[PATCH v7 07/23] mm/ksw: add HWBP pre-allocation

[Jinchao Wang <wangjinchao600@gmail.com>]

Pre-allocate per-CPU hardware breakpoints at init with a place holder
address, which will be retargeted dynamically in kprobe handler.
This avoids allocation in atomic context.

At most max_watch breakpoints are allocated (0 means no limit).

Signed-off-by: Jinchao Wang <wangjinchao600@gmail.com>
---
 mm/kstackwatch/kstackwatch.h | 13 +++++
 mm/kstackwatch/watch.c       | 97 ++++++++++++++++++++++++++++++++++++
 2 files changed, 110 insertions(+)

diff --git a/mm/kstackwatch/kstackwatch.h b/mm/kstackwatch/kstackwatch.h
index 983125d5cf18..4eac1be3b325 100644
--- a/mm/kstackwatch/kstackwatch.h
+++ b/mm/kstackwatch/kstackwatch.h
@@ -2,6 +2,9 @@
 #ifndef _KSTACKWATCH_H
 #define _KSTACKWATCH_H
 
+#include <linux/llist.h>
+#include <linux/percpu.h>
+#include <linux/perf_event.h>
 #include <linux/types.h>
 
 #define MAX_CONFIG_STR_LEN 128
@@ -32,4 +35,14 @@ struct ksw_config {
 // singleton, only modified in kernel.c
 const struct ksw_config *ksw_get_config(void);
 
+/* watch management */
+struct ksw_watchpoint {
+	struct perf_event *__percpu *event;
+	struct perf_event_attr attr;
+	struct llist_node node; // for atomic watch_on and off
+	struct list_head list; // for cpu online and offline
+};
+int ksw_watch_init(void);
+void ksw_watch_exit(void);
+
 #endif /* _KSTACKWATCH_H */
diff --git a/mm/kstackwatch/watch.c b/mm/kstackwatch/watch.c
index cec594032515..1d8e24fede54 100644
--- a/mm/kstackwatch/watch.c
+++ b/mm/kstackwatch/watch.c
@@ -1 +1,98 @@
 // SPDX-License-Identifier: GPL-2.0
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpuhotplug.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/irqflags.h>
+#include <linux/mutex.h>
+#include <linux/printk.h>
+
+#include "kstackwatch.h"
+
+static LLIST_HEAD(free_wp_list);
+static LIST_HEAD(all_wp_list);
+static DEFINE_MUTEX(all_wp_mutex);
+
+static ulong holder;
+bool panic_on_catch;
+module_param(panic_on_catch, bool, 0644);
+MODULE_PARM_DESC(panic_on_catch, "panic immediately on corruption catch");
+
+static void ksw_watch_handler(struct perf_event *bp,
+			      struct perf_sample_data *data,
+			      struct pt_regs *regs)
+{
+	pr_err("========== KStackWatch: Caught stack corruption =======\n");
+	pr_err("config %s\n", ksw_get_config()->user_input);
+	dump_stack();
+	pr_err("=================== KStackWatch End ===================\n");
+
+	if (panic_on_catch)
+		panic("Stack corruption detected");
+}
+
+static int ksw_watch_alloc(void)
+{
+	int max_watch = ksw_get_config()->max_watch;
+	struct ksw_watchpoint *wp;
+	int success = 0;
+	int ret;
+
+	init_llist_head(&free_wp_list);
+
+	//max_watch=0 means at most
+	while (!max_watch || success < max_watch) {
+		wp = kzalloc(sizeof(*wp), GFP_KERNEL);
+		if (!wp)
+			return success > 0 ? success : -EINVAL;
+
+		hw_breakpoint_init(&wp->attr);
+		wp->attr.bp_addr = (ulong)&holder;
+		wp->attr.bp_len = sizeof(ulong);
+		wp->attr.bp_type = HW_BREAKPOINT_W;
+		wp->event = register_wide_hw_breakpoint(&wp->attr,
+							ksw_watch_handler, wp);
+		if (IS_ERR((void *)wp->event)) {
+			ret = PTR_ERR((void *)wp->event);
+			kfree(wp);
+			return success > 0 ? success : ret;
+		}
+		llist_add(&wp->node, &free_wp_list);
+		mutex_lock(&all_wp_mutex);
+		list_add(&wp->list, &all_wp_list);
+		mutex_unlock(&all_wp_mutex);
+		success++;
+	}
+
+	return success;
+}
+
+static void ksw_watch_free(void)
+{
+	struct ksw_watchpoint *wp, *tmp;
+
+	mutex_lock(&all_wp_mutex);
+	list_for_each_entry_safe(wp, tmp, &all_wp_list, list) {
+		list_del(&wp->list);
+		unregister_wide_hw_breakpoint(wp->event);
+		kfree(wp);
+	}
+	mutex_unlock(&all_wp_mutex);
+}
+
+int ksw_watch_init(void)
+{
+	int ret;
+
+	ret = ksw_watch_alloc();
+	if (ret <= 0)
+		return -EBUSY;
+
+
+	return 0;
+}
+
+void ksw_watch_exit(void)
+{
+	ksw_watch_free();
+}
-- 
2.43.0