[for-next][PATCH 0/3] tracing: Updates for v6.15

[for-next][PATCH 0/3] tracing: Updates for v6.15

[Steven Rostedt]

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

Head SHA1: 77feaf4a2efb078f4f8c703dce5918c0ce08b7e9


Masami Hiramatsu (Google) (2):
      mm/memblock: Add reserved memory release function
      tracing: Freeable reserved ring buffer

Steven Rostedt (1):
      tracing: Add traceoff_after_boot option

----
 Documentation/admin-guide/kernel-parameters.txt |  9 ++++
 include/linux/mm.h                              |  1 +
 kernel/trace/trace.c                            | 24 ++++++++-
 kernel/trace/trace.h                            |  1 +
 mm/memblock.c                                   | 66 ++++++++++++++++++++-----
 5 files changed, 88 insertions(+), 13 deletions(-)

[for-next][PATCH 1/3] tracing: Add traceoff_after_boot option

[Steven Rostedt]

From: Steven Rostedt <rostedt@goodmis.org>

Sometimes tracing is used to debug issues during the boot process. Since
the trace buffer has a limited amount of storage, it may be prudent to
disable tracing after the boot is finished, otherwise the critical
information may be overwritten.  With this option, the main tracing buffer
will be turned off at the end of the boot process.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Borislav Petkov <bp@alien8.de>
Link: https://lore.kernel.org/20250208103017.48a7ec83@batman.local.home
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  9 +++++++++
 kernel/trace/trace.c                            | 11 +++++++++++
 2 files changed, 20 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index fb8752b42ec8..e8ca4eabd152 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -7279,6 +7279,15 @@
 			See also "Event triggers" in Documentation/trace/events.rst
 
 
+	traceoff_after_boot
+			[FTRACE] Sometimes tracing is used to debug issues
+			during the boot process. Since the trace buffer has a
+			limited amount of storage, it may be prudent to
+			disable tracing after the boot is finished, otherwise
+			the critical information may be overwritten.  With this
+			option, the main tracing buffer will be turned off at
+			the end of the boot process.
+
 	traceoff_on_warning
 			[FTRACE] enable this option to disable tracing when a
 			warning is hit. This turns off "tracing_on". Tracing can
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0e6d517e74e0..61458d8c3a61 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -87,6 +87,7 @@ void __init disable_tracing_selftest(const char *reason)
 static struct trace_iterator *tracepoint_print_iter;
 int tracepoint_printk;
 static bool tracepoint_printk_stop_on_boot __initdata;
+static bool traceoff_after_boot __initdata;
 static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key);
 
 /* For tracers that don't implement custom flags */
@@ -330,6 +331,13 @@ static int __init set_tracepoint_printk_stop(char *str)
 }
 __setup("tp_printk_stop_on_boot", set_tracepoint_printk_stop);
 
+static int __init set_traceoff_after_boot(char *str)
+{
+	traceoff_after_boot = true;
+	return 1;
+}
+__setup("traceoff_after_boot", set_traceoff_after_boot);
+
 unsigned long long ns2usecs(u64 nsec)
 {
 	nsec += 500;
@@ -10704,6 +10712,9 @@ __init static int late_trace_init(void)
 		tracepoint_printk = 0;
 	}
 
+	if (traceoff_after_boot)
+		tracing_off();
+
 	tracing_set_default_clock();
 	clear_boot_tracer();
 	return 0;
-- 
2.47.2

[for-next][PATCH 2/3] mm/memblock: Add reserved memory release function

[Steven Rostedt]

