b20c9f29c5
Commit 1fcf7ce0c6
(arm: kvm: implement CPU PM notifier) added
support for CPU power-management, using a cpu_notifier to re-init
KVM on a CPU that entered CPU idle.
The code assumed that a CPU entering idle would actually be powered
off, loosing its state entierely, and would then need to be
reinitialized. It turns out that this is not always the case, and
some HW performs CPU PM without actually killing the core. In this
case, we try to reinitialize KVM while it is still live. It ends up
badly, as reported by Andre Przywara (using a Calxeda Midway):
[ 3.663897] Kernel panic - not syncing: unexpected prefetch abort in Hyp mode at: 0x685760
[ 3.663897] unexpected data abort in Hyp mode at: 0xc067d150
[ 3.663897] unexpected HVC/SVC trap in Hyp mode at: 0xc0901dd0
The trick here is to detect if we've been through a full re-init or
not by looking at HVBAR (VBAR_EL2 on arm64). This involves
implementing the backend for __hyp_get_vectors in the main KVM HYP
code (rather small), and checking the return value against the
default one when the CPU notifier is called on CPU_PM_EXIT.
Reported-by: Andre Przywara <osp@andrep.de>
Tested-by: Andre Przywara <osp@andrep.de>
Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Rob Herring <rob.herring@linaro.org>
Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
511 lines
13 KiB
ArmAsm
511 lines
13 KiB
ArmAsm
/*
|
|
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
|
|
* Author: Christoffer Dall <c.dall@virtualopensystems.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, write to the Free Software
|
|
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
#include <linux/const.h>
|
|
#include <asm/unified.h>
|
|
#include <asm/page.h>
|
|
#include <asm/ptrace.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/kvm_asm.h>
|
|
#include <asm/kvm_arm.h>
|
|
#include <asm/vfpmacros.h>
|
|
#include "interrupts_head.S"
|
|
|
|
.text
|
|
|
|
__kvm_hyp_code_start:
|
|
.globl __kvm_hyp_code_start
|
|
|
|
/********************************************************************
|
|
* Flush per-VMID TLBs
|
|
*
|
|
* void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
|
|
*
|
|
* We rely on the hardware to broadcast the TLB invalidation to all CPUs
|
|
* inside the inner-shareable domain (which is the case for all v7
|
|
* implementations). If we come across a non-IS SMP implementation, we'll
|
|
* have to use an IPI based mechanism. Until then, we stick to the simple
|
|
* hardware assisted version.
|
|
*
|
|
* As v7 does not support flushing per IPA, just nuke the whole TLB
|
|
* instead, ignoring the ipa value.
|
|
*/
|
|
ENTRY(__kvm_tlb_flush_vmid_ipa)
|
|
push {r2, r3}
|
|
|
|
dsb ishst
|
|
add r0, r0, #KVM_VTTBR
|
|
ldrd r2, r3, [r0]
|
|
mcrr p15, 6, r2, r3, c2 @ Write VTTBR
|
|
isb
|
|
mcr p15, 0, r0, c8, c3, 0 @ TLBIALLIS (rt ignored)
|
|
dsb ish
|
|
isb
|
|
mov r2, #0
|
|
mov r3, #0
|
|
mcrr p15, 6, r2, r3, c2 @ Back to VMID #0
|
|
isb @ Not necessary if followed by eret
|
|
|
|
pop {r2, r3}
|
|
bx lr
|
|
ENDPROC(__kvm_tlb_flush_vmid_ipa)
|
|
|
|
/********************************************************************
|
|
* Flush TLBs and instruction caches of all CPUs inside the inner-shareable
|
|
* domain, for all VMIDs
|
|
*
|
|
* void __kvm_flush_vm_context(void);
|
|
*/
|
|
ENTRY(__kvm_flush_vm_context)
|
|
mov r0, #0 @ rn parameter for c15 flushes is SBZ
|
|
|
|
/* Invalidate NS Non-Hyp TLB Inner Shareable (TLBIALLNSNHIS) */
|
|
mcr p15, 4, r0, c8, c3, 4
|
|
/* Invalidate instruction caches Inner Shareable (ICIALLUIS) */
|
|
mcr p15, 0, r0, c7, c1, 0
|
|
dsb ish
|
|
isb @ Not necessary if followed by eret
|
|
|
|
bx lr
|
|
ENDPROC(__kvm_flush_vm_context)
|
|
|
|
|
|
/********************************************************************
|
|
* Hypervisor world-switch code
|
|
*
|
|
*
|
|
* int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
|
|
*/
|
|
ENTRY(__kvm_vcpu_run)
|
|
@ Save the vcpu pointer
|
|
mcr p15, 4, vcpu, c13, c0, 2 @ HTPIDR
|
|
|
|
save_host_regs
|
|
|
|
restore_vgic_state
|
|
restore_timer_state
|
|
|
|
@ Store hardware CP15 state and load guest state
|
|
read_cp15_state store_to_vcpu = 0
|
|
write_cp15_state read_from_vcpu = 1
|
|
|
|
@ If the host kernel has not been configured with VFPv3 support,
|
|
@ then it is safer if we deny guests from using it as well.
