On Mon, 23 Dec 2019 03:35:55 PST (-0800), Anup Patel wrote:
This patch implements VCPU create, init and destroy functions
required by generic KVM module. We don't have much dynamic
resources in struct kvm_vcpu_arch so these functions are quite
simple for KVM RISC-V.
Signed-off-by: Anup Patel <anup.patel@xxxxxxx>
Acked-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Reviewed-by: Alexander Graf <graf@xxxxxxxxxx>
---
arch/riscv/include/asm/kvm_host.h | 68 +++++++++++++++++++++++++++++++
arch/riscv/kvm/vcpu.c | 68 +++++++++++++++++++++++++++++--
2 files changed, 132 insertions(+), 4 deletions(-)
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index e0b633f616a4..297431660be6 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -53,7 +53,75 @@ struct kvm_arch {
phys_addr_t pgd_phys;
};
+struct kvm_cpu_context {
+ unsigned long zero;
+ unsigned long ra;
+ unsigned long sp;
+ unsigned long gp;
+ unsigned long tp;
+ unsigned long t0;
+ unsigned long t1;
+ unsigned long t2;
+ unsigned long s0;
+ unsigned long s1;
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+ unsigned long s2;
+ unsigned long s3;
+ unsigned long s4;
+ unsigned long s5;
+ unsigned long s6;
+ unsigned long s7;
+ unsigned long s8;
+ unsigned long s9;
+ unsigned long s10;
+ unsigned long s11;
+ unsigned long t3;
+ unsigned long t4;
+ unsigned long t5;
+ unsigned long t6;
+ unsigned long sepc;
+ unsigned long sstatus;
+ unsigned long hstatus;
+};
Looks like pretty much everyone else is putting 'struct kvm_regs' at the start
of 'struct kvm_cpu_context', which I'm assuming avoids duplication when
implementing KVM_{GET,SET}_REGS. That would probably be cleaner, but if I
think it'd be best to just have this match our mcontext.
+
+struct kvm_vcpu_csr {
+ unsigned long vsstatus;
+ unsigned long hie;
+ unsigned long vstvec;
+ unsigned long vsscratch;
+ unsigned long vsepc;
+ unsigned long vscause;
+ unsigned long vstval;
+ unsigned long hip;
+ unsigned long vsatp;
+};
+
struct kvm_vcpu_arch {
+ /* VCPU ran atleast once */
+ bool ran_atleast_once;
+
+ /* ISA feature bits (similar to MISA) */
+ unsigned long isa;
+
+ /* CPU context of Guest VCPU */
+ struct kvm_cpu_context guest_context;
+
+ /* CPU CSR context of Guest VCPU */
+ struct kvm_vcpu_csr guest_csr;
It looks like other architectures either put the entire CPU state in 'struct
kvm_cpu_context' (arm64, for example) or inline all the definitions (mips, for
example). I'd lean the arm64 way here, but I haven't gotten sufficiently far
until the user ABI to figure out if this would help in a meaningful fashion.
+ /* CPU context upon Guest VCPU reset */
+ struct kvm_cpu_context guest_reset_context;
+
+ /* CPU CSR context upon Guest VCPU reset */
+ struct kvm_vcpu_csr guest_reset_csr;
+
/* Don't run the VCPU (blocked) */
bool pause;
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index bd7d6b154f61..cf8ca8d4a9ea 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -31,10 +31,48 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ NULL }
};
+#define KVM_RISCV_ISA_ALLOWED (riscv_isa_extension_mask(a) | \
+ riscv_isa_extension_mask(c) | \
+ riscv_isa_extension_mask(d) | \
+ riscv_isa_extension_mask(f) | \
+ riscv_isa_extension_mask(i) | \
+ riscv_isa_extension_mask(m) | \
+ riscv_isa_extension_mask(s) | \
+ riscv_isa_extension_mask(u))
+
+static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+ struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
+ struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+ struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context;
+
+ memcpy(csr, reset_csr, sizeof(*csr));
+
+ memcpy(cntx, reset_cntx, sizeof(*cntx));
+}
+
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
{
- /* TODO: */
- return NULL;
+ int err;
+ struct kvm_vcpu *vcpu;
+
+ vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+ if (!vcpu) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ err = kvm_vcpu_init(vcpu, kvm, id);
+ if (err)
+ goto free_vcpu;
+
+ return vcpu;
+
+free_vcpu:
+ kmem_cache_free(kvm_vcpu_cache, vcpu);
+out:
+ return ERR_PTR(err);
}
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
@@ -48,13 +86,32 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
- /* TODO: */
+ struct kvm_cpu_context *cntx;
+
+ /* Mark this VCPU never ran */
+ vcpu->arch.ran_atleast_once = false;
+
+ /* Setup ISA features available to VCPU */
+ vcpu->arch.isa = riscv_isa_extension_base(NULL) & KVM_RISCV_ISA_ALLOWED;
+
+ /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */
+ cntx = &vcpu->arch.guest_reset_context;
+ cntx->sstatus = SR_SPP | SR_SPIE;
+ cntx->hstatus = 0;
+ cntx->hstatus |= HSTATUS_SP2V;
+ cntx->hstatus |= HSTATUS_SP2P;
+ cntx->hstatus |= HSTATUS_SPV;
+
+ /* Reset VCPU */
+ kvm_riscv_reset_vcpu(vcpu);
+
return 0;
}
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
- /* TODO: */
+ kvm_riscv_stage2_flush_cache(vcpu);
There needs to be a comment as to why there's a flush here.
The definition of kvm_riscv_stage2_flush_cache() should also have a comment
describing what it actually does.
+ kmem_cache_free(kvm_vcpu_cache, vcpu);
}
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
@@ -199,6 +256,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
int ret;
unsigned long scause, stval, htval, htinst;
+ /* Mark this VCPU ran atleast once */
+ vcpu->arch.ran_atleast_once = true;
I'm having some trouble figuring out how this doesn't have a race condition,
but that's probably more applicable to the patch that uses it. Also, a bit of
a nit pick: "at least" is two words. I don't care that much about the variable
name, but the comments should use real words.
+
vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
/* Process MMIO value returned from user-space */
--
2.17.1
