, krph_val, rand1);
 }
 
 static int return_handler2(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	unsigned long ret = regs_return_value(regs);
 
-	if (ret != (rand1 / div_factor) + 1) {
-		handler_errors++;
-		pr_err("incorrect value in kretprobe handler2\n");
-	}
-	if (krph_val == 0) {
-		handler_errors++;
-		pr_err("call to kretprobe entry handler failed\n");
-	}
-
+	KUNIT_EXPECT_EQ(current_test, ret, (rand1 / div_factor) + 1);
+	KUNIT_EXPECT_NE(current_test, krph_val, 0);
 	krph_val = rand1;
 	return 0;
 }
@@ -236,78 +156,54 @@ static struct kretprobe rp2 = {
 	.kp.symbol_name = "kprobe_target2"
 };
 
-static int test_kretprobes(void)
+static void test_kretprobes(struct kunit *test)
 {
-	int ret;
 	struct kretprobe *rps[2] = {&rp, &rp2};
 
+	current_test = test;
 	/* addr and flags should be cleard for reusing kprobe. */
 	rp.kp.addr = NULL;
 	rp.kp.flags = 0;
-	ret = register_kretprobes(rps, 2);
-	if (ret < 0) {
-		pr_err("register_kretprobe returned %d\n", ret);
-		return ret;
-	}
+	KUNIT_EXPECT_EQ(test, 0, register_kretprobes(rps, 2));
 
 	krph_val = 0;
-	ret = target(rand1);
-	if (krph_val != rand1) {
-		pr_err("kretprobe handler not called\n");
-		handler_errors++;
-	}
+	target(rand1);
+	KUNIT_EXPECT_EQ(test, krph_val, rand1);
 
 	krph_val = 0;
-	ret = target2(rand1);
-	if (krph_val != rand1) {
-		pr_err("kretprobe handler2 not called\n");
-		handler_errors++;
-	}
+	target2(rand1);
+	KUNIT_EXPECT_EQ(test, krph_val, rand1);
 	unregister_kretprobes(rps, 2);
-	return 0;
 }
 #endif /* CONFIG_KRETPROBES */
 
-int init_test_probes(void)
+static int kprobes_test_init(struct kunit *test)
 {
-	int ret;
-
 	target = kprobe_target;
 	target2 = kprobe_target2;
 
 	do {
 		rand1 = prandom_u32();
 	} while (rand1 <= div_factor);
+	return 0;
+}
 
-	pr_info("started\n");
-	num_tests++;
-	ret = test_kprobe();
-	if (ret < 0)
-		errors++;
-
-	num_tests++;
-	ret = test_kprobes();
-	if (ret < 0)
-		errors++;
-
+static struct kunit_case kprobes_testcases[] = {
+	KUNIT_CASE(test_kprobe),
+	KUNIT_CASE(test_kprobes),
 #ifdef CONFIG_KRETPROBES
-	num_tests++;
-	ret = test_kretprobe();
-	if (ret < 0)
-		errors++;
-
-	num_tests++;
-	ret = test_kretprobes();
-	if (ret < 0)
-		errors++;
-#endif /* CONFIG_KRETPROBES */
+	KUNIT_CASE(test_kretprobe),
+	KUNIT_CASE(test_kretprobes),
+#endif
+	{}
+};
 
-	if (errors)
-		pr_err("BUG: %d out of %d tests failed\n", errors, num_tests);
-	else if (handler_errors)
-		pr_err("BUG: %d error(s) running handlers\n", handler_errors);
-	else
-		pr_info("passed successfully\n");
+static struct kunit_suite kprobes_test_suite = {
+	.name = "kprobes_test",
+	.init = kprobes_test_init,
+	.test_cases = kprobes_testcases,
+};
 
-	return 0;
-}
+kunit_test_suites(&kprobes_test_suite);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2a9b6dcdac4f..6ceb11a43e4c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2080,9 +2080,10 @@ config TEST_DIV64
 	  If unsure, say N.
 
 config KPROBES_SANITY_TEST
-	bool "Kprobes sanity tests"
+	tristate "Kprobes sanity tests"
 	depends on DEBUG_KERNEL
 	depends on KPROBES
+	depends on KUNIT
 	help
 	  This option provides for testing basic kprobes functionality on
 	  boot. Samples of kprobe and kretprobe are inserted and
-- 
2.33.0

[for-next][PATCH 34/40] x86/unwind: Compile kretprobe fixup code only if CONFIG_KRETPROBES=y

