diff mbox series

[039/178] mm: page_poison: print page info when corruption is caught

Message ID 20210430055512.z1ThP17xP%akpm@linux-foundation.org (mailing list archive)
State New
Headers show
Series [001/178] arch/ia64/kernel/head.S: remove duplicate include | expand

Commit Message

Andrew Morton April 30, 2021, 5:55 a.m. UTC
From: Sergei Trofimovich <slyfox@gentoo.org>
Subject: mm: page_poison: print page info when corruption is caught

When page_poison detects page corruption it's useful to see who freed a
page recently to have a guess where write-after-free corruption happens.

After this change corruption report has extra page data.
Example report from real corruption (includes only page_pwner part):

    pagealloc: memory corruption
    e00000014cd61d10: 11 00 00 00 00 00 00 00 30 1d d2 ff ff 0f 00 60  ........0......`
    e00000014cd61d20: b0 1d d2 ff ff 0f 00 60 90 fe 1c 00 08 00 00 20  .......`.......
    ...
    CPU: 1 PID: 220402 Comm: cc1plus Not tainted 5.12.0-rc5-00107-g9720c6f59ecf #245
    Hardware name: hp server rx3600, BIOS 04.03 04/08/2008
    ...
    Call Trace:
     [<a000000100015210>] show_stack+0x90/0xc0
     [<a000000101163390>] dump_stack+0x150/0x1c0
     [<a0000001003f1e90>] __kernel_unpoison_pages+0x410/0x440
     [<a0000001003c2460>] get_page_from_freelist+0x1460/0x2ca0
     [<a0000001003c6be0>] __alloc_pages_nodemask+0x3c0/0x660
     [<a0000001003ed690>] alloc_pages_vma+0xb0/0x500
     [<a00000010037deb0>] __handle_mm_fault+0x1230/0x1fe0
     [<a00000010037ef70>] handle_mm_fault+0x310/0x4e0
     [<a00000010005dc70>] ia64_do_page_fault+0x1f0/0xb80
     [<a00000010000ca00>] ia64_leave_kernel+0x0/0x270
    page_owner tracks the page as freed
    page allocated via order 0, migratetype Movable,
      gfp_mask 0x100dca(GFP_HIGHUSER_MOVABLE|__GFP_ZERO), pid 37, ts 8173444098740
     __reset_page_owner+0x40/0x200
     free_pcp_prepare+0x4d0/0x600
     free_unref_page+0x20/0x1c0
     __put_page+0x110/0x1a0
     migrate_pages+0x16d0/0x1dc0
     compact_zone+0xfc0/0x1aa0
     proactive_compact_node+0xd0/0x1e0
     kcompactd+0x550/0x600
     kthread+0x2c0/0x2e0
     call_payload+0x50/0x80

Here we can see that page was freed by page migration but something
managed to write to it afterwards.

[slyfox@gentoo.org: s/dump_page_owner/dump_page/, per Vlastimil]
  Link: https://lkml.kernel.org/r/20210407230800.1086854-1-slyfox@gentoo.org
Link: https://lkml.kernel.org/r/20210404141735.2152984-1-slyfox@gentoo.org
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_poison.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
diff mbox series

Patch

--- a/mm/page_poison.c~mm-page_poison-print-page-owner-info-when-corruption-is-caught
+++ a/mm/page_poison.c
@@ -2,6 +2,7 @@ 
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/mm.h>
+#include <linux/mmdebug.h>
 #include <linux/highmem.h>
 #include <linux/page_ext.h>
 #include <linux/poison.h>
@@ -45,7 +46,7 @@  static bool single_bit_flip(unsigned cha
 	return error && !(error & (error - 1));
 }
 
-static void check_poison_mem(unsigned char *mem, size_t bytes)
+static void check_poison_mem(struct page *page, unsigned char *mem, size_t bytes)
 {
 	static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 10);
 	unsigned char *start;
@@ -70,6 +71,7 @@  static void check_poison_mem(unsigned ch
 	print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, start,
 			end - start + 1, 1);
 	dump_stack();
+	dump_page(page, "pagealloc: corrupted page details");
 }
 
 static void unpoison_page(struct page *page)
@@ -83,7 +85,7 @@  static void unpoison_page(struct page *p
 	 * that is freed to buddy. Thus no extra check is done to
 	 * see if a page was poisoned.
 	 */
-	check_poison_mem(kasan_reset_tag(addr), PAGE_SIZE);
+	check_poison_mem(page, kasan_reset_tag(addr), PAGE_SIZE);
 	kasan_enable_current();
 	kunmap_atomic(addr);
 }