Commit 42b00f12 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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
  ...
parents 460023a5 a0aea130
......@@ -305,6 +305,9 @@ the address space for which you want to return the dirty bitmap.
They must be less than the value that KVM_CHECK_EXTENSION returns for
the KVM_CAP_MULTI_ADDRESS_SPACE capability.
The bits in the dirty bitmap are cleared before the ioctl returns, unless
KVM_CAP_MANUAL_DIRTY_LOG_PROTECT is enabled. For more information,
see the description of the capability.
4.9 KVM_SET_MEMORY_ALIAS
......@@ -1129,10 +1132,15 @@ documentation when it pops into existence).
4.37 KVM_ENABLE_CAP
Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM
Architectures: x86 (only KVM_CAP_ENABLE_CAP_VM),
mips (only KVM_CAP_ENABLE_CAP), ppc, s390
Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM)
Capability: KVM_CAP_ENABLE_CAP
Architectures: mips, ppc, s390
Type: vcpu ioctl
Parameters: struct kvm_enable_cap (in)
Returns: 0 on success; -1 on error
Capability: KVM_CAP_ENABLE_CAP_VM
Architectures: all
Type: vcpu ioctl
Parameters: struct kvm_enable_cap (in)
Returns: 0 on success; -1 on error
......@@ -3753,6 +3761,102 @@ Coalesced pio is based on coalesced mmio. There is little difference
between coalesced mmio and pio except that coalesced pio records accesses
to I/O ports.
4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_dirty_log (in)
Returns: 0 on success, -1 on error
/* for KVM_CLEAR_DIRTY_LOG */
struct kvm_clear_dirty_log {
__u32 slot;
__u32 num_pages;
__u64 first_page;
union {
void __user *dirty_bitmap; /* one bit per page */
__u64 padding;
};
};
The ioctl clears the dirty status of pages in a memory slot, according to
the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap
field. Bit 0 of the bitmap corresponds to page "first_page" in the
memory slot, and num_pages is the size in bits of the input bitmap.
Both first_page and num_pages must be a multiple of 64. For each bit
that is set in the input bitmap, the corresponding page is marked "clean"
in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
(for example via write-protection, or by clearing the dirty bit in
a page table entry).
If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
the address space for which you want to return the dirty bitmap.
They must be less than the value that KVM_CHECK_EXTENSION returns for
the KVM_CAP_MULTI_ADDRESS_SPACE capability.
This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
is enabled; for more information, see the description of the capability.
However, it can always be used as long as KVM_CHECK_EXTENSION confirms
that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT is present.
4.118 KVM_GET_SUPPORTED_HV_CPUID
Capability: KVM_CAP_HYPERV_CPUID
Architectures: x86
Type: vcpu ioctl
Parameters: struct kvm_cpuid2 (in/out)
Returns: 0 on success, -1 on error
struct kvm_cpuid2 {
__u32 nent;
__u32 padding;
struct kvm_cpuid_entry2 entries[0];
};
struct kvm_cpuid_entry2 {
__u32 function;
__u32 index;
__u32 flags;
__u32 eax;
__u32 ebx;
__u32 ecx;
__u32 edx;
__u32 padding[3];
};
This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in
KVM. Userspace can use the information returned by this ioctl to construct
cpuid information presented to guests consuming Hyper-V enlightenments (e.g.
Windows or Hyper-V guests).
CPUID feature leaves returned by this ioctl are defined by Hyper-V Top Level
Functional Specification (TLFS). These leaves can't be obtained with
KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature
leaves (0x40000000, 0x40000001).
Currently, the following list of CPUID leaves are returned:
HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
HYPERV_CPUID_INTERFACE
HYPERV_CPUID_VERSION
HYPERV_CPUID_FEATURES
HYPERV_CPUID_ENLIGHTMENT_INFO
HYPERV_CPUID_IMPLEMENT_LIMITS
HYPERV_CPUID_NESTED_FEATURES
HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was
enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
with the 'nent' field indicating the number of entries in the variable-size
array 'entries'. If the number of entries is too low to describe all Hyper-V
feature leaves, an error (E2BIG) is returned. If the number is more or equal
to the number of Hyper-V feature leaves, the 'nent' field is adjusted to the
number of valid entries in the 'entries' array, which is then filled.
'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved,
userspace should not expect to get any particular value there.
5. The kvm_run structure
------------------------
......@@ -4647,6 +4751,30 @@ and injected exceptions.
* For the new DR6 bits, note that bit 16 is set iff the #DB exception
will clear DR6.RTM.
