KVM: ppc: E500 core-specific code

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This commit is contained in:
Hollis Blanchard 2009-01-03 16:23:10 -06:00 committed by Avi Kivity
parent 17c885eb5c
commit bc8080cbcc
7 changed files with 1330 additions and 0 deletions

View File

@ -0,0 +1,67 @@
/*
* Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Yu Liu, <yu.liu@freescale.com>
*
* Description:
* This file is derived from arch/powerpc/include/asm/kvm_44x.h,
* by Hollis Blanchard <hollisb@us.ibm.com>.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2, as
* published by the Free Software Foundation.
*/
#ifndef __ASM_KVM_E500_H__
#define __ASM_KVM_E500_H__
#include <linux/kvm_host.h>
#define BOOKE_INTERRUPT_SIZE 36
#define E500_PID_NUM 3
#define E500_TLB_NUM 2
struct tlbe{
u32 mas1;
u32 mas2;
u32 mas3;
u32 mas7;
};
struct kvmppc_vcpu_e500 {
/* Unmodified copy of the guest's TLB. */
struct tlbe *guest_tlb[E500_TLB_NUM];
/* TLB that's actually used when the guest is running. */
struct tlbe *shadow_tlb[E500_TLB_NUM];
/* Pages which are referenced in the shadow TLB. */
struct page **shadow_pages[E500_TLB_NUM];
unsigned int guest_tlb_size[E500_TLB_NUM];
unsigned int shadow_tlb_size[E500_TLB_NUM];
unsigned int guest_tlb_nv[E500_TLB_NUM];
u32 host_pid[E500_PID_NUM];
u32 pid[E500_PID_NUM];
u32 mas0;
u32 mas1;
u32 mas2;
u32 mas3;
u32 mas4;
u32 mas5;
u32 mas6;
u32 mas7;
u32 l1csr1;
u32 hid0;
u32 hid1;
struct kvm_vcpu vcpu;
};
static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
{
return container_of(vcpu, struct kvmppc_vcpu_e500, vcpu);
}
#endif /* __ASM_KVM_E500_H__ */

View File

@ -43,6 +43,19 @@ config KVM_EXIT_TIMING
If unsure, say N.
config KVM_E500
bool "KVM support for PowerPC E500 processors"
depends on EXPERIMENTAL && E500
select KVM
---help---
Support running unmodified E500 guest kernels in virtual machines on
E500 host processors.
This module provides access to the hardware capabilities through
a character device node named /dev/kvm.
If unsure, say N.
config KVM_TRACE
bool "KVM trace support"
depends on KVM && MARKERS && SYSFS

View File

@ -22,3 +22,12 @@ kvm-440-objs := \
44x_tlb.o \
44x_emulate.o
obj-$(CONFIG_KVM_440) += kvm-440.o
kvm-e500-objs := \
booke.o \
booke_emulate.o \
booke_interrupts.o \
e500.o \
e500_tlb.o \
e500_emulate.o
obj-$(CONFIG_KVM_E500) += kvm-e500.o

151
arch/powerpc/kvm/e500.c Normal file
View File

@ -0,0 +1,151 @@
/*
* Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Yu Liu, <yu.liu@freescale.com>
*
* Description:
* This file is derived from arch/powerpc/kvm/44x.c,
* by Hollis Blanchard <hollisb@us.ibm.com>.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2, as
* published by the Free Software Foundation.
*/
#include <linux/kvm_host.h>
#include <linux/err.h>
#include <asm/reg.h>
#include <asm/cputable.h>
#include <asm/tlbflush.h>
#include <asm/kvm_e500.h>
#include <asm/kvm_ppc.h>
#include "e500_tlb.h"
void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
{
}
void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
{
}
void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
kvmppc_e500_tlb_load(vcpu, cpu);
}
void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
{
kvmppc_e500_tlb_put(vcpu);
}
int kvmppc_core_check_processor_compat(void)
{
int r;
if (strcmp(cur_cpu_spec->cpu_name, "e500v2") == 0)
r = 0;
else
r = -ENOTSUPP;
return r;
}
int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
kvmppc_e500_tlb_setup(vcpu_e500);
/* Use the same core vertion as host's */
vcpu->arch.pvr = mfspr(SPRN_PVR);
return 0;
}
/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
struct kvm_translation *tr)
{
int index;
gva_t eaddr;
u8 pid;
u8 as;
eaddr = tr->linear_address;
pid = (tr->linear_address >> 32) & 0xff;
as = (tr->linear_address >> 40) & 0x1;
index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
if (index < 0) {
tr->valid = 0;
return 0;
}
tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
/* XXX what does "writeable" and "usermode" even mean? */
tr->valid = 1;
return 0;
}
struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
{
struct kvmppc_vcpu_e500 *vcpu_e500;
struct kvm_vcpu *vcpu;
int err;
vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
if (!vcpu_e500) {
err = -ENOMEM;
goto out;
}
vcpu = &vcpu_e500->vcpu;
err = kvm_vcpu_init(vcpu, kvm, id);
if (err)
goto free_vcpu;
err = kvmppc_e500_tlb_init(vcpu_e500);
if (err)
goto uninit_vcpu;
return vcpu;
uninit_vcpu:
kvm_vcpu_uninit(vcpu);
free_vcpu:
kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
out:
return ERR_PTR(err);
}
void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
kvmppc_e500_tlb_uninit(vcpu_e500);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
}
static int kvmppc_e500_init(void)
{
int r;
r = kvmppc_booke_init();
if (r)
return r;
return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
}
static void kvmppc_e500_exit(void)
{
kvmppc_booke_exit();
}
module_init(kvmppc_e500_init);
module_exit(kvmppc_e500_exit);

