mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 14:09:55 +07:00
42b00f122c
single-stepping fixes, improved tracing, various timer and vGIC fixes * x86: Processor Tracing virtualization, STIBP support, some correctness fixes, refactorings and splitting of vmx.c, use the Hyper-V range TLB flush hypercall, reduce order of vcpu struct, WBNOINVD support, do not use -ftrace for __noclone functions, nested guest support for PAUSE filtering on AMD, more Hyper-V enlightenments (direct mode for synthetic timers) * PPC: nested VFIO * s390: bugfixes only this time -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) iQEcBAABAgAGBQJcH0vFAAoJEL/70l94x66Dw/wH/2FZp1YOM5OgiJzgqnXyDbyf dNEfWo472MtNiLsuf+ZAfJojVIu9cv7wtBfXNzW+75XZDfh/J88geHWNSiZDm3Fe aM4MOnGG0yF3hQrRQyEHe4IFhGFNERax8Ccv+OL44md9CjYrIrsGkRD08qwb+gNh P8T/3wJEKwUcVHA/1VHEIM8MlirxNENc78p6JKd/C7zb0emjGavdIpWFUMr3SNfs CemabhJUuwOYtwjRInyx1y34FzYwW3Ejuc9a9UoZ+COahUfkuxHE8u+EQS7vLVF6 2VGVu5SA0PqgmLlGhHthxLqVgQYo+dB22cRnsLtXlUChtVAq8q9uu5sKzvqEzuE= =b4Jx -----END PGP SIGNATURE----- Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm Pull KVM updates from Paolo Bonzini: "ARM: - selftests improvements - large PUD support for HugeTLB - single-stepping fixes - improved tracing - various timer and vGIC fixes x86: - Processor Tracing virtualization - STIBP support - some correctness fixes - refactorings and splitting of vmx.c - use the Hyper-V range TLB flush hypercall - reduce order of vcpu struct - WBNOINVD support - do not use -ftrace for __noclone functions - nested guest support for PAUSE filtering on AMD - more Hyper-V enlightenments (direct mode for synthetic timers) PPC: - nested VFIO s390: - bugfixes only this time" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (171 commits) KVM: x86: Add CPUID support for new instruction WBNOINVD kvm: selftests: ucall: fix exit mmio address guessing Revert "compiler-gcc: disable -ftracer for __noclone functions" KVM: VMX: Move VM-Enter + VM-Exit handling to non-inline sub-routines KVM: VMX: Explicitly reference RCX as the vmx_vcpu pointer in asm blobs KVM: x86: Use jmp to invoke kvm_spurious_fault() from .fixup MAINTAINERS: Add arch/x86/kvm sub-directories to existing KVM/x86 entry KVM/x86: Use SVM assembly instruction mnemonics instead of .byte streams KVM/MMU: Flush tlb directly in the kvm_zap_gfn_range() KVM/MMU: Flush tlb directly in kvm_set_pte_rmapp() KVM/MMU: Move tlb flush in kvm_set_pte_rmapp() to kvm_mmu_notifier_change_pte() KVM: Make kvm_set_spte_hva() return int KVM: Replace old tlb flush function with new one to flush a specified range. KVM/MMU: Add tlb flush with range helper function KVM/VMX: Add hv tlb range flush support x86/hyper-v: Add HvFlushGuestAddressList hypercall support KVM: Add tlb_remote_flush_with_range callback in kvm_x86_ops KVM: x86: Disable Intel PT when VMXON in L1 guest KVM: x86: Set intercept for Intel PT MSRs read/write KVM: x86: Implement Intel PT MSRs read/write emulation ...
