[PATCH v2 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.

This threshold is microarchitecture dependent and can/should be
overwritten by vendors.

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>
---
 arch/riscv/mm/tlbflush.c | 41 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 39 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 3e4acef1f6bc..8017d2130e27 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -24,13 +24,48 @@ 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. Platforms may override the threshold
+ * value based on marchid, mvendorid, and mimpid.
+ */
+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 != -1)
+			local_flush_tlb_all_asid(asid);
+		else
+			local_flush_tlb_all();
+		return;
+	}
+
+	for (i = 0; i < nr_ptes_in_range; ++i) {
+		if (asid != -1)
+			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 == (unsigned long)-1)
 		local_flush_tlb_all();
+	else
+		local_flush_tlb_range_threshold_asid(start, size, stride, -1);
+
 }
 
 static inline void local_flush_tlb_range_asid(unsigned long start,
@@ -38,8 +73,10 @@ 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 == (unsigned long)-1)
 		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)
-- 
2.39.2