View File

@ -0,0 +1,169 @@
/*
* Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Yu Liu, <yu.liu@freescale.com>
*
* Description:
* This file is derived from arch/powerpc/kvm/44x_emulate.c,
* by Hollis Blanchard <hollisb@us.ibm.com>.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2, as
* published by the Free Software Foundation.
*/
#include <asm/kvm_ppc.h>
#include <asm/disassemble.h>
#include <asm/kvm_e500.h>
#include "booke.h"
#include "e500_tlb.h"
#define XOP_TLBIVAX 786
#define XOP_TLBSX 914
#define XOP_TLBRE 946
#define XOP_TLBWE 978
int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int inst, int *advance)
{
int emulated = EMULATE_DONE;
int ra;
int rb;
int rs;
int rt;
switch (get_op(inst)) {
case 31:
switch (get_xop(inst)) {
case XOP_TLBRE:
emulated = kvmppc_e500_emul_tlbre(vcpu);
break;
case XOP_TLBWE:
emulated = kvmppc_e500_emul_tlbwe(vcpu);
break;
case XOP_TLBSX:
rb = get_rb(inst);
emulated = kvmppc_e500_emul_tlbsx(vcpu,rb);
break;
case XOP_TLBIVAX:
ra = get_ra(inst);
rb = get_rb(inst);
emulated = kvmppc_e500_emul_tlbivax(vcpu, ra, rb);
break;
default:
emulated = EMULATE_FAIL;
}
break;
default:
emulated = EMULATE_FAIL;
}
if (emulated == EMULATE_FAIL)
emulated = kvmppc_booke_emulate_op(run, vcpu, inst, advance);
return emulated;
}
int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int emulated = EMULATE_DONE;
switch (sprn) {
case SPRN_PID:
vcpu_e500->pid[0] = vcpu->arch.shadow_pid =
vcpu->arch.pid = vcpu->arch.gpr[rs];
break;
case SPRN_PID1:
vcpu_e500->pid[1] = vcpu->arch.gpr[rs]; break;
case SPRN_PID2:
vcpu_e500->pid[2] = vcpu->arch.gpr[rs]; break;
case SPRN_MAS0:
vcpu_e500->mas0 = vcpu->arch.gpr[rs]; break;
case SPRN_MAS1:
vcpu_e500->mas1 = vcpu->arch.gpr[rs]; break;
case SPRN_MAS2:
vcpu_e500->mas2 = vcpu->arch.gpr[rs]; break;
case SPRN_MAS3:
vcpu_e500->mas3 = vcpu->arch.gpr[rs]; break;
case SPRN_MAS4:
vcpu_e500->mas4 = vcpu->arch.gpr[rs]; break;
case SPRN_MAS6:
vcpu_e500->mas6 = vcpu->arch.gpr[rs]; break;
case SPRN_MAS7:
vcpu_e500->mas7 = vcpu->arch.gpr[rs]; break;
case SPRN_L1CSR1:
vcpu_e500->l1csr1 = vcpu->arch.gpr[rs]; break;
case SPRN_HID0:
vcpu_e500->hid0 = vcpu->arch.gpr[rs]; break;
case SPRN_HID1:
vcpu_e500->hid1 = vcpu->arch.gpr[rs]; break;
default:
emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
}
return emulated;
}
int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int emulated = EMULATE_DONE;
switch (sprn) {
case SPRN_PID:
vcpu->arch.gpr[rt] = vcpu_e500->pid[0]; break;
case SPRN_PID1:
vcpu->arch.gpr[rt] = vcpu_e500->pid[1]; break;
case SPRN_PID2:
vcpu->arch.gpr[rt] = vcpu_e500->pid[2]; break;
case SPRN_MAS0:
vcpu->arch.gpr[rt] = vcpu_e500->mas0; break;
case SPRN_MAS1:
vcpu->arch.gpr[rt] = vcpu_e500->mas1; break;
case SPRN_MAS2:
vcpu->arch.gpr[rt] = vcpu_e500->mas2; break;
case SPRN_MAS3:
vcpu->arch.gpr[rt] = vcpu_e500->mas3; break;
case SPRN_MAS4:
vcpu->arch.gpr[rt] = vcpu_e500->mas4; break;
case SPRN_MAS6:
vcpu->arch.gpr[rt] = vcpu_e500->mas6; break;
case SPRN_MAS7:
vcpu->arch.gpr[rt] = vcpu_e500->mas7; break;
case SPRN_TLB0CFG:
vcpu->arch.gpr[rt] = mfspr(SPRN_TLB0CFG);
vcpu->arch.gpr[rt] &= ~0xfffUL;
vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[0];
break;
case SPRN_TLB1CFG:
vcpu->arch.gpr[rt] = mfspr(SPRN_TLB1CFG);
vcpu->arch.gpr[rt] &= ~0xfffUL;
vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[1];
break;
case SPRN_L1CSR1:
vcpu->arch.gpr[rt] = vcpu_e500->l1csr1; break;
case SPRN_HID0:
vcpu->arch.gpr[rt] = vcpu_e500->hid0; break;
case SPRN_HID1:
vcpu->arch.gpr[rt] = vcpu_e500->hid1; break;
default:
emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
}
return emulated;
}

