arm64: mm: enable RCU fast_gup

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.

Some pre-requisite functions pud_write and pud_page are also added.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Tested-by: Dann Frazier <dann.frazier@canonical.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 39 insertions, 1 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1ffd9a05206b..73bfb477ca0d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -111,6 +111,9 @@ config GENERIC_CALIBRATE_DELAY
 config ZONE_DMA
 	def_bool y
 
+config HAVE_GENERIC_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 d58e40cde88e..464c5cecdd15 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -244,6 +244,16 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
+static inline pte_t pud_pte(pud_t pud)
+{
+	return __pte(pud_val(pud));
+}
+
+static inline pmd_t pud_pmd(pud_t pud)
+{
+	return __pmd(pud_val(pud));
+}
+
 static inline pte_t pmd_pte(pmd_t pmd)
 {
 	return __pte(pmd_val(pmd));
@@ -261,7 +271,13 @@ 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)))
@@ -282,6 +298,7 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+#define pud_write(pud)		pte_write(pud_pte(pud))
 #define pud_pfn(pud)		(((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
 
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
@@ -381,6 +398,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
 }
 
+#define pud_page(pud)           pmd_page(pud_pmd(pud))
+
 #endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 2 */
 
 #if CONFIG_ARM64_PGTABLE_LEVELS > 3
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 0d64089d28b5..b6f14e8d2121 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -104,3 +104,19 @@ 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
+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 */
+	kick_all_cpus_sync();
+}
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */