kprobes: kretprobe scalability improvement

kretprobe is using freelist to manage return-instances, but freelist,
as LIFO queue based on singly linked list, scales badly and reduces
the overall throughput of kretprobed routines, especially for high
contention scenarios.

Here's a typical throughput test of sys_prctl (counts in 10 seconds,
measured with perf stat -a -I 10000 -e syscalls:sys_enter_prctl):

OS: Debian 10 X86_64, Linux 6.5rc7 with freelist
HW: XEON 8336C x 2, 64 cores/128 threads, DDR4 3200MT/s

         1T       2T       4T       8T      16T      24T
   24150045 29317964 15446741 12494489 18287272 17708768
        32T      48T      64T      72T      96T     128T
   16200682 13737658 11645677 11269858 10470118  9931051

This patch introduces objpool to replace freelist. objpool is a
high performance queue, which can bring near-linear scalability
to kretprobed routines. Tests of kretprobe throughput show the
biggest ratio as 159x of original freelist. Here's the result:

                  1T         2T         4T         8T        16T
native:     41186213   82336866  164250978  328662645  658810299
freelist:   24150045   29317964   15446741   12494489   18287272
objpool:    23926730   48010314   96125218  191782984  385091769
                 32T        48T        64T        96T       128T
native:   1330338351 1969957941 2512291791 2615754135 2671040914
freelist:   16200682   13737658   11645677   10470118    9931051
objpool:   764481096 1147149781 1456220214 1502109662 1579015050

Testings on 96-core ARM64 output similarly, but with the biggest
ratio up to 448x:

OS: Debian 10 AARCH64, Linux 6.5rc7
HW: Kunpeng-920 96 cores/2 sockets/4 NUMA nodes, DDR4 2933 MT/s

                  1T         2T         4T         8T        16T
native: .   30066096   63569843  126194076  257447289  505800181
freelist:   16152090   11064397   11124068    7215768    5663013
objpool:    13997541   28032100   55726624  110099926  221498787
                 24T        32T        48T        64T        96T
native:    763305277 1015925192 1521075123 2033009392 3021013752
freelist:    5015810    4602893    3766792    3382478    2945292
objpool:   328192025  439439564  668534502  887401381 1319972072

Link: https://lore.kernel.org/all/20231017135654.82270-4-wuqiang.matt@bytedance.com/

Signed-off-by: wuqiang.matt <wuqiang.matt@bytedance.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>

1 files changed, 10 insertions, 18 deletions

diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 3b21f4063258..6890f4fd17fc 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -187,7 +187,7 @@ static void fprobe_init(struct fprobe *fp)
 
 static int fprobe_init_rethook(struct fprobe *fp, int num)
 {
-	int i, size;
+	int size;
 
 	if (num < 0)
 		return -EINVAL;
@@ -205,26 +205,18 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
 	if (size < 0)
 		return -E2BIG;
 
-	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
-	if (!fp->rethook)
-		return -ENOMEM;
-	for (i = 0; i < size; i++) {
-		struct fprobe_rethook_node *node;
-
-		node = kzalloc(sizeof(*node) + fp->entry_data_size, GFP_KERNEL);
-		if (!node) {
-			rethook_free(fp->rethook);
-			fp->rethook = NULL;
-			return -ENOMEM;
-		}
-		rethook_add_node(fp->rethook, &node->node);
-	}
+	/* Initialize rethook */
+	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler,
+				sizeof(struct fprobe_rethook_node), size);
+	if (IS_ERR(fp->rethook))
+		return PTR_ERR(fp->rethook);
+
 	return 0;
 }
 
 static void fprobe_fail_cleanup(struct fprobe *fp)
 {
-	if (fp->rethook) {
+	if (!IS_ERR_OR_NULL(fp->rethook)) {
 		/* Don't need to cleanup rethook->handler because this is not used. */
 		rethook_free(fp->rethook);
 		fp->rethook = NULL;
@@ -379,14 +371,14 @@ int unregister_fprobe(struct fprobe *fp)
 	if (!fprobe_is_registered(fp))
 		return -EINVAL;
 
-	if (fp->rethook)
+	if (!IS_ERR_OR_NULL(fp->rethook))
 		rethook_stop(fp->rethook);
 
 	ret = unregister_ftrace_function(&fp->ops);
 	if (ret < 0)
 		return ret;
 
-	if (fp->rethook)
+	if (!IS_ERR_OR_NULL(fp->rethook))
 		rethook_free(fp->rethook);
 
 	ftrace_free_filter(&fp->ops);