diff options
Diffstat (limited to 'arch/x86/kernel/cpu')
23 files changed, 1531 insertions, 691 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d7e3ceaf75c1..4350f6bfc064 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -27,7 +27,7 @@ obj-y += cpuid-deps.o obj-y += umwait.o obj-$(CONFIG_PROC_FS) += proc.o -obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o +obj-y += capflags.o powerflags.o obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o ifdef CONFIG_CPU_SUP_INTEL @@ -54,7 +54,6 @@ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o obj-$(CONFIG_ACRN_GUEST) += acrn.o -ifdef CONFIG_X86_FEATURE_NAMES quiet_cmd_mkcapflags = MKCAP $@ cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^ @@ -63,5 +62,4 @@ vmxfeature = $(src)/../../include/asm/vmxfeatures.h $(obj)/capflags.c: $(cpufeature) $(vmxfeature) $(src)/mkcapflags.sh FORCE $(call if_changed,mkcapflags) -endif targets += capflags.c diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 571abf808ea3..7eca6a8abbb1 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -27,11 +27,6 @@ #include "cpu.h" -static const int amd_erratum_383[]; -static const int amd_erratum_400[]; -static const int amd_erratum_1054[]; -static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); - /* * nodes_per_socket: Stores the number of nodes per socket. * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX @@ -39,6 +34,83 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); */ static u32 nodes_per_socket = 1; +/* + * AMD errata checking + * + * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or + * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that + * have an OSVW id assigned, which it takes as first argument. Both take a + * variable number of family-specific model-stepping ranges created by + * AMD_MODEL_RANGE(). + * + * Example: + * + * const int amd_erratum_319[] = + * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), + * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), + * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); + */ + +#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } +#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } +#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ + ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) +#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) +#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) +#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) + +static const int amd_erratum_400[] = + AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), + AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); + +static const int amd_erratum_383[] = + AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); + +/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ +static const int amd_erratum_1054[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); + +static const int amd_zenbleed[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf), + AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), + AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf), + AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); + +static const int amd_div0[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), + AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); + +static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) +{ + int osvw_id = *erratum++; + u32 range; + u32 ms; + + if (osvw_id >= 0 && osvw_id < 65536 && + cpu_has(cpu, X86_FEATURE_OSVW)) { + u64 osvw_len; + + rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); + if (osvw_id < osvw_len) { + u64 osvw_bits; + + rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), + osvw_bits); + return osvw_bits & (1ULL << (osvw_id & 0x3f)); + } + } + + /* OSVW unavailable or ID unknown, match family-model-stepping range */ + ms = (cpu->x86_model << 4) | cpu->x86_stepping; + while ((range = *erratum++)) + if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && + (ms >= AMD_MODEL_RANGE_START(range)) && + (ms <= AMD_MODEL_RANGE_END(range))) + return true; + + return false; +} + static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -916,6 +988,47 @@ static void init_amd_zn(struct cpuinfo_x86 *c) } } +static bool cpu_has_zenbleed_microcode(void) +{ + u32 good_rev = 0; + + switch (boot_cpu_data.x86_model) { + case 0x30 ... 0x3f: good_rev = 0x0830107a; break; + case 0x60 ... 0x67: good_rev = 0x0860010b; break; + case 0x68 ... 0x6f: good_rev = 0x08608105; break; + case 0x70 ... 0x7f: good_rev = 0x08701032; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + + default: + return false; + break; + } + + if (boot_cpu_data.microcode < good_rev) + return false; + + return true; +} + +static void zenbleed_check(struct cpuinfo_x86 *c) +{ + if (!cpu_has_amd_erratum(c, amd_zenbleed)) + return; + + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return; + + if (!cpu_has(c, X86_FEATURE_AVX)) + return; + + if (!cpu_has_zenbleed_microcode()) { + pr_notice_once("Zenbleed: please update your microcode for the most optimal fix\n"); + msr_set_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT); + } else { + msr_clear_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT); + } +} + static void init_amd(struct cpuinfo_x86 *c) { early_init_amd(c); @@ -1020,6 +1133,13 @@ static void init_amd(struct cpuinfo_x86 *c) if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && cpu_has(c, X86_FEATURE_AUTOIBRS)) WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS)); + + zenbleed_check(c); + + if (cpu_has_amd_erratum(c, amd_div0)) { + pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); + setup_force_cpu_bug(X86_BUG_DIV0); + } } #ifdef CONFIG_X86_32 @@ -1115,73 +1235,6 @@ static const struct cpu_dev amd_cpu_dev = { cpu_dev_register(amd_cpu_dev); -/* - * AMD errata checking - * - * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or - * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that - * have an OSVW id assigned, which it takes as first argument. Both take a - * variable number of family-specific model-stepping ranges created by - * AMD_MODEL_RANGE(). - * - * Example: - * - * const int amd_erratum_319[] = - * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), - * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), - * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); - */ - -#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } -#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } -#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ - ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) -#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) -#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) -#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) - -static const int amd_erratum_400[] = - AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), - AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); - -static const int amd_erratum_383[] = - AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); - -/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ -static const int amd_erratum_1054[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); - -static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) -{ - int osvw_id = *erratum++; - u32 range; - u32 ms; - - if (osvw_id >= 0 && osvw_id < 65536 && - cpu_has(cpu, X86_FEATURE_OSVW)) { - u64 osvw_len; - - rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); - if (osvw_id < osvw_len) { - u64 osvw_bits; - - rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), - osvw_bits); - return osvw_bits & (1ULL << (osvw_id & 0x3f)); - } - } - - /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_stepping; - while ((range = *erratum++)) - if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && - (ms >= AMD_MODEL_RANGE_START(range)) && - (ms <= AMD_MODEL_RANGE_END(range))) - return true; - - return false; -} - static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[4], amd_dr_addr_mask); static unsigned int amd_msr_dr_addr_masks[] = { @@ -1235,3 +1288,45 @@ u32 amd_get_highest_perf(void) return 255; } EXPORT_SYMBOL_GPL(amd_get_highest_perf); + +static void zenbleed_check_cpu(void *unused) +{ + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + + zenbleed_check(c); +} + +void amd_check_microcode(void) +{ + on_each_cpu(zenbleed_check_cpu, NULL, 1); +} + +bool cpu_has_ibpb_brtype_microcode(void) +{ + switch (boot_cpu_data.x86) { + /* Zen1/2 IBPB flushes branch type predictions too. */ + case 0x17: + return boot_cpu_has(X86_FEATURE_AMD_IBPB); + case 0x19: + /* Poke the MSR bit on Zen3/4 to check its presence. */ + if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { + setup_force_cpu_cap(X86_FEATURE_SBPB); + return true; + } else { + return false; + } + default: + return false; + } +} + +/* + * Issue a DIV 0/1 insn to clear any division data from previous DIV + * operations. + */ +void noinstr amd_clear_divider(void) +{ + asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) + :: "a" (0), "d" (0), "r" (1)); +} +EXPORT_SYMBOL_GPL(amd_clear_divider); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 182af64387d0..f081d26616ac 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,7 +9,6 @@ * - Andrew D. Balsa (code cleanup). */ #include <linux/init.h> -#include <linux/utsname.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/nospec.h> @@ -27,8 +26,6 @@ #include <asm/msr.h> #include <asm/vmx.h> #include <asm/paravirt.h> -#include <asm/alternative.h> -#include <asm/set_memory.h> #include <asm/intel-family.h> #include <asm/e820/api.h> #include <asm/hypervisor.h> @@ -50,6 +47,8 @@ static void __init taa_select_mitigation(void); static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); +static void __init srso_select_mitigation(void); +static void __init gds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -59,8 +58,13 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; +EXPORT_SYMBOL_GPL(x86_pred_cmd); + static DEFINE_MUTEX(spec_ctrl_mutex); +void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk; + /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { @@ -125,21 +129,8 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); EXPORT_SYMBOL_GPL(mmio_stale_data_clear); -void __init check_bugs(void) +void __init cpu_select_mitigations(void) { - identify_boot_cpu(); - - /* - * identify_boot_cpu() initialized SMT support information, let the - * core code know. - */ - cpu_smt_check_topology(); - - if (!IS_ENABLED(CONFIG_SMP)) { - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); - } - /* * Read the SPEC_CTRL MSR to account for reserved bits which may * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD @@ -177,38 +168,12 @@ void __init check_bugs(void) srbds_select_mitigation(); l1d_flush_select_mitigation(); - arch_smt_update(); - -#ifdef CONFIG_X86_32 - /* - * Check whether we are able to run this kernel safely on SMP. - * - * - i386 is no longer supported. - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - */ - if (boot_cpu_data.x86 < 4) - panic("Kernel requires i486+ for 'invlpg' and other features"); - - init_utsname()->machine[1] = - '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); - alternative_instructions(); - - fpu__init_check_bugs(); -#else /* CONFIG_X86_64 */ - alternative_instructions(); - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. + * srso_select_mitigation() depends and must run after + * retbleed_select_mitigation(). */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -#endif + srso_select_mitigation(); + gds_select_mitigation(); } /* @@ -695,6 +660,149 @@ static int __init l1d_flush_parse_cmdline(char *str) early_param("l1d_flush", l1d_flush_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "GDS: " fmt + +enum gds_mitigations { + GDS_MITIGATION_OFF, + GDS_MITIGATION_UCODE_NEEDED, + GDS_MITIGATION_FORCE, + GDS_MITIGATION_FULL, + GDS_MITIGATION_FULL_LOCKED, + GDS_MITIGATION_HYPERVISOR, +}; + +#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION) +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; +#else +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; +#endif + +static const char * const gds_strings[] = { + [GDS_MITIGATION_OFF] = "Vulnerable", + [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [GDS_MITIGATION_FORCE] = "Mitigation: AVX disabled, no microcode", + [GDS_MITIGATION_FULL] = "Mitigation: Microcode", + [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", + [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +bool gds_ucode_mitigated(void) +{ + return (gds_mitigation == GDS_MITIGATION_FULL || + gds_mitigation == GDS_MITIGATION_FULL_LOCKED); +} +EXPORT_SYMBOL_GPL(gds_ucode_mitigated); + +void update_gds_msr(void) +{ + u64 mcu_ctrl_after; + u64 mcu_ctrl; + + switch (gds_mitigation) { + case GDS_MITIGATION_OFF: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl |= GDS_MITG_DIS; + break; + case GDS_MITIGATION_FULL_LOCKED: + /* + * The LOCKED state comes from the boot CPU. APs might not have + * the same state. Make sure the mitigation is enabled on all + * CPUs. + */ + case GDS_MITIGATION_FULL: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl &= ~GDS_MITG_DIS; + break; + case GDS_MITIGATION_FORCE: + case GDS_MITIGATION_UCODE_NEEDED: + case GDS_MITIGATION_HYPERVISOR: + return; + }; + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + /* + * Check to make sure that the WRMSR value was not ignored. Writes to + * GDS_MITG_DIS will be ignored if this processor is locked but the boot + * processor was not. + */ + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after); + WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after); +} + +static void __init gds_select_mitigation(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + gds_mitigation = GDS_MITIGATION_HYPERVISOR; + goto out; + } + + if (cpu_mitigations_off()) + gds_mitigation = GDS_MITIGATION_OFF; + /* Will verify below that mitigation _can_ be disabled */ + + /* No microcode */ + if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (gds_mitigation == GDS_MITIGATION_FORCE) { + /* + * This only needs to be done on the boot CPU so do it + * here rather than in update_gds_msr() + */ + setup_clear_cpu_cap(X86_FEATURE_AVX); + pr_warn("Microcode update needed! Disabling AVX as mitigation.\n"); + } else { + gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + } + goto out; + } + + /* Microcode has mitigation, use it */ + if (gds_mitigation == GDS_MITIGATION_FORCE) + gds_mitigation = GDS_MITIGATION_FULL; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + if (mcu_ctrl & GDS_MITG_LOCKED) { + if (gds_mitigation == GDS_MITIGATION_OFF) + pr_warn("Mitigation locked. Disable failed.\n"); + + /* + * The mitigation is selected from the boot CPU. All other CPUs + * _should_ have the same state. If the boot CPU isn't locked + * but others are then update_gds_msr() will WARN() of the state + * mismatch. If the boot CPU is locked update_gds_msr() will + * ensure the other CPUs have the mitigation enabled. + */ + gds_mitigation = GDS_MITIGATION_FULL_LOCKED; + } + + update_gds_msr(); +out: + pr_info("%s\n", gds_strings[gds_mitigation]); +} + +static int __init gds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return 0; + + if (!strcmp(str, "off")) + gds_mitigation = GDS_MITIGATION_OFF; + else if (!strcmp(str, "force")) + gds_mitigation = GDS_MITIGATION_FORCE; + + return 0; +} +early_param("gather_data_sampling", gds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -934,6 +1042,9 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); + if (IS_ENABLED(CONFIG_RETHUNK)) + x86_return_thunk = retbleed_return_thunk; + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) pr_err(RETBLEED_UNTRAIN_MSG); @@ -943,6 +1054,7 @@ do_cmd_auto: case RETBLEED_MITIGATION_IBPB: setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); mitigate_smt = true; break; @@ -1199,19 +1311,21 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * If no STIBP, Intel enhanced IBRS is enabled, or SMT impossible, STIBP * is not required. * - * Enhanced IBRS also protects against cross-thread branch target + * Intel's Enhanced IBRS also protects against cross-thread branch target * injection in user-mode as the IBRS bit remains always set which * implicitly enables cross-thread protections. However, in legacy IBRS * mode, the IBRS bit is set only on kernel entry and cleared on return - * to userspace. This disables the implicit cross-thread protection, - * so allow for STIBP to be selected in that case. + * to userspace. AMD Automatic IBRS also does not protect userspace. + * These modes therefore disable the implicit cross-thread protection, + * so allow for STIBP to be selected in those cases. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS))) return; /* @@ -2235,6 +2349,170 @@ static int __init l1tf_cmdline(char *str) early_param("l1tf", l1tf_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt + +enum srso_mitigation { + SRSO_MITIGATION_NONE, + SRSO_MITIGATION_MICROCODE, + SRSO_MITIGATION_SAFE_RET, + SRSO_MITIGATION_IBPB, + SRSO_MITIGATION_IBPB_ON_VMEXIT, +}; + +enum srso_mitigation_cmd { + SRSO_CMD_OFF, + SRSO_CMD_MICROCODE, + SRSO_CMD_SAFE_RET, + SRSO_CMD_IBPB, + SRSO_CMD_IBPB_ON_VMEXIT, +}; + +static const char * const srso_strings[] = { + [SRSO_MITIGATION_NONE] = "Vulnerable", + [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", + [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", + [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" +}; + +static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; +static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET; + +static int __init srso_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + srso_cmd = SRSO_CMD_OFF; + else if (!strcmp(str, "microcode")) + srso_cmd = SRSO_CMD_MICROCODE; + else if (!strcmp(str, "safe-ret")) + srso_cmd = SRSO_CMD_SAFE_RET; + else if (!strcmp(str, "ibpb")) + srso_cmd = SRSO_CMD_IBPB; + else if (!strcmp(str, "ibpb-vmexit")) + srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT; + else + pr_err("Ignoring unknown SRSO option (%s).", str); + + return 0; +} +early_param("spec_rstack_overflow", srso_parse_cmdline); + +#define SRSO_NOTICE "WARNING: See https://kernel.org/doc/html/latest/admin-guide/hw-vuln/srso.html for mitigation options." + +static void __init srso_select_mitigation(void) +{ + bool has_microcode; + + if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) + goto pred_cmd; + + /* + * The first check is for the kernel running as a guest in order + * for guests to verify whether IBPB is a viable mitigation. + */ + has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode(); + if (!has_microcode) { + pr_warn("IBPB-extending microcode not applied!\n"); + pr_warn(SRSO_NOTICE); + } else { + /* + * Enable the synthetic (even if in a real CPUID leaf) + * flags for guests. + */ + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + + /* + * Zen1/2 with SMT off aren't vulnerable after the right + * IBPB microcode has been applied. + */ + if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) { + setup_force_cpu_cap(X86_FEATURE_SRSO_NO); + return; + } + } + + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { + if (has_microcode) { + pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n"); + srso_mitigation = SRSO_MITIGATION_IBPB; + goto pred_cmd; + } + } + + switch (srso_cmd) { + case SRSO_CMD_OFF: + return; + + case SRSO_CMD_MICROCODE: + if (has_microcode) { + srso_mitigation = SRSO_MITIGATION_MICROCODE; + pr_warn(SRSO_NOTICE); + } + break; + + case SRSO_CMD_SAFE_RET: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + /* + * Enable the return thunk for generated code + * like ftrace, static_call, etc. + */ + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_UNRET); + + if (boot_cpu_data.x86 == 0x19) { + setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); + x86_return_thunk = srso_alias_return_thunk; + } else { + setup_force_cpu_cap(X86_FEATURE_SRSO); + x86_return_thunk = srso_return_thunk; + } + srso_mitigation = SRSO_MITIGATION_SAFE_RET; + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + + case SRSO_CMD_IBPB: + if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + if (has_microcode) { + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + srso_mitigation = SRSO_MITIGATION_IBPB; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + goto pred_cmd; + } + break; + + case SRSO_CMD_IBPB_ON_VMEXIT: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); + srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + + default: + break; + } + + pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); + +pred_cmd: + if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) && + boot_cpu_has(X86_FEATURE_SBPB)) + x86_pred_cmd = PRED_CMD_SBPB; +} + +#undef pr_fmt #define pr_fmt(fmt) fmt #ifdef CONFIG_SYSFS @@ -2343,7 +2621,8 @@ static ssize_t mmio_stale_data_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS)) return ""; switch (spectre_v2_user_stibp) { @@ -2431,6 +2710,21 @@ static ssize_t retbleed_show_state(char *buf) return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } +static ssize_t srso_show_state(char *buf) +{ + if (boot_cpu_has(X86_FEATURE_SRSO_NO)) + return sysfs_emit(buf, "Mitigation: SMT disabled\n"); + + return sysfs_emit(buf, "%s%s\n", + srso_strings[srso_mitigation], + (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); +} + +static ssize_t gds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2480,6 +2774,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RETBLEED: return retbleed_show_state(buf); + case X86_BUG_SRSO: + return srso_show_state(buf); + + case X86_BUG_GDS: + return gds_show_state(buf); + default: break; } @@ -2544,4 +2844,14 @@ ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, cha { return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); } + +ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); +} + +ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_GDS); +} #endif diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 4063e8991211..8f86eacf69f7 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -39,6 +39,8 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); /* Shared L2 cache maps */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); +static cpumask_var_t cpu_cacheinfo_mask; + /* Kernel controls MTRR and/or PAT MSRs. */ unsigned int memory_caching_control __ro_after_init; @@ -1172,8 +1174,10 @@ void cache_bp_restore(void) cache_cpu_init(); } -static int cache_ap_init(unsigned int cpu) +static int cache_ap_online(unsigned int cpu) { + cpumask_set_cpu(cpu, cpu_cacheinfo_mask); + if (!memory_caching_control || get_cache_aps_delayed_init()) return 0; @@ -1191,11 +1195,17 @@ static int cache_ap_init(unsigned int cpu) * lock to prevent MTRR entry changes */ stop_machine_from_inactive_cpu(cache_rendezvous_handler, NULL, - cpu_callout_mask); + cpu_cacheinfo_mask); return 0; } +static int cache_ap_offline(unsigned int cpu) +{ + cpumask_clear_cpu(cpu, cpu_cacheinfo_mask); + return 0; +} + /* * Delayed cache initialization for all AP's */ @@ -1210,9 +1220,12 @@ void cache_aps_init(void) static int __init cache_ap_register(void) { + zalloc_cpumask_var(&cpu_cacheinfo_mask, GFP_KERNEL); + cpumask_set_cpu(smp_processor_id(), cpu_cacheinfo_mask); + cpuhp_setup_state_nocalls(CPUHP_AP_CACHECTRL_STARTING, "x86/cachectrl:starting", - cache_ap_init, NULL); + cache_ap_online, cache_ap_offline); return 0; } -core_initcall(cache_ap_register); +early_initcall(cache_ap_register); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 80710a68ef7d..00f043a094fc 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,12 +18,16 @@ #include <linux/init.h> #include <linux/kprobes.h> #include <linux/kgdb.h> +#include <linux/mem_encrypt.h> #include <linux/smp.h> +#include <linux/cpu.h> #include <linux/io.h> #include <linux/syscore_ops.h> #include <linux/pgtable.h> #include <linux/stackprotector.h> +#include <linux/utsname.h> +#include <asm/alternative.h> #include <asm/cmdline.