[PATCH v3 3/4] riscv: Make __flush_tlb_range() loop over pte instead of flushing the whole tlb

[Alexandre Ghiti]

Currently, when the range to flush covers more than one page (a 4K page or
a hugepage), __flush_tlb_range() flushes the whole tlb. Flushing the whole
tlb comes with a greater cost than flushing a single entry so we should
flush single entries up to a certain threshold so that:
threshold * cost of flushing a single entry < cost of flushing the whole
tlb.

Co-developed-by: Mayuresh Chitale <mchitale at ventanamicro.com>
Signed-off-by: Mayuresh Chitale <mchitale at ventanamicro.com>
Signed-off-by: Alexandre Ghiti <alexghiti at rivosinc.com>
Reviewed-by: Andrew Jones <ajones at ventanamicro.com>
---
 arch/riscv/mm/tlbflush.c | 48 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 44 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index d883df0dee4a..0c955c474f3a 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -7,6 +7,9 @@
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
+#define FLUSH_TLB_MAX_SIZE	((unsigned long)-1)
+#define FLUSH_TLB_NO_ASID	((unsigned long)-1)
+
 static inline void local_flush_tlb_all_asid(unsigned long asid)
 {
 	__asm__ __volatile__ ("sfence.vma x0, %0"
@@ -24,13 +27,48 @@ static inline void local_flush_tlb_page_asid(unsigned long addr,
 			: "memory");
 }
 
+/*
+ * Flush entire TLB if number of entries to be flushed is greater
+ * than the threshold below.
+ */
+static unsigned long tlb_flush_all_threshold __read_mostly = 64;
+
+static void local_flush_tlb_range_threshold_asid(unsigned long start,
+						 unsigned long size,
+						 unsigned long stride,
+						 unsigned long asid)
+{
+	u16 nr_ptes_in_range = DIV_ROUND_UP(size, stride);
+	int i;
+
+	if (nr_ptes_in_range > tlb_flush_all_threshold) {
+		if (asid != FLUSH_TLB_NO_ASID)
+			local_flush_tlb_all_asid(asid);
+		else
+			local_flush_tlb_all();
+		return;
+	}
+
+	for (i = 0; i < nr_ptes_in_range; ++i) {
+		if (asid != FLUSH_TLB_NO_ASID)
+			local_flush_tlb_page_asid(start, asid);
+		else
+			local_flush_tlb_page(start);
+		start += stride;
+	}
+}
+
 static inline void local_flush_tlb_range(unsigned long start,
 		unsigned long size, unsigned long stride)
 {
 	if (size <= stride)
 		local_flush_tlb_page(start);
-	else
+	else if (size == FLUSH_TLB_MAX_SIZE)
 		local_flush_tlb_all();
+	else
+		local_flush_tlb_range_threshold_asid(start, size, stride,
+						     FLUSH_TLB_NO_ASID);
+
 }
 
 static inline void local_flush_tlb_range_asid(unsigned long start,
@@ -38,8 +76,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 {
 	if (size <= stride)
 		local_flush_tlb_page_asid(start, asid);
-	else
+	else if (size == FLUSH_TLB_MAX_SIZE)
 		local_flush_tlb_all_asid(asid);
+	else
+		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
 static void __ipi_flush_tlb_all(void *info)
@@ -52,7 +92,7 @@ void flush_tlb_all(void)
 	if (riscv_use_ipi_for_rfence())
 		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
 	else
-		sbi_remote_sfence_vma(NULL, 0, -1);
+		sbi_remote_sfence_vma(NULL, 0, FLUSH_TLB_MAX_SIZE);
 }
 
 struct flush_tlb_range_data {
@@ -130,7 +170,7 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__flush_tlb_range(mm, 0, -1, PAGE_SIZE);
+	__flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_mm_range(struct mm_struct *mm,
-- 
2.39.2