linux_dsm_epyc7002/arch/mips/include/asm/kvm_host.h

1053 lines
34 KiB
C
Raw Normal View History

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
* Authors: Sanjay Lal <sanjayl@kymasys.com>
*/
#ifndef __MIPS_KVM_HOST_H__
#define __MIPS_KVM_HOST_H__
#include <linux/mutex.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/types.h>
#include <linux/kvm.h>
#include <linux/kvm_types.h>
#include <linux/threads.h>
#include <linux/spinlock.h>
#include <asm/inst.h>
#include <asm/mipsregs.h>
/* MIPS KVM register ids */
#define MIPS_CP0_32(_R, _S) \
(KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U32 | (8 * (_R) + (_S)))
#define MIPS_CP0_64(_R, _S) \
(KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U64 | (8 * (_R) + (_S)))
#define KVM_REG_MIPS_CP0_INDEX MIPS_CP0_32(0, 0)
#define KVM_REG_MIPS_CP0_ENTRYLO0 MIPS_CP0_64(2, 0)
#define KVM_REG_MIPS_CP0_ENTRYLO1 MIPS_CP0_64(3, 0)
#define KVM_REG_MIPS_CP0_CONTEXT MIPS_CP0_64(4, 0)
#define KVM_REG_MIPS_CP0_USERLOCAL MIPS_CP0_64(4, 2)
#define KVM_REG_MIPS_CP0_PAGEMASK MIPS_CP0_32(5, 0)
#define KVM_REG_MIPS_CP0_PAGEGRAIN MIPS_CP0_32(5, 1)
#define KVM_REG_MIPS_CP0_WIRED MIPS_CP0_32(6, 0)
#define KVM_REG_MIPS_CP0_HWRENA MIPS_CP0_32(7, 0)
#define KVM_REG_MIPS_CP0_BADVADDR MIPS_CP0_64(8, 0)
#define KVM_REG_MIPS_CP0_COUNT MIPS_CP0_32(9, 0)
#define KVM_REG_MIPS_CP0_ENTRYHI MIPS_CP0_64(10, 0)
#define KVM_REG_MIPS_CP0_COMPARE MIPS_CP0_32(11, 0)
#define KVM_REG_MIPS_CP0_STATUS MIPS_CP0_32(12, 0)
#define KVM_REG_MIPS_CP0_INTCTL MIPS_CP0_32(12, 1)
#define KVM_REG_MIPS_CP0_CAUSE MIPS_CP0_32(13, 0)
#define KVM_REG_MIPS_CP0_EPC MIPS_CP0_64(14, 0)
#define KVM_REG_MIPS_CP0_PRID MIPS_CP0_32(15, 0)
#define KVM_REG_MIPS_CP0_EBASE MIPS_CP0_64(15, 1)
#define KVM_REG_MIPS_CP0_CONFIG MIPS_CP0_32(16, 0)
#define KVM_REG_MIPS_CP0_CONFIG1 MIPS_CP0_32(16, 1)
#define KVM_REG_MIPS_CP0_CONFIG2 MIPS_CP0_32(16, 2)
#define KVM_REG_MIPS_CP0_CONFIG3 MIPS_CP0_32(16, 3)
#define KVM_REG_MIPS_CP0_CONFIG4 MIPS_CP0_32(16, 4)
#define KVM_REG_MIPS_CP0_CONFIG5 MIPS_CP0_32(16, 5)
#define KVM_REG_MIPS_CP0_CONFIG7 MIPS_CP0_32(16, 7)
#define KVM_REG_MIPS_CP0_XCONTEXT MIPS_CP0_64(20, 0)
#define KVM_REG_MIPS_CP0_ERROREPC MIPS_CP0_64(30, 0)
#define KVM_REG_MIPS_CP0_KSCRATCH1 MIPS_CP0_64(31, 2)
#define KVM_REG_MIPS_CP0_KSCRATCH2 MIPS_CP0_64(31, 3)
#define KVM_REG_MIPS_CP0_KSCRATCH3 MIPS_CP0_64(31, 4)
#define KVM_REG_MIPS_CP0_KSCRATCH4 MIPS_CP0_64(31, 5)
#define KVM_REG_MIPS_CP0_KSCRATCH5 MIPS_CP0_64(31, 6)
#define KVM_REG_MIPS_CP0_KSCRATCH6 MIPS_CP0_64(31, 7)
#define KVM_MAX_VCPUS 8
#define KVM_USER_MEM_SLOTS 8
/* memory slots that does not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 0
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
#define KVM_HALT_POLL_NS_DEFAULT 500000
/*
* Special address that contains the comm page, used for reducing # of traps
* This needs to be within 32Kb of 0x0 (so the zero register can be used), but
* preferably not at 0x0 so that most kernel NULL pointer dereferences can be
* caught.
*/
#define KVM_GUEST_COMMPAGE_ADDR ((PAGE_SIZE > 0x8000) ? 0 : \
(0x8000 - PAGE_SIZE))
#define KVM_GUEST_KERNEL_MODE(vcpu) ((kvm_read_c0_guest_status(vcpu->arch.cop0) & (ST0_EXL | ST0_ERL)) || \
((kvm_read_c0_guest_status(vcpu->arch.cop0) & KSU_USER) == 0))
#define KVM_GUEST_KUSEG 0x00000000UL
#define KVM_GUEST_KSEG0 0x40000000UL
#define KVM_GUEST_KSEG1 0x40000000UL
#define KVM_GUEST_KSEG23 0x60000000UL
#define KVM_GUEST_KSEGX(a) ((_ACAST32_(a)) & 0xe0000000)
#define KVM_GUEST_CPHYSADDR(a) ((_ACAST32_(a)) & 0x1fffffff)
#define KVM_GUEST_CKSEG0ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG0)
#define KVM_GUEST_CKSEG1ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG1)
#define KVM_GUEST_CKSEG23ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG23)
/*
* Map an address to a certain kernel segment
*/
#define KVM_GUEST_KSEG0ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG0)
#define KVM_GUEST_KSEG1ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG1)
#define KVM_GUEST_KSEG23ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG23)
#define KVM_INVALID_PAGE 0xdeadbeef
#define KVM_INVALID_ADDR 0xdeadbeef
/*
* EVA has overlapping user & kernel address spaces, so user VAs may be >
* PAGE_OFFSET. For this reason we can't use the default KVM_HVA_ERR_BAD of
* PAGE_OFFSET.
*/
#define KVM_HVA_ERR_BAD (-1UL)
#define KVM_HVA_ERR_RO_BAD (-2UL)
static inline bool kvm_is_error_hva(unsigned long addr)
{
return IS_ERR_VALUE(addr);
}
struct kvm_vm_stat {
ulong remote_tlb_flush;
};
struct kvm_vcpu_stat {
u64 wait_exits;
u64 cache_exits;
u64 signal_exits;
u64 int_exits;
u64 cop_unusable_exits;
u64 tlbmod_exits;
u64 tlbmiss_ld_exits;
u64 tlbmiss_st_exits;
u64 addrerr_st_exits;
u64 addrerr_ld_exits;
u64 syscall_exits;
u64 resvd_inst_exits;
u64 break_inst_exits;
u64 trap_inst_exits;
u64 msa_fpe_exits;
u64 fpe_exits;
u64 msa_disabled_exits;
u64 flush_dcache_exits;
#ifdef CONFIG_KVM_MIPS_VZ
u64 vz_gpsi_exits;
u64 vz_gsfc_exits;
u64 vz_hc_exits;
u64 vz_grr_exits;
u64 vz_gva_exits;
u64 vz_ghfc_exits;
u64 vz_gpa_exits;
u64 vz_resvd_exits;
#endif
u64 halt_successful_poll;
u64 halt_attempted_poll;
u64 halt_poll_invalid;
u64 halt_wakeup;
};
struct kvm_arch_memory_slot {
};
struct kvm_arch {
/* Guest physical mm */
struct mm_struct gpa_mm;
};
#define N_MIPS_COPROC_REGS 32
#define N_MIPS_COPROC_SEL 8
struct mips_coproc {
unsigned long reg[N_MIPS_COPROC_REGS][N_MIPS_COPROC_SEL];
#ifdef CONFIG_KVM_MIPS_DEBUG_COP0_COUNTERS
unsigned long stat[N_MIPS_COPROC_REGS][N_MIPS_COPROC_SEL];
#endif
};
/*
* Coprocessor 0 register names
*/
#define MIPS_CP0_TLB_INDEX 0
#define MIPS_CP0_TLB_RANDOM 1
#define MIPS_CP0_TLB_LOW 2
#define MIPS_CP0_TLB_LO0 2
#define MIPS_CP0_TLB_LO1 3
#define MIPS_CP0_TLB_CONTEXT 4
#define MIPS_CP0_TLB_PG_MASK 5
#define MIPS_CP0_TLB_WIRED 6
#define MIPS_CP0_HWRENA 7
#define MIPS_CP0_BAD_VADDR 8
#define MIPS_CP0_COUNT 9
#define MIPS_CP0_TLB_HI 10
#define MIPS_CP0_COMPARE 11
#define MIPS_CP0_STATUS 12
#define MIPS_CP0_CAUSE 13
#define MIPS_CP0_EXC_PC 14
#define MIPS_CP0_PRID 15
#define MIPS_CP0_CONFIG 16
#define MIPS_CP0_LLADDR 17
#define MIPS_CP0_WATCH_LO 18
#define MIPS_CP0_WATCH_HI 19
#define MIPS_CP0_TLB_XCONTEXT 20
#define MIPS_CP0_ECC 26
#define MIPS_CP0_CACHE_ERR 27
#define MIPS_CP0_TAG_LO 28
#define MIPS_CP0_TAG_HI 29
#define MIPS_CP0_ERROR_PC 30
#define MIPS_CP0_DEBUG 23
#define MIPS_CP0_DEPC 24
#define MIPS_CP0_PERFCNT 25
#define MIPS_CP0_ERRCTL 26
#define MIPS_CP0_DATA_LO 28
#define MIPS_CP0_DATA_HI 29
#define MIPS_CP0_DESAVE 31
#define MIPS_CP0_CONFIG_SEL 0
#define MIPS_CP0_CONFIG1_SEL 1
#define MIPS_CP0_CONFIG2_SEL 2
#define MIPS_CP0_CONFIG3_SEL 3
#define MIPS_CP0_CONFIG4_SEL 4
#define MIPS_CP0_CONFIG5_SEL 5
/* Resume Flags */
#define RESUME_FLAG_DR (1<<0) /* Reload guest nonvolatile state? */
#define RESUME_FLAG_HOST (1<<1) /* Resume host? */
#define RESUME_GUEST 0
#define RESUME_GUEST_DR RESUME_FLAG_DR
#define RESUME_HOST RESUME_FLAG_HOST
enum emulation_result {
EMULATE_DONE, /* no further processing */
EMULATE_DO_MMIO, /* kvm_run filled with MMIO request */
EMULATE_FAIL, /* can't emulate this instruction */
EMULATE_WAIT, /* WAIT instruction */
EMULATE_PRIV_FAIL,
EMULATE_EXCEPT, /* A guest exception has been generated */
EMULATE_HYPERCALL, /* HYPCALL instruction */
};
#define mips3_paddr_to_tlbpfn(x) \
(((unsigned long)(x) >> MIPS3_PG_SHIFT) & MIPS3_PG_FRAME)
#define mips3_tlbpfn_to_paddr(x) \
((unsigned long)((x) & MIPS3_PG_FRAME) << MIPS3_PG_SHIFT)
#define MIPS3_PG_SHIFT 6
#define MIPS3_PG_FRAME 0x3fffffc0
#define VPN2_MASK 0xffffe000
#define KVM_ENTRYHI_ASID MIPS_ENTRYHI_ASID
#define TLB_IS_GLOBAL(x) ((x).tlb_lo[0] & (x).tlb_lo[1] & ENTRYLO_G)
#define TLB_VPN2(x) ((x).tlb_hi & VPN2_MASK)
#define TLB_ASID(x) ((x).tlb_hi & KVM_ENTRYHI_ASID)
#define TLB_LO_IDX(x, va) (((va) >> PAGE_SHIFT) & 1)
#define TLB_IS_VALID(x, va) ((x).tlb_lo[TLB_LO_IDX(x, va)] & ENTRYLO_V)
#define TLB_IS_DIRTY(x, va) ((x).tlb_lo[TLB_LO_IDX(x, va)] & ENTRYLO_D)
#define TLB_HI_VPN2_HIT(x, y) ((TLB_VPN2(x) & ~(x).tlb_mask) == \
((y) & VPN2_MASK & ~(x).tlb_mask))
#define TLB_HI_ASID_HIT(x, y) (TLB_IS_GLOBAL(x) || \
TLB_ASID(x) == ((y) & KVM_ENTRYHI_ASID))
struct kvm_mips_tlb {
long tlb_mask;
long tlb_hi;
long tlb_lo[2];
};
#define KVM_NR_MEM_OBJS 4
/*
* We don't want allocation failures within the mmu code, so we preallocate
* enough memory for a single page fault in a cache.
