niansa-misc/linux
1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
Code Issues Projects Releases Packages Wiki Activity
linux/arch/powerpc/kvm/emulate_loadstore.c
Jordan Niethe 19d31c5f11 KVM: PPC: Add support for nestedv2 guests 
A series of hcalls have been added to the PAPR which allow a regular
guest partition to create and manage guest partitions of its own. KVM
already had an interface that allowed this on powernv platforms. This
existing interface will now be called "nestedv1". The newly added PAPR
interface will be called "nestedv2".  PHYP will support the nestedv2
interface. At this time the host side of the nestedv2 interface has not
been implemented on powernv but there is no technical reason why it
could not be added.

The nestedv1 interface is still supported.

Add support to KVM to utilize these hcalls to enable running nested
guests as a pseries guest on PHYP.

Overview of the new hcall usage:

- L1 and L0 negotiate capabilities with
  H_GUEST_{G,S}ET_CAPABILITIES()

- L1 requests the L0 create a L2 with
  H_GUEST_CREATE() and receives a handle to use in future hcalls

- L1 requests the L0 create a L2 vCPU with
  H_GUEST_CREATE_VCPU()

- L1 sets up the L2 using H_GUEST_SET and the
  H_GUEST_VCPU_RUN input buffer

- L1 requests the L0 runs the L2 vCPU using H_GUEST_VCPU_RUN()

- L2 returns to L1 with an exit reason and L1 reads the
  H_GUEST_VCPU_RUN output buffer populated by the L0

- L1 handles the exit using H_GET_STATE if necessary

- L1 reruns L2 vCPU with H_GUEST_VCPU_RUN

- L1 frees the L2 in the L0 with H_GUEST_DELETE()

Support for the new API is determined by trying
H_GUEST_GET_CAPABILITIES. On a successful return, use the nestedv2
interface.

Use the vcpu register state setters for tracking modified guest state
elements and copy the thread wide values into the H_GUEST_VCPU_RUN input
buffer immediately before running a L2. The guest wide
elements can not be added to the input buffer so send them with a
separate H_GUEST_SET call if necessary.

Make the vcpu register getter load the corresponding value from the real
host with H_GUEST_GET. To avoid unnecessarily calling H_GUEST_GET, track
which values have already been loaded between H_GUEST_VCPU_RUN calls. If
an element is present in the H_GUEST_VCPU_RUN output buffer it also does
not need to be loaded again.

Tested-by: Sachin Sant <sachinp@linux.ibm.com>
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Gautam Menghani <gautam@linux.ibm.com>
Signed-off-by: Kautuk Consul <kconsul@linux.vnet.ibm.com>
Signed-off-by: Amit Machhiwal <amachhiw@linux.vnet.ibm.com>
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20230914030600.16993-11-jniethe5@gmail.com
2023-09-14 22:04:24 +10:00