737
arch/powerpc/kvm/e500_tlb.c Normal file
View File

@ -0,0 +1,737 @@
/*
* Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Yu Liu, yu.liu@freescale.com
*
* Description:
* This file is based on arch/powerpc/kvm/44x_tlb.c,
* by Hollis Blanchard <hollisb@us.ibm.com>.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2, as
* published by the Free Software Foundation.
*/
#include <linux/types.h>
#include <linux/string.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/highmem.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_e500.h>
#include "e500_tlb.h"
#define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
static unsigned int tlb1_entry_num;
void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
struct tlbe *tlbe;
int i, tlbsel;
printk("| %8s | %8s | %8s | %8s | %8s |\n",
"nr", "mas1", "mas2", "mas3", "mas7");
for (tlbsel = 0; tlbsel < 2; tlbsel++) {
printk("Guest TLB%d:\n", tlbsel);
for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) {
tlbe = &vcpu_e500->guest_tlb[tlbsel][i];
if (tlbe->mas1 & MAS1_VALID)
printk(" G[%d][%3d] | %08X | %08X | %08X | %08X |\n",
tlbsel, i, tlbe->mas1, tlbe->mas2,
tlbe->mas3, tlbe->mas7);
}
}
for (tlbsel = 0; tlbsel < 2; tlbsel++) {
printk("Shadow TLB%d:\n", tlbsel);
for (i = 0; i < vcpu_e500->shadow_tlb_size[tlbsel]; i++) {
tlbe = &vcpu_e500->shadow_tlb[tlbsel][i];
if (tlbe->mas1 & MAS1_VALID)
printk(" S[%d][%3d] | %08X | %08X | %08X | %08X |\n",
tlbsel, i, tlbe->mas1, tlbe->mas2,
tlbe->mas3, tlbe->mas7);
}
}
}
static inline unsigned int tlb0_get_next_victim(
struct kvmppc_vcpu_e500 *vcpu_e500)
{
unsigned int victim;
victim = vcpu_e500->guest_tlb_nv[0]++;
if (unlikely(vcpu_e500->guest_tlb_nv[0] >= KVM_E500_TLB0_WAY_NUM))
vcpu_e500->guest_tlb_nv[0] = 0;
return victim;
}
static inline unsigned int tlb1_max_shadow_size(void)
{
return tlb1_entry_num - tlbcam_index;
}
static inline int tlbe_is_writable(struct tlbe *tlbe)
{
return tlbe->mas3 & (MAS3_SW|MAS3_UW);
}
static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
{
/* Mask off reserved bits. */
mas3 &= MAS3_ATTRIB_MASK;
if (!usermode) {
/* Guest is in supervisor mode,
* so we need to translate guest
* supervisor permissions into user permissions. */
mas3 &= ~E500_TLB_USER_PERM_MASK;
mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
}
return mas3 | E500_TLB_SUPER_PERM_MASK;
}
static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
{
return mas2 & MAS2_ATTRIB_MASK;
}
/*
* writing shadow tlb entry to host TLB
*/
static inline void __write_host_tlbe(struct tlbe *stlbe)
{
mtspr(SPRN_MAS1, stlbe->mas1);
mtspr(SPRN_MAS2, stlbe->mas2);
mtspr(SPRN_MAS3, stlbe->mas3);
mtspr(SPRN_MAS7, stlbe->mas7);
__asm__ __volatile__ ("tlbwe\n" : : );
}
static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
int tlbsel, int esel)
{
struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
local_irq_disable();
if (tlbsel == 0) {
__write_host_tlbe(stlbe);
} else {
unsigned register mas0;
mas0 = mfspr(SPRN_MAS0);
mtspr(SPRN_MAS0, MAS0_TLBSEL(1) | MAS0_ESEL(to_htlb1_esel(esel)));
__write_host_tlbe(stlbe);
mtspr(SPRN_MAS0, mas0);
}
local_irq_enable();
}
void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int i;
unsigned register mas0;
/* Load all valid TLB1 entries to reduce guest tlb miss fault */
local_irq_disable();
mas0 = mfspr(SPRN_MAS0);
for (i = 0; i < tlb1_max_shadow_size(); i++) {
struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i];
if (get_tlb_v(stlbe)) {
mtspr(SPRN_MAS0, MAS0_TLBSEL(1)
| MAS0_ESEL(to_htlb1_esel(i)));
__write_host_tlbe(stlbe);
}
}
mtspr(SPRN_MAS0, mas0);
local_irq_enable();
}
void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
{
_tlbia();
}
/* Search the guest TLB for a matching entry. */
static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
gva_t eaddr, int tlbsel, unsigned int pid, int as)
{
int i;
/* XXX Replace loop with fancy data structures. */
for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) {
struct tlbe *tlbe = &vcpu_e500->guest_tlb[tlbsel][i];
unsigned int tid;
if (eaddr < get_tlb_eaddr(tlbe))
continue;
if (eaddr > get_tlb_end(tlbe))
continue;
tid = get_tlb_tid(tlbe);
if (tid && (tid != pid))
continue;
if (!get_tlb_v(tlbe))
continue;
if (get_tlb_ts(tlbe) != as && as != -1)
continue;
return i;
}
return -1;
}
static void kvmppc_e500_shadow_release(struct kvmppc_vcpu_e500 *vcpu_e500,
