The basic idea is the same as with PTE level: the lock is embedded into
struct page of table's page.
We can't use mm->pmd_huge_pte to store pgtables for THP, since we don't
take mm->page_table_lock anymore. Let's reuse page->lru of table's page
for that.
pgtable_pmd_page_ctor() returns true, if initialization is successful
and false otherwise. Current implementation never fails, but assumption
that constructor can fail will help to port it to -rt where spinlock_t
is rather huge and cannot be embedded into struct page -- dynamic
allocation is required.
Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Tested-by: Alex Thorlton <athorlton@xxxxxxx>
---
include/linux/mm.h | 32 ++++++++++++++++++++++++++++++++
include/linux/mm_types.h | 8 +++++++-
kernel/fork.c | 4 ++--
mm/Kconfig | 3 +++
4 files changed, 44 insertions(+), 3 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b96aac9622..75735f6171 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1294,13 +1294,45 @@ static inline void pgtable_page_dtor(struct page *page)
((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
NULL: pte_offset_kernel(pmd, address))
+#if USE_SPLIT_PMD_PTLOCKS
+
+static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+ return &virt_to_page(pmd)->ptl;
+}
+
+static inline bool pgtable_pmd_page_ctor(struct page *page)
+{
+ spin_lock_init(&page->ptl);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ page->pmd_huge_pte = NULL;
+#endif
+ return true;
+}
+
+static inline void pgtable_pmd_page_dtor(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ VM_BUG_ON(page->pmd_huge_pte);
+#endif
+}
+
+#define pmd_huge_pte(mm, pmd) (virt_to_page(pmd)->pmd_huge_pte)
+
+#else
+
static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
{
return &mm->page_table_lock;
}
+static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; }
+static inline void pgtable_pmd_page_dtor(struct page *page) {}
+
#define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
+#endif
+
static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
{
spinlock_t *ptl = pmd_lockptr(mm, pmd);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 99f19e850d..498a75b96f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -24,6 +24,9 @@
struct address_space;
#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
+/* hugetlb hasn't converted to split locking yet */
+#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \
+ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
/*
* Each physical page in the system has a struct page associated with
@@ -130,6 +133,9 @@ struct page {
struct list_head list; /* slobs list of pages */
struct slab *slab_page; /* slab fields */
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
+ pgtable_t pmd_huge_pte; /* protected by page->ptl */
+#endif
};
/* Remainder is not double word aligned */
@@ -406,7 +412,7 @@ struct mm_struct {
#ifdef CONFIG_MMU_NOTIFIER
struct mmu_notifier_mm *mmu_notifier_mm;
#endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
pgtable_t pmd_huge_pte; /* protected by page_table_lock */
#endif
#ifdef CONFIG_CPUMASK_OFFSTACK
diff --git a/kernel/fork.c b/kernel/fork.c
index afe70530db..943051284f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -560,7 +560,7 @@ static void check_mm(struct mm_struct *mm)
"mm:%p idx:%d val:%ld\n", mm, i, x);
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
VM_BUG_ON(mm->pmd_huge_pte);
#endif
}
@@ -814,7 +814,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
memcpy(mm, oldmm, sizeof(*mm));
mm_init_cpumask(mm);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
#endif
#ifdef CONFIG_NUMA_BALANCING
diff --git a/mm/Kconfig b/mm/Kconfig
index 026771a9b0..89d56e31f9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -214,6 +214,9 @@ config SPLIT_PTLOCK_CPUS
default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
default "4"
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+ boolean
+
#
# support for memory balloon compaction
config BALLOON_COMPACTION
--
1.8.4.rc3
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>