From beda430177f56656e7980dcce93456ffaa35676b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 4 Mar 2021 18:18:08 -0800 Subject: KVM: x86: Ensure deadline timer has truly expired before posting its IRQ When posting a deadline timer interrupt, open code the checks guarding __kvm_wait_lapic_expire() in order to skip the lapic_timer_int_injected() check in kvm_wait_lapic_expire(). The injection check will always fail since the interrupt has not yet be injected. Moving the call after injection would also be wrong as that wouldn't actually delay delivery of the IRQ if it is indeed sent via posted interrupt. Fixes: 010fd37fddf6 ("KVM: LAPIC: Reduce world switch latency caused by timer_advance_ns") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210305021808.3769732-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 45d40bfacb7c..cb8ebfaccfb6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1642,7 +1642,16 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) } if (kvm_use_posted_timer_interrupt(apic->vcpu)) { - kvm_wait_lapic_expire(vcpu); + /* + * Ensure the guest's timer has truly expired before posting an + * interrupt. Open code the relevant checks to avoid querying + * lapic_timer_int_injected(), which will be false since the + * interrupt isn't yet injected. Waiting until after injecting + * is not an option since that won't help a posted interrupt. + */ + if (vcpu->arch.apic->lapic_timer.expired_tscdeadline && + vcpu->arch.apic->lapic_timer.timer_advance_ns) + __kvm_wait_lapic_expire(vcpu); kvm_apic_inject_pending_timer_irqs(apic); return; } -- cgit v1.2.3 From 99840a75454b66d69d2a450ab04e6438d75eba48 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 4 Mar 2021 18:16:37 -0800 Subject: KVM: SVM: Connect 'npt' module param to KVM's internal 'npt_enabled' Directly connect the 'npt' param to the 'npt_enabled' variable so that runtime adjustments to npt_enabled are reflected in sysfs. Move the !PAE restriction to a runtime check to ensure NPT is forced off if the host is using 2-level paging, and add a comment explicitly stating why NPT requires a 64-bit kernel or a kernel with PAE enabled. Opportunistically switch the param to octal permissions. Signed-off-by: Sean Christopherson Message-Id: <20210305021637.3768573-1-seanjc@google.com> Reviewed-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index baee91c1e936..58a45bb139f8 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -115,13 +115,6 @@ static const struct svm_direct_access_msrs { { .index = MSR_INVALID, .always = false }, }; -/* enable NPT for AMD64 and X86 with PAE */ -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) -bool npt_enabled = true; -#else -bool npt_enabled; -#endif - /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * pause_filter_count: On processors that support Pause filtering(indicated @@ -170,9 +163,12 @@ module_param(pause_filter_count_shrink, ushort, 0444); static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX; module_param(pause_filter_count_max, ushort, 0444); -/* allow nested paging (virtualized MMU) for all guests */ -static int npt = true; -module_param(npt, int, S_IRUGO); +/* + * Use nested page tables by default. Note, NPT may get forced off by + * svm_hardware_setup() if it's unsupported by hardware or the host kernel. + */ +bool npt_enabled = true; +module_param_named(npt, npt_enabled, bool, 0444); /* allow nested virtualization in KVM/SVM */ static int nested = true; @@ -988,10 +984,15 @@ static __init int svm_hardware_setup(void) goto err; } - if (!boot_cpu_has(X86_FEATURE_NPT)) + /* + * KVM's MMU doesn't support using 2-level paging for itself, and thus + * NPT isn't supported if the host is using 2-level paging since host + * CR4 is unchanged on VMRUN. + */ + if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE)) npt_enabled = false; - if (npt_enabled && !npt) + if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G); -- cgit v1.2.3 From 4691453406c3a799fdebac83a689919c2c877f04 Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Fri, 5 Mar 2021 23:08:16 +0500 Subject: kvm: x86: use NULL instead of using plain integer as pointer Sparse warnings removed: warning: Using plain integer as NULL pointer Signed-off-by: Muhammad Usama Anjum Message-Id: <20210305180816.GA488770@LEGION> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 868213ca4f98..46b0e52671bb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10600,7 +10600,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, return (void __user *)hva; } else { if (!slot || !slot->npages) - return 0; + return NULL; old_npages = slot->npages; hva = slot->userspace_addr; -- cgit v1.2.3 From 6fcd9cbc6a903f48eebaa14657aeccb003f69a3d Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Sat, 6 Mar 2021 00:11:23 +0500 Subject: kvm: x86: annotate RCU pointers This patch adds the annotation to fix the following sparse errors: arch/x86/kvm//x86.c:8147:15: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//x86.c:8147:15: struct kvm_apic_map [noderef] __rcu * arch/x86/kvm//x86.c:8147:15: struct kvm_apic_map * arch/x86/kvm//x86.c:10628:16: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//x86.c:10628:16: struct kvm_apic_map [noderef] __rcu * arch/x86/kvm//x86.c:10628:16: struct kvm_apic_map * arch/x86/kvm//x86.c:10629:15: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//x86.c:10629:15: struct kvm_pmu_event_filter [noderef] __rcu * arch/x86/kvm//x86.c:10629:15: struct kvm_pmu_event_filter * arch/x86/kvm//lapic.c:267:15: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//lapic.c:267:15: struct kvm_apic_map [noderef] __rcu * arch/x86/kvm//lapic.c:267:15: struct kvm_apic_map * arch/x86/kvm//lapic.c:269:9: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//lapic.c:269:9: struct kvm_apic_map [noderef] __rcu * arch/x86/kvm//lapic.c:269:9: struct kvm_apic_map * arch/x86/kvm//lapic.c:637:15: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//lapic.c:637:15: struct kvm_apic_map [noderef] __rcu * arch/x86/kvm//lapic.c:637:15: struct kvm_apic_map * arch/x86/kvm//lapic.c:994:15: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//lapic.c:994:15: struct kvm_apic_map [noderef] __rcu * arch/x86/kvm//lapic.c:994:15: struct kvm_apic_map * arch/x86/kvm//lapic.c:1036:15: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//lapic.c:1036:15: struct kvm_apic_map [noderef] __rcu * arch/x86/kvm//lapic.c:1036:15: struct kvm_apic_map * arch/x86/kvm//lapic.c:1173:15: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//lapic.c:1173:15: struct kvm_apic_map [noderef] __rcu * arch/x86/kvm//lapic.c:1173:15: struct kvm_apic_map * arch/x86/kvm//pmu.c:190:18: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//pmu.c:190:18: struct kvm_pmu_event_filter [noderef] __rcu * arch/x86/kvm//pmu.c:190:18: struct kvm_pmu_event_filter * arch/x86/kvm//pmu.c:251:18: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//pmu.c:251:18: struct kvm_pmu_event_filter [noderef] __rcu * arch/x86/kvm//pmu.c:251:18: struct kvm_pmu_event_filter * arch/x86/kvm//pmu.c:522:18: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//pmu.c:522:18: struct kvm_pmu_event_filter [noderef] __rcu * arch/x86/kvm//pmu.c:522:18: struct kvm_pmu_event_filter * arch/x86/kvm//pmu.c:522:18: error: incompatible types in comparison expression (different address spaces): arch/x86/kvm//pmu.c:522:18: struct kvm_pmu_event_filter [noderef] __rcu * arch/x86/kvm//pmu.c:522:18: struct kvm_pmu_event_filter * Signed-off-by: Muhammad Usama Anjum Message-Id: <20210305191123.GA497469@LEGION> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 877a4025d8da..9bc091ecaaeb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -963,7 +963,7 @@ struct kvm_arch { struct kvm_pit *vpit; atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; - struct kvm_apic_map *apic_map; + struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; bool apic_access_page_done; @@ -1036,7 +1036,7 @@ struct kvm_arch { bool bus_lock_detection_enabled; - struct kvm_pmu_event_filter *pmu_event_filter; + struct kvm_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_lpage_recovery_thread; #ifdef CONFIG_X86_64 -- cgit v1.2.3 From d7eb79c6290c7ae4561418544072e0a3266e7384 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Wed, 24 Feb 2021 09:37:29 +0800 Subject: KVM: kvmclock: Fix vCPUs > 64 can't be online/hotpluged # lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 88 On-line CPU(s) list: 0-63 Off-line CPU(s) list: 64-87 # cat /proc/cmdline BOOT_IMAGE=/vmlinuz-5.10.0-rc3-tlinux2-0050+ root=/dev/mapper/cl-root ro rd.lvm.lv=cl/root rhgb quiet console=ttyS0 LANG=en_US .UTF-8 no-kvmclock-vsyscall # echo 1 > /sys/devices/system/cpu/cpu76/online -bash: echo: write error: Cannot allocate memory The per-cpu vsyscall pvclock data pointer assigns either an element of the static array hv_clock_boot (#vCPU <= 64) or dynamically allocated memory hvclock_mem (vCPU > 64), the dynamically memory will not be allocated if kvmclock vsyscall is disabled, this can result in cpu hotpluged fails in kvmclock_setup_percpu() which returns -ENOMEM. It's broken for no-vsyscall and sometimes you end up with vsyscall disabled if the host does something strange. This patch fixes it by allocating this dynamically memory unconditionally even if vsyscall is disabled. Fixes: 6a1cac56f4 ("x86/kvm: Use __bss_decrypted attribute in shared variables") Reported-by: Zelin Deng Cc: Brijesh Singh Cc: stable@vger.kernel.org#v4.19-rc5+ Signed-off-by: Wanpeng Li Message-Id: <1614130683-24137-1-git-send-email-wanpengli@tencent.com> Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvmclock.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index aa593743acf6..1fc0962c89c0 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -268,21 +268,20 @@ static void __init kvmclock_init_mem(void) static int __init kvm_setup_vsyscall_timeinfo(void) { -#ifdef CONFIG_X86_64 - u8 flags; + kvmclock_init_mem(); - if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall) - return 0; +#ifdef CONFIG_X86_64 + if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) { + u8 flags; - flags = pvclock_read_flags(&hv_clock_boot[0].pvti); - if (!(flags & PVCLOCK_TSC_STABLE_BIT)) - return 0; + flags = pvclock_read_flags(&hv_clock_boot[0].pvti); + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) + return 0; - kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK; + kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK; + } #endif - kvmclock_init_mem(); - return 0; } early_initcall(kvm_setup_vsyscall_timeinfo); -- cgit v1.2.3 From 8df9f1af2eced9720f71cf310275d81c1bf07a06 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 9 Mar 2021 16:30:29 -0800 Subject: KVM: x86/mmu: Skip !MMU-present SPTEs when removing SP in exclusive mode If mmu_lock is held for write, don't bother setting !PRESENT SPTEs to REMOVED_SPTE when recursively zapping SPTEs as part of shadow page removal. The concurrent write protections provided by REMOVED_SPTE are not needed, there are no backing page side effects to record, and MMIO SPTEs can be left as is since they are protected by the memslot generation, not by ensuring that the MMIO SPTE is unreachable (which is racy with respect to lockless walks regardless of zapping behavior). Skipping !PRESENT drastically reduces the number of updates needed to tear down sparsely populated MMUs, e.g. when tearing down a 6gb VM that didn't touch much memory, 6929/7168 (~96.6%) of SPTEs were '0' and could be skipped. Avoiding the write itself is likely close to a wash, but avoiding __handle_changed_spte() is a clear-cut win as that involves saving and restoring all non-volatile GPRs (it's a subtly big function), as well as several conditional branches before bailing out. Cc: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210310003029.1250571-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index c926c6b899a1..d78915019b08 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -337,7 +337,18 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt, cpu_relax(); } } else { + /* + * If the SPTE is not MMU-present, there is no backing + * page associated with the SPTE and so no side effects + * that need to be recorded, and exclusive ownership of + * mmu_lock ensures the SPTE can't be made present. + * Note, zapping MMIO SPTEs is also unnecessary as they + * are guarded by the memslots generation, not by being + * unreachable. + */ old_child_spte = READ_ONCE(*sptep); + if (!is_shadow_present_pte(old_child_spte)) + continue; /* * Marking the SPTE as a removed SPTE is not -- cgit v1.2.3 From 35737d2db2f4567106c90060ad110b27cb354fa4 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 4 Mar 2021 08:35:18 +0800 Subject: KVM: LAPIC: Advancing the timer expiration on guest initiated write Advancing the timer expiration should only be necessary on guest initiated writes. When we cancel the timer and clear .pending during state restore, clear expired_tscdeadline as well. Reviewed-by: Sean Christopherson Signed-off-by: Wanpeng Li Message-Id: <1614818118-965-1-git-send-email-wanpengli@tencent.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cb8ebfaccfb6..cc369b9ad8f1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2604,6 +2604,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) apic_update_ppr(apic); hrtimer_cancel(&apic->lapic_timer.timer); + apic->lapic_timer.expired_tscdeadline = 0; apic_update_lvtt(apic); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); -- cgit v1.2.3