diff options
Diffstat (limited to 'arch/x86')
36 files changed, 778 insertions, 328 deletions
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6db4e2932b3d..65d147974f8d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ /* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6dcccb304775..ec9830d2aabf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -703,7 +703,6 @@ struct kvm_vcpu_arch { struct fpu_guest guest_fpu; u64 xcr0; - u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3faf0f97edb1..a4a39c3e0f19 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -476,6 +476,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index cc74dc584836..acbaeaf83b61 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -84,7 +84,7 @@ #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else jmp *%\reg #endif @@ -94,7 +94,7 @@ #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \ __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else call *%\reg #endif @@ -146,7 +146,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ - X86_FEATURE_RETPOLINE_AMD) + X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "r" (addr) @@ -176,7 +176,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ - X86_FEATURE_RETPOLINE_AMD) + X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif @@ -188,9 +188,11 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, - SPECTRE_V2_RETPOLINE_GENERIC, - SPECTRE_V2_RETPOLINE_AMD, - SPECTRE_V2_IBRS_ENHANCED, + SPECTRE_V2_RETPOLINE, + SPECTRE_V2_LFENCE, + SPECTRE_V2_EIBRS, + SPECTRE_V2_EIBRS_RETPOLINE, + SPECTRE_V2_EIBRS_LFENCE, }; /* The indirect branch speculation control variants */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index b00dbc5fac2b..bb2fb78523ce 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -220,6 +220,42 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) #define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2) + +/* AVIC */ +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 +#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) + +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) +#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) +#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) +#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFF) + +#define AVIC_DOORBELL_PHYSICAL_ID_MASK (0xFF) + +#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 +#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 +#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF + +enum avic_ipi_failure_cause { + AVIC_IPI_FAILURE_INVALID_INT_TYPE, + AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, + AVIC_IPI_FAILURE_INVALID_TARGET, + AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, +}; + + +/* + * 0xff is broadcast, so the max index allowed for physical APIC ID + * table is 0xfe. APIC IDs above 0xff are reserved. + */ +#define AVIC_MAX_PHYSICAL_ID_COUNT 0xff + +#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) +#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL + + struct vmcb_seg { u16 selector; u16 attrib; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5007c3ffe96f..b4470eabf151 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -389,7 +389,7 @@ static int emit_indirect(int op, int reg, u8 *bytes) * * CALL *%\reg * - * It also tries to inline spectre_v2=retpoline,amd when size permits. + * It also tries to inline spectre_v2=retpoline,lfence when size permits. */ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) { @@ -407,7 +407,7 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) BUG_ON(reg == 4); if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) && - !cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) + !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) return -1; op = insn->opcode.bytes[0]; @@ -438,9 +438,9 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) } /* - * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE. + * For RETPOLINE_LFENCE: prepend the indirect CALL/JMP with an LFENCE. */ - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { bytes[i++] = 0x0f; bytes[i++] = 0xae; bytes[i++] = 0xe8; /* LFENCE */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1c1f218a701d..6296e1ebed1d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -16,6 +16,7 @@ #include <linux/prctl.h> #include <linux/sched/smt.h> #include <linux/pgtable.h> +#include <linux/bpf.h> #include <asm/spec-ctrl.h> #include <asm/cmdline.h> @@ -650,6 +651,32 @@ static inline const char *spectre_v2_module_string(void) static inline const char *spectre_v2_module_string(void) { return ""; } #endif +#define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n" +#define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n" +#define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n" + +#ifdef CONFIG_BPF_SYSCALL +void unpriv_ebpf_notify(int new_state) +{ + if (new_state) + return; + + /* Unprivileged eBPF is enabled */ + + switch (spectre_v2_enabled) { + case SPECTRE_V2_EIBRS: + pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); + break; + case SPECTRE_V2_EIBRS_LFENCE: + if (sched_smt_active()) + pr_err(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); + break; + default: + break; + } +} +#endif + static inline bool match_option(const char *arg, int arglen, const char *opt) { int len = strlen(opt); @@ -664,7 +691,10 @@ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_FORCE, SPECTRE_V2_CMD_RETPOLINE, SPECTRE_V2_CMD_RETPOLINE_GENERIC, - SPECTRE_V2_CMD_RETPOLINE_AMD, + SPECTRE_V2_CMD_RETPOLINE_LFENCE, + SPECTRE_V2_CMD_EIBRS, + SPECTRE_V2_CMD_EIBRS_RETPOLINE, + SPECTRE_V2_CMD_EIBRS_LFENCE, }; enum spectre_v2_user_cmd { @@ -737,6 +767,13 @@ spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) return SPECTRE_V2_USER_CMD_AUTO; } +static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) +{ + return (mode == SPECTRE_V2_EIBRS || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_EIBRS_LFENCE); +} + static void __init spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) { @@ -804,7 +841,7 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return; /* @@ -824,9 +861,11 @@ set_mode: static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", - [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", - [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", - [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", + [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", + [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", + [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", + [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", + [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", }; static const struct { @@ -837,8 +876,12 @@ static const struct { { "off", SPECTRE_V2_CMD_NONE, false }, { "on", SPECTRE_V2_CMD_FORCE, true }, { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, - { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false }, + { "retpoline,lfence", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false }, { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "eibrs", SPECTRE_V2_CMD_EIBRS, false }, + { "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false }, + { "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false }, { "auto", SPECTRE_V2_CMD_AUTO, false }, }; @@ -875,10 +918,30 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if ((cmd == SPECTRE_V2_CMD_RETPOLINE || - cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || - cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if ((cmd == SPECTRE_V2_CMD_EIBRS || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { + pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE) && + !boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("%s selected, but CPU doesn't have a serializing LFENCE. Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -887,6 +950,16 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return cmd; } +static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) +{ + if (!IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("Kernel not compiled with retpoline; no mitigation available!"); + return SPECTRE_V2_NONE; + } + + return SPECTRE_V2_RETPOLINE; +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -907,49 +980,64 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_CMD_FORCE: case SPECTRE_V2_CMD_AUTO: if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { - mode = SPECTRE_V2_IBRS_ENHANCED; - /* Force it so VMEXIT will restore correctly */ - x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); - goto specv2_set_mode; + mode = SPECTRE_V2_EIBRS; + break; } - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_auto; + + mode = spectre_v2_select_retpoline(); break; - case SPECTRE_V2_CMD_RETPOLINE_AMD: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_amd; + + case SPECTRE_V2_CMD_RETPOLINE_LFENCE: + pr_err(SPECTRE_V2_LFENCE_MSG); + mode = SPECTRE_V2_LFENCE; break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_generic; + mode = SPECTRE_V2_RETPOLINE; break; + case SPECTRE_V2_CMD_RETPOLINE: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_auto; + mode = spectre_v2_select_retpoline(); + break; + + case SPECTRE_V2_CMD_EIBRS: + mode = SPECTRE_V2_EIBRS; + break; + + case SPECTRE_V2_CMD_EIBRS_LFENCE: + mode = SPECTRE_V2_EIBRS_LFENCE; + break; + + case SPECTRE_V2_CMD_EIBRS_RETPOLINE: + mode = SPECTRE_V2_EIBRS_RETPOLINE; break; } - pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); - return; -retpoline_auto: - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { - retpoline_amd: - if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); - goto retpoline_generic; - } - mode = SPECTRE_V2_RETPOLINE_AMD; - setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); - setup_force_cpu_cap(X86_FEATURE_RETPOLINE); - } else { - retpoline_generic: - mode = SPECTRE_V2_RETPOLINE_GENERIC; + if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) + pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); + + if (spectre_v2_in_eibrs_mode(mode)) { + /* Force it so VMEXIT will restore correctly */ + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + } + + switch (mode) { + case SPECTRE_V2_NONE: + case SPECTRE_V2_EIBRS: + break; + + case SPECTRE_V2_LFENCE: + case SPECTRE_V2_EIBRS_LFENCE: + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); + fallthrough; + + case SPECTRE_V2_RETPOLINE: + case SPECTRE_V2_EIBRS_RETPOLINE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + break; } -specv2_set_mode: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -975,7 +1063,7 @@ specv2_set_mode: * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) { + if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } @@ -1045,6 +1133,10 @@ void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); + if (sched_smt_active() && unprivileged_ebpf_enabled() && + spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) + pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: break; @@ -1684,7 +1776,7 @@ static ssize_t tsx_async_abort_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { @@ -1714,6 +1806,27 @@ static char *ibpb_state(void) return ""; } +static ssize_t spectre_v2_show_state(char *buf) +{ + if (spectre_v2_enabled == SPECTRE_V2_LFENCE) + return sprintf(buf, "Vulnerable: LFENCE\n"); + + if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) + return sprintf(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); + + if (sched_smt_active() && unprivileged_ebpf_enabled() && + spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) + return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); + + return sprintf(buf, "%s%s%s%s%s%s\n", + spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + spectre_v2_module_string()); +} + static ssize_t srbds_show_state(char *buf) { return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); @@ -1739,12 +1852,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: - return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", - spectre_v2_module_string()); + return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 48afe96ae0f0..7c63a1911fae 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -13,6 +13,30 @@ #include "sgx.h" /* + * Calculate byte offset of a PCMD struct associated with an enclave page. PCMD's + * follow right after the EPC data in the backing storage. In addition to the + * visible enclave pages, there's one extra page slot for SECS, before PCMD + * structs. + */ +static inline pgoff_t sgx_encl_get_backing_page_pcmd_offset(struct sgx_encl *encl, + unsigned long page_index) +{ + pgoff_t epc_end_off = encl->size + sizeof(struct sgx_secs); + + return epc_end_off + page_index * sizeof(struct sgx_pcmd); +} + +/* + * Free a page from the backing storage in the given page index. + */ +static inline void sgx_encl_truncate_backing_page(struct sgx_encl *encl, unsigned long page_index) +{ + struct inode *inode = file_inode(encl->backing); + + shmem_truncate_range(inode, PFN_PHYS(page_index), PFN_PHYS(page_index) + PAGE_SIZE - 1); +} + +/* * ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC * Pages" in the SDM. */ @@ -22,9 +46,11 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, { unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK; struct sgx_encl *encl = encl_page->encl; + pgoff_t page_index, page_pcmd_off; struct sgx_pageinfo pginfo; struct sgx_backing b; - pgoff_t page_index; + bool pcmd_page_empty; + u8 *pcmd_page; int ret; if (secs_page) @@ -32,14 +58,16 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, else page_index = PFN_DOWN(encl->size); + page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); + ret = sgx_encl_get_backing(encl, page_index, &b); if (ret) return ret; pginfo.addr = encl_page->desc & PAGE_MASK; pginfo.contents = (unsigned long)kmap_atomic(b.contents); - pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) + - b.pcmd_offset; + pcmd_page = kmap_atomic(b.pcmd); + pginfo.metadata = (unsigned long)pcmd_page + b.pcmd_offset; if (secs_page) pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page); @@ -55,11 +83,24 