int tlbsel, int esel)
{
struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
struct page *page = vcpu_e500->shadow_pages[tlbsel][esel];
if (page) {
vcpu_e500->shadow_pages[tlbsel][esel] = NULL;
if (get_tlb_v(stlbe)) {
if (tlbe_is_writable(stlbe))
kvm_release_page_dirty(page);
else
kvm_release_page_clean(page);
}
}
}
static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
int tlbsel, int esel)
{
struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
stlbe->mas1 = 0;
KVMTRACE_5D(STLB_INVAL, &vcpu_e500->vcpu, index_of(tlbsel, esel),
stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
handler);
}
static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
gva_t eaddr, gva_t eend, u32 tid)
{
unsigned int pid = tid & 0xff;
unsigned int i;
/* XXX Replace loop with fancy data structures. */
for (i = 0; i < vcpu_e500->guest_tlb_size[1]; i++) {
struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i];
unsigned int tid;
if (!get_tlb_v(stlbe))
continue;
if (eend < get_tlb_eaddr(stlbe))
continue;
if (eaddr > get_tlb_end(stlbe))
continue;
tid = get_tlb_tid(stlbe);
if (tid && (tid != pid))
continue;
kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i);
write_host_tlbe(vcpu_e500, 1, i);
}
}
static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
unsigned int eaddr, int as)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
unsigned int victim, pidsel, tsized;
int tlbsel;
/* since we only have tow TLBs, only lower bit is used. */
tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
tsized = (vcpu_e500->mas4 >> 8) & 0xf;
vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
vcpu_e500->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
| MAS1_TID(vcpu_e500->pid[pidsel])
| MAS1_TSIZE(tsized);
vcpu_e500->mas2 = (eaddr & MAS2_EPN)
| (vcpu_e500->mas4 & MAS2_ATTRIB_MASK);
vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
vcpu_e500->mas6 = (vcpu_e500->mas6 & MAS6_SPID1)
| (get_cur_pid(vcpu) << 16)
| (as ? MAS6_SAS : 0);
vcpu_e500->mas7 = 0;
}
static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, int tlbsel, int esel)
{
struct page *new_page;
struct tlbe *stlbe;
hpa_t hpaddr;
stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
/* Get reference to new page. */
new_page = gfn_to_page(vcpu_e500->vcpu.kvm, gfn);
if (is_error_page(new_page)) {
printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", gfn);
kvm_release_page_clean(new_page);
return;
}
hpaddr = page_to_phys(new_page);
/* Drop reference to old page. */
kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
vcpu_e500->shadow_pages[tlbsel][esel] = new_page;
/* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
stlbe->mas1 = MAS1_TSIZE(BOOKE_PAGESZ_4K)
| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
stlbe->mas2 = (gvaddr & MAS2_EPN)
| e500_shadow_mas2_attrib(gtlbe->mas2,
vcpu_e500->vcpu.arch.msr & MSR_PR);
stlbe->mas3 = (hpaddr & MAS3_RPN)
| e500_shadow_mas3_attrib(gtlbe->mas3,
vcpu_e500->vcpu.arch.msr & MSR_PR);
stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
KVMTRACE_5D(STLB_WRITE, &vcpu_e500->vcpu, index_of(tlbsel, esel),
stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
handler);
}
/* XXX only map the one-one case, for now use TLB0 */
static int kvmppc_e500_stlbe_map(struct kvmppc_vcpu_e500 *vcpu_e500,
int tlbsel, int esel)
{
struct tlbe *gtlbe;
gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
gtlbe, tlbsel, esel);
return esel;
}
/* Caller must ensure that the specified guest TLB entry is safe to insert into
* the shadow TLB. */
/* XXX for both one-one and one-to-many , for now use TLB1 */
static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe)
{
unsigned int victim;
victim = vcpu_e500->guest_tlb_nv[1]++;
if (unlikely(vcpu_e500->guest_tlb_nv[1] >= tlb1_max_shadow_size()))
vcpu_e500->guest_tlb_nv[1] = 0;
kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, victim);
return victim;
}
/* Invalidate all guest kernel mappings when enter usermode,
* so that when they fault back in they will get the
* proper permission bits. */
void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode)
{
if (usermode) {
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int i;
/* XXX Replace loop with fancy data structures. */
/* needn't set modified since tlbia will make TLB1 coherent */