*/
struct kvm_mmu_memory_cache {
int nobjs;
void *objects[KVM_NR_MEM_OBJS];
};
#define KVM_MIPS_AUX_FPU 0x1
#define KVM_MIPS_AUX_MSA 0x2
MIPS: KVM: Add base guest FPU support Add base code for supporting FPU in MIPS KVM guests. The FPU cannot yet be enabled in the guest, we're just laying the groundwork. Whether the guest's FPU context is loaded is stored in a bit in the fpu_inuse vcpu member. This allows the FPU to be disabled when the guest disables it, but keeping the FPU context loaded so it doesn't have to be reloaded if the guest re-enables it. An fpu_enabled vcpu member stores whether userland has enabled the FPU capability (which will be wired up in a later patch). New assembly code is added for saving and restoring the FPU context, and for saving/clearing and restoring FCSR (which can itself cause an FP exception depending on the value). The FCSR is restored before returning to the guest if the FPU is already enabled, and a die notifier is registered to catch the possible FP exception and step over the ctc1 instruction. The helper function kvm_lose_fpu() is added to save FPU context and disable the FPU, which is used when saving hardware state before a context switch or KVM exit (the vcpu_get_regs() callback). The helper function kvm_own_fpu() is added to enable the FPU and restore the FPU context if it isn't already loaded, which will be used in a later patch when the guest attempts to use the FPU for the first time and triggers a co-processor unusable exception. The helper function kvm_drop_fpu() is added to discard the FPU context and disable the FPU, which will be used in a later patch when the FPU state will become architecturally UNPREDICTABLE (change of FR mode) to force a reload of [stale] context in the new FR mode. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2014-11-18 21:09:12 +07:00
#define KVM_MIPS_GUEST_TLB_SIZE 64
struct kvm_vcpu_arch {
void *guest_ebase;
int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
/* Host registers preserved across guest mode execution */
unsigned long host_stack;
unsigned long host_gp;
unsigned long host_pgd;
unsigned long host_entryhi;
/* Host CP0 registers used when handling exits from guest */
unsigned long host_cp0_badvaddr;
unsigned long host_cp0_epc;
u32 host_cp0_cause;
u32 host_cp0_guestctl0;
u32 host_cp0_badinstr;
u32 host_cp0_badinstrp;
/* GPRS */
unsigned long gprs[32];
unsigned long hi;
unsigned long lo;
unsigned long pc;
/* FPU State */
struct mips_fpu_struct fpu;
/* Which auxiliary state is loaded (KVM_MIPS_AUX_*) */
unsigned int aux_inuse;
/* COP0 State */
struct mips_coproc *cop0;
/* Host KSEG0 address of the EI/DI offset */
void *kseg0_commpage;
/* Resume PC after MMIO completion */
unsigned long io_pc;
/* GPR used as IO source/target */
u32 io_gpr;
MIPS: KVM: Rewrite count/compare timer emulation Previously the emulation of the CPU timer was just enough to get a Linux guest running but some shortcuts were taken: - The guest timer interrupt was hard coded to always happen every 10 ms rather than being timed to when CP0_Count would match CP0_Compare. - The guest's CP0_Count register was based on the host's CP0_Count register. This isn't very portable and fails on cores without a CP_Count register implemented such as Ingenic XBurst. It also meant that the guest's CP0_Cause.DC bit to disable the CP0_Count register took no effect. - The guest's CP0_Count register was emulated by just dividing the host's CP0_Count register by 4. This resulted in continuity problems when used as a clock source, since when the host CP0_Count overflows from 0x7fffffff to 0x80000000, the guest CP0_Count transitions discontinuously from 0x1fffffff to 0xe0000000. Therefore rewrite & fix emulation of the guest timer based on the monotonic kernel time (i.e. ktime_get()). Internally a 32-bit count_bias value is added to the frequency scaled nanosecond monotonic time to get the guest's CP0_Count. The frequency of the timer is initialised to 100MHz and cannot yet be changed, but a later patch will allow the frequency to be configured via the KVM_{GET,SET}_ONE_REG ioctl interface. The timer can now be stopped via the CP0_Cause.DC bit (by the guest or via the KVM_SET_ONE_REG ioctl interface), at which point the current CP0_Count is stored and can be read directly. When it is restarted the bias is recalculated such that the CP0_Count value is continuous. Due to the nature of hrtimer interrupts any read of the guest's CP0_Count register while it is running triggers a check for whether the hrtimer has expired, so that the guest/userland cannot observe the CP0_Count passing CP0_Compare without queuing a timer interrupt. This is also taken advantage of when stopping the timer to ensure that a pending timer interrupt is queued. This replaces the implementation of: - Guest read of CP0_Count - Guest write of CP0_Count - Guest write of CP0_Compare - Guest write of CP0_Cause - Guest read of HWR 2 (CC) with RDHWR - Host read of CP0_Count via KVM_GET_ONE_REG ioctl interface - Host write of CP0_Count via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Compare via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Cause via KVM_SET_ONE_REG ioctl interface Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:35 +07:00
struct hrtimer comparecount_timer;
MIPS: KVM: Add master disable count interface Expose two new virtual registers to userland via the KVM_{GET,SET}_ONE_REG ioctls. KVM_REG_MIPS_COUNT_CTL is for timer configuration fields and just contains a master disable count bit. This can be used by userland to freeze the timer in order to read a consistent state from the timer count value and timer interrupt pending bit. This cannot be done with the CP0_Cause.DC bit because the timer interrupt pending bit (TI) is also in CP0_Cause so it would be impossible to stop the timer without also risking a race with an hrtimer interrupt and having to explicitly check whether an interrupt should have occurred. When the timer is re-enabled it resumes without losing time, i.e. the CP0_Count value jumps to what it would have been had the timer not been disabled, which would also be impossible to do from userland with CP0_Cause.DC. The timer interrupt also cannot be lost, i.e. if a timer interrupt would have occurred had the timer not been disabled it is queued when the timer is re-enabled. This works by storing the nanosecond monotonic time when the master disable is set, and using it for various operations instead of the current monotonic time (e.g. when recalculating the bias when the CP0_Count is set), until the master disable is cleared again, i.e. the timer state is read/written as it would have been at that time. This state is exposed to userland via the read-only KVM_REG_MIPS_COUNT_RESUME virtual register so that userland can determine the exact time the master disable took effect. This should allow userland to atomically save the state of the timer, and later restore it. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David Daney <david.daney@cavium.com> Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:37 +07:00
/* Count timer control KVM register */
u32 count_ctl;
MIPS: KVM: Rewrite count/compare timer emulation Previously the emulation of the CPU timer was just enough to get a Linux guest running but some shortcuts were taken: - The guest timer interrupt was hard coded to always happen every 10 ms rather than being timed to when CP0_Count would match CP0_Compare. - The guest's CP0_Count register was based on the host's CP0_Count register. This isn't very portable and fails on cores without a CP_Count register implemented such as Ingenic XBurst. It also meant that the guest's CP0_Cause.DC bit to disable the CP0_Count register took no effect. - The guest's CP0_Count register was emulated by just dividing the host's CP0_Count register by 4. This resulted in continuity problems when used as a clock source, since when the host CP0_Count overflows from 0x7fffffff to 0x80000000, the guest CP0_Count transitions discontinuously from 0x1fffffff to 0xe0000000. Therefore rewrite & fix emulation of the guest timer based on the monotonic kernel time (i.e. ktime_get()). Internally a 32-bit count_bias value is added to the frequency scaled nanosecond monotonic time to get the guest's CP0_Count. The frequency of the timer is initialised to 100MHz and cannot yet be changed, but a later patch will allow the frequency to be configured via the KVM_{GET,SET}_ONE_REG ioctl interface. The timer can now be stopped via the CP0_Cause.DC bit (by the guest or via the KVM_SET_ONE_REG ioctl interface), at which point the current CP0_Count is stored and can be read directly. When it is restarted the bias is recalculated such that the CP0_Count value is continuous. Due to the nature of hrtimer interrupts any read of the guest's CP0_Count register while it is running triggers a check for whether the hrtimer has expired, so that the guest/userland cannot observe the CP0_Count passing CP0_Compare without queuing a timer interrupt. This is also taken advantage of when stopping the timer to ensure that a pending timer interrupt is queued. This replaces the implementation of: - Guest read of CP0_Count - Guest write of CP0_Count - Guest write of CP0_Compare - Guest write of CP0_Cause - Guest read of HWR 2 (CC) with RDHWR - Host read of CP0_Count via KVM_GET_ONE_REG ioctl interface - Host write of CP0_Count via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Compare via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Cause via KVM_SET_ONE_REG ioctl interface Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:35 +07:00
/* Count bias from the raw time */
u32 count_bias;
MIPS: KVM: Rewrite count/compare timer emulation Previously the emulation of the CPU timer was just enough to get a Linux guest running but some shortcuts were taken: - The guest timer interrupt was hard coded to always happen every 10 ms rather than being timed to when CP0_Count would match CP0_Compare. - The guest's CP0_Count register was based on the host's CP0_Count register. This isn't very portable and fails on cores without a CP_Count register implemented such as Ingenic XBurst. It also meant that the guest's CP0_Cause.DC bit to disable the CP0_Count register took no effect. - The guest's CP0_Count register was emulated by just dividing the host's CP0_Count register by 4. This resulted in continuity problems when used as a clock source, since when the host CP0_Count overflows from 0x7fffffff to 0x80000000, the guest CP0_Count transitions discontinuously from 0x1fffffff to 0xe0000000. Therefore rewrite & fix emulation of the guest timer based on the monotonic kernel time (i.e. ktime_get()). Internally a 32-bit count_bias value is added to the frequency scaled nanosecond monotonic time to get the guest's CP0_Count. The frequency of the timer is initialised to 100MHz and cannot yet be changed, but a later patch will allow the frequency to be configured via the KVM_{GET,SET}_ONE_REG ioctl interface. The timer can now be stopped via the CP0_Cause.DC bit (by the guest or via the KVM_SET_ONE_REG ioctl interface), at which point the current CP0_Count is stored and can be read directly. When it is restarted the bias is recalculated such that the CP0_Count value is continuous. Due to the nature of hrtimer interrupts any read of the guest's CP0_Count register while it is running triggers a check for whether the hrtimer has expired, so that the guest/userland cannot observe the CP0_Count passing CP0_Compare without queuing a timer interrupt. This is also taken advantage of when stopping the timer to ensure that a pending timer interrupt is queued. This replaces the implementation of: - Guest read of CP0_Count - Guest write of CP0_Count - Guest write of CP0_Compare - Guest write of CP0_Cause - Guest read of HWR 2 (CC) with RDHWR - Host read of CP0_Count via KVM_GET_ONE_REG ioctl interface - Host write of CP0_Count via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Compare via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Cause via KVM_SET_ONE_REG ioctl interface Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:35 +07:00