368 lines
9.2 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0-only
/*
*
* Copyright IBM Corp. 2007
* Copyright 2011 Freescale Semiconductor, Inc.
*
* Authors: Hollis Blanchard <hollisb@us.ibm.com>
*/
#include <linux/jiffies.h>
#include <linux/hrtimer.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/kvm_host.h>
#include <linux/clockchips.h>
#include <asm/reg.h>
#include <asm/time.h>
#include <asm/byteorder.h>
#include <asm/kvm_ppc.h>
#include <asm/disassemble.h>
#include <asm/ppc-opcode.h>
#include <asm/sstep.h>
#include "timing.h"
#include "trace.h"
#ifdef CONFIG_PPC_FPU
static bool kvmppc_check_fp_disabled(struct kvm_vcpu *vcpu)
{
if (!(kvmppc_get_msr(vcpu) & MSR_FP)) {
kvmppc_core_queue_fpunavail(vcpu, kvmppc_get_msr(vcpu) & SRR1_PREFIXED);
return true;
}
return false;
}
#endif /* CONFIG_PPC_FPU */
#ifdef CONFIG_VSX
static bool kvmppc_check_vsx_disabled(struct kvm_vcpu *vcpu)
{
if (!(kvmppc_get_msr(vcpu) & MSR_VSX)) {
kvmppc_core_queue_vsx_unavail(vcpu, kvmppc_get_msr(vcpu) & SRR1_PREFIXED);
return true;
}
return false;
}
#endif /* CONFIG_VSX */
#ifdef CONFIG_ALTIVEC
static bool kvmppc_check_altivec_disabled(struct kvm_vcpu *vcpu)
{
if (!(kvmppc_get_msr(vcpu) & MSR_VEC)) {
kvmppc_core_queue_vec_unavail(vcpu, kvmppc_get_msr(vcpu) & SRR1_PREFIXED);
return true;
}
return false;
}
#endif /* CONFIG_ALTIVEC */
/*
* XXX to do:
* lfiwax, lfiwzx
* vector loads and stores
*
* Instructions that trap when used on cache-inhibited mappings
* are not emulated here: multiple and string instructions,
* lq/stq, and the load-reserve/store-conditional instructions.
*/
int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
{
ppc_inst_t inst;
enum emulation_result emulated = EMULATE_FAIL;
struct instruction_op op;
/* this default type might be overwritten by subcategories */
kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst);
if (emulated != EMULATE_DONE)
return emulated;
vcpu->arch.mmio_vsx_copy_nums = 0;
vcpu->arch.mmio_vsx_offset = 0;
vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
vcpu->arch.mmio_sp64_extend = 0;
vcpu->arch.mmio_sign_extend = 0;
vcpu->arch.mmio_vmx_copy_nums = 0;
vcpu->arch.mmio_vmx_offset = 0;
vcpu->arch.mmio_host_swabbed = 0;
emulated = EMULATE_FAIL;
vcpu->arch.regs.msr = kvmppc_get_msr(vcpu);
kvmhv_nestedv2_reload_ptregs(vcpu, &vcpu->arch.regs);
if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
int type = op.type & INSTR_TYPE_MASK;
int size = GETSIZE(op.type);
vcpu->mmio_is_write = OP_IS_STORE(type);
switch (type) {
case LOAD: {
int instr_byte_swap = op.type & BYTEREV;
if (op.type & SIGNEXT)
emulated = kvmppc_handle_loads(vcpu,
op.reg, size, !instr_byte_swap);
else
emulated = kvmppc_handle_load(vcpu,
op.reg, size, !instr_byte_swap);
if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
break;
}
#ifdef CONFIG_PPC_FPU
case LOAD_FP:
if (kvmppc_check_fp_disabled(vcpu))
return EMULATE_DONE;
if (op.type & FPCONV)
vcpu->arch.mmio_sp64_extend = 1;
if (op.type & SIGNEXT)
emulated = kvmppc_handle_loads(vcpu,
KVM_MMIO_REG_FPR|op.reg, size, 1);
else
emulated = kvmppc_handle_load(vcpu,
KVM_MMIO_REG_FPR|op.reg, size, 1);
if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
break;
#endif
#ifdef CONFIG_ALTIVEC
case LOAD_VMX:
if (kvmppc_check_altivec_disabled(vcpu))
return EMULATE_DONE;
/* Hardware enforces alignment of VMX accesses */
vcpu->arch.vaddr_accessed &= ~((unsigned long)size - 1);
vcpu->arch.paddr_accessed &= ~((unsigned long)size - 1);
if (size == 16) { /* lvx */
vcpu->arch.mmio_copy_type =
KVMPPC_VMX_COPY_DWORD;
} else if (size == 4) { /* lvewx */
vcpu->arch.mmio_copy_type =
KVMPPC_VMX_COPY_WORD;
} else if (size == 2) { /* lvehx */
vcpu->arch.mmio_copy_type =
KVMPPC_VMX_COPY_HWORD;
} else if (size == 1) { /* lvebx */
vcpu->arch.mmio_copy_type =
KVMPPC_VMX_COPY_BYTE;
} else
break;
vcpu->arch.mmio_vmx_offset =
(vcpu->arch.vaddr_accessed & 0xf)/size;
if (size == 16) {
vcpu->arch.mmio_vmx_copy_nums = 2;
emulated = kvmppc_handle_vmx_load(vcpu,
KVM_MMIO_REG_VMX|op.reg,
8, 1);
} else {
vcpu->arch.mmio_vmx_copy_nums = 1;
emulated = kvmppc_handle_vmx_load(vcpu,
KVM_MMIO_REG_VMX|op.reg,
size, 1);
}
break;
#endif
#ifdef CONFIG_VSX
case LOAD_VSX: {
int io_size_each;
if (op.vsx_flags & VSX_CHECK_VEC) {
if (kvmppc_check_altivec_disabled(vcpu))
return EMULATE_DONE;
} else {
if (kvmppc_check_vsx_disabled(vcpu))
return EMULATE_DONE;
}
if (op.vsx_flags & VSX_FPCONV)
vcpu->arch.mmio_sp64_extend = 1;
if (op.element_size == 8) {
if (op.vsx_flags & VSX_SPLAT)
vcpu->arch.mmio_copy_type =
KVMPPC_VSX_COPY_DWORD_LOAD_DUMP;
else
vcpu->arch.mmio_copy_type =
KVMPPC_VSX_COPY_DWORD;
} else if (op.element_size == 4) {
if (op.vsx_flags & VSX_SPLAT)
vcpu->arch.mmio_copy_type =
KVMPPC_VSX_COPY_WORD_LOAD_DUMP;
else
vcpu->arch.mmio_copy_type =
KVMPPC_VSX_COPY_WORD;
} else
break;
if (size < op.element_size) {
/* precision convert case: lxsspx, etc */
vcpu->arch.mmio_vsx_copy_nums = 1;
io_size_each = size;
} else { /* lxvw4x, lxvd2x, etc */
vcpu->arch.mmio_vsx_copy_nums =
size/op.element_size;
io_size_each = op.element_size;
}
emulated = kvmppc_handle_vsx_load(vcpu,
KVM_MMIO_REG_VSX|op.reg, io_size_each,
1, op.type & SIGNEXT);
break;
}
#endif
case STORE:
/* if need byte reverse, op.val has been reversed by
* analyse_instr().
*/
emulated = kvmppc_handle_store(vcpu, op.val, size, 1);
if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
break;
#ifdef CONFIG_PPC_FPU
case STORE_FP:
if (kvmppc_check_fp_disabled(vcpu))
return EMULATE_DONE;
/* The FP registers need to be flushed so that
* kvmppc_handle_store() can read actual FP vals
* from vcpu->arch.
*/
if (vcpu->kvm->arch.kvm_ops->giveup_ext)
vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
MSR_FP);
if (op.type & FPCONV)
vcpu->arch.mmio_sp64_extend = 1;
emulated = kvmppc_handle_store(vcpu,
kvmppc_get_fpr(vcpu, op.reg), size, 1);
if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
break;
#endif
#ifdef CONFIG_ALTIVEC
case STORE_VMX:
if (kvmppc_check_altivec_disabled(vcpu))
return EMULATE_DONE;
/* Hardware enforces alignment of VMX accesses. */
vcpu->arch.vaddr_accessed &= ~((unsigned long)size - 1);
vcpu->arch.paddr_accessed &= ~((unsigned long)size - 1);
if (vcpu->kvm->arch.kvm_ops->giveup_ext)
vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
MSR_VEC);
if (size == 16) { /* stvx */
vcpu->arch.mmio_copy_type =
KVMPPC_VMX_COPY_DWORD;
} else if (size == 4) { /* stvewx */
vcpu->arch.mmio_copy_type =
KVMPPC_VMX_COPY_WORD;
} else if (size == 2) { /* stvehx */
vcpu->arch.mmio_copy_type =
KVMPPC_VMX_COPY_HWORD;
} else if (size == 1) { /* stvebx */
vcpu->arch.mmio_copy_type =
KVMPPC_VMX_COPY_BYTE;
} else
break;
vcpu->arch.mmio_vmx_offset =
(vcpu->arch.vaddr_accessed & 0xf)/size;
if (size == 16) {
vcpu->arch.mmio_vmx_copy_nums = 2;
emulated = kvmppc_handle_vmx_store(vcpu,
op.reg, 8, 1);
} else {
vcpu->arch.mmio_vmx_copy_nums = 1;
emulated = kvmppc_handle_vmx_store(vcpu,
op.reg, size, 1);
}
break;
#endif
#ifdef CONFIG_VSX
case STORE_VSX: {
int io_size_each;
if (op.vsx_flags & VSX_CHECK_VEC) {
if (kvmppc_check_altivec_disabled(vcpu))
return EMULATE_DONE;
} else {
if (kvmppc_check_vsx_disabled(vcpu))
return EMULATE_DONE;
}
if (vcpu->kvm->arch.kvm_ops->giveup_ext)
vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu,
MSR_VSX);
if (op.vsx_flags & VSX_FPCONV)
vcpu->arch.mmio_sp64_extend = 1;
if (op.element_size == 8)
vcpu->arch.mmio_copy_type =
KVMPPC_VSX_COPY_DWORD;
else if (op.element_size == 4)
vcpu->arch.mmio_copy_type =
KVMPPC_VSX_COPY_WORD;
else
break;
if (size < op.element_size) {
/* precise conversion case, like stxsspx */
vcpu->arch.mmio_vsx_copy_nums = 1;
io_size_each = size;
} else { /* stxvw4x, stxvd2x, etc */
vcpu->arch.mmio_vsx_copy_nums =
size/op.element_size;
io_size_each = op.element_size;
}
emulated = kvmppc_handle_vsx_store(vcpu,
op.reg, io_size_each, 1);
break;
}
#endif
case CACHEOP:
/* Do nothing. The guest is performing dcbi because
* hardware DMA is not snooped by the dcache, but
* emulated DMA either goes through the dcache as
* normal writes, or the host kernel has handled dcache
* coherence.
*/
emulated = EMULATE_DONE;
break;
default:
break;
}
}
trace_kvm_ppc_instr(ppc_inst_val(inst), kvmppc_get_pc(vcpu), emulated);
kvmhv_nestedv2_mark_dirty_ptregs(vcpu, &vcpu->arch.regs);
/* Advance past emulated instruction. */
if (emulated != EMULATE_FAIL)
kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + ppc_inst_len(inst));
return emulated;
}
Reference in a new issue View git blame Copy permalink