Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
From:   Anup Patel <apatel@ventanamicro.com>
To:     Paolo Bonzini <pbonzini@redhat.com>,
        Atish Patra <atishp@atishpatra.org>
Cc:     Palmer Dabbelt <palmer@dabbelt.com>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Alistair Francis <Alistair.Francis@wdc.com>,
        Anup Patel <anup@brainfault.org>, kvm@vger.kernel.org,
        kvm-riscv@lists.infradead.org, linux-riscv@lists.infradead.org,
        linux-kernel@vger.kernel.org, Anup Patel <apatel@ventanamicro.com>
Subject: [PATCH 4/6] RISC-V: KVM: Introduce range based local HFENCE functions
Date:   Tue, 12 Apr 2022 15:37:11 +0530
Message-Id: <20220412100713.1415094-5-apatel@ventanamicro.com>
In-Reply-To: <20220412100713.1415094-1-apatel@ventanamicro.com>
References: <20220412100713.1415094-1-apatel@ventanamicro.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Various  __kvm_riscv_hfence_xyz() functions implemented in the
kvm/tlb.S are equivalent to corresponding HFENCE.GVMA instructions
and we don't have range based local HFENCE functions.

This patch provides complete set of local HFENCE functions which
supports range based TLB invalidation and supports HFENCE.VVMA
based functions. This is also a preparatory patch for upcoming
Svinval support in KVM RISC-V.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
---
 arch/riscv/include/asm/kvm_host.h |  25 +++-
 arch/riscv/kvm/mmu.c              |   4 +-
 arch/riscv/kvm/tlb.S              |  74 ----------
 arch/riscv/kvm/tlb.c              | 231 ++++++++++++++++++++++++++++++
 arch/riscv/kvm/vcpu.c             |   2 +-
 arch/riscv/kvm/vmid.c             |   2 +-
 6 files changed, 255 insertions(+), 83 deletions(-)
 delete mode 100644 arch/riscv/kvm/tlb.S
 create mode 100644 arch/riscv/kvm/tlb.c

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 3e2cbbd7d1c9..806f74dc0bfc 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -204,11 +204,26 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 
-void __kvm_riscv_hfence_gvma_vmid_gpa(unsigned long gpa_divby_4,
-				      unsigned long vmid);
-void __kvm_riscv_hfence_gvma_vmid(unsigned long vmid);
-void __kvm_riscv_hfence_gvma_gpa(unsigned long gpa_divby_4);
-void __kvm_riscv_hfence_gvma_all(void);
+#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
+
+void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
+					  gpa_t gpa, gpa_t gpsz,
+					  unsigned long order);
+void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid);
+void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz,
+				     unsigned long order);
+void kvm_riscv_local_hfence_gvma_all(void);
+void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid,
+					  unsigned long asid,
+					  unsigned long gva,
+					  unsigned long gvsz,
+					  unsigned long order);
+void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid,
+					  unsigned long asid);
+void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid,
+				     unsigned long gva, unsigned long gvsz,
+				     unsigned long order);
+void kvm_riscv_local_hfence_vvma_all(unsigned long vmid);
 
 int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 			 struct kvm_memory_slot *memslot,
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 8823eb32dcde..1e07603c905b 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -745,7 +745,7 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu)
 	csr_write(CSR_HGATP, hgatp);
 
 	if (!kvm_riscv_gstage_vmid_bits())
-		__kvm_riscv_hfence_gvma_all();
+		kvm_riscv_local_hfence_gvma_all();
 }
 
 void kvm_riscv_gstage_mode_detect(void)
@@ -768,7 +768,7 @@ void kvm_riscv_gstage_mode_detect(void)
 skip_sv48x4_test:
 
 	csr_write(CSR_HGATP, 0);
-	__kvm_riscv_hfence_gvma_all();
+	kvm_riscv_local_hfence_gvma_all();
 #endif
 }
 