/* Frequency of timer in Hz */
u32 count_hz;
MIPS: KVM: Rewrite count/compare timer emulation Previously the emulation of the CPU timer was just enough to get a Linux guest running but some shortcuts were taken: - The guest timer interrupt was hard coded to always happen every 10 ms rather than being timed to when CP0_Count would match CP0_Compare. - The guest's CP0_Count register was based on the host's CP0_Count register. This isn't very portable and fails on cores without a CP_Count register implemented such as Ingenic XBurst. It also meant that the guest's CP0_Cause.DC bit to disable the CP0_Count register took no effect. - The guest's CP0_Count register was emulated by just dividing the host's CP0_Count register by 4. This resulted in continuity problems when used as a clock source, since when the host CP0_Count overflows from 0x7fffffff to 0x80000000, the guest CP0_Count transitions discontinuously from 0x1fffffff to 0xe0000000. Therefore rewrite & fix emulation of the guest timer based on the monotonic kernel time (i.e. ktime_get()). Internally a 32-bit count_bias value is added to the frequency scaled nanosecond monotonic time to get the guest's CP0_Count. The frequency of the timer is initialised to 100MHz and cannot yet be changed, but a later patch will allow the frequency to be configured via the KVM_{GET,SET}_ONE_REG ioctl interface. The timer can now be stopped via the CP0_Cause.DC bit (by the guest or via the KVM_SET_ONE_REG ioctl interface), at which point the current CP0_Count is stored and can be read directly. When it is restarted the bias is recalculated such that the CP0_Count value is continuous. Due to the nature of hrtimer interrupts any read of the guest's CP0_Count register while it is running triggers a check for whether the hrtimer has expired, so that the guest/userland cannot observe the CP0_Count passing CP0_Compare without queuing a timer interrupt. This is also taken advantage of when stopping the timer to ensure that a pending timer interrupt is queued. This replaces the implementation of: - Guest read of CP0_Count - Guest write of CP0_Count - Guest write of CP0_Compare - Guest write of CP0_Cause - Guest read of HWR 2 (CC) with RDHWR - Host read of CP0_Count via KVM_GET_ONE_REG ioctl interface - Host write of CP0_Count via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Compare via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Cause via KVM_SET_ONE_REG ioctl interface Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:35 +07:00
/* Dynamic nanosecond bias (multiple of count_period) to avoid overflow */
s64 count_dyn_bias;
MIPS: KVM: Add master disable count interface Expose two new virtual registers to userland via the KVM_{GET,SET}_ONE_REG ioctls. KVM_REG_MIPS_COUNT_CTL is for timer configuration fields and just contains a master disable count bit. This can be used by userland to freeze the timer in order to read a consistent state from the timer count value and timer interrupt pending bit. This cannot be done with the CP0_Cause.DC bit because the timer interrupt pending bit (TI) is also in CP0_Cause so it would be impossible to stop the timer without also risking a race with an hrtimer interrupt and having to explicitly check whether an interrupt should have occurred. When the timer is re-enabled it resumes without losing time, i.e. the CP0_Count value jumps to what it would have been had the timer not been disabled, which would also be impossible to do from userland with CP0_Cause.DC. The timer interrupt also cannot be lost, i.e. if a timer interrupt would have occurred had the timer not been disabled it is queued when the timer is re-enabled. This works by storing the nanosecond monotonic time when the master disable is set, and using it for various operations instead of the current monotonic time (e.g. when recalculating the bias when the CP0_Count is set), until the master disable is cleared again, i.e. the timer state is read/written as it would have been at that time. This state is exposed to userland via the read-only KVM_REG_MIPS_COUNT_RESUME virtual register so that userland can determine the exact time the master disable took effect. This should allow userland to atomically save the state of the timer, and later restore it. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David Daney <david.daney@cavium.com> Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:37 +07:00
/* Resume time */
ktime_t count_resume;
MIPS: KVM: Rewrite count/compare timer emulation Previously the emulation of the CPU timer was just enough to get a Linux guest running but some shortcuts were taken: - The guest timer interrupt was hard coded to always happen every 10 ms rather than being timed to when CP0_Count would match CP0_Compare. - The guest's CP0_Count register was based on the host's CP0_Count register. This isn't very portable and fails on cores without a CP_Count register implemented such as Ingenic XBurst. It also meant that the guest's CP0_Cause.DC bit to disable the CP0_Count register took no effect. - The guest's CP0_Count register was emulated by just dividing the host's CP0_Count register by 4. This resulted in continuity problems when used as a clock source, since when the host CP0_Count overflows from 0x7fffffff to 0x80000000, the guest CP0_Count transitions discontinuously from 0x1fffffff to 0xe0000000. Therefore rewrite & fix emulation of the guest timer based on the monotonic kernel time (i.e. ktime_get()). Internally a 32-bit count_bias value is added to the frequency scaled nanosecond monotonic time to get the guest's CP0_Count. The frequency of the timer is initialised to 100MHz and cannot yet be changed, but a later patch will allow the frequency to be configured via the KVM_{GET,SET}_ONE_REG ioctl interface. The timer can now be stopped via the CP0_Cause.DC bit (by the guest or via the KVM_SET_ONE_REG ioctl interface), at which point the current CP0_Count is stored and can be read directly. When it is restarted the bias is recalculated such that the CP0_Count value is continuous. Due to the nature of hrtimer interrupts any read of the guest's CP0_Count register while it is running triggers a check for whether the hrtimer has expired, so that the guest/userland cannot observe the CP0_Count passing CP0_Compare without queuing a timer interrupt. This is also taken advantage of when stopping the timer to ensure that a pending timer interrupt is queued. This replaces the implementation of: - Guest read of CP0_Count - Guest write of CP0_Count - Guest write of CP0_Compare - Guest write of CP0_Cause - Guest read of HWR 2 (CC) with RDHWR - Host read of CP0_Count via KVM_GET_ONE_REG ioctl interface - Host write of CP0_Count via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Compare via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Cause via KVM_SET_ONE_REG ioctl interface Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:35 +07:00
/* Period of timer tick in ns */
u64 count_period;
/* Bitmask of exceptions that are pending */
unsigned long pending_exceptions;
/* Bitmask of pending exceptions to be cleared */
unsigned long pending_exceptions_clr;
/* S/W Based TLB for guest */
struct kvm_mips_tlb guest_tlb[KVM_MIPS_GUEST_TLB_SIZE];
/* Guest kernel/user [partial] mm */
struct mm_struct guest_kernel_mm, guest_user_mm;
/* Guest ASID of last user mode execution */
unsigned int last_user_gasid;
/* Cache some mmu pages needed inside spinlock regions */
struct kvm_mmu_memory_cache mmu_page_cache;
int last_sched_cpu;
/* WAIT executed */
int wait;
MIPS: KVM: Add base guest FPU support Add base code for supporting FPU in MIPS KVM guests. The FPU cannot yet be enabled in the guest, we're just laying the groundwork. Whether the guest's FPU context is loaded is stored in a bit in the fpu_inuse vcpu member. This allows the FPU to be disabled when the guest disables it, but keeping the FPU context loaded so it doesn't have to be reloaded if the guest re-enables it. An fpu_enabled vcpu member stores whether userland has enabled the FPU capability (which will be wired up in a later patch). New assembly code is added for saving and restoring the FPU context, and for saving/clearing and restoring FCSR (which can itself cause an FP exception depending on the value). The FCSR is restored before returning to the guest if the FPU is already enabled, and a die notifier is registered to catch the possible FP exception and step over the ctc1 instruction. The helper function kvm_lose_fpu() is added to save FPU context and disable the FPU, which is used when saving hardware state before a context switch or KVM exit (the vcpu_get_regs() callback). The helper function kvm_own_fpu() is added to enable the FPU and restore the FPU context if it isn't already loaded, which will be used in a later patch when the guest attempts to use the FPU for the first time and triggers a co-processor unusable exception. The helper function kvm_drop_fpu() is added to discard the FPU context and disable the FPU, which will be used in a later patch when the FPU state will become architecturally UNPREDICTABLE (change of FR mode) to force a reload of [stale] context in the new FR mode. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2014-11-18 21:09:12 +07:00
u8 fpu_enabled;
MIPS: KVM: Add base guest MSA support Add base code for supporting the MIPS SIMD Architecture (MSA) in MIPS KVM guests. MSA cannot yet be enabled in the guest, we're just laying the groundwork. As with the FPU, whether the guest's MSA context is loaded is stored in another bit in the fpu_inuse vcpu member. This allows MSA to be disabled when the guest disables it, but keeping the MSA context loaded so it doesn't have to be reloaded if the guest re-enables it. New assembly code is added for saving and restoring the MSA context, restoring only the upper half of the MSA context (for if the FPU context is already loaded) and for saving/clearing and restoring MSACSR (which can itself cause an MSA FP exception depending on the value). The MSACSR is restored before returning to the guest if MSA is already enabled, and the existing FP exception die notifier is extended to catch the possible MSA FP exception and step over the ctcmsa instruction. The helper function kvm_own_msa() is added to enable MSA and restore the MSA context if it isn't already loaded, which will be used in a later patch when the guest attempts to use MSA for the first time and triggers an MSA disabled exception. The existing FPU helpers are extended to handle MSA. kvm_lose_fpu() saves the full MSA context if it is loaded (which includes the FPU context) and both kvm_lose_fpu() and kvm_drop_fpu() disable MSA. kvm_own_fpu() also needs to lose any MSA context if FR=0, since there would be a risk of getting reserved instruction exceptions if CU1 is enabled and we later try and save the MSA context. We shouldn't usually hit this case since it will be handled when emulating CU1 changes, however there's nothing to stop the guest modifying the Status register directly via the comm page, which will cause this case to get hit. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2015-03-05 18:43:36 +07:00
u8 msa_enabled;
};
