uprobes: Use percpu_rw_semaphore to fix register/unregister vs dup_mmap() race

This was always racy, but 268720903f87e0b84b161626c4447b81671b5d18
"uprobes: Rework register_for_each_vma() to make it O(n)" should be
blamed anyway, it made everything worse and I didn't notice.

register/unregister call build_map_info() and then do install/remove
breakpoint for every mm which mmaps inode/offset. This can obviously
race with fork()->dup_mmap() in between and we can miss the child.

uprobe_register() could be easily fixed but unregister is much worse,
the new mm inherits "int3" from parent and there is no way to detect
this if uprobe goes away.

So this patch simply adds percpu_down_read/up_read around dup_mmap(),
and percpu_down_write/up_write into register_for_each_vma().

This adds 2 new hooks into dup_mmap() but we can kill uprobe_dup_mmap()
and fold it into uprobe_end_dup_mmap().

Reported-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>

1 files changed, 23 insertions, 3 deletions

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 5ce99cfd2e6..dea7acfbb07 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -33,6 +33,7 @@
 #include <linux/ptrace.h>	/* user_enable_single_step */
 #include <linux/kdebug.h>	/* notifier mechanism */
 #include "../../mm/internal.h"	/* munlock_vma_page */
+#include <linux/percpu-rwsem.h>
 
 #include <linux/uprobes.h>
 
@@ -71,6 +72,8 @@ static struct mutex uprobes_mutex[UPROBES_HASH_SZ];
 static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
 #define uprobes_mmap_hash(v)	(&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
 
+static struct percpu_rw_semaphore dup_mmap_sem;
+
 /*
  * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe
  * events active at this time.  Probably a fine grained per inode count is
@@ -766,10 +769,13 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 	struct map_info *info;
 	int err = 0;
 
+	percpu_down_write(&dup_mmap_sem);
 	info = build_map_info(uprobe->inode->i_mapping,
 					uprobe->offset, is_register);
-	if (IS_ERR(info))
-		return PTR_ERR(info);
+	if (IS_ERR(info)) {
+		err = PTR_ERR(info);
+		goto out;
+	}
 
 	while (info) {
 		struct mm_struct *mm = info->mm;
@@ -799,7 +805,8 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 		mmput(mm);
 		info = free_map_info(info);
 	}
-
+ out:
+	percpu_up_write(&dup_mmap_sem);
 	return err;
 }
 
@@ -1131,6 +1138,16 @@ void uprobe_clear_state(struct mm_struct *mm)
 	kfree(area);
 }
 
+void uprobe_start_dup_mmap(void)
+{
+	percpu_down_read(&dup_mmap_sem);
+}
+
+void uprobe_end_dup_mmap(void)
+{
+	percpu_up_read(&dup_mmap_sem);
+}
+
 void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
 {
 	newmm->uprobes_state.xol_area = NULL;
@@ -1597,6 +1614,9 @@ static int __init init_uprobes(void)
 		mutex_init(&uprobes_mmap_mutex[i]);
 	}
 
+	if (percpu_init_rwsem(&dup_mmap_sem))
+		return -ENOMEM;
+
 	return register_die_notifier(&uprobe_exception_nb);
 }
 module_init(init_uprobes);