linux/arch/s390/kvm/priv.c
Linus Torvalds ecefbd94b8 KVM updates for the 3.7 merge window
-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.12 (GNU/Linux)
 
 iQIcBAABAgAGBQJQbY/2AAoJEI7yEDeUysxlymQQAIv5svpAI/FUe3FhvBi3IW2h
 WWMIpbdhHyocaINT18qNp8prO0iwoaBfgsnU8zuB34MrbdUgiwSHgM6T4Ff4NGa+
 R4u+gpyKYwxNQYKeJyj04luXra/krxwHL1u9OwN7o44JuQXAmzrw2tZ9ad1ArvL3
 eoZ6kGsPcdHPZMZWw2jN5xzBsRtqybm0GPPQh1qPXdn8UlPPd1X7owvbaud2y4+e
 StVIpGY6wrsO36f7UcA4Gm1EP/1E6Lm5KMXJyHgM9WBRkEfp92jTY5+XKv91vK8Z
 VKUd58QMdZE5NCNBkAR9U5N9aH0oSXnFU/g8hgiwGvrhS3IsSkKUePE6sVyMVTIO
 VptKRYe0AdmD/g25p6ApJsguV7ITlgoCPaE4rMmRcW9/bw8+iY098r7tO7w11H8M
 TyFOXihc3B+rlH8WdzOblwxHMC4yRuiPIktaA3WwbX7eA7Xv/ZRtdidifXKtgsVE
 rtubVqwGyYcHoX1Y+JiByIW1NN0pYncJhPEdc8KbRe2wKs3amA9rio1mUpBYYBPO
 B0ygcITftyXbhcTtssgcwBDGXB0AAGqI7wqdtJhFeIrKwHXD7fNeAGRwO8oKxmlj
 0aPwo9fDtpI+e6BFTohEgjZBocRvXXNWLnDSFB0E7xDR31bACck2FG5FAp1DxdS7
 lb/nbAsXf9UJLgGir4I1
 =kN6V
 -----END PGP SIGNATURE-----

Merge tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights of the changes for this release include support for vfio
  level triggered interrupts, improved big real mode support on older
  Intels, a streamlines guest page table walker, guest APIC speedups,
  PIO optimizations, better overcommit handling, and read-only memory."

* tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
  KVM: s390: Fix vcpu_load handling in interrupt code
  KVM: x86: Fix guest debug across vcpu INIT reset
  KVM: Add resampling irqfds for level triggered interrupts
  KVM: optimize apic interrupt delivery
  KVM: MMU: Eliminate pointless temporary 'ac'
  KVM: MMU: Avoid access/dirty update loop if all is well
  KVM: MMU: Eliminate eperm temporary
  KVM: MMU: Optimize is_last_gpte()
  KVM: MMU: Simplify walk_addr_generic() loop
  KVM: MMU: Optimize pte permission checks
  KVM: MMU: Update accessed and dirty bits after guest pagetable walk
  KVM: MMU: Move gpte_access() out of paging_tmpl.h
  KVM: MMU: Optimize gpte_access() slightly
  KVM: MMU: Push clean gpte write protection out of gpte_access()
  KVM: clarify kvmclock documentation
  KVM: make processes waiting on vcpu mutex killable
  KVM: SVM: Make use of asm.h
  KVM: VMX: Make use of asm.h
  KVM: VMX: Make lto-friendly
  KVM: x86: lapic: Clean up find_highest_vector() and count_vectors()
  ...

Conflicts:
	arch/s390/include/asm/processor.h
	arch/x86/kvm/i8259.c
2012-10-04 09:30:33 -07:00