MIPS: KVM: Fix timer race modifying guest CP0_Cause The hrtimer callback for guest timer timeouts sets the guest's CP0_Cause.TI bit to indicate to the guest that a timer interrupt is pending, however there is no mutual exclusion implemented to prevent this occurring while the guest's CP0_Cause register is being read-modify-written elsewhere. When this occurs the setting of the CP0_Cause.TI bit is undone and the guest misses the timer interrupt and doesn't reprogram the CP0_Compare register for the next timeout. Currently another timer interrupt will be triggered again in another 10ms anyway due to the way timers are emulated, but after the MIPS timer emulation is fixed this would result in Linux guest time standing still and the guest scheduler not being invoked until the guest CP0_Count has looped around again, which at 100MHz takes just under 43 seconds. Currently this is the only asynchronous modification of guest registers, therefore it is fixed by adjusting the implementations of the kvm_set_c0_guest_cause(), kvm_clear_c0_guest_cause(), and kvm_change_c0_guest_cause() macros which are used for modifying the guest CP0_Cause register to use ll/sc to ensure atomic modification. This should work in both UP and SMP cases without requiring interrupts to be disabled. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:33 +07:00
static inline void _kvm_atomic_set_c0_guest_reg(unsigned long *reg,
unsigned long val)
{
unsigned long temp;
do {
__asm__ __volatile__(
" .set "MIPS_ISA_ARCH_LEVEL" \n"
MIPS: KVM: Fix timer race modifying guest CP0_Cause The hrtimer callback for guest timer timeouts sets the guest's CP0_Cause.TI bit to indicate to the guest that a timer interrupt is pending, however there is no mutual exclusion implemented to prevent this occurring while the guest's CP0_Cause register is being read-modify-written elsewhere. When this occurs the setting of the CP0_Cause.TI bit is undone and the guest misses the timer interrupt and doesn't reprogram the CP0_Compare register for the next timeout. Currently another timer interrupt will be triggered again in another 10ms anyway due to the way timers are emulated, but after the MIPS timer emulation is fixed this would result in Linux guest time standing still and the guest scheduler not being invoked until the guest CP0_Count has looped around again, which at 100MHz takes just under 43 seconds. Currently this is the only asynchronous modification of guest registers, therefore it is fixed by adjusting the implementations of the kvm_set_c0_guest_cause(), kvm_clear_c0_guest_cause(), and kvm_change_c0_guest_cause() macros which are used for modifying the guest CP0_Cause register to use ll/sc to ensure atomic modification. This should work in both UP and SMP cases without requiring interrupts to be disabled. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:33 +07:00
" " __LL "%0, %1 \n"
" or %0, %2 \n"
" " __SC "%0, %1 \n"
" .set mips0 \n"
: "=&r" (temp), "+m" (*reg)
: "r" (val));
} while (unlikely(!temp));
}
static inline void _kvm_atomic_clear_c0_guest_reg(unsigned long *reg,
unsigned long val)
{
unsigned long temp;
do {
__asm__ __volatile__(
" .set "MIPS_ISA_ARCH_LEVEL" \n"
MIPS: KVM: Fix timer race modifying guest CP0_Cause The hrtimer callback for guest timer timeouts sets the guest's CP0_Cause.TI bit to indicate to the guest that a timer interrupt is pending, however there is no mutual exclusion implemented to prevent this occurring while the guest's CP0_Cause register is being read-modify-written elsewhere. When this occurs the setting of the CP0_Cause.TI bit is undone and the guest misses the timer interrupt and doesn't reprogram the CP0_Compare register for the next timeout. Currently another timer interrupt will be triggered again in another 10ms anyway due to the way timers are emulated, but after the MIPS timer emulation is fixed this would result in Linux guest time standing still and the guest scheduler not being invoked until the guest CP0_Count has looped around again, which at 100MHz takes just under 43 seconds. Currently this is the only asynchronous modification of guest registers, therefore it is fixed by adjusting the implementations of the kvm_set_c0_guest_cause(), kvm_clear_c0_guest_cause(), and kvm_change_c0_guest_cause() macros which are used for modifying the guest CP0_Cause register to use ll/sc to ensure atomic modification. This should work in both UP and SMP cases without requiring interrupts to be disabled. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:33 +07:00
" " __LL "%0, %1 \n"
" and %0, %2 \n"
" " __SC "%0, %1 \n"
" .set mips0 \n"
: "=&r" (temp), "+m" (*reg)
: "r" (~val));
} while (unlikely(!temp));
}
static inline void _kvm_atomic_change_c0_guest_reg(unsigned long *reg,
unsigned long change,
unsigned long val)
{
unsigned long temp;
do {
__asm__ __volatile__(
" .set "MIPS_ISA_ARCH_LEVEL" \n"
MIPS: KVM: Fix timer race modifying guest CP0_Cause The hrtimer callback for guest timer timeouts sets the guest's CP0_Cause.TI bit to indicate to the guest that a timer interrupt is pending, however there is no mutual exclusion implemented to prevent this occurring while the guest's CP0_Cause register is being read-modify-written elsewhere. When this occurs the setting of the CP0_Cause.TI bit is undone and the guest misses the timer interrupt and doesn't reprogram the CP0_Compare register for the next timeout. Currently another timer interrupt will be triggered again in another 10ms anyway due to the way timers are emulated, but after the MIPS timer emulation is fixed this would result in Linux guest time standing still and the guest scheduler not being invoked until the guest CP0_Count has looped around again, which at 100MHz takes just under 43 seconds. Currently this is the only asynchronous modification of guest registers, therefore it is fixed by adjusting the implementations of the kvm_set_c0_guest_cause(), kvm_clear_c0_guest_cause(), and kvm_change_c0_guest_cause() macros which are used for modifying the guest CP0_Cause register to use ll/sc to ensure atomic modification. This should work in both UP and SMP cases without requiring interrupts to be disabled. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:33 +07:00
" " __LL "%0, %1 \n"
" and %0, %2 \n"
" or %0, %3 \n"
" " __SC "%0, %1 \n"
" .set mips0 \n"
: "=&r" (temp), "+m" (*reg)
: "r" (~change), "r" (val & change));
} while (unlikely(!temp));
}
KVM: MIPS: Abstract guest CP0 register access for VZ Abstract the MIPS KVM guest CP0 register access macros into inline functions which are generated by macros. This allows them to be generated differently for VZ, where they will usually need to access the hardware guest CP0 context rather than the saved values in RAM. Accessors for each individual register are generated using these macros: - __BUILD_KVM_*_SW() for registers which are not present in the VZ hardware guest context, so kvm_{read,write}_c0_guest_##name() will access the saved value in RAM regardless of whether VZ is enabled. - __BUILD_KVM_*_HW() for registers which are present in the VZ hardware guest context, so kvm_{read,write}_c0_guest_##name() will access the hardware register when VZ is enabled. These build the underlying accessors using further macros: - __BUILD_KVM_*_SAVED() builds e.g. kvm_{read,write}_sw_gc0_##name() functions for accessing the saved versions of the registers in RAM. This is used for implementing the common kvm_{read,write}_c0_guest_##name() accessors with T&E where registers are always stored in RAM, but are also available with VZ HW registers to allow them to be accessed while saved. - __BUILD_KVM_*_VZ() builds e.g. kvm_{read,write}_vz_gc0_##name() functions for accessing the VZ hardware guest context registers directly. This is used for implementing the common kvm_{read,write}_c0_guest_##name() accessors with VZ. - __BUILD_KVM_*_WRAP() builds wrappers with different names, which allows the common kvm_{read,write}_c0_guest_##name() functions to be implemented using the VZ accessors while still having the SAVED accessors available too. - __BUILD_KVM_SAVE_VZ() builds functions for saving and restoring VZ hardware guest context register state to RAM, improving conciseness of VZ context saving and restoring. Similar macros exist for generating modifiers (set, clear, change), either with a normal unlocked read/modify/write, or using atomic LL/SC sequences. These changes change the types of 32-bit registers to u32 instead of unsigned long, which requires some changes to printk() functions in MIPS KVM. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2017-03-14 17:15:25 +07:00
/* Guest register types, used in accessor build below */
#define __KVMT32 u32
#define __KVMTl unsigned long
MIPS: KVM: Fix timer race modifying guest CP0_Cause The hrtimer callback for guest timer timeouts sets the guest's CP0_Cause.TI bit to indicate to the guest that a timer interrupt is pending, however there is no mutual exclusion implemented to prevent this occurring while the guest's CP0_Cause register is being read-modify-written elsewhere. When this occurs the setting of the CP0_Cause.TI bit is undone and the guest misses the timer interrupt and doesn't reprogram the CP0_Compare register for the next timeout. Currently another timer interrupt will be triggered again in another 10ms anyway due to the way timers are emulated, but after the MIPS timer emulation is fixed this would result in Linux guest time standing still and the guest scheduler not being invoked until the guest CP0_Count has looped around again, which at 100MHz takes just under 43 seconds. Currently this is the only asynchronous modification of guest registers, therefore it is fixed by adjusting the implementations of the kvm_set_c0_guest_cause(), kvm_clear_c0_guest_cause(), and kvm_change_c0_guest_cause() macros which are used for modifying the guest CP0_Cause register to use ll/sc to ensure atomic modification. This should work in both UP and SMP cases without requiring interrupts to be disabled. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:33 +07:00
KVM: MIPS: Abstract guest CP0 register access for VZ Abstract the MIPS KVM guest CP0 register access macros into inline functions which are generated by macros. This allows them to be generated differently for VZ, where they will usually need to access the hardware guest CP0 context rather than the saved values in RAM. Accessors for each individual register are generated using these macros: - __BUILD_KVM_*_SW() for registers which are not present in the VZ hardware guest context, so kvm_{read,write}_c0_guest_##name() will access the saved value in RAM regardless of whether VZ is enabled. - __BUILD_KVM_*_HW() for registers which are present in the VZ hardware guest context, so kvm_{read,write}_c0_guest_##name() will access the hardware register when VZ is enabled. These build the underlying accessors using further macros: - __BUILD_KVM_*_SAVED() builds e.g. kvm_{read,write}_sw_gc0_##name() functions for accessing the saved versions of the registers in RAM. This is used for implementing the common kvm_{read,write}_c0_guest_##name() accessors with T&E where registers are always stored in RAM, but are also available with VZ HW registers to allow them to be accessed while saved. - __BUILD_KVM_*_VZ() builds e.g. kvm_{read,write}_vz_gc0_##name() functions for accessing the VZ hardware guest context registers directly. This is used for implementing the common kvm_{read,write}_c0_guest_##name() accessors with VZ. - __BUILD_KVM_*_WRAP() builds wrappers with different names, which allows the common kvm_{read,write}_c0_guest_##name() functions to be implemented using the VZ accessors while still having the SAVED accessors available too. - __BUILD_KVM_SAVE_VZ() builds functions for saving and restoring VZ hardware guest context register state to RAM, improving conciseness of VZ context saving and restoring. Similar macros exist for generating modifiers (set, clear, change), either with a normal unlocked read/modify/write, or using atomic LL/SC sequences. These changes change the types of 32-bit registers to u32 instead of unsigned long, which requires some changes to printk() functions in MIPS KVM. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2017-03-14 17:15:25 +07:00
/*
* __BUILD_KVM_$ops_SAVED(): kvm_$op_sw_gc0_$reg()
* These operate on the saved guest C0 state in RAM.
*/
/* Generate saved context simple accessors */
#define __BUILD_KVM_RW_SAVED(name, type, _reg, sel) \
static inline __KVMT##type kvm_read_sw_gc0_##name(struct mips_coproc *cop0) \
{ \
return cop0->reg[(_reg)][(sel)]; \
} \
static inline void kvm_write_sw_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
cop0->reg[(_reg)][(sel)] = val; \
}
/* Generate saved context bitwise modifiers */
#define __BUILD_KVM_SET_SAVED(name, type, _reg, sel) \
static inline void kvm_set_sw_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
cop0->reg[(_reg)][(sel)] |= val; \
} \
static inline void kvm_clear_sw_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
cop0->reg[(_reg)][(sel)] &= ~val; \
} \
static inline void kvm_change_sw_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type mask, \
__KVMT##type val) \
{ \
unsigned long _mask = mask; \
cop0->reg[(_reg)][(sel)] &= ~_mask; \
cop0->reg[(_reg)][(sel)] |= val & _mask; \
}
/* Generate saved context atomic bitwise modifiers */
#define __BUILD_KVM_ATOMIC_SAVED(name, type, _reg, sel) \
static inline void kvm_set_sw_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
_kvm_atomic_set_c0_guest_reg(&cop0->reg[(_reg)][(sel)], val); \
} \
static inline void kvm_clear_sw_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
_kvm_atomic_clear_c0_guest_reg(&cop0->reg[(_reg)][(sel)], val); \
} \
static inline void kvm_change_sw_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type mask, \
__KVMT##type val) \
{ \
KVM: MIPS: Abstract guest CP0 register access for VZ Abstract the MIPS KVM guest CP0 register access macros into inline functions which are generated by macros. This allows them to be generated differently for VZ, where they will usually need to access the hardware guest CP0 context rather than the saved values in RAM. Accessors for each individual register are generated using these macros: - __BUILD_KVM_*_SW() for registers which are not present in the VZ hardware guest context, so kvm_{read,write}_c0_guest_##name() will access the saved value in RAM regardless of whether VZ is enabled. - __BUILD_KVM_*_HW() for registers which are present in the VZ hardware guest context, so kvm_{read,write}_c0_guest_##name() will access the hardware register when VZ is enabled. These build the underlying accessors using further macros: - __BUILD_KVM_*_SAVED() builds e.g. kvm_{read,write}_sw_gc0_##name() functions for accessing the saved versions of the registers in RAM. This is used for implementing the common kvm_{read,write}_c0_guest_##name() accessors with T&E where registers are always stored in RAM, but are also available with VZ HW registers to allow them to be accessed while saved. - __BUILD_KVM_*_VZ() builds e.g. kvm_{read,write}_vz_gc0_##name() functions for accessing the VZ hardware guest context registers directly. This is used for implementing the common kvm_{read,write}_c0_guest_##name() accessors with VZ. - __BUILD_KVM_*_WRAP() builds wrappers with different names, which allows the common kvm_{read,write}_c0_guest_##name() functions to be implemented using the VZ accessors while still having the SAVED accessors available too. - __BUILD_KVM_SAVE_VZ() builds functions for saving and restoring VZ hardware guest context register state to RAM, improving conciseness of VZ context saving and restoring. Similar macros exist for generating modifiers (set, clear, change), either with a normal unlocked read/modify/write, or using atomic LL/SC sequences. These changes change the types of 32-bit registers to u32 instead of unsigned long, which requires some changes to printk() functions in MIPS KVM. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2017-03-14 17:15:25 +07:00
_kvm_atomic_change_c0_guest_reg(&cop0->reg[(_reg)][(sel)], mask, \
val); \
}
KVM: MIPS: Abstract guest CP0 register access for VZ Abstract the MIPS KVM guest CP0 register access macros into inline functions which are generated by macros. This allows them to be generated differently for VZ, where they will usually need to access the hardware guest CP0 context rather than the saved values in RAM. Accessors for each individual register are generated using these macros: - __BUILD_KVM_*_SW() for registers which are not present in the VZ hardware guest context, so kvm_{read,write}_c0_guest_##name() will access the saved value in RAM regardless of whether VZ is enabled. - __BUILD_KVM_*_HW() for registers which are present in the VZ hardware guest context, so kvm_{read,write}_c0_guest_##name() will access the hardware register when VZ is enabled. These build the underlying accessors using further macros: - __BUILD_KVM_*_SAVED() builds e.g. kvm_{read,write}_sw_gc0_##name() functions for accessing the saved versions of the registers in RAM. This is used for implementing the common kvm_{read,write}_c0_guest_##name() accessors with T&E where registers are always stored in RAM, but are also available with VZ HW registers to allow them to be accessed while saved. - __BUILD_KVM_*_VZ() builds e.g. kvm_{read,write}_vz_gc0_##name() functions for accessing the VZ hardware guest context registers directly. This is used for implementing the common kvm_{read,write}_c0_guest_##name() accessors with VZ. - __BUILD_KVM_*_WRAP() builds wrappers with different names, which allows the common kvm_{read,write}_c0_guest_##name() functions to be implemented using the VZ accessors while still having the SAVED accessors available too. - __BUILD_KVM_SAVE_VZ() builds functions for saving and restoring VZ hardware guest context register state to RAM, improving conciseness of VZ context saving and restoring. Similar macros exist for generating modifiers (set, clear, change), either with a normal unlocked read/modify/write, or using atomic LL/SC sequences. These changes change the types of 32-bit registers to u32 instead of unsigned long, which requires some changes to printk() functions in MIPS KVM. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2017-03-14 17:15:25 +07:00
/*
* __BUILD_KVM_$ops_VZ(): kvm_$op_vz_gc0_$reg()
* These operate on the VZ guest C0 context in hardware.
*/
/* Generate VZ guest context simple accessors */
#define __BUILD_KVM_RW_VZ(name, type, _reg, sel) \
static inline __KVMT##type kvm_read_vz_gc0_##name(struct mips_coproc *cop0) \
{ \
return read_gc0_##name(); \
} \
static inline void kvm_write_vz_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
write_gc0_##name(val); \
}
/* Generate VZ guest context bitwise modifiers */
#define __BUILD_KVM_SET_VZ(name, type, _reg, sel) \
static inline void kvm_set_vz_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
set_gc0_##name(val); \
} \
static inline void kvm_clear_vz_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
clear_gc0_##name(val); \
} \
static inline void kvm_change_vz_gc0_##name(struct mips_coproc *cop0, \
__KVMT##type mask, \
__KVMT##type val) \
{ \
change_gc0_##name(mask, val); \
}
/* Generate VZ guest context save/restore to/from saved context */
#define __BUILD_KVM_SAVE_VZ(name, _reg, sel) \
static inline void kvm_restore_gc0_##name(struct mips_coproc *cop0) \
{ \
write_gc0_##name(cop0->reg[(_reg)][(sel)]); \
} \
static inline void kvm_save_gc0_##name(struct mips_coproc *cop0) \
{ \
cop0->reg[(_reg)][(sel)] = read_gc0_##name(); \
}
/*
* __BUILD_KVM_$ops_WRAP(): kvm_$op_$name1() -> kvm_$op_$name2()
* These wrap a set of operations to provide them with a different name.
*/
/* Generate simple accessor wrapper */
#define __BUILD_KVM_RW_WRAP(name1, name2, type) \
static inline __KVMT##type kvm_read_##name1(struct mips_coproc *cop0) \
{ \
return kvm_read_##name2(cop0); \
} \
static inline void kvm_write_##name1(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
kvm_write_##name2(cop0, val); \
}
/* Generate bitwise modifier wrapper */
#define __BUILD_KVM_SET_WRAP(name1, name2, type) \
static inline void kvm_set_##name1(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
kvm_set_##name2(cop0, val); \
} \
static inline void kvm_clear_##name1(struct mips_coproc *cop0, \
__KVMT##type val) \
{ \
kvm_clear_##name2(cop0, val); \
} \
static inline void kvm_change_##name1(struct mips_coproc *cop0, \
__KVMT##type mask, \
__KVMT##type val) \
{ \
kvm_change_##name2(cop0, mask, val); \
}
/*
* __BUILD_KVM_$ops_SW(): kvm_$op_c0_guest_$reg() -> kvm_$op_sw_gc0_$reg()
* These generate accessors operating on the saved context in RAM, and wrap them
* with the common guest C0 accessors (for use by common emulation code).
*/
#define __BUILD_KVM_RW_SW(name, type, _reg, sel) \
__BUILD_KVM_RW_SAVED(name, type, _reg, sel) \
__BUILD_KVM_RW_WRAP(c0_guest_##name, sw_gc0_##name, type)
#define __BUILD_KVM_SET_SW(name, type, _reg, sel) \
__BUILD_KVM_SET_SAVED(name, type, _reg, sel) \
__BUILD_KVM_SET_WRAP(c0_guest_##name, sw_gc0_##name, type)
#define __BUILD_KVM_ATOMIC_SW(name, type, _reg, sel) \
__BUILD_KVM_ATOMIC_SAVED(name, type, _reg, sel) \
__BUILD_KVM_SET_WRAP(c0_guest_##name, sw_gc0_##name, type)
#ifndef CONFIG_KVM_MIPS_VZ
/*
* T&E (trap & emulate software based virtualisation)
* We generate the common accessors operating exclusively on the saved context
* in RAM.
*/
#define __BUILD_KVM_RW_HW __BUILD_KVM_RW_SW
#define __BUILD_KVM_SET_HW __BUILD_KVM_SET_SW
#define __BUILD_KVM_ATOMIC_HW __BUILD_KVM_ATOMIC_SW
#else
/*
* VZ (hardware assisted virtualisation)
* These macros use the active guest state in VZ mode (hardware registers),
*/
/*
* __BUILD_KVM_$ops_HW(): kvm_$op_c0_guest_$reg() -> kvm_$op_vz_gc0_$reg()
* These generate accessors operating on the VZ guest context in hardware, and
* wrap them with the common guest C0 accessors (for use by common emulation
* code).
*
* Accessors operating on the saved context in RAM are also generated to allow
* convenient explicit saving and restoring of the state.
*/
#define __BUILD_KVM_RW_HW(name, type, _reg, sel) \
__BUILD_KVM_RW_SAVED(name, type, _reg, sel) \
__BUILD_KVM_RW_VZ(name, type, _reg, sel) \
__BUILD_KVM_RW_WRAP(c0_guest_##name, vz_gc0_##name, type) \
__BUILD_KVM_SAVE_VZ(name, _reg, sel)
#define __BUILD_KVM_SET_HW(name, type, _reg, sel) \
__BUILD_KVM_SET_SAVED(name, type, _reg, sel) \
__BUILD_KVM_SET_VZ(name, type, _reg, sel) \
__BUILD_KVM_SET_WRAP(c0_guest_##name, vz_gc0_##name, type)
/*
* We can't do atomic modifications of COP0 state if hardware can modify it.
* Races must be handled explicitly.
*/
#define __BUILD_KVM_ATOMIC_HW __BUILD_KVM_SET_HW
#endif
/*
* Define accessors for CP0 registers that are accessible to the guest. These
* are primarily used by common emulation code, which may need to access the
* registers differently depending on the implementation.