for (i = 0; i < tlb1_max_shadow_size(); i++)
kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i);
_tlbia();
}
}
static int kvmppc_e500_gtlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
int tlbsel, int esel)
{
struct tlbe *gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
if (unlikely(get_tlb_iprot(gtlbe)))
return -1;
if (tlbsel == 1) {
kvmppc_e500_tlb1_invalidate(vcpu_e500, get_tlb_eaddr(gtlbe),
get_tlb_end(gtlbe),
get_tlb_tid(gtlbe));
} else {
kvmppc_e500_stlbe_invalidate(vcpu_e500, tlbsel, esel);
}
gtlbe->mas1 = 0;
return 0;
}
int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
unsigned int ia;
int esel, tlbsel;
gva_t ea;
ea = ((ra) ? vcpu->arch.gpr[ra] : 0) + vcpu->arch.gpr[rb];
ia = (ea >> 2) & 0x1;
/* since we only have tow TLBs, only lower bit is used. */
tlbsel = (ea >> 3) & 0x1;
if (ia) {
/* invalidate all entries */
for (esel = 0; esel < vcpu_e500->guest_tlb_size[tlbsel]; esel++)
kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
} else {
ea &= 0xfffff000;
esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel,
get_cur_pid(vcpu), -1);
if (esel >= 0)
kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
}
_tlbia();
return EMULATE_DONE;
}
int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int tlbsel, esel;
struct tlbe *gtlbe;
tlbsel = get_tlb_tlbsel(vcpu_e500);
esel = get_tlb_esel(vcpu_e500, tlbsel);
gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
vcpu_e500->mas0 &= MAS0_NV(0);
vcpu_e500->mas0 |= MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
vcpu_e500->mas1 = gtlbe->mas1;
vcpu_e500->mas2 = gtlbe->mas2;
vcpu_e500->mas3 = gtlbe->mas3;
vcpu_e500->mas7 = gtlbe->mas7;
return EMULATE_DONE;
}
int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int as = !!get_cur_sas(vcpu_e500);
unsigned int pid = get_cur_spid(vcpu_e500);
int esel, tlbsel;
struct tlbe *gtlbe = NULL;
gva_t ea;
ea = vcpu->arch.gpr[rb];
for (tlbsel = 0; tlbsel < 2; tlbsel++) {
esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
if (esel >= 0) {
gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
break;
}
}
if (gtlbe) {
vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel)
| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
vcpu_e500->mas1 = gtlbe->mas1;
vcpu_e500->mas2 = gtlbe->mas2;
vcpu_e500->mas3 = gtlbe->mas3;
vcpu_e500->mas7 = gtlbe->mas7;
} else {
int victim;
/* since we only have tow TLBs, only lower bit is used. */
tlbsel = vcpu_e500->mas4 >> 28 & 0x1;
victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
vcpu_e500->mas1 = (vcpu_e500->mas6 & MAS6_SPID0)
| (vcpu_e500->mas6 & (MAS6_SAS ? MAS1_TS : 0))
| (vcpu_e500->mas4 & MAS4_TSIZED(~0));
vcpu_e500->mas2 &= MAS2_EPN;
vcpu_e500->mas2 |= vcpu_e500->mas4 & MAS2_ATTRIB_MASK;
vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
vcpu_e500->mas7 = 0;
}
return EMULATE_DONE;
}
int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
u64 eaddr;
u64 raddr;
u32 tid;
struct tlbe *gtlbe;
int tlbsel, esel, stlbsel, sesel;
tlbsel = get_tlb_tlbsel(vcpu_e500);
esel = get_tlb_esel(vcpu_e500, tlbsel);
gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
if (get_tlb_v(gtlbe) && tlbsel == 1) {
eaddr = get_tlb_eaddr(gtlbe);
tid = get_tlb_tid(gtlbe);
kvmppc_e500_tlb1_invalidate(vcpu_e500, eaddr,
get_tlb_end(gtlbe), tid);
}
gtlbe->mas1 = vcpu_e500->mas1;
gtlbe->mas2 = vcpu_e500->mas2;
gtlbe->mas3 = vcpu_e500->mas3;
gtlbe->mas7 = vcpu_e500->mas7;
KVMTRACE_5D(GTLB_WRITE, vcpu, vcpu_e500->mas0,
gtlbe->mas1, gtlbe->mas2, gtlbe->mas3, gtlbe->mas7,
handler);
/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
if (tlbe_is_host_safe(vcpu, gtlbe)) {
switch (tlbsel) {
case 0:
/* TLB0 */
gtlbe->mas1 &= ~MAS1_TSIZE(~0);
gtlbe->mas1 |= MAS1_TSIZE(BOOKE_PAGESZ_4K);
stlbsel = 0;
sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel);
break;
case 1:
/* TLB1 */
eaddr = get_tlb_eaddr(gtlbe);
raddr = get_tlb_raddr(gtlbe);
/* Create a 4KB mapping on the host.
* If the guest wanted a large page,
* only the first 4KB is mapped here and the rest
* are mapped on the fly. */
stlbsel = 1;
sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
raddr >> PAGE_SHIFT, gtlbe);
break;
default:
BUG();
}
write_host_tlbe(vcpu_e500, stlbsel, sesel);
}
return EMULATE_DONE;
}
int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
unsigned int as = !!(vcpu->arch.msr & MSR_IS);
