uprobes: Introduce MMF_HAS_UPROBES

Add the new MMF_HAS_UPROBES flag. It is set by install_breakpoint()
and it is copied by dup_mmap(), uprobe_pre_sstep_notifier() checks
it to avoid the slow path if the task was never probed. Perhaps it
makes sense to check it in valid_vma(is_register => false) as well.

This needs the new dup_mmap()->uprobe_dup_mmap() hook. We can't use
uprobe_reset_state() or put MMF_HAS_UPROBES into MMF_INIT_MASK, we
need oldmm->mmap_sem to avoid the race with uprobe_register() or
mmap() from another thread.

Currently we never clear this bit, it can be false-positive after
uprobe_unregister() or uprobe_munmap() or if dup_mmap() hits the
probed VM_DONTCOPY vma. But this is fine correctness-wise and has
no effect unless the task hits the non-uprobe breakpoint.

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

4 files changed, 29 insertions, 1 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b8c86648a2f9..3667c332e61d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -446,6 +446,8 @@ extern int get_dumpable(struct mm_struct *mm);
 #define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
 #define MMF_EXE_FILE_CHANGED	18	/* see prctl_set_mm_exe_file() */
 
+#define MMF_HAS_UPROBES		19	/* might have uprobes */
+
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
 
 struct sighand_struct {
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 03ae547c1c31..4a37ab153247 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -108,6 +108,7 @@ extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_con
 extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_mmap(struct vm_area_struct *vma);
 extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
 extern void uprobe_free_utask(struct task_struct *t);
 extern void uprobe_copy_process(struct task_struct *t);
 extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
@@ -138,6 +139,10 @@ static inline void
 uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
 }
+static inline void
+uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+}
 static inline void uprobe_notify_resume(struct pt_regs *regs)
 {
 }
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 3e2996b809be..33870b17e1dd 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -647,6 +647,7 @@ static int
 install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 			struct vm_area_struct *vma, unsigned long vaddr)
 {
+	bool first_uprobe;
 	int ret;
 
 	/*
@@ -678,7 +679,17 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 		uprobe->flags |= UPROBE_COPY_INSN;
 	}
 
+	/*
+	 * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(),
+	 * the task can hit this breakpoint right after __replace_page().
+	 */
+	first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags);
+	if (first_uprobe)
+		set_bit(MMF_HAS_UPROBES, &mm->flags);
+
 	ret = set_swbp(&uprobe->arch, mm, vaddr);
+	if (ret && first_uprobe)
+		clear_bit(MMF_HAS_UPROBES, &mm->flags);
 
 	return ret;
 }
@@ -1032,6 +1043,9 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon
 	if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
 		return;
 
+	if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags))
+		return;
+
 	/* TODO: unmapping uprobe(s) will need more work */
 }
 
@@ -1142,6 +1156,12 @@ void uprobe_reset_state(struct mm_struct *mm)
 	mm->uprobes_state.xol_area = NULL;
 }
 
+void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+	if (test_bit(MMF_HAS_UPROBES, &oldmm->flags))
+		set_bit(MMF_HAS_UPROBES, &newmm->flags);
+}
+
 /*
  *  - search for a free slot.
  */
@@ -1507,7 +1527,7 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs)
 {
 	struct uprobe_task *utask;
 
-	if (!current->mm)
+	if (!current->mm || !test_bit(MMF_HAS_UPROBES, &current->mm->flags))
 		return 0;
 
 	utask = current->utask;
diff --git a/kernel/fork.c b/kernel/fork.c
index 912b6f6fe5b8..cbb5f9fcd3e8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -353,6 +353,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 	down_write(&oldmm->mmap_sem);
 	flush_cache_dup_mm(oldmm);
+	uprobe_dup_mmap(oldmm, mm);
 	/*
 	 * Not linked in yet - no deadlock potential:
 	 */