This is a backport of the CR0.WP KVM series[1] to Linux v5.10. It further extends the v5.15 backport by two patches, namely patch 5 (which is the prerequisite for Lai's patches) and patch 8 which was already part of the v5.15.27 stable update but didn't made it to v5.10.
I used 'ssdd 10 50000' from rt-tests[2] as a micro-benchmark, running on a grsecurity L1 VM. Below table shows the results (runtime in seconds, lower is better):
legacy TDP shadow Linux v5.10.177 10.37s 88.7s 69.7s + patches 4.88s 4.92s 70.1s
TDP MMU is, as for v5.15, slower than shadow paging on a vanilla kernel. Fortunately it's disabled by default.
The KVM unit test suite showed no regressions.
Please consider applying.
Thanks, Mathias
[1] https://lore.kernel.org/kvm/20230322013731.102955-1-minipli@grsecurity.net/ [2] https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git
Lai Jiangshan (4): KVM: X86: Don't reset mmu context when X86_CR4_PCIDE 1->0 KVM: X86: Don't reset mmu context when toggling X86_CR4_PGE KVM: X86: Ensure that dirty PDPTRs are loaded KVM: x86/mmu: Reconstruct shadow page root if the guest PDPTEs is changed
Mathias Krause (3): KVM: x86: Do not unload MMU roots when only toggling CR0.WP with TDP enabled KVM: x86: Make use of kvm_read_cr*_bits() when testing bits KVM: VMX: Make CR0.WP a guest owned bit
Paolo Bonzini (1): KVM: x86/mmu: Avoid indirect call for get_cr3
Sean Christopherson (2): KVM: x86: Read and pass all CR0/CR4 role bits to shadow MMU helper KVM: x86/mmu: Refresh CR0.WP prior to checking for emulated permission faults
arch/x86/kvm/kvm_cache_regs.h | 2 +- arch/x86/kvm/mmu.h | 42 +++++++++++++++++++++++++++++++++- arch/x86/kvm/mmu/mmu.c | 32 +++++++++++++++++++------- arch/x86/kvm/mmu/paging_tmpl.h | 2 +- arch/x86/kvm/pmu.c | 4 ++-- arch/x86/kvm/vmx/nested.c | 4 ++-- arch/x86/kvm/vmx/vmx.c | 6 ++--- arch/x86/kvm/vmx/vmx.h | 18 +++++++++++++++ arch/x86/kvm/x86.c | 32 +++++++++++++++++++++----- 9 files changed, 118 insertions(+), 24 deletions(-)
From: Paolo Bonzini pbonzini@redhat.com
[ Upstream commit 2fdcc1b324189b5fb20655baebd40cd82e2bdf0c ]
Most of the time, calls to get_guest_pgd result in calling kvm_read_cr3 (the exception is only nested TDP). Hardcode the default instead of using the get_cr3 function, avoiding a retpoline if they are enabled.
Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Mathias Krause minipli@grsecurity.net Link: https://lore.kernel.org/r/20230322013731.102955-2-minipli@grsecurity.net Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- arch/x86/kvm/mmu.h | 11 +++++++++++ arch/x86/kvm/mmu/mmu.c | 12 ++++++------ arch/x86/kvm/mmu/paging_tmpl.h | 2 +- arch/x86/kvm/x86.c | 2 +- 4 files changed, 19 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 581925e476d6..dcbd882545b4 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -99,6 +99,17 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) vcpu->arch.mmu->shadow_root_level); }
+unsigned long get_guest_cr3(struct kvm_vcpu *vcpu); + +static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) + return kvm_read_cr3(vcpu); + + return mmu->get_guest_pgd(vcpu); +} + int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 13bf3198d0ce..da9e7cea475a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3278,7 +3278,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) hpa_t root; int i;
- root_pgd = vcpu->arch.mmu->get_guest_pgd(vcpu); + root_pgd = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu); root_gfn = root_pgd >> PAGE_SHIFT;
if (mmu_check_root(vcpu, root_gfn)) @@ -3652,7 +3652,7 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, arch.token = alloc_apf_token(vcpu); arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->direct_map; - arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); + arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu);
return kvm_setup_async_pf(vcpu, cr2_or_gpa, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); @@ -3934,7 +3934,7 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush, } EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
-static unsigned long get_cr3(struct kvm_vcpu *vcpu) +unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) { return kvm_read_cr3(vcpu); } @@ -4523,7 +4523,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->invlpg = NULL; context->shadow_root_level = kvm_mmu_get_tdp_level(vcpu); context->direct_map = true; - context->get_guest_pgd = get_cr3; + context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault;
@@ -4718,7 +4718,7 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu) kvm_read_cr4_bits(vcpu, X86_CR4_PAE), vcpu->arch.efer);
- context->get_guest_pgd = get_cr3; + context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; } @@ -4756,7 +4756,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) return;
g_context->mmu_role.as_u64 = new_role.as_u64; - g_context->get_guest_pgd = get_cr3; + g_context->get_guest_pgd = get_guest_cr3; g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault;
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index c6daeeff1d9c..3d84fc56caca 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -330,7 +330,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, trace_kvm_mmu_pagetable_walk(addr, access); retry_walk: walker->level = mmu->root_level; - pte = mmu->get_guest_pgd(vcpu); + pte = kvm_mmu_get_guest_pgd(vcpu, mmu); have_ad = PT_HAVE_ACCESSED_DIRTY(mmu);
#if PTTYPE == 64 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0ccc8d1b972c..7464ca3806fa 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11080,7 +11080,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) return;
if (!vcpu->arch.mmu->direct_map && - work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu)) + work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu)) return;
kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
[ Upstream commit 01b31714bd90be2784f7145bf93b7f78f3d081e1 ]
There is no need to unload the MMU roots with TDP enabled when only CR0.WP has changed -- the paging structures are still valid, only the permission bitmap needs to be updated.
One heavy user of toggling CR0.WP is grsecurity's KERNEXEC feature to implement kernel W^X.
The optimization brings a huge performance gain for this case as the following micro-benchmark running 'ssdd 10 50000' from rt-tests[1] on a grsecurity L1 VM shows (runtime in seconds, lower is better):
legacy TDP shadow kvm-x86/next@d8708b 8.43s 9.45s 70.3s +patch 5.39s 5.63s 70.2s
For legacy MMU this is ~36% faster, for TDP MMU even ~40% faster. Also TDP and legacy MMU now both have a similar runtime which vanishes the need to disable TDP MMU for grsecurity.
Shadow MMU sees no measurable difference and is still slow, as expected.
[1] https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git
Signed-off-by: Mathias Krause minipli@grsecurity.net Link: https://lore.kernel.org/r/20230322013731.102955-3-minipli@grsecurity.net Co-developed-by: Sean Christopherson seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- - account for different kvm_init_mmu() arguments
arch/x86/kvm/x86.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7464ca3806fa..bd4d64c1bdf9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -868,6 +868,18 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
kvm_x86_ops.set_cr0(vcpu, cr0);
+ /* + * CR0.WP is incorporated into the MMU role, but only for non-nested, + * indirect shadow MMUs. If TDP is enabled, the MMU's metadata needs + * to be updated, e.g. so that emulating guest translations does the + * right thing, but there's no need to unload the root as CR0.WP + * doesn't affect SPTEs. + */ + if (tdp_enabled && (cr0 ^ old_cr0) == X86_CR0_WP) { + kvm_init_mmu(vcpu, false); + return 0; + } + if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu);
[ Upstream commit 74cdc836919bf34684ef66f995273f35e2189daf ]
Make use of the kvm_read_cr{0,4}_bits() helper functions when we only want to know the state of certain bits instead of the whole register.
