Received-SPF: pass (google.com: domain of linux-kernel+bounces-89361-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: Bibo Mao <maobibo@loongson.cn>
To: Huacai Chen <chenhuacai@kernel.org>,
	Tianrui Zhao <zhaotianrui@loongson.cn>,
	Juergen Gross <jgross@suse.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Jonathan Corbet <corbet@lwn.net>
Cc: loongarch@lists.linux.dev,
	linux-kernel@vger.kernel.org,
	virtualization@lists.linux.dev,
	kvm@vger.kernel.org,
	linux-doc@vger.kernel.org
Subject: [PATCH v6 5/7] LoongArch: KVM: Add pv ipi support on kvm side
Date: Sat,  2 Mar 2024 15:51:18 +0800
Message-Id: <20240302075120.1414999-6-maobibo@loongson.cn>
In-Reply-To: <20240302075120.1414999-1-maobibo@loongson.cn>
References: <20240302075120.1414999-1-maobibo@loongson.cn>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

On LoongArch system, ipi hw uses iocsr registers, there is one iocsr
register access on ipi sending, and two iocsr access on ipi receiving
which is ipi interrupt handler. On VM mode all iocsr accessing will
cause VM to trap into hypervisor. So with one ipi hw notification
there will be three times of trap.

PV ipi is added for VM, hypercall instruction is used for ipi sender,
and hypervisor will inject SWI to destination vcpu. During SWI interrupt
handler, only estat CSR register is written to clear irq. Estat CSR
register access will not trap into hypervisor. So with pv ipi supported,
there is one trap with pv ipi sender, and no trap with ipi receiver,
there is only one trap with ipi notification.

Also this patch adds ipi multicast support, the method is similar with
x86. With ipi multicast support, ipi notification can be sent to at most
128 vcpus at one time. It reduces trap times into hypervisor greatly.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
---
 arch/loongarch/include/asm/kvm_host.h  |   1 +
 arch/loongarch/include/asm/kvm_para.h  | 130 +++++++++++++++++++++++++
 arch/loongarch/include/asm/loongarch.h |   1 +
 arch/loongarch/kvm/exit.c              |  76 ++++++++++++++-
 arch/loongarch/kvm/vcpu.c              |   1 +
 5 files changed, 207 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 3ba16ef1fe69..0b96c6303cf7 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -43,6 +43,7 @@ struct kvm_vcpu_stat {
 	u64 idle_exits;
 	u64 cpucfg_exits;
 	u64 signal_exits;
+	u64 hypercall_exits;
 };
 
 #define KVM_MEM_HUGEPAGE_CAPABLE	(1UL << 0)
diff --git a/arch/loongarch/include/asm/kvm_para.h b/arch/loongarch/include/asm/kvm_para.h
index d48f993ae206..a82bffbbf8a1 100644
--- a/arch/loongarch/include/asm/kvm_para.h
+++ b/arch/loongarch/include/asm/kvm_para.h
@@ -2,6 +2,16 @@
 #ifndef _ASM_LOONGARCH_KVM_PARA_H
 #define _ASM_LOONGARCH_KVM_PARA_H
 
+/*
+ * Hypercall code field
+ */
+#define HYPERVISOR_KVM			1
+#define HYPERVISOR_VENDOR_SHIFT		8
+#define HYPERCALL_CODE(vendor, code)	((vendor << HYPERVISOR_VENDOR_SHIFT) + code)
+#define KVM_HCALL_CODE_PV_SERVICE	0
+#define KVM_HCALL_PV_SERVICE		HYPERCALL_CODE(HYPERVISOR_KVM, KVM_HCALL_CODE_PV_SERVICE)
+#define  KVM_HCALL_FUNC_PV_IPI		1
+
 /*
  * LoongArch hypercall return code
  */
@@ -9,6 +19,126 @@
 #define KVM_HCALL_INVALID_CODE		-1UL
 #define KVM_HCALL_INVALID_PARAMETER	-2UL
 