return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
}
int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
unsigned int as = !!(vcpu->arch.msr & MSR_DS);
return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
}
void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
{
unsigned int as = !!(vcpu->arch.msr & MSR_IS);
kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.pc, as);
}
void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
{
unsigned int as = !!(vcpu->arch.msr & MSR_DS);
kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.fault_dear, as);
}
gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
gva_t eaddr)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
struct tlbe *gtlbe =
&vcpu_e500->guest_tlb[tlbsel_of(index)][esel_of(index)];
u64 pgmask = get_tlb_bytes(gtlbe) - 1;
return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
}
void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int tlbsel, i;
for (tlbsel = 0; tlbsel < 2; tlbsel++)
for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++)
kvmppc_e500_shadow_release(vcpu_e500, tlbsel, i);
/* discard all guest mapping */
_tlbia();
}
void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
unsigned int index)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int tlbsel = tlbsel_of(index);
int esel = esel_of(index);
int stlbsel, sesel;
switch (tlbsel) {
case 0:
stlbsel = 0;
sesel = esel;
break;
case 1: {
gfn_t gfn = gpaddr >> PAGE_SHIFT;
struct tlbe *gtlbe
= &vcpu_e500->guest_tlb[tlbsel][esel];
stlbsel = 1;
sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, gtlbe);
break;
}
default:
BUG();
break;
}
write_host_tlbe(vcpu_e500, stlbsel, sesel);
}
int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
gva_t eaddr, unsigned int pid, int as)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int esel, tlbsel;
for (tlbsel = 0; tlbsel < 2; tlbsel++) {
esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
if (esel >= 0)
return index_of(tlbsel, esel);
}
return -1;
}
void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
{
struct tlbe *tlbe;
/* Insert large initial mapping for guest. */
tlbe = &vcpu_e500->guest_tlb[1][0];
tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_256M);
tlbe->mas2 = 0;
tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
tlbe->mas7 = 0;
/* 4K map for serial output. Used by kernel wrapper. */
tlbe = &vcpu_e500->guest_tlb[1][1];
tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_4K);
tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
tlbe->mas7 = 0;
}
int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
{
tlb1_entry_num = mfspr(SPRN_TLB1CFG) & 0xFFF;
vcpu_e500->guest_tlb_size[0] = KVM_E500_TLB0_SIZE;
vcpu_e500->guest_tlb[0] =
kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
if (vcpu_e500->guest_tlb[0] == NULL)
goto err_out;
vcpu_e500->shadow_tlb_size[0] = KVM_E500_TLB0_SIZE;
vcpu_e500->shadow_tlb[0] =
kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
if (vcpu_e500->shadow_tlb[0] == NULL)
goto err_out_guest0;
vcpu_e500->guest_tlb_size[1] = KVM_E500_TLB1_SIZE;
vcpu_e500->guest_tlb[1] =
kzalloc(sizeof(struct tlbe) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
if (vcpu_e500->guest_tlb[1] == NULL)
goto err_out_shadow0;
vcpu_e500->shadow_tlb_size[1] = tlb1_entry_num;
vcpu_e500->shadow_tlb[1] =
kzalloc(sizeof(struct tlbe) * tlb1_entry_num, GFP_KERNEL);
if (vcpu_e500->shadow_tlb[1] == NULL)
goto err_out_guest1;
vcpu_e500->shadow_pages[0] = (struct page **)
kzalloc(sizeof(struct page *) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
if (vcpu_e500->shadow_pages[0] == NULL)
goto err_out_shadow1;
vcpu_e500->shadow_pages[1] = (struct page **)
kzalloc(sizeof(struct page *) * tlb1_entry_num, GFP_KERNEL);
if (vcpu_e500->shadow_pages[1] == NULL)
goto err_out_page0;
return 0;
err_out_page0:
kfree(vcpu_e500->shadow_pages[0]);
err_out_shadow1:
kfree(vcpu_e500->shadow_tlb[1]);
err_out_guest1:
kfree(vcpu_e500->guest_tlb[1]);
err_out_shadow0:
kfree(vcpu_e500->shadow_tlb[0]);
err_out_guest0:
kfree(vcpu_e500->guest_tlb[0]);
err_out:
return -1;
}
void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
{
kfree(vcpu_e500->shadow_pages[1]);
kfree(vcpu_e500->shadow_pages[0]);
kfree(vcpu_e500->shadow_tlb[1]);
kfree(vcpu_e500->guest_tlb[1]);
kfree(vcpu_e500->shadow_tlb[0]);
kfree(vcpu_e500->guest_tlb[0]);
}