diff --git a/arch/riscv/kvm/tlb.S b/arch/riscv/kvm/tlb.S
deleted file mode 100644
index 899f75d60bad..000000000000
--- a/arch/riscv/kvm/tlb.S
+++ /dev/null
@@ -1,74 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2019 Western Digital Corporation or its affiliates.
- *
- * Authors:
- *     Anup Patel <anup.patel@wdc.com>
- */
-
-#include <linux/linkage.h>
-#include <asm/asm.h>
-
-	.text
-	.altmacro
-	.option norelax
-
-	/*
-	 * Instruction encoding of hfence.gvma is:
-	 * HFENCE.GVMA rs1, rs2
-	 * HFENCE.GVMA zero, rs2
-	 * HFENCE.GVMA rs1
-	 * HFENCE.GVMA
-	 *
-	 * rs1!=zero and rs2!=zero ==> HFENCE.GVMA rs1, rs2
-	 * rs1==zero and rs2!=zero ==> HFENCE.GVMA zero, rs2
-	 * rs1!=zero and rs2==zero ==> HFENCE.GVMA rs1
-	 * rs1==zero and rs2==zero ==> HFENCE.GVMA
-	 *
-	 * Instruction encoding of HFENCE.GVMA is:
-	 * 0110001 rs2(5) rs1(5) 000 00000 1110011
-	 */
-
-ENTRY(__kvm_riscv_hfence_gvma_vmid_gpa)
-	/*
-	 * rs1 = a0 (GPA >> 2)
-	 * rs2 = a1 (VMID)
-	 * HFENCE.GVMA a0, a1
-	 * 0110001 01011 01010 000 00000 1110011
-	 */
-	.word 0x62b50073
-	ret
-ENDPROC(__kvm_riscv_hfence_gvma_vmid_gpa)
-
-ENTRY(__kvm_riscv_hfence_gvma_vmid)
-	/*
-	 * rs1 = zero
-	 * rs2 = a0 (VMID)
-	 * HFENCE.GVMA zero, a0
-	 * 0110001 01010 00000 000 00000 1110011
-	 */
-	.word 0x62a00073
-	ret
-ENDPROC(__kvm_riscv_hfence_gvma_vmid)
-
-ENTRY(__kvm_riscv_hfence_gvma_gpa)
-	/*
-	 * rs1 = a0 (GPA >> 2)
-	 * rs2 = zero
-	 * HFENCE.GVMA a0
-	 * 0110001 00000 01010 000 00000 1110011
-	 */
-	.word 0x62050073
-	ret
-ENDPROC(__kvm_riscv_hfence_gvma_gpa)
-
-ENTRY(__kvm_riscv_hfence_gvma_all)
-	/*
-	 * rs1 = zero
-	 * rs2 = zero
-	 * HFENCE.GVMA
-	 * 0110001 00000 00000 000 00000 1110011
-	 */
-	.word 0x62000073
-	ret
-ENDPROC(__kvm_riscv_hfence_gvma_all)
diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c
new file mode 100644
index 000000000000..f817d3921973
--- /dev/null
+++ b/arch/riscv/kvm/tlb.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+
+/* Page sizes supported in G-stage TLB entries */
+static unsigned long gstage_tlb_pgsize_bitmap =
+			BIT(KVM_RISCV_GSTAGE_TLB_MIN_ORDER);
+
+#define hfence_update_order(__order)				\
+do {								\
+	if (!(BIT(__order) & gstage_tlb_pgsize_bitmap))		\
+		(__order) = KVM_RISCV_GSTAGE_TLB_MIN_ORDER;	\
+} while (0)
+
+/*
+ * Instruction encoding of hfence.gvma is:
+ * HFENCE.GVMA rs1, rs2
+ * HFENCE.GVMA zero, rs2
+ * HFENCE.GVMA rs1
+ * HFENCE.GVMA
+ *
+ * rs1!=zero and rs2!=zero ==> HFENCE.GVMA rs1, rs2
+ * rs1==zero and rs2!=zero ==> HFENCE.GVMA zero, rs2
+ * rs1!=zero and rs2==zero ==> HFENCE.GVMA rs1
+ * rs1==zero and rs2==zero ==> HFENCE.GVMA
+ *
+ * Instruction encoding of HFENCE.GVMA is:
+ * 0110001 rs2(5) rs1(5) 000 00000 1110011
+ */
+
+void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
+					  gpa_t gpa, gpa_t gpsz,
+					  unsigned long order)
+{
+	gpa_t pos;
+
+	hfence_update_order(order);
+
+	if (PTRS_PER_PTE < (gpsz >> order)) {
+		kvm_riscv_local_hfence_gvma_vmid_all(vmid);
+		return;
+	}
+
+	for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order)) {
+		/*
+		 * rs1 = a0 (GPA >> 2)
+		 * rs2 = a1 (VMID)
+		 * HFENCE.GVMA a0, a1
+		 * 0110001 01011 01010 000 00000 1110011
+		 */
+		asm volatile ("srli a0, %0, 2\n"
+			      "add a1, %1, zero\n"
+			      ".word 0x62b50073\n"
+			      :: "r" (pos), "r" (vmid)
+			      : "a0", "a1", "memory");
+	}
+}
+
+void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid)
+{
+	/*
+	 * rs1 = zero
+	 * rs2 = a0 (VMID)
+	 * HFENCE.GVMA zero, a0
+	 * 0110001 01010 00000 000 00000 1110011
+	 */
+	asm volatile ("add a0, %0, zero\n"
+		      ".word 0x62a00073\n"
+		      :: "r" (vmid) : "a0", "memory");
+}
+
+void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz,
+				     unsigned long order)
+{
+	gpa_t pos;
+
+	hfence_update_order(order);
+
+	if (PTRS_PER_PTE < (gpsz >> order)) {
+		kvm_riscv_local_hfence_gvma_all();
+		return;
+	}
+
+	for (pos = gpa; pos < (gpa + gpsz); pos += BIT(order)) {
+		/*
+		 * rs1 = a0 (GPA >> 2)
