ftrace: remove old pointers to mcount

When a mcount pointer is recorded into a table, it is used to add or
remove calls to mcount (replacing them with nops). If the code is removed
via removing a module, the pointers still exist.  At modifying the code
a check is always made to make sure the code being replaced is the code
expected. In-other-words, the code being replaced is compared to what
it is expected to be before being replaced.

There is a very small chance that the code being replaced just happens
to look like code that calls mcount (very small since the call to mcount
is relative). To remove this chance, this patch adds ftrace_release to
allow module unloading to remove the pointers to mcount within the module.

Another change for init calls is made to not trace calls marked with
__init. The tracing can not be started until after init is done anyway.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 41 insertions, 7 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4936489..6b232a2 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -165,10 +165,12 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
 extern void ftrace_init_module(unsigned long *start, unsigned long *end);
+extern void ftrace_release(void *start, unsigned long size);
 #else
 static inline void ftrace_init(void) { }
 static inline void
 ftrace_init_module(unsigned long *start, unsigned long *end) { }
+static inline void ftrace_release(void *start, unsigned long size) { }
 #endif
 
 #endif /* _LINUX_FTRACE_H */
diff --git a/include/linux/init.h b/include/linux/init.h
index 93538b6..27f61f6 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -40,7 +40,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold
+#define __init		__section(.init.text) __cold notrace
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)
diff --git a/kernel/module.c b/kernel/module.c
index d753fd9..7576c2d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1431,6 +1431,9 @@ static void free_module(struct module *mod)
 	/* Module unload stuff */
 	module_unload_free(mod);
 
+	/* release any pointers to mcount in this module */
+	ftrace_release(mod->module_core, mod->core_size);
+
 	/* This may be NULL, but that's OK */
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
@@ -1839,6 +1842,7 @@ static noinline struct module *load_module(void __user *umod,
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+	void *mseg;
 	struct exception_table_entry *extable;
 	mm_segment_t old_fs;
 
@@ -2190,10 +2194,9 @@ static noinline struct module *load_module(void __user *umod,
 #endif
 	}
 
-	if (mcountindex) {
-		void *mseg = (void *)sechdrs[mcountindex].sh_addr;
-		ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size);
-	}
+	/* sechdrs[0].sh_size is always zero */
+	mseg = (void *)sechdrs[mcountindex].sh_addr;
+	ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size);
 
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
@@ -2264,6 +2267,7 @@ static noinline struct module *load_module(void __user *umod,
  cleanup:
 	kobject_del(&mod->mkobj.kobj);
 	kobject_put(&mod->mkobj.kobj);
+	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
 	module_free(mod, mod->module_init);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8affb6d..eadd0ea 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -294,13 +294,37 @@ static inline void ftrace_del_hash(struct dyn_ftrace *node)
 
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
-	/* no locking, only called from kstop_machine */
-
 	rec->ip = (unsigned long)ftrace_free_records;
 	ftrace_free_records = rec;
 	rec->flags |= FTRACE_FL_FREE;
 }
 
+void ftrace_release(void *start, unsigned long size)
+{
+	struct dyn_ftrace *rec;
+	struct ftrace_page *pg;
+	unsigned long s = (unsigned long)start;
+	unsigned long e = s + size;
+	int i;
+
+	if (!start)
+		return;
+
+	/* No interrupt should call this */
+	spin_lock(&ftrace_lock);
+
+	for (pg = ftrace_pages_start; pg; pg = pg->next) {
+		for (i = 0; i < pg->index; i++) {
+			rec = &pg->records[i];
+
+			if ((rec->ip >= s) && (rec->ip < e))
+				ftrace_free_rec(rec);
+		}
+	}
+	spin_unlock(&ftrace_lock);
+
+}
+
 static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
 {
 	struct dyn_ftrace *rec;
@@ -1527,7 +1551,9 @@ static int ftrace_convert_nops(unsigned long *start,
 	p = start;
 	while (p < end) {
 		addr = ftrace_call_adjust(*p++);
+		spin_lock(&ftrace_lock);
 		ftrace_record_ip(addr);
+		spin_unlock(&ftrace_lock);
 		ftrace_shutdown_replenish();
 	}
 
@@ -1541,6 +1567,8 @@ static int ftrace_convert_nops(unsigned long *start,
 
 void ftrace_init_module(unsigned long *start, unsigned long *end)
 {
+	if (start == end)
+		return;
 	ftrace_convert_nops(start, end);
 }