Files
linux-stable-mirror/arch/x86/include/asm/cpuid.h
Linus Torvalds 3efc57369a Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull x86 kvm updates from Paolo Bonzini:
 "x86:

   - KVM currently invalidates the entirety of the page tables, not just
     those for the memslot being touched, when a memslot is moved or
     deleted.

     This does not traditionally have particularly noticeable overhead,
     but Intel's TDX will require the guest to re-accept private pages
     if they are dropped from the secure EPT, which is a non starter.

     Actually, the only reason why this is not already being done is a
     bug which was never fully investigated and caused VM instability
     with assigned GeForce GPUs, so allow userspace to opt into the new
     behavior.

   - Advertise AVX10.1 to userspace (effectively prep work for the
     "real" AVX10 functionality that is on the horizon)

   - Rework common MSR handling code to suppress errors on userspace
     accesses to unsupported-but-advertised MSRs

     This will allow removing (almost?) all of KVM's exemptions for
     userspace access to MSRs that shouldn't exist based on the vCPU
     model (the actual cleanup is non-trivial future work)

   - Rework KVM's handling of x2APIC ICR, again, because AMD (x2AVIC)
     splits the 64-bit value into the legacy ICR and ICR2 storage,
     whereas Intel (APICv) stores the entire 64-bit value at the ICR
     offset

   - Fix a bug where KVM would fail to exit to userspace if one was
     triggered by a fastpath exit handler

   - Add fastpath handling of HLT VM-Exit to expedite re-entering the
     guest when there's already a pending wake event at the time of the
     exit

   - Fix a WARN caused by RSM entering a nested guest from SMM with
     invalid guest state, by forcing the vCPU out of guest mode prior to
     signalling SHUTDOWN (the SHUTDOWN hits the VM altogether, not the
     nested guest)

   - Overhaul the "unprotect and retry" logic to more precisely identify
     cases where retrying is actually helpful, and to harden all retry
     paths against putting the guest into an infinite retry loop

   - Add support for yielding, e.g. to honor NEED_RESCHED, when zapping
     rmaps in the shadow MMU

   - Refactor pieces of the shadow MMU related to aging SPTEs in
     prepartion for adding multi generation LRU support in KVM

   - Don't stuff the RSB after VM-Exit when RETPOLINE=y and AutoIBRS is
     enabled, i.e. when the CPU has already flushed the RSB

   - Trace the per-CPU host save area as a VMCB pointer to improve
     readability and cleanup the retrieval of the SEV-ES host save area

   - Remove unnecessary accounting of temporary nested VMCB related
     allocations

   - Set FINAL/PAGE in the page fault error code for EPT violations if
     and only if the GVA is valid. If the GVA is NOT valid, there is no
     guest-side page table walk and so stuffing paging related metadata
     is nonsensical

   - Fix a bug where KVM would incorrectly synthesize a nested VM-Exit
     instead of emulating posted interrupt delivery to L2

   - Add a lockdep assertion to detect unsafe accesses of vmcs12
     structures

   - Harden eVMCS loading against an impossible NULL pointer deref
     (really truly should be impossible)

   - Minor SGX fix and a cleanup

   - Misc cleanups

  Generic:

   - Register KVM's cpuhp and syscore callbacks when enabling
     virtualization in hardware, as the sole purpose of said callbacks
     is to disable and re-enable virtualization as needed

   - Enable virtualization when KVM is loaded, not right before the
     first VM is created

     Together with the previous change, this simplifies a lot the logic
     of the callbacks, because their very existence implies
     virtualization is enabled

   - Fix a bug that results in KVM prematurely exiting to userspace for
     coalesced MMIO/PIO in many cases, clean up the related code, and
     add a testcase

   - Fix a bug in kvm_clear_guest() where it would trigger a buffer
     overflow _if_ the gpa+len crosses a page boundary, which thankfully
     is guaranteed to not happen in the current code base. Add WARNs in
     more helpers that read/write guest memory to detect similar bugs

  Selftests:

   - Fix a goof that caused some Hyper-V tests to be skipped when run on
     bare metal, i.e. NOT in a VM

   - Add a regression test for KVM's handling of SHUTDOWN for an SEV-ES
     guest

   - Explicitly include one-off assets in .gitignore. Past Sean was
     completely wrong about not being able to detect missing .gitignore
     entries

   - Verify userspace single-stepping works when KVM happens to handle a
     VM-Exit in its fastpath