184
arch/powerpc/kvm/e500_tlb.h Normal file
View File

@ -0,0 +1,184 @@
/*
* Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Yu Liu, yu.liu@freescale.com
*
* Description:
* This file is based on arch/powerpc/kvm/44x_tlb.h,
* by Hollis Blanchard <hollisb@us.ibm.com>.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2, as
* published by the Free Software Foundation.
*/
#ifndef __KVM_E500_TLB_H__
#define __KVM_E500_TLB_H__
#include <linux/kvm_host.h>
#include <asm/mmu-fsl-booke.h>
#include <asm/tlb.h>
#include <asm/kvm_e500.h>
#define KVM_E500_TLB0_WAY_SIZE_BIT 7 /* Fixed */
#define KVM_E500_TLB0_WAY_SIZE (1UL << KVM_E500_TLB0_WAY_SIZE_BIT)
#define KVM_E500_TLB0_WAY_SIZE_MASK (KVM_E500_TLB0_WAY_SIZE - 1)
#define KVM_E500_TLB0_WAY_NUM_BIT 1 /* No greater than 7 */
#define KVM_E500_TLB0_WAY_NUM (1UL << KVM_E500_TLB0_WAY_NUM_BIT)
#define KVM_E500_TLB0_WAY_NUM_MASK (KVM_E500_TLB0_WAY_NUM - 1)
#define KVM_E500_TLB0_SIZE (KVM_E500_TLB0_WAY_SIZE * KVM_E500_TLB0_WAY_NUM)
#define KVM_E500_TLB1_SIZE 16
#define index_of(tlbsel, esel) (((tlbsel) << 16) | ((esel) & 0xFFFF))
#define tlbsel_of(index) ((index) >> 16)
#define esel_of(index) ((index) & 0xFFFF)
#define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW)
#define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW)
#define MAS2_ATTRIB_MASK \
(MAS2_X0 | MAS2_X1 | MAS2_W | MAS2_I | MAS2_M | MAS2_G | MAS2_E)
#define MAS3_ATTRIB_MASK \
(MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
| E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
extern void kvmppc_dump_tlbs(struct kvm_vcpu *);
extern int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *);
extern int kvmppc_e500_emul_tlbre(struct kvm_vcpu *);
extern int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *, int, int);
extern int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *, int);
extern int kvmppc_e500_tlb_search(struct kvm_vcpu *, gva_t, unsigned int, int);
extern void kvmppc_e500_tlb_put(struct kvm_vcpu *);
extern void kvmppc_e500_tlb_load(struct kvm_vcpu *, int);
extern int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *);
extern void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *);
extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
/* TLB helper functions */
static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
{
return (tlbe->mas1 >> 8) & 0xf;
}
static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
{
return tlbe->mas2 & 0xfffff000;