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Compile kretprobe related stacktrace entry recovery code and
unwind_state::kr_cur field only when CONFIG_KRETPROBES=y.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/x86/include/asm/unwind.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index fca2e783e3ce..2a1f8734416d 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -16,7 +16,9 @@ struct unwind_state {
 	unsigned long stack_mask;
 	struct task_struct *task;
 	int graph_idx;
+#ifdef CONFIG_KRETPROBES
 	struct llist_node *kr_cur;
+#endif
 	bool error;
 #if defined(CONFIG_UNWINDER_ORC)
 	bool signal, full_regs;
@@ -105,9 +107,13 @@ static inline
 unsigned long unwind_recover_kretprobe(struct unwind_state *state,
 				       unsigned long addr, unsigned long *addr_p)
 {
+#ifdef CONFIG_KRETPROBES
 	return is_kretprobe_trampoline(addr) ?
 		kretprobe_find_ret_addr(state->task, addr_p, &state->kr_cur) :
 		addr;
+#else
+	return addr;
+#endif
 }
 
 /* Recover the return address modified by kretprobe and ftrace_graph. */
-- 
2.33.0

[for-next][PATCH 35/40] arm64: kprobes: Record frame pointer with kretprobe instance

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Record the frame pointer instead of stack address with kretprobe
instance as the identifier on the instance list.
Since arm64 always enable CONFIG_FRAME_POINTER, we can use the
actual frame pointer (x29).

This will allow the stacktrace code to find the original return
address from the FP alone.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/arm64/kernel/probes/kprobes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index e7ad6da980e8..d9dfa82c1f18 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -401,14 +401,14 @@ int __init arch_populate_kprobe_blacklist(void)
 
 void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
 {
-	return (void *)kretprobe_trampoline_handler(regs, (void *)kernel_stack_pointer(regs));
+	return (void *)kretprobe_trampoline_handler(regs, (void *)regs->regs[29]);
 }
 
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)regs->regs[30];
-	ri->fp = (void *)kernel_stack_pointer(regs);
+	ri->fp = (void *)regs->regs[29];
 
 	/* replace return addr (x30) with trampoline */
 	regs->regs[30] = (long)&__kretprobe_trampoline;
-- 
2.33.0

[for-next][PATCH 36/40] arm64: kprobes: Make a frame pointer on __kretprobe_trampoline

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Make a frame pointer (make the x29 register points the
address of pt_regs->regs[29]) on __kretprobe_trampoline.

This frame pointer will be used by the stacktracer when it is
called from the kretprobe handlers. In this case, the stack
tracer will unwind stack to trampoline_probe_handler() and
find the next frame pointer in the stack frame of the
__kretprobe_trampoline().

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/arm64/kernel/probes/kprobes_trampoline.S | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
index 520ee8711db1..9a6499bed58b 100644
--- a/arch/arm64/kernel/probes/kprobes_trampoline.S
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -66,6 +66,9 @@ SYM_CODE_START(__kretprobe_trampoline)
 
 	save_all_base_regs
 
+	/* Setup a frame pointer. */
+	add x29, sp, #S_FP
+
 	mov x0, sp
 	bl trampoline_probe_handler
 	/*
@@ -74,6 +77,7 @@ SYM_CODE_START(__kretprobe_trampoline)
 	 */
 	mov lr, x0
 
+	/* The frame pointer (x29) is restored with other registers. */
 	restore_all_base_regs
 
 	add sp, sp, #PT_REGS_SIZE
-- 
2.33.0

[for-next][PATCH 37/40] arm64: Recover kretprobe modified return address in stacktrace

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Since the kretprobe replaces the function return address with
the kretprobe_trampoline on the stack, stack unwinder shows it
instead of the correct return address.

This checks whether the next return address is the
__kretprobe_trampoline(), and if so, try to find the correct
return address from the kretprobe instance list. For this purpose
this adds 'kr_cur' loop cursor to memorize the current kretprobe
instance.

With this fix, now arm64 can enable
CONFIG_ARCH_CORRECT_STACKTRACE_ON_KRETPROBE, and pass the
kprobe self tests.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/arm64/Kconfig                  | 1 +
 arch/arm64/include/asm/stacktrace.h | 4 ++++
 arch/arm64/kernel/stacktrace.c      | 7 +++++++
 3 files changed, 12 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5c7ae4c3954b..edde5171ffb2 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -11,6 +11,7 @@ config ARM64
 	select ACPI_PPTT if ACPI
 	select ARCH_HAS_DEBUG_WX
 	select ARCH_BINFMT_ELF_STATE
+	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 8aebc00c1718..a4e046ef4568 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -9,6 +9,7 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/types.h>
+#include <linux/llist.h>
 
 #include <asm/memory.h>
 #include <asm/ptrace.h>
@@ -59,6 +60,9 @@ struct stackframe {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	int graph;
 #endif
+#ifdef CONFIG_KRETPROBES
+	struct llist_node *kr_cur;
+#endif
 };
 
 extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 8982a2b78acf..c30624fff6ac 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -41,6 +41,9 @@ void start_backtrace(struct stackframe *frame, unsigned long fp,
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	frame->graph = 0;
 #endif
+#ifdef CONFIG_KRETPROBES
+	frame->kr_cur = NULL;
+#endif
 
