mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 00:06:51 +07:00
0d1e8b8d2b
ARM: - Improved guest IPA space support (32 to 52 bits) - RAS event delivery for 32bit - PMU fixes - Guest entry hardening - Various cleanups - Port of dirty_log_test selftest PPC: - Nested HV KVM support for radix guests on POWER9. The performance is much better than with PR KVM. Migration and arbitrary level of nesting is supported. - Disable nested HV-KVM on early POWER9 chips that need a particular hardware bug workaround - One VM per core mode to prevent potential data leaks - PCI pass-through optimization - merge ppc-kvm topic branch and kvm-ppc-fixes to get a better base s390: - Initial version of AP crypto virtualization via vfio-mdev - Improvement for vfio-ap - Set the host program identifier - Optimize page table locking x86: - Enable nested virtualization by default - Implement Hyper-V IPI hypercalls - Improve #PF and #DB handling - Allow guests to use Enlightened VMCS - Add migration selftests for VMCS and Enlightened VMCS - Allow coalesced PIO accesses - Add an option to perform nested VMCS host state consistency check through hardware - Automatic tuning of lapic_timer_advance_ns - Many fixes, minor improvements, and cleanups -----BEGIN PGP SIGNATURE----- iQEcBAABCAAGBQJb0FINAAoJEED/6hsPKofoI60IAJRS3vOAQ9Fav8cJsO1oBHcX 3+NexfnBke1bzrjIR3SUcHKGZbdnVPNZc+Q4JjIbPpPmmOMU5jc9BC1dmd5f4Vzh BMnQ0yCvgFv3A3fy/Icx1Z8NJppxosdmqdQLrQrNo8aD3cjnqY2yQixdXrAfzLzw XEgKdIFCCz8oVN/C9TT4wwJn6l9OE7BM5bMKGFy5VNXzMu7t64UDOLbbjZxNgi1g teYvfVGdt5mH0N7b2GPPWRbJmgnz5ygVVpVNQUEFrdKZoCm6r5u9d19N+RRXAwan ZYFj10W2T8pJOUf3tryev4V33X7MRQitfJBo4tP5hZfi9uRX89np5zP1CFE7AtY= =yEPW -----END PGP SIGNATURE----- Merge tag 'kvm-4.20-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm Pull KVM updates from Radim Krčmář: "ARM: - Improved guest IPA space support (32 to 52 bits) - RAS event delivery for 32bit - PMU fixes - Guest entry hardening - Various cleanups - Port of dirty_log_test selftest PPC: - Nested HV KVM support for radix guests on POWER9. The performance is much better than with PR KVM. Migration and arbitrary level of nesting is supported. - Disable nested HV-KVM on early POWER9 chips that need a particular hardware bug workaround - One VM per core mode to prevent potential data leaks - PCI pass-through optimization - merge ppc-kvm topic branch and kvm-ppc-fixes to get a better base s390: - Initial version of AP crypto virtualization via vfio-mdev - Improvement for vfio-ap - Set the host program identifier - Optimize page table locking x86: - Enable nested virtualization by default - Implement Hyper-V IPI hypercalls - Improve #PF and #DB handling - Allow guests to use Enlightened VMCS - Add migration selftests for VMCS and Enlightened VMCS - Allow coalesced PIO accesses - Add an option to perform nested VMCS host state consistency check through hardware - Automatic tuning of lapic_timer_advance_ns - Many fixes, minor improvements, and cleanups" * tag 'kvm-4.20-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits) KVM/nVMX: Do not validate that posted_intr_desc_addr is page aligned Revert "kvm: x86: optimize dr6 restore" KVM: PPC: Optimize clearing TCEs for sparse tables x86/kvm/nVMX: tweak shadow fields selftests/kvm: add missing executables to .gitignore KVM: arm64: Safety check PSTATE when entering guest and handle IL KVM: PPC: Book3S HV: Don't use streamlined entry path on early POWER9 chips arm/arm64: KVM: Enable 32 bits kvm vcpu events support arm/arm64: KVM: Rename function kvm_arch_dev_ioctl_check_extension() KVM: arm64: Fix caching of host MDCR_EL2 value KVM: VMX: enable nested virtualization by default KVM/x86: Use 32bit xor to clear registers in svm.c kvm: x86: Introduce KVM_CAP_EXCEPTION_PAYLOAD kvm: vmx: Defer setting of DR6 until #DB delivery kvm: x86: Defer setting of CR2 until #PF delivery kvm: x86: Add payload operands to kvm_multiple_exception kvm: x86: Add exception payload fields to kvm_vcpu_events kvm: x86: Add has_payload and payload to kvm_queued_exception KVM: Documentation: Fix omission in struct kvm_vcpu_events KVM: selftests: add Enlightened VMCS test ...
