diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/Kconfig | 45 | ||||
-rw-r--r-- | arch/x86/events/amd/ibs.c | 8 | ||||
-rw-r--r-- | arch/x86/include/asm/cpufeatures.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/kvm_host.h | 6 | ||||
-rw-r--r-- | arch/x86/include/asm/msr-index.h | 16 | ||||
-rw-r--r-- | arch/x86/include/asm/nospec-branch.h | 4 | ||||
-rw-r--r-- | arch/x86/include/asm/processor.h | 7 | ||||
-rw-r--r-- | arch/x86/include/asm/smp.h | 10 | ||||
-rw-r--r-- | arch/x86/kernel/apic/apic.c | 122 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/bugs.c | 161 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/common.c | 94 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/cpu.h | 18 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/intel.c | 5 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/tsx.c | 140 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.c | 8 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 374 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/mmutrace.h | 59 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 65 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 10 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 14 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 63 |
23 files changed, 1024 insertions, 213 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8fec1585ac7a..b58daecc591e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1853,6 +1853,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS If unsure, say y. +choice + prompt "TSX enable mode" + depends on CPU_SUP_INTEL + default X86_INTEL_TSX_MODE_OFF + help + Intel's TSX (Transactional Synchronization Extensions) feature + allows to optimize locking protocols through lock elision which + can lead to a noticeable performance boost. + + On the other hand it has been shown that TSX can be exploited + to form side channel attacks (e.g. TAA) and chances are there + will be more of those attacks discovered in the future. + + Therefore TSX is not enabled by default (aka tsx=off). An admin + might override this decision by tsx=on the command line parameter. + Even with TSX enabled, the kernel will attempt to enable the best + possible TAA mitigation setting depending on the microcode available + for the particular machine. + + This option allows to set the default tsx mode between tsx=on, =off + and =auto. See Documentation/admin-guide/kernel-parameters.txt for more + details. + + Say off if not sure, auto if TSX is in use but it should be used on safe + platforms or on if TSX is in use and the security aspect of tsx is not + relevant. + +config X86_INTEL_TSX_MODE_OFF + bool "off" + help + TSX is disabled if possible - equals to tsx=off command line parameter. + +config X86_INTEL_TSX_MODE_ON + bool "on" + help + TSX is always enabled on TSX capable HW - equals the tsx=on command + line parameter. + +config X86_INTEL_TSX_MODE_AUTO + bool "auto" + help + TSX is enabled on TSX capable HW that is believed to be safe against + side channel attacks- equals the tsx=auto command line parameter. +endchoice + config EFI bool "EFI runtime service support" depends on ACPI diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 7a86fbc07ddc..f24e9adaa316 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -389,7 +389,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { config &= ~perf_ibs->cnt_mask; - wrmsrl(hwc->config_base, config); + if (boot_cpu_data.x86 == 0x10) + wrmsrl(hwc->config_base, config); config &= ~perf_ibs->enable_mask; wrmsrl(hwc->config_base, config); } @@ -564,7 +565,8 @@ static struct perf_ibs perf_ibs_op = { }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, - .cnt_mask = IBS_OP_MAX_CNT, + .cnt_mask = IBS_OP_MAX_CNT | IBS_OP_CUR_CNT | + IBS_OP_CUR_CNT_RAND, .enable_mask = IBS_OP_ENABLE, .valid_mask = IBS_OP_VAL, .max_period = IBS_OP_MAX_CNT << 4, @@ -625,7 +627,7 @@ fail: if (event->attr.sample_type & PERF_SAMPLE_RAW) offset_max = perf_ibs->offset_max; else if (check_rip) - offset_max = 2; + offset_max = 3; else offset_max = 1; do { diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 14357354cd28..b4bef819d5d5 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -388,5 +388,7 @@ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 00c12158a5dc..d0e17813a9b0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -277,6 +277,7 @@ struct kvm_rmap_head { struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; + struct list_head lpage_disallowed_link; /* * The following two entries are used to key the shadow page in the @@ -289,6 +290,7 @@ struct kvm_mmu_page { /* hold the gfn of each spte inside spt */ gfn_t *gfns; bool unsync; + bool lpage_disallowed; /* Can't be replaced by an equiv large page */ int root_count; /* Currently serving as active root */ unsigned int unsync_children; struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ @@ -779,6 +781,7 @@ struct kvm_arch { */ struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; + struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -854,6 +857,8 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + + struct task_struct *nx_lpage_recovery_thread; }; struct kvm_vm_stat { @@ -867,6 +872,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong nx_lpage_splits; ulong max_mmu_page_hash_collisions; }; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index fda3bf75de6c..5761a86b88e0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -84,6 +84,18 @@ * Microarchitectural