Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
IronPort-SDR: ZOkMS7SWKn6og2i3CpFR/I921imTa39c9cDcRvFImGL7ugiUCOmz4eoFWsgKDWlOLyWDiI5nXD
 6b1JR+QgjoctexHSb1HdD5UGiQtzp5bXjCz/u5HD9peEd7y7lWju9JNIktufDYc5xy6XR3w9HH
 QWH7kIVfzZiihymhRrWeW6Hdu8sS5VauUhhn1U1TCJ7FGCfG0oAeIFZNO3W0QYQKqHVoRRHfZI
 bmXhvUM99KWljqzDgyhEGCrBqL+Hv/d4fbywxQ9S0QM9aym1XGZEFSYolraNMHH6qd1FBKL/Re
 yFU=
IronPort-SDR: AFnbuUyy/lRph9+KcYeXg3ey1XHcjVeLwHbsoTdxDjXuZ/47kGZXKg/Wwu2oA9LV+wuc+uPK1f
 b8vmdNGnLHAHuDJnsrcOe7bEPIkSQis+zrEO6RUGxmGO7kUMJFpLmMle+KfeLalUqWzWfywXuk
 LJoQIyo4tcemgmUZMdxcRi8MUkic2xQm/iLRlZojXjzs3ZoAYcsb0N0Di7YnwJy/p3urxDC4ob
 4pTxph44h61TatRGfhpIpnbXpQvjUPxojqqEdPMA0DfaQKFo229guU08e/4q3lDJNwnAbFpV29
 El7o8EAI/IXc34SQij8mXLDN
IronPort-SDR: 5cO7xlMPnvqQEdneKaDfxVLumwgrPiNAymBKl7/ACH5XG2lPhxIzijuIs4b7a0bV3rgy0faDcB
 ebce1EgaxSH8raP3yBgpez9GcF0InYakqHxD/VnIKsghZ0zhQb1Iy8k3difYzr8N0o9J73R+Hj
 Xf8buN3qZImFqAxYfjldxM5/zUq/R8JpefLbstNZoTZv4Y1bsxC8urlyZjaG5wnlRDW7F5aLiP
 sMl2s/DI9qwPBxifEOubuhQ17pRYq+yEeDa9/b/prcOdTS6FQCK0zJknAIJehYGbtMe8TlYS6U
 Vaw=
From:   Atish Patra <atish.patra@wdc.com>
To:     linux-kernel@vger.kernel.org
Cc:     Atish Patra <atish.patra@wdc.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        Alexios Zavras <alexios.zavras@intel.com>,
        Allison Randal <allison@lohutok.net>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        linux-riscv@lists.infradead.org,
        Palmer Dabbelt <palmer@sifive.com>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Anup Patel <anup.patel@wdc.com>
Subject: [PATCH] RISC-V: Issue a local tlb flush if possible.
Date:   Fri,  9 Aug 2019 18:43:09 -0700
Message-Id: <20190810014309.20838-1-atish.patra@wdc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

In RISC-V, tlb flush happens via SBI which is expensive.
If the target cpumask contains a local hartid, some cost
can be saved by issuing a local tlb flush as we do that
in OpenSBI anyways.

Signed-off-by: Atish Patra <atish.patra@wdc.com>
---
 arch/riscv/include/asm/tlbflush.h | 33 +++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 687dd19735a7..b32ba4fa5888 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -8,6 +8,7 @@
 #define _ASM_RISCV_TLBFLUSH_H
 
 #include <linux/mm_types.h>
+#include <linux/sched.h>
 #include <asm/smp.h>
 
 /*
@@ -46,14 +47,38 @@ static inline void remote_sfence_vma(struct cpumask *cmask, unsigned long start,
 				     unsigned long size)
 {
 	struct cpumask hmask;
+	struct cpumask tmask;
+	int cpuid = smp_processor_id();
 
 	cpumask_clear(&hmask);
-	riscv_cpuid_to_hartid_mask(cmask, &hmask);
-	sbi_remote_sfence_vma(hmask.bits, start, size);
+	cpumask_clear(&tmask);
+
+	if (cmask)
+		cpumask_copy(&tmask, cmask);
+	else
+		cpumask_copy(&tmask, cpu_online_mask);
+
+	if (cpumask_test_cpu(cpuid, &tmask)) {
+		/* Save trap cost by issuing a local tlb flush here */
+		if ((start == 0 && size == -1) || (size > PAGE_SIZE))
+			local_flush_tlb_all();
+		else if (size == PAGE_SIZE)
+			local_flush_tlb_page(start);
+		cpumask_clear_cpu(cpuid, &tmask);
+	} else if (cpumask_empty(&tmask)) {
+		/* cpumask is empty. So just do a local flush */
+		local_flush_tlb_all();
+		return;
+	}
+
+	if (!cpumask_empty(&tmask)) {
+		riscv_cpuid_to_hartid_mask(&tmask, &hmask);
+		sbi_remote_sfence_vma(hmask.bits, start, size);
+	}
 }
 
-#define flush_tlb_all() sbi_remote_sfence_vma(NULL, 0, -1)
-#define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
+#define flush_tlb_all() remote_sfence_vma(NULL, 0, -1)
+#define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, (addr) + PAGE_SIZE)
 #define flush_tlb_range(vma, start, end) \
 	remote_sfence_vma(mm_cpumask((vma)->vm_mm), start, (end) - (start))
 #define flush_tlb_mm(mm) \
-- 
2.21.0