This not only makes the intent cleaner, it also avoids a potential VMREAD in case the tested bits aren't guest owned.
Signed-off-by: Mathias Krause minipli@grsecurity.net Link: https://lore.kernel.org/r/20230322013731.102955-5-minipli@grsecurity.net Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- arch/x86/kvm/pmu.c | 4 ++-- arch/x86/kvm/vmx/vmx.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index e5322a0dc5bb..5b494564faa2 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -374,9 +374,9 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (!pmc) return 1;
- if (!(kvm_read_cr4(vcpu) & X86_CR4_PCE) && + if (!kvm_read_cr4_bits(vcpu, X86_CR4_PCE) && (kvm_x86_ops.get_cpl(vcpu) != 0) && - (kvm_read_cr0(vcpu) & X86_CR0_PE)) + kvm_read_cr0_bits(vcpu, X86_CR0_PE)) return 1;
*data = pmc_read_counter(pmc) & mask; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 2c5d8b9f9873..db769fc68378 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5180,7 +5180,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) break; case 3: /* lmsw */ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; - trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val); + trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val)); kvm_lmsw(vcpu, val);
return kvm_skip_emulated_instruction(vcpu); @@ -7212,7 +7212,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) goto exit; }
- if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { ipat = VMX_EPT_IPAT_BIT; if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cache = MTRR_TYPE_WRBACK;
[ Upstream commit fb509f76acc8d42bed11bca308404f81c2be856a ]
Guests like grsecurity that make heavy use of CR0.WP to implement kernel level W^X will suffer from the implied VMEXITs.
With EPT there is no need to intercept a guest change of CR0.WP, so simply make it a guest owned bit if we can do so.
This implies that a read of a guest's CR0.WP bit might need a VMREAD. However, the only potentially affected user seems to be kvm_init_mmu() which is a heavy operation to begin with. But also most callers already cache the full value of CR0 anyway, so no additional VMREAD is needed. The only exception is nested_vmx_load_cr3().
This change is VMX-specific, as SVM has no such fine grained control register intercept control.
Suggested-by: Sean Christopherson seanjc@google.com Signed-off-by: Mathias Krause minipli@grsecurity.net Link: https://lore.kernel.org/r/20230322013731.102955-7-minipli@grsecurity.net Co-developed-by: Sean Christopherson seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- arch/x86/kvm/kvm_cache_regs.h | 2 +- arch/x86/kvm/vmx/nested.c | 4 ++-- arch/x86/kvm/vmx/vmx.c | 2 +- arch/x86/kvm/vmx/vmx.h | 18 ++++++++++++++++++ 4 files changed, 22 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index a889563ad02d..4471aa86270a 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -4,7 +4,7 @@
#include <linux/kvm_host.h>
-#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS +#define KVM_POSSIBLE_CR0_GUEST_BITS (X86_CR0_TS | X86_CR0_WP) #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index c165ddbb672f..5ddb177dd40d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4247,7 +4247,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs12->host_cr0);
/* Same as above - no reason to call set_cr4_guest_host_mask(). */ @@ -4397,7 +4397,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
- vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index db769fc68378..ff36d93b2552 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4456,7 +4456,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl());
- vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits);
set_cr4_guest_host_mask(vmx); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index ed4b6da83aa8..28210741fd08 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -447,6 +447,24 @@ static inline u32 vmx_vmexit_ctrl(void) u32 vmx_exec_control(struct vcpu_vmx *vmx); u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx);
+static inline unsigned long vmx_l1_guest_owned_cr0_bits(void) +{ + unsigned long bits = KVM_POSSIBLE_CR0_GUEST_BITS; + + /* + * CR0.WP needs to be intercepted when KVM is shadowing legacy paging + * in order to construct shadow PTEs with the correct protections. + * Note! CR0.WP technically can be passed through to the guest if + * paging is disabled, but checking CR0.PG would generate a cyclical + * dependency of sorts due to forcing the caller to ensure CR0 holds + * the correct value prior to determining which CR0 bits can be owned + * by L1. Keep it simple and limit the optimization to EPT. + */ + if (!enable_ept) + bits &= ~X86_CR0_WP; + return bits; +} + static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { return container_of(kvm, struct kvm_vmx, kvm);
From: Sean Christopherson seanjc@google.com
[ Upstream commit 20f632bd0060e12fca083adc44b097231e2f4649 ]
Grab all CR0/CR4 MMU role bits from current vCPU state when initializing a non-nested shadow MMU. Extract the masks from kvm_post_set_cr{0,4}(), as the CR0/CR4 update masks must exactly match the mmu_role bits, with one exception (see below). The "full" CR0/CR4 will be used by future commits to initialize the MMU and its role, as opposed to the current approach of pulling everything from vCPU, which is incorrect for certain flows, e.g. nested NPT.
