linux_dsm_epyc7002/arch/arm64/kvm/hyp/switch.c
Linus Torvalds 221bb8a46e - ARM: GICv3 ITS emulation and various fixes. Removal of the old
VGIC implementation.
 
 - s390: support for trapping software breakpoints, nested virtualization
 (vSIE), the STHYI opcode, initial extensions for CPU model support.
 
 - MIPS: support for MIPS64 hosts (32-bit guests only) and lots of cleanups,
 preliminary to this and the upcoming support for hardware virtualization
 extensions.
 
 - x86: support for execute-only mappings in nested EPT; reduced vmexit
 latency for TSC deadline timer (by about 30%) on Intel hosts; support for
 more than 255 vCPUs.
 
 - PPC: bugfixes.
 
 The ugly bit is the conflicts.  A couple of them are simple conflicts due
 to 4.7 fixes, but most of them are with other trees. There was definitely
 too much reliance on Acked-by here.  Some conflicts are for KVM patches
 where _I_ gave my Acked-by, but the worst are for this pull request's
 patches that touch files outside arch/*/kvm.  KVM submaintainers should
 probably learn to synchronize better with arch maintainers, with the
 latter providing topic branches whenever possible instead of Acked-by.
 This is what we do with arch/x86.  And I should learn to refuse pull
 requests when linux-next sends scary signals, even if that means that
 submaintainers have to rebase their branches.
 
 Anyhow, here's the list:
 
 - arch/x86/kvm/vmx.c: handle_pcommit and EXIT_REASON_PCOMMIT was removed
 by the nvdimm tree.  This tree adds handle_preemption_timer and
 EXIT_REASON_PREEMPTION_TIMER at the same place.  In general all mentions
 of pcommit have to go.
 
 There is also a conflict between a stable fix and this patch, where the
 stable fix removed the vmx_create_pml_buffer function and its call.
 
 - virt/kvm/kvm_main.c: kvm_cpu_notifier was removed by the hotplug tree.
 This tree adds kvm_io_bus_get_dev at the same place.
 
 - virt/kvm/arm/vgic.c: a few final bugfixes went into 4.7 before the
 file was completely removed for 4.8.
 
 - include/linux/irqchip/arm-gic-v3.h: this one is entirely our fault;
 this is a change that should have gone in through the irqchip tree and
 pulled by kvm-arm.  I think I would have rejected this kvm-arm pull
 request.  The KVM version is the right one, except that it lacks
 GITS_BASER_PAGES_SHIFT.
 
 - arch/powerpc: what a mess.  For the idle_book3s.S conflict, the KVM
 tree is the right one; everything else is trivial.  In this case I am
 not quite sure what went wrong.  The commit that is causing the mess
 (fd7bacbca4, "KVM: PPC: Book3S HV: Fix TB corruption in guest exit
 path on HMI interrupt", 2016-05-15) touches both arch/powerpc/kernel/
 and arch/powerpc/kvm/.  It's large, but at 396 insertions/5 deletions
 I guessed that it wasn't really possible to split it and that the 5
 deletions wouldn't conflict.  That wasn't the case.
 
 - arch/s390: also messy.  First is hypfs_diag.c where the KVM tree
 moved some code and the s390 tree patched it.  You have to reapply the
 relevant part of commits 6c22c98637, plus all of e030c1125e, to
 arch/s390/kernel/diag.c.  Or pick the linux-next conflict
 resolution from http://marc.info/?l=kvm&m=146717549531603&w=2.
 Second, there is a conflict in gmap.c between a stable fix and 4.8.
 The KVM version here is the correct one.
 
