kernel-fxtec-pro1x/arch/arm64/include/asm/kvm_mmu.h
Linus Torvalds b9085bcbf5 Fairly small update, but there are some interesting new features.
Common: Optional support for adding a small amount of polling on each HLT
 instruction executed in the guest (or equivalent for other architectures).
 This can improve latency up to 50% on some scenarios (e.g. O_DSYNC writes
 or TCP_RR netperf tests).  This also has to be enabled manually for now,
 but the plan is to auto-tune this in the future.
 
 ARM/ARM64: the highlights are support for GICv3 emulation and dirty page
 tracking
 
 s390: several optimizations and bugfixes.  Also a first: a feature
 exposed by KVM (UUID and long guest name in /proc/sysinfo) before
 it is available in IBM's hypervisor! :)
 
 MIPS: Bugfixes.
 
 x86: Support for PML (page modification logging, a new feature in
 Broadwell Xeons that speeds up dirty page tracking), nested virtualization
 improvements (nested APICv---a nice optimization), usual round of emulation
 fixes.  There is also a new option to reduce latency of the TSC deadline
 timer in the guest; this needs to be tuned manually.
 
 Some commits are common between this pull and Catalin's; I see you
 have already included his tree.
 
 ARM has other conflicts where functions are added in the same place
 by 3.19-rc and 3.20 patches.  These are not large though, and entirely
 within KVM.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQEcBAABAgAGBQJU28rkAAoJEL/70l94x66DXqQH/1TDOfJIjW7P2kb0Sw7Fy1wi
 cEX1KO/VFxAqc8R0E/0Wb55CXyPjQJM6xBXuFr5cUDaIjQ8ULSktL4pEwXyyv/s5
 DBDkN65mriry2w5VuEaRLVcuX9Wy+tqLQXWNkEySfyb4uhZChWWHvKEcgw5SqCyg
 NlpeHurYESIoNyov3jWqvBjr4OmaQENyv7t2c6q5ErIgG02V+iCux5QGbphM2IC9
 LFtPKxoqhfeB2xFxTOIt8HJiXrZNwflsTejIlCl/NSEiDVLLxxHCxK2tWK/tUXMn
 JfLD9ytXBWtNMwInvtFm4fPmDouv2VDyR0xnK2db+/axsJZnbxqjGu1um4Dqbak=
 =7gdx
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM update from Paolo Bonzini:
 "Fairly small update, but there are some interesting new features.

  Common:
     Optional support for adding a small amount of polling on each HLT
     instruction executed in the guest (or equivalent for other
     architectures).  This can improve latency up to 50% on some
     scenarios (e.g. O_DSYNC writes or TCP_RR netperf tests).  This
     also has to be enabled manually for now, but the plan is to
     auto-tune this in the future.

  ARM/ARM64:
     The highlights are support for GICv3 emulation and dirty page
     tracking

  s390:
     Several optimizations and bugfixes.  Also a first: a feature
     exposed by KVM (UUID and long guest name in /proc/sysinfo) before
     it is available in IBM's hypervisor! :)

  MIPS:
     Bugfixes.

  x86:
     Support for PML (page modification logging, a new feature in
     Broadwell Xeons that speeds up dirty page tracking), nested
     virtualization improvements (nested APICv---a nice optimization),
     usual round of emulation fixes.

     There is also a new option to reduce latency of the TSC deadline
     timer in the guest; this needs to be tuned manually.

     Some commits are common between this pull and Catalin's; I see you
     have already included his tree.

  Powerpc:
     Nothing yet.

     The KVM/PPC changes will come in through the PPC maintainers,
     because I haven't received them yet and I might end up being
     offline for some part of next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
  KVM: ia64: drop kvm.h from installed user headers
  KVM: x86: fix build with !CONFIG_SMP
  KVM: x86: emulate: correct page fault error code for NoWrite instructions
  KVM: Disable compat ioctl for s390
  KVM: s390: add cpu model support
  KVM: s390: use facilities and cpu_id per KVM
  KVM: s390/CPACF: Choose crypto control block format
  s390/kernel: Update /proc/sysinfo file with Extended Name and UUID
  KVM: s390: reenable LPP facility
  KVM: s390: floating irqs: fix user triggerable endless loop
  kvm: add halt_poll_ns module parameter
  kvm: remove KVM_MMIO_SIZE
  KVM: MIPS: Don't leak FPU/DSP to guest
  KVM: MIPS: Disable HTW while in guest
  KVM: nVMX: Enable nested posted interrupt processing
  KVM: nVMX: Enable nested virtual interrupt delivery
  KVM: nVMX: Enable nested apic register virtualization
  KVM: nVMX: Make nested control MSRs per-cpu
  KVM: nVMX: Enable nested virtualize x2apic mode
  KVM: nVMX: Prepare for using hardware MSR bitmap
  ...
2015-02-13 09:55:09 -08:00

