thp: add pmd_huge_pte to mm_struct

This increase the size of the mm struct a bit but it is needed to
preallocate one pte for each hugepage so that split_huge_page will not
require a fail path.  Guarantee of success is a fundamental property of
split_huge_page to avoid decrasing swapping reliability and to avoid
adding -ENOMEM fail paths that would otherwise force the hugepage-unaware
VM code to learn rolling back in the middle of its pte mangling operations
(if something we need it to learn handling pmd_trans_huge natively rather
being capable of rollback).  When split_huge_page runs a pte is needed to
succeed the split, to map the newly splitted regular pages with a regular
pte.  This way all existing VM code remains backwards compatible by just
adding a split_huge_page* one liner.  The memory waste of those
preallocated ptes is negligible and so it is worth it.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bb7288a782fde2ff1d19978a7b9cb387476575ba..26bc4e2cd2750aea3695f9f38a8e365716f764ac 100644 (file)
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -309,6 +309,9 @@ struct mm_struct {
 #endif
 #ifdef CONFIG_MMU_NOTIFIER
        struct mmu_notifier_mm *mmu_notifier_mm;
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+       pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
        /* How many tasks sharing this mm are OOM_DISABLE */
        atomic_t oom_disable_count;

diff --git a/kernel/fork.c b/kernel/fork.c
index 1499607e4da290b33309703fc7670b5eeb429a72..f78f50ba6cb2ec943f88ba60b59373c037e8f9c7 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -529,6 +529,9 @@ void __mmdrop(struct mm_struct *mm)
        mm_free_pgd(mm);
        destroy_context(mm);
        mmu_notifier_mm_destroy(mm);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+       VM_BUG_ON(mm->pmd_huge_pte);
+#endif
        free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -669,6 +672,10 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
        mm->token_priority = 0;
        mm->last_interval = 0;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+       mm->pmd_huge_pte = NULL;
+#endif
+
        if (!mm_init(mm, tsk))
                goto fail_nomem;