CR4.LA57 is an exception, as it can be toggled on VM-Exit (for L1's MMU) but can't be toggled via MOV CR4 while long mode is active. I.e. LA57 needs to be in the mmu_role, but technically doesn't need to be checked by kvm_post_set_cr4(). However, the extra check is completely benign as the hardware restrictions simply mean LA57 will never be _the_ cause of a MMU reset during MOV CR4.
Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20210622175739.3610207-18-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- - prerequisite for Lai Jiangshan's follow-up patches - only visible change is that changes to CR4.SMEP and CR4.LA57 are taken into account as well now to trigger a MMU reset in kvm_set_cr4()
arch/x86/kvm/mmu.h | 6 ++++++ arch/x86/kvm/mmu/mmu.c | 4 ++-- arch/x86/kvm/x86.c | 6 ++---- 3 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index dcbd882545b4..0d73e8b45642 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -44,6 +44,12 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3
+#define KVM_MMU_CR4_ROLE_BITS (X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | \ + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE | \ + X86_CR4_LA57) + +#define KVM_MMU_CR0_ROLE_BITS (X86_CR0_PG | X86_CR0_WP) + static inline u64 rsvd_bits(int s, int e) { if (e < s) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index da9e7cea475a..e1107723ffdc 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4714,8 +4714,8 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu) struct kvm_mmu *context = &vcpu->arch.root_mmu;
kvm_init_shadow_mmu(vcpu, - kvm_read_cr0_bits(vcpu, X86_CR0_PG), - kvm_read_cr4_bits(vcpu, X86_CR4_PAE), + kvm_read_cr0_bits(vcpu, KVM_MMU_CR0_ROLE_BITS), + kvm_read_cr4_bits(vcpu, KVM_MMU_CR4_ROLE_BITS), vcpu->arch.efer);
context->get_guest_pgd = get_guest_cr3; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bd4d64c1bdf9..d6bb2c300e16 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -829,7 +829,6 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG; - unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;
cr0 |= X86_CR0_ET;
@@ -885,7 +884,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) kvm_async_pf_hash_reset(vcpu); }
- if ((cr0 ^ old_cr0) & update_bits) + if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) kvm_mmu_reset_context(vcpu);
if (((cr0 ^ old_cr0) & X86_CR0_CD) && @@ -1017,7 +1016,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP; - unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -1044,7 +1042,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
kvm_x86_ops.set_cr4(vcpu, cr4);
- if (((cr4 ^ old_cr4) & mmu_role_bits) || + if (((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu);
From: Lai Jiangshan laijs@linux.alibaba.com
[ Upstream commit 552617382c197949ff965a3559da8952bf3c1fa5 ]
X86_CR4_PCIDE doesn't participate in kvm_mmu_role, so the mmu context doesn't need to be reset. It is only required to flush all the guest tlb.
