diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-12 14:18:44 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-12 14:18:44 -0800 |
| commit | 2da68a77b940722b04c2f7604a758eab46cf6cf9 (patch) | |
| tree | 0804deaffa7a891a648433287082a2fd9461b0a1 /arch/x86/kvm/cpuid.c | |
| parent | c1f0fcd85d3d66f002fc1a4986363840fcca766d (diff) | |
| parent | 89e927bbcd45d507e5612ef72fda04182e544a38 (diff) | |
| download | linux-2da68a77b940722b04c2f7604a758eab46cf6cf9.tar.bz2 | |
Merge tag 'x86_sgx_for_6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 sgx updates from Dave Hansen:
"The biggest deal in this series is support for a new hardware feature
that allows enclaves to detect and mitigate single-stepping attacks.
There's also a minor performance tweak and a little piece of the
kmap_atomic() -> kmap_local() transition.
Summary:
- Introduce a new SGX feature (Asynchrounous Exit Notification) for
bare-metal enclaves and KVM guests to mitigate single-step attacks
- Increase batching to speed up enclave release
- Replace kmap/kunmap_atomic() calls"
* tag 'x86_sgx_for_6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/sgx: Replace kmap/kunmap_atomic() calls
KVM/VMX: Allow exposing EDECCSSA user leaf function to KVM guest
x86/sgx: Allow enclaves to use Asynchrounous Exit Notification
x86/sgx: Reduce delay and interference of enclave release
Diffstat (limited to 'arch/x86/kvm/cpuid.c')
| -rw-r--r-- | arch/x86/kvm/cpuid.c | 6 |
1 files changed, 2 insertions, 4 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 62bc7a01cecc..c92c49a0b35b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -665,7 +665,7 @@ void kvm_set_cpu_caps(void) ); kvm_cpu_cap_init_scattered(CPUID_12_EAX, - SF(SGX1) | SF(SGX2) + SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA) ); kvm_cpu_cap_mask(CPUID_8000_0001_ECX, @@ -1047,9 +1047,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * userspace. ATTRIBUTES.XFRM is not adjusted as userspace is * expected to derive it from supported XCR0. */ - entry->eax &= SGX_ATTR_DEBUG | SGX_ATTR_MODE64BIT | - SGX_ATTR_PROVISIONKEY | SGX_ATTR_EINITTOKENKEY | - SGX_ATTR_KSS; + entry->eax &= SGX_ATTR_PRIV_MASK | SGX_ATTR_UNPRIV_MASK; entry->ebx &= 0; break; /* Intel PT */ |