371 lines
8.8 KiB
C
371 lines
8.8 KiB
C
/*
|
|
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
|
|
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License, version 2, as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
|
*/
|
|
|
|
#ifndef __ARM_KVM_MMU_H__
|
|
#define __ARM_KVM_MMU_H__
|
|
|
|
#include <asm/memory.h>
|
|
#include <asm/page.h>
|
|
|
|
/*
|
|
* We directly use the kernel VA for the HYP, as we can directly share
|
|
* the mapping (HTTBR "covers" TTBR1).
|
|
*/
|
|
#define kern_hyp_va(kva) (kva)
|
|
|
|
/* Contrary to arm64, there is no need to generate a PC-relative address */
|
|
#define hyp_symbol_addr(s) \
|
|
({ \
|
|
typeof(s) *addr = &(s); \
|
|
addr; \
|
|
})
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#include <linux/highmem.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/cputype.h>
|
|
#include <asm/kvm_arm.h>
|
|
#include <asm/kvm_hyp.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/stage2_pgtable.h>
|
|
|
|
/* Ensure compatibility with arm64 */
|
|
#define VA_BITS 32
|
|
|
|
#define kvm_phys_shift(kvm) KVM_PHYS_SHIFT
|
|
#define kvm_phys_size(kvm) (1ULL << kvm_phys_shift(kvm))
|
|
#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - 1ULL)
|
|
#define kvm_vttbr_baddr_mask(kvm) VTTBR_BADDR_MASK
|
|
|
|
#define stage2_pgd_size(kvm) (PTRS_PER_S2_PGD * sizeof(pgd_t))
|
|
|
|
int create_hyp_mappings(void *from, void *to, pgprot_t prot);
|
|
int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
|
|
void __iomem **kaddr,
|
|
void __iomem **haddr);
|
|
int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
|
|
void **haddr);
|
|
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_get_idmap_vector(void);
|
|
int kvm_mmu_init(void);
|
|
void kvm_clear_hyp_idmap(void);
|
|
|
|
#define kvm_mk_pmd(ptep) __pmd(__pa(ptep) | PMD_TYPE_TABLE)
|
|
#define kvm_mk_pud(pmdp) __pud(__pa(pmdp) | PMD_TYPE_TABLE)
|
|
#define kvm_mk_pgd(pudp) ({ BUILD_BUG(); 0; })
|
|
|
|
static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
|
|
{
|
|
pte_val(pte) |= L_PTE_S2_RDWR;
|
|
return pte;
|
|
}
|
|
|
|
static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
|
|
{
|
|
pmd_val(pmd) |= L_PMD_S2_RDWR;
|
|
return pmd;
|
|
}
|
|
|
|
static inline pte_t kvm_s2pte_mkexec(pte_t pte)
|
|
{
|
|
pte_val(pte) &= ~L_PTE_XN;
|
|
return pte;
|
|
}
|
|
|
|
static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
|
|
{
|
|
pmd_val(pmd) &= ~PMD_SECT_XN;
|
|
return pmd;
|
|
}
|
|
|
|
static inline void kvm_set_s2pte_readonly(pte_t *pte)
|
|
{
|
|
pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY;
|
|
}
|
|
|
|
static inline bool kvm_s2pte_readonly(pte_t *pte)
|
|
{
|
|
return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY;
|
|
}
|
|
|
|
static inline bool kvm_s2pte_exec(pte_t *pte)
|
|
{
|
|
return !(pte_val(*pte) & L_PTE_XN);
|
|
}
|
|
|
|
static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
|
