mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
7beaa24ba4
- x86: miscellaneous fixes, AVIC support (local APIC virtualization, AMD version) - s390: polling for interrupts after a VCPU goes to halted state is now enabled for s390; use hardware provided information about facility bits that do not need any hypervisor activity, and other fixes for cpu models and facilities; improve perf output; floating interrupt controller improvements. - MIPS: miscellaneous fixes - PPC: bugfixes only - ARM: 16K page size support, generic firmware probing layer for timer and GIC Christoffer Dall (KVM-ARM maintainer) says: "There are a few changes in this pull request touching things outside KVM, but they should all carry the necessary acks and it made the merge process much easier to do it this way." though actually the irqchip maintainers' acks didn't make it into the patches. Marc Zyngier, who is both irqchip and KVM-ARM maintainer, later acked at http://mid.gmane.org/573351D1.4060303@arm.com "more formally and for documentation purposes". -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) iQEcBAABAgAGBQJXPJjyAAoJEL/70l94x66DhioH/j4fwQ0FmfPSM9PArzaFHQdx LNE3tU4+bobbsy1BJr4DiAaOUQn3DAgwUvGLWXdeLiOXtoWXBiFHKaxlqEsCA6iQ xcTH1TgfxsVoqGQ6bT9X/2GCx70heYpcWG3f+zqBy7ZfFmQykLAC/HwOr52VQL8f hUFi3YmTHcnorp0n5Xg+9r3+RBS4D/kTbtdn6+KCLnPJ0RcgNkI3/NcafTemoofw Tkv8+YYFNvKV13qlIfVqxMa0GwWI3pP6YaNKhaS5XO8Pu16HuuF1JthJsUBDzwBa RInp8R9MoXgsBYhLpz3jc9vWG7G9yDl5LehsD9KOUGOaFYJ7sQN+QZOusa6jFgA= =llO5 -----END PGP SIGNATURE----- Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm Pull KVM updates from Paolo Bonzini: "Small release overall. x86: - miscellaneous fixes - AVIC support (local APIC virtualization, AMD version) s390: - polling for interrupts after a VCPU goes to halted state is now enabled for s390 - use hardware provided information about facility bits that do not need any hypervisor activity, and other fixes for cpu models and facilities - improve perf output - floating interrupt controller improvements. MIPS: - miscellaneous fixes PPC: - bugfixes only ARM: - 16K page size support - generic firmware probing layer for timer and GIC Christoffer Dall (KVM-ARM maintainer) says: "There are a few changes in this pull request touching things outside KVM, but they should all carry the necessary acks and it made the merge process much easier to do it this way." though actually the irqchip maintainers' acks didn't make it into the patches. Marc Zyngier, who is both irqchip and KVM-ARM maintainer, later acked at http://mid.gmane.org/573351D1.4060303@arm.com ('more formally and for documentation purposes')" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (82 commits) KVM: MTRR: remove MSR 0x2f8 KVM: x86: make hwapic_isr_update and hwapic_irr_update look the same svm: Manage vcpu load/unload when enable AVIC svm: Do not intercept CR8 when enable AVIC svm: Do not expose x2APIC when enable AVIC KVM: x86: Introducing kvm_x86_ops.apicv_post_state_restore svm: Add VMEXIT handlers for AVIC svm: Add interrupt injection via AVIC KVM: x86: Detect and Initialize AVIC support svm: Introduce new AVIC VMCB registers KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick KVM: x86: Introducing kvm_x86_ops VCPU blocking/unblocking hooks KVM: x86: Introducing kvm_x86_ops VM init/destroy hooks KVM: x86: Rename kvm_apic_get_reg to kvm_lapic_get_reg KVM: x86: Misc LAPIC changes to expose helper functions KVM: shrink halt polling even more for invalid wakeups KVM: s390: set halt polling to 80 microseconds KVM: halt_polling: provide a way to qualify wakeups during poll KVM: PPC: Book3S HV: Re-enable XICS fast path for irqfd-generated interrupts kvm: Conditionally register IRQ bypass consumer ...