|
|
#ifdef CONFIG_VFPv3
|
|
@ Set FPEXC_EN so the guest doesn't trap floating point instructions
|
|
VFPFMRX r2, FPEXC @ VMRS
|
|
push {r2}
|
|
orr r2, r2, #FPEXC_EN
|
|
VFPFMXR FPEXC, r2 @ VMSR
|
|
#endif
|
|
|
|
@ Configure Hyp-role
|
|
configure_hyp_role vmentry
|
|
|
|
@ Trap coprocessor CRx accesses
|
|
set_hstr vmentry
|
|
set_hcptr vmentry, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
|
|
set_hdcr vmentry
|
|
|
|
@ Write configured ID register into MIDR alias
|
|
ldr r1, [vcpu, #VCPU_MIDR]
|
|
mcr p15, 4, r1, c0, c0, 0
|
|
|
|
@ Write guest view of MPIDR into VMPIDR
|
|
ldr r1, [vcpu, #CP15_OFFSET(c0_MPIDR)]
|
|
mcr p15, 4, r1, c0, c0, 5
|
|
|
|
@ Set up guest memory translation
|
|
ldr r1, [vcpu, #VCPU_KVM]
|
|
add r1, r1, #KVM_VTTBR
|
|
ldrd r2, r3, [r1]
|
|
mcrr p15, 6, r2, r3, c2 @ Write VTTBR
|
|
|
|
@ We're all done, just restore the GPRs and go to the guest
|
|
restore_guest_regs
|
|
clrex @ Clear exclusive monitor
|
|
eret
|
|
|
|
__kvm_vcpu_return:
|
|
/*
|
|
* return convention:
|
|
* guest r0, r1, r2 saved on the stack
|
|
* r0: vcpu pointer
|
|
* r1: exception code
|
|
*/
|
|
save_guest_regs
|
|
|
|
@ Set VMID == 0
|
|
mov r2, #0
|
|
mov r3, #0
|
|
mcrr p15, 6, r2, r3, c2 @ Write VTTBR
|
|
|
|
@ Don't trap coprocessor accesses for host kernel
|
|
set_hstr vmexit
|
|
set_hdcr vmexit
|
|
set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
|
|
|
|
#ifdef CONFIG_VFPv3
|
|
@ Save floating point registers we if let guest use them.
|
|
tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
|
|
bne after_vfp_restore
|
|
|
|
@ Switch VFP/NEON hardware state to the host's
|
|
add r7, vcpu, #VCPU_VFP_GUEST
|
|
store_vfp_state r7
|
|
add r7, vcpu, #VCPU_VFP_HOST
|
|
ldr r7, [r7]
|
|
restore_vfp_state r7
|
|
|
|
after_vfp_restore:
|
|
@ Restore FPEXC_EN which we clobbered on entry
|
|
pop {r2}
|
|
VFPFMXR FPEXC, r2
|
|
#endif
|
|
|
|
@ Reset Hyp-role
|
|
configure_hyp_role vmexit
|
|
|
|
@ Let host read hardware MIDR
|
|
mrc p15, 0, r2, c0, c0, 0
|
|
mcr p15, 4, r2, c0, c0, 0
|
|
|
|
@ Back to hardware MPIDR
|
|
mrc p15, 0, r2, c0, c0, 5
|
|
mcr p15, 4, r2, c0, c0, 5
|
|
|
|
@ Store guest CP15 state and restore host state
|
|
read_cp15_state store_to_vcpu = 1
|
|
write_cp15_state read_from_vcpu = 0
|
|
|
|
save_timer_state
|
|
save_vgic_state
|
|
|
|
restore_host_regs
|
|
clrex @ Clear exclusive monitor
|
|
mov r0, r1 @ Return the return code
|
|
mov r1, #0 @ Clear upper bits in return value
|
|
bx lr @ return to IOCTL
|
|
|
|
/********************************************************************
|
|
* Call function in Hyp mode
|
|
*
|
|
*
|
|
* u64 kvm_call_hyp(void *hypfn, ...);
|
|
*
|
|
* This is not really a variadic function in the classic C-way and care must
|
|
* be taken when calling this to ensure parameters are passed in registers
|
|
* only, since the stack will change between the caller and the callee.
