#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mm_inline.h>
+#include <asm/pgalloc.h>
#include <asm/tlb.h>
/*
return pmd;
}
#endif
+
+/* arch define pte_free_defer in asm/pgalloc.h for its own implementation */
+#ifndef pte_free_defer
+static void pte_free_now(struct rcu_head *head)
+{
+ struct page *page;
+
+ page = container_of(head, struct page, rcu_head);
+ pte_free(NULL /* mm not passed and not used */, (pgtable_t)page);
+}
+
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
+{
+ struct page *page;
+
+ page = pgtable;
+ call_rcu(&page->rcu_head, pte_free_now);
+}
+#endif /* pte_free_defer */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#if defined(CONFIG_GUP_GET_PXX_LOW_HIGH) && \
+ (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RCU))
+/*
+ * See the comment above ptep_get_lockless() in include/linux/pgtable.h:
+ * the barriers in pmdp_get_lockless() cannot guarantee that the value in
+ * pmd_high actually belongs with the value in pmd_low; but holding interrupts
+ * off blocks the TLB flush between present updates, which guarantees that a
+ * successful __pte_offset_map() points to a page from matched halves.
+ */
+static unsigned long pmdp_get_lockless_start(void)
+{
+ unsigned long irqflags;
+
+ local_irq_save(irqflags);
+ return irqflags;
+}
+static void pmdp_get_lockless_end(unsigned long irqflags)
+{
+ local_irq_restore(irqflags);
+}
+#else
+static unsigned long pmdp_get_lockless_start(void) { return 0; }
+static void pmdp_get_lockless_end(unsigned long irqflags) { }
+#endif
+
pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
{
+ unsigned long irqflags;
pmd_t pmdval;
- /* rcu_read_lock() to be added later */
+ rcu_read_lock();
+ irqflags = pmdp_get_lockless_start();
pmdval = pmdp_get_lockless(pmd);
+ pmdp_get_lockless_end(irqflags);
+
if (pmdvalp)
*pmdvalp = pmdval;
if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval)))
}
return __pte_map(&pmdval, addr);
nomap:
- /* rcu_read_unlock() to be added later */
+ rcu_read_unlock();
return NULL;
}
return pte;
}
+/*
+ * pte_offset_map_lock(mm, pmd, addr, ptlp), and its internal implementation
+ * __pte_offset_map_lock() below, is usually called with the pmd pointer for
+ * addr, reached by walking down the mm's pgd, p4d, pud for addr: either while
+ * holding mmap_lock or vma lock for read or for write; or in truncate or rmap
+ * context, while holding file's i_mmap_lock or anon_vma lock for read (or for
+ * write). In a few cases, it may be used with pmd pointing to a pmd_t already
+ * copied to or constructed on the stack.
+ *
+ * When successful, it returns the pte pointer for addr, with its page table
+ * kmapped if necessary (when CONFIG_HIGHPTE), and locked against concurrent
+ * modification by software, with a pointer to that spinlock in ptlp (in some
+ * configs mm->page_table_lock, in SPLIT_PTLOCK configs a spinlock in table's
+ * struct page). pte_unmap_unlock(pte, ptl) to unlock and unmap afterwards.
+ *
+ * But it is unsuccessful, returning NULL with *ptlp unchanged, if there is no
+ * page table at *pmd: if, for example, the page table has just been removed,
+ * or replaced by the huge pmd of a THP. (When successful, *pmd is rechecked
+ * after acquiring the ptlock, and retried internally if it changed: so that a
+ * page table can be safely removed or replaced by THP while holding its lock.)
+ *
+ * pte_offset_map(pmd, addr), and its internal helper __pte_offset_map() above,
+ * just returns the pte pointer for addr, its page table kmapped if necessary;
+ * or NULL if there is no page table at *pmd. It does not attempt to lock the
+ * page table, so cannot normally be used when the page table is to be updated,
+ * or when entries read must be stable. But it does take rcu_read_lock(): so
+ * that even when page table is racily removed, it remains a valid though empty
+ * and disconnected table. Until pte_unmap(pte) unmaps and rcu_read_unlock()s
+ * afterwards.
+ *
+ * pte_offset_map_nolock(mm, pmd, addr, ptlp), above, is like pte_offset_map();
+ * but when successful, it also outputs a pointer to the spinlock in ptlp - as
+ * pte_offset_map_lock() does, but in this case without locking it. This helps
+ * the caller to avoid a later pte_lockptr(mm, *pmd), which might by that time
+ * act on a changed *pmd: pte_offset_map_nolock() provides the correct spinlock
+ * pointer for the page table that it returns. In principle, the caller should
+ * recheck *pmd once the lock is taken; in practice, no callsite needs that -
+ * either the mmap_lock for write, or pte_same() check on contents, is enough.
+ *
+ * Note that free_pgtables(), used after unmapping detached vmas, or when
+ * exiting the whole mm, does not take page table lock before freeing a page
+ * table, and may not use RCU at all: "outsiders" like khugepaged should avoid
+ * pte_offset_map() and co once the vma is detached from mm or mm_users is zero.
+ */
pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, spinlock_t **ptlp)
{
projects / linux-2.6-microblaze.git / blobdiff