uprobes/core: Decrement uprobe count before the pages are unmapped

Uprobes has a callback (uprobe_munmap()) in the unmap path to
maintain the uprobes count.

In the exit path this callback gets called in unlink_file_vma().
However by the time unlink_file_vma() is called, the pages would
have been unmapped (in unmap_vmas()) and the task->rss_stat counts
accounted (in zap_pte_range()).

If the exiting process has probepoints, uprobe_munmap() checks if
the breakpoint instruction was around before decrementing the probe
count.

This results in a file backed page being reread by uprobe_munmap()
and hence it does not find the breakpoint.

This patch fixes this problem by moving the callback to
unmap_single_vma(). Since unmap_single_vma() may not unmap the
complete vma, add start and end parameters to uprobe_munmap().

This bug became apparent courtesy of commit c3f0327f8e9d
("mm: add rss counters consistency check").

Signed-off-by: Srikar Dronamraju <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Ananth N Mavinakayanahalli <[e-mail]>
Cc: Jim Keniston <[e-mail]>
Cc: Linux-mm <[e-mail]>
Cc: Oleg Nesterov <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Christoph Hellwig <[e-mail]>
Cc: Steven Rostedt <[e-mail]>
Cc: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Masami Hiramatsu <[e-mail]>
Cc: Anton Arapov <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

include/linux/uprobes.h

···
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 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);
+extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 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);
···
 {
 	return 0;
 }
-static inline void uprobe_munmap(struct vm_area_struct *vma)
+static inline void
+uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
 }
 static inline void uprobe_notify_resume(struct pt_regs *regs)

kernel/events/uprobes.c

···
 /*
  * Called in context of a munmap of a vma.
  */
-void uprobe_munmap(struct vm_area_struct *vma)
+void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
 	struct list_head tmp_list;
 	struct uprobe *uprobe, *u;
···
 		list_del(&uprobe->pending_list);
 		vaddr = vma_address(vma, uprobe->offset);
 
-		if (vaddr >= vma->vm_start && vaddr < vma->vm_end) {
+		if (vaddr >= start && vaddr < end) {
 			/*
 			 * An unregister could have removed the probe before
 			 * unmap. So check before we decrement the count.

mm/memory.c

···
 	if (end <= vma->vm_start)
 		return;
 
+	if (vma->vm_file)
+		uprobe_munmap(vma, start, end);
+
 	if (vma->vm_flags & VM_ACCOUNT)
 		*nr_accounted += (end - start) >> PAGE_SHIFT;
 

mm/mmap.c

···
 		mutex_lock(&mapping->i_mmap_mutex);
 		__remove_shared_vm_struct(vma, file, mapping);
 		mutex_unlock(&mapping->i_mmap_mutex);
-		uprobe_munmap(vma);
 	}
 }
 
···
 		mapping = file->f_mapping;
 		if (!(vma->vm_flags & VM_NONLINEAR)) {
 			root = &mapping->i_mmap;
-			uprobe_munmap(vma);
+			uprobe_munmap(vma, vma->vm_start, vma->vm_end);
 
 			if (adjust_next)
-				uprobe_munmap(next);
+				uprobe_munmap(next, next->vm_start,
+							next->vm_end);
 		}
 
 		mutex_lock(&mapping->i_mmap_mutex);
···
 
 	if (remove_next) {
 		if (file) {
-			uprobe_munmap(next);
+			uprobe_munmap(next, next->vm_start, next->vm_end);
 			fput(file);
 			if (next->vm_flags & VM_EXECUTABLE)
 				removed_exe_file_vma(mm);