   - Misc cleanups"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (127 commits)
  Documentation: KVM: fix warning in "make htmldocs"
  s390: Enable KVM_S390_UCONTROL config in debug_defconfig
  selftests: kvm: s390: Add VM run test case
  KVM: SVM: let alternatives handle the cases when RSB filling is required
  KVM: VMX: Set PFERR_GUEST_{FINAL,PAGE}_MASK if and only if the GVA is valid
  KVM: x86/mmu: Use KVM_PAGES_PER_HPAGE() instead of an open coded equivalent
  KVM: x86/mmu: Add KVM_RMAP_MANY to replace open coded '1' and '1ul' literals
  KVM: x86/mmu: Fold mmu_spte_age() into kvm_rmap_age_gfn_range()
  KVM: x86/mmu: Morph kvm_handle_gfn_range() into an aging specific helper
  KVM: x86/mmu: Honor NEED_RESCHED when zapping rmaps and blocking is allowed
  KVM: x86/mmu: Add a helper to walk and zap rmaps for a memslot
  KVM: x86/mmu: Plumb a @can_yield parameter into __walk_slot_rmaps()
  KVM: x86/mmu: Move walk_slot_rmaps() up near for_each_slot_rmap_range()
  KVM: x86/mmu: WARN on MMIO cache hit when emulating write-protected gfn
  KVM: x86/mmu: Detect if unprotect will do anything based on invalid_list
  KVM: x86/mmu: Subsume kvm_mmu_unprotect_page() into the and_retry() version
  KVM: x86: Rename reexecute_instruction()=>kvm_unprotect_and_retry_on_failure()
  KVM: x86: Update retry protection fields when forcing retry on emulation failure
  KVM: x86: Apply retry protection to "unprotect on failure" path
  KVM: x86: Check EMULTYPE_WRITE_PF_TO_SP before unprotecting gfn
  ...
2024-09-28 09:20:14 -07:00

214 lines
4.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* CPUID-related helpers/definitions
*/
#ifndef _ASM_X86_CPUID_H
#define _ASM_X86_CPUID_H
#include <asm/string.h>
struct cpuid_regs {
u32 eax, ebx, ecx, edx;
};
enum cpuid_regs_idx {
CPUID_EAX = 0,
CPUID_EBX,
CPUID_ECX,
CPUID_EDX,
};
#ifdef CONFIG_X86_32
extern int have_cpuid_p(void);
#else
static inline int have_cpuid_p(void)
{
return 1;
}
#endif
static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
/* ecx is often an input as well as an output. */
asm volatile("cpuid"
: "=a" (*eax),
"=b" (*ebx),
"=c" (*ecx),
"=d" (*edx)
: "0" (*eax), "2" (*ecx)
: "memory");
}
#define native_cpuid_reg(reg) \
static inline unsigned int native_cpuid_##reg(unsigned int op) \
{ \
unsigned int eax = op, ebx, ecx = 0, edx; \
\
native_cpuid(&eax, &ebx, &ecx, &edx); \
\
return reg; \
}
/*
* Native CPUID functions returning a single datum.
*/
native_cpuid_reg(eax)
native_cpuid_reg(ebx)
native_cpuid_reg(ecx)
native_cpuid_reg(edx)
#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#define __cpuid native_cpuid
#endif
/*
* Generic CPUID function
* clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
* resulting in stale register contents being returned.
*/
static inline void cpuid(unsigned int op,
unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
*eax = op;
*ecx = 0;
__cpuid(eax, ebx, ecx, edx);
}
/* Some CPUID calls want 'count' to be placed in ecx */
static inline void cpuid_count(unsigned int op, int count,
unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
*eax = op;
*ecx = count;
__cpuid(eax, ebx, ecx, edx);
}
/*
* CPUID functions returning a single datum
*/
static inline unsigned int cpuid_eax(unsigned int op)
{
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
return eax;
}
static inline unsigned int cpuid_ebx(unsigned int op)
{
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
return ebx;
}
static inline unsigned int cpuid_ecx(unsigned int op)
{
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
return ecx;
}
static inline unsigned int cpuid_edx(unsigned int op)
{
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
return edx;
}
static inline void __cpuid_read(unsigned int leaf, unsigned int subleaf, u32 *regs)
{
regs[CPUID_EAX] = leaf;
regs[CPUID_ECX] = subleaf;
__cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX);
}
#define cpuid_subleaf(leaf, subleaf, regs) { \
static_assert(sizeof(*(regs)) == 16); \
__cpuid_read(leaf, subleaf, (u32 *)(regs)); \
}
#define cpuid_leaf(leaf, regs) { \
static_assert(sizeof(*(regs)) == 16); \
__cpuid_read(leaf, 0, (u32 *)(regs)); \
}
static inline void __cpuid_read_reg(unsigned int leaf, unsigned int subleaf,
enum cpuid_regs_idx regidx, u32 *reg)
{
u32 regs[4];
__cpuid_read(leaf, subleaf, regs);
*reg = regs[regidx];
}
#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) { \
static_assert(sizeof(*(reg)) == 4); \
__cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg)); \
}
#define cpuid_leaf_reg(leaf, regidx, reg) { \
static_assert(sizeof(*(reg)) == 4); \
__cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg)); \
}
static __always_inline bool cpuid_function_is_indexed(u32 function)
{
switch (function) {
case 4:
case 7:
case 0xb:
case 0xd:
case 0xf:
case 0x10:
case 0x12:
case 0x14:
case 0x17:
case 0x18:
case 0x1d:
case 0x1e:
case 0x1f:
case 0x24:
case 0x8000001d:
return true;
}
return false;
}
#define for_each_possible_hypervisor_cpuid_base(function) \
for (function = 0x40000000; function < 0x40010000; function += 0x100)
static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
{
uint32_t base, eax, signature[3];
for_each_possible_hypervisor_cpuid_base(base) {
cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
/*
* This must not compile to "call memcmp" because it's called
* from PVH early boot code before instrumentation is set up
* and memcmp() itself may be instrumented.
*/
if (!__builtin_memcmp(sig, signature, 12) &&
(leaves == 0 || ((eax - base) >= leaves)))
return base;
}
return 0;
}
#endif /* _ASM_X86_CPUID_H */