From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>

Add reserve_mem_release_by_name() to release a reserved memory region
with a given name. This allows us to release reserved memory which is
defined by kernel cmdline, after boot.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: linux-mm@kvack.org
Link: https://lore.kernel.org/173989133862.230693.14094993331347437600.stgit@devnote2
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/mm.h |  1 +
 mm/memblock.c      | 66 +++++++++++++++++++++++++++++++++++++---------
 2 files changed, 55 insertions(+), 12 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7b1068ddcbb7..1ee9e7447485 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4123,6 +4123,7 @@ void vma_pgtable_walk_begin(struct vm_area_struct *vma);
 void vma_pgtable_walk_end(struct vm_area_struct *vma);
 
 int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size);
+int reserve_mem_release_by_name(const char *name);
 
 #ifdef CONFIG_64BIT
 int do_mseal(unsigned long start, size_t len_in, unsigned long flags);
diff --git a/mm/memblock.c b/mm/memblock.c
index 95af35fd1389..8cd95f60015d 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -16,6 +16,7 @@
 #include <linux/kmemleak.h>
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
+#include <linux/mutex.h>
 
 #include <asm/sections.h>
 #include <linux/io.h>
@@ -2283,6 +2284,7 @@ struct reserve_mem_table {
 };
 static struct reserve_mem_table reserved_mem_table[RESERVE_MEM_MAX_ENTRIES];
 static int reserved_mem_count;
+static DEFINE_MUTEX(reserve_mem_lock);
 
 /* Add wildcard region with a lookup name */
 static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size,
@@ -2296,6 +2298,21 @@ static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size,
 	strscpy(map->name, name);
 }
 
+static struct reserve_mem_table *reserve_mem_find_by_name_nolock(const char *name)
+{
+	struct reserve_mem_table *map;
+	int i;
+
+	for (i = 0; i < reserved_mem_count; i++) {
+		map = &reserved_mem_table[i];
+		if (!map->size)
+			continue;
+		if (strcmp(name, map->name) == 0)
+			return map;
+	}
+	return NULL;
+}
+
 /**
  * reserve_mem_find_by_name - Find reserved memory region with a given name
  * @name: The name that is attached to a reserved memory region
@@ -2309,22 +2326,47 @@ static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size,
 int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size)
 {
 	struct reserve_mem_table *map;
-	int i;
 
-	for (i = 0; i < reserved_mem_count; i++) {
-		map = &reserved_mem_table[i];
-		if (!map->size)
-			continue;
-		if (strcmp(name, map->name) == 0) {
-			*start = map->start;
-			*size = map->size;
-			return 1;
-		}
-	}
-	return 0;
+	guard(mutex)(&reserve_mem_lock);
+	map = reserve_mem_find_by_name_nolock(name);
+	if (!map)
+		return 0;
+
+	*start = map->start;
+	*size = map->size;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(reserve_mem_find_by_name);
 
+/**
+ * reserve_mem_release_by_name - Release reserved memory region with a given name
+ * @name: The name that is attatched to a reserved memory region
+ *
+ * Forcibly release the pages in the reserved memory region so that those memory
+ * can be used as free memory. After released the reserved region size becomes 0.
+ *
+ * Returns: 1 if released or 0 if not found.
+ */
+int reserve_mem_release_by_name(const char *name)
+{
+	char buf[RESERVE_MEM_NAME_SIZE + 12];
+	struct reserve_mem_table *map;
+	void *start, *end;
+
+	guard(mutex)(&reserve_mem_lock);
+	map = reserve_mem_find_by_name_nolock(name);
+	if (!map)
+		return 0;
+
+	start = phys_to_virt(map->start);
+	end = start + map->size - 1;
+	snprintf(buf, sizeof(buf), "reserve_mem:%s", name);
+	free_reserved_area(start, end, 0, buf);
+	map->size = 0;
+
+	return 1;
+}
+
 /*
  * Parse reserve_mem=nn:align:name
  */
-- 
2.47.2

[for-next][PATCH 3/3] tracing: Freeable reserved ring buffer

[Steven Rostedt]

From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>

Make the ring buffer on reserved memory to be freeable. This allows us
to free the trace instance on the reserved memory without changing
cmdline and rebooting. Even if we can not change the kernel cmdline
for security reason, we can release the reserved memory for the ring
buffer as free (available) memory.