+/*
+ * Hypercall interface for KVM hypervisor
+ *
+ * a0: function identifier
+ * a1-a6: args
+ * Return value will be placed in v0.
+ * Up to 6 arguments are passed in a1, a2, a3, a4, a5, a6.
+ */
+static __always_inline long kvm_hypercall(u64 fid)
+{
+	register long ret asm("v0");
+	register unsigned long fun asm("a0") = fid;
+
+	__asm__ __volatile__(
+		"hvcl "__stringify(KVM_HCALL_PV_SERVICE)
+		: "=r" (ret)
+		: "r" (fun)
+		: "memory"
+		);
+
+	return ret;
+}
+
+static __always_inline long kvm_hypercall1(u64 fid, unsigned long arg0)
+{
+	register long ret asm("v0");
+	register unsigned long fun asm("a0") = fid;
+	register unsigned long a1  asm("a1") = arg0;
+
+	__asm__ __volatile__(
+		"hvcl "__stringify(KVM_HCALL_PV_SERVICE)
+		: "=r" (ret)
+		: "r" (fun), "r" (a1)
+		: "memory"
+		);
+
+	return ret;
+}
+
+static __always_inline long kvm_hypercall2(u64 fid,
+		unsigned long arg0, unsigned long arg1)
+{
+	register long ret asm("v0");
+	register unsigned long fun asm("a0") = fid;
+	register unsigned long a1  asm("a1") = arg0;
+	register unsigned long a2  asm("a2") = arg1;
+
+	__asm__ __volatile__(
+			"hvcl "__stringify(KVM_HCALL_PV_SERVICE)
+			: "=r" (ret)
+			: "r" (fun), "r" (a1), "r" (a2)
+			: "memory"
+			);
+
+	return ret;
+}
+
+static __always_inline long kvm_hypercall3(u64 fid,
+	unsigned long arg0, unsigned long arg1, unsigned long arg2)
+{
+	register long ret asm("v0");
+	register unsigned long fun asm("a0") = fid;
+	register unsigned long a1  asm("a1") = arg0;
+	register unsigned long a2  asm("a2") = arg1;
+	register unsigned long a3  asm("a3") = arg2;
+
+	__asm__ __volatile__(
+		"hvcl "__stringify(KVM_HCALL_PV_SERVICE)
+		: "=r" (ret)
+		: "r" (fun), "r" (a1), "r" (a2), "r" (a3)
+		: "memory"
+		);
+
+	return ret;
+}
+
+static __always_inline long kvm_hypercall4(u64 fid,
+		unsigned long arg0, unsigned long arg1, unsigned long arg2,
+		unsigned long arg3)
+{
+	register long ret asm("v0");
+	register unsigned long fun asm("a0") = fid;
+	register unsigned long a1  asm("a1") = arg0;
+	register unsigned long a2  asm("a2") = arg1;
+	register unsigned long a3  asm("a3") = arg2;
+	register unsigned long a4  asm("a4") = arg3;
+
+	__asm__ __volatile__(
+		"hvcl "__stringify(KVM_HCALL_PV_SERVICE)
+		: "=r" (ret)
+		: "r"(fun), "r" (a1), "r" (a2), "r" (a3), "r" (a4)
+		: "memory"
+		);
+
+	return ret;
+}
+
+static __always_inline long kvm_hypercall5(u64 fid,
+		unsigned long arg0, unsigned long arg1, unsigned long arg2,
+		unsigned long arg3, unsigned long arg4)
+{
+	register long ret asm("v0");
+	register unsigned long fun asm("a0") = fid;
+	register unsigned long a1  asm("a1") = arg0;
+	register unsigned long a2  asm("a2") = arg1;
+	register unsigned long a3  asm("a3") = arg2;
+	register unsigned long a4  asm("a4") = arg3;
+	register unsigned long a5  asm("a5") = arg4;
+
+	__asm__ __volatile__(
+		"hvcl "__stringify(KVM_HCALL_PV_SERVICE)
+		: "=r" (ret)
+		: "r"(fun), "r" (a1), "r" (a2), "r" (a3), "r" (a4), "r" (a5)
+		: "memory"
+		);
+
+	return ret;
+}
+
+
 static inline unsigned int kvm_arch_para_features(void)
 {
 	return 0;