7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
Architectures: all
Parameters: args[0] whether feature should be enabled or not
With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
clear and write-protect all pages that are returned as dirty.
Rather, userspace will have to do this operation separately using
KVM_CLEAR_DIRTY_LOG.
At the cost of a slightly more complicated operation, this provides better
scalability and responsiveness for two reasons. First,
KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64-page granularity rather
than requiring to sync a full memslot; this ensures that KVM does not
take spinlocks for an extended period of time. Second, in some cases a
large amount of time can pass between a call to KVM_GET_DIRTY_LOG and
userspace actually using the data in the page. Pages can be modified
during this time, which is inefficint for both the guest and userspace:
the guest will incur a higher penalty due to write protection faults,
while userspace can see false reports of dirty pages. Manual reprotection
helps reducing this time, improving guest performance and reducing the
number of dirty log false positives.
8. Other capabilities.
----------------------
......
......@@ -8309,6 +8309,7 @@ W: http://www.linux-kvm.org
T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
S: Supported
F: arch/x86/kvm/
F: arch/x86/kvm/*/
F: arch/x86/include/uapi/asm/kvm*
F: arch/x86/include/asm/kvm*
F: arch/x86/include/asm/pvclock-abi.h
......
......@@ -23,6 +23,10 @@
#define ARM_EXIT_WITH_ABORT_BIT 31
#define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_ABORT_BIT))
#define ARM_EXCEPTION_IS_TRAP(x) \
(ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_PREF_ABORT || \
ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_DATA_ABORT || \
ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_HVC)
#define ARM_ABORT_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_ABORT_BIT))
#define ARM_EXCEPTION_RESET 0
......
......@@ -225,7 +225,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
#define KVM_ARCH_WANT_MMU_NOTIFIER
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_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
......@@ -296,11 +296,6 @@ static inline void kvm_arm_init_debug(void) {}
static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
static inline bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu,
struct kvm_run *run)
{
return false;
}
int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
......
......@@ -82,6 +82,67 @@ void kvm_clear_hyp_idmap(void);
#define kvm_mk_pud(pmdp) __pud(__pa(pmdp) | PMD_TYPE_TABLE)
#define kvm_mk_pgd(pudp) ({ BUILD_BUG(); 0; })
#define kvm_pfn_pte(pfn, prot) pfn_pte(pfn, prot)
#define kvm_pfn_pmd(pfn, prot) pfn_pmd(pfn, prot)
#define kvm_pfn_pud(pfn, prot) (__pud(0))
#define kvm_pud_pfn(pud) ({ WARN_ON(1); 0; })
#define kvm_pmd_mkhuge(pmd) pmd_mkhuge(pmd)
/* No support for pud hugepages */
#define kvm_pud_mkhuge(pud) ( {WARN_ON(1); pud; })
/*
* The following kvm_*pud*() functions are provided strictly to allow
* sharing code with arm64. They should never be called in practice.
*/
static inline void kvm_set_s2pud_readonly(pud_t *pud)
{
WARN_ON(1);
}
static inline bool kvm_s2pud_readonly(pud_t *pud)
{
WARN_ON(1);
return false;
}
static inline void kvm_set_pud(pud_t *pud, pud_t new_pud)
{
WARN_ON(1);
}
static inline pud_t kvm_s2pud_mkwrite(pud_t pud)
{
WARN_ON(1);
return pud;
}
static inline pud_t kvm_s2pud_mkexec(pud_t pud)
{
WARN_ON(1);
return pud;
}
static inline bool kvm_s2pud_exec(pud_t *pud)
{
WARN_ON(1);
return false;
}
static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
{
BUG();
return pud;
}
static inline bool kvm_s2pud_young(pud_t pud)
{
WARN_ON(1);
return false;
}
static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
{
pte_val(pte) |= L_PTE_S2_RDWR;
......
......@@ -68,4 +68,12 @@ stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
#define stage2_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
#define stage2_pud_table_empty(kvm, pudp) false
static inline bool kvm_stage2_has_pud(struct kvm *kvm)
{
return false;
}
#define S2_PMD_MASK PMD_MASK
#define S2_PMD_SIZE PMD_SIZE
#endif /* __ARM_S2_PGTABLE_H_ */
......@@ -602,8 +602,8 @@ static int emulate_cp15(struct kvm_vcpu *vcpu,
}
} else {
/* If access function fails, it should complain. */
kvm_err("Unsupported guest CP15 access at: %08lx\n",
*vcpu_pc(vcpu));
kvm_err("Unsupported guest CP15 access at: %08lx [%08lx]\n",
*vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
print_cp_instr(params);
kvm_inject_undefined(vcpu);
}
......