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> @@ -59,7 +63,7 @@ #include <asm/intel-family.h> #include <asm/cpu_device_id.h> #include <asm/uv/uv.h> -#include <asm/sigframe.h> +#include <asm/set_memory.h> #include <asm/traps.h> #include <asm/sev.h> @@ -67,14 +71,6 @@ u32 elf_hwcap2 __read_mostly; -/* all of these masks are initialized in setup_cpu_local_masks() */ -cpumask_var_t cpu_initialized_mask; -cpumask_var_t cpu_callout_mask; -cpumask_var_t cpu_callin_mask; - -/* representing cpus for which sibling maps can be computed */ -cpumask_var_t cpu_sibling_setup_mask; - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); @@ -169,15 +165,6 @@ clear_ppin: clear_cpu_cap(c, info->feature); } -/* correctly size the local cpu masks */ -void __init setup_cpu_local_masks(void) -{ - alloc_bootmem_cpumask_var(&cpu_initialized_mask); - alloc_bootmem_cpumask_var(&cpu_callin_mask); - alloc_bootmem_cpumask_var(&cpu_callout_mask); - alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); -} - static void default_init(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 @@ -1263,6 +1250,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RETBLEED BIT(3) /* CPU is affected by SMT (cross-thread) return predictions */ #define SMT_RSB BIT(4) +/* CPU is affected by SRSO */ +#define SRSO BIT(5) +/* CPU is affected by GDS */ +#define GDS BIT(6) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1274,28 +1265,31 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED | SMT_RSB), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), + VULNBL_AMD(0x19, SRSO), {} }; @@ -1419,6 +1413,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) setup_force_cpu_bug(X86_BUG_SMT_RSB); + if (!cpu_has(c, X86_FEATURE_SRSO_NO)) { + if (cpu_matches(cpu_vuln_blacklist, SRSO)) + setup_force_cpu_bug(X86_BUG_SRSO); + } + + /* + * Check if CPU is vulnerable to GDS. If running in a virtual machine on + * an affected processor, the VMM may have disabled the use of GATHER by + * disabling AVX2. The only way to do this in HW is to clear XCR0[2], + * which means that AVX will be disabled. + */ + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + boot_cpu_has(X86_FEATURE_AVX)) + setup_force_cpu_bug(X86_BUG_GDS); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1502,12 +1511,10 @@ static void __init cpu_parse_early_param(void) if (!kstrtouint(opt, 10, &bit)) { if (bit < NCAPINTS * 32) { -#ifdef CONFIG_X86_FEATURE_NAMES /* empty-string, i.e., ""-defined feature flags */ if (!x86_cap_flags[bit]) pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit)); else -#endif pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); setup_clear_cpu_cap(bit); @@ -1520,7 +1527,6 @@ static void __init cpu_parse_early_param(void) continue; } -#ifdef CONFIG_X86_FEATURE_NAMES for (bit = 0; bit < 32 * NCAPINTS; bit++) { if (!x86_cap_flag(bit)) continue; @@ -1537,7 +1543,6 @@ static void __init cpu_parse_early_param(void) if (!found) pr_cont(" (unknown: %s)", opt); -#endif } pr_cont("\n"); @@ -1600,10 +1605,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) sld_setup(c); - fpu__init_system(c); - - init_sigframe_size(); - #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says @@ -1983,6 +1984,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); + if (boot_cpu_has_bug(X86_BUG_GDS)) + update_gds_msr(); tsx_ap_init(); } @@ -2123,19 +2126,6 @@ static void dbg_restore_debug_regs(void) #define dbg_restore_debug_regs() #endif /* ! CONFIG_KGDB */ -static void wait_for_master_cpu(int cpu) -{ -#ifdef CONFIG_SMP - /* - * wait for ACK from master CPU before continuing - * with AP initialization - */ - WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)); - while (!cpumask_test_cpu(cpu, cpu_callout_mask)) - cpu_relax(); -#endif -} - static inline void setup_getcpu(int cpu) { unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu)); @@ -2158,11 +2148,7 @@ static inline void setup_getcpu(int cpu) } #ifdef CONFIG_X86_64 -static inline void ucode_cpu_init(int cpu) -{ - if (cpu) - load_ucode_ap(); -} +static inline void ucode_cpu_init(int cpu) { } static inline void tss_setup_ist(struct tss_struct *tss) { @@ -2239,8 +2225,6 @@ void cpu_init(void) struct task_struct *cur = current; int cpu = raw_smp_processor_id(); - wait_for_master_cpu(cpu); - ucode_cpu_init(cpu); #ifdef CONFIG_NUMA @@ -2285,26 +2269,12 @@ void cpu_init(void) doublefault_init_cpu_tss(); - fpu__init_cpu(); - if (is_uv_system()) uv_cpu_init(); load_fixmap_gdt(cpu); } -#ifdef CONFIG_SMP -void cpu_init_secondary(void) -{ - /* - * Relies on the BP having set-up the IDT tables, which are loaded - * on this CPU in cpu_init_exception_handling(). - */ - cpu_init_exception_handling(); - cpu_init(); -} -#endif - #ifdef CONFIG_MICROCODE_LATE_LOADING /** * store_cpu_caps() - Store a snapshot of CPU capabilities @@ -2341,6 +2311,8 @@ void microcode_check(struct cpuinfo_x86 *prev_info) perf_check_microcode(); + amd_check_microcode(); + store_cpu_caps(&curr_info); if (!memcmp(&prev_info->x86_capability, &curr_info.x86_capability, @@ -2362,3 +2334,69 @@ void arch_smt_update(void) /* Check whether IPI broadcasting can be enabled */ apic_smt_update(); } + +void __init arch_cpu_finalize_init(void) +{ + identify_boot_cpu(); + + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology(); + + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + + cpu_select_mitigations(); + + arch_smt_update(); + + if (IS_ENABLED(CONFIG_X86_32)) { + /* + * Check whether this is a real i386 which is not longer + * supported and fixup