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index a1d22e8b6f94..0ad36704cb4b 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -167,6 +167,7 @@
 #define CPUCFG_KVM_SIG			CPUCFG_KVM_BASE
 #define  KVM_SIGNATURE			"KVM\0"
 #define CPUCFG_KVM_FEATURE		(CPUCFG_KVM_BASE + 4)
+#define  KVM_FEATURE_PV_IPI		BIT(1)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index a8d3b652d3ea..933879ad0ddc 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -239,6 +239,12 @@ static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst)
 		else
 			vcpu->arch.gprs[rd] = 0;
 		break;
+	case CPUCFG_KVM_FEATURE:
+		if ((plv & CSR_CRMD_PLV) == PLV_KERN)
+			vcpu->arch.gprs[rd] = KVM_FEATURE_PV_IPI;
+		else
+			vcpu->arch.gprs[rd] = 0;
+		break;
 	default:
 		vcpu->arch.gprs[rd] = 0;
 		break;
@@ -712,12 +718,78 @@ static int kvm_handle_lasx_disabled(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
+static int kvm_pv_send_ipi(struct kvm_vcpu *vcpu)
+{
+	unsigned long ipi_bitmap;
+	unsigned int min, cpu, i;
+	struct kvm_vcpu *dest;
+
+	min = vcpu->arch.gprs[LOONGARCH_GPR_A3];
+	for (i = 0; i < 2; i++, min += BITS_PER_LONG) {
+		ipi_bitmap = vcpu->arch.gprs[LOONGARCH_GPR_A1 + i];
+		if (!ipi_bitmap)
+			continue;
+
+		cpu = find_first_bit((void *)&ipi_bitmap, BITS_PER_LONG);
+		while (cpu < BITS_PER_LONG) {
+			dest = kvm_get_vcpu_by_cpuid(vcpu->kvm, cpu + min);
+			cpu = find_next_bit((void *)&ipi_bitmap, BITS_PER_LONG,
+					cpu + 1);
+			if (!dest)
+				continue;
+
+			/*
+			 * Send SWI0 to dest vcpu to emulate IPI interrupt
+			 */
+			kvm_queue_irq(dest, INT_SWI0);
+			kvm_vcpu_kick(dest);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * hypercall emulation always return to guest, Caller should check retval.
+ */
+static void kvm_handle_pv_service(struct kvm_vcpu *vcpu)
+{
+	unsigned long func = vcpu->arch.gprs[LOONGARCH_GPR_A0];
+	long ret;
+
+	switch (func) {
+	case KVM_HCALL_FUNC_PV_IPI:
+		kvm_pv_send_ipi(vcpu);
+		ret = KVM_HCALL_STATUS_SUCCESS;
+		break;
+	default:
+		ret = KVM_HCALL_INVALID_CODE;
+		break;
+	};
+
+	vcpu->arch.gprs[LOONGARCH_GPR_A0] = ret;
+}
+
 static int kvm_handle_hypercall(struct kvm_vcpu *vcpu)
 {
+	larch_inst inst;
+	unsigned int code;
+
+	inst.word = vcpu->arch.badi;
+	code = inst.reg0i15_format.immediate;
 	update_pc(&vcpu->arch);
 
-	/* Treat it as noop intruction, only set return value */
-	vcpu->arch.gprs[LOONGARCH_GPR_A0] = KVM_HCALL_INVALID_CODE;
+	switch (code) {
+	case KVM_HCALL_PV_SERVICE:
+		vcpu->stat.hypercall_exits++;
+		kvm_handle_pv_service(vcpu);
+		break;
+	default:
+		/* Treat it as noop intruction, only set return value */
+		vcpu->arch.gprs[LOONGARCH_GPR_A0] = KVM_HCALL_INVALID_CODE;
+		break;
+	}
+
 	return RESUME_GUEST;
 }
 
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index a1a1dc4a3cf2..5a4b0db9c36f 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -19,6 +19,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, idle_exits),
 	STATS_DESC_COUNTER(VCPU, cpucfg_exits),
 	STATS_DESC_COUNTER(VCPU, signal_exits),
+	STATS_DESC_COUNTER(VCPU, hypercall_exits)
 };
 
 const struct kvm_stats_header kvm_vcpu_stats_header = {
-- 
2.39.3