Data * Sampling (MDS) vulnerabilities. */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -94,6 +106,10 @@ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f6b496d11097..b73a16a56e4f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -323,7 +323,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the @@ -346,7 +346,7 @@ static inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d55a0adbcf27..6a87eda9691e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -994,4 +994,11 @@ enum mds_mitigations { MDS_MITIGATION_VMWERV, }; +enum taa_mitigations { + TAA_MITIGATION_OFF, + TAA_MITIGATION_UCODE_NEEDED, + TAA_MITIGATION_VERW, + TAA_MITIGATION_TSX_DISABLED, +}; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index fe2ee61880a8..a14730ca9d1e 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -175,16 +175,6 @@ static inline int wbinvd_on_all_cpus(void) extern unsigned disabled_cpus; #ifdef CONFIG_X86_LOCAL_APIC - -#ifndef CONFIG_X86_64 -static inline int logical_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); -} - -#endif - extern int hard_smp_processor_id(void); #else /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ea2de324ab02..6415b4aead54 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1362,6 +1362,56 @@ static void lapic_setup_esr(void) oldvalue, value); } +static void apic_pending_intr_clear(void) +{ + long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned long long tsc = 0, ntsc; + unsigned int value, queued; + int i, j, acked = 0; + + if (boot_cpu_has(X86_FEATURE_TSC)) + tsc = rdtsc(); + /* + * After a crash, we no longer service the interrupts and a pending + * interrupt from previous kernel might still have ISR bit set. + * + * Most probably by now CPU has serviced that pending interrupt and + * it might not have done the ack_APIC_irq() because it thought, + * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it + * does not clear the ISR bit and cpu thinks it has already serivced + * the interrupt. Hence a vector might get locked. It was noticed + * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. + */ + do { + queued = 0; + for (i = APIC_ISR_NR - 1; i >= 0; i--) + queued |= apic_read(APIC_IRR + i*0x10); + + for (i = APIC_ISR_NR - 1; i >= 0; i--) { + value = apic_read(APIC_ISR + i*0x10); + for (j = 31; j >= 0; j--) { + if (value & (1<<j)) { + ack_APIC_irq(); + acked++; + } + } + } + if (acked > 256) { + printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", + acked); + break; + } + if (queued) { + if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { + ntsc = rdtsc(); + max_loops = (cpu_khz << 10) - (ntsc - tsc); + } else + max_loops--; + } + } while (queued && max_loops > 0); + WARN_ON(max_loops <= 0); +} + /** * setup_local_APIC - setup the local APIC * @@ -1371,13 +1421,8 @@ static void lapic_setup_esr(void) void setup_local_APIC(void) { int cpu = smp_processor_id(); - unsigned int value, queued; - int i, j, acked = 0; - unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned int value; - if (boot_cpu_has(X86_FEATURE_TSC)) - tsc = rdtsc(); if (disable_apic) { disable_ioapic_support(); @@ -1417,16 +1462,21 @@ void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - /* - * APIC LDR is initialized. If logical_apicid mapping was - * initialized during get_smp_config(), make sure it matches the - * actual value. - */ - i = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - WARN_ON(i != BAD_APICID && i != logical_smp_processor_id()); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = - logical_smp_processor_id(); + if (apic->dest_logical) { + int logical_apicid, ldr_apicid; + + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches + * the actual value. + */ + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (logical_apicid != BAD_APICID) + WARN_ON(logical_apicid != ldr_apicid); + /* Always use the value from LDR. */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + } #endif /* @@ -1437,45 +1487,7 @@ void setup_local_APIC(void) value &= ~APIC_TPRI_MASK; apic_write(APIC_TASKPRI, value); - /* - * After a crash, we no longer service the interrupts and a pending - * interrupt from previous kernel might still have ISR bit set. - * - * Most probably by now CPU has serviced that pending interrupt and - * it might not have done the ack_APIC_irq() because it thought, - * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it - * does not clear the ISR bit and cpu thinks it has already serivced - * the interrupt. Hence a vector might get locked. It was noticed - * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. - */ - do { - queued = 0; - for (i = APIC_ISR_NR - 1; i >= 0; i--) - queued |= apic_read(APIC_IRR + i*0x10); - - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for (j = 31; j >= 0; j--) { - if (value & (1<<j)) { - ack_APIC_irq(); - acked++; - } - } - } - if (acked > 256) { - printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", - acked); - break; - } - if (queued) { - if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { - ntsc = rdtsc(); - max_loops = (cpu_khz << 10) - (ntsc - tsc); - } else - max_loops--; - } - } while (queued && max_loops > 0); - WARN_ON(max_loops <= 0); + apic_pending_intr_clear(); /* * Now that we are all set up, enable the APIC diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 570e8bb1f386..e13ddd19a76c 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -28,7 +28,7 @@ obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel.o tsx.