The vmalloc() code uses vmalloc_sync_all() to synchronize changes to
the global reference kernel PGD to task PGDs in certain rare cases,
like register_die_notifier().

This use seems to be somewhat questionable, as most other vmalloc
page table fixups are vmalloc_fault() driven, but nevertheless
it's there and it's using the pgd_list.

But we don't need the global list, as we can walk the task list
under RCU.

Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Brian Gerst <[email protected]>
Cc: Denys Vlasenko <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Waiman Long <[email protected]>
Cc: [email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
 arch/x86/mm/fault.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f890f5463ac1..9322d5ad3811 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -14,6 +14,7 @@
 #include <linux/prefetch.h>            /* prefetchw                    */
 #include <linux/context_tracking.h>    /* exception_enter(), ...       */
 #include <linux/uaccess.h>             /* faulthandler_disabled()      */
+#include <linux/oom.h>                 /* find_lock_task_mm(), ...     */
 
 #include <asm/traps.h>                 /* dotraplinkage, ...           */
 #include <asm/pgalloc.h>               /* pgd_*(), ...                 */
@@ -237,24 +238,38 @@ void vmalloc_sync_all(void)
        for (address = VMALLOC_START & PMD_MASK;
             address >= TASK_SIZE && address < FIXADDR_TOP;
             address += PMD_SIZE) {
-               struct page *page;
 
+               struct task_struct *g;
+
+               rcu_read_lock(); /* Task list walk */
                spin_lock(&pgd_lock);
-               list_for_each_entry(page, &pgd_list, lru) {
+
+               for_each_process(g) {
+                       struct task_struct *p;
+                       struct mm_struct *mm;
                        spinlock_t *pgt_lock;
-                       pmd_t *ret;
+                       pmd_t *pmd_ret;
+
+                       p = find_lock_task_mm(g);
+                       if (!p)
+                               continue;
 
-                       /* the pgt_lock only for Xen */
-                       pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+                       mm = p->mm;
 
+                       /* The pgt_lock is only used on Xen: */
+                       pgt_lock = &mm->page_table_lock;
                        spin_lock(pgt_lock);
-                       ret = vmalloc_sync_one(page_address(page), address);
+                       pmd_ret = vmalloc_sync_one(mm->pgd, address);
                        spin_unlock(pgt_lock);
 
-                       if (!ret)
+                       task_unlock(p);
+
+                       if (!pmd_ret)
                                break;
                }
+
                spin_unlock(&pgd_lock);
+               rcu_read_unlock();
        }
 }
 
-- 
2.1.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to