arm64: enable THP_SWAP for arm64

THP_SWAP has been proven to improve the swap throughput significantly
on x86_64 according to commit bd4c82c22c367e ("mm, THP, swap: delay
splitting THP after swapped out").
As long as arm64 uses 4K page size, it is quite similar with x86_64
by having 2MB PMD THP. THP_SWAP is architecture-independent, thus,
enabling it on arm64 will benefit arm64 as well.
A corner case is that MTE has an assumption that only base pages
can be swapped. We won't enable THP_SWAP for ARM64 hardware with
MTE support until MTE is reworked to coexist with THP_SWAP.

A micro-benchmark is written to measure thp swapout throughput as
below,

 unsigned long long tv_to_ms(struct timeval tv)
 {
 	return tv.tv_sec * 1000 + tv.tv_usec / 1000;
 }

 main()
 {
 	struct timeval tv_b, tv_e;;
 #define SIZE 400*1024*1024
 	volatile void *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE,
 				MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (!p) {
 		perror("fail to get memory");
 		exit(-1);
 	}

 	madvise(p, SIZE, MADV_HUGEPAGE);
 	memset(p, 0x11, SIZE); /* write to get mem */

 	gettimeofday(&tv_b, NULL);
 	madvise(p, SIZE, MADV_PAGEOUT);
 	gettimeofday(&tv_e, NULL);

 	printf("swp out bandwidth: %ld bytes/ms\n",
 			SIZE/(tv_to_ms(tv_e) - tv_to_ms(tv_b)));
 }

Testing is done on rk3568 64bit Quad Core Cortex-A55 platform -
ROCK 3A.
thp swp throughput w/o patch: 2734bytes/ms (mean of 10 tests)
thp swp throughput w/  patch: 3331bytes/ms (mean of 10 tests)

Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Steven Price <steven.price@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Link: https://lore.kernel.org/r/20220720093737.133375-1-21cnbao@gmail.com
Signed-off-by: Will Deacon <will@kernel.org>

4 files changed, 20 insertions, 1 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1652a9800ebe..e1c540e80eec 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -101,6 +101,7 @@ config ARM64
 	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_NO_INSTR
+	select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0b6632f18364..78d6f6014bfb 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -45,6 +45,12 @@
 	__flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+static inline bool arch_thp_swp_supported(void)
+{
+	return !system_supports_mte();
+}
+#define arch_thp_swp_supported arch_thp_swp_supported
+
 /*
  * Outside of a few very special situations (e.g. hibernation), we always
  * use broadcast TLB invalidation instructions, therefore a spurious page
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index de29821231c9..4ddaf6ad73ef 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -461,4 +461,16 @@ static inline int split_folio_to_list(struct folio *folio,
 	return split_huge_page_to_list(&folio->page, list);
 }
 
+/*
+ * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to
+ * limitations in the implementation like arm64 MTE can override this to
+ * false
+ */
+#ifndef arch_thp_swp_supported
+static inline bool arch_thp_swp_supported(void)
+{
+	return true;
+}
+#endif
+
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 2a65a89b5b4d..10b94d64cc25 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -307,7 +307,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
 	entry.val = 0;
 
 	if (folio_test_large(folio)) {
-		if (IS_ENABLED(CONFIG_THP_SWAP))
+		if (IS_ENABLED(CONFIG_THP_SWAP) && arch_thp_swp_supported())
 			get_swap_pages(1, &entry, folio_nr_pages(folio));
 		goto out;
 	}