Let's add a helper that lets us batch-process multiple consecutive PTEs.
Note that the loop will get optimized out on all architectures except on
powerpc. We have to add an early define of __tlb_remove_tlb_entry() on
ppc to make the compiler happy (and avoid making tlb_remove_tlb_entries() a
macro).
Reviewed-by: Ryan Roberts <ryan.roberts@xxxxxxx>
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
arch/powerpc/include/asm/tlb.h | 2 ++
include/asm-generic/tlb.h | 20 ++++++++++++++++++++
2 files changed, 22 insertions(+)
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index b3de6102a907..1ca7d4c4b90d 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -19,6 +19,8 @@
#include <linux/pagemap.h>
+static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
+ unsigned long address);
#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry
#define tlb_flush tlb_flush
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 2eb7b0d4f5d2..95d60a4f468a 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -608,6 +608,26 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
__tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
+/**
+ * tlb_remove_tlb_entries - remember unmapping of multiple consecutive ptes for
+ * later tlb invalidation.
+ *
+ * Similar to tlb_remove_tlb_entry(), but remember unmapping of multiple
+ * consecutive ptes instead of only a single one.
+ */
+static inline void tlb_remove_tlb_entries(struct mmu_gather *tlb,
+ pte_t *ptep, unsigned int nr, unsigned long address)
+{
+ tlb_flush_pte_range(tlb, address, PAGE_SIZE * nr);
+ for (;;) {
+ __tlb_remove_tlb_entry(tlb, ptep, address);
+ if (--nr == 0)
+ break;
+ ptep++;
+ address += PAGE_SIZE;
+ }
+}
+
#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
do { \
unsigned long _sz = huge_page_size(h); \
--
2.43.0
