tracing: Have saved_cmdlines arrays all in one allocation

BugLink: https://bugs.launchpad.net/bugs/2097393

[ Upstream commit 0b18c85 ]

The saved_cmdlines have three arrays for mapping PIDs to COMMs:

 - map_pid_to_cmdline[]
 - map_cmdline_to_pid[]
 - saved_cmdlines

The map_pid_to_cmdline[] is PID_MAX_DEFAULT in size and holds the index
into the other arrays. The map_cmdline_to_pid[] is a mapping back to the
full pid as it can be larger than PID_MAX_DEFAULT. And the
saved_cmdlines[] just holds the COMMs associated to the pids.

Currently the map_pid_to_cmdline[] and saved_cmdlines[] are allocated
together (in reality the saved_cmdlines is just in the memory of the
rounding of the allocation of the structure as it is always allocated in
powers of two). The map_cmdline_to_pid[] array is allocated separately.

Since the rounding to a power of two is rather large (it allows for 8000
elements in saved_cmdlines), also include the map_cmdline_to_pid[] array.
(This drops it to 6000 by default, which is still plenty for most use
cases). This saves even more memory as the map_cmdline_to_pid[] array
doesn't need to be allocated.

Link: https://lore.kernel.org/linux-trace-kernel/20240212174011.068211d9@gandalf.local.home/
Link: https://lore.kernel.org/linux-trace-kernel/20240220140703.182330529@goodmis.org

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Mete Durlu <meted@linux.ibm.com>
Fixes: 44dc5c4 ("tracing: Fix wasted memory in saved_cmdlines logic")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Manuel Diewald <manuel.diewald@canonical.com>
Signed-off-by: Koichiro Den <koichiro.den@canonical.com>

Author: rostedt

kernel/trace/trace.c

@@ -2346,6 +2346,10 @@ struct saved_cmdlines_buffer {
 };
 static struct saved_cmdlines_buffer *savedcmd;
 
+/* Holds the size of a cmdline and pid element */
+#define SAVED_CMDLINE_MAP_ELEMENT_SIZE(s)			\
+	(TASK_COMM_LEN + sizeof((s)->map_cmdline_to_pid[0]))
+
 static inline char *get_saved_cmdlines(int idx)
 {
 	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
@@ -2360,7 +2364,6 @@ static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
 {
 	int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
 
-	kfree(s->map_cmdline_to_pid);
 	kmemleak_free(s);
 	free_pages((unsigned long)s, order);
 }
@@ -2373,7 +2376,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
 	int order;
 
 	/* Figure out how much is needed to hold the given number of cmdlines */
-	orig_size = sizeof(*s) + val * TASK_COMM_LEN;
+	orig_size = sizeof(*s) + val * SAVED_CMDLINE_MAP_ELEMENT_SIZE(s);
 	order = get_order(orig_size);
 	size = 1 << (order + PAGE_SHIFT);
 	page = alloc_pages(GFP_KERNEL, order);
@@ -2385,16 +2388,11 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
 	memset(s, 0, sizeof(*s));
 
 	/* Round up to actual allocation */
-	val = (size - sizeof(*s)) / TASK_COMM_LEN;
+	val = (size - sizeof(*s)) / SAVED_CMDLINE_MAP_ELEMENT_SIZE(s);
 	s->cmdline_num = val;
 
-	s->map_cmdline_to_pid = kmalloc_array(val,
-					      sizeof(*s->map_cmdline_to_pid),
-					      GFP_KERNEL);
-	if (!s->map_cmdline_to_pid) {
-		free_saved_cmdlines_buffer(s);
-		return NULL;
-	}
+	/* Place map_cmdline_to_pid array right after saved_cmdlines */
+	s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN];
 
 	s->cmdline_idx = 0;
 	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,