For example, boot kernel with reserved memory;
"reserve_mem=20M:2M:trace trace_instance=boot_mapped^traceoff@trace"

~ # free
              total        used        free      shared  buff/cache   available
Mem:        1995548       50544     1927568       14964       17436     1911480
Swap:             0           0           0
~ # rmdir /sys/kernel/tracing/instances/boot_mapped/
[   23.704023] Freeing reserve_mem:trace memory: 20476K
~ # free
              total        used        free      shared  buff/cache   available
Mem:        2016024       41844     1956740       14968       17440     1940572
Swap:             0           0           0

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Mike Rapoport <rppt@kernel.org>
Link: https://lore.kernel.org/173989134814.230693.18199312930337815629.stgit@devnote2
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 13 ++++++++++++-
 kernel/trace/trace.h |  1 +
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 61458d8c3a61..b4bcb85094d9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9292,6 +9292,9 @@ static void free_trace_buffers(struct trace_array *tr)
 #ifdef CONFIG_TRACER_MAX_TRACE
 	free_trace_buffer(&tr->max_buffer);
 #endif
+
+	if (tr->range_addr_start)
+		vunmap((void *)tr->range_addr_start);
 }
 
 static void init_trace_flags_index(struct trace_array *tr)
@@ -9453,6 +9456,7 @@ trace_array_create_systems(const char *name, const char *systems,
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
 	kfree_const(tr->system_names);
+	kfree(tr->range_name);
 	kfree(tr->name);
 	kfree(tr);
 
@@ -9579,6 +9583,11 @@ static int __remove_instance(struct trace_array *tr)
 	free_trace_buffers(tr);
 	clear_tracing_err_log(tr);
 
+	if (tr->range_name) {
+		reserve_mem_release_by_name(tr->range_name);
+		kfree(tr->range_name);
+	}
+
 	for (i = 0; i < tr->nr_topts; i++) {
 		kfree(tr->topts[i].topts);
 	}
@@ -10376,6 +10385,7 @@ __init static void enable_instances(void)
 		bool traceoff = false;
 		char *flag_delim;
 		char *addr_delim;
+		char *rname __free(kfree) = NULL;
 
 		tok = strsep(&curr_str, ",");
 
@@ -10432,6 +10442,7 @@ __init static void enable_instances(void)
 				pr_warn("Failed to map boot instance %s to %s\n", name, tok);
 				continue;
 			}
+			rname = kstrdup(tok, GFP_KERNEL);
 		}
 
 		if (start) {
@@ -10468,7 +10479,7 @@ __init static void enable_instances(void)
 		 */
 		if (start) {
 			tr->flags |= TRACE_ARRAY_FL_BOOT;
-			tr->ref++;
+			tr->range_name = no_free_ptr(rname);
 		}
 
 		while ((tok = strsep(&curr_str, ","))) {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9c21ba45b7af..93b6279d3da4 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -348,6 +348,7 @@ struct trace_array {
 	unsigned int		mapped;
 	unsigned long		range_addr_start;
 	unsigned long		range_addr_size;
+	char			*range_name;
 	long			text_delta;
 	long			data_delta;
 
-- 
2.47.2

Re: [for-next][PATCH 0/3] tracing: Updates for v6.15

[Steven Rostedt]

On Wed, 26 Feb 2025 19:12:35 -0500
Steven Rostedt <rostedt@goodmis.org> wrote:

> Masami Hiramatsu (Google) (2):
>       mm/memblock: Add reserved memory release function
>       tracing: Freeable reserved ring buffer

Masami,

I'm going to revert these two patches from the trace/for-next tree and
rebase them on top of the ring-buffer/for-next, as they conflict, and I
rather not send Linus a pull request that has conflicts between two of my
topic branches.

-- Steve