343 lines
12 KiB
C
343 lines
12 KiB
C
/*
|
|
* Copyright (C) 2012,2013 - ARM Ltd
|
|
* Author: Marc Zyngier <marc.zyngier@arm.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#ifndef __ARM64_KVM_ARM_H__
|
|
#define __ARM64_KVM_ARM_H__
|
|
|
|
#include <asm/esr.h>
|
|
#include <asm/memory.h>
|
|
#include <asm/types.h>
|
|
|
|
/* Hyp Configuration Register (HCR) bits */
|
|
#define HCR_FWB (UL(1) << 46)
|
|
#define HCR_API (UL(1) << 41)
|
|
#define HCR_APK (UL(1) << 40)
|
|
#define HCR_TEA (UL(1) << 37)
|
|
#define HCR_TERR (UL(1) << 36)
|
|
#define HCR_TLOR (UL(1) << 35)
|
|
#define HCR_E2H (UL(1) << 34)
|
|
#define HCR_ID (UL(1) << 33)
|
|
#define HCR_CD (UL(1) << 32)
|
|
#define HCR_RW_SHIFT 31
|
|
#define HCR_RW (UL(1) << HCR_RW_SHIFT)
|
|
#define HCR_TRVM (UL(1) << 30)
|
|
#define HCR_HCD (UL(1) << 29)
|
|
#define HCR_TDZ (UL(1) << 28)
|
|
#define HCR_TGE (UL(1) << 27)
|
|
#define HCR_TVM (UL(1) << 26)
|
|
#define HCR_TTLB (UL(1) << 25)
|
|
#define HCR_TPU (UL(1) << 24)
|
|
#define HCR_TPC (UL(1) << 23)
|
|
#define HCR_TSW (UL(1) << 22)
|
|
#define HCR_TAC (UL(1) << 21)
|
|
#define HCR_TIDCP (UL(1) << 20)
|
|
#define HCR_TSC (UL(1) << 19)
|
|
#define HCR_TID3 (UL(1) << 18)
|
|
#define HCR_TID2 (UL(1) << 17)
|
|
#define HCR_TID1 (UL(1) << 16)
|
|
#define HCR_TID0 (UL(1) << 15)
|
|
#define HCR_TWE (UL(1) << 14)
|
|
#define HCR_TWI (UL(1) << 13)
|
|
#define HCR_DC (UL(1) << 12)
|
|
#define HCR_BSU (3 << 10)
|
|
#define HCR_BSU_IS (UL(1) << 10)
|
|
#define HCR_FB (UL(1) << 9)
|
|
#define HCR_VSE (UL(1) << 8)
|
|
#define HCR_VI (UL(1) << 7)
|
|
#define HCR_VF (UL(1) << 6)
|
|
#define HCR_AMO (UL(1) << 5)
|
|
#define HCR_IMO (UL(1) << 4)
|
|
#define HCR_FMO (UL(1) << 3)
|
|
#define HCR_PTW (UL(1) << 2)
|
|
#define HCR_SWIO (UL(1) << 1)
|
|
#define HCR_VM (UL(1) << 0)
|
|
|
|
/*
|
|
* The bits we set in HCR:
|
|
* TLOR: Trap LORegion register accesses
|
|
* RW: 64bit by default, can be overridden for 32bit VMs
|
|
* TAC: Trap ACTLR
|
|
* TSC: Trap SMC
|
|
* TVM: Trap VM ops (until M+C set in SCTLR_EL1)
|
|
* TSW: Trap cache operations by set/way
|
|
* TWE: Trap WFE
|
|
* TWI: Trap WFI
|
|
* TIDCP: Trap L2CTLR/L2ECTLR
|
|
* BSU_IS: Upgrade barriers to the inner shareable domain
|
|
* FB: Force broadcast of all maintainance operations
|
|
* AMO: Override CPSR.A and enable signaling with VA
|
|
* IMO: Override CPSR.I and enable signaling with VI
|
|
* FMO: Override CPSR.F and enable signaling with VF
|
|
* SWIO: Turn set/way invalidates into set/way clean+invalidate
|
|
*/
|
|
#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
|
|
HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
|
|
HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
|
|
HCR_FMO | HCR_IMO)
|
|
#define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
|
|
#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
|
|
#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
|
|
|
|
/* TCR_EL2 Registers bits */
|
|
#define TCR_EL2_RES1 ((1 << 31) | (1 << 23))
|
|
#define TCR_EL2_TBI (1 << 20)
|
|
#define TCR_EL2_PS_SHIFT 16
|
|