 	/*
 	 * Prime the first unwind.
@@ -129,6 +132,10 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 		frame->pc = ret_stack->ret;
 	}
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+#ifdef CONFIG_KRETPROBES
+	if (is_kretprobe_trampoline(frame->pc))
+		frame->pc = kretprobe_find_ret_addr(tsk, (void *)frame->fp, &frame->kr_cur);
+#endif
 
 	frame->pc = ptrauth_strip_insn_pac(frame->pc);
 
-- 
2.33.0

[for-next][PATCH 38/40] ARM: clang: Do not rely on lr register for stacktrace

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Currently the stacktrace on clang compiled arm kernel uses the 'lr'
register to find the first frame address from pt_regs. However, that
is wrong after calling another function, because the 'lr' register
is used by 'bl' instruction and never be recovered.

As same as gcc arm kernel, directly use the frame pointer (r11) of
the pt_regs to find the first frame address.

Note that this fixes kretprobe stacktrace issue only with
CONFIG_UNWINDER_FRAME_POINTER=y. For the CONFIG_UNWINDER_ARM,
we need another fix.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/arm/kernel/stacktrace.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 76ea4178a55c..db798eac7431 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -54,8 +54,7 @@ int notrace unwind_frame(struct stackframe *frame)
 
 	frame->sp = frame->fp;
 	frame->fp = *(unsigned long *)(fp);
-	frame->pc = frame->lr;
-	frame->lr = *(unsigned long *)(fp + 4);
+	frame->pc = *(unsigned long *)(fp + 4);
 #else
 	/* check current frame pointer is within bounds */
 	if (fp < low + 12 || fp > high - 4)
-- 
2.33.0

[for-next][PATCH 39/40] ARM: kprobes: Make a frame pointer on __kretprobe_trampoline

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Currently kretprobe on ARM just fills r0-r11 of pt_regs, but
that is not enough for the stacktrace. Moreover, from the user
kretprobe handler, stacktrace needs a frame pointer on the
__kretprobe_trampoline.

This adds a frame pointer on __kretprobe_trampoline for both gcc
and clang case. Those have different frame pointer so we need
different but similar stack on pt_regs.

Gcc makes the frame pointer (fp) to point the 'pc' address of
the {fp, ip (=sp), lr, pc}, this means {r11, r13, r14, r15}.
Thus if we save the r11 (fp) on pt_regs->r12, we can make this
set on the end of pt_regs.

On the other hand, Clang makes the frame pointer to point the
'fp' address of {fp, lr} on stack. Since the next to the
pt_regs->lr is pt_regs->sp, I reused the pair of pt_regs->fp
and pt_regs->ip.
So this stores the 'lr' on pt_regs->ip and make the fp to point
pt_regs->fp.

For both cases, saves __kretprobe_trampoline address to
pt_regs->lr, so that the stack tracer can identify this frame
pointer has been made by the __kretprobe_trampoline.

Note that if the CONFIG_FRAME_POINTER is not set, this keeps
fp as is.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/arm/probes/kprobes/core.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 95f23b47ba27..4848404ba51b 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -368,16 +368,36 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 /*
  * When a retprobed function returns, trampoline_handler() is called,
  * calling the kretprobe's handler. We construct a struct pt_regs to
- * give a view of registers r0-r11 to the user return-handler.  This is
- * not a complete pt_regs structure, but that should be plenty sufficient
- * for kretprobe handlers which should normally be interested in r0 only
- * anyway.
+ * give a view of registers r0-r11, sp, lr, and pc to the user
+ * return-handler. This is not a complete pt_regs structure, but that
+ * should be enough for stacktrace from the return handler with or
+ * without pt_regs.
  */
 void __naked __kprobes __kretprobe_trampoline(void)
 {
 	__asm__ __volatile__ (
+#ifdef CONFIG_FRAME_POINTER
+		"ldr	lr, =__kretprobe_trampoline	\n\t"
+	/* __kretprobe_trampoline makes a framepointer on pt_regs. */
+#ifdef CONFIG_CC_IS_CLANG
+		"stmdb	sp, {sp, lr, pc}	\n\t"
+		"sub	sp, sp, #12		\n\t"
+		/* In clang case, pt_regs->ip = lr. */
+		"stmdb	sp!, {r0 - r11, lr}	\n\t"
+		/* fp points regs->r11 (fp) */
+		"add	fp, sp,	#44		\n\t"
+#else /* !CONFIG_CC_IS_CLANG */
+		/* In gcc case, pt_regs->ip = fp. */
+		"stmdb	sp, {fp, sp, lr, pc}	\n\t"
 		"sub	sp, sp, #16		\n\t"
 		"stmdb	sp!, {r0 - r11}		\n\t"
+		/* fp points regs->r15 (pc) */
+		"add	fp, sp, #60		\n\t"
+#endif /* CONFIG_CC_IS_CLANG */
+#else /* !CONFIG_FRAME_POINTER */
+		"sub	sp, sp, #16		\n\t"
+		"stmdb	sp!, {r0 - r11}		\n\t"
+#endif /* CONFIG_FRAME_POINTER */
 		"mov	r0, sp			\n\t"
 		"bl	trampoline_handler	\n\t"
 		"mov	lr, r0			\n\t"
-- 
2.33.0