}
static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
{
unsigned int pgsize = get_tlb_size(tlbe);
return 1ULL << 10 << (pgsize << 1);
}
static inline gva_t get_tlb_end(const struct tlbe *tlbe)
{
u64 bytes = get_tlb_bytes(tlbe);
return get_tlb_eaddr(tlbe) + bytes - 1;
}
static inline u64 get_tlb_raddr(const struct tlbe *tlbe)
{
u64 rpn = tlbe->mas7;
return (rpn << 32) | (tlbe->mas3 & 0xfffff000);
}
static inline unsigned int get_tlb_tid(const struct tlbe *tlbe)
{
return (tlbe->mas1 >> 16) & 0xff;
}
static inline unsigned int get_tlb_ts(const struct tlbe *tlbe)
{
return (tlbe->mas1 >> 12) & 0x1;
}
static inline unsigned int get_tlb_v(const struct tlbe *tlbe)
{
return (tlbe->mas1 >> 31) & 0x1;
}
static inline unsigned int get_tlb_iprot(const struct tlbe *tlbe)
{
return (tlbe->mas1 >> 30) & 0x1;
}
static inline unsigned int get_cur_pid(struct kvm_vcpu *vcpu)
{
return vcpu->arch.pid & 0xff;
}
static inline unsigned int get_cur_spid(
const struct kvmppc_vcpu_e500 *vcpu_e500)
{
return (vcpu_e500->mas6 >> 16) & 0xff;
}
static inline unsigned int get_cur_sas(
const struct kvmppc_vcpu_e500 *vcpu_e500)
{
return vcpu_e500->mas6 & 0x1;
}
static inline unsigned int get_tlb_tlbsel(
const struct kvmppc_vcpu_e500 *vcpu_e500)
{
/*
* Manual says that tlbsel has 2 bits wide.
* Since we only have tow TLBs, only lower bit is used.
*/
return (vcpu_e500->mas0 >> 28) & 0x1;
}
static inline unsigned int get_tlb_nv_bit(
const struct kvmppc_vcpu_e500 *vcpu_e500)
{
return vcpu_e500->mas0 & 0xfff;
}
static inline unsigned int get_tlb_esel_bit(
const struct kvmppc_vcpu_e500 *vcpu_e500)
{
return (vcpu_e500->mas0 >> 16) & 0xfff;
}
static inline unsigned int get_tlb_esel(
const struct kvmppc_vcpu_e500 *vcpu_e500,
int tlbsel)
{
unsigned int esel = get_tlb_esel_bit(vcpu_e500);
if (tlbsel == 0) {
esel &= KVM_E500_TLB0_WAY_NUM_MASK;
esel |= ((vcpu_e500->mas2 >> 12) & KVM_E500_TLB0_WAY_SIZE_MASK)
<< KVM_E500_TLB0_WAY_NUM_BIT;
} else {
esel &= KVM_E500_TLB1_SIZE - 1;
}
return esel;
}
static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
const struct tlbe *tlbe)
{
gpa_t gpa;
if (!get_tlb_v(tlbe))
return 0;
/* Does it match current guest AS? */
/* XXX what about IS != DS? */
if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
return 0;
gpa = get_tlb_raddr(tlbe);
if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
/* Mapping is not for RAM. */
return 0;
return 1;
}
#endif /* __KVM_E500_TLB_H__ */