#define TCR_EL2_PS_MASK (7 << TCR_EL2_PS_SHIFT)
|
|
#define TCR_EL2_PS_40B (2 << TCR_EL2_PS_SHIFT)
|
|
#define TCR_EL2_TG0_MASK TCR_TG0_MASK
|
|
#define TCR_EL2_SH0_MASK TCR_SH0_MASK
|
|
#define TCR_EL2_ORGN0_MASK TCR_ORGN0_MASK
|
|
#define TCR_EL2_IRGN0_MASK TCR_IRGN0_MASK
|
|
#define TCR_EL2_T0SZ_MASK 0x3f
|
|
#define TCR_EL2_MASK (TCR_EL2_TG0_MASK | TCR_EL2_SH0_MASK | \
|
|
TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
|
|
|
|
/* VTCR_EL2 Registers bits */
|
|
#define VTCR_EL2_RES1 (1U << 31)
|
|
#define VTCR_EL2_HD (1 << 22)
|
|
#define VTCR_EL2_HA (1 << 21)
|
|
#define VTCR_EL2_PS_SHIFT TCR_EL2_PS_SHIFT
|
|
#define VTCR_EL2_PS_MASK TCR_EL2_PS_MASK
|
|
#define VTCR_EL2_TG0_MASK TCR_TG0_MASK
|
|
#define VTCR_EL2_TG0_4K TCR_TG0_4K
|
|
#define VTCR_EL2_TG0_16K TCR_TG0_16K
|
|
#define VTCR_EL2_TG0_64K TCR_TG0_64K
|
|
#define VTCR_EL2_SH0_MASK TCR_SH0_MASK
|
|
#define VTCR_EL2_SH0_INNER TCR_SH0_INNER
|
|
#define VTCR_EL2_ORGN0_MASK TCR_ORGN0_MASK
|
|
#define VTCR_EL2_ORGN0_WBWA TCR_ORGN0_WBWA
|
|
#define VTCR_EL2_IRGN0_MASK TCR_IRGN0_MASK
|
|
#define VTCR_EL2_IRGN0_WBWA TCR_IRGN0_WBWA
|
|
#define VTCR_EL2_SL0_SHIFT 6
|
|
#define VTCR_EL2_SL0_MASK (3 << VTCR_EL2_SL0_SHIFT)
|
|
#define VTCR_EL2_T0SZ_MASK 0x3f
|
|
#define VTCR_EL2_VS_SHIFT 19
|
|
#define VTCR_EL2_VS_8BIT (0 << VTCR_EL2_VS_SHIFT)
|
|
#define VTCR_EL2_VS_16BIT (1 << VTCR_EL2_VS_SHIFT)
|
|
|
|
#define VTCR_EL2_T0SZ(x) TCR_T0SZ(x)
|
|
|
|
/*
|
|
* We configure the Stage-2 page tables to always restrict the IPA space to be
|
|
* 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are
|
|
* not known to exist and will break with this configuration.
|
|
*
|
|
* The VTCR_EL2 is configured per VM and is initialised in kvm_arm_setup_stage2().
|
|
*
|
|
* Note that when using 4K pages, we concatenate two first level page tables
|
|
* together. With 16K pages, we concatenate 16 first level page tables.
|
|
*
|
|
*/
|
|
|
|
#define VTCR_EL2_COMMON_BITS (VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
|
|
VTCR_EL2_IRGN0_WBWA | VTCR_EL2_RES1)
|
|
|
|
/*
|
|
* VTCR_EL2:SL0 indicates the entry level for Stage2 translation.
|
|
* Interestingly, it depends on the page size.
|
|
* See D.10.2.121, VTCR_EL2, in ARM DDI 0487C.a
|
|
*
|
|
* -----------------------------------------
|
|
* | Entry level | 4K | 16K/64K |
|
|
* ------------------------------------------
|
|
* | Level: 0 | 2 | - |
|
|
* ------------------------------------------
|
|
* | Level: 1 | 1 | 2 |
|
|
* ------------------------------------------
|
|
* | Level: 2 | 0 | 1 |
|
|
* ------------------------------------------
|
|
* | Level: 3 | - | 0 |
|
|
* ------------------------------------------
|
|
*
|
|
* The table roughly translates to :
|
|
*
|
|
* SL0(PAGE_SIZE, Entry_level) = TGRAN_SL0_BASE - Entry_Level
|
|
*
|
|
* Where TGRAN_SL0_BASE is a magic number depending on the page size:
|
|
* TGRAN_SL0_BASE(4K) = 2
|
|
* TGRAN_SL0_BASE(16K) = 3
|
|
* TGRAN_SL0_BASE(64K) = 3
|
|
* provided we take care of ruling out the unsupported cases and
|
|
* Entry_Level = 4 - Number_of_levels.