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 8bf21bc7a190..8596811843cc 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -32,11 +32,14 @@ #include <asm/intel-family.h> #include <asm/e820/api.h> +#include "cpu.h" + static void __init spectre_v1_select_mitigation(void); static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -103,6 +106,7 @@ void __init check_bugs(void) ssb_select_mitigation(); l1tf_select_mitigation(); mds_select_mitigation(); + taa_select_mitigation(); arch_smt_update(); @@ -267,6 +271,100 @@ static int __init mds_cmdline(char *str) early_param("mds", mds_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "TAA: " fmt + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static bool taa_nosmt __ro_after_init; + +static const char * const taa_strings[] = { + [TAA_MITIGATION_OFF] = "Vulnerable", + [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", + [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", +}; + +static void __init taa_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TSX previously disabled by tsx=off */ + if (!boot_cpu_has(X86_FEATURE_RTM)) { + taa_mitigation = TAA_MITIGATION_TSX_DISABLED; + goto out; + } + + if (cpu_mitigations_off()) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */ + if (taa_mitigation == TAA_MITIGATION_OFF) + goto out; + + if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) + taa_mitigation = TAA_MITIGATION_VERW; + else + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. + * A microcode update fixes this behavior to clear CPU buffers. It also + * adds support for MSR_IA32_TSX_CTRL which is enumerated by the + * ARCH_CAP_TSX_CTRL_MSR bit. + * + * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode + * update is required. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ( (ia32_cap & ARCH_CAP_MDS_NO) && + !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * TSX is enabled, select alternate mitigation for TAA which is + * the same as MDS. Enable MDS static branch to clear CPU buffers. + * + * For guests that can't determine whether the correct microcode is + * present on host, enable the mitigation for UCODE_NEEDED as well. + */ + static_branch_enable(&mds_user_clear); + + if (taa_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); + +out: + pr_info("%s\n", taa_strings[taa_mitigation]); +} + +static int __init tsx_async_abort_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_TAA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + taa_mitigation = TAA_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + taa_mitigation = TAA_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_nosmt = true; + } + + return 0; +} +early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -772,13 +870,10 @@ static void update_mds_branch_idle(void) } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" void arch_smt_update(void) { - /* Enhanced IBRS implies STIBP. No update required. */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) - return; - mutex_lock(&spec_ctrl_mutex); switch (spectre_v2_user) { @@ -804,6 +899,17 @@ void arch_smt_update(void) break; } + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -1119,6 +1225,9 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +bool itlb_multihit_kvm_mitigation; +EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); + #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt @@ -1274,11 +1383,24 @@ static ssize_t l1tf_show_state(char *buf) l1tf_vmx_states[l1tf_vmx_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + if (itlb_multihit_kvm_mitigation) + return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + else + return sprintf(buf, "KVM: Vulnerable\n"); +} #else static ssize_t l1tf_show_state(char *buf) { return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + return sprintf(buf, "Processor vulnerable\n"); +} #endif static ssize_t mds_show_state(char *buf) @@ -1298,6 +1420,21 @@ static ssize_t mds_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t tsx_async_abort_show_state(char *buf) +{ + if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || + (taa_mitigation == TAA_MITIGATION_OFF)) + return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); + } + + return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1363,6 +1500,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MDS: return mds_show_state(buf); + case X86_BUG_TAA: + return tsx_async_abort_show_state(buf); + + case X86_BUG_ITLB_MULTIHIT: + return itlb_multihit_show_state(buf); + default: break; } @@ -1399,4 +1542,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_MDS); } + +ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TAA); +} + +ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 551c6bed7c8c..c0c9c5a44e82 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -897,13 +897,14 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) c->x86_cache_bits = c->x86_phys_bits; } -#define NO_SPECULATION BIT(0) -#define NO_MELTDOWN BIT(1) -#define NO_SSB BIT(2) -#define NO_L1TF BIT(3) -#define NO_MDS BIT(4) -#define MSBDS_ONLY BIT(5) -#define NO_SWAPGS BIT(6) +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) +#define NO_ITLB_MULTIHIT BIT(7) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -921,26 +922,26 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ - VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), - - VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(CORE_YONAH, NO_SSB), - VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -950,14 +951,16 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { * good enough for our purposes. */ + VULNWL_INTEL(ATOM_TREMONT_X, NO_ITLB_MULTIHIT), + /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), {} }; @@ -968,19 +971,30 @@ static bool __init cpu_matches(unsigned long which) return m && !!