|
|
*
|
|
* Call the function with the first argument containing a pointer to the
|
|
* function you wish to call in Hyp mode, and subsequent arguments will be
|
|
* passed as r0, r1, and r2 (a maximum of 3 arguments in addition to the
|
|
* function pointer can be passed). The function being called must be mapped
|
|
* in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are
|
|
* passed in r0 and r1.
|
|
*
|
|
* A function pointer with a value of 0xffffffff has a special meaning,
|
|
* and is used to implement __hyp_get_vectors in the same way as in
|
|
* arch/arm/kernel/hyp_stub.S.
|
|
*
|
|
* The calling convention follows the standard AAPCS:
|
|
* r0 - r3: caller save
|
|
* r12: caller save
|
|
* rest: callee save
|
|
*/
|
|
ENTRY(kvm_call_hyp)
|
|
hvc #0
|
|
bx lr
|
|
|
|
/********************************************************************
|
|
* Hypervisor exception vector and handlers
|
|
*
|
|
*
|
|
* The KVM/ARM Hypervisor ABI is defined as follows:
|
|
*
|
|
* Entry to Hyp mode from the host kernel will happen _only_ when an HVC
|
|
* instruction is issued since all traps are disabled when running the host
|
|
* kernel as per the Hyp-mode initialization at boot time.
|
|
*
|
|
* HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc
|
|
* below) when the HVC instruction is called from SVC mode (i.e. a guest or the
|
|
* host kernel) and they cause a trap to the vector page + offset 0x8 when HVC
|
|
* instructions are called from within Hyp-mode.
|
|
*
|
|
* Hyp-ABI: Calling HYP-mode functions from host (in SVC mode):
|
|
* Switching to Hyp mode is done through a simple HVC #0 instruction. The
|
|
* exception vector code will check that the HVC comes from VMID==0 and if
|
|
* so will push the necessary state (SPSR, lr_usr) on the Hyp stack.
|
|
* - r0 contains a pointer to a HYP function
|
|
* - r1, r2, and r3 contain arguments to the above function.
|
|
* - The HYP function will be called with its arguments in r0, r1 and r2.
|
|
* On HYP function return, we return directly to SVC.
|
|
*
|
|
* Note that the above is used to execute code in Hyp-mode from a host-kernel
|
|
* point of view, and is a different concept from performing a world-switch and
|
|
* executing guest code SVC mode (with a VMID != 0).
|
|
*/
|
|
|
|
/* Handle undef, svc, pabt, or dabt by crashing with a user notice */
|
|
.macro bad_exception exception_code, panic_str
|
|
push {r0-r2}
|
|
mrrc p15, 6, r0, r1, c2 @ Read VTTBR
|
|
lsr r1, r1, #16
|
|
ands r1, r1, #0xff
|
|
beq 99f
|
|
|
|
load_vcpu @ Load VCPU pointer
|
|
.if \exception_code == ARM_EXCEPTION_DATA_ABORT
|
|
mrc p15, 4, r2, c5, c2, 0 @ HSR
|
|
mrc p15, 4, r1, c6, c0, 0 @ HDFAR
|
|
str r2, [vcpu, #VCPU_HSR]
|
|
str r1, [vcpu, #VCPU_HxFAR]
|
|
.endif
|
|
.if \exception_code == ARM_EXCEPTION_PREF_ABORT
|
|
mrc p15, 4, r2, c5, c2, 0 @ HSR
|
|
mrc p15, 4, r1, c6, c0, 2 @ HIFAR
|
|
str r2, [vcpu, #VCPU_HSR]
|
|
str r1, [vcpu, #VCPU_HxFAR]
|
|
.endif
|
|
mov r1, #\exception_code
|
|
b __kvm_vcpu_return
|
|
|
|
@ We were in the host already. Let's craft a panic-ing return to SVC.
