badpage: ratelimit print_bad_pte and bad_page

print_bad_pte() and bad_page() might each need ratelimiting - especially
for their dump_stacks, almost never of interest, yet not quite
dispensible.  Correlating corruption across neighbouring entries can be
very helpful, so allow a burst of 60 reports before keeping quiet for the
remainder of that minute (or allow a steady drip of one report per
second).

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 48 insertions, 1 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 0f9abbaf618c..b12888c1b4e3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -383,6 +383,29 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
         pmd_t *pmd = pmd_offset(pud, addr);
         struct address_space *mapping;
         pgoff_t index;
+        static unsigned long resume;
+        static unsigned long nr_shown;
+        static unsigned long nr_unshown;
+
+        /*
+         * Allow a burst of 60 reports, then keep quiet for that minute;
+         * or allow a steady drip of one report per second.
+         */
+        if (nr_shown == 60) {
+                if (time_before(jiffies, resume)) {
+                        nr_unshown++;
+                        return;
+                }
+                if (nr_unshown) {
+                        printk(KERN_EMERG
+                                "Bad page map: %lu messages suppressed\n",
+                                nr_unshown);
+                        nr_unshown = 0;
+                }
+                nr_shown = 0;
+        }
+        if (nr_shown++ == 0)
+                resume = jiffies + 60 * HZ;
 
         mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
         index = linear_page_index(vma, addr);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 755c99a0ac71..d1a80f652c6f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -223,6 +223,30 @@ static inline int bad_range(struct zone *zone, struct page *page)
 
 static void bad_page(struct page *page)
 {
+        static unsigned long resume;
+        static unsigned long nr_shown;
+        static unsigned long nr_unshown;
+
+        /*
+         * Allow a burst of 60 reports, then keep quiet for that minute;
+         * or allow a steady drip of one report per second.
+         */
+        if (nr_shown == 60) {
+                if (time_before(jiffies, resume)) {
+                        nr_unshown++;
+                        goto out;
+                }
+                if (nr_unshown) {
+                        printk(KERN_EMERG
+                                "Bad page state: %lu messages suppressed\n",
+                                nr_unshown);
+                        nr_unshown = 0;
+                }
+                nr_shown = 0;
+        }
+        if (nr_shown++ == 0)
+                resume = jiffies + 60 * HZ;
+
         printk(KERN_EMERG "Bad page state in process %s  pfn:%05lx\n",
                 current->comm, page_to_pfn(page));
         printk(KERN_EMERG
@@ -232,7 +256,7 @@ static void bad_page(struct page *page)
         printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n");
 
         dump_stack();
-
+out:
         /* Leave bad fields for debug, except PageBuddy could make trouble */
         __ClearPageBuddy(page);
         add_taint(TAINT_BAD_PAGE);