kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Anup Patel <Anup.Patel@wdc.com>
To: Palmer Dabbelt <palmer@sifive.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Paolo Bonzini <pbonzini@redhat.com>, Radim K <rkrcmar@redhat.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Atish Patra <Atish.Patra@wdc.com>,
	Alistair Francis <Alistair.Francis@wdc.com>,
	Damien Le Moal <Damien.LeMoal@wdc.com>,
	Christoph Hellwig <hch@infradead.org>,
	Anup Patel <anup@brainfault.org>,
	"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	"linux-riscv@lists.infradead.org"
	<linux-riscv@lists.infradead.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Anup Patel <Anup.Patel@wdc.com>
Subject: [PATCH v5 12/20] RISC-V: KVM: Implement VMID allocator
Date: Thu, 22 Aug 2019 08:45:19 +0000	[thread overview]
Message-ID: <20190822084131.114764-13-anup.patel@wdc.com> (raw)
In-Reply-To: <20190822084131.114764-1-anup.patel@wdc.com>

We implement a simple VMID allocator for Guests/VMs which:
1. Detects number of VMID bits at boot-time
2. Uses atomic number to track VMID version and increments
   VMID version whenever we run-out of VMIDs
3. Flushes Guest TLBs on all host CPUs whenever we run-out
   of VMIDs
4. Force updates HW Stage2 VMID for each Guest VCPU whenever
   VMID changes using VCPU request KVM_REQ_UPDATE_HGATP

Signed-off-by: Anup Patel <anup.patel@wdc.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/riscv/include/asm/kvm_host.h |  25 ++++++
 arch/riscv/kvm/Makefile           |   3 +-
 arch/riscv/kvm/main.c             |   4 +
 arch/riscv/kvm/tlb.S              |  43 +++++++++++
 arch/riscv/kvm/vcpu.c             |   9 +++
 arch/riscv/kvm/vm.c               |   6 ++
 arch/riscv/kvm/vmid.c             | 123 ++++++++++++++++++++++++++++++
 7 files changed, 212 insertions(+), 1 deletion(-)
 create mode 100644 arch/riscv/kvm/tlb.S
 create mode 100644 arch/riscv/kvm/vmid.c

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 4388bace6d70..3b09158f80f2 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
 #define KVM_REQ_SLEEP \
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_VCPU_RESET		KVM_ARCH_REQ(1)
+#define KVM_REQ_UPDATE_HGATP		KVM_ARCH_REQ(2)
 
 struct kvm_vm_stat {
 	ulong remote_tlb_flush;
@@ -47,7 +48,19 @@ struct kvm_vcpu_stat {
 struct kvm_arch_memory_slot {
 };
 
+struct kvm_vmid {
+	/*
+	 * Writes to vmid_version and vmid happen with vmid_lock held
+	 * whereas reads happen without any lock held.
+	 */
+	unsigned long vmid_version;
+	unsigned long vmid;
+};
+
 struct kvm_arch {
+	/* stage2 vmid */
+	struct kvm_vmid vmid;
+
 	/* stage2 page table */
 	pgd_t *pgd;
 	phys_addr_t pgd_phys;
@@ -169,6 +182,12 @@ static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 int kvm_riscv_setup_vsip(void);
 void kvm_riscv_cleanup_vsip(void);
 
+extern void __kvm_riscv_hfence_gvma_vmid_gpa(unsigned long vmid,
+					     unsigned long gpa);
+extern void __kvm_riscv_hfence_gvma_vmid(unsigned long vmid);
+extern void __kvm_riscv_hfence_gvma_gpa(unsigned long gpa);
+extern void __kvm_riscv_hfence_gvma_all(void);
+
 int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned long hva,
 			 bool is_write);
 void kvm_riscv_stage2_flush_cache(struct kvm_vcpu *vcpu);
@@ -176,6 +195,12 @@ int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm);
 void kvm_riscv_stage2_free_pgd(struct kvm *kvm);
 void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu);
 
+void kvm_riscv_stage2_vmid_detect(void);
+unsigned long kvm_riscv_stage2_vmid_bits(void);
+int kvm_riscv_stage2_vmid_init(struct kvm *kvm);
+bool kvm_riscv_stage2_vmid_ver_changed(struct kvm_vmid *vmid);
+void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu);
+
 int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			unsigned long scause, unsigned long stval);
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
index 845579273727..c0f57f26c13d 100644
--- a/arch/riscv/kvm/Makefile
+++ b/arch/riscv/kvm/Makefile
@@ -8,6 +8,7 @@ ccflags-y := -Ivirt/kvm -Iarch/riscv/kvm
 
 kvm-objs := $(common-objs-y)
 