|
|
99: mrs r2, cpsr
|
|
bic r2, r2, #MODE_MASK
|
|
orr r2, r2, #SVC_MODE
|
|
THUMB( orr r2, r2, #PSR_T_BIT )
|
|
msr spsr_cxsf, r2
|
|
mrs r1, ELR_hyp
|
|
ldr r2, =BSYM(panic)
|
|
msr ELR_hyp, r2
|
|
ldr r0, =\panic_str
|
|
clrex @ Clear exclusive monitor
|
|
eret
|
|
.endm
|
|
|
|
.text
|
|
|
|
.align 5
|
|
__kvm_hyp_vector:
|
|
.globl __kvm_hyp_vector
|
|
|
|
@ Hyp-mode exception vector
|
|
W(b) hyp_reset
|
|
W(b) hyp_undef
|
|
W(b) hyp_svc
|
|
W(b) hyp_pabt
|
|
W(b) hyp_dabt
|
|
W(b) hyp_hvc
|
|
W(b) hyp_irq
|
|
W(b) hyp_fiq
|
|
|
|
.align
|
|
hyp_reset:
|
|
b hyp_reset
|
|
|
|
.align
|
|
hyp_undef:
|
|
bad_exception ARM_EXCEPTION_UNDEFINED, und_die_str
|
|
|
|
.align
|
|
hyp_svc:
|
|
bad_exception ARM_EXCEPTION_HVC, svc_die_str
|
|
|
|
.align
|
|
hyp_pabt:
|
|
bad_exception ARM_EXCEPTION_PREF_ABORT, pabt_die_str
|
|
|
|
.align
|
|
hyp_dabt:
|
|
bad_exception ARM_EXCEPTION_DATA_ABORT, dabt_die_str
|
|
|
|
.align
|
|
hyp_hvc:
|
|
/*
|
|
* Getting here is either becuase of a trap from a guest or from calling
|
|
* HVC from the host kernel, which means "switch to Hyp mode".
|
|
*/
|
|
push {r0, r1, r2}
|
|
|
|
@ Check syndrome register
|
|
mrc p15, 4, r1, c5, c2, 0 @ HSR
|
|
lsr r0, r1, #HSR_EC_SHIFT
|
|
#ifdef CONFIG_VFPv3
|
|
cmp r0, #HSR_EC_CP_0_13
|
|
beq switch_to_guest_vfp
|
|
#endif
|
|
cmp r0, #HSR_EC_HVC
|
|
bne guest_trap @ Not HVC instr.
|
|
|
|
/*
|
|
* Let's check if the HVC came from VMID 0 and allow simple
|
|
* switch to Hyp mode
|
|
*/
|
|
mrrc p15, 6, r0, r2, c2
|
|
lsr r2, r2, #16
|
|
and r2, r2, #0xff
|
|
cmp r2, #0
|
|
bne guest_trap @ Guest called HVC
|
|
|
|
host_switch_to_hyp:
|
|
pop {r0, r1, r2}
|
|
|
|
/* Check for __hyp_get_vectors */
|
|
cmp r0, #-1
|
|
mrceq p15, 4, r0, c12, c0, 0 @ get HVBAR
|
|
beq 1f
|
|
|
|
push {lr}
|
|
mrs lr, SPSR
|
|
push {lr}
|
|
|
|
mov lr, r0
|
|
mov r0, r1
|
|
mov r1, r2
|
|
mov r2, r3
|
|
|
|
THUMB( orr lr, #1)
|
|
blx lr @ Call the HYP function
|
|
|
|
pop {lr}
|
|
msr SPSR_csxf, lr
|
|
pop {lr}
|
|
1: eret
|
|
|
|
guest_trap:
|
|
load_vcpu @ Load VCPU pointer to r0
|
|
str r1, [vcpu, #VCPU_HSR]
|
|
|
|
@ Check if we need the fault information
|
|
lsr r1, r1, #HSR_EC_SHIFT
|
|
cmp r1, #HSR_EC_IABT
|
|
mrceq p15, 4, r2, c6, c0, 2 @ HIFAR
|
|
beq 2f
|
|
cmp r1, #HSR_EC_DABT
|
|
bne 1f
|
|
mrc p15, 4, r2, c6, c0, 0 @ HDFAR
|
|
|
|
2: str r2, [vcpu, #VCPU_HxFAR]
|
|
|
|
/*
|
|
* B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode:
|
|
*
|
|
* Abort on the stage 2 translation for a memory access from a
|
|
* Non-secure PL1 or PL0 mode:
|
|
*
|
|
* For any Access flag fault or Translation fault, and also for any
|
|
* Permission fault on the stage 2 translation of a memory access
|
|
* made as part of a translation table walk for a stage 1 translation,
|
|
* the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR
|
|
* is UNKNOWN.
