From 0cc011c576aaa4de505046f7a6c90933d7c749a9 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 31 May 2022 15:29:51 -0700 Subject: lib/list_debug.c: Detect uninitialized lists In some circumstances, attempts are made to add entries to or to remove entries from an uninitialized list. A prime example is amdgpu_bo_vm_destroy(): It is indirectly called from ttm_bo_init_reserved() if that function fails, and tries to remove an entry from a list. However, that list is only initialized in amdgpu_bo_create_vm() after the call to ttm_bo_init_reserved() returned success. This results in crashes such as BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 1479 Comm: chrome Not tainted 5.10.110-15768-g29a72e65dae5 Hardware name: Google Grunt/Grunt, BIOS Google_Grunt.11031.149.0 07/15/2020 RIP: 0010:__list_del_entry_valid+0x26/0x7d ... Call Trace: amdgpu_bo_vm_destroy+0x48/0x8b ttm_bo_init_reserved+0x1d7/0x1e0 amdgpu_bo_create+0x212/0x476 ? amdgpu_bo_user_destroy+0x23/0x23 ? kmem_cache_alloc+0x60/0x271 amdgpu_bo_create_vm+0x40/0x7d amdgpu_vm_pt_create+0xe8/0x24b ... Check if the list's prev and next pointers are NULL to catch such problems. Link: https://lkml.kernel.org/r/20220531222951.92073-1-linux@roeck-us.net Signed-off-by: Guenter Roeck Cc: Steven Rostedt Signed-off-by: Andrew Morton --- lib/list_debug.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/lib/list_debug.c b/lib/list_debug.c index 9daa3fb9d1cd..d98d43f80958 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -20,7 +20,11 @@ bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { - if (CHECK_DATA_CORRUPTION(next->prev != prev, + if (CHECK_DATA_CORRUPTION(prev == NULL, + "list_add corruption. prev is NULL.\n") || + CHECK_DATA_CORRUPTION(next == NULL, + "list_add corruption. next is NULL.\n") || + CHECK_DATA_CORRUPTION(next->prev != prev, "list_add corruption. next->prev should be prev (%px), but was %px. (next=%px).\n", prev, next->prev, next) || CHECK_DATA_CORRUPTION(prev->next != next, @@ -42,7 +46,11 @@ bool __list_del_entry_valid(struct list_head *entry) prev = entry->prev; next = entry->next; - if (CHECK_DATA_CORRUPTION(next == LIST_POISON1, + if (CHECK_DATA_CORRUPTION(next == NULL, + "list_del corruption, %px->next is NULL\n", entry) || + CHECK_DATA_CORRUPTION(prev == NULL, + "list_del corruption, %px->prev is NULL\n", entry) || + CHECK_DATA_CORRUPTION(next == LIST_POISON1, "list_del corruption, %px->next is LIST_POISON1 (%px)\n", entry, LIST_POISON1) || CHECK_DATA_CORRUPTION(prev == LIST_POISON2, -- cgit