421 lines
11 KiB
C

/*
* handling privileged instructions
*
* Copyright IBM Corp. 2008
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License (version 2 only)
* as published by the Free Software Foundation.
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
*/
#include <linux/kvm.h>
#include <linux/gfp.h>
#include <linux/errno.h>
#include <asm/current.h>
#include <asm/debug.h>
#include <asm/ebcdic.h>
#include <asm/sysinfo.h>
#include "gaccess.h"
#include "kvm-s390.h"
#include "trace.h"
static int handle_set_prefix(struct kvm_vcpu *vcpu)
{
int base2 = vcpu->arch.sie_block->ipb >> 28;
int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
u64 operand2;
u32 address = 0;
u8 tmp;
vcpu->stat.instruction_spx++;
operand2 = disp2;
if (base2)
operand2 += vcpu->run->s.regs.gprs[base2];
/* must be word boundary */
if (operand2 & 3) {
kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
goto out;
}
/* get the value */
if (get_guest_u32(vcpu, operand2, &address)) {
kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
goto out;
}
address = address & 0x7fffe000u;
/* make sure that the new value is valid memory */
if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
(copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1))) {
kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
goto out;
}
kvm_s390_set_prefix(vcpu, address);
VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
trace_kvm_s390_handle_prefix(vcpu, 1, address);
out:
return 0;
}
static int handle_store_prefix(struct kvm_vcpu *vcpu)
{
int base2 = vcpu->arch.sie_block->ipb >> 28;
int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
u64 operand2;
u32 address;
vcpu->stat.instruction_stpx++;
operand2 = disp2;
if (base2)
operand2 += vcpu->run->s.regs.gprs[base2];
/* must be word boundary */
if (operand2 & 3) {
kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
goto out;
}
address = vcpu->arch.sie_block->prefix;
address = address & 0x7fffe000u;
/* get the value */
if (put_guest_u32(vcpu, operand2, address)) {
kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
goto out;
}
VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
trace_kvm_s390_handle_prefix(vcpu, 0, address);
out:
return 0;
}
static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
{
int base2 = vcpu->arch.sie_block->ipb >> 28;
int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
u64 useraddr;
int rc;
vcpu->stat.instruction_stap++;
useraddr = disp2;
if (base2)
useraddr += vcpu->run->s.regs.gprs[base2];
if (useraddr & 1) {
kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
goto out;
}
rc = put_guest_u16(vcpu, useraddr, vcpu->vcpu_id);
if (rc == -EFAULT) {
kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
goto out;
}
VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", useraddr);
trace_kvm_s390_handle_stap(vcpu, useraddr);
out:
return 0;
}
static int handle_skey(struct kvm_vcpu *vcpu)
{
vcpu->stat.instruction_storage_key++;
vcpu->arch.sie_block->gpsw.addr -= 4;
VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
return 0;
}
static int handle_stsch(struct kvm_vcpu *vcpu)
{
vcpu->stat.instruction_stsch++;
VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3");
/* condition code 3 */
vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
return 0;
}
static int handle_chsc(struct kvm_vcpu *vcpu)
{
vcpu->stat.instruction_chsc++;
VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3");
/* condition code 3 */
vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
return 0;
}
static int handle_stfl(struct kvm_vcpu *vcpu)
{
unsigned int facility_list;
int rc;
vcpu->stat.instruction_stfl++;
/* only pass the facility bits, which we can handle */
facility_list = S390_lowcore.stfl_fac_list & 0xff00fff3;
rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list),
&facility_list, sizeof(facility_list));
if (rc == -EFAULT)
kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
else {
VCPU_EVENT(vcpu, 5, "store facility list value %x",
facility_list);
trace_kvm_s390_handle_stfl(vcpu, facility_list);
}
return 0;
}
static int handle_stidp(struct kvm_vcpu *vcpu)
{
int base2 = vcpu->arch.sie_block->ipb >> 28;
int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
u64 operand2;
int rc;
vcpu->stat.instruction_stidp++;
operand2 = disp2;
if (base2)
operand2 += vcpu->run->s.regs.gprs[base2];
if (operand2 & 7) {
kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
goto out;
}
rc = put_guest_u64(vcpu, operand2, vcpu->arch.stidp_data);
if (rc == -EFAULT) {
kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
goto out;
}
VCPU_EVENT(vcpu, 5, "%s", "store cpu id");
out:
return 0;
}
static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
{
struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
int cpus = 0;
int n;
spin_lock(&fi->lock);
for (n = 0; n < KVM_MAX_VCPUS; n++)
if (fi->local_int[n])
cpus++;
spin_unlock(&fi->lock);
/* deal with other level 3 hypervisors */
if (stsi(mem, 3, 2, 2))
mem->count = 0;
if (mem->count < 8)
mem->count++;
for (n = mem->count - 1; n > 0 ; n--)
memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0]));
mem->vm[0].cpus_total = cpus;
mem->vm[0].cpus_configured = cpus;
mem->vm[0].cpus_standby = 0;
mem->vm[0].cpus_reserved = 0;
mem->vm[0].caf = 1000;
memcpy(mem->vm[0].name, "KVMguest", 8);
ASCEBC(mem->vm[0].name, 8);
memcpy(mem->vm[0].cpi, "KVM/Linux ", 16);
ASCEBC(mem->vm[0].cpi, 16);
}
static int handle_stsi(struct kvm_vcpu *vcpu)
{
int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28;
int sel1 = vcpu->run->s.regs.gprs[0] & 0xff;
int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff;
int base2 = vcpu->arch.sie_block->ipb >> 28;
int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
u64 operand2;
unsigned long mem;
vcpu->stat.instruction_stsi++;
VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
operand2 = disp2;
if (base2)
operand2 += vcpu->run->s.regs.gprs[base2];
if (operand2 & 0xfff && fc > 0)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
switch (fc) {
case 0:
vcpu->run->s.regs.gprs[0] = 3 << 28;
vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
return 0;
case 1: /* same handling for 1 and 2 */
case 2:
mem = get_zeroed_page(GFP_KERNEL);
if (!mem)
goto out_fail;
if (stsi((void *) mem, fc, sel1, sel2))
goto out_mem;
break;
case 3:
if (sel1 != 2 || sel2 != 2)
goto out_fail;
mem = get_zeroed_page(GFP_KERNEL);
if (!mem)
goto out_fail;
handle_stsi_3_2_2(vcpu, (void *) mem);
break;
default:
goto out_fail;
}
if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) {
kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
goto out_mem;
}
trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2);
free_page(mem);
vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
vcpu->run->s.regs.gprs[0] = 0;
return 0;
out_mem:
free_page(mem);
out_fail:
/* condition code 3 */
vcpu->arch.sie_block->gpsw.mask |= 3ul << 44;
return 0;
}
static intercept_handler_t priv_handlers[256] = {
[0x02] = handle_stidp,
[0x10] = handle_set_prefix,
[0x11] = handle_store_prefix,
[0x12] = handle_store_cpu_address,
[0x29] = handle_skey,
[0x2a] = handle_skey,
[0x2b] = handle_skey,
[0x34] = handle_stsch,
[0x5f] = handle_chsc,
[0x7d] = handle_stsi,
[0xb1] = handle_stfl,
};
int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
{
intercept_handler_t handler;
/*
* a lot of B2 instructions are priviledged. We first check for
* the privileged ones, that we can handle in the kernel. If the
* kernel can handle this instruction, we check for the problem
* state bit and (a) handle the instruction or (b) send a code 2
* program check.
* Anything else goes to userspace.*/
handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
if (handler) {
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu,
PGM_PRIVILEGED_OPERATION);
else
return handler(vcpu);
}
return -EOPNOTSUPP;
}
static int handle_tprot(struct kvm_vcpu *vcpu)
{
int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
u64 address1 = disp1 + base1 ? vcpu->run->s.regs.gprs[base1] : 0;
u64 address2 = disp2 + base2 ? vcpu->run->s.regs.gprs[base2] : 0;
struct vm_area_struct *vma;
unsigned long user_address;
vcpu->stat.instruction_tprot++;
/* we only handle the Linux memory detection case:
* access key == 0
* guest DAT == off
* everything else goes to userspace. */
if (address2 & 0xf0)
return -EOPNOTSUPP;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
return -EOPNOTSUPP;
/* we must resolve the address without holding the mmap semaphore.
* This is ok since the userspace hypervisor is not supposed to change
* the mapping while the guest queries the memory. Otherwise the guest
* might crash or get wrong info anyway. */
user_address = (unsigned long) __guestaddr_to_user(vcpu, address1);
down_read(&current->mm->mmap_sem);
vma = find_vma(current->mm, user_address);
if (!vma) {
up_read(&current->mm->mmap_sem);
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
}
vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
if (!(vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_READ))
vcpu->arch.sie_block->gpsw.mask |= (1ul << 44);
if (!(vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_READ))
vcpu->arch.sie_block->gpsw.mask |= (2ul << 44);
up_read(&current->mm->mmap_sem);
return 0;
}
int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)
{
/* For e5xx... instructions we only handle TPROT */
if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01)
return handle_tprot(vcpu);
return -EOPNOTSUPP;
}
static int handle_sckpf(struct kvm_vcpu *vcpu)
{
u32 value;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu,
PGM_PRIVILEGED_OPERATION);
if (vcpu->run->s.regs.gprs[0] & 0x00000000ffff0000)
return kvm_s390_inject_program_int(vcpu,
PGM_SPECIFICATION);
value = vcpu->run->s.regs.gprs[0] & 0x000000000000ffff;
vcpu->arch.sie_block->todpr = value;
return 0;
}
static intercept_handler_t x01_handlers[256] = {
[0x07] = handle_sckpf,
};
int kvm_s390_handle_01(struct kvm_vcpu *vcpu)
{
intercept_handler_t handler;
handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
if (handler)
return handler(vcpu);
return -EOPNOTSUPP;
}