(m->driver_data & which); } -static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +u64 x86_read_arch_cap_msr(void) { u64 ia32_cap = 0; + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + return ia32_cap; +} + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ + if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); + if (cpu_matches(NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -997,6 +1011,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (!cpu_matches(NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); + /* + * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when: + * - TSX is supported or + * - TSX_CTRL is present + * + * TSX_CTRL check is needed for cases when TSX could be disabled before + * the kernel boot e.g. kexec. + * TSX_CTRL check alone is not sufficient for cases when the microcode + * update is not present or running as guest that don't get TSX_CTRL. + */ + if (!(ia32_cap & ARCH_CAP_TAA_NO) && + (cpu_has(c, X86_FEATURE_RTM) || + (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + setup_force_cpu_bug(X86_BUG_TAA); + if (cpu_matches(NO_MELTDOWN)) return; @@ -1407,6 +1436,7 @@ void __init identify_boot_cpu(void) enable_sep_cpu(); #endif cpu_detect_tlb(&boot_cpu_data); + tsx_init(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index cca588407dca..db10a63687d3 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -45,6 +45,22 @@ struct _tlb_table { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; +#ifdef CONFIG_CPU_SUP_INTEL +enum tsx_ctrl_states { + TSX_CTRL_ENABLE, + TSX_CTRL_DISABLE, + TSX_CTRL_NOT_SUPPORTED, +}; + +extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; + +extern void __init tsx_init(void); +extern void tsx_enable(void); +extern void tsx_disable(void); +#else +static inline void tsx_init(void) { } +#endif /* CONFIG_CPU_SUP_INTEL */ + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); extern int detect_extended_topology_early(struct cpuinfo_x86 *c); @@ -54,4 +70,6 @@ unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern u64 x86_read_arch_cap_msr(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 574dcdc092ab..3a5ea741701b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -695,6 +695,11 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_energy_perf(c); init_intel_misc_features(c); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c new file mode 100644 index 000000000000..3e20d322bc98 --- /dev/null +++ b/arch/x86/kernel/cpu/tsx.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Transactional Synchronization Extensions (TSX) control. + * + * Copyright (C) 2019 Intel Corporation + * + * Author: + * Pawan Gupta <pawan.kumar.gupta@linux.intel.com> + */ + +#include <linux/cpufeature.h> + +#include <asm/cmdline.h> + +#include "cpu.h" + +enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; + +void tsx_disable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Force all transactions to immediately abort */ + tsx |= TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is not enumerated in CPUID. + * This is visible to userspace and will ensure they + * do not waste resources trying TSX transactions that + * will always abort. + */ + tsx |= TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +void tsx_enable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Enable the RTM feature in the cpu */ + tsx &= ~TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is enumerated in CPUID. + * This is visible to userspace and will ensure they + * can enumerate and use the TSX feature. + */ + tsx &= ~TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +static bool __init tsx_ctrl_is_supported(void) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); +} + +static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) +{ + if (boot_cpu_has_bug(X86_BUG_TAA)) + return TSX_CTRL_DISABLE; + + return TSX_CTRL_ENABLE; +} + +void __init tsx_init(void) +{ + char arg[5] = {}; + int ret; + + if (!tsx_ctrl_is_supported()) + return; + + ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg)); + if (ret >= 0) { + if (!strcmp(arg, "on")) { + tsx_ctrl_state = TSX_CTRL_ENABLE; + } else if (!strcmp(arg, "off")) { + tsx_ctrl_state = TSX_CTRL_DISABLE; + } else if (!strcmp(arg, "auto")) { + tsx_ctrl_state = x86_get_tsx_auto_mode(); + } else { + tsx_ctrl_state = TSX_CTRL_DISABLE; + pr_err("tsx: invalid option, defaulting to off\n"); + } + } else { + /* tsx= not provided */ + if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO)) + tsx_ctrl_state = x86_get_tsx_auto_mode(); + else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF)) + tsx_ctrl_state = TSX_CTRL_DISABLE; + else + tsx_ctrl_state = TSX_CTRL_ENABLE; + } + + if (tsx_ctrl_state == TSX_CTRL_DISABLE) { + tsx_disable(); + + /* + * tsx_disable() will change the state of the + * RTM CPUID bit. Clear it here since it is now + * expected to be not set. + */ + setup_clear_cpu_cap(X86_FEATURE_RTM); + } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { + + /* + * HW defaults TSX to be enabled at bootup. + * We may still need the TSX enable support + * during init for special cases like + * kexec after TSX is disabled. + */ + tsx_enable(); + + /* + * tsx_enable() will