*
* fns_hw/sw name type reg num select
*/
__BUILD_KVM_RW_HW(index, 32, MIPS_CP0_TLB_INDEX, 0)
__BUILD_KVM_RW_HW(entrylo0, l, MIPS_CP0_TLB_LO0, 0)
__BUILD_KVM_RW_HW(entrylo1, l, MIPS_CP0_TLB_LO1, 0)
__BUILD_KVM_RW_HW(context, l, MIPS_CP0_TLB_CONTEXT, 0)
__BUILD_KVM_RW_HW(userlocal, l, MIPS_CP0_TLB_CONTEXT, 2)
__BUILD_KVM_RW_HW(pagemask, l, MIPS_CP0_TLB_PG_MASK, 0)
__BUILD_KVM_RW_HW(pagegrain, 32, MIPS_CP0_TLB_PG_MASK, 1)
__BUILD_KVM_RW_HW(wired, 32, MIPS_CP0_TLB_WIRED, 0)
__BUILD_KVM_RW_HW(hwrena, 32, MIPS_CP0_HWRENA, 0)
__BUILD_KVM_RW_HW(badvaddr, l, MIPS_CP0_BAD_VADDR, 0)
__BUILD_KVM_RW_SW(count, 32, MIPS_CP0_COUNT, 0)
__BUILD_KVM_RW_HW(entryhi, l, MIPS_CP0_TLB_HI, 0)
__BUILD_KVM_RW_HW(compare, 32, MIPS_CP0_COMPARE, 0)
__BUILD_KVM_RW_HW(status, 32, MIPS_CP0_STATUS, 0)
__BUILD_KVM_RW_HW(intctl, 32, MIPS_CP0_STATUS, 1)
__BUILD_KVM_RW_HW(cause, 32, MIPS_CP0_CAUSE, 0)
__BUILD_KVM_RW_HW(epc, l, MIPS_CP0_EXC_PC, 0)
__BUILD_KVM_RW_SW(prid, 32, MIPS_CP0_PRID, 0)
__BUILD_KVM_RW_HW(ebase, l, MIPS_CP0_PRID, 1)
__BUILD_KVM_RW_HW(config, 32, MIPS_CP0_CONFIG, 0)
__BUILD_KVM_RW_HW(config1, 32, MIPS_CP0_CONFIG, 1)
__BUILD_KVM_RW_HW(config2, 32, MIPS_CP0_CONFIG, 2)
__BUILD_KVM_RW_HW(config3, 32, MIPS_CP0_CONFIG, 3)
__BUILD_KVM_RW_HW(config4, 32, MIPS_CP0_CONFIG, 4)
__BUILD_KVM_RW_HW(config5, 32, MIPS_CP0_CONFIG, 5)
__BUILD_KVM_RW_HW(config6, 32, MIPS_CP0_CONFIG, 6)
__BUILD_KVM_RW_HW(config7, 32, MIPS_CP0_CONFIG, 7)
__BUILD_KVM_RW_HW(errorepc, l, MIPS_CP0_ERROR_PC, 0)
__BUILD_KVM_RW_HW(kscratch1, l, MIPS_CP0_DESAVE, 2)
__BUILD_KVM_RW_HW(kscratch2, l, MIPS_CP0_DESAVE, 3)
__BUILD_KVM_RW_HW(kscratch3, l, MIPS_CP0_DESAVE, 4)
__BUILD_KVM_RW_HW(kscratch4, l, MIPS_CP0_DESAVE, 5)
__BUILD_KVM_RW_HW(kscratch5, l, MIPS_CP0_DESAVE, 6)
__BUILD_KVM_RW_HW(kscratch6, l, MIPS_CP0_DESAVE, 7)
/* Bitwise operations (on HW state) */
__BUILD_KVM_SET_HW(status, 32, MIPS_CP0_STATUS, 0)
/* Cause can be modified asynchronously from hardirq hrtimer callback */
__BUILD_KVM_ATOMIC_HW(cause, 32, MIPS_CP0_CAUSE, 0)
__BUILD_KVM_SET_HW(ebase, l, MIPS_CP0_PRID, 1)
MIPS: KVM: Add base guest FPU support Add base code for supporting FPU in MIPS KVM guests. The FPU cannot yet be enabled in the guest, we're just laying the groundwork. Whether the guest's FPU context is loaded is stored in a bit in the fpu_inuse vcpu member. This allows the FPU to be disabled when the guest disables it, but keeping the FPU context loaded so it doesn't have to be reloaded if the guest re-enables it. An fpu_enabled vcpu member stores whether userland has enabled the FPU capability (which will be wired up in a later patch). New assembly code is added for saving and restoring the FPU context, and for saving/clearing and restoring FCSR (which can itself cause an FP exception depending on the value). The FCSR is restored before returning to the guest if the FPU is already enabled, and a die notifier is registered to catch the possible FP exception and step over the ctc1 instruction. The helper function kvm_lose_fpu() is added to save FPU context and disable the FPU, which is used when saving hardware state before a context switch or KVM exit (the vcpu_get_regs() callback). The helper function kvm_own_fpu() is added to enable the FPU and restore the FPU context if it isn't already loaded, which will be used in a later patch when the guest attempts to use the FPU for the first time and triggers a co-processor unusable exception. The helper function kvm_drop_fpu() is added to discard the FPU context and disable the FPU, which will be used in a later patch when the FPU state will become architecturally UNPREDICTABLE (change of FR mode) to force a reload of [stale] context in the new FR mode. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2014-11-18 21:09:12 +07:00
/* Helpers */
static inline bool kvm_mips_guest_can_have_fpu(struct kvm_vcpu_arch *vcpu)
{
return (!__builtin_constant_p(raw_cpu_has_fpu) || raw_cpu_has_fpu) &&
MIPS: KVM: Add base guest FPU support Add base code for supporting FPU in MIPS KVM guests. The FPU cannot yet be enabled in the guest, we're just laying the groundwork. Whether the guest's FPU context is loaded is stored in a bit in the fpu_inuse vcpu member. This allows the FPU to be disabled when the guest disables it, but keeping the FPU context loaded so it doesn't have to be reloaded if the guest re-enables it. An fpu_enabled vcpu member stores whether userland has enabled the FPU capability (which will be wired up in a later patch). New assembly code is added for saving and restoring the FPU context, and for saving/clearing and restoring FCSR (which can itself cause an FP exception depending on the value). The FCSR is restored before returning to the guest if the FPU is already enabled, and a die notifier is registered to catch the possible FP exception and step over the ctc1 instruction. The helper function kvm_lose_fpu() is added to save FPU context and disable the FPU, which is used when saving hardware state before a context switch or KVM exit (the vcpu_get_regs() callback). The helper function kvm_own_fpu() is added to enable the FPU and restore the FPU context if it isn't already loaded, which will be used in a later patch when the guest attempts to use the FPU for the first time and triggers a co-processor unusable exception. The helper function kvm_drop_fpu() is added to discard the FPU context and disable the FPU, which will be used in a later patch when the FPU state will become architecturally UNPREDICTABLE (change of FR mode) to force a reload of [stale] context in the new FR mode. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2014-11-18 21:09:12 +07:00
vcpu->fpu_enabled;
}
static inline bool kvm_mips_guest_has_fpu(struct kvm_vcpu_arch *vcpu)
{
return kvm_mips_guest_can_have_fpu(vcpu) &&
kvm_read_c0_guest_config1(vcpu->cop0) & MIPS_CONF1_FP;
}
MIPS: KVM: Add base guest MSA support Add base code for supporting the MIPS SIMD Architecture (MSA) in MIPS KVM guests. MSA cannot yet be enabled in the guest, we're just laying the groundwork. As with the FPU, whether the guest's MSA context is loaded is stored in another bit in the fpu_inuse vcpu member. This allows MSA to be disabled when the guest disables it, but keeping the MSA context loaded so it doesn't have to be reloaded if the guest re-enables it. New assembly code is added for saving and restoring the MSA context, restoring only the upper half of the MSA context (for if the FPU context is already loaded) and for saving/clearing and restoring MSACSR (which can itself cause an MSA FP exception depending on the value). The MSACSR is restored before returning to the guest if MSA is already enabled, and the existing FP exception die notifier is extended to catch the possible MSA FP exception and step over the ctcmsa instruction. The helper function kvm_own_msa() is added to enable MSA and restore the MSA context if it isn't already loaded, which will be used in a later patch when the guest attempts to use MSA for the first time and triggers an MSA disabled exception. The existing FPU helpers are extended to handle MSA. kvm_lose_fpu() saves the full MSA context if it is loaded (which includes the FPU context) and both kvm_lose_fpu() and kvm_drop_fpu() disable MSA. kvm_own_fpu() also needs to lose any MSA context if FR=0, since there would be a risk of getting reserved instruction exceptions if CU1 is enabled and we later try and save the MSA context. We shouldn't usually hit this case since it will be handled when emulating CU1 changes, however there's nothing to stop the guest modifying the Status register directly via the comm page, which will cause this case to get hit. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2015-03-05 18:43:36 +07:00
static inline bool kvm_mips_guest_can_have_msa(struct kvm_vcpu_arch *vcpu)
{
return (!__builtin_constant_p(cpu_has_msa) || cpu_has_msa) &&
vcpu->msa_enabled;
}
static inline bool kvm_mips_guest_has_msa(struct kvm_vcpu_arch *vcpu)
{
return kvm_mips_guest_can_have_msa(vcpu) &&
kvm_read_c0_guest_config3(vcpu->cop0) & MIPS_CONF3_MSA;
}
struct kvm_mips_callbacks {
int (*handle_cop_unusable)(struct kvm_vcpu *vcpu);
int (*handle_tlb_mod)(struct kvm_vcpu *vcpu);
int (*handle_tlb_ld_miss)(struct kvm_vcpu *vcpu);
int (*handle_tlb_st_miss)(struct kvm_vcpu *vcpu);
int (*handle_addr_err_st)(struct kvm_vcpu *vcpu);
int (*handle_addr_err_ld)(struct kvm_vcpu *vcpu);
int (*handle_syscall)(struct kvm_vcpu *vcpu);
int (*handle_res_inst)(struct kvm_vcpu *vcpu);
int (*handle_break)(struct kvm_vcpu *vcpu);
int (*handle_trap)(struct kvm_vcpu *vcpu);
int (*handle_msa_fpe)(struct kvm_vcpu *vcpu);
int (*handle_fpe)(struct kvm_vcpu *vcpu);
int (*handle_msa_disabled)(struct kvm_vcpu *vcpu);
int (*handle_guest_exit)(struct kvm_vcpu *vcpu);
int (*hardware_enable)(void);
void (*hardware_disable)(void);
int (*check_extension)(struct kvm *kvm, long ext);
int (*vcpu_init)(struct kvm_vcpu *vcpu);
void (*vcpu_uninit)(struct kvm_vcpu *vcpu);
int (*vcpu_setup)(struct kvm_vcpu *vcpu);
void (*flush_shadow_all)(struct kvm *kvm);
/*
* Must take care of flushing any cached GPA PTEs (e.g. guest entries in
* VZ root TLB, or T&E GVA page tables and corresponding root TLB
* mappings).
