uprobes: use vm_special_mapping close() functionality

The following KASAN splat was shown:

[   44.505448] ==================================================================                                                                      20:37:27 [3421/145075]
[   44.505455] BUG: KASAN: slab-use-after-free in special_mapping_close+0x9c/0xc8
[   44.505471] Read of size 8 at addr 00000000868dac48 by task sh/1384
[   44.505479]
[   44.505486] CPU: 51 UID: 0 PID: 1384 Comm: sh Not tainted 6.11.0-rc6-next-20240902-dirty #1496
[   44.505503] Hardware name: IBM 3931 A01 704 (z/VM 7.3.0)
[   44.505508] Call Trace:
[   44.505511]  [<000b0324d2f78080>] dump_stack_lvl+0xd0/0x108
[   44.505521]  [<000b0324d2f5435c>] print_address_description.constprop.0+0x34/0x2e0
[   44.505529]  [<000b0324d2f5464c>] print_report+0x44/0x138
[   44.505536]  [<000b0324d1383192>] kasan_report+0xc2/0x140
[   44.505543]  [<000b0324d2f52904>] special_mapping_close+0x9c/0xc8
[   44.505550]  [<000b0324d12c7978>] remove_vma+0x78/0x120
[   44.505557]  [<000b0324d128a2c6>] exit_mmap+0x326/0x750
[   44.505563]  [<000b0324d0ba655a>] __mmput+0x9a/0x370
[   44.505570]  [<000b0324d0bbfbe0>] exit_mm+0x240/0x340
[   44.505575]  [<000b0324d0bc0228>] do_exit+0x548/0xd70
[   44.505580]  [<000b0324d0bc1102>] do_group_exit+0x132/0x390
[   44.505586]  [<000b0324d0bc13b6>] __s390x_sys_exit_group+0x56/0x60
[   44.505592]  [<000b0324d0adcbd6>] do_syscall+0x2f6/0x430
[   44.505599]  [<000b0324d2f78434>] __do_syscall+0xa4/0x170
[   44.505606]  [<000b0324d2f9454c>] system_call+0x74/0x98
[   44.505614]
[   44.505616] Allocated by task 1384:
[   44.505621]  kasan_save_stack+0x40/0x70
[   44.505630]  kasan_save_track+0x28/0x40
[   44.505636]  __kasan_kmalloc+0xa0/0xc0
[   44.505642]  __create_xol_area+0xfa/0x410
[   44.505648]  get_xol_area+0xb0/0xf0
[   44.505652]  uprobe_notify_resume+0x27a/0x470
[   44.505657]  irqentry_exit_to_user_mode+0x15e/0x1d0
[   44.505664]  pgm_check_handler+0x122/0x170
[   44.505670]
[   44.505672] Freed by task 1384:
[   44.505676]  kasan_save_stack+0x40/0x70
[   44.505682]  kasan_save_track+0x28/0x40
[   44.505687]  kasan_save_free_info+0x4a/0x70
[   44.505693]  __kasan_slab_free+0x5a/0x70
[   44.505698]  kfree+0xe8/0x3f0
[   44.505704]  __mmput+0x20/0x370
[   44.505709]  exit_mm+0x240/0x340
[   44.505713]  do_exit+0x548/0xd70
[   44.505718]  do_group_exit+0x132/0x390
[   44.505722]  __s390x_sys_exit_group+0x56/0x60
[   44.505727]  do_syscall+0x2f6/0x430
[   44.505732]  __do_syscall+0xa4/0x170
[   44.505738]  system_call+0x74/0x98

The problem is that uprobe_clear_state() kfree's struct xol_area, which
contains struct vm_special_mapping *xol_mapping. This one is passed to
_install_special_mapping() in xol_add_vma().
__mput reads:

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 */
        exit_mmap(mm);
        ...
}

So uprobe_clear_state() in the beginning free's the memory area
containing the vm_special_mapping data, but exit_mmap() uses this
address later via vma->vm_private_data (which was set in
_install_special_mapping().

Fix this by moving uprobe_clear_state() to uprobes.c and use it as
close() callback.

[usama.anjum@collabora.com: remove unneeded condition]
  Link: https://lkml.kernel.org/r/20240906101825.177490-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20240903073629.2442754-1-svens@linux.ibm.com
Fixes: 223febc6 ("mm: add optional close() to struct vm_special_mapping")
Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
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: 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: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/uprobes.h

@@ -126,7 +126,6 @@ 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

@@ -1482,6 +1482,22 @@ 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;
@@ -1500,6 +1516,7 @@ 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])
@@ -1545,25 +1562,6 @@ 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

@@ -1338,7 +1338,6 @@ 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 */