Signed-off-by: Lai Jiangshan laijs@linux.alibaba.com Reviewed-by: Sean Christopherson seanjc@google.com Message-Id: 20210919024246.89230-2-jiangshanlai@gmail.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- - no kvm_post_set_cr4() in this kernel yet, it's part of kvm_set_cr4()
arch/x86/kvm/x86.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d6bb2c300e16..952281f18987 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1042,9 +1042,10 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
kvm_x86_ops.set_cr4(vcpu, cr4);
- if (((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) || - (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) + if ((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) kvm_mmu_reset_context(vcpu); + else if (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)) + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) kvm_update_cpuid_runtime(vcpu);
From: Lai Jiangshan laijs@linux.alibaba.com
[ Upstream commit a91a7c7096005113d8e749fd8dfdd3e1eecee263 ]
X86_CR4_PGE doesn't participate in kvm_mmu_role, so the mmu context doesn't need to be reset. It is only required to flush all the guest tlb.
It is also inconsistent that X86_CR4_PGE is in KVM_MMU_CR4_ROLE_BITS while kvm_mmu_role doesn't use X86_CR4_PGE. So X86_CR4_PGE is also removed from KVM_MMU_CR4_ROLE_BITS.
Signed-off-by: Lai Jiangshan laijs@linux.alibaba.com Reviewed-by: Sean Christopherson seanjc@google.com Message-Id: 20210919024246.89230-3-jiangshanlai@gmail.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- - no kvm_post_set_cr4() in this kernel yet, it's part of kvm_set_cr4()
arch/x86/kvm/mmu.h | 5 ++--- arch/x86/kvm/x86.c | 3 ++- 2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 0d73e8b45642..a77f6acb46f6 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -44,9 +44,8 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3
-#define KVM_MMU_CR4_ROLE_BITS (X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | \ - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE | \ - X86_CR4_LA57) +#define KVM_MMU_CR4_ROLE_BITS (X86_CR4_PSE | X86_CR4_PAE | X86_CR4_LA57 | \ + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE)
#define KVM_MMU_CR0_ROLE_BITS (X86_CR0_PG | X86_CR0_WP)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 952281f18987..b2378ec80305 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1044,7 +1044,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
if ((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) kvm_mmu_reset_context(vcpu); - else if (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)) + else if (((cr4 ^ old_cr4) & X86_CR4_PGE) || + (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
From: Lai Jiangshan laijs@linux.alibaba.com
[ Upstream commit 2c5653caecc4807b8abfe9c41880ac38417be7bf ]
For VMX with EPT, dirty PDPTRs need to be loaded before the next vmentry via vmx_load_mmu_pgd()
But not all paths that call load_pdptrs() will cause vmx_load_mmu_pgd() to be invoked. Normally, kvm_mmu_reset_context() is used to cause KVM_REQ_LOAD_MMU_PGD, but sometimes it is skipped:
* commit d81135a57aa6("KVM: x86: do not reset mmu if CR0.CD and CR0.NW are changed") skips kvm_mmu_reset_context() after load_pdptrs() when changing CR0.CD and CR0.NW.
* commit 21823fbda552("KVM: x86: Invalidate all PGDs for the current PCID on MOV CR3 w/ flush") skips KVM_REQ_LOAD_MMU_PGD after load_pdptrs() when rewriting the CR3 with the same value.
* commit a91a7c709600("KVM: X86: Don't reset mmu context when toggling X86_CR4_PGE") skips kvm_mmu_reset_context() after load_pdptrs() when changing CR4.PGE.