[for-next][PATCH 40/40] ARM: Recover kretprobe modified return address in stacktrace

[Steven Rostedt]

From: Masami Hiramatsu <mhiramat@kernel.org>

Since the kretprobe replaces the function return address with
the kretprobe_trampoline on the stack, arm unwinder shows it
instead of the correct return address.

This finds the correct return address from the per-task
kretprobe_instances list and verify it is in between the
caller fp and callee fp.

Note that this supports both GCC and clang if CONFIG_FRAME_POINTER=y
and CONFIG_ARM_UNWIND=n. For the ARM unwinder, this is still
not working correctly.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/arm/Kconfig                  |  1 +
 arch/arm/include/asm/stacktrace.h |  9 +++++++++
 arch/arm/kernel/return_address.c  |  4 ++++
 arch/arm/kernel/stacktrace.c      | 14 ++++++++++++++
 4 files changed, 28 insertions(+)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index fc196421b2ce..bb4f1872967c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -3,6 +3,7 @@ config ARM
 	bool
 	default y
 	select ARCH_32BIT_OFF_T
+	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE if HAVE_KRETPROBES && FRAME_POINTER && !ARM_UNWIND
 	select ARCH_HAS_BINFMT_FLAT
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE
diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h
index 2d76a2e29f05..8f54f9ad8a9b 100644
--- a/arch/arm/include/asm/stacktrace.h
+++ b/arch/arm/include/asm/stacktrace.h
@@ -3,6 +3,7 @@
 #define __ASM_STACKTRACE_H
 
 #include <asm/ptrace.h>
+#include <linux/llist.h>
 
 struct stackframe {
 	/*
@@ -13,6 +14,10 @@ struct stackframe {
 	unsigned long sp;
 	unsigned long lr;
 	unsigned long pc;
+#ifdef CONFIG_KRETPROBES
+	struct llist_node *kr_cur;
+	struct task_struct *tsk;
+#endif
 };
 
 static __always_inline
@@ -22,6 +27,10 @@ void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame)
 		frame->sp = regs->ARM_sp;
 		frame->lr = regs->ARM_lr;
 		frame->pc = regs->ARM_pc;
+#ifdef CONFIG_KRETPROBES
+		frame->kr_cur = NULL;
+		frame->tsk = current;
+#endif
 }
 
 extern int unwind_frame(struct stackframe *frame);
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index 7b42ac010fdf..00c11579406c 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -42,6 +42,10 @@ void *return_address(unsigned int level)
 	frame.sp = current_stack_pointer;
 	frame.lr = (unsigned long)__builtin_return_address(0);
 	frame.pc = (unsigned long)return_address;
+#ifdef CONFIG_KRETPROBES
+	frame.kr_cur = NULL;
+	frame.tsk = current;
+#endif
 
 	walk_stackframe(&frame, save_return_addr, &data);
 
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index db798eac7431..75e905508f27 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/export.h>
+#include <linux/kprobes.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/stacktrace.h>
@@ -65,6 +66,11 @@ int notrace unwind_frame(struct stackframe *frame)
 	frame->sp = *(unsigned long *)(fp - 8);
 	frame->pc = *(unsigned long *)(fp - 4);
 #endif
+#ifdef CONFIG_KRETPROBES
+	if (is_kretprobe_trampoline(frame->pc))
+		frame->pc = kretprobe_find_ret_addr(frame->tsk,
+					(void *)frame->fp, &frame->kr_cur);
+#endif
 
 	return 0;
 }
@@ -156,6 +162,10 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 		frame.lr = (unsigned long)__builtin_return_address(0);
 		frame.pc = (unsigned long)__save_stack_trace;
 	}
+#ifdef CONFIG_KRETPROBES
+	frame.kr_cur = NULL;
+	frame.tsk = tsk;
+#endif
 
 	walk_stackframe(&frame, save_trace, &data);
 }
@@ -173,6 +183,10 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 	frame.sp = regs->ARM_sp;
 	frame.lr = regs->ARM_lr;
 	frame.pc = regs->ARM_pc;
+#ifdef CONFIG_KRETPROBES
+	frame.kr_cur = NULL;
+	frame.tsk = current;
+#endif
 
 	walk_stackframe(&frame, save_trace, &data);
 }
-- 
2.33.0