|
|
*/
|
|
|
|
/* Check for permission fault, and S1PTW */
|
|
mrc p15, 4, r1, c5, c2, 0 @ HSR
|
|
and r0, r1, #HSR_FSC_TYPE
|
|
cmp r0, #FSC_PERM
|
|
tsteq r1, #(1 << 7) @ S1PTW
|
|
mrcne p15, 4, r2, c6, c0, 4 @ HPFAR
|
|
bne 3f
|
|
|
|
/* Preserve PAR */
|
|
mrrc p15, 0, r0, r1, c7 @ PAR
|
|
push {r0, r1}
|
|
|
|
/* Resolve IPA using the xFAR */
|
|
mcr p15, 0, r2, c7, c8, 0 @ ATS1CPR
|
|
isb
|
|
mrrc p15, 0, r0, r1, c7 @ PAR
|
|
tst r0, #1
|
|
bne 4f @ Failed translation
|
|
ubfx r2, r0, #12, #20
|
|
lsl r2, r2, #4
|
|
orr r2, r2, r1, lsl #24
|
|
|
|
/* Restore PAR */
|
|
pop {r0, r1}
|
|
mcrr p15, 0, r0, r1, c7 @ PAR
|
|
|
|
3: load_vcpu @ Load VCPU pointer to r0
|
|
str r2, [r0, #VCPU_HPFAR]
|
|
|
|
1: mov r1, #ARM_EXCEPTION_HVC
|
|
b __kvm_vcpu_return
|
|
|
|
4: pop {r0, r1} @ Failed translation, return to guest
|
|
mcrr p15, 0, r0, r1, c7 @ PAR
|
|
clrex
|
|
pop {r0, r1, r2}
|
|
eret
|
|
|
|
/*
|
|
* If VFPv3 support is not available, then we will not switch the VFP
|
|
* registers; however cp10 and cp11 accesses will still trap and fallback
|
|
* to the regular coprocessor emulation code, which currently will
|
|
* inject an undefined exception to the guest.
|
|
*/
|
|
#ifdef CONFIG_VFPv3
|
|
switch_to_guest_vfp:
|
|
load_vcpu @ Load VCPU pointer to r0
|
|
push {r3-r7}
|
|
|
|
@ NEON/VFP used. Turn on VFP access.
|
|
set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
|
|
|
|
@ Switch VFP/NEON hardware state to the guest's
|
|
add r7, r0, #VCPU_VFP_HOST
|
|
ldr r7, [r7]
|
|
store_vfp_state r7
|
|
add r7, r0, #VCPU_VFP_GUEST
|
|
restore_vfp_state r7
|
|
|
|
pop {r3-r7}
|
|
pop {r0-r2}
|
|
clrex
|
|
eret
|
|
#endif
|
|
|
|
.align
|
|
hyp_irq:
|
|
push {r0, r1, r2}
|
|
mov r1, #ARM_EXCEPTION_IRQ
|
|
load_vcpu @ Load VCPU pointer to r0
|
|
b __kvm_vcpu_return
|
|
|
|
.align
|
|
hyp_fiq:
|
|
b hyp_fiq
|
|
|
|
.ltorg
|
|
|
|
__kvm_hyp_code_end:
|
|
.globl __kvm_hyp_code_end
|
|
|
|
.section ".rodata"
|
|
|
|
und_die_str:
|
|
.ascii "unexpected undefined exception in Hyp mode at: %#08x\n"
|
|
pabt_die_str:
|
|
.ascii "unexpected prefetch abort in Hyp mode at: %#08x\n"
|
|
dabt_die_str:
|
|
.ascii "unexpected data abort in Hyp mode at: %#08x\n"
|
|
svc_die_str:
|
|
.ascii "unexpected HVC/SVC trap in Hyp mode at: %#08x\n"
|