269 lines
7.3 KiB
C
269 lines
7.3 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_MMU_H__
|
|
#define __ARM64_KVM_MMU_H__
|
|
|
|
#include <asm/page.h>
|
|
#include <asm/memory.h>
|
|
#include <asm/cpufeature.h>
|
|
|
|
/*
|
|
* As ARMv8.0 only has the TTBR0_EL2 register, we cannot express
|
|
* "negative" addresses. This makes it impossible to directly share
|
|
* mappings with the kernel.
|
|
*
|
|
* Instead, give the HYP mode its own VA region at a fixed offset from
|
|
* the kernel by just masking the top bits (which are all ones for a
|
|
* kernel address).
|
|
*
|
|
* ARMv8.1 (using VHE) does have a TTBR1_EL2, and doesn't use these
|
|
* macros (the entire kernel runs at EL2).
|
|
*/
|
|
#define HYP_PAGE_OFFSET_SHIFT VA_BITS
|
|
#define HYP_PAGE_OFFSET_MASK ((UL(1) << HYP_PAGE_OFFSET_SHIFT) - 1)
|
|
#define HYP_PAGE_OFFSET (PAGE_OFFSET & HYP_PAGE_OFFSET_MASK)
|
|
|
|
/*
|
|
* Our virtual mapping for the idmap-ed MMU-enable code. Must be
|
|
* shared across all the page-tables. Conveniently, we use the last
|
|
* possible page, where no kernel mapping will ever exist.
|
|
*/
|
|
#define TRAMPOLINE_VA (HYP_PAGE_OFFSET_MASK & PAGE_MASK)
|
|
|
|
#ifdef __ASSEMBLY__
|
|
|
|
#include <asm/alternative.h>
|
|
#include <asm/cpufeature.h>
|
|
|
|
/*
|
|
* Convert a kernel VA into a HYP VA.
|
|
* reg: VA to be converted.
|
|
*/
|
|
.macro kern_hyp_va reg
|
|
alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
|
|
and \reg, \reg, #HYP_PAGE_OFFSET_MASK
|
|
alternative_else
|
|
nop
|
|
alternative_endif
|
|
.endm
|
|
|
|
#else
|
|
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/cachetype.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
#define KERN_TO_HYP(kva) ((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)
|
|
|
|
/*
|
|
* We currently only support a 40bit IPA.
|
|
*/
|
|
#define KVM_PHYS_SHIFT (40)
|
|
#define KVM_PHYS_SIZE (1UL << KVM_PHYS_SHIFT)
|
|
#define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1UL)
|
|
|
|
#include <asm/stage2_pgtable.h>
|
|
|
|
int create_hyp_mappings(void *from, void *to);
|
|
int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
|
|
void free_boot_hyp_pgd(void);
|
|
void free_hyp_pgds(void);
|
|
|
|
void stage2_unmap_vm(struct kvm *kvm);
|
|
int kvm_alloc_stage2_pgd(struct kvm *kvm);
|
|
void kvm_free_stage2_pgd(struct kvm *kvm);
|
|
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
|
|
phys_addr_t pa, unsigned long size, bool writable);
|
|
|
|
int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
|
|
|
|
void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
|
|
|
|
phys_addr_t kvm_mmu_get_httbr(void);
|
|
phys_addr_t kvm_mmu_get_boot_httbr(void);
|
|
phys_addr_t kvm_get_idmap_vector(void);
|
|
phys_addr_t kvm_get_idmap_start(void);
|
|
int kvm_mmu_init(void);
|
|
void kvm_clear_hyp_idmap(void);
|
|
|
|
#define kvm_set_pte(ptep, pte) set_pte(ptep, pte)
|
|
#define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd)
|
|
|
|
static inline void kvm_clean_pgd(pgd_t *pgd) {}
|
|
static inline void kvm_clean_pmd(pmd_t *pmd) {}
|
|
static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
|
|
static inline void kvm_clean_pte(pte_t *pte) {}
|
|
static inline void kvm_clean_pte_entry(pte_t *pte) {}
|
|
|
|
static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
|
|
{
|
|
pte_val(pte) |= PTE_S2_RDWR;
|
|
return pte;
|
|
}
|
|
|
|
static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
|
|
{
|
|
pmd_val(pmd) |= PMD_S2_RDWR;
|
|
return pmd;
|
|
}
|
|
|
|
static inline void kvm_set_s2pte_readonly(pte_t *pte)
|
|
{
|
|
pteval_t pteval;
|
|
unsigned long tmp;
|
|
|
|
asm volatile("// kvm_set_s2pte_readonly\n"
|
|
" prfm pstl1strm, %2\n"
|
|
"1: ldxr %0, %2\n"
|
|
" and %0, %0, %3 // clear PTE_S2_RDWR\n"
|
|
" orr %0, %0, %4 // set PTE_S2_RDONLY\n"
|
|
" stxr %w1, %0, %2\n"
|
|