-kvm-objs += main.o vm.o mmu.o vcpu.o vcpu_exit.o vcpu_switch.o
+kvm-objs += main.o vm.o vmid.o tlb.o mmu.o
+kvm-objs += vcpu.o vcpu_exit.o vcpu_switch.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c
index d088247843c5..55df85184241 100644
--- a/arch/riscv/kvm/main.c
+++ b/arch/riscv/kvm/main.c
@@ -72,8 +72,12 @@ int kvm_arch_init(void *opaque)
 	if (ret)
 		return ret;
 
+	kvm_riscv_stage2_vmid_detect();
+
 	kvm_info("hypervisor extension available\n");
 
+	kvm_info("host has %ld VMID bits\n", kvm_riscv_stage2_vmid_bits());
+
 	return 0;
 }
 
diff --git a/arch/riscv/kvm/tlb.S b/arch/riscv/kvm/tlb.S
new file mode 100644
index 000000000000..453fca8d7940
--- /dev/null
+++ b/arch/riscv/kvm/tlb.S
@@ -0,0 +1,43 @@
+/* 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:
+	 * 0110001 rs2(5) rs1(5) 000 00000 1110011
+	 */
+
+ENTRY(__kvm_riscv_hfence_gvma_vmid_gpa)
+	/* hfence.gvma a1, a0 */
+	.word 0x62a60073
+	ret
+ENDPROC(__kvm_riscv_hfence_gvma_vmid_gpa)
+
+ENTRY(__kvm_riscv_hfence_gvma_vmid)
+	/* hfence.gvma zero, a0 */
+	.word 0x62a00073
+	ret
+ENDPROC(__kvm_riscv_hfence_gvma_vmid)
+
+ENTRY(__kvm_riscv_hfence_gvma_gpa)
+	/* hfence.gvma a0 */
+	.word 0x62050073
+	ret
+ENDPROC(__kvm_riscv_hfence_gvma_gpa)
+
+ENTRY(__kvm_riscv_hfence_gvma_all)
+	/* hfence.gvma */
+	.word 0x62000073
+	ret
+ENDPROC(__kvm_riscv_hfence_gvma_all)
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index e6d74a9a2fdf..6124077d154f 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -628,6 +628,12 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
 			kvm_riscv_reset_vcpu(vcpu);
+
+		if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu))
+			kvm_riscv_stage2_update_hgatp(vcpu);
+
+		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
+			__kvm_riscv_hfence_gvma_all();
 	}
 }
 
@@ -690,6 +696,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		/* Check conditions before entering the guest */
 		cond_resched();
 
+		kvm_riscv_stage2_vmid_update(vcpu);
+
 		kvm_riscv_check_vcpu_requests(vcpu);
 
 		preempt_disable();
@@ -726,6 +734,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		kvm_riscv_update_vsip(vcpu);
 
 		if (ret <= 0 ||
+		    kvm_riscv_stage2_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
 		    kvm_request_pending(vcpu)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			local_irq_enable();
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index ac0211820521..c5aab5478c38 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -26,6 +26,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (r)
 		return r;
 
+	r = kvm_riscv_stage2_vmid_init(kvm);
+	if (r) {
+		kvm_riscv_stage2_free_pgd(kvm);
+		return r;
+	}
+
 	return 0;
 }
 
diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c
new file mode 100644
index 000000000000..8154feea12d5
--- /dev/null
+++ b/arch/riscv/kvm/vmid.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Anup Patel <anup.patel@wdc.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/kvm_host.h>
+#include <asm/csr.h>
+
+static unsigned long vmid_version = 1;
+static unsigned long vmid_next;
+static unsigned long vmid_bits;
+static DEFINE_SPINLOCK(vmid_lock);
+
+void kvm_riscv_stage2_vmid_detect(void)
+{
+	unsigned long old;
+
+	/* Figure-out number of VMID bits in HW */
+	old = csr_read(CSR_HGATP);
+	csr_write(CSR_HGATP, old | HGATP_VMID_MASK);
+	vmid_bits = csr_read(CSR_HGATP);
+	vmid_bits = (vmid_bits & HGATP_VMID_MASK) >> HGATP_VMID_SHIFT;
+	vmid_bits = fls_long(vmid_bits);
+	csr_write(CSR_HGATP, old);
+
+	/* We polluted local TLB so flush all guest TLB */
+	__kvm_riscv_hfence_gvma_all();
+
+	/* We don't use VMID bits if they are not sufficient */
+	if ((1UL << vmid_bits) < num_possible_cpus())
+		vmid_bits = 0;
+}
+
+unsigned long kvm_riscv_stage2_vmid_bits(void)
+{
+	return vmid_bits;
+}
+
+int kvm_riscv_stage2_vmid_init(struct kvm *kvm)
+{
+	/* Mark the initial VMID and VMID version invalid */
+	kvm->arch.vmid.vmid_version = 0;
+	kvm->arch.vmid.vmid = 0;
+
+	return 0;
+}
+
+static void local_guest_tlb_flush_all(void *info)
+{
+	__kvm_riscv_hfence_gvma_all();
+}
+
+bool kvm_riscv_stage2_vmid_ver_changed(struct kvm_vmid *vmid)
+{
+	if (!vmid_bits)
+		return false;
+
+	return unlikely(READ_ONCE(vmid->vmid_version) !=
+			READ_ONCE(vmid_version));
+}
+
+void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_vcpu *v;
+	struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid;
+
+	if (!kvm_riscv_stage2_vmid_ver_changed(vmid))
+		return;
+
+	spin_lock(&vmid_lock);
+
+	/*
+	 * We need to re-check the vmid_version here to ensure that if
+	 * another vcpu already allocated a valid vmid for this vm.
+	 */
+	if (!kvm_riscv_stage2_vmid_ver_changed(vmid)) {
+		spin_unlock(&vmid_lock);
+		return;
+	}
+
+	/* First user of a new VMID version? */
+	if (unlikely(vmid_next == 0)) {
+		WRITE_ONCE(vmid_version, READ_ONCE(vmid_version) + 1);
+		vmid_next = 1;
+
+		/*
+		 * We ran out of VMIDs so we increment vmid_version and
+		 * start assigning VMIDs from 1.
+		 *
+		 * This also means existing VMIDs assignement to all Guest
+		 * instances is invalid and we have force VMID re-assignement
+		 * for all Guest instances. The Guest instances that were not
+		 * running will automatically pick-up new VMIDs because will
+		 * call kvm_riscv_stage2_vmid_update() whenever they enter
+		 * in-kernel run loop. For Guest instances that are already
+		 * running, we force VM exits on all host CPUs using IPI and
+		 * flush all Guest TLBs.
+		 */
+		smp_call_function_many(cpu_all_mask, local_guest_tlb_flush_all,
+				       NULL, true);
+	}
+
+	vmid->vmid = vmid_next;
+	vmid_next++;
+	vmid_next &= (1 << vmid_bits) - 1;
+
+	WRITE_ONCE(vmid->vmid_version, READ_ONCE(vmid_version));
+
+	spin_unlock(&vmid_lock);
+
+	/* Request stage2 page table update for all VCPUs */
+	kvm_for_each_vcpu(i, v, vcpu->kvm)
+		kvm_make_request(KVM_REQ_UPDATE_HGATP, v);
+}
-- 
2.17.1


