[PATCH 1/3] arm64: Use FEAT_HAFDBS to track dirty pages when available

[Ying-Chun Liu (PaulLiu)]

From: Marc Zyngier <maz at kernel.org>

Some recent arm64 cores have a facility that allows the page
table walker to track the dirty state of a page. This makes it
really efficient to perform CMOs by VA as we only need to look
at dirty pages.

Signed-off-by: Marc Zyngier <maz at kernel.org>
[ Paul: pick from the Android tree. Rebase to the upstream ]
Signed-off-by: Ying-Chun Liu (PaulLiu) <paul.liu at linaro.org>
Cc: Tom Rini <trini at konsulko.com>
Link: https://android.googlesource.com/platform/external/u-boot/+/3c433724e6f830a6b2edd5ec3d4a504794887263
---
 arch/arm/cpu/armv8/cache_v8.c      | 16 +++++++++++++++-
 arch/arm/include/asm/armv8/mmu.h   | 14 ++++++++++----
 arch/arm/include/asm/global_data.h |  1 +
 3 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/arch/arm/cpu/armv8/cache_v8.c b/arch/arm/cpu/armv8/cache_v8.c
index 697334086f..4760064ee1 100644
--- a/arch/arm/cpu/armv8/cache_v8.c
+++ b/arch/arm/cpu/armv8/cache_v8.c
@@ -93,6 +93,8 @@ u64 get_tcr(u64 *pips, u64 *pva_bits)
 
 	if (el == 1) {
 		tcr = TCR_EL1_RSVD | (ips << 32) | TCR_EPD1_DISABLE;
+		if (gd->arch.has_hafdbs)
+			tcr |= TCR_HA | TCR_HD;
 	} else if (el == 2) {
 		tcr = TCR_EL2_RSVD | (ips << 16);
 	} else {
@@ -200,6 +202,9 @@ static void __cmo_on_leaves(void (*cmo_fn)(unsigned long, unsigned long),
 		    attrs != PTE_BLOCK_MEMTYPE(MT_NORMAL_NC))
 			continue;
 
+		if (gd->arch.has_hafdbs && (pte & (PTE_RDONLY | PTE_DBM)) != PTE_DBM)
+			continue;
+
 		end = va + BIT(level2shift(level)) - 1;
 
 		/* No intersection with RAM? */
@@ -348,6 +353,9 @@ static void add_map(struct mm_region *map)
 	if (va_bits < 39)
 		level = 1;
 
+	if (gd->arch.has_hafdbs)
+		attrs |= PTE_DBM | PTE_RDONLY;
+
 	map_range(map->virt, map->phys, map->size, level,
 		  (u64 *)gd->arch.tlb_addr, attrs);
 }
@@ -399,7 +407,13 @@ static int count_ranges(void)
 __weak u64 get_page_table_size(void)
 {
 	u64 one_pt = MAX_PTE_ENTRIES * sizeof(u64);
-	u64 size;
+	u64 size, mmfr1;
+
+	asm volatile("mrs %0, id_aa64mmfr1_el1" : "=r" (mmfr1));
+	if ((mmfr1 & 0xf) == 2)
+		gd->arch.has_hafdbs = true;
+	else
+		gd->arch.has_hafdbs = false;
 
 	/* Account for all page tables we would need to cover our memory map */
 	size = one_pt * count_ranges();
diff --git a/arch/arm/include/asm/armv8/mmu.h b/arch/arm/include/asm/armv8/mmu.h
index 9f58cedb65..98a27db316 100644
--- a/arch/arm/include/asm/armv8/mmu.h
+++ b/arch/arm/include/asm/armv8/mmu.h
@@ -49,10 +49,13 @@
 #define PTE_TYPE_BLOCK		(1 << 0)
 #define PTE_TYPE_VALID		(1 << 0)
 
-#define PTE_TABLE_PXN		(1UL << 59)
-#define PTE_TABLE_XN		(1UL << 60)
-#define PTE_TABLE_AP		(1UL << 61)
-#define PTE_TABLE_NS		(1UL << 63)
+#define PTE_RDONLY		BIT(7)
+#define PTE_DBM			BIT(51)
+
+#define PTE_TABLE_PXN		BIT(59)
+#define PTE_TABLE_XN		BIT(60)
+#define PTE_TABLE_AP		BIT(61)
+#define PTE_TABLE_NS		BIT(63)
 
 /*
  * Block
@@ -99,6 +102,9 @@
 #define TCR_TG0_16K		(2 << 14)
 #define TCR_EPD1_DISABLE	(1 << 23)
 
+#define TCR_HA			BIT(39)
+#define TCR_HD			BIT(40)
+
 #define TCR_EL1_RSVD		(1U << 31)
 #define TCR_EL2_RSVD		(1U << 31 | 1 << 23)
 #define TCR_EL3_RSVD		(1U << 31 | 1 << 23)
diff --git a/arch/arm/include/asm/global_data.h b/arch/arm/include/asm/global_data.h
index 9e746e380a..eda99b5b41 100644
--- a/arch/arm/include/asm/global_data.h
+++ b/arch/arm/include/asm/global_data.h
@@ -52,6 +52,7 @@ struct arch_global_data {
 #if defined(CONFIG_ARM64)
 	unsigned long tlb_fillptr;
 	unsigned long tlb_emerg;
+	bool has_hafdbs;
 #endif
 #endif
 #ifdef CFG_SYS_MEM_RESERVE_SECURE
-- 
2.39.2