[RFC PATCH V5 6/6] arm64: mm: Enable RCU fast_gup

[Steve Capper]

Activate the RCU fast_gup for ARM64. We also need to force THP splits
to broadcast an IPI s.t. we block in the fast_gup page walker. As THP
splits are comparatively rare, this should not lead to a noticeable
performance degradation.

Signed-off-by: Steve Capper <steve.capper at linaro.org>
---
 arch/arm64/Kconfig               |  3 +++
 arch/arm64/include/asm/pgtable.h |  8 +++++++-
 arch/arm64/mm/flush.c            | 19 +++++++++++++++++++
 3 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 2420390..5168949 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -95,6 +95,9 @@ config GENERIC_CALIBRATE_DELAY
 config ZONE_DMA
 	def_bool y
 
+config HAVE_RCU_GUP
+	def_bool y
+
 config ARCH_DMA_ADDR_T_64BIT
 	def_bool y
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 90c811f..126ed77e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -244,7 +244,13 @@ static inline pmd_t pte_pmd(pte_t pte)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
 #define pmd_trans_splitting(pmd)	pte_special(pmd_pte(pmd))
-#endif
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+struct vm_area_struct;
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp);
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index e4193e3..ddf96c1 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -103,3 +103,22 @@ EXPORT_SYMBOL(flush_dcache_page);
  */
 EXPORT_SYMBOL(flush_cache_all);
 EXPORT_SYMBOL(flush_icache_range);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+static void thp_splitting_flush_sync(void *arg)
+{
+}
+
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp)
+{
+	pmd_t pmd = pmd_mksplitting(*pmdp);
+	VM_BUG_ON(address & ~PMD_MASK);
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+
+	/* dummy IPI to serialise against fast_gup */
+	smp_call_function(thp_splitting_flush_sync, NULL, 1);
+}
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-- 
1.8.1.4