diff mbox series

[Resend] mm: add stackdepot information on page->private for tracking

Message ID 1665107561-23030-1-git-send-email-zhaoyang.huang@unisoc.com (mailing list archive)
State New
Headers show
Series [Resend] mm: add stackdepot information on page->private for tracking | expand

Commit Message

zhaoyang.huang Oct. 7, 2022, 1:52 a.m. UTC 
From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>

Private is vacant for most of Non-LRU pages while the user has explicitly
operation on page->private via set_page_private, I would like introduce
stackdepot information on page->private for a simplified tracking mechanism
which could be help for kernel driver's memory leak.

Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
---
 mm/page_alloc.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

Comments

kernel test robot Oct. 7, 2022, 3 p.m. UTC | #1 
Greeting,

FYI, we noticed the following commit (built with gcc-11):

commit: 795534bb6e5a83f062dcec24c28f17e1d8d03d5b ("[Resend PATCH] mm: add stackdepot information on page->private for tracking")
url: https://github.com/intel-lab-lkp/linux/commits/zhaoyang-huang/mm-add-stackdepot-information-on-page-private-for-tracking/20221007-095337
base: https://git.kernel.org/cgit/linux/kernel/git/akpm/mm.git mm-everything
patch link: https://lore.kernel.org/linux-mm/1665107561-23030-1-git-send-email-zhaoyang.huang@unisoc.com

in testcase: boot

on test machine: qemu-system-x86_64 -enable-kvm -cpu SandyBridge -smp 2 -m 16G

caused below changes (please refer to attached dmesg/kmsg for entire log/backtrace):


+------------------------------------------------------------------------+------------+------------+
|                                                                        | 183de549a0 | 795534bb6e |
+------------------------------------------------------------------------+------------+------------+
| boot_successes                                                         | 14         | 0          |
| boot_failures                                                          | 0          | 12         |
| Kernel_panic-not_syncing:corrupted_stack_end_detected_inside_scheduler | 0          | 12         |
+------------------------------------------------------------------------+------------+------------+


If you fix the issue, kindly add following tag
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Link: https://lore.kernel.org/r/202210072204.cfea59d3-oliver.sang@intel.com


[    1.903497][    T0] Kernel panic - not syncing: corrupted stack end detected inside scheduler
[    1.904137][    T0] CPU: 0 PID: 0 Comm: swapper Not tainted 6.0.0-rc3-00705-g795534bb6e5a #23
[    1.904818][    T0] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-debian-1.16.0-4 04/01/2014
[    1.905608][    T0] Call Trace:
[    1.905941][    T0]  dump_stack_lvl+0x29/0x36
[    1.906284][    T0]  dump_stack+0xd/0x10
[    1.906293][    T0]  panic+0xe2/0x242
[    1.906293][    T0]  schedule_debug+0x1b/0x11d
[    1.906293][    T0]  __schedule+0x1b/0x3cb
[    1.906293][    T0]  ? trace_hardirqs_on+0x3d/0x3f
[    1.906293][    T0]  schedule+0x5f/0x8e
[    1.906293][    T0]  schedule_preempt_disabled+0xe/0x16
[    1.906293][    T0]  rest_init+0xb1/0xbb
[    1.906293][    T0]  arch_call_rest_init+0x8/0x9
[    1.906293][    T0]  start_kernel+0x458/0x466
[    1.906293][    T0]  i386_start_kernel+0x42/0x44
[    1.906293][    T0]  startup_32_smp+0x161/0x170



To reproduce:

        # build kernel
	cd linux
	cp config-6.0.0-rc3-00705-g795534bb6e5a .config
	make HOSTCC=gcc-11 CC=gcc-11 ARCH=i386 olddefconfig prepare modules_prepare bzImage modules
	make HOSTCC=gcc-11 CC=gcc-11 ARCH=i386 INSTALL_MOD_PATH=<mod-install-dir> modules_install
	cd <mod-install-dir>
	find lib/ | cpio -o -H newc --quiet | gzip > modules.cgz


        git clone https://github.com/intel/lkp-tests.git
        cd lkp-tests
        bin/lkp qemu -k <bzImage> -m modules.cgz job-script # job-script is attached in this email

        # if come across any failure that blocks the test,
        # please remove ~/.lkp and /lkp dir to run from a clean state.
diff mbox series

Patch

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e5486d4..b79a503 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -75,6 +75,7 @@ 
 #include <linux/khugepaged.h>
 #include <linux/buffer_head.h>
 #include <linux/delayacct.h>
+#include <linux/stackdepot.h>
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -2464,6 +2465,25 @@  static inline bool should_skip_init(gfp_t flags)
 	return (flags & __GFP_SKIP_ZERO);
 }
 
+#ifdef CONFIG_STACKDEPOT
+static noinline depot_stack_handle_t set_track_prepare(void)
+{
+       depot_stack_handle_t trace_handle;
+       unsigned long entries[16];
+       unsigned int nr_entries;
+
+       nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3);
+       trace_handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT);
+
+       return trace_handle;
+}
+#else
+static inline depot_stack_handle_t set_track_prepare(void)
+{
+       return 0;
+}
+#endif
+
 inline void post_alloc_hook(struct page *page, unsigned int order,
 				gfp_t gfp_flags)
 {
@@ -2471,8 +2491,14 @@  inline void post_alloc_hook(struct page *page, unsigned int order,
 			!should_skip_init(gfp_flags);
 	bool init_tags = init && (gfp_flags & __GFP_ZEROTAGS);
 	int i;
+	depot_stack_handle_t stack_handle = set_track_prepare();
 
-	set_page_private(page, 0);
+	/*
+	 * Don't worry, user will cover private directly without checking
+	 * this field and has ability to trace the page. This also will not
+	 * affect expected state when freeing
+	 */
+	set_page_private(page, stack_handle);
 	set_page_refcounted(page);
 
 	arch_alloc_page(page, order);