  parent reply	other threads:[~2019-08-22  8:45 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-22  8:42 [PATCH v5 00/20] KVM RISC-V Support Anup Patel
2019-08-22  8:42 ` [PATCH v5 01/20] KVM: RISC-V: Add KVM_REG_RISCV for ONE_REG interface Anup Patel
2019-08-22  8:42 ` [PATCH v5 02/20] RISC-V: Add bitmap reprensenting ISA features common across CPUs Anup Patel
2019-08-22  8:43 ` [PATCH v5 03/20] RISC-V: Export few kernel symbols Anup Patel
2019-08-22  8:43 ` [PATCH v5 04/20] RISC-V: Add hypervisor extension related CSR defines Anup Patel
2019-08-22  8:43 ` [PATCH v5 05/20] RISC-V: Add initial skeletal KVM support Anup Patel
2019-08-22  8:43 ` [PATCH v5 06/20] RISC-V: KVM: Implement VCPU create, init and destroy functions Anup Patel
2019-08-22  8:44 ` [PATCH v5 07/20] RISC-V: KVM: Implement VCPU interrupts and requests handling Anup Patel
2019-08-22  8:44 ` [PATCH v5 08/20] RISC-V: KVM: Implement KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls Anup Patel
2019-08-22 12:01   ` Alexander Graf
2019-08-22 14:00     ` Anup Patel
2019-08-22 14:12       ` Alexander Graf
2019-08-23 11:20         ` Anup Patel
2019-08-23 11:42           ` Graf (AWS), Alexander
2019-08-22 14:05     ` Anup Patel
2019-08-22  8:44 ` [PATCH v5 09/20] RISC-V: KVM: Implement VCPU world-switch Anup Patel
2019-08-22  8:44 ` [PATCH v5 10/20] RISC-V: KVM: Handle MMIO exits for VCPU Anup Patel
2019-08-22 12:10   ` Alexander Graf
2019-08-22 12:21     ` Andrew Jones
2019-08-22 12:27     ` Anup Patel
2019-08-22 12:14   ` Alexander Graf
2019-08-22 12:33     ` Anup Patel
2019-08-22 13:25       ` Alexander Graf
2019-08-22 13:55         ` Anup Patel
2019-08-22  8:45 ` [PATCH v5 11/20] RISC-V: KVM: Handle WFI " Anup Patel
2019-08-22 12:19   ` Alexander Graf
2019-08-22 12:50     ` Anup Patel
2019-08-22  8:45 ` Anup Patel [this message]
2019-08-22  8:45 ` [PATCH v5 13/20] RISC-V: KVM: Implement stage2 page table programming Anup Patel
2019-08-22 12:28   ` Alexander Graf
2019-08-22 12:38     ` Anup Patel
2019-08-22 13:27       ` Alexander Graf
2019-08-22 13:58         ` Anup Patel
2019-08-22 14:09           ` Alexander Graf
2019-08-23 11:21             ` Anup Patel
2019-08-22  8:45 ` [PATCH v5 14/20] RISC-V: KVM: Implement MMU notifiers Anup Patel
2019-08-22  8:46 ` [PATCH v5 15/20] RISC-V: KVM: Add timer functionality Anup Patel
2019-08-23  7:52   ` Alexander Graf
2019-08-23 11:04     ` Anup Patel
2019-08-23 11:33       ` Graf (AWS), Alexander
2019-08-23 11:46         ` Anup Patel
2019-08-23 11:49           ` Alexander Graf
2019-08-23 12:11             ` Anup Patel
2019-08-23 12:25               ` Alexander Graf
2019-08-22  8:46 ` [PATCH v5 16/20] RISC-V: KVM: FP lazy save/restore Anup Patel
2019-08-22  8:46 ` [PATCH v5 17/20] RISC-V: KVM: Implement ONE REG interface for FP registers Anup Patel
2019-08-22  8:46 ` [PATCH v5 18/20] RISC-V: KVM: Add SBI v0.1 support Anup Patel
2019-08-23  8:04   ` Alexander Graf
2019-08-23 11:17     ` Anup Patel
2019-08-23 11:38       ` Graf (AWS), Alexander
2019-08-23 12:00         ` Anup Patel
2019-08-23 12:19           ` Alexander Graf
2019-08-23 12:28             ` Anup Patel
2019-08-22  8:47 ` [PATCH v5 19/20] RISC-V: Enable VIRTIO drivers in RV64 and RV32 defconfig Anup Patel
2019-08-22  8:47 ` [PATCH v5 20/20] RISC-V: KVM: Add MAINTAINERS entry Anup Patel
2019-08-23  8:08 ` [PATCH v5 00/20] KVM RISC-V Support Alexander Graf
2019-08-23 11:25   ` Anup Patel
2019-08-23 11:44     ` Graf (AWS), Alexander
2019-08-23 12:10       ` Paolo Bonzini
2019-08-23 12:19         ` Anup Patel
2019-08-23 12:28           ` Alexander Graf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190822084131.114764-13-anup.patel@wdc.com \
    --to=anup.patel@wdc.com \
    --cc=Alistair.Francis@wdc.com \
    --cc=Atish.Patra@wdc.com \
    --cc=Damien.LeMoal@wdc.com \
    --cc=anup@brainfault.org \
    --cc=daniel.lezcano@linaro.org \
    --cc=hch@infradead.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=palmer@sifive.com \
    --cc=paul.walmsley@sifive.com \
    --cc=pbonzini@redhat.com \
    --cc=rkrcmar@redhat.com \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).