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, 40 insertions, 50 deletions

diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 5eb9b598f4e9..13c8e6773892 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -9,6 +9,7 @@
 #include <linux/rethook.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
+#include <linux/smp.h>
 
 /* Return hook list (shadow stack by list) */
 
@@ -36,21 +37,7 @@ void rethook_flush_task(struct task_struct *tk)
 static void rethook_free_rcu(struct rcu_head *head)
 {
 	struct rethook *rh = container_of(head, struct rethook, rcu);
-	struct rethook_node *rhn;
-	struct freelist_node *node;
-	int count = 1;
-
-	node = rh->pool.head;
-	while (node) {
-		rhn = container_of(node, struct rethook_node, freelist);
-		node = node->next;
-		kfree(rhn);
-		count++;
-	}
-
-	/* The rh->ref is the number of pooled node + 1 */
-	if (refcount_sub_and_test(count, &rh->ref))
-		kfree(rh);
+	objpool_fini(&rh->pool);
 }
 
 /**
@@ -83,54 +70,62 @@ void rethook_free(struct rethook *rh)
 	call_rcu(&rh->rcu, rethook_free_rcu);
 }
 
+static int rethook_init_node(void *nod, void *context)
+{
+	struct rethook_node *node = nod;
+
+	node->rethook = context;
+	return 0;
+}
+
+static int rethook_fini_pool(struct objpool_head *head, void *context)
+{
+	kfree(context);
+	return 0;
+}
+
 /**
  * rethook_alloc() - Allocate struct rethook.
  * @data: a data to pass the @handler when hooking the return.
- * @handler: the return hook callback function.
+ * @handler: the return hook callback function, must NOT be NULL
+ * @size: node size: rethook node and additional data
+ * @num: number of rethook nodes to be preallocated
  *
  * Allocate and initialize a new rethook with @data and @handler.
- * Return NULL if memory allocation fails or @handler is NULL.
+ * Return pointer of new rethook, or error codes for failures.
+ *
  * Note that @handler == NULL means this rethook is going to be freed.
  */
-struct rethook *rethook_alloc(void *data, rethook_handler_t handler)
+struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
+			      int size, int num)
 {
-	struct rethook *rh = kzalloc(sizeof(struct rethook), GFP_KERNEL);
+	struct rethook *rh;
 
-	if (!rh || !handler) {
-		kfree(rh);
-		return NULL;
-	}
+	if (!handler || num <= 0 || size < sizeof(struct rethook_node))
+		return ERR_PTR(-EINVAL);
+
+	rh = kzalloc(sizeof(struct rethook), GFP_KERNEL);
+	if (!rh)
+		return ERR_PTR(-ENOMEM);
 
 	rh->data = data;
 	rh->handler = handler;
-	rh->pool.head = NULL;
-	refcount_set(&rh->ref, 1);
 
+	/* initialize the objpool for rethook nodes */
+	if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
+			 rethook_init_node, rethook_fini_pool)) {
+		kfree(rh);
+		return ERR_PTR(-ENOMEM);
+	}
 	return rh;
 }
 
-/**
- * rethook_add_node() - Add a new node to the rethook.
- * @rh: the struct rethook.
- * @node: the struct rethook_node to be added.
- *
- * Add @node to @rh. User must allocate @node (as a part of user's
- * data structure.) The @node fields are initialized in this function.
- */
-void rethook_add_node(struct rethook *rh, struct rethook_node *node)
-{
-	node->rethook = rh;
-	freelist_add(&node->freelist, &rh->pool);
-	refcount_inc(&rh->ref);
-}
-
 static void free_rethook_node_rcu(struct rcu_head *head)
 {
 	struct rethook_node *node = container_of(head, struct rethook_node, rcu);
+	struct rethook *rh = node->rethook;
 
-	if (refcount_dec_and_test(&node->rethook->ref))
-		kfree(node->rethook);
-	kfree(node);
+	objpool_drop(node, &rh->pool);
 }
 
 /**
@@ -145,7 +140,7 @@ void rethook_recycle(struct rethook_node *node)
 	lockdep_assert_preemption_disabled();
 
 	if (likely(READ_ONCE(node->rethook->handler)))
-		freelist_add(&node->freelist, &node->rethook->pool);
+		objpool_push(node, &node->rethook->pool);
 	else
 		call_rcu(&node->rcu, free_rethook_node_rcu);
 }
@@ -161,7 +156,6 @@ NOKPROBE_SYMBOL(rethook_recycle);
 struct rethook_node *rethook_try_get(struct rethook *rh)
 {
 	rethook_handler_t handler = READ_ONCE(rh->handler);
-	struct freelist_node *fn;
 
 	lockdep_assert_preemption_disabled();
 
@@ -178,11 +172,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
 	if (unlikely(!rcu_is_watching()))
 		return NULL;
 
-	fn = freelist_try_get(&rh->pool);
-	if (!fn)
-		return NULL;
-
-	return container_of(fn, struct rethook_node, freelist);
+	return (struct rethook_node *)objpool_pop(&rh->pool);
 }
 NOKPROBE_SYMBOL(rethook_try_get);