 I have pushed my resolution at refs/heads/merge-20160802 (commit
 3d1f53419842) at git://git.kernel.org/pub/scm/virt/kvm/kvm.git.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQEcBAABAgAGBQJXoGm7AAoJEL/70l94x66DugQIAIj703ePAFepB/fCrKHkZZia
 SGrsBdvAtNsOhr7FQ5qvvjLxiv/cv7CymeuJivX8H+4kuUHUllDzey+RPHYHD9X7
 U6n1PdCH9F15a3IXc8tDjlDdOMNIKJixYuq1UyNZMU6NFwl00+TZf9JF8A2US65b
 x/41W98ilL6nNBAsoDVmCLtPNWAqQ3lajaZELGfcqRQ9ZGKcAYOaLFXHv2YHf2XC
 qIDMf+slBGSQ66UoATnYV2gAopNlWbZ7n0vO6tE2KyvhHZ1m399aBX1+k8la/0JI
 69r+Tz7ZHUSFtmlmyByi5IAB87myy2WQHyAPwj+4vwJkDGPcl0TrupzbG7+T05Y=
 =42ti
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:

 - ARM: GICv3 ITS emulation and various fixes.  Removal of the
   old VGIC implementation.

 - s390: support for trapping software breakpoints, nested
   virtualization (vSIE), the STHYI opcode, initial extensions
   for CPU model support.

 - MIPS: support for MIPS64 hosts (32-bit guests only) and lots
   of cleanups, preliminary to this and the upcoming support for
   hardware virtualization extensions.

 - x86: support for execute-only mappings in nested EPT; reduced
   vmexit latency for TSC deadline timer (by about 30%) on Intel
   hosts; support for more than 255 vCPUs.

 - PPC: bugfixes.

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (302 commits)
  KVM: PPC: Introduce KVM_CAP_PPC_HTM
  MIPS: Select HAVE_KVM for MIPS64_R{2,6}
  MIPS: KVM: Reset CP0_PageMask during host TLB flush
  MIPS: KVM: Fix ptr->int cast via KVM_GUEST_KSEGX()
  MIPS: KVM: Sign extend MFC0/RDHWR results
  MIPS: KVM: Fix 64-bit big endian dynamic translation
  MIPS: KVM: Fail if ebase doesn't fit in CP0_EBase
  MIPS: KVM: Use 64-bit CP0_EBase when appropriate
  MIPS: KVM: Set CP0_Status.KX on MIPS64
  MIPS: KVM: Make entry code MIPS64 friendly
  MIPS: KVM: Use kmap instead of CKSEG0ADDR()
  MIPS: KVM: Use virt_to_phys() to get commpage PFN
  MIPS: Fix definition of KSEGX() for 64-bit
  KVM: VMX: Add VMCS to CPU's loaded VMCSs before VMPTRLD
  kvm: x86: nVMX: maintain internal copy of current VMCS
  KVM: PPC: Book3S HV: Save/restore TM state in H_CEDE
  KVM: PPC: Book3S HV: Pull out TM state save/restore into separate procedures
  KVM: arm64: vgic-its: Simplify MAPI error handling
  KVM: arm64: vgic-its: Make vgic_its_cmd_handle_mapi similar to other handlers
  KVM: arm64: vgic-its: Turn device_id validation into generic ID validation
  ...
2016-08-02 16:11:27 -04:00