*/
void (*flush_shadow_memslot)(struct kvm *kvm,
const struct kvm_memory_slot *slot);
gpa_t (*gva_to_gpa)(gva_t gva);
void (*queue_timer_int)(struct kvm_vcpu *vcpu);
void (*dequeue_timer_int)(struct kvm_vcpu *vcpu);
void (*queue_io_int)(struct kvm_vcpu *vcpu,
struct kvm_mips_interrupt *irq);
void (*dequeue_io_int)(struct kvm_vcpu *vcpu,
struct kvm_mips_interrupt *irq);
int (*irq_deliver)(struct kvm_vcpu *vcpu, unsigned int priority,
u32 cause);
int (*irq_clear)(struct kvm_vcpu *vcpu, unsigned int priority,
u32 cause);
unsigned long (*num_regs)(struct kvm_vcpu *vcpu);
int (*copy_reg_indices)(struct kvm_vcpu *vcpu, u64 __user *indices);
int (*get_one_reg)(struct kvm_vcpu *vcpu,
const struct kvm_one_reg *reg, s64 *v);
int (*set_one_reg)(struct kvm_vcpu *vcpu,
const struct kvm_one_reg *reg, s64 v);
int (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
int (*vcpu_put)(struct kvm_vcpu *vcpu, int cpu);
int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
void (*vcpu_reenter)(struct kvm_run *run, struct kvm_vcpu *vcpu);
};
extern struct kvm_mips_callbacks *kvm_mips_callbacks;
int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks);
/* Debug: dump vcpu state */
int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
extern int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu);
/* Building of entry/exception code */
int kvm_mips_entry_setup(void);
void *kvm_mips_build_vcpu_run(void *addr);
void *kvm_mips_build_tlb_refill_exception(void *addr, void *handler);
void *kvm_mips_build_exception(void *addr, void *handler);
void *kvm_mips_build_exit(void *addr);
MIPS: KVM: Add base guest MSA support Add base code for supporting the MIPS SIMD Architecture (MSA) in MIPS KVM guests. MSA cannot yet be enabled in the guest, we're just laying the groundwork. As with the FPU, whether the guest's MSA context is loaded is stored in another bit in the fpu_inuse vcpu member. This allows MSA to be disabled when the guest disables it, but keeping the MSA context loaded so it doesn't have to be reloaded if the guest re-enables it. New assembly code is added for saving and restoring the MSA context, restoring only the upper half of the MSA context (for if the FPU context is already loaded) and for saving/clearing and restoring MSACSR (which can itself cause an MSA FP exception depending on the value). The MSACSR is restored before returning to the guest if MSA is already enabled, and the existing FP exception die notifier is extended to catch the possible MSA FP exception and step over the ctcmsa instruction. The helper function kvm_own_msa() is added to enable MSA and restore the MSA context if it isn't already loaded, which will be used in a later patch when the guest attempts to use MSA for the first time and triggers an MSA disabled exception. The existing FPU helpers are extended to handle MSA. kvm_lose_fpu() saves the full MSA context if it is loaded (which includes the FPU context) and both kvm_lose_fpu() and kvm_drop_fpu() disable MSA. kvm_own_fpu() also needs to lose any MSA context if FR=0, since there would be a risk of getting reserved instruction exceptions if CU1 is enabled and we later try and save the MSA context. We shouldn't usually hit this case since it will be handled when emulating CU1 changes, however there's nothing to stop the guest modifying the Status register directly via the comm page, which will cause this case to get hit. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2015-03-05 18:43:36 +07:00
/* FPU/MSA context management */
MIPS: KVM: Add base guest FPU support Add base code for supporting FPU in MIPS KVM guests. The FPU cannot yet be enabled in the guest, we're just laying the groundwork. Whether the guest's FPU context is loaded is stored in a bit in the fpu_inuse vcpu member. This allows the FPU to be disabled when the guest disables it, but keeping the FPU context loaded so it doesn't have to be reloaded if the guest re-enables it. An fpu_enabled vcpu member stores whether userland has enabled the FPU capability (which will be wired up in a later patch). New assembly code is added for saving and restoring the FPU context, and for saving/clearing and restoring FCSR (which can itself cause an FP exception depending on the value). The FCSR is restored before returning to the guest if the FPU is already enabled, and a die notifier is registered to catch the possible FP exception and step over the ctc1 instruction. The helper function kvm_lose_fpu() is added to save FPU context and disable the FPU, which is used when saving hardware state before a context switch or KVM exit (the vcpu_get_regs() callback). The helper function kvm_own_fpu() is added to enable the FPU and restore the FPU context if it isn't already loaded, which will be used in a later patch when the guest attempts to use the FPU for the first time and triggers a co-processor unusable exception. The helper function kvm_drop_fpu() is added to discard the FPU context and disable the FPU, which will be used in a later patch when the FPU state will become architecturally UNPREDICTABLE (change of FR mode) to force a reload of [stale] context in the new FR mode. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2014-11-18 21:09:12 +07:00
void __kvm_save_fpu(struct kvm_vcpu_arch *vcpu);
void __kvm_restore_fpu(struct kvm_vcpu_arch *vcpu);
void __kvm_restore_fcsr(struct kvm_vcpu_arch *vcpu);
MIPS: KVM: Add base guest MSA support Add base code for supporting the MIPS SIMD Architecture (MSA) in MIPS KVM guests. MSA cannot yet be enabled in the guest, we're just laying the groundwork. As with the FPU, whether the guest's MSA context is loaded is stored in another bit in the fpu_inuse vcpu member. This allows MSA to be disabled when the guest disables it, but keeping the MSA context loaded so it doesn't have to be reloaded if the guest re-enables it. New assembly code is added for saving and restoring the MSA context, restoring only the upper half of the MSA context (for if the FPU context is already loaded) and for saving/clearing and restoring MSACSR (which can itself cause an MSA FP exception depending on the value). The MSACSR is restored before returning to the guest if MSA is already enabled, and the existing FP exception die notifier is extended to catch the possible MSA FP exception and step over the ctcmsa instruction. The helper function kvm_own_msa() is added to enable MSA and restore the MSA context if it isn't already loaded, which will be used in a later patch when the guest attempts to use MSA for the first time and triggers an MSA disabled exception. The existing FPU helpers are extended to handle MSA. kvm_lose_fpu() saves the full MSA context if it is loaded (which includes the FPU context) and both kvm_lose_fpu() and kvm_drop_fpu() disable MSA. kvm_own_fpu() also needs to lose any MSA context if FR=0, since there would be a risk of getting reserved instruction exceptions if CU1 is enabled and we later try and save the MSA context. We shouldn't usually hit this case since it will be handled when emulating CU1 changes, however there's nothing to stop the guest modifying the Status register directly via the comm page, which will cause this case to get hit. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2015-03-05 18:43:36 +07:00
void __kvm_save_msa(struct kvm_vcpu_arch *vcpu);
void __kvm_restore_msa(struct kvm_vcpu_arch *vcpu);
void __kvm_restore_msa_upper(struct kvm_vcpu_arch *vcpu);
void __kvm_restore_msacsr(struct kvm_vcpu_arch *vcpu);
MIPS: KVM: Add base guest FPU support Add base code for supporting FPU in MIPS KVM guests. The FPU cannot yet be enabled in the guest, we're just laying the groundwork. Whether the guest's FPU context is loaded is stored in a bit in the fpu_inuse vcpu member. This allows the FPU to be disabled when the guest disables it, but keeping the FPU context loaded so it doesn't have to be reloaded if the guest re-enables it. An fpu_enabled vcpu member stores whether userland has enabled the FPU capability (which will be wired up in a later patch). New assembly code is added for saving and restoring the FPU context, and for saving/clearing and restoring FCSR (which can itself cause an FP exception depending on the value). The FCSR is restored before returning to the guest if the FPU is already enabled, and a die notifier is registered to catch the possible FP exception and step over the ctc1 instruction. The helper function kvm_lose_fpu() is added to save FPU context and disable the FPU, which is used when saving hardware state before a context switch or KVM exit (the vcpu_get_regs() callback). The helper function kvm_own_fpu() is added to enable the FPU and restore the FPU context if it isn't already loaded, which will be used in a later patch when the guest attempts to use the FPU for the first time and triggers a co-processor unusable exception. The helper function kvm_drop_fpu() is added to discard the FPU context and disable the FPU, which will be used in a later patch when the FPU state will become architecturally UNPREDICTABLE (change of FR mode) to force a reload of [stale] context in the new FR mode. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2014-11-18 21:09:12 +07:00
void kvm_own_fpu(struct kvm_vcpu *vcpu);
MIPS: KVM: Add base guest MSA support Add base code for supporting the MIPS SIMD Architecture (MSA) in MIPS KVM guests. MSA cannot yet be enabled in the guest, we're just laying the groundwork. As with the FPU, whether the guest's MSA context is loaded is stored in another bit in the fpu_inuse vcpu member. This allows MSA to be disabled when the guest disables it, but keeping the MSA context loaded so it doesn't have to be reloaded if the guest re-enables it. New assembly code is added for saving and restoring the MSA context, restoring only the upper half of the MSA context (for if the FPU context is already loaded) and for saving/clearing and restoring MSACSR (which can itself cause an MSA FP exception depending on the value). The MSACSR is restored before returning to the guest if MSA is already enabled, and the existing FP exception die notifier is extended to catch the possible MSA FP exception and step over the ctcmsa instruction. The helper function kvm_own_msa() is added to enable MSA and restore the MSA context if it isn't already loaded, which will be used in a later patch when the guest attempts to use MSA for the first time and triggers an MSA disabled exception. The existing FPU helpers are extended to handle MSA. kvm_lose_fpu() saves the full MSA context if it is loaded (which includes the FPU context) and both kvm_lose_fpu() and kvm_drop_fpu() disable MSA. kvm_own_fpu() also needs to lose any MSA context if FR=0, since there would be a risk of getting reserved instruction exceptions if CU1 is enabled and we later try and save the MSA context. We shouldn't usually hit this case since it will be handled when emulating CU1 changes, however there's nothing to stop the guest modifying the Status register directly via the comm page, which will cause this case to get hit. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2015-03-05 18:43:36 +07:00
void kvm_own_msa(struct kvm_vcpu *vcpu);
MIPS: KVM: Add base guest FPU support Add base code for supporting FPU in MIPS KVM guests. The FPU cannot yet be enabled in the guest, we're just laying the groundwork. Whether the guest's FPU context is loaded is stored in a bit in the fpu_inuse vcpu member. This allows the FPU to be disabled when the guest disables it, but keeping the FPU context loaded so it doesn't have to be reloaded if the guest re-enables it. An fpu_enabled vcpu member stores whether userland has enabled the FPU capability (which will be wired up in a later patch). New assembly code is added for saving and restoring the FPU context, and for saving/clearing and restoring FCSR (which can itself cause an FP exception depending on the value). The FCSR is restored before returning to the guest if the FPU is already enabled, and a die notifier is registered to catch the possible FP exception and step over the ctc1 instruction. The helper function kvm_lose_fpu() is added to save FPU context and disable the FPU, which is used when saving hardware state before a context switch or KVM exit (the vcpu_get_regs() callback). The helper function kvm_own_fpu() is added to enable the FPU and restore the FPU context if it isn't already loaded, which will be used in a later patch when the guest attempts to use the FPU for the first time and triggers a co-processor unusable exception. The helper function kvm_drop_fpu() is added to discard the FPU context and disable the FPU, which will be used in a later patch when the FPU state will become architecturally UNPREDICTABLE (change of FR mode) to force a reload of [stale] context in the new FR mode. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2014-11-18 21:09:12 +07:00
void kvm_drop_fpu(struct kvm_vcpu *vcpu);
void kvm_lose_fpu(struct kvm_vcpu *vcpu);
/* TLB handling */
u32 kvm_get_kernel_asid(struct kvm_vcpu *vcpu);
u32 kvm_get_user_asid(struct kvm_vcpu *vcpu);
u32 kvm_get_commpage_asid (struct kvm_vcpu *vcpu);
extern int kvm_mips_handle_kseg0_tlb_fault(unsigned long badbaddr,
struct kvm_vcpu *vcpu,
bool write_fault);
extern int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr,
struct kvm_vcpu *vcpu);
extern int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
struct kvm_mips_tlb *tlb,
unsigned long gva,
bool write_fault);
extern enum emulation_result kvm_mips_handle_tlbmiss(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu,
bool write_fault);
extern void kvm_mips_dump_host_tlbs(void);
extern void kvm_mips_dump_guest_tlbs(struct kvm_vcpu *vcpu);
extern int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long entryhi,
bool user, bool kernel);
extern int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu,
unsigned long entryhi);
void kvm_mips_suspend_mm(int cpu);
void kvm_mips_resume_mm(int cpu);
/* MMU handling */
/**
* enum kvm_mips_flush - Types of MMU flushes.
* @KMF_USER: Flush guest user virtual memory mappings.
* Guest USeg only.
* @KMF_KERN: Flush guest kernel virtual memory mappings.
* Guest USeg and KSeg2/3.
* @KMF_GPA: Flush guest physical memory mappings.
* Also includes KSeg0 if KMF_KERN is set.