309 lines
8.8 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>
/*
* As we only have 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).
*/
#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)
/*
* KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
* levels in addition to the PGD and potentially the PUD which are
* pre-allocated (we pre-allocate the fake PGD and the PUD when the Stage-2
* tables use one level of tables less than the kernel.
*/
#ifdef CONFIG_ARM64_64K_PAGES
#define KVM_MMU_CACHE_MIN_PAGES 1
#else
#define KVM_MMU_CACHE_MIN_PAGES 2
#endif
#ifdef __ASSEMBLY__
/*
* Convert a kernel VA into a HYP VA.
* reg: VA to be converted.
*/
.macro kern_hyp_va reg
and \reg, \reg, #HYP_PAGE_OFFSET_MASK
.endm
#else
#include <asm/pgalloc.h>
#include <asm/cachetype.h>
#include <asm/cacheflush.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)
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);
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 void kvm_set_s2pte_writable(pte_t *pte)
{
pte_val(*pte) |= PTE_S2_RDWR;
}
static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
{
pmd_val(*pmd) |= PMD_S2_RDWR;
}
static inline void kvm_set_s2pte_readonly(pte_t *pte)
{
pte_val(*pte) = (pte_val(*pte) & ~PTE_S2_RDWR) | 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)
{
pmd_val(*pmd) = (pmd_val(*pmd) & ~PMD_S2_RDWR) | PMD_S2_RDONLY;
}
static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
{
return (pmd_val(*pmd) & PMD_S2_RDWR) == PMD_S2_RDONLY;
}
#define kvm_pgd_addr_end(addr, end) pgd_addr_end(addr, end)
#define kvm_pud_addr_end(addr, end) pud_addr_end(addr, end)
#define kvm_pmd_addr_end(addr, end) pmd_addr_end(addr, end)
/*
* In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address
* the entire IPA input range with a single pgd entry, and we would only need
* one pgd entry. Note that in this case, the pgd is actually not used by
* the MMU for Stage-2 translations, but is merely a fake pgd used as a data
* structure for the kernel pgtable macros to work.
*/
#if PGDIR_SHIFT > KVM_PHYS_SHIFT
#define PTRS_PER_S2_PGD_SHIFT 0
#else
#define PTRS_PER_S2_PGD_SHIFT (KVM_PHYS_SHIFT - PGDIR_SHIFT)
#endif
#define PTRS_PER_S2_PGD (1 << PTRS_PER_S2_PGD_SHIFT)
#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
/*
* If we are concatenating first level stage-2 page tables, we would have less
* than or equal to 16 pointers in the fake PGD, because that's what the
* architecture allows. In this case, (4 - CONFIG_ARM64_PGTABLE_LEVELS)
* represents the first level for the host, and we add 1 to go to the next
* level (which uses contatenation) for the stage-2 tables.
*/
#if PTRS_PER_S2_PGD <= 16
#define KVM_PREALLOC_LEVEL (4 - CONFIG_ARM64_PGTABLE_LEVELS + 1)
#else
#define KVM_PREALLOC_LEVEL (0)
#endif
/**
* kvm_prealloc_hwpgd - allocate inital table for VTTBR
* @kvm: The KVM struct pointer for the VM.
* @pgd: The kernel pseudo pgd
*
* When the kernel uses more levels of page tables than the guest, we allocate
* a fake PGD and pre-populate it to point to the next-level page table, which
* will be the real initial page table pointed to by the VTTBR.
*
* When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
* the kernel will use folded pud. When KVM_PREALLOC_LEVEL==1, we
* allocate 2 consecutive PUD pages.
*/
static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
{
unsigned int i;
unsigned long hwpgd;
if (KVM_PREALLOC_LEVEL == 0)
return 0;
hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
if (!hwpgd)
return -ENOMEM;
for (i = 0; i < PTRS_PER_S2_PGD; i++) {
if (KVM_PREALLOC_LEVEL == 1)
pgd_populate(NULL, pgd + i,
(pud_t *)hwpgd + i * PTRS_PER_PUD);
else if (KVM_PREALLOC_LEVEL == 2)
pud_populate(NULL, pud_offset(pgd, 0) + i,
(pmd_t *)hwpgd + i * PTRS_PER_PMD);
}
return 0;
}
static inline void *kvm_get_hwpgd(struct kvm *kvm)
{
pgd_t *pgd = kvm->arch.pgd;
pud_t *pud;
if (KVM_PREALLOC_LEVEL == 0)
return pgd;
pud = pud_offset(pgd, 0);
if (KVM_PREALLOC_LEVEL == 1)
return pud;
BUG_ON(KVM_PREALLOC_LEVEL != 2);
return pmd_offset(pud, 0);
}
static inline void kvm_free_hwpgd(struct kvm *kvm)
{
if (KVM_PREALLOC_LEVEL > 0) {
unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
}
}
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)
#ifdef __PAGETABLE_PMD_FOLDED
#define kvm_pmd_table_empty(kvm, pmdp) (0)
#else
#define kvm_pmd_table_empty(kvm, pmdp) \
(kvm_page_empty(pmdp) && (!(kvm) || KVM_PREALLOC_LEVEL < 2))
#endif
#ifdef __PAGETABLE_PUD_FOLDED
#define kvm_pud_table_empty(kvm, pudp) (0)
#else
#define kvm_pud_table_empty(kvm, pudp) \
(kvm_page_empty(pudp) && (!(kvm) || KVM_PREALLOC_LEVEL < 1))
#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, 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);
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */