Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) client-ip=2620:137:e000::3:8;
From:   Alexandre Ghiti <alexghiti@rivosinc.com>
To:     Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will@kernel.org>,
        Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Nicholas Piggin <npiggin@gmail.com>,
        Christophe Leroy <christophe.leroy@csgroup.eu>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        Andrew Morton <akpm@linux-foundation.org>,
        Ved Shanbhogue <ved@rivosinc.com>,
        Matt Evans <mev@rivosinc.com>,
        Dylan Jhong <dylan@andestech.com>,
        linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org,
        linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
        linux-riscv@lists.infradead.org, linux-mm@kvack.org
Cc:     Alexandre Ghiti <alexghiti@rivosinc.com>
Subject: [PATCH RFC/RFT 4/4] TEMP: riscv: Add debugfs interface to retrieve #sfence.vma
Date:   Thu,  7 Dec 2023 16:03:48 +0100
Message-Id: <20231207150348.82096-5-alexghiti@rivosinc.com>
In-Reply-To: <20231207150348.82096-1-alexghiti@rivosinc.com>
References: <20231207150348.82096-1-alexghiti@rivosinc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This is useful for testing/benchmarking.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
 arch/riscv/include/asm/pgtable.h  |  6 ++++--
 arch/riscv/include/asm/tlbflush.h |  4 ++++
 arch/riscv/kernel/sbi.c           | 12 ++++++++++++
 arch/riscv/mm/tlbflush.c          | 17 +++++++++++++++++
 4 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 89aa5650f104..b0855a620cfd 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -550,7 +550,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 	return false;
 }
 
-extern u64 nr_sfence_vma_handle_exception;
+extern u64 nr_sfence_vma_spurious_read;
 extern bool tlb_caching_invalid_entries;
 
 #define flush_tlb_fix_spurious_read_fault flush_tlb_fix_spurious_read_fault
@@ -558,8 +558,10 @@ static inline void flush_tlb_fix_spurious_read_fault(struct vm_area_struct *vma,
 						     unsigned long address,
 						     pte_t *ptep)
 {
-	if (tlb_caching_invalid_entries)
+	if (tlb_caching_invalid_entries) {
+		__sync_fetch_and_add(&nr_sfence_vma_spurious_read, 1UL);
 		flush_tlb_page(vma, address);
+	}
 }
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index a09196f8de68..f419ec9d2207 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -14,14 +14,18 @@
 #ifdef CONFIG_MMU
 extern unsigned long asid_mask;
 
+extern u64 nr_sfence_vma, nr_sfence_vma_all, nr_sfence_vma_all_asid;
+
 static inline void local_flush_tlb_all(void)
 {
+	__sync_fetch_and_add(&nr_sfence_vma_all, 1UL);
 	__asm__ __volatile__ ("sfence.vma" : : : "memory");
 }
 
 /* Flush one page from local TLB */
 static inline void local_flush_tlb_page(unsigned long addr)
 {
+	__sync_fetch_and_add(&nr_sfence_vma, 1UL);
 	ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory"));
 }
 #else /* CONFIG_MMU */
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index c672c8ba9a2a..ac1617759583 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -376,6 +376,8 @@ int sbi_remote_fence_i(const struct cpumask *cpu_mask)
 }
 EXPORT_SYMBOL(sbi_remote_fence_i);
 
+extern u64 nr_sfence_vma, nr_sfence_vma_all, nr_sfence_vma_all_asid;
+
 /**
  * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
  *			     harts for the specified virtual address range.
@@ -389,6 +391,11 @@ int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
 			   unsigned long start,
 			   unsigned long size)
 {
+	if (size == (unsigned long)-1)
+		__sync_fetch_and_add(&nr_sfence_vma_all, 1UL);
+	else
+		__sync_fetch_and_add(&nr_sfence_vma, ALIGN(size, PAGE_SIZE) / PAGE_SIZE);
+
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
 			    cpu_mask, start, size, 0, 0);
 }
@@ -410,6 +417,11 @@ int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
 				unsigned long size,
 				unsigned long asid)
 {
+	if (size == (unsigned long)-1)
+		__sync_fetch_and_add(&nr_sfence_vma_all_asid, 1UL);
+	else
+		__sync_fetch_and_add(&nr_sfence_vma, ALIGN(size, PAGE_SIZE) / PAGE_SIZE);
+
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
 			    cpu_mask, start, size, asid, 0);
 }
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 77be59aadc73..75a3e2dff16a 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -3,11 +3,16 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/debugfs.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
+u64 nr_sfence_vma, nr_sfence_vma_all, nr_sfence_vma_all_asid,
+	nr_sfence_vma_handle_exception, nr_sfence_vma_spurious_read;
+
 static inline void local_flush_tlb_all_asid(unsigned long asid)
 {
+	__sync_fetch_and_add(&nr_sfence_vma_all_asid, 1);
 	__asm__ __volatile__ ("sfence.vma x0, %0"
 			:
 			: "r" (asid)
@@ -17,6 +22,7 @@ static inline void local_flush_tlb_all_asid(unsigned long asid)
 static inline void local_flush_tlb_page_asid(unsigned long addr,
 		unsigned long asid)
 {
+	__sync_fetch_and_add(&nr_sfence_vma, 1);
 	__asm__ __volatile__ ("sfence.vma %0, %1"
 			:
 			: "r" (addr), "r" (asid)
@@ -149,3 +155,14 @@ void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 	__flush_tlb_range(vma->vm_mm, start, end - start, PMD_SIZE);
 }
 #endif
+
+static int debugfs_nr_sfence_vma(void)
+{
+	debugfs_create_u64("nr_sfence_vma", 0444, NULL, &nr_sfence_vma);
+	debugfs_create_u64("nr_sfence_vma_all", 0444, NULL, &nr_sfence_vma_all);
+	debugfs_create_u64("nr_sfence_vma_all_asid", 0444, NULL, &nr_sfence_vma_all_asid);
+	debugfs_create_u64("nr_sfence_vma_handle_exception", 0444, NULL, &nr_sfence_vma_handle_exception);
+	debugfs_create_u64("nr_sfence_vma_spurious_read", 0444, NULL, &nr_sfence_vma_spurious_read);
+	return 0;
+}
+device_initcall(debugfs_nr_sfence_vma);
-- 
2.39.2