the utsname. + */ + if (boot_cpu_data.x86 < 4) + panic("Kernel requires i486+ for 'invlpg' and other features"); + + init_utsname()->machine[1] = + '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + } + + /* + * Must be before alternatives because it might set or clear + * feature bits. + */ + fpu__init_system(); + fpu__init_cpu(); + + alternative_instructions(); + + if (IS_ENABLED(CONFIG_X86_64)) { + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); + } else { + fpu__init_check_bugs(); + } + + /* + * This needs to be called before any devices perform DMA + * operations that might use the SWIOTLB bounce buffers. It will + * mark the bounce buffers as decrypted so that their usage will + * not cause "plain-text" data to be decrypted when accessed. It + * must be called after late_time_init() so that Hyper-V x86/x64 + * hypercalls work when the SWIOTLB bounce buffers are decrypted. + */ + mem_encrypt_init(); +} diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index f97b0fe13da8..1dcd7d4e38ef 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -79,9 +79,11 @@ extern void detect_ht(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); +extern void update_gds_msr(void); extern enum spectre_v2_mitigation spectre_v2_enabled; diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 0b971f974096..c4ec4ca47e11 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -715,11 +715,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) bool amd_mce_is_memory_error(struct mce *m) { + enum smca_bank_types bank_type; /* ErrCodeExt[20:16] */ u8 xec = (m->status >> 16) & 0x1f; + bank_type = smca_get_bank_type(m->extcpu, m->bank); if (mce_flags.smca) - return smca_get_bank_type(m->extcpu, m->bank) == SMCA_UMC && xec == 0x0; + return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0; return m->bank == 4 && xec == 0x8; } @@ -1050,7 +1052,7 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol if (bank_type >= N_SMCA_BANK_TYPES) return NULL; - if (b && bank_type == SMCA_UMC) { + if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; return NULL; @@ -1259,10 +1261,10 @@ static void __threshold_remove_blocks(struct threshold_bank *b) struct threshold_block *pos = NULL; struct threshold_block *tmp = NULL; - kobject_del(b->kobj); + kobject_put(b->kobj); list_for_each_entry_safe(pos, tmp, &b->blocks->miscj, miscj) - kobject_del(&pos->kobj); + kobject_put(b->kobj); } static void threshold_remove_bank(struct threshold_bank *bank) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2eec60f50057..17eb6a37a587 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -843,6 +843,26 @@ static noinstr bool quirk_skylake_repmov(void) } /* + * Some Zen-based Instruction Fetch Units set EIPV=RIPV=0 on poison consumption + * errors. This means mce_gather_info() will not save the "ip" and "cs" registers. + * + * However, the context is still valid, so save the "cs" register for later use. + * + * The "ip" register is truly unknown, so don't save it or fixup EIPV/RIPV. + * + * The Instruction Fetch Unit is at MCA bank 1 for all affected systems. + */ +static __always_inline void quirk_zen_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 1) + return; + if (!(m->status & MCI_STATUS_POISON)) + return; + + m->cs = regs->cs; +} + +/* * Do a quick check if any of the events requires a panic. * This decides if we keep the events around or clear them. */ @@ -861,6 +881,9 @@ static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned lo if (mce_flags.snb_ifu_quirk) quirk_sandybridge_ifu(i, m, regs); + if (mce_flags.zen_ifu_quirk) + quirk_zen_ifu(i, m, regs); + m->bank = i; if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) { mce_read_aux(m, i); @@ -1022,12 +1045,12 @@ static noinstr int mce_start(int *no_way_out) if (!timeout) return ret; - arch_atomic_add(*no_way_out, &global_nwo); + raw_atomic_add(*no_way_out, &global_nwo); /* * Rely on the implied barrier below, such that global_nwo * is updated before mce_callin. */ - order = arch_atomic_inc_return(&mce_callin); + order = raw_atomic_inc_return(&mce_callin); arch_cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus); /* Enable instrumentation around calls to external facilities */ @@ -1036,10 +1059,10 @@ static noinstr int mce_start(int *no_way_out) /* * Wait for everyone. */ - while (arch_atomic_read(&mce_callin) != num_online_cpus()) { + while (raw_atomic_read(&mce_callin) != num_online_cpus()) { if (mce_timed_out(&timeout, "Timeout: Not all CPUs entered broadcast exception handler")) { - arch_atomic_set(&global_nwo, 0); + raw_atomic_set(&global_nwo, 0); goto out; } ndelay(SPINUNIT); @@ -1054,7 +1077,7 @@ static noinstr int mce_start(int *no_way_out) /* * Monarch: Starts executing now, the others wait. */ - arch_atomic_set(&mce_executing, 1); + raw_atomic_set(&mce_executing, 1); } else { /* * Subject: Now start the scanning loop one by one in @@ -1062,10 +1085,10 @@ static noinstr int mce_start(int *no_way_out) * This way when there are any shared banks it will be * only seen by one CPU before cleared, avoiding duplicates. */ - while (arch_atomic_read(&mce_executing) < order) { + while (raw_atomic_read(&mce_executing) < order) { if (mce_timed_out(&timeout, "Timeout: Subject CPUs unable to finish machine check processing")) { - arch_atomic_set(&global_nwo, 0); + raw_atomic_set(&global_nwo, 0); goto out; } ndelay(SPINUNIT); @@ -1075,7 +1098,7 @@ static noinstr int mce_start(int *no_way_out) /* * Cache the global no_way_out state. */ - *no_way_out = arch_atomic_read(&global_nwo); + *no_way_out = raw_atomic_read(&global_nwo); ret = order; @@ -1533,7 +1556,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - if (kill_current_task) + if (!mce_usable_address(&m)) queue_task_work(&m, msg, kill_me_now); else queue_task_work(&m, msg, kill_me_maybe); @@ -1842,6 +1865,9 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 0x15 && c->x86_model <= 