Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:3 as permitted sender) client-ip=2620:137:e000::3:3;
From:   Alexandre Ghiti <alexghiti@rivosinc.com>
To:     Will Deacon <will@kernel.org>,
        "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Nick Piggin <npiggin@gmail.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Mayuresh Chitale <mchitale@ventanamicro.com>,
        Vincent Chen <vincent.chen@sifive.com>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>, linux-arch@vger.kernel.org,
        linux-mm@kvack.org, linux-riscv@lists.infradead.org,
        linux-kernel@vger.kernel.org, Samuel Holland <samuel@sholland.org>,
        Lad Prabhakar <prabhakar.csengg@gmail.com>
Cc:     Alexandre Ghiti <alexghiti@rivosinc.com>
Subject: [PATCH v5 2/4] riscv: Improve flush_tlb_range() for hugetlb pages
Date:   Thu, 19 Oct 2023 16:01:49 +0200
Message-Id: <20231019140151.21629-3-alexghiti@rivosinc.com>
In-Reply-To: <20231019140151.21629-1-alexghiti@rivosinc.com>
References: <20231019140151.21629-1-alexghiti@rivosinc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

flush_tlb_range() uses a fixed stride of PAGE_SIZE and in its current form,
when a hugetlb mapping needs to be flushed, flush_tlb_range() flushes the
whole tlb: so set a stride of the size of the hugetlb mapping in order to
only flush the hugetlb mapping. However, if the hugepage is a NAPOT region,
all PTEs that constitute this mapping must be invalidated, so the stride
size must actually be the size of the PTE.

Note that THPs are directly handled by flush_pmd_tlb_range().

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
 arch/riscv/mm/tlbflush.c | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index fa03289853d8..5933744df91a 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -3,6 +3,7 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/hugetlb.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
@@ -147,7 +148,35 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 {
-	__flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+	unsigned long stride_size;
+
+	if (!is_vm_hugetlb_page(vma)) {
+		stride_size = PAGE_SIZE;
+	} else {
+		stride_size = huge_page_size(hstate_vma(vma));
+
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+		/*
+		 * As stated in the privileged specification, every PTE in a
+		 * NAPOT region must be invalidated, so reset the stride in that
+		 * case.
+		 */
+		if (has_svnapot()) {
+			if (stride_size >= PGDIR_SIZE)
+				stride_size = PGDIR_SIZE;
+			else if (stride_size >= P4D_SIZE)
+				stride_size = P4D_SIZE;
+			else if (stride_size >= PUD_SIZE)
+				stride_size = PUD_SIZE;
+			else if (stride_size >= PMD_SIZE)
+				stride_size = PMD_SIZE;
+			else
+				stride_size = PAGE_SIZE;
+		}
+#endif
+	}
+
+	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
-- 
2.39.2