diff options
| author | Andrea Arcangeli <aarcange@redhat.com> | 2011-01-13 15:46:45 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2011-01-13 17:32:41 -0800 |
| commit | e7a00c45f29c0155007aa150bf231a70fa470365 (patch) | |
| tree | 3225a79905dede614ed44e98776cdc6285bbd28a | |
| parent | 4e6af67e970a2ac287739a4c526c857b5bda27ec (diff) | |
| download | op-kernel-dev-e7a00c45f29c0155007aa150bf231a70fa470365.zip op-kernel-dev-e7a00c45f29c0155007aa150bf231a70fa470365.tar.gz | |
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>
| -rw-r--r-- | include/linux/mm_types.h | 3 | ||||
| -rw-r--r-- | kernel/fork.c | 7 |
2 files changed, 10 insertions, 0 deletions
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bb7288a..26bc4e2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -310,6 +310,9 @@ struct mm_struct { #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 1499607..f78f50b 100644 --- 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; |