......@@ -107,7 +107,7 @@
TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
/* VTCR_EL2 Registers bits */
#define VTCR_EL2_RES1 (1 << 31)
#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
......@@ -323,10 +323,6 @@
#define PAR_TO_HPFAR(par) \
(((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8)
#define kvm_arm_exception_type \
{0, "IRQ" }, \
{1, "TRAP" }
#define ECN(x) { ESR_ELx_EC_##x, #x }
#define kvm_arm_exception_class \
......
......@@ -25,6 +25,7 @@
#define ARM_EXIT_WITH_SERROR_BIT 31
#define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
#define ARM_EXCEPTION_IS_TRAP(x) (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_TRAP)
#define ARM_SERROR_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_SERROR_BIT))
#define ARM_EXCEPTION_IRQ 0
......@@ -34,6 +35,12 @@
/* The hyp-stub will return this for any kvm_call_hyp() call */
#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR
#define kvm_arm_exception_type \
{ARM_EXCEPTION_IRQ, "IRQ" }, \
{ARM_EXCEPTION_EL1_SERROR, "SERROR" }, \
{ARM_EXCEPTION_TRAP, "TRAP" }, \
{ARM_EXCEPTION_HYP_GONE, "HYP_GONE" }
#ifndef __ASSEMBLY__
#include <linux/mm.h>
......
......@@ -24,6 +24,7 @@
#include <linux/kvm_host.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_hyp.h>
......@@ -147,14 +148,6 @@ static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu)
return true;
}
static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
{
if (vcpu_mode_is_32bit(vcpu))
kvm_skip_instr32(vcpu, is_wide_instr);
else
*vcpu_pc(vcpu) += 4;
}
static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
{
*vcpu_cpsr(vcpu) |= PSR_AA32_T_BIT;
......@@ -424,4 +417,30 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
return data; /* Leave LE untouched */
}
static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
{
if (vcpu_mode_is_32bit(vcpu))
kvm_skip_instr32(vcpu, is_wide_instr);
else
*vcpu_pc(vcpu) += 4;
/* advance the singlestep state machine */
*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
}
/*
* Skip an instruction which has been emulated at hyp while most guest sysregs
* are live.
*/
static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
{
*vcpu_pc(vcpu) = read_sysreg_el2(elr);
vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr);
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr);
write_sysreg_el2(*vcpu_pc(vcpu), elr);
}
#endif /* __ARM64_KVM_EMULATE_H__ */
......@@ -319,7 +319,7 @@ struct kvm_vcpu_arch {
*/
#define __vcpu_sys_reg(v,r) ((v)->arch.ctxt.sys_regs[(r)])
u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg);
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
/*
......@@ -360,7 +360,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
#define KVM_ARCH_WANT_MMU_NOTIFIER
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_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);
......@@ -449,7 +449,6 @@ void kvm_arm_init_debug(void);
void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
......
......@@ -184,6 +184,17 @@ void kvm_clear_hyp_idmap(void);
#define kvm_mk_pgd(pudp) \
__pgd(__phys_to_pgd_val(__pa(pudp)) | PUD_TYPE_TABLE)
#define kvm_set_pud(pudp, pud) set_pud(pudp, pud)
#define kvm_pfn_pte(pfn, prot) pfn_pte(pfn, prot)
#define kvm_pfn_pmd(pfn, prot) pfn_pmd(pfn, prot)
#define kvm_pfn_pud(pfn, prot) pfn_pud(pfn, prot)
#define kvm_pud_pfn(pud) pud_pfn(pud)
#define kvm_pmd_mkhuge(pmd) pmd_mkhuge(pmd)
#define kvm_pud_mkhuge(pud) pud_mkhuge(pud)
static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
{
pte_val(pte) |= PTE_S2_RDWR;
......@@ -196,6 +207,12 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
return pmd;
}
static inline pud_t kvm_s2pud_mkwrite(pud_t pud)
{
pud_val(pud) |= PUD_S2_RDWR;
return pud;
}
static inline pte_t kvm_s2pte_mkexec(pte_t pte)
{
pte_val(pte) &= ~PTE_S2_XN;
......@@ -208,6 +225,12 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
return pmd;
}
static inline pud_t kvm_s2pud_mkexec(pud_t pud)
{
pud_val(pud) &= ~PUD_S2_XN;
return pud;
}
static inline void kvm_set_s2pte_readonly(pte_t *ptep)
{
pteval_t old_pteval, pteval;
......@@ -246,6 +269,31 @@ static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
}
static inline void kvm_set_s2pud_readonly(pud_t *pudp)
{
kvm_set_s2pte_readonly((pte_t *)pudp);
}
static inline bool kvm_s2pud_readonly(pud_t *pudp)
{
return kvm_s2pte_readonly((pte_t *)pudp);
}
static inline bool kvm_s2pud_exec(pud_t *pudp)
{
return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN);
}
static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
{
return pud_mkyoung(pud);
}
static inline bool kvm_s2pud_young(pud_t pud)
{
return pud_young(pud);
}
#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
#ifdef __PAGETABLE_PMD_FOLDED
......
