diff mbox series

[13/29] mm: add speculative_page_walk_begin() and speculative_page_walk_end()

Message ID 20210430195232.30491-14-michel@lespinasse.org (mailing list archive)
State New
Headers show
Series [01/29] mm: export dump_mm | expand

Commit Message

Michel Lespinasse April 30, 2021, 7:52 p.m. UTC
Speculative page faults will use these to protect against races with
page table reclamation.

This could always be handled by disabling local IRQs as the fast GUP
code does; however speculative page faults do not need to protect
against races with THP page splitting, so a weaker rcu read lock is
sufficient in the MMU_GATHER_RCU_TABLE_FREE case.

Signed-off-by: Michel Lespinasse <michel@lespinasse.org>
---
 mm/memory.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
diff mbox series

Patch

diff --git a/mm/memory.c b/mm/memory.c
index 8258ff93a055..b28047765de7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2566,6 +2566,28 @@  int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(apply_to_existing_page_range);
 
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+
+/*
+ * speculative_page_walk_begin() ... speculative_page_walk_end() protects
+ * against races with page table reclamation.
+ *
+ * This is similar to what fast GUP does, but fast GUP also needs to
+ * protect against races with THP page splitting, so it always needs
+ * to disable interrupts.
+ * Speculative page faults only need to protect against page table reclamation,
+ * so rcu_read_lock() is sufficient in the MMU_GATHER_RCU_TABLE_FREE case.
+ */
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
+#define speculative_page_walk_begin() rcu_read_lock()
+#define speculative_page_walk_end()   rcu_read_unlock()
+#else
+#define speculative_page_walk_begin() local_irq_disable()
+#define speculative_page_walk_end()   local_irq_enable()
+#endif
+
+#endif	/* CONFIG_SPECULATIVE_PAGE_FAULT */
+
 /*
  * handle_pte_fault chooses page fault handler according to an entry which was
  * read non-atomically.  Before making any commitment, on those architectures