*/
enum kvm_mips_flush {
KMF_USER = 0x0,
KMF_KERN = 0x1,
KMF_GPA = 0x2,
};
void kvm_mips_flush_gva_pt(pgd_t *pgd, enum kvm_mips_flush flags);
bool kvm_mips_flush_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn);
int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn);
pgd_t *kvm_pgd_alloc(void);
void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
void kvm_trap_emul_invalidate_gva(struct kvm_vcpu *vcpu, unsigned long addr,
bool user);
void kvm_trap_emul_gva_lockless_begin(struct kvm_vcpu *vcpu);
void kvm_trap_emul_gva_lockless_end(struct kvm_vcpu *vcpu);
enum kvm_mips_fault_result {
KVM_MIPS_MAPPED = 0,
KVM_MIPS_GVA,
KVM_MIPS_GPA,
KVM_MIPS_TLB,
KVM_MIPS_TLBINV,
KVM_MIPS_TLBMOD,
};
enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu,
unsigned long gva,
bool write);
KVM: MIPS/MMU: Implement KVM_CAP_SYNC_MMU Implement the SYNC_MMU capability for KVM MIPS, allowing changes in the underlying user host virtual address (HVA) mappings to be promptly reflected in the corresponding guest physical address (GPA) mappings. This allows for several features to work with guest RAM which require mappings to be altered or protected, such as copy-on-write, KSM (Kernel Samepage Merging), idle page tracking, memory swapping, and guest memory ballooning. There are two main aspects of this change, described below. The KVM MMU notifier architecture callbacks are implemented so we can be notified of changes in the HVA mappings. These arrange for the guest physical address (GPA) page tables to be modified and possibly for derived mappings (GVA page tables and TLBs) to be flushed. - kvm_unmap_hva[_range]() - These deal with HVA mappings being removed, for example before a copy-on-write takes place, which requires the corresponding GPA page table mappings to be removed too. - kvm_set_spte_hva() - These update a GPA page table entry to match the new HVA entry, but must be careful to respect KVM specific configuration such as not dirtying a clean guest page which is dirty to the host, and write protecting writable pages in read only memslots (which will soon be supported). - kvm[_test]_age_hva() - These update GPA page table entries to be old (invalid) so that access can be tracked, making them young again. The GPA page fault handling (kvm_mips_map_page) is updated to use gfn_to_pfn_prot() (which may provide read-only pages), to handle asynchronous page table invalidation from MMU notifier callbacks, and to handle more cases in the fast path. - mmu_notifier_seq is used to detect asynchronous page table invalidations while we're holding a pfn from gfn_to_pfn_prot() outside of kvm->mmu_lock, retrying if invalidations have taken place, e.g. a COW or a KSM page merge. - The fast path (_kvm_mips_map_page_fast) now handles marking old pages as young / accessed, and disallowing dirtying of clean pages that aren't actually writable (e.g. shared pages that should COW, and read-only memory regions when they are enabled in a future patch). - Due to the use of MMU notifications we no longer need to keep the page references after we've updated the GPA page tables. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
2016-12-13 23:32:39 +07:00
#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_unmap_hva_range(struct kvm *kvm,
unsigned long start, unsigned long end);
void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
unsigned long address)
{
}
/* Emulation */
int kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu, u32 *out);
enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause);
int kvm_get_badinstr(u32 *opc, struct kvm_vcpu *vcpu, u32 *out);
int kvm_get_badinstrp(u32 *opc, struct kvm_vcpu *vcpu, u32 *out);
/**
* kvm_is_ifetch_fault() - Find whether a TLBL exception is due to ifetch fault.
* @vcpu: Virtual CPU.
*
* Returns: Whether the TLBL exception was likely due to an instruction
* fetch fault rather than a data load fault.
*/
static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *vcpu)
{
unsigned long badvaddr = vcpu->host_cp0_badvaddr;
unsigned long epc = msk_isa16_mode(vcpu->pc);
u32 cause = vcpu->host_cp0_cause;
if (epc == badvaddr)
return true;
/*
* Branches may be 32-bit or 16-bit instructions.
* This isn't exact, but we don't really support MIPS16 or microMIPS yet
* in KVM anyway.
*/
if ((cause & CAUSEF_BD) && badvaddr - epc <= 4)
return true;
return false;
}
extern enum emulation_result kvm_mips_emulate_inst(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
long kvm_mips_guest_exception_base(struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_syscall(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_tlbmiss_ld(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_tlbinv_ld(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_tlbmiss_st(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_tlbinv_st(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_tlbmod(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_fpu_exc(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_handle_ri(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_ri_exc(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_bp_exc(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_trap_exc(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_msafpe_exc(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_fpe_exc(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_emulate_msadis_exc(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
struct kvm_run *run);
u32 kvm_mips_read_count(struct kvm_vcpu *vcpu);
void kvm_mips_write_count(struct kvm_vcpu *vcpu, u32 count);
void kvm_mips_write_compare(struct kvm_vcpu *vcpu, u32 compare, bool ack);
void kvm_mips_init_count(struct kvm_vcpu *vcpu, unsigned long count_hz);
MIPS: KVM: Add master disable count interface Expose two new virtual registers to userland via the KVM_{GET,SET}_ONE_REG ioctls. KVM_REG_MIPS_COUNT_CTL is for timer configuration fields and just contains a master disable count bit. This can be used by userland to freeze the timer in order to read a consistent state from the timer count value and timer interrupt pending bit. This cannot be done with the CP0_Cause.DC bit because the timer interrupt pending bit (TI) is also in CP0_Cause so it would be impossible to stop the timer without also risking a race with an hrtimer interrupt and having to explicitly check whether an interrupt should have occurred. When the timer is re-enabled it resumes without losing time, i.e. the CP0_Count value jumps to what it would have been had the timer not been disabled, which would also be impossible to do from userland with CP0_Cause.DC. The timer interrupt also cannot be lost, i.e. if a timer interrupt would have occurred had the timer not been disabled it is queued when the timer is re-enabled. This works by storing the nanosecond monotonic time when the master disable is set, and using it for various operations instead of the current monotonic time (e.g. when recalculating the bias when the CP0_Count is set), until the master disable is cleared again, i.e. the timer state is read/written as it would have been at that time. This state is exposed to userland via the read-only KVM_REG_MIPS_COUNT_RESUME virtual register so that userland can determine the exact time the master disable took effect. This should allow userland to atomically save the state of the timer, and later restore it. Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David Daney <david.daney@cavium.com> Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:37 +07:00
int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl);
int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume);
int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz);
MIPS: KVM: Rewrite count/compare timer emulation Previously the emulation of the CPU timer was just enough to get a Linux guest running but some shortcuts were taken: - The guest timer interrupt was hard coded to always happen every 10 ms rather than being timed to when CP0_Count would match CP0_Compare. - The guest's CP0_Count register was based on the host's CP0_Count register. This isn't very portable and fails on cores without a CP_Count register implemented such as Ingenic XBurst. It also meant that the guest's CP0_Cause.DC bit to disable the CP0_Count register took no effect. - The guest's CP0_Count register was emulated by just dividing the host's CP0_Count register by 4. This resulted in continuity problems when used as a clock source, since when the host CP0_Count overflows from 0x7fffffff to 0x80000000, the guest CP0_Count transitions discontinuously from 0x1fffffff to 0xe0000000. Therefore rewrite & fix emulation of the guest timer based on the monotonic kernel time (i.e. ktime_get()). Internally a 32-bit count_bias value is added to the frequency scaled nanosecond monotonic time to get the guest's CP0_Count. The frequency of the timer is initialised to 100MHz and cannot yet be changed, but a later patch will allow the frequency to be configured via the KVM_{GET,SET}_ONE_REG ioctl interface. The timer can now be stopped via the CP0_Cause.DC bit (by the guest or via the KVM_SET_ONE_REG ioctl interface), at which point the current CP0_Count is stored and can be read directly. When it is restarted the bias is recalculated such that the CP0_Count value is continuous. Due to the nature of hrtimer interrupts any read of the guest's CP0_Count register while it is running triggers a check for whether the hrtimer has expired, so that the guest/userland cannot observe the CP0_Count passing CP0_Compare without queuing a timer interrupt. This is also taken advantage of when stopping the timer to ensure that a pending timer interrupt is queued. This replaces the implementation of: - Guest read of CP0_Count - Guest write of CP0_Count - Guest write of CP0_Compare - Guest write of CP0_Cause - Guest read of HWR 2 (CC) with RDHWR - Host read of CP0_Count via KVM_GET_ONE_REG ioctl interface - Host write of CP0_Count via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Compare via KVM_SET_ONE_REG ioctl interface - Host write of CP0_Cause via KVM_SET_ONE_REG ioctl interface Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Gleb Natapov <gleb@kernel.org> Cc: kvm@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: Sanjay Lal <sanjayl@kymasys.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-05-29 16:16:35 +07:00
void kvm_mips_count_enable_cause(struct kvm_vcpu *vcpu);
void kvm_mips_count_disable_cause(struct kvm_vcpu *vcpu);
enum hrtimer_restart kvm_mips_count_timeout(struct kvm_vcpu *vcpu);
enum emulation_result kvm_mips_check_privilege(u32 cause,
u32 *opc,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst,
u32 *opc,
u32 cause,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst,
u32 *opc,
u32 cause,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
enum emulation_result kvm_mips_emulate_store(union mips_instruction inst,
u32 cause,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
u32 cause,
struct kvm_run *run,
struct kvm_vcpu *vcpu);
unsigned int kvm_mips_config1_wrmask(struct kvm_vcpu *vcpu);
unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu);
unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu);
unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu);
/* Hypercalls (hypcall.c) */
enum emulation_result kvm_mips_emul_hypcall(struct kvm_vcpu *vcpu,
union mips_instruction inst);
int kvm_mips_handle_hypcall(struct kvm_vcpu *vcpu);
/* Dynamic binary translation */
extern int kvm_mips_trans_cache_index(union mips_instruction inst,
u32 *opc, struct kvm_vcpu *vcpu);
extern int kvm_mips_trans_cache_va(union mips_instruction inst, u32 *opc,
struct kvm_vcpu *vcpu);
extern int kvm_mips_trans_mfc0(union mips_instruction inst, u32 *opc,
struct kvm_vcpu *vcpu);
extern int kvm_mips_trans_mtc0(union mips_instruction inst, u32 *opc,
struct kvm_vcpu *vcpu);
/* Misc */
extern void kvm_mips_dump_stats(struct kvm_vcpu *vcpu);
extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm);
static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_free_memslot(struct kvm *kvm,
struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
KVM: halt_polling: provide a way to qualify wakeups during poll Some wakeups should not be considered a sucessful poll. For example on s390 I/O interrupts are usually floating, which means that _ALL_ CPUs would be considered runnable - letting all vCPUs poll all the time for transactional like workload, even if one vCPU would be enough. This can result in huge CPU usage for large guests. This patch lets architectures provide a way to qualify wakeups if they should be considered a good/bad wakeups in regard to polls. For s390 the implementation will fence of halt polling for anything but known good, single vCPU events. The s390 implementation for floating interrupts does a wakeup for one vCPU, but the interrupt will be delivered by whatever CPU checks first for a pending interrupt. We prefer the woken up CPU by marking the poll of this CPU as "good" poll. This code will also mark several other wakeup reasons like IPI or expired timers as "good". This will of course also mark some events as not sucessful. As KVM on z runs always as a 2nd level hypervisor, we prefer to not poll, unless we are really sure, though. This patch successfully limits the CPU usage for cases like uperf 1byte transactional ping pong workload or wakeup heavy workload like OLTP while still providing a proper speedup. This also introduced a new vcpu stat "halt_poll_no_tuning" that marks wakeups that are considered not good for polling. Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Acked-by: Radim Krčmář <rkrcmar@redhat.com> (for an earlier version) Cc: David Matlack <dmatlack@google.com> Cc: Wanpeng Li <kernellwp@gmail.com> [Rename config symbol. - Paolo] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2016-05-13 17:16:35 +07:00
static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
#endif /* __MIPS_KVM_HOST_H__ */