353 lines
9.1 KiB
C

/*
* Copyright (C) 2015 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/types.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_hyp.h>
static bool __hyp_text __fpsimd_enabled_nvhe(void)
{
return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
}
static bool __hyp_text __fpsimd_enabled_vhe(void)
{
return !!(read_sysreg(cpacr_el1) & CPACR_EL1_FPEN);
}
static hyp_alternate_select(__fpsimd_is_enabled,
__fpsimd_enabled_nvhe, __fpsimd_enabled_vhe,
ARM64_HAS_VIRT_HOST_EXTN);
bool __hyp_text __fpsimd_enabled(void)
{
return __fpsimd_is_enabled()();
}
static void __hyp_text __activate_traps_vhe(void)
{
u64 val;
val = read_sysreg(cpacr_el1);
val |= CPACR_EL1_TTA;
val &= ~CPACR_EL1_FPEN;
write_sysreg(val, cpacr_el1);
write_sysreg(__kvm_hyp_vector, vbar_el1);
}
static void __hyp_text __activate_traps_nvhe(void)
{
u64 val;
val = CPTR_EL2_DEFAULT;
val |= CPTR_EL2_TTA | CPTR_EL2_TFP;
write_sysreg(val, cptr_el2);
}
static hyp_alternate_select(__activate_traps_arch,
__activate_traps_nvhe, __activate_traps_vhe,
ARM64_HAS_VIRT_HOST_EXTN);
static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
{
u64 val;
/*
* We are about to set CPTR_EL2.TFP to trap all floating point
* register accesses to EL2, however, the ARM ARM clearly states that
* traps are only taken to EL2 if the operation would not otherwise
* trap to EL1. Therefore, always make sure that for 32-bit guests,
* we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
*/
val = vcpu->arch.hcr_el2;
if (!(val & HCR_RW)) {
write_sysreg(1 << 30, fpexc32_el2);
isb();
}
write_sysreg(val, hcr_el2);
/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
write_sysreg(1 << 15, hstr_el2);
/* Make sure we trap PMU access from EL0 to EL2 */
write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
__activate_traps_arch()();
}
static void __hyp_text __deactivate_traps_vhe(void)
{
extern char vectors[]; /* kernel exception vectors */
write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
write_sysreg(CPACR_EL1_FPEN, cpacr_el1);
write_sysreg(vectors, vbar_el1);
}
static void __hyp_text __deactivate_traps_nvhe(void)
{
write_sysreg(HCR_RW, hcr_el2);
write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
}
static hyp_alternate_select(__deactivate_traps_arch,
__deactivate_traps_nvhe, __deactivate_traps_vhe,
ARM64_HAS_VIRT_HOST_EXTN);
static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
{
__deactivate_traps_arch()();
write_sysreg(0, hstr_el2);
write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2);
write_sysreg(0, pmuserenr_el0);
}
static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = kern_hyp_va(vcpu->kvm);
write_sysreg(kvm->arch.vttbr, vttbr_el2);
}
static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
{
write_sysreg(0, vttbr_el2);
}
static hyp_alternate_select(__vgic_call_save_state,
__vgic_v2_save_state, __vgic_v3_save_state,
ARM64_HAS_SYSREG_GIC_CPUIF);
static hyp_alternate_select(__vgic_call_restore_state,
__vgic_v2_restore_state, __vgic_v3_restore_state,
ARM64_HAS_SYSREG_GIC_CPUIF);
static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu)
{
__vgic_call_save_state()(vcpu);
write_sysreg(read_sysreg(hcr_el2) & ~HCR_INT_OVERRIDE, hcr_el2);
}
static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
{
u64 val;
val = read_sysreg(hcr_el2);
val |= HCR_INT_OVERRIDE;
val |= vcpu->arch.irq_lines;
write_sysreg(val, hcr_el2);
__vgic_call_restore_state()(vcpu);
}
static bool __hyp_text __true_value(void)
{
return true;
}
static bool __hyp_text __false_value(void)
{
return false;
}
static hyp_alternate_select(__check_arm_834220,
__false_value, __true_value,
ARM64_WORKAROUND_834220);
static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
{
u64 par, tmp;
/*
* Resolve the IPA the hard way using the guest VA.
*
* Stage-1 translation already validated the memory access
* rights. As such, we can use the EL1 translation regime, and
* don't have to distinguish between EL0 and EL1 access.
*
* We do need to save/restore PAR_EL1 though, as we haven't