change the state of the + * RTM CPUID bit. Force it here since it is now + * expected to be set. + */ + setup_force_cpu_cap(X86_FEATURE_RTM); + } +} diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 5c82b4bc4a68..33f87b696487 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -481,8 +481,16 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); + entry->edx &= kvm_cpuid_7_0_edx_x86_features; cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && + boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even * if the host doesn't support it. diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 87a0601b1c20..8cd26e50d41c 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -40,6 +40,7 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kthread.h> #include <asm/page.h> #include <asm/cmpxchg.h> @@ -48,6 +49,30 @@ #include <asm/kvm_page_track.h> #include "trace.h" +extern bool itlb_multihit_kvm_mitigation; + +static int __read_mostly nx_huge_pages = -1; +static uint __read_mostly nx_huge_pages_recovery_ratio = 60; + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); + +static struct kernel_param_ops nx_huge_pages_ops = { + .set = set_nx_huge_pages, + .get = param_get_bool, +}; + +static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { + .set = set_nx_huge_pages_recovery_ratio, + .get = param_get_uint, +}; + +module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); +__MODULE_PARM_TYPE(nx_huge_pages, "bool"); +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, + &nx_huge_pages_recovery_ratio, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -139,9 +164,6 @@ module_param(dbg, bool, 0644); #include <trace/events/kvm.h> -#define CREATE_TRACE_POINTS -#include "mmutrace.h" - #define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) #define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) @@ -244,6 +266,11 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); +static bool is_executable_pte(u64 spte); + +#define CREATE_TRACE_POINTS +#include "mmutrace.h" + void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) { @@ -264,6 +291,11 @@ static inline bool spte_ad_enabled(u64 spte) return !(spte & shadow_acc_track_value); } +static bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); +} + static inline u64 spte_shadow_accessed_mask(u64 spte) { MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); @@ -1008,10 +1040,16 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) { - if (sp->role.direct) - BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index)); - else + if (!sp->role.direct) { sp->gfns[index] = gfn; + return; + } + + if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index))) + pr_err_ratelimited("gfn mismatch under direct page %llx " + "(expected %llx, got %llx)\n", + sp->gfn, + kvm_mmu_page_get_gfn(sp, index), gfn); } /* @@ -1070,6 +1108,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); } +static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + if (sp->lpage_disallowed) + return; + + ++kvm->stat.nx_lpage_splits; + list_add_tail(&sp->lpage_disallowed_link, + &kvm->arch.lpage_disallowed_mmu_pages); + sp->lpage_disallowed = true; +} + static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; @@ -1087,6 +1136,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } +static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + --kvm->stat.nx_lpage_splits; + sp->lpage_disallowed = false; + list_del(&sp->lpage_disallowed_link); +} + static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, struct kvm_memory_slot *slot) { @@ -2634,6 +2690,9 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_reload_remote_mmus(kvm); } + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + sp->role.invalid = 1; return ret; } @@ -2788,6 +2847,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= spte_shadow_accessed_mask(spte); + if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + is_nx_huge_page_enabled()) { + pte_access &= ~ACC_EXEC_MASK; + } + if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; else @@ -2903,10 +2967,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, ret = RET_PF_EMULATE; pgprintk("%s: setting spte %llx\n", __func__, *sptep); - pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", - is_large_pte(*sptep)? "2MB" : "4kB", - *sptep & PT_WRITABLE_MASK ? "RW" : "R", gfn, - *sptep, sptep); + trace_kvm_mmu_set_spte(level, gfn, sptep); if (!was_rmapped && is_large_pte(*sptep)) ++vcpu->kvm->stat.lpages; @@ -2918,8 +2979,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, } } - kvm_release_pfn_clean(pfn); - return ret; } @@ -2954,9 +3013,11 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, if (ret <= 0) return -1; - for (i = 0; i < ret; i++, gfn++, start++) + for (i = 0; i < ret; i++, gfn++, start++) { mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn, page_to_pfn(pages[i]), true, true); + put_page(pages[i]); + } return 0; } @@ -3004,40 +3065,71 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } -static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, - int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) +static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) { - struct kvm_shadow_walk_iterator iterator; + int level = *levelp; + u64 spte = *it.sptep; + + if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + is_nx_huge_page_enabled() && + is_shadow_present_pte(spte) && + !is_large_pte(spte)) { + /* + * A small SPTE exists for this pfn, but