[PATCH 4/4] arm64: add software prefetches for AmpereOne

[Huang Shijie <shijie@os.amperecomputing.com>]

0) Background:
   We found that AmpereOne benefits from aggressive prefetches when
   using 4K page size.

1) This patch:
    1.1) adds new WORKAROUND_AMPERE_AC03_PREFETCH capability.
    1.2) uses MIDR_AMPERE1 to filter the processor.
    1.3) uses alternative_if to alternative the code
         for AmpereOne.
    1.4) adds software prefetches for the specific loop.
    	 Also add a macro add_prefetch.

2) Test result:
    In hugetlb or tmpfs, We can get big seqential read performance improvement
    up to 1.3x ~ 1.4x.

Signed-off-by: Huang Shijie <shijie@os.amperecomputing.com>
---
 arch/arm64/Kconfig.platforms   |  7 +++++++
 arch/arm64/kernel/cpu_errata.c |  9 +++++++++
 arch/arm64/lib/copy_template.S | 31 +++++++++++++++++++++++++++++++
 arch/arm64/tools/cpucaps       |  1 +
 4 files changed, 48 insertions(+)

diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 6069120199bb..74ab8bea0019 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -8,6 +8,13 @@ config ARCH_ACTIONS
 	help
 	  This enables support for the Actions Semiconductor S900 SoC family.
 
+config ARCH_AMPEREONE
+	bool "AmpereOne Platforms"
+	help
+	  This enables support for the ARMv8 based AmpereOne chipsets.
+	  AmpereOne is the next generation of Cloud Native Processors from
+	  Ampere.
+
 config ARCH_SUNXI
 	bool "Allwinner sunxi 64-bit SoC Family"
 	select ARCH_HAS_RESET_CONTROLLER
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 5706e74c5578..c0060d3086d0 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -744,6 +744,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_WORKAROUND_AMPERE_AC03_CPU_38,
 		ERRATA_MIDR_ALL_VERSIONS(MIDR_AMPERE1),
 	},
+#endif
+#if defined(CONFIG_ARCH_AMPEREONE) && defined(CONFIG_ARM64_4K_PAGES)
+	{
+		.desc = "Optimization for AmpereOne chip",
+		.capability = ARM64_WORKAROUND_AMPERE_AC03_PREFETCH,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = is_affected_midr_range,
+		.midr_range = MIDR_ALL_VERSIONS(MIDR_AMPERE1)
+	},
 #endif
 	{
 	}
diff --git a/arch/arm64/lib/copy_template.S b/arch/arm64/lib/copy_template.S
index 79b32569260c..b707c3ec6820 100644
--- a/arch/arm64/lib/copy_template.S
+++ b/arch/arm64/lib/copy_template.S
@@ -41,6 +41,18 @@
 	b.ne	.Ltail63
 .endm
 
+#if defined(CONFIG_ARCH_AMPEREONE) && defined(CONFIG_ARM64_4K_PAGES)
+.macro add_prefetch
+	/*
+	 * Add prefetch two cache lines by prfm to optimize the
+	 * performance. The 2K offset is the best offset which
+	 * we get from the tests.
+	 */
+	prfm	pldl2keep, [src, #2048]
+	prfm	pldl2keep, [src, #2112]
+.endm
+#endif
+
 /*
  * Copy a buffer from src to dest (alignment handled by the hardware)
  *
@@ -156,6 +168,13 @@ D_h	.req	x14
 	b	.Lexitfunc
 
 .Lcpy_over64:
+#if defined(CONFIG_ARCH_AMPEREONE) && defined(CONFIG_ARM64_4K_PAGES)
+alternative_if  ARM64_WORKAROUND_AMPERE_AC03_PREFETCH
+	cmp	count, #PAGE_SIZE
+	b.ge	.Lcpy_over_pagesize
+alternative_else_nop_endif
+#endif
+
 	subs	count, count, #128
 	b.ge	.Lcpy_body_large
 	/*
@@ -182,4 +201,16 @@ D_h	.req	x14
 	.p2align	L1_CACHE_SHIFT
 .Lcpy_body_large:
 	loop_for_copy_128_bytes
+
+#if defined(CONFIG_ARCH_AMPEREONE) && defined(CONFIG_ARM64_4K_PAGES)
+	b	.Lexitfunc
+
+	.p2align        L1_CACHE_SHIFT
+.Lcpy_over_pagesize:
+alternative_if  ARM64_WORKAROUND_AMPERE_AC03_PREFETCH
+	subs	count, count, #128
+	loop_for_copy_128_bytes add_prefetch
+alternative_else_nop_endif
+#endif
+
 .Lexitfunc:
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index dea3dc89234b..13e197abf249 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -100,3 +100,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP
 WORKAROUND_QCOM_FALKOR_E1003
 WORKAROUND_REPEAT_TLBI
 WORKAROUND_SPECULATIVE_AT
+WORKAROUND_AMPERE_AC03_PREFETCH
-- 
2.40.1