0xf) mce_flags.overflow_recov = 1; + if (c->x86 >= 0x17 && c->x86 <= 0x1A) + mce_flags.zen_ifu_quirk = 1; + } if (c->x86_vendor == X86_VENDOR_INTEL) { diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index d2412ce2d312..d5946fcdcd5d 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -157,6 +157,9 @@ struct mce_vendor_flags { */ smca : 1, + /* Zen IFU quirk */ + zen_ifu_quirk : 1, + /* AMD-style error thresholding banks present. */ amd_threshold : 1, @@ -172,7 +175,7 @@ struct mce_vendor_flags { /* Skylake, Cascade Lake, Cooper Lake REP;MOVS* quirk */ skx_repmov_quirk : 1, - __reserved_0 : 56; + __reserved_0 : 55; }; extern struct mce_vendor_flags mce_flags; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index f5fdeb1e3606..87208e46f7ed 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -78,8 +78,6 @@ static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig) if (sig == e->installed_cpu) return e->equiv_cpu; - - e++; } return 0; } @@ -596,11 +594,6 @@ void reload_ucode_amd(unsigned int cpu) } } } -static u16 __find_equiv_id(unsigned int cpu) -{ - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - return find_equiv_id(&equiv_table, uci->cpu_sig.sig); -} /* * a small, trivial cache of per-family ucode patches @@ -651,9 +644,11 @@ static void free_cache(void) static struct ucode_patch *find_patch(unsigned int cpu) { + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; u16 equiv_id; - equiv_id = __find_equiv_id(cpu); + + equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig); if (!equiv_id) return NULL; @@ -705,7 +700,7 @@ static enum ucode_state apply_microcode_amd(int cpu) rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); /* need to apply patch? */ - if (rev >= mc_amd->hdr.patch_id) { + if (rev > mc_amd->hdr.patch_id) { ret = UCODE_OK; goto out; } diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile index cc4f9f1cb94c..aee4bc5ad496 100644 --- a/arch/x86/kernel/cpu/mtrr/Makefile +++ b/arch/x86/kernel/cpu/mtrr/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := mtrr.o if.o generic.o cleanup.o -obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o +obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o legacy.o diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c index eff6ac62c0ff..ef3e8e42b782 100644 --- a/arch/x86/kernel/cpu/mtrr/amd.c +++ b/arch/x86/kernel/cpu/mtrr/amd.c @@ -110,7 +110,7 @@ amd_validate_add_page(unsigned long base, unsigned long size, unsigned int type) } const struct mtrr_ops amd_mtrr_ops = { - .vendor = X86_VENDOR_AMD, + .var_regs = 2, .set = amd_set_mtrr, .get = amd_get_mtrr, .get_free_region = generic_get_free_region, diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index b8a74eddde83..6f6c3ae92943 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -45,15 +45,6 @@ centaur_get_free_region(unsigned long base, unsigned long size, int replace_reg) return -ENOSPC; } -/* - * Report boot time MCR setups - */ -void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) -{ - centaur_mcr[mcr].low = lo; - centaur_mcr[mcr].high = hi; -} - static void centaur_get_mcr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type * type) @@ -112,7 +103,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t } const struct mtrr_ops centaur_mtrr_ops = { - .vendor = X86_VENDOR_CENTAUR, + .var_regs = 8, .set = centaur_set_mcr, .get = centaur_get_mcr, .get_free_region = centaur_get_free_region, diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index b5f43049fa5f..18cf79d6e2c5 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -55,9 +55,6 @@ static int __initdata nr_range; static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; -static int __initdata debug_print; -#define Dprintk(x...) do { if (debug_print) pr_debug(x); } while (0) - #define BIOS_BUG_MSG \ "WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n" @@ -79,12 +76,11 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, base, base + size); } - if (debug_print) { - pr_debug("After WB checking\n"); - for (i = 0; i < nr_range; i++) - pr_debug("MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end); - } + + Dprintk("After WB checking\n"); + for (i = 0; i < nr_range; i++) + Dprintk("MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); /* Take out UC ranges: */ for (i = 0; i < num_var_ranges; i++) { @@ -112,24 +108,22 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, subtract_range(range, RANGE_NUM, extra_remove_base, extra_remove_base + extra_remove_size); - if (debug_print) { - pr_debug("After UC checking\n"); - for (i = 0; i < RANGE_NUM; i++) { - if (!range[i].end) - continue; - pr_debug("MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end); - } + Dprintk("After UC checking\n"); + for (i = 0; i < RANGE_NUM; i++) { + if (!range[i].end) + continue; + + Dprintk("MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); } /* sort the ranges */ nr_range = clean_sort_range(range, RANGE_NUM); - if (debug_print) { - pr_debug("After sorting\n"); - for (i = 0; i < nr_range; i++) - pr_debug("MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end); - } + + Dprintk("After sorting\n"); + for (i = 0; i < nr_range; i++) + Dprintk("MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); return nr_range; } @@ -164,16 +158,9 @@ static int __init enable_mtrr_cleanup_setup(char *str) } early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup); -static int __init mtrr_cleanup_debug_setup(char *str) -{ - debug_print = 1; - return 0; -} -early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup); - static void __init set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, - unsigned char type, unsigned int address_bits) + unsigned char type) { u32 base_lo, base_hi, mask_lo, mask_hi; u64 base, mask; @@ -183,7 +170,7 @@ set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, return; } - mask = (1ULL << address_bits) - 1; + mask = (1ULL << boot_cpu_data.x86_phys_bits) - 1; mask &= ~((((u64)sizek) << 10) - 1); base = ((u64)basek) << 10; @@ -209,7 +196,7 @@ save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, range_state[reg].type = type; } -static void __init set_var_mtrr_all(unsigned int address_bits) +static void __init set_var_mtrr_all(void) { unsigned long basek, sizek; unsigned char type; @@ -220,7 +207,7 @@ static void __init set_var_mtrr_all(unsigned int address_bits) sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10); type = range_state[reg].type; - set_var_mtrr(reg, basek, sizek, type, address_bits); + set_var_mtrr(reg, basek, sizek, type); } } @@ -267,7 +254,7 @@ range_to_mtrr(unsigned int reg, unsigned long range_startk, align = max_align; sizek = 1UL << align; - if (debug_print) { + if (mtrr_debug) { char start_factor = 'K', size_factor = 'K'; unsigned long start_base, size_base; @@ -542,7 +529,7 @@ static void __init print_out_mtrr_range_state(void) start_base = to_size_factor(start_base, &start_factor); type = range_state[i].type; - pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n", + Dprintk("reg %d, base: %ld%cB, range: %ld%cB, type %s\n", i, start_base, start_factor, size_base, size_factor, (type == MTRR_TYPE_UNCACHABLE) ? "UC" : @@ -680,7 +667,7 @@ static int __init mtrr_search_optimal_index(void) return index_good; } -int __init mtrr_cleanup(unsigned address_bits) +int __init mtrr_cleanup(void) { unsigned long x_remove_base, x_remove_size; unsigned long base, size, def, dummy; @@ -689,7 +676,10 @@ int __init mtrr_cleanup(unsigned address_bits) int index_good; int i; - if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1) + if (!mtrr_enabled()) + return 0; + + if (!cpu_feature_enabled(X86_FEATURE_MTRR) || enable_mtrr_cleanup < 1) return 0; rdmsr(MSR_MTRRdefType, def, dummy); @@ -711,7 +701,7 @@ int __init mtrr_cleanup(unsigned address_bits) return 0; /* Print original var MTRRs at first, for debugging: */ - pr_debug("original variable MTRRs\n"); + Dprintk("original variable MTRRs\n"); print_out_mtrr_range_state(); memset(range, 0, sizeof(range)); @@ -742,8 +732,8 @@ int __init mtrr_cleanup(unsigned address_bits) mtrr_print_out_one_result(i); if (!result[i].bad) { - set_var_mtrr_all(address_bits); - pr_debug("New variable MTRRs\n"); + set_var_mtrr_all(); + Dprintk("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; } @@ -763,7 +753,7 @@ int __init mtrr_cleanup(unsigned address_bits) mtrr_calc_range_state(chunk_size, gran_size, x_remove_base, x_remove_size, i); - if (debug_print) { + if (mtrr_debug) { mtrr_print_out_one_result(i); pr_info("\n"); } @@ -786,8 +776,8 @@ int __init mtrr_cleanup(unsigned address_bits) gran_size = result[i].gran_sizek; gran_size <<= 10; x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size); - set_var_mtrr_all(address_bits); - pr_debug("New variable MTRRs\n"); + set_var_mtrr_all(); + Dprintk("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; } else { @@ -802,7 +792,7 @@ int __init mtrr_cleanup(unsigned address_bits) return 0; } #else -int __init mtrr_cleanup(unsigned address_bits) +int __init mtrr_cleanup(void) { return 0; } @@ -882,15 +872,18 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* extra one for all 0 */ int num[MTRR_NUM_TYPES + 1]; + if (!mtrr_enabled()) + return 0; + /* * Make sure we only trim uncachable memory on machines that * support the Intel MTRR architecture: */ - if (!is_cpu(INTEL) || disable_mtrr_trim) + if (!cpu_feature_enabled(X86_FEATURE_MTRR) || disable_mtrr_trim) return 0; rdmsr(MSR_MTRRdefType, def, dummy); - def &= 0xff; + def &= MTRR_DEF_TYPE_TYPE; if (def != MTRR_TYPE_UNCACHABLE) return 0; diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 173b9e01e623..238dad57d4d6 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -235,7 +235,7 @@ static void cyrix_set_arr(unsigned int reg, unsigned long base, } const struct mtrr_ops cyrix_mtrr_ops = { - .vendor = X86_VENDOR_CYRIX, + .var_regs = 8, .set = cyrix_set_arr, .get = cyrix_get_arr, .get_free_region = cyrix_get_free_region, diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index ee09d359e08f..2d6aa5d2e3d7 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -8,10 +8,12 @@ #include <linux/init.h> #include <linux/io.h> #include <linux/mm.h> - +#include <linux/cc_platform.h> #include <asm/processor-flags.h> #include <asm/cacheinfo.h> #include <asm/cpufeature.h> +#include <asm/hypervisor.h> +#include <asm/mshyperv.h> #include <asm/tlbflush.h> #include <asm/mtrr.h> #include <asm/msr.h> @@ -31,6 +33,55 @@ static struct fixed_range_block fixed_range_blocks[] = { {} }; +struct cache_map { + u64 start; + u64 end; + u64 flags; + u64 type:8; + u64 fixed:1; +}; + +bool mtrr_debug; + +static int __init mtrr_param_setup(char *str) +{ + int rc = 0; + + if (!str) + return -EINVAL; + if (!strcmp(str, "debug")) + mtrr_debug = true; + else + rc = -EINVAL; + + return rc; +} +early_param("mtrr", mtrr_param_setup); + +/* + * CACHE_MAP_MAX is the maximum number of memory ranges in cache_map, where + * no 2 adjacent ranges have the same cache mode (those would be merged). + * The number is based on the worst case: + * - no two adjacent fixed MTRRs share the same cache mode + * - one variable MTRR is spanning a huge area with mode WB + * - 255 variable MTRRs with mode UC all overlap with the WB MTRR, creating 2 + * additional ranges each (result like "ababababa...aba" with a = WB, b = UC), + * accounting for MTRR_MAX_VAR_RANGES * 2 - 1 range entries + * - a TOP_MEM2 area (even with overlapping an UC MTRR can't add 2 range entries + * to the possible maximum, as it always starts at 4GB, thus it can't be in + * the middle of that MTRR, unless that MTRR starts at 0, which would remove + * the initial "a" from the "abababa" pattern above) + * The map won't contain ranges with no matching MTRR (those fall back to the + * default cache mode). + */ +#define CACHE_MAP_MAX (MTRR_NUM_