FNAME(fetch) + * and __direct_map would like to create a large PTE + * instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of + * the address. + */ + u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1); + *pfnp |= gfn & page_mask; + (*levelp)--; + } +} + +static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, + int map_writable, int level, kvm_pfn_t pfn, + bool prefault, bool lpage_disallowed) +{ + struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; - int emulate = 0; - gfn_t pseudo_gfn; + int ret; + gfn_t gfn = gpa >> PAGE_SHIFT; + gfn_t base_gfn = gfn; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return 0; + return RET_PF_RETRY; - for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { - if (iterator.level == level) { - emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, - write, level, gfn, pfn, prefault, - map_writable); - direct_pte_prefetch(vcpu, iterator.sptep); - ++vcpu->stat.pf_fixed; - break; - } + trace_kvm_mmu_spte_requested(gpa, level, pfn); + for_each_shadow_entry(vcpu, gpa, it) { + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &level); - drop_large_spte(vcpu, iterator.sptep); - if (!is_shadow_present_pte(*iterator.sptep)) { - u64 base_addr = iterator.addr; + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == level) + break; - base_addr &= PT64_LVL_ADDR_MASK(iterator.level); - pseudo_gfn = base_addr >> PAGE_SHIFT; - sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, - iterator.level - 1, 1, ACC_ALL); + drop_large_spte(vcpu, it.sptep); + if (!is_shadow_present_pte(*it.sptep)) { + sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr, + it.level - 1, true, ACC_ALL); - link_shadow_page(vcpu, iterator.sptep, sp); + link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } - return emulate; + + ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL, + write, level, base_gfn, pfn, prefault, + map_writable); + direct_pte_prefetch(vcpu, it.sptep); + ++vcpu->stat.pf_fixed; + return ret; } static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) @@ -3072,11 +3164,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, kvm_pfn_t *pfnp, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) { kvm_pfn_t pfn = *pfnp; - gfn_t gfn = *gfnp; int level = *levelp; /* @@ -3103,8 +3194,6 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, mask = KVM_PAGES_PER_HPAGE(level) - 1; VM_BUG_ON((gfn & mask) != (pfn & mask)); if (pfn & mask) { - gfn &= ~mask; - *gfnp = gfn; kvm_release_pfn_clean(pfn); pfn &= ~mask; kvm_get_pfn(pfn); @@ -3331,11 +3420,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, { int r; int level; - bool force_pt_level = false; + bool force_pt_level; kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + force_pt_level = lpage_disallowed; level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { /* @@ -3361,22 +3453,20 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) return r; + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; - + transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); + r = __direct_map(vcpu, v, write, map_writable, level, pfn, + prefault, false); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } @@ -3922,6 +4012,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; bool map_writable; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); @@ -3932,8 +4024,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, - PT_DIRECTORY_LEVEL); + force_pt_level = + lpage_disallowed || + !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL); level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { if (level > PT_DIRECTORY_LEVEL && @@ -3954,22 +4047,20 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) return r; + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; - + transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, + prefault, lpage_disallowed); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } static void nonpaging_init_context(struct kvm_vcpu *vcpu, @@ -5454,7 +5545,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) int nr_to_scan = sc->nr_to_scan; unsigned long freed = 0; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx; @@ -5504,7 +5595,7 @@ unlock: break; } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); return freed; } @@ -5528,8 +5619,58 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static bool get_nx_auto_mode(void) +{ + /* Return true when CPU has the bug, and mitigations are ON */ + return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); +} + +static void __set_nx_huge_pages(bool val) +{ + nx_huge_pages = itlb_multihit_kvm_mitigation = val; +} + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) +{ + bool old_val = nx_huge_pages; + bool new_val; + + /* In "auto" mode deploy workaround only if CPU has the bug. */ + if (sysfs_streq(val, "off")) + new_val = 0; + else if (sysfs_streq(val, "force")) + new_val = 1; + else if (sysfs_streq(val, "auto")) + new_val = get_nx_auto_mode(); + else if (strtobool(val, &new_val) < 0) + return -EINVAL; + + __set_nx_huge_pages(new_val); + + if (new_val != old_val) { + struct kvm *kvm; + int idx; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + idx = srcu_read_lock(&kvm->srcu); + kvm_mmu_invalidate_zap_all_pages(kvm); + srcu_read_unlock(&kvm->srcu, idx); + + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + } + mutex_unlock(&kvm_lock); + } + + return 0; +} + int kvm_mmu_module_init(void) { + if (nx_huge_pages == -1) + __set_nx_huge_pages(get_nx_auto_mode()); + kvm_mmu_reset_all_pte_masks(); pte_list_desc_cache = kmem_cache_create("pte_list_desc", @@ -5595,3 +5736,116 @@ void kvm_mmu_module_exit(void) unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } + +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +{ + unsigned int old_val; + int err; + + old_val = nx_huge_pages_recovery_ratio; + err = param_set_uint(val, kp); + if (err) + return err; + + if (READ_ONCE(nx_huge_pages) && + !old_val && nx_huge_pages_recovery_ratio) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + + mutex_unlock(&kvm_lock); + } + + return err; +} + +static void kvm_recover_nx_lpages(struct kvm *kvm) +{ + int rcu_idx; + struct kvm_mmu_page *sp; + unsigned int ratio; + LIST_HEAD(invalid_list); + ulong to_zap; + + rcu_idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) { + /* + * We use a separate list instead of just using active_mmu_pages + * because the number of lpage_disallowed pages is expected to + * be relatively small compared to the total. + */ + sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + struct kvm_mmu_page, + lpage_disallowed_link); + WARN_ON_ONCE(!sp->lpage_disallowed); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + WARN_ON_ONCE(sp->lpage_disallowed); + + if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + if (to_zap) + cond_resched_lock(&kvm->mmu_lock); + } + } + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, rcu_idx); +} + +static long get_nx_lpage_recovery_timeout(u64 start_time) +{ + return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) + ? start_time + 60 * HZ - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; +} + +static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +{ + u64 start_time; + long remaining_time; + + while (true) { + start_time = get_jiffies_64(); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop() && remaining_time > 0) { + schedule_timeout(remaining_time); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + set_current_state(TASK_INTERRUPTIBLE); + } + + set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + return 0; + + kvm_recover_nx_lpages(kvm); + } +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + int err; + + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + "kvm-nx-lpage-recovery", + &kvm->arch.nx_lpage_recovery_thread); + if (!err) + kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + + return err; +} + +void kvm_mmu_pre_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.nx_lpage_recovery_thread) + kthread_stop(kvm->arch.nx_lpage_recovery_thread); +} diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index efc857615d8e..068feab64acf 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -195,4 +195,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); + +int kvm_mmu_post_init_vm(struct kvm *kvm); +void kvm_mmu_pre_destroy_vm(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index c73bf4e4988c..918b0d5bf272 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -325,6 +325,65 @@ TRACE_EVENT( __entry->kvm_gen == __entry->spte_gen ) ); + +TRACE_EVENT( + kvm_mmu_set_spte, + TP_PROTO(int level, gfn_t gfn, u64 *sptep), + TP_ARGS(level, gfn, sptep), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, spte) + __field(u64, sptep) + __field(u8, level) + /* These depend on page entry type, so compute them now. */ + __field(bool, r) + __field(bool, x) + __field(u8, u) + ), + + TP_fast_assign( + __entry->gfn = gfn; + __entry->spte = *sptep; + __entry->sptep = virt_to_phys(sptep); + __entry->level = level; + __entry->r = shadow_present_mask || (__entry->spte & PT_PRESENT_MASK); + __entry->x = is_executable_pte(__entry->spte); + __entry->u = shadow_user_mask ? !!(__entry->spte & shadow_user_mask) : -1; + ), + + TP_printk("gfn %llx spte %llx (%s%s%s%s) level %d at %llx", + __entry->gfn, __entry->spte, + __entry->r ? "r" : "-", + __entry->spte & PT_WRITABLE_MASK ? "w" : "-", + __entry->x ? "x" : "-", + __entry->u == -1 ? "" : (__entry->u ? "u" : "-"), + __entry->level, __entry->sptep + ) +); + +TRACE_EVENT( + kvm_mmu_spte_requested, + TP_PROTO(gpa_t addr, int level, kvm_pfn_t pfn), + TP_ARGS(addr, level, pfn), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, pfn) + __field(u8, level) + ), + + TP_fast_assign( + __entry->gfn = addr >> PAGE_SHIFT; + __entry->pfn = pfn | (__entry->gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); + __entry->level = level; + ), + + TP_printk("gfn %llx pfn %llx level %d", + __entry->gfn, __entry->pfn, __entry->level + ) +); + #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6288e9d7068e..8cf7a09bdd73 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -522,6 +522,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true); + kvm_release_pfn_clean(pfn); return true; } @@ -595,12 +596,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - kvm_pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault, + bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; int top_level, ret; + gfn_t gfn, base_gfn; direct_access = gw->pte_access; @@ -645,35 +648,48 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - for (; - shadow_walk_okay(&it) && it.level > hlevel; - shadow_walk_next(&it)) { - gfn_t direct_gfn; + /* + * FNAME(page_fault) might have clobbered the bottom bits of + * gw->gfn, restore them from the virtual address. + */ + gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT); + base_gfn = gfn; + trace_kvm_mmu_spte_requested(addr, gw->level, pfn); + + for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); - validate_direct_spte(vcpu, it.sptep, direct_access); - drop_large_spte(vcpu, it.sptep); + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel); - if (is_shadow_present_pte(*it.sptep)) - continue; + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == hlevel) + break; + + validate_direct_spte(vcpu, it.sptep, direct_access); - direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + drop_large_spte(vcpu, it.sptep); - sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, - true, direct_access); - link_shadow_page(vcpu, it.sptep, sp); + if (!is_shadow_present_pte(*it.sptep)) { + sp = kvm_mmu_get_page(vcpu, base_gfn, addr, + it.level - 1, true, direct_access); + link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); + } } - clear_sp_write_flooding_count(it.sptep); ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, - it.level, gw->gfn, pfn, prefault, map_writable); + it.level, base_gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); - + ++vcpu->stat.pf_fixed; return ret; out_gpte_changed: - kvm_release_pfn_clean(pfn); return RET_PF_RETRY; } @@ -740,9 +756,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int r; kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; - bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + bool force_pt_level = lpage_disallowed; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -821,6 +839,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, walker.pte_access &= ~ACC_EXEC_MASK; } + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; @@ -829,19 +848,15 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (!force_pt_level) - transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); + transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault); - ++vcpu->stat.pf_fixed; + level, pfn, map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f6adc8db0e32..52edb8cf1c40 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -608,8 +608,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; - if (!npt_enabled && !(efer & EFER_LMA)) - efer &= ~EFER_LME; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 02c0326dc259..cd5a8e888eb6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2259,17 +2259,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; - if (!enable_ept) { - /* - * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing - * host CPUID is more efficient than testing guest CPUID - * or CR4. Host SMEP is anyway a requirement for guest SMEP. - */ - if (boot_cpu_has(X86_FEATURE_SMEP)) - guest_efer |= EFER_NX; - else if (!(guest_efer & EFER_NX)) - ignore_bits |= EFER_NX; - } + /* Shadow paging assumes NX to be available. */ + if (!enable_ept) + guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4927d0f5be13..dcee3282112d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -90,8 +90,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -191,7 +191,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages) }, + { "largepages", VM_STAT(lpages, .mode = 0444) }, + { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -1070,6 +1071,14 @@ u64 kvm_get_arch_capabilities(void) rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data); /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; + + /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us @@ -1081,8 +1090,35 @@ u64 kvm_get_arch_capabilities(void) if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + data |= ARCH_CAP_RDCL_NO; + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + data |= ARCH_CAP_SSB_NO; + if (!boot_cpu_has_bug(X86_BUG_MDS)) + data |= ARCH_CAP_MDS_NO; + + /* + * On TAA affected systems, export MDS_NO=0 when: + * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1. + * - Updated microcode is present. This is detected by + * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures + * that VERW clears CPU buffers. + * + * When MDS_NO=0 is exported, guests deploy clear CPU buffer + * mitigation and don't complain: + * + * "Vulnerable: Clear CPU buffers attempted, no microcode" + * + * If TSX is disabled on the system, guests are also mitigated against + * TAA and clear CPU buffer mitigation is not required for guests. + */ + if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) && + (data & ARCH_CAP_TSX_CTRL_MSR)) + data &= ~ARCH_CAP_MDS_NO; + return data; } + EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); static int kvm_get_msr_feature(struct kvm_msr_entry *msr) @@ -6129,17 +6165,17 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) continue; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - if (vcpu->cpu != smp_processor_id()) + if (vcpu->cpu != raw_smp_processor_id()) send_ipi = 1; } } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -6276,12 +6312,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work) struct kvm_vcpu *vcpu; int i; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); atomic_set(&kvm_guest_has_master_clock, 0); - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); @@ -8334,6 +8370,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -8363,6 +8400,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } +int kvm_arch_post_init_vm(struct kvm *kvm) +{ + return kvm_mmu_post_init_vm(kvm); +} + static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { int r; @@ -8466,6 +8508,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(x86_set_memory_region); +void kvm_arch_pre_destroy_vm(struct kvm *kvm) +{ + kvm_mmu_pre_destroy_vm(kvm); +} + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { |