Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Anup Patel <apatel@ventanamicro.com>
To:     Palmer Dabbelt <palmer@dabbelt.com>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Marc Zyngier <maz@kernel.org>,
        Daniel Lezcano <daniel.lezcano@linaro.org>
Cc:     Atish Patra <atishp@atishpatra.org>,
        Alistair Francis <Alistair.Francis@wdc.com>,
        Anup Patel <anup@brainfault.org>,
        linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
        Anup Patel <apatel@ventanamicro.com>
Subject: [PATCH v2 5/6] RISC-V: Use IPIs for remote TLB flush when possible
Date:   Fri, 28 Jan 2022 10:55:04 +0530
Message-Id: <20220128052505.859518-6-apatel@ventanamicro.com>
In-Reply-To: <20220128052505.859518-1-apatel@ventanamicro.com>
References: <20220128052505.859518-1-apatel@ventanamicro.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

If IPI calls are injected using SBI IPI calls then remote TLB flush
using SBI RFENCE calls is much faster because using IPIs for remote
TLB flush would still endup as SBI IPI calls with extra processing
on kernel side.

It is now possible to have specialized hardware (such as RISC-V AIA
and RISC-V ACLINT) which allows S-mode software to directly inject
IPIs without any assistance from M-mode runtime firmware.

This patch extends remote TLB flush functions to use IPIs whenever
underlying IPI operations are suitable for remote FENCEs.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
---
 arch/riscv/mm/tlbflush.c | 93 +++++++++++++++++++++++++++++++++-------
 1 file changed, 78 insertions(+), 15 deletions(-)

diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 37ed760d007c..27a7db8eb2c4 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -23,14 +23,62 @@ static inline void local_flush_tlb_page_asid(unsigned long addr,
 			: "memory");
 }
 
+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
+		local_flush_tlb_all();
+}
+
+static inline void local_flush_tlb_range_asid(unsigned long start,
+		unsigned long size, unsigned long stride, unsigned long asid)
+{
+	if (size <= stride)
+		local_flush_tlb_page_asid(start, asid);
+	else
+		local_flush_tlb_all_asid(asid);
+}
+
+static void __ipi_flush_tlb_all(void *info)
+{
+	local_flush_tlb_all();
+}
+
 void flush_tlb_all(void)
 {
-	sbi_remote_sfence_vma(NULL, 0, -1);
+	if (riscv_use_ipi_for_rfence())
+		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
+	else
+		sbi_remote_sfence_vma(NULL, 0, -1);
+}
+
+struct flush_tlb_range_data {
+	unsigned long asid;
+	unsigned long start;
+	unsigned long size;
+	unsigned long stride;
+};
+
+static void __ipi_flush_tlb_range_asid(void *info)
+{
+	struct flush_tlb_range_data *d = info;
+
+	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
+}
+
+static void __ipi_flush_tlb_range(void *info)
+{
+	struct flush_tlb_range_data *d = info;
+
+	local_flush_tlb_range(d->start, d->size, d->stride);
 }
 
-static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
-				  unsigned long size, unsigned long stride)
+static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
+			      unsigned long size, unsigned long stride)
 {
+	struct flush_tlb_range_data ftd;
 	struct cpumask *cmask = mm_cpumask(mm);
 	unsigned int cpuid;
 	bool broadcast;
@@ -45,19 +93,34 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 		unsigned long asid = atomic_long_read(&mm->context.id);
 
 		if (broadcast) {
-			sbi_remote_sfence_vma_asid(cmask, start, size, asid);
-		} else if (size <= stride) {
-			local_flush_tlb_page_asid(start, asid);
+			if (riscv_use_ipi_for_rfence()) {
+				ftd.asid = asid;
+				ftd.start = start;
+				ftd.size = size;
+				ftd.stride = stride;
+				on_each_cpu_mask(cmask,
+						 __ipi_flush_tlb_range_asid,
+						 &ftd, 1);
+			} else
+				sbi_remote_sfence_vma_asid(cmask,
+							   start, size, asid);
 		} else {
-			local_flush_tlb_all_asid(asid);
+			local_flush_tlb_range_asid(start, size, stride, asid);
 		}
 	} else {
 		if (broadcast) {
-			sbi_remote_sfence_vma(cmask, start, size);
-		} else if (size <= stride) {
-			local_flush_tlb_page(start);
+			if (riscv_use_ipi_for_rfence()) {
+				ftd.asid = 0;
+				ftd.start = start;
+				ftd.size = size;
+				ftd.stride = stride;
+				on_each_cpu_mask(cmask,
+						 __ipi_flush_tlb_range,
+						 &ftd, 1);
+			} else
+				sbi_remote_sfence_vma(cmask, start, size);
 		} else {
-			local_flush_tlb_all();
+			local_flush_tlb_range(start, size, stride);
 		}
 	}
 
@@ -66,23 +129,23 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__sbi_tlb_flush_range(mm, 0, -1, PAGE_SIZE);
+	__flush_tlb_range(mm, 0, -1, PAGE_SIZE);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
-	__sbi_tlb_flush_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
+	__flush_tlb_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 {
-	__sbi_tlb_flush_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+	__flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
 {
-	__sbi_tlb_flush_range(vma->vm_mm, start, end - start, PMD_SIZE);
+	__flush_tlb_range(vma->vm_mm, start, end - start, PMD_SIZE);
 }
 #endif
-- 
2.25.1