|
{
|
|
pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY;
|
|
}
|
|
|
|
static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
|
|
{
|
|
return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY;
|
|
}
|
|
|
|
static inline bool kvm_s2pmd_exec(pmd_t *pmd)
|
|
{
|
|
return !(pmd_val(*pmd) & PMD_SECT_XN);
|
|
}
|
|
|
|
static inline bool kvm_page_empty(void *ptr)
|
|
{
|
|
struct page *ptr_page = virt_to_page(ptr);
|
|
return page_count(ptr_page) == 1;
|
|
}
|
|
|
|
#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
|
|
#define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
|
|
#define kvm_pud_table_empty(kvm, pudp) false
|
|
|
|
#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
|
|
#define hyp_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
|
|
#define hyp_pud_table_empty(pudp) false
|
|
|
|
struct kvm;
|
|
|
|
#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l))
|
|
|
|
static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
|
|
{
|
|
return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101;
|
|
}
|
|
|
|
static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
|
|
{
|
|
/*
|
|
* Clean the dcache to the Point of Coherency.
|
|
*
|
|
* We need to do this through a kernel mapping (using the
|
|
* user-space mapping has proved to be the wrong
|
|
* solution). For that, we need to kmap one page at a time,
|
|
* and iterate over the range.
|
|
*/
|
|
|
|
VM_BUG_ON(size & ~PAGE_MASK);
|
|
|
|
while (size) {
|
|
void *va = kmap_atomic_pfn(pfn);
|
|
|
|
kvm_flush_dcache_to_poc(va, PAGE_SIZE);
|
|
|
|
size -= PAGE_SIZE;
|
|
pfn++;
|
|
|
|
kunmap_atomic(va);
|
|
}
|
|
}
|
|
|
|
static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
|
|
unsigned long size)
|
|
{
|
|
u32 iclsz;
|
|
|
|
/*
|
|
* If we are going to insert an instruction page and the icache is
|
|
* either VIPT or PIPT, there is a potential problem where the host
|
|
* (or another VM) may have used the same page as this guest, and we
|
|
* read incorrect data from the icache. If we're using a PIPT cache,
|
|
* we can invalidate just that page, but if we are using a VIPT cache
|
|
* we need to invalidate the entire icache - damn shame - as written
|
|
* in the ARM ARM (DDI 0406C.b - Page B3-1393).
|
|
*
|
|
* VIVT caches are tagged using both the ASID and the VMID and doesn't
|
|
* need any kind of flushing (DDI 0406C.b - Page B3-1392).
|
|
*/
|
|
|
|
VM_BUG_ON(size & ~PAGE_MASK);
|
|
|
|
if (icache_is_vivt_asid_tagged())
|
|
return;
|
|
|
|
if (!icache_is_pipt()) {
|
|
/* any kind of VIPT cache */
|
|
__flush_icache_all();
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* CTR IminLine contains Log2 of the number of words in the
|
|
* cache line, so we can get the number of words as
|
|
* 2 << (IminLine - 1). To get the number of bytes, we
|
|
* multiply by 4 (the number of bytes in a 32-bit word), and
|
|
* get 4 << (IminLine).