......@@ -193,6 +193,10 @@
#define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */
#define PMD_S2_XN (_AT(pmdval_t, 2) << 53) /* XN[1:0] */
#define PUD_S2_RDONLY (_AT(pudval_t, 1) << 6) /* HAP[2:1] */
#define PUD_S2_RDWR (_AT(pudval_t, 3) << 6) /* HAP[2:1] */
#define PUD_S2_XN (_AT(pudval_t, 2) << 53) /* XN[1:0] */
/*
* Memory Attribute override for Stage-2 (MemAttr[3:0])
*/
......
......@@ -315,6 +315,11 @@ static inline pte_t pud_pte(pud_t pud)
return __pte(pud_val(pud));
}
static inline pud_t pte_pud(pte_t pte)
{
return __pud(pte_val(pte));
}
static inline pmd_t pud_pmd(pud_t pud)
{
return __pmd(pud_val(pud));
......@@ -382,8 +387,12 @@ static inline int pmd_protnone(pmd_t pmd)
#define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot)
#define pud_young(pud) pte_young(pud_pte(pud))
#define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud)))
#define pud_write(pud) pte_write(pud_pte(pud))
#define pud_mkhuge(pud) (__pud(pud_val(pud) & ~PUD_TABLE_BIT))
#define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud))
#define __phys_to_pud_val(phys) __phys_to_pte_val(phys)
#define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
......
......@@ -30,16 +30,14 @@
#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls))
/*
* The hardware supports concatenation of up to 16 tables at stage2 entry level
* and we use the feature whenever possible.
* The hardware supports concatenation of up to 16 tables at stage2 entry
* level and we use the feature whenever possible, which means we resolve 4
* additional bits of address at the entry level.
*
* Now, the minimum number of bits resolved at any level is (PAGE_SHIFT - 3).
* On arm64, the smallest PAGE_SIZE supported is 4k, which means
* (PAGE_SHIFT - 3) > 4 holds for all page sizes.
* This implies, the total number of page table levels at stage2 expected
* by the hardware is actually the number of levels required for (IPA_SHIFT - 4)
* in normal translations(e.g, stage1), since we cannot have another level in
* the range (IPA_SHIFT, IPA_SHIFT - 4).
* This implies, the total number of page table levels required for
* IPA_SHIFT at stage2 expected by the hardware can be calculated using
* the same logic used for the (non-collapsable) stage1 page tables but for
* (IPA_SHIFT - 4).
*/
#define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
#define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr)
......
......@@ -236,24 +236,3 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
}
}
}
/*
* After successfully emulating an instruction, we might want to
* return to user space with a KVM_EXIT_DEBUG. We can only do this
* once the emulation is complete, though, so for userspace emulations
* we have to wait until we have re-entered KVM before calling this
* helper.
*
* Return true (and set exit_reason) to return to userspace or false
* if no further action is required.
*/
bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
run->exit_reason = KVM_EXIT_DEBUG;
run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT;
return true;
}
return false;
}
......@@ -247,13 +247,6 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
handled = exit_handler(vcpu, run);
}
/*
* kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run
* structure if we need to return to userspace.
*/
if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run))
handled = 0;
return handled;
}
......@@ -287,12 +280,7 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
case ARM_EXCEPTION_IRQ:
return 1;
case ARM_EXCEPTION_EL1_SERROR:
/* We may still need to return for single-step */
if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
&& kvm_arm_handle_step_debug(vcpu, run))
return 0;
else
return 1;
return 1;
case ARM_EXCEPTION_TRAP:
return handle_trap_exceptions(vcpu, run);
case ARM_EXCEPTION_HYP_GONE:
......
......@@ -313,33 +313,6 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
return true;
}
/* Skip an instruction which has been emulated. Returns true if
* execution can continue or false if we need to exit hyp mode because
* single-step was in effect.
*/
static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)