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, ret = -EFAULT; } - kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset)); + memset(pcmd_page + b.pcmd_offset, 0, sizeof(struct sgx_pcmd)); + + /* + * The area for the PCMD in the page was zeroed above. Check if the + * whole page is now empty meaning that all PCMD's have been zeroed: + */ + pcmd_page_empty = !memchr_inv(pcmd_page, 0, PAGE_SIZE); + + kunmap_atomic(pcmd_page); kunmap_atomic((void *)(unsigned long)pginfo.contents); sgx_encl_put_backing(&b, false); + sgx_encl_truncate_backing_page(encl, page_index); + + if (pcmd_page_empty) + sgx_encl_truncate_backing_page(encl, PFN_DOWN(page_pcmd_off)); + return ret; } @@ -579,7 +620,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { - pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5); + pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); struct page *contents; struct page *pcmd; @@ -587,7 +628,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, if (IS_ERR(contents)) return PTR_ERR(contents); - pcmd = sgx_encl_get_backing_page(encl, pcmd_index); + pcmd = sgx_encl_get_backing_page(encl, PFN_DOWN(page_pcmd_off)); if (IS_ERR(pcmd)) { put_page(contents); return PTR_ERR(pcmd); @@ -596,9 +637,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, backing->page_index = page_index; backing->contents = contents; backing->pcmd = pcmd; - backing->pcmd_offset = - (page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) * - sizeof(struct sgx_pcmd); + backing->pcmd_offset = page_pcmd_off & (PAGE_SIZE - 1); return 0; } diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 4b41efc9e367..8e4bc6453d26 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -344,10 +344,8 @@ static void sgx_reclaim_pages(void) { struct sgx_epc_page *chunk[SGX_NR_TO_SCAN]; struct sgx_backing backing[SGX_NR_TO_SCAN]; - struct sgx_epc_section *section; struct sgx_encl_page *encl_page; struct sgx_epc_page *epc_page; - struct sgx_numa_node *node; pgoff_t page_index; int cnt = 0; int ret; @@ -418,13 +416,7 @@ skip: kref_put(&encl_page->encl->refcount, sgx_encl_release); epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED; - section = &sgx_epc_sections[epc_page->section]; - node = section->node; - - spin_lock(&node->lock); - list_add_tail(&epc_page->list, &node->free_page_list); - spin_unlock(&node->lock); - atomic_long_inc(&sgx_nr_free_pages); + sgx_free_epc_page(epc_page); } } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index bc0657f0deed..f267205f2d5a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -995,8 +995,10 @@ early_param("memmap", parse_memmap_opt); */ void __init e820__reserve_setup_data(void) { + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; + u32 len; pa_data = boot_params.hdr.setup_data; if (!pa_data) @@ -1004,6 +1006,14 @@ void __init e820__reserve_setup_data(void) while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); + if (!data) { + pr_warn("e820: failed to memremap setup_data entry\n"); + return; + } + + len = sizeof(*data); + pa_next = data->next; + e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* @@ -1015,18 +1025,27 @@ void __init e820__reserve_setup_data(void) sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - e820__range_update(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - e820__range_update_kexec(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + if (data->type == SETUP_INDIRECT) { + len += data->len; + early_memunmap(data, sizeof(*data)); + data = early_memremap(pa_data, len); + if (!data) { + pr_warn("e820: failed to memremap indirect setup_data\n"); + return; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + e820__range_update(indirect->addr, indirect->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + e820__range_update_kexec(indirect->addr, indirect->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + } } - pa_data = data->next; - early_memunmap(data, sizeof(*data)); + pa_data = pa_next; + early_memunmap(data, len); } e820__update_table(e820_table); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 437d7c930c0b..75ffaef8c299 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -91,11 +91,9 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { struct fpu *fpu = &target->thread.fpu; - struct user32_fxsr_struct newstate; + struct fxregs_state newstate; int ret; - BUILD_BUG_ON(sizeof(newstate) != sizeof(struct fxregs_state)); - if (!cpu_feature_enabled(X86_FEATURE_FXSR)) return -ENODEV; @@ -116,9 +114,10 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, /* Copy the state */ memcpy(&fpu->fpstate->regs.fxsave, &newstate, sizeof(newstate)); - /* Clear xmm8..15 */ + /* Clear xmm8..15 for 32-bit callers */ BUILD_BUG_ON(sizeof(fpu->__fpstate.regs.fxsave.xmm_space) != 16 * 16); - memset(&fpu->fpstate->regs.fxsave.xmm_space[8], 0, 8 * 16); + if (in_ia32_syscall()) + memset(&fpu->fpstate->regs.fxsave.xmm_space[8*4], 0, 8 * 16); /* Mark FP and SSE as in use when XSAVE is enabled */ if (use_xsave()) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 02b3ddaf4f75..7c7824ae7862 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1558,7 +1558,10 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; - newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; + + if (!guest_fpu) + newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; + newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 64b6da95af98..e2e89bebcbc3 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -88,11 +88,13 @@ create_setup_data_node(struct dentry *parent, int no, static int __init create_setup_data_nodes(struct dentry *parent) { + struct setup_indirect *indirect; struct setup_data_node *node; struct setup_data *data; - int error; + u64 pa_data, pa_next; struct dentry *d; - u64 pa_data; + int error; + u32 len; int no = 0; d = debugfs_create_dir("setup_data", parent); @@ -112,12 +114,29 @@ static int __init create_setup_data_nodes(struct dentry *parent) error = -ENOMEM; goto err_dir; } - - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - node->paddr = ((struct setup_indirect *)data->data)->addr; - node->type = ((struct setup_indirect *)data->data)->type; - node->len = ((struct setup_indirect *)data->data)->len; + pa_next = data->next; + + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(pa_data, len, MEMREMAP_WB); + if (!data) { + kfree(node); + error = -ENOMEM; + goto err_dir; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + node->paddr = indirect->addr; + node->type = indirect->type; + node->len = indirect->len; + } else { + node->paddr = pa_data; + node->type = data->type; + node->len = data->len; + } } else { node->paddr = pa_data; node->type = data->type; @@ -125,7 +144,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) } create_setup_data_node(d, no, node); - pa_data = data->next; + pa_data = pa_next; memunmap(data); no++; diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index d0a19121c6a4..257892fcefa7 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -91,26 +91,41 @@ static int get_setup_data_paddr(int nr, u64 *paddr) static int __init get_setup_data_size(int nr, size_t *size) { - int i = 0; + u64 pa_data = boot_params.hdr.setup_data, pa_next; + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data = boot_params.hdr.setup_data; + int i = 0; + u32 len; while (pa_data) { data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; + pa_next = data->next; + if (nr == i) { - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) - *size = ((struct setup_indirect *)data->data)->len; - else + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(pa_data, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) + *size = indirect->len; + else + *size = data->len; + } else { *size = data->len; + } memunmap(data); return 0; } - pa_data = data->next; + pa_data = pa_next; memunmap(data); i++; } @@ -120,9 +135,11 @@ static int __init get_setup_data_size(int nr, size_t *size) static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { + struct setup_indirect *indirect; + struct setup_data *data; int nr, ret; u64 paddr; - struct setup_data *data; + u32 len; ret = kobj_to_setup_data_nr(kobj, &nr); if (ret) @@ -135,10 +152,20 @@ static ssize_t type_show(struct kobject *kobj, if (!data) return -ENOMEM; - if (data->type == SETUP_INDIRECT) - ret = sprintf(buf, "0x%x\n", ((struct setup_indirect *)data->data)->type); - else + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(paddr, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + ret = sprintf(buf, "0x%x\n", indirect->type); + } else { ret = sprintf(buf, "0x%x\n", data->type); + } + memunmap(data); return ret; } @@ -149,9 +176,10 @@ static ssize_t setup_data_data_read(struct file *fp, char *buf, loff_t off, size_t count) { + struct setup_indirect *indirect; + struct setup_data *data; int nr, ret = 0; u64 paddr, len; - struct setup_data *data; void *p; ret = kobj_to_setup_data_nr(kobj, &nr); @@ -165,10 +193,27 @@ static ssize_t setup_data_data_read(struct file *fp, if (!data) return -ENOMEM; - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - paddr = ((struct setup_indirect *)data->data)->addr; - len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(paddr, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } else { + /* + * Even though this is technically undefined, return + * the data as though it is a normal setup_data struct. + * This will at least allow it to be inspected. + */ + paddr += sizeof(*data); + len = data->len; + } } else { paddr += sizeof(*data); len = data->len; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a438217cbfac..d77481ecb0d5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -462,19 +462,24 @@ static bool pv_tlb_flush_supported(void) { return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && + !boot_cpu_has(X86_FEATURE_MWAIT) && + (num_possible_cpus() != 1)); } static bool pv_ipi_supported(void) { - return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI); + return (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI) && + (num_possible_cpus() != 1)); } static bool pv_sched_yield_supported(void) { return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && + !boot_cpu_has(X86_FEATURE_MWAIT) && + (num_possible_cpus() != 1)); } #define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) @@ -619,7 +624,7 @@ static void kvm_smp_send_call_func_ipi(const struct cpumask *mask) /* Make sure other vCPUs get a chance to run if they need to. */ for_each_cpu(cpu, mask) { - if (vcpu_is_preempted(cpu)) { + if (!idle_cpu(cpu) && vcpu_is_preempted(cpu)) { kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu)); break; } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index a35cbf9107af..c5caa7311bd8 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -239,6 +239,9 @@ static void __init kvmclock_init_mem(void) static int __init kvm_setup_vsyscall_timeinfo(void) { + if (!kvm_para_available() || !kvmclock) + return 0; + kvmclock_init_mem(); #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 95fa745e310a..96d7c27b7093 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -273,6 +273,14 @@ int module_finalize(const Elf_Ehdr *hdr, retpolines = s; } + /* + * See alternative_instructions() for the ordering rules between the + * various patching types. + */ + if (para) { + void *pseg = (void *)para->sh_addr; + apply_paravirt(pseg, pseg + para->sh_size); + } if (retpolines) { void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); @@ -290,11 +298,6 @@ int module_finalize(const Elf_Ehdr *hdr, tseg, tseg + text->sh_size); } - if (para) { - void *pseg = (void *)para->sh_addr; - apply_paravirt(pseg, pseg + para->sh_size); - } - /* make jump label nops */ jump_label_apply_nops(me); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 6d2244c94799..8d2f2f995539 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1224,7 +1224,7 @@ static struct user_regset x86_64_regsets[] __ro_after_init = { }, [REGSET_FP] = { .core_note_type = NT_PRFPREG, - .n = sizeof(struct user_i387_struct) / sizeof(long), + .n = sizeof(struct fxregs_state) / sizeof(long), .size = sizeof(long), .align = sizeof(long), .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set }, @@ -1271,7 +1271,7 @@ static struct user_regset x86_32_regsets[] __ro_after_init = { }, [REGSET_XFP] = { .core_note_type = NT_PRXFPREG, - .n = sizeof(struct user32_fxsr_struct) / sizeof(u32), + .n = sizeof(struct fxregs_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set }, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f7a132eb794d..90d7e1788c91 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -369,21 +369,41 @@ static void __init parse_setup_data(void) static void __init memblock_x86_reserve_range_setup_data(void) { + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; + u32 len; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); + if (!data) { + pr_warn("setup: failed to memremap setup_data entry\n"); + return; + } + + len = sizeof(*data); + pa_next = data->next; + memblock_reserve(pa_data, sizeof(*data) + data->len); - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) - memblock_reserve(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len); + if (data->type == SETUP_INDIRECT) { + len += data->len; + early_memunmap(data, sizeof(*data)); + data = early_memremap(pa_data, len); + if (!data) { + pr_warn("setup: failed to memremap indirect setup_data\n"); + return; + } - pa_data = data->next; - early_memunmap(data, sizeof(*data)); + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) + memblock_reserve(indirect->addr, indirect->len); + } + + pa_data = pa_next; + early_memunmap(data, len); } } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c9d566dcf89a..8143693a7ea6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -659,6 +659,7 @@ static bool do_int3(struct pt_regs *regs) return res == NOTIFY_STOP; } +NOKPROBE_SYMBOL(do_int3); static void do_int3_user(struct pt_regs *regs) { diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 494d4d351859..b8f8d268d058 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -282,6 +282,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; + u64 guest_supported_xcr0; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (best && apic) { @@ -293,9 +294,11 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - vcpu->arch.guest_supported_xcr0 = + guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); + vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0; + kvm_update_pv_runtime(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d7e6fde82d25..9322e6340a74 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2306,7 +2306,12 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) apic->irr_pending = true; apic->isr_count = 1; } else { - apic->irr_pending = (apic_search_irr(apic) != -1); + /* + * Don't clear irr_pending, searching the IRR can race with + * updates from the CPU as APICv is still active from hardware's + * perspective. The flag will be cleared as appropriate when + * KVM injects the interrupt. + */ apic->isr_count = count_vectors(apic->regs + APIC_ISR); } } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 593093b52395..5628d0ba637e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3565,7 +3565,7 @@ set_root_pgd: out_unlock: write_unlock(&vcpu->kvm->mmu_lock); - return 0; + return r; } static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) @@ -3889,12 +3889,23 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } +static u32 alloc_apf_token(struct kvm_vcpu *vcpu) +{ + /* make sure the token value is not 0 */ + u32 id = vcpu->arch.apf.id; + + if (id << 12 == 0) + vcpu->arch.apf.id = 1; + + return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; +} + static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, gfn_t gfn) { struct kvm_arch_async_pf arch; - arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; + 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); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index f614f95acc6b..b1a02993782b 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -95,7 +95,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, } static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, - unsigned config, bool exclude_user, + u64 config, bool exclude_user, bool exclude_kernel, bool intr, bool in_tx, bool in_tx_cp) { @@ -181,7 +181,8 @@ static int cmp_u64(const void *a, const void *b) void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { - unsigned config, type = PERF_TYPE_RAW; + u64 config; + u32 type = PERF_TYPE_RAW; struct kvm *kvm = pmc->vcpu->kvm; struct kvm_pmu_event_filter *filter; bool allow_event = true; @@ -220,7 +221,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) } if (type == PERF_TYPE_RAW) - config = eventsel & X86_RAW_EVENT_MASK; + config = eventsel & AMD64_RAW_EVENT_MASK; if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) return; diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 90364d02f22a..fb3e20791338 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,20 +27,6 @@ #include "irq.h" #include "svm.h" -#define SVM_AVIC_DOORBELL 0xc001011b - -#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) - -/* - * 0xff is broadcast, so the max index allowed for physical APIC ID - * table is 0xfe. APIC IDs above 0xff are reserved. - */ -#define AVIC_MAX_PHYSICAL_ID_COUNT 255 - -#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 -#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 -#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF - /* AVIC GATAG is encoded using VM and VCPU IDs */ #define AVIC_VCPU_ID_BITS 8 #define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) @@ -73,12 +59,6 @@ struct amd_svm_iommu_ir { void *data; /* Storing pointer to struct amd_ir_data */ }; -enum avic_ipi_failure_cause { - AVIC_IPI_FAILURE_INVALID_INT_TYPE, - AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, - AVIC_IPI_FAILURE_INVALID_TARGET, - AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, -}; /* Note: * This function is called from IOMMU driver to notify @@ -289,6 +269,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +void avic_ring_doorbell(struct kvm_vcpu *vcpu) +{ + /* + * Note, the vCPU could get migrated to a different pCPU at any point, + * which could result in signalling the wrong/previous pCPU. But if + * that happens the vCPU is guaranteed to do a VMRUN (after being + * migrated) and thus will process pending interrupts, i.e. a doorbell + * is not needed (and the spurious one is harmless). + */ + int cpu = READ_ONCE(vcpu->cpu); + + if (cpu != get_cpu()) + wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); + put_cpu(); +} + static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { @@ -304,8 +300,13 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, kvm_for_each_vcpu(i, vcpu, kvm) { if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & APIC_DEST_MASK)) - kvm_vcpu_wake_up(vcpu); + icrl & APIC_DEST_MASK)) { + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); + } } } @@ -345,8 +346,6 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh); break; case AVIC_IPI_FAILURE_INVALID_TARGET: - WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n", - index, vcpu->vcpu_id, icrh, icrl); break; case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); @@ -669,52 +668,6 @@ void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) -{ - if (!vcpu->arch.apicv_active) - return -1; - - kvm_lapic_set_irr(vec, vcpu->arch.apic); - - /* - * Pairs with the smp_mb_*() after setting vcpu->guest_mode in - * vcpu_enter_guest() to ensure the write to the vIRR is ordered before - * the read of guest_mode, which guarantees that either VMRUN will see - * and process the new vIRR entry, or that the below code will signal - * the doorbell if the vCPU is already running in the guest. - */ - smp_mb__after_atomic(); - - /* - * Signal the doorbell to tell hardware to inject the IRQ if the vCPU - * is in the guest. If the vCPU is not in the guest, hardware will - * automatically process AVIC interrupts at VMRUN. - */ - if (vcpu->mode == IN_GUEST_MODE) { - int cpu = READ_ONCE(vcpu->cpu); - - /* - * Note, the vCPU could get migrated to a different pCPU at any - * point, which could result in signalling the wrong/previous - * pCPU. But if that happens the vCPU is guaranteed to do a - * VMRUN (after being migrated) and thus will process pending - * interrupts, i.e. a doorbell is not needed (and the spurious - * one is harmless). - */ - if (cpu != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); - put_cpu(); - } else { - /* - * Wake the vCPU if it was blocking. KVM will then detect the - * pending IRQ when checking if the vCPU has a wake event. - */ - kvm_vcpu_wake_up(vcpu); - } - - return 0; -} - bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { return false; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 1218b5a342fc..39d280e7e80e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1457,18 +1457,6 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, !