Fixes: d81135a57aa6 ("KVM: x86: do not reset mmu if CR0.CD and CR0.NW are changed") Fixes: 21823fbda552 ("KVM: x86: Invalidate all PGDs for the current PCID on MOV CR3 w/ flush") Fixes: a91a7c709600 ("KVM: X86: Don't reset mmu context when toggling X86_CR4_PGE") Signed-off-by: Lai Jiangshan laijs@linux.alibaba.com Message-Id: 20211108124407.12187-2-jiangshanlai@gmail.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b2378ec80305..038ac5bbdd19 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -794,6 +794,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu);
out:
From: Lai Jiangshan laijs@linux.alibaba.com
[ Upstream commit 6b123c3a89a90ac6418e4d64b1e23f09d458a77d ]
For shadow paging, the page table needs to be reconstructed before the coming VMENTER if the guest PDPTEs is changed.
But not all paths that call load_pdptrs() will cause the page tables to be reconstructed. Normally, kvm_mmu_reset_context() and kvm_mmu_free_roots() are used to launch later reconstruction.
The commit d81135a57aa6("KVM: x86: do not reset mmu if CR0.CD and CR0.NW are changed") skips kvm_mmu_reset_context() after load_pdptrs() when changing CR0.CD and CR0.NW.
The commit 21823fbda552("KVM: x86: Invalidate all PGDs for the current PCID on MOV CR3 w/ flush") skips kvm_mmu_free_roots() after load_pdptrs() when rewriting the CR3 with the same value.
The commit a91a7c709600("KVM: X86: Don't reset mmu context when toggling X86_CR4_PGE") skips kvm_mmu_reset_context() after load_pdptrs() when changing CR4.PGE.
Guests like linux would keep the PDPTEs unchanged for every instance of pagetable, so this missing reconstruction has no problem for linux guests.
Fixes: d81135a57aa6("KVM: x86: do not reset mmu if CR0.CD and CR0.NW are changed") Fixes: 21823fbda552("KVM: x86: Invalidate all PGDs for the current PCID on MOV CR3 w/ flush") Fixes: a91a7c709600("KVM: X86: Don't reset mmu context when toggling X86_CR4_PGE") Suggested-by: Sean Christopherson seanjc@google.com Signed-off-by: Lai Jiangshan laijs@linux.alibaba.com Message-Id: 20211216021938.11752-3-jiangshanlai@gmail.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Mathias Krause minipli@grsecurity.net --- arch/x86/kvm/x86.c | 7 +++++++ 1 file changed, 7 insertions(+)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 038ac5bbdd19..065e1a5b3b94 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -792,6 +792,13 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } ret = 1;
+ /* + * Marking VCPU_EXREG_PDPTR dirty doesn't work for !tdp_enabled. + * Shadow page roots need to be reconstructed instead. + */ + if (!tdp_enabled && memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs))) + kvm_mmu_free_roots(vcpu, mmu, KVM_MMU_ROOT_CURRENT); + memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu);
From: Sean Christopherson seanjc@google.com
[ Upstream commit cf9f4c0eb1699d306e348b1fd0225af7b2c282d3 ]
Refresh the MMU's snapshot of the vCPU's CR0.WP prior to checking for permission faults when emulating a guest memory access and CR0.WP may be guest owned. If the guest toggles only CR0.WP and triggers emulation of a supervisor write, e.g. when KVM is emulating UMIP, KVM may consume a stale CR0.WP, i.e. use stale protection bits metadata.
Note, KVM passes through CR0.WP if and only if EPT is enabled as CR0.WP is part of the MMU role for legacy shadow paging, and SVM (NPT) doesn't support per-bit interception controls for CR0. Don't bother checking for EPT vs. NPT as the "old == new" check will always be true under NPT, i.e. the only cost is the read of vcpu->arch.cr4 (SVM unconditionally grabs CR0 from the VMCB on VM-Exit).