" cbnz %w1, 1b\n"
|
|
: "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*pte))
|
|
: "L" (~PTE_S2_RDWR), "L" (PTE_S2_RDONLY));
|
|
}
|
|
|
|
static inline bool kvm_s2pte_readonly(pte_t *pte)
|
|
{
|
|
return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
|
|
}
|
|
|
|
static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
|
|
{
|
|
kvm_set_s2pte_readonly((pte_t *)pmd);
|
|
}
|
|
|
|
static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
|
|
{
|
|
return kvm_s2pte_readonly((pte_t *)pmd);
|
|
}
|
|
|
|
static inline bool kvm_page_empty(void *ptr)
|
|
{
|
|
struct page *ptr_page = virt_to_page(ptr);
|
|
return page_count(ptr_page) == 1;
|
|
}
|
|
|
|
#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
|
|
|
|
#ifdef __PAGETABLE_PMD_FOLDED
|
|
#define hyp_pmd_table_empty(pmdp) (0)
|
|
#else
|
|
#define hyp_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
|
|
#endif
|
|
|
|
#ifdef __PAGETABLE_PUD_FOLDED
|
|
#define hyp_pud_table_empty(pudp) (0)
|
|
#else
|
|
#define hyp_pud_table_empty(pudp) kvm_page_empty(pudp)
|
|
#endif
|
|
|
|
struct kvm;
|
|
|
|
#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l))
|
|
|
|
static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
|
|
{
|
|
return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
|
|
}
|
|
|
|
static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
|
|
kvm_pfn_t pfn,
|
|
unsigned long size,
|
|
bool ipa_uncached)
|
|
{
|
|
void *va = page_address(pfn_to_page(pfn));
|
|
|
|
if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached)
|
|
kvm_flush_dcache_to_poc(va, size);
|
|
|
|
if (!icache_is_aliasing()) { /* PIPT */
|
|
flush_icache_range((unsigned long)va,
|
|
(unsigned long)va + size);
|
|
} else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */
|
|
/* any kind of VIPT cache */
|
|
__flush_icache_all();
|
|
}
|
|
}
|
|
|
|
static inline void __kvm_flush_dcache_pte(pte_t pte)
|
|
{
|
|
struct page *page = pte_page(pte);
|
|
kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
|
|
}
|
|
|
|
static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
|
|
{
|
|
struct page *page = pmd_page(pmd);
|
|
kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
|
|
}
|
|
|
|
static inline void __kvm_flush_dcache_pud(pud_t pud)
|
|
{
|
|
struct page *page = pud_page(pud);
|
|
kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
|
|
}
|
|
|
|
#define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x))
|
|
|
|
void kvm_set_way_flush(struct kvm_vcpu *vcpu);
|
|
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
|
|
|
|
static inline bool __kvm_cpu_uses_extended_idmap(void)
|
|
{
|
|
return __cpu_uses_extended_idmap();
|
|
}
|
|
|
|
static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
|
|
pgd_t *hyp_pgd,
|
|
pgd_t *merged_hyp_pgd,
|
|
unsigned long hyp_idmap_start)
|
|
{
|
|
int idmap_idx;
|
|
|
|
/*
|
|
* Use the first entry to access the HYP mappings. It is
|
|
* guaranteed to be free, otherwise we wouldn't use an
|
|
* extended idmap.
|
|
*/
|
|
VM_BUG_ON(pgd_val(merged_hyp_pgd[0]));
|
|
merged_hyp_pgd[0] = __pgd(__pa(hyp_pgd) | PMD_TYPE_TABLE);
|
|
|
|
/*
|
|
* Create another extended level entry that points to the boot HYP map,
|
|
* which contains an ID mapping of the HYP init code. We essentially
|
|
* merge the boot and runtime HYP maps by doing so, but they don't
|
|
* overlap anyway, so this is fine.
|
|
*/
|
|
idmap_idx = hyp_idmap_start >> VA_BITS;
|
|
VM_BUG_ON(pgd_val(merged_hyp_pgd[idmap_idx]));
|
|
merged_hyp_pgd[idmap_idx] = __pgd(__pa(boot_hyp_pgd) | PMD_TYPE_TABLE);
|
|
}
|
|
|
|
static inline unsigned int kvm_get_vmid_bits(void)
|
|
{
|
|
int reg = read_system_reg(SYS_ID_AA64MMFR1_EL1);
|
|
|
|
return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
|
|
}
|
|
|
|
#endif /* __ASSEMBLY__ */
|
|
#endif /* __ARM64_KVM_MMU_H__ */
|