__nested_vmcb_check_save(vcpu, &save_cached)) goto out_free; - /* - * While the nested guest CR3 is already checked and set by - * KVM_SET_SREGS, it was set when nested state was yet loaded, - * thus MMU might not be initialized correctly. - * Set it again to fix this. - */ - - ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, - nested_npt_enabled(svm), false); - if (WARN_ON_ONCE(ret)) - goto out_free; - /* * All checks done, we can enter guest mode. Userspace provides @@ -1494,6 +1482,20 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm_switch_vmcb(svm, &svm->nested.vmcb02); nested_vmcb02_prepare_control(svm); + + /* + * While the nested guest CR3 is already checked and set by + * KVM_SET_SREGS, it was set when nested state was yet loaded, + * thus MMU might not be initialized correctly. + * Set it again to fix this. + */ + + ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, + nested_npt_enabled(svm), false); + if (WARN_ON_ONCE(ret)) + goto out_free; + + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); ret = 0; out_free: diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index a290efb272ad..fd3a00c892c7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1585,6 +1585,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); u64 hcr0 = cr0; + bool old_paging = is_paging(vcpu); #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { @@ -1601,8 +1602,11 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) #endif vcpu->arch.cr0 = cr0; - if (!npt_enabled) + if (!npt_enabled) { hcr0 |= X86_CR0_PG | X86_CR0_WP; + if (old_paging != is_paging(vcpu)) + svm_set_cr4(vcpu, kvm_read_cr4(vcpu)); + } /* * re-enable caching here because the QEMU bios @@ -1646,8 +1650,12 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) svm_flush_tlb(vcpu); vcpu->arch.cr4 = cr4; - if (!npt_enabled) + if (!npt_enabled) { cr4 |= X86_CR4_PAE; + + if (!is_paging(vcpu)) + cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); + } cr4 |= host_cr4_mce; to_svm(vcpu)->vmcb->save.cr4 = cr4; vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -2685,8 +2693,23 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; switch (ecx) { case MSR_AMD64_TSC_RATIO: - if (!msr->host_initiated && !svm->tsc_scaling_enabled) - return 1; + + if (!svm->tsc_scaling_enabled) { + + if (!msr->host_initiated) + return 1; + /* + * In case TSC scaling is not enabled, always + * leave this MSR at the default value. + * + * Due to bug in qemu 6.2.0, it would try to set + * this msr to 0 if tsc scaling is not enabled. + * Ignore this value as well. + */ + if (data != 0 && data != svm->tsc_ratio_msr) + return 1; + break; + } if (data & TSC_RATIO_RSVD) return 1; @@ -3291,21 +3314,55 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } -static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, - int trig_mode, int vector) +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vector) { - struct kvm_vcpu *vcpu = apic->vcpu; + /* + * vcpu->arch.apicv_active must be read after vcpu->mode. + * Pairs with smp_store_release in vcpu_enter_guest. + */ + bool in_guest_mode = (smp_load_acquire(&vcpu->mode) == IN_GUEST_MODE); - if (svm_deliver_avic_intr(vcpu, vector)) { - kvm_lapic_set_irr(vector, apic); + if (!READ_ONCE(vcpu->arch.apicv_active)) { + /* Process the interrupt via inject_pending_event */ kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); + return; + } + + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); + if (in_guest_mode) { + /* + * Signal the doorbell to tell hardware to inject the IRQ. If + * the vCPU exits the guest before the doorbell chimes, hardware + * will automatically process AVIC interrupts at the next VMRUN. + */ + avic_ring_doorbell(vcpu); } else { - trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, - trig_mode, vector); + /* + * Wake the vCPU if it was blocking. KVM will then detect the + * pending IRQ when checking if the vCPU has a wake event. + */ + kvm_vcpu_wake_up(vcpu); } } +static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + kvm_lapic_set_irr(vector, apic); + + /* + * Pairs with the smp_mb_*() after setting vcpu->guest_mode in + * vcpu_enter_guest() to ensure the write to the vIRR is ordered before + * the read of guest_mode. This guarantees that either VMRUN will see + * and process the new vIRR entry, or that svm_complete_interrupt_delivery + * will signal the doorbell if the CPU has already entered the guest. + */ + smp_mb__after_atomic(); + svm_complete_interrupt_delivery(apic->vcpu, delivery_mode, trig_mode, vector); +} + static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3353,11 +3410,13 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_nmi_blocked(vcpu)) + return 0; + /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return -EBUSY; - - return !svm_nmi_blocked(vcpu); + return 1; } static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) @@ -3409,9 +3468,13 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_interrupt_blocked(vcpu)) + return 0; + /* * An IRQ must not be injected into L2 if it's supposed to VM-Exit, * e.g. if the IRQ arrived asynchronously after checking nested events. @@ -3419,7 +3482,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm)) return -EBUSY; - return !svm_interrupt_blocked(vcpu); + return 1; } static void svm_enable_irq_window(struct kvm_vcpu *vcpu) @@ -4150,11 +4213,14 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_smi_blocked(vcpu)) + return 0; + /* An SMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_smi(svm)) return -EBUSY; - return !svm_smi_blocked(vcpu); + return 1; } static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) @@ -4248,11 +4314,18 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) * Enter the nested guest now */ + vmcb_mark_all_dirty(svm->vmcb01.ptr); + vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); + if (ret) + goto unmap_save; + + svm->nested.nested_run_pending = 1; + unmap_save: kvm_vcpu_unmap(vcpu, &map_save, true); unmap_map: @@ -4637,6 +4710,7 @@ static __init void svm_set_cpu_caps(void) /* CPUID 0x80000001 and 0x8000000A (SVM features) */ if (nested) { kvm_cpu_cap_set(X86_FEATURE_SVM); + kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN); if (nrips) kvm_cpu_cap_set(X86_FEATURE_NRIPS); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 73525353e424..fa98d6844728 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -489,6 +489,8 @@ void svm_set_gif(struct vcpu_svm *svm, bool value); int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code); void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, int read, int write); +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vec); /* nested.c */ @@ -556,17 +558,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ -#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) -#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 -#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) - -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) -#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) -#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) - -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); @@ -583,12 +574,12 @@ bool svm_check_apicv_inhibit_reasons(ulong bit); void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec); bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu); int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); +void avic_ring_doorbell(struct kvm_vcpu *vcpu); /* sev.c */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ba34e94049c7..dc822a1d403d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -246,8 +246,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, src = &prev->host_state; dest = &vmx->loaded_vmcs->host_state; - vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel, - src->fs_base, src->gs_base); + vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base); dest->ldt_sel = src->ldt_sel; #ifdef CONFIG_X86_64 dest->ds_sel = src->ds_sel; @@ -3056,7 +3055,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr4; + unsigned long cr3, cr4; bool vm_fail; if (!nested_early_check) @@ -3079,6 +3078,12 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) */ vmcs_writel(GUEST_RFLAGS, 0); + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->loaded_vmcs->host_state.cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 6c27bd0c89e1..b730d799c26e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1080,14 +1080,9 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } -void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, - u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base) +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base) { - if (unlikely(cr3 != host->cr3)) { - vmcs_writel(HOST_CR3, cr3); - host->cr3 = cr3; - } if (unlikely(fs_sel != host->fs_sel)) { if (!(fs_sel & 7)) vmcs_write16(HOST_FS_SELECTOR, fs_sel); @@ -1182,9 +1177,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) gs_base = segment_base(gs_sel); #endif - vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(), - fs_sel, gs_sel, fs_base, gs_base); - + vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); vmx->guest_state_loaded = true; } @@ -6791,7 +6784,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr4; + unsigned long cr3, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -6834,6 +6827,19 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; + /* + * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately + * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time + * it switches back to the current->mm, which can occur in KVM context + * when switching to a temporary mm to patch kernel code, e.g. if KVM + * toggles a static key while handling a VM-Exit. + */ + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->loaded_vmcs->host_state.cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -7659,6 +7665,7 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (ret) return ret; + vmx->nested.nested_run_pending = 1; vmx->nested.smm.guest_mode = false; } return 0; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f2c82e7f38f..9c6bfcd84008 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -374,9 +374,8 @@ int allocate_vpid(void); void free_vpid(int vpid); void vmx_set_constant_host_state(struct vcpu_vmx *vmx); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); -void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, - u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base); +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7131d735b1ef..eb4029660bd9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -984,6 +984,18 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); +static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_fpu.fpstate->user_xfeatures; +} + +#ifdef CONFIG_X86_64 +static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) +{ + return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; +} +#endif + static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; @@ -1003,7 +1015,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ - valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; + valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; @@ -2351,10 +2363,12 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } +#ifdef CONFIG_X86_64 static inline int gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } +#endif static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { @@ -3706,8 +3720,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); @@ -3717,8 +3730,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; vcpu->arch.guest_fpu.xfd_err = data; @@ -4233,6 +4245,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_SYS_ATTRIBUTES: + case KVM_CAP_ENABLE_CAP: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -8942,6 +8955,13 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; + /* + * When tsc is in permanent catchup mode guests won't be able to use + * pvclock_read_retry loop to get consistent view of pvclock + */ + if (vcpu->arch.tsc_always_catchup) + return -KVM_EOPNOTSUPP; + if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; @@ -9160,6 +9180,7 @@ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) likely(!pic_in_kernel(vcpu->kvm)); } +/* Called within kvm->srcu read side. */ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; @@ -9168,16 +9189,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - /* - * The call to kvm_ready_for_interrupt_injection() may end up in - * kvm_xen_has_interrupt() which may require the srcu lock to be - * held, to protect against changes in the vcpu_info address. - */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; @@ -9795,6 +9809,7 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); /* + * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. @@ -9983,7 +9998,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * result in virtual interrupt delivery. */ local_irq_disable(); - vcpu->mode = IN_GUEST_MODE; + + /* Store vcpu->apicv_active before vcpu->mode. */ + smp_store_release(&vcpu->mode, IN_GUEST_MODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -10171,6 +10188,7 @@ out: return r; } +/* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10230,12 +10248,12 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted); } +/* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; struct kvm *kvm = vcpu->kvm; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -10263,14 +10281,12 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (__xfer_to_guest_mode_work_pending()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); r = xfer_to_guest_mode_handle_work(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (r) return r; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - return r; } @@ -10376,6 +10392,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; + struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10383,6 +10400,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10393,7 +10411,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * use before KVM has ever run the vCPU. */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); + + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; @@ -10453,8 +10475,9 