Reported-by: Mathias Krause minipli@grsecurity.net Link: https://lkml.kernel.org/r/677169b4-051f-fcae-756b-9a3e1bb9f8fe%40grsecurity.... Fixes: fb509f76acc8 ("KVM: VMX: Make CR0.WP a guest owned bit") Tested-by: Mathias Krause minipli@grsecurity.net Link: https://lore.kernel.org/r/20230405002608.418442-1-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.10.x --- - this kernel lacks the MMU role bits access helpers, so I simply open coded them - it also has "historic" ones for vCPU ones, like is_write_protection() - no reset_guest_paging_metadata() yet either, so I open-coded its v5.10 pendant as well
arch/x86/kvm/mmu.h | 26 +++++++++++++++++++++++++- arch/x86/kvm/mmu/mmu.c | 16 ++++++++++++++++ 2 files changed, 41 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index a77f6acb46f6..ee4dd4eb7c1c 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -70,6 +70,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); +void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu);
static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { @@ -171,6 +173,24 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu) return kvm_read_cr0_bits(vcpu, X86_CR0_WP); }
+static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + /* + * When EPT is enabled, KVM may passthrough CR0.WP to the guest, i.e. + * @mmu's snapshot of CR0.WP and thus all related paging metadata may + * be stale. Refresh CR0.WP and the metadata on-demand when checking + * for permission faults. Exempt nested MMUs, i.e. MMUs for shadowing + * nEPT and nNPT, as CR0.WP is ignored in both cases. Note, KVM does + * need to refresh nested_mmu, a.k.a. the walker used to translate L2 + * GVAs to GPAs, as that "MMU" needs to honor L2's CR0.WP. + */ + if (!tdp_enabled || mmu == &vcpu->arch.guest_mmu) + return; + + __kvm_mmu_refresh_passthrough_bits(vcpu, mmu); +} + /* * Check if a given access (described through the I/D, W/R and U/S bits of a * page fault error code pfec) causes a permission fault with the given PTE @@ -202,8 +222,12 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long smap = (cpl - 3) & (rflags & X86_EFLAGS_AC); int index = (pfec >> 1) + (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1)); - bool fault = (mmu->permissions[index] >> pte_access) & 1; u32 errcode = PFERR_PRESENT_MASK; + bool fault; + + kvm_mmu_refresh_passthrough_bits(vcpu, mmu); + + fault = (mmu->permissions[index] >> pte_access) & 1;
WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK)); if (unlikely(mmu->pkru_mask)) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e1107723ffdc..a17f222b628e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4486,6 +4486,22 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu, return role; }
+void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + const bool cr0_wp = is_write_protection(vcpu); + + BUILD_BUG_ON((KVM_MMU_CR0_ROLE_BITS & KVM_POSSIBLE_CR0_GUEST_BITS) != X86_CR0_WP); + BUILD_BUG_ON((KVM_MMU_CR4_ROLE_BITS & KVM_POSSIBLE_CR4_GUEST_BITS)); + + if (mmu->mmu_role.base.cr0_wp == cr0_wp) + return; + + mmu->mmu_role.base.cr0_wp = cr0_wp; + update_permission_bitmask(vcpu, mmu, false); + update_pkru_bitmask(vcpu, mmu, false); +} + static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) { /* Use 5-level TDP if and only if it's useful/necessary. */
On Mon, May 08, 2023, Mathias Krause wrote:
This is a backport of the CR0.WP KVM series[1] to Linux v5.10. It further extends the v5.15 backport by two patches, namely patch 5 (which is the prerequisite for Lai's patches) and patch 8 which was already part of the v5.15.27 stable update but didn't made it to v5.10.
I used 'ssdd 10 50000' from rt-tests[2] as a micro-benchmark, running on a grsecurity L1 VM. Below table shows the results (runtime in seconds, lower is better):
legacy TDP shadow Linux v5.10.177 10.37s 88.7s 69.7s + patches 4.88s 4.92s 70.1sTDP MMU is, as for v5.15, slower than shadow paging on a vanilla kernel. Fortunately it's disabled by default.
The KVM unit test suite showed no regressions.
Please consider applying.
NAK, same reasoning as the 5.15 backports.
linux-stable-mirror@lists.linaro.org
-
Mathias Krause -
Sean Christopherson