|
|
*
|
|
*/
|
|
#ifdef CONFIG_ARM64_64K_PAGES
|
|
|
|
#define VTCR_EL2_TGRAN VTCR_EL2_TG0_64K
|
|
#define VTCR_EL2_TGRAN_SL0_BASE 3UL
|
|
|
|
#elif defined(CONFIG_ARM64_16K_PAGES)
|
|
|
|
#define VTCR_EL2_TGRAN VTCR_EL2_TG0_16K
|
|
#define VTCR_EL2_TGRAN_SL0_BASE 3UL
|
|
|
|
#else /* 4K */
|
|
|
|
#define VTCR_EL2_TGRAN VTCR_EL2_TG0_4K
|
|
#define VTCR_EL2_TGRAN_SL0_BASE 2UL
|
|
|
|
#endif
|
|
|
|
#define VTCR_EL2_LVLS_TO_SL0(levels) \
|
|
((VTCR_EL2_TGRAN_SL0_BASE - (4 - (levels))) << VTCR_EL2_SL0_SHIFT)
|
|
#define VTCR_EL2_SL0_TO_LVLS(sl0) \
|
|
((sl0) + 4 - VTCR_EL2_TGRAN_SL0_BASE)
|
|
#define VTCR_EL2_LVLS(vtcr) \
|
|
VTCR_EL2_SL0_TO_LVLS(((vtcr) & VTCR_EL2_SL0_MASK) >> VTCR_EL2_SL0_SHIFT)
|
|
|
|
#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN)
|
|
#define VTCR_EL2_IPA(vtcr) (64 - ((vtcr) & VTCR_EL2_T0SZ_MASK))
|
|
|
|
/*
|
|
* ARM VMSAv8-64 defines an algorithm for finding the translation table
|
|
* descriptors in section D4.2.8 in ARM DDI 0487C.a.
|
|
*
|
|
* The algorithm defines the expectations on the translation table
|
|
* addresses for each level, based on PAGE_SIZE, entry level
|
|
* and the translation table size (T0SZ). The variable "x" in the
|
|
* algorithm determines the alignment of a table base address at a given
|
|
* level and thus determines the alignment of VTTBR:BADDR for stage2
|
|
* page table entry level.
|
|
* Since the number of bits resolved at the entry level could vary
|
|
* depending on the T0SZ, the value of "x" is defined based on a
|
|
* Magic constant for a given PAGE_SIZE and Entry Level. The
|
|
* intermediate levels must be always aligned to the PAGE_SIZE (i.e,
|
|
* x = PAGE_SHIFT).
|
|
*
|
|
* The value of "x" for entry level is calculated as :
|
|
* x = Magic_N - T0SZ
|
|
*
|
|
* where Magic_N is an integer depending on the page size and the entry
|
|
* level of the page table as below:
|
|
*
|
|
* --------------------------------------------
|
|
* | Entry level | 4K 16K 64K |
|
|
* --------------------------------------------
|
|
* | Level: 0 (4 levels) | 28 | - | - |
|
|
* --------------------------------------------
|
|
* | Level: 1 (3 levels) | 37 | 31 | 25 |
|
|
* --------------------------------------------
|
|
* | Level: 2 (2 levels) | 46 | 42 | 38 |
|
|
* --------------------------------------------
|
|
* | Level: 3 (1 level) | - | 53 | 51 |
|
|
* --------------------------------------------
|
|
*
|
|
* We have a magic formula for the Magic_N below:
|
|
*
|
|
* Magic_N(PAGE_SIZE, Level) = 64 - ((PAGE_SHIFT - 3) * Number_of_levels)
|
|
*
|
|
* where Number_of_levels = (4 - Level). We are only interested in the
|
|
* value for Entry_Level for the stage2 page table.
|
|
*
|
|
* So, given that T0SZ = (64 - IPA_SHIFT), we can compute 'x' as follows:
|
|
*
|
|
* x = (64 - ((PAGE_SHIFT - 3) * Number_of_levels)) - (64 - IPA_SHIFT)
|
|
* = IPA_SHIFT - ((PAGE_SHIFT - 3) * Number of levels)
|
|
*
|
|
* Here is one way to explain the Magic Formula:
|
|
*
|
|
* x = log2(Size_of_Entry_Level_Table)
|
|
*
|
|
* Since, we can resolve (PAGE_SHIFT - 3) bits at each level, and another
|
|
* PAGE_SHIFT bits in the PTE, we have :
|
|
*
|
|
* Bits_Entry_level = IPA_SHIFT - ((PAGE_SHIFT - 3) * (n - 1) + PAGE_SHIFT)
|
|
* = IPA_SHIFT - (PAGE_SHIFT - 3) * n - 3
|
|
* where n = number of levels, and since each pointer is 8bytes, we have:
|
|
*
|
|
* x = Bits_Entry_Level + 3
|
|
* = IPA_SHIFT - (PAGE_SHIFT - 3) * n
|
|
*
|
|
* The only constraint here is that, we have to find the number of page table
|
|
* levels for a given IPA size (which we do, see stage2_pt_levels())
|
|
*/
|
|
#define ARM64_VTTBR_X(ipa, levels) ((ipa) - ((levels) * (PAGE_SHIFT - 3)))
|
|
|
|
#define VTTBR_CNP_BIT (UL(1))
|
|
#define VTTBR_VMID_SHIFT (UL(48))
|
|
#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
|
|
|
|
/* Hyp System Trap Register */
|
|
#define HSTR_EL2_T(x) (1 << x)
|
|
|
|
/* Hyp Coprocessor Trap Register Shifts */
|
|
#define CPTR_EL2_TFP_SHIFT 10
|
|
|
|
/* Hyp Coprocessor Trap Register */
|
|
#define CPTR_EL2_TCPAC (1 << 31)
|
|
#define CPTR_EL2_TTA (1 << 20)
|
|
#define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT)
|
|
#define CPTR_EL2_TZ (1 << 8)
|
|
#define CPTR_EL2_RES1 0x000032ff /* known RES1 bits in CPTR_EL2 */
|
|
#define CPTR_EL2_DEFAULT CPTR_EL2_RES1
|
|
|
|
/* Hyp Debug Configuration Register bits */
|
|
#define MDCR_EL2_TPMS (1 << 14)
|
|
#define MDCR_EL2_E2PB_MASK (UL(0x3))
|
|
#define MDCR_EL2_E2PB_SHIFT (UL(12))
|
|
#define MDCR_EL2_TDRA (1 << 11)
|
|
#define MDCR_EL2_TDOSA (1 << 10)
|
|
#define MDCR_EL2_TDA (1 << 9)
|
|
#define MDCR_EL2_TDE (1 << 8)
|
|
#define MDCR_EL2_HPME (1 << 7)
|
|
#define MDCR_EL2_TPM (1 << 6)
|
|
#define MDCR_EL2_TPMCR (1 << 5)
|
|
#define MDCR_EL2_HPMN_MASK (0x1F)
|
|
|
|
/* For compatibility with fault code shared with 32-bit */
|
|
#define FSC_FAULT ESR_ELx_FSC_FAULT
|
|
#define FSC_ACCESS ESR_ELx_FSC_ACCESS
|
|
#define FSC_PERM ESR_ELx_FSC_PERM
|
|
#define FSC_SEA ESR_ELx_FSC_EXTABT
|
|
#define FSC_SEA_TTW0 (0x14)
|
|
#define FSC_SEA_TTW1 (0x15)
|
|
#define FSC_SEA_TTW2 (0x16)
|
|
#define FSC_SEA_TTW3 (0x17)
|
|
#define FSC_SECC (0x18)
|
|
#define FSC_SECC_TTW0 (0x1c)
|
|
#define FSC_SECC_TTW1 (0x1d)
|
|
#define FSC_SECC_TTW2 (0x1e)
|
|
#define FSC_SECC_TTW3 (0x1f)
|
|
|
|
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
|
|
#define HPFAR_MASK (~UL(0xf))
|
|
/*
|
|
* We have
|
|
* PAR [PA_Shift - 1 : 12] = PA [PA_Shift - 1 : 12]
|
|
* HPFAR [PA_Shift - 9 : 4] = FIPA [PA_Shift - 1 : 12]
|
|
*/
|
|
#define PAR_TO_HPFAR(par) \
|
|
(((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8)
|
|
|
|
#define ECN(x) { ESR_ELx_EC_##x, #x }
|
|
|
|
#define kvm_arm_exception_class \
|
|
ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \
|
|
ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(CP14_64), ECN(SVC64), \
|
|
ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(IMP_DEF), ECN(IABT_LOW), \
|
|
ECN(IABT_CUR), ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \
|
|
ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \
|
|
ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \
|
|
ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
|
|
ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)
|
|
|
|
#define CPACR_EL1_FPEN (3 << 20)
|
|
#define CPACR_EL1_TTA (1 << 28)
|
|
#define CPACR_EL1_DEFAULT (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN)
|
|
|
|
#endif /* __ARM64_KVM_ARM_H__ */
|