Revert "uprobes: use vm_special_mapping close() functionality"

This reverts commit 08e28de.

A malicious application can munmap() its "[uprobes]" vma and in this case
xol_mapping.close == uprobe_clear_state() will free the memory which can
be used by another thread, or the same thread when it hits the uprobe bp
afterwards.

Link: https://lkml.kernel.org/r/20240911131320.GA3448@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Author: oleg-nesterov

include/linux/uprobes.h

@@ -126,6 +126,7 @@ extern int uprobe_pre_sstep_notifier(struct pt_regs *regs);
 extern void uprobe_notify_resume(struct pt_regs *regs);
 extern bool uprobe_deny_signal(void);
 extern bool arch_uprobe_skip_sstep(struct arch_uprobe *aup, struct pt_regs *regs);
+extern void uprobe_clear_state(struct mm_struct *mm);
 extern int  arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);
 extern int  arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);

kernel/events/uprobes.c

@@ -1482,22 +1482,6 @@ void * __weak arch_uprobe_trampoline(unsigned long *psize)
 	return &insn;
 }
 
-/*
- * uprobe_clear_state - Free the area allocated for slots.
- */
-static void uprobe_clear_state(const struct vm_special_mapping *sm, struct vm_area_struct *vma)
-{
-	struct xol_area *area = container_of(vma->vm_private_data, struct xol_area, xol_mapping);
-
-	mutex_lock(&delayed_uprobe_lock);
-	delayed_uprobe_remove(NULL, vma->vm_mm);
-	mutex_unlock(&delayed_uprobe_lock);
-
-	put_page(area->pages[0]);
-	kfree(area->bitmap);
-	kfree(area);
-}
-
 static struct xol_area *__create_xol_area(unsigned long vaddr)
 {
 	struct mm_struct *mm = current->mm;
@@ -1516,7 +1500,6 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
 
 	area->xol_mapping.name = "[uprobes]";
 	area->xol_mapping.fault = NULL;
-	area->xol_mapping.close = uprobe_clear_state;
 	area->xol_mapping.pages = area->pages;
 	area->pages[0] = alloc_page(GFP_HIGHUSER);
 	if (!area->pages[0])
@@ -1562,6 +1545,25 @@ static struct xol_area *get_xol_area(void)
 	return area;
 }
 
+/*
+ * uprobe_clear_state - Free the area allocated for slots.
+ */
+void uprobe_clear_state(struct mm_struct *mm)
+{
+	struct xol_area *area = mm->uprobes_state.xol_area;
+
+	mutex_lock(&delayed_uprobe_lock);
+	delayed_uprobe_remove(NULL, mm);
+	mutex_unlock(&delayed_uprobe_lock);
+
+	if (!area)
+		return;
+
+	put_page(area->pages[0]);
+	kfree(area->bitmap);
+	kfree(area);
+}
+
 void uprobe_start_dup_mmap(void)
 {
 	percpu_down_read(&dup_mmap_sem);

kernel/fork.c

@@ -1338,6 +1338,7 @@ static inline void __mmput(struct mm_struct *mm)
 {
 	VM_BUG_ON(atomic_read(&mm->mm_users));
 
+	uprobe_clear_state(mm);
 	exit_aio(mm);
 	ksm_exit(mm);
 	khugepaged_exit(mm); /* must run before exit_mmap */