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - kvm_sigset_deactivate(vcpu); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); return r; } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index bad57535fad0..74be1fda58e3 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -133,32 +133,57 @@ static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) { struct kvm_vcpu_xen *vx = &v->arch.xen; + struct gfn_to_hva_cache *ghc = &vx->runstate_cache; + struct kvm_memslots *slots = kvm_memslots(v->kvm); + bool atomic = (state == RUNSTATE_runnable); uint64_t state_entry_time; - unsigned int offset; + int __user *user_state; + uint64_t __user *user_times; kvm_xen_update_runstate(v, state); if (!vx->runstate_set) return; - BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + if (unlikely(slots->generation != ghc->generation || kvm_is_error_hva(ghc->hva)) && + kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len)) + return; + + /* We made sure it fits in a single page */ + BUG_ON(!ghc->memslot); + + if (atomic) + pagefault_disable(); - offset = offsetof(struct compat_vcpu_runstate_info, state_entry_time); -#ifdef CONFIG_X86_64 /* - * The only difference is alignment of uint64_t in 32-bit. - * So the first field 'state' is accessed directly using - * offsetof() (where its offset happens to be zero), while the - * remaining fields which are all uint64_t, start at 'offset' - * which we tweak here by adding 4. + * The only difference between 32-bit and 64-bit versions of the + * runstate struct us the alignment of uint64_t in 32-bit, which + * means that the 64-bit version has an additional 4 bytes of + * padding after the first field 'state'. + * + * So we use 'int __user *user_state' to point to the state field, + * and 'uint64_t __user *user_times' for runstate_entry_time. So + * the actual array of time[] in each state starts at user_times[1]. */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != 0); + BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state) != 0); + user_state = (int __user *)ghc->hva; + + BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct compat_vcpu_runstate_info, + state_entry_time)); +#ifdef CONFIG_X86_64 BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4); BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) != offsetof(struct compat_vcpu_runstate_info, time) + 4); if (v->kvm->arch.xen.long_mode) - offset = offsetof(struct vcpu_runstate_info, state_entry_time); + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct vcpu_runstate_info, + state_entry_time)); #endif /* * First write the updated state_entry_time at the appropriate @@ -172,10 +197,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + if (__put_user(state_entry_time, user_times)) + goto out; smp_wmb(); /* @@ -189,11 +212,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) != sizeof(vx->current_runstate)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->current_runstate, - offsetof(struct vcpu_runstate_info, state), - sizeof(vx->current_runstate))) - return; + if (__put_user(vx->current_runstate, user_state)) + goto out; /* * Write the actual runstate times immediately after the @@ -208,24 +228,23 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof(vx->runstate_times)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->runstate_times[0], - offset + sizeof(u64), - sizeof(vx->runstate_times))) - return; - + if (__copy_to_user(user_times + 1, vx->runstate_times, sizeof(vx->runstate_times))) + goto out; smp_wmb(); /* * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's * runstate_entry_time field. */ - state_entry_time &= ~XEN_RUNSTATE_UPDATE; - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + __put_user(state_entry_time, user_times); + smp_wmb(); + + out: + mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + + if (atomic) + pagefault_enable(); } int __kvm_xen_has_interrupt(struct kvm_vcpu *v) @@ -443,6 +462,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache, data->u.gpa, @@ -460,6 +485,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct pvclock_vcpu_time_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache, data->u.gpa, @@ -481,6 +512,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_runstate_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.runstate_cache, data->u.gpa, diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 89b3fb244e15..afbdda539b80 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -34,7 +34,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE .endm diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 026031b3b782..17a492c27306 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -615,6 +615,7 @@ static bool memremap_is_efi_data(resource_size_t phys_addr, static bool memremap_is_setup_data(resource_size_t phys_addr, unsigned long size) { + struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; @@ -627,6 +628,10 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, data = memremap(paddr, sizeof(*data), MEMREMAP_WB | MEMREMAP_DEC); + if (!data) { + pr_warn("failed to memremap setup_data entry\n"); + return false; + } paddr_next = data->next; len = data->len; @@ -636,10 +641,21 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, return true; } - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - paddr = ((struct setup_indirect *)data->data)->addr; - len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + memunmap(data); + data = memremap(paddr, sizeof(*data) + len, + MEMREMAP_WB | MEMREMAP_DEC); + if (!data) { + pr_warn("failed to memremap indirect setup_data\n"); + return false; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } } memunmap(data); @@ -660,22 +676,51 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, unsigned long size) { + struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; paddr = boot_params.hdr.setup_data; while (paddr) { - unsigned int len; + unsigned int len, size; if (phys_addr == paddr) return true; data = early_memremap_decrypted(paddr, sizeof(*data)); + if (!data) { + pr_warn("failed to early memremap setup_data entry\n"); + return false; + } + + size = sizeof(*data); paddr_next = data->next; len = data->len; - early_memunmap(data, sizeof(*data)); + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) { + early_memunmap(data, sizeof(*data)); + return true; + } + + if (data->type == SETUP_INDIRECT) { + size += len; + early_memunmap(data, sizeof(*data)); + data = early_memremap_decrypted(paddr, size); + if (!data) { + pr_warn("failed to early memremap indirect setup_data\n"); + return false; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } + } + + early_memunmap(data, size); if ((phys_addr > paddr) && (phys_addr < (paddr + len))) return true; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2b1e266ff95c..0ecb140864b2 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -394,7 +394,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) u8 *prog = *pprog; #ifdef CONFIG_RETPOLINE - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { |