arm: mm: enable RCU fast_gup

Activate the RCU fast_gup for ARM.  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.
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dann Frazier <dann.frazier@canonical.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>

arch/arm/Kconfig

@@ -1661,6 +1661,10 @@ config ARCH_SELECT_MEMORY_MODEL
 config HAVE_ARCH_PFN_VALID
 	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
 
+config HAVE_GENERIC_RCU_GUP
+	def_bool y
+	depends on ARM_LPAE
+
 config HIGHMEM
 	bool "High Memory Support"
 	depends on MMU

arch/arm/include/asm/pgtable-3level.h

@@ -224,6 +224,8 @@ static inline pte_t pte_mkspecial(pte_t pte)
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
 #define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
+#define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
+#define pud_write(pud)		pmd_write(__pmd(pud_val(pud)))
 
 #define pmd_hugewillfault(pmd)	(!pmd_young(pmd) || !pmd_write(pmd))
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
@@ -231,6 +233,12 @@ static inline pte_t pte_mkspecial(pte_t pte)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !pmd_table(pmd))
 #define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp);
+#endif
 #endif
 
 #define PMD_BIT_FUNC(fn,op) \

arch/arm/mm/flush.c

@@ -400,3 +400,18 @@ void __flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned l
 	 */
 	__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 }
+
+#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 */