|
|
*/
|
|
iclsz = 4 << (read_cpuid(CPUID_CACHETYPE) & 0xf);
|
|
|
|
while (size) {
|
|
void *va = kmap_atomic_pfn(pfn);
|
|
void *end = va + PAGE_SIZE;
|
|
void *addr = va;
|
|
|
|
do {
|
|
write_sysreg(addr, ICIMVAU);
|
|
addr += iclsz;
|
|
} while (addr < end);
|
|
|
|
dsb(ishst);
|
|
isb();
|
|
|
|
size -= PAGE_SIZE;
|
|
pfn++;
|
|
|
|
kunmap_atomic(va);
|
|
}
|
|
|
|
/* Check if we need to invalidate the BTB */
|
|
if ((read_cpuid_ext(CPUID_EXT_MMFR1) >> 28) != 4) {
|
|
write_sysreg(0, BPIALLIS);
|
|
dsb(ishst);
|
|
isb();
|
|
}
|
|
}
|
|
|
|
static inline void __kvm_flush_dcache_pte(pte_t pte)
|
|
{
|
|
void *va = kmap_atomic(pte_page(pte));
|
|
|
|
kvm_flush_dcache_to_poc(va, PAGE_SIZE);
|
|
|
|
kunmap_atomic(va);
|
|
}
|
|
|
|
static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
|
|
{
|
|
unsigned long size = PMD_SIZE;
|
|
kvm_pfn_t pfn = pmd_pfn(pmd);
|
|
|
|
while (size) {
|
|
void *va = kmap_atomic_pfn(pfn);
|
|
|
|
kvm_flush_dcache_to_poc(va, PAGE_SIZE);
|
|
|
|
pfn++;
|
|
size -= PAGE_SIZE;
|
|
|
|
kunmap_atomic(va);
|
|
}
|
|
}
|
|
|
|
static inline void __kvm_flush_dcache_pud(pud_t pud)
|
|
{
|
|
}
|
|
|
|
#define kvm_virt_to_phys(x) virt_to_idmap((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 false;
|
|
}
|
|
|
|
static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
|
|
{
|
|
return PTRS_PER_PGD;
|
|
}
|
|
|
|
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) { }
|
|
|
|
static inline unsigned int kvm_get_vmid_bits(void)
|
|
{
|
|
return 8;
|
|
}
|
|
|
|
/*
|
|
* We are not in the kvm->srcu critical section most of the time, so we take
|
|
* the SRCU read lock here. Since we copy the data from the user page, we
|
|
* can immediately drop the lock again.
|
|
*/
|
|
static inline int kvm_read_guest_lock(struct kvm *kvm,
|
|
gpa_t gpa, void *data, unsigned long len)
|
|
{
|
|
int srcu_idx = srcu_read_lock(&kvm->srcu);
|
|
int ret = kvm_read_guest(kvm, gpa, data, len);
|
|
|
|
srcu_read_unlock(&kvm->srcu, srcu_idx);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static inline void *kvm_get_hyp_vector(void)
|
|
{
|
|
switch(read_cpuid_part()) {
|
|
#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
|
|
case ARM_CPU_PART_CORTEX_A12:
|
|
case ARM_CPU_PART_CORTEX_A17:
|
|
{
|
|
extern char __kvm_hyp_vector_bp_inv[];
|
|
return kvm_ksym_ref(__kvm_hyp_vector_bp_inv);
|
|
}
|
|
|
|
case ARM_CPU_PART_BRAHMA_B15:
|
|
case ARM_CPU_PART_CORTEX_A15:
|
|
{
|
|
extern char __kvm_hyp_vector_ic_inv[];
|
|
return kvm_ksym_ref(__kvm_hyp_vector_ic_inv);
|
|
}
|
|
#endif
|
|
default:
|
|
{
|
|
extern char __kvm_hyp_vector[];
|
|
return kvm_ksym_ref(__kvm_hyp_vector);
|
|
}
|
|
}
|
|
}
|
|
|
|
static inline int kvm_map_vectors(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int hyp_map_aux_data(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#define kvm_phys_to_vttbr(addr) (addr)
|
|
|
|
static inline void kvm_set_ipa_limit(void) {}
|
|
|
|
static inline bool kvm_cpu_has_cnp(void)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
#endif /* __ARM_KVM_MMU_H__ */
|