* saved the guest context yet, and we may return early...
*/
par = read_sysreg(par_el1);
asm volatile("at s1e1r, %0" : : "r" (far));
isb();
tmp = read_sysreg(par_el1);
write_sysreg(par, par_el1);
if (unlikely(tmp & 1))
return false; /* Translation failed, back to guest */
/* Convert PAR to HPFAR format */
*hpfar = ((tmp >> 12) & ((1UL << 36) - 1)) << 4;
return true;
}
static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
{
u64 esr = read_sysreg_el2(esr);
u8 ec = ESR_ELx_EC(esr);
u64 hpfar, far;
vcpu->arch.fault.esr_el2 = esr;
if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
return true;
far = read_sysreg_el2(far);
/*
* The HPFAR can be invalid if the stage 2 fault did not
* happen during a stage 1 page table walk (the ESR_EL2.S1PTW
* bit is clear) and one of the two following cases are true:
* 1. The fault was due to a permission fault
* 2. The processor carries errata 834220
*
* Therefore, for all non S1PTW faults where we either have a
* permission fault or the errata workaround is enabled, we
* resolve the IPA using the AT instruction.
*/
if (!(esr & ESR_ELx_S1PTW) &&
(__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
if (!__translate_far_to_hpfar(far, &hpfar))
return false;
} else {
hpfar = read_sysreg(hpfar_el2);
}
vcpu->arch.fault.far_el2 = far;
vcpu->arch.fault.hpfar_el2 = hpfar;
return true;
}
static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *host_ctxt;
struct kvm_cpu_context *guest_ctxt;
bool fp_enabled;
u64 exit_code;
vcpu = kern_hyp_va(vcpu);
write_sysreg(vcpu, tpidr_el2);
host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
guest_ctxt = &vcpu->arch.ctxt;
__sysreg_save_host_state(host_ctxt);
__debug_cond_save_host_state(vcpu);
__activate_traps(vcpu);
__activate_vm(vcpu);
__vgic_restore_state(vcpu);
__timer_restore_state(vcpu);
/*
* We must restore the 32-bit state before the sysregs, thanks
* to Cortex-A57 erratum #852523.
*/
__sysreg32_restore_state(vcpu);
__sysreg_restore_guest_state(guest_ctxt);
__debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
/* Jump in the fire! */
again:
exit_code = __guest_enter(vcpu, host_ctxt);
/* And we're baaack! */
if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
goto again;
fp_enabled = __fpsimd_enabled();
__sysreg_save_guest_state(guest_ctxt);
__sysreg32_save_state(vcpu);
__timer_save_state(vcpu);
__vgic_save_state(vcpu);
__deactivate_traps(vcpu);
__deactivate_vm(vcpu);
__sysreg_restore_host_state(host_ctxt);
if (fp_enabled) {
__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
__fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs);
}
__debug_save_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
__debug_cond_restore_host_state(vcpu);
return exit_code;
}
__alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
{
unsigned long str_va;
/*
* Force the panic string to be loaded from the literal pool,
* making sure it is a kernel address and not a PC-relative
* reference.
*/
asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));
__hyp_do_panic(str_va,
spsr, elr,
read_sysreg(esr_el2), read_sysreg_el2(far),
read_sysreg(hpfar_el2), par,
(void *)read_sysreg(tpidr_el2));
}
static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par)
{
panic(__hyp_panic_string,
spsr, elr,
read_sysreg_el2(esr), read_sysreg_el2(far),
read_sysreg(hpfar_el2), par,
(void *)read_sysreg(tpidr_el2));
}
static hyp_alternate_select(__hyp_call_panic,
__hyp_call_panic_nvhe, __hyp_call_panic_vhe,
ARM64_HAS_VIRT_HOST_EXTN);
void __hyp_text __noreturn __hyp_panic(void)
{
u64 spsr = read_sysreg_el2(spsr);
u64 elr = read_sysreg_el2(elr);
u64 par = read_sysreg(par_el1);
if (read_sysreg(vttbr_el2)) {
struct kvm_vcpu *vcpu;
struct kvm_cpu_context *host_ctxt;
vcpu = (struct kvm_vcpu *)read_sysreg(tpidr_el2);
host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
__deactivate_traps(vcpu);
__deactivate_vm(vcpu);
__sysreg_restore_host_state(host_ctxt);
}
/* Call panic for real */
__hyp_call_panic()(spsr, elr, par);
unreachable();
}