+		 * rs2 = zero
+		 * HFENCE.GVMA a0
+		 * 0110001 00000 01010 000 00000 1110011
+		 */
+		asm volatile ("srli a0, %0, 2\n"
+			      ".word 0x62050073\n"
+			      :: "r" (pos) : "a0", "memory");
+	}
+}
+
+void kvm_riscv_local_hfence_gvma_all(void)
+{
+	/*
+	 * rs1 = zero
+	 * rs2 = zero
+	 * HFENCE.GVMA
+	 * 0110001 00000 00000 000 00000 1110011
+	 */
+	asm volatile (".word 0x62000073" ::: "memory");
+}
+
+/*
+ * Instruction encoding of hfence.gvma is:
+ * HFENCE.VVMA rs1, rs2
+ * HFENCE.VVMA zero, rs2
+ * HFENCE.VVMA rs1
+ * HFENCE.VVMA
+ *
+ * rs1!=zero and rs2!=zero ==> HFENCE.VVMA rs1, rs2
+ * rs1==zero and rs2!=zero ==> HFENCE.VVMA zero, rs2
+ * rs1!=zero and rs2==zero ==> HFENCE.VVMA rs1
+ * rs1==zero and rs2==zero ==> HFENCE.VVMA
+ *
+ * Instruction encoding of HFENCE.VVMA is:
+ * 0010001 rs2(5) rs1(5) 000 00000 1110011
+ */
+
+void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid,
+					  unsigned long asid,
+					  unsigned long gva,
+					  unsigned long gvsz,
+					  unsigned long order)
+{
+	unsigned long pos, hgatp;
+
+	hfence_update_order(order);
+
+	if (PTRS_PER_PTE < (gvsz >> order)) {
+		kvm_riscv_local_hfence_vvma_asid_all(vmid, asid);
+		return;
+	}
+
+	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
+
+	for (pos = gva; pos < (gva + gvsz); pos += BIT(order)) {
+		/*
+		 * rs1 = a0 (GVA)
+		 * rs2 = a1 (ASID)
+		 * HFENCE.VVMA a0, a1
+		 * 0010001 01011 01010 000 00000 1110011
+		 */
+		asm volatile ("add a0, %0, zero\n"
+			      "add a1, %1, zero\n"
+			      ".word 0x22b50073\n"
+			      :: "r" (pos), "r" (asid)
+			      : "a0", "a1", "memory");
+	}
+
+	csr_write(CSR_HGATP, hgatp);
+}
+
+void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid,
+					  unsigned long asid)
+{
+	unsigned long hgatp;
+
+	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
+
+	/*
+	 * rs1 = zero
+	 * rs2 = a0 (ASID)
+	 * HFENCE.VVMA zero, a0
+	 * 0010001 01010 00000 000 00000 1110011
+	 */
+	asm volatile ("add a0, %0, zero\n"
+		      ".word 0x22a00073\n"
+		      :: "r" (asid) : "a0", "memory");
+
+	csr_write(CSR_HGATP, hgatp);
+}
+
+void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid,
+				     unsigned long gva, unsigned long gvsz,
+				     unsigned long order)
+{
+	unsigned long pos, hgatp;
+
+	hfence_update_order(order);
+
+	if (PTRS_PER_PTE < (gvsz >> order)) {
+		kvm_riscv_local_hfence_vvma_all(vmid);
+		return;
+	}
+
+	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
+
+	for (pos = gva; pos < (gva + gvsz); pos += BIT(order)) {
+		/*
+		 * rs1 = a0 (GVA)
+		 * rs2 = zero
+		 * HFENCE.VVMA a0
+		 * 0010001 00000 01010 000 00000 1110011
+		 */
+		asm volatile ("add a0, %0, zero\n"
+			      ".word 0x22050073\n"
+			      :: "r" (pos) : "a0", "memory");
+	}
+
+	csr_write(CSR_HGATP, hgatp);
+}
+
+void kvm_riscv_local_hfence_vvma_all(unsigned long vmid)
+{
+	unsigned long hgatp;
+
+	hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT);
+
+	/*
+	 * rs1 = zero
+	 * rs2 = zero
+	 * HFENCE.VVMA
+	 * 0010001 00000 00000 000 00000 1110011
+	 */
+	asm volatile (".word 0x22000073" ::: "memory");
+
+	csr_write(CSR_HGATP, hgatp);
+}
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 0b8073374ed7..dbf6b8d73e23 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -690,7 +690,7 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 			kvm_riscv_gstage_update_hgatp(vcpu);
 
 		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
-			__kvm_riscv_hfence_gvma_all();
+			kvm_riscv_local_hfence_gvma_all();
 	}
 }
 
diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c
index 01fdc342ad76..8987e76aa6db 100644
--- a/arch/riscv/kvm/vmid.c
+++ b/arch/riscv/kvm/vmid.c
@@ -33,7 +33,7 @@ void kvm_riscv_gstage_vmid_detect(void)
 	csr_write(CSR_HGATP, old);
 
 	/* We polluted local TLB so flush all guest TLB */
-	__kvm_riscv_hfence_gvma_all();
+	kvm_riscv_local_hfence_gvma_all();
 
 	/* We don't use VMID bits if they are not sufficient */
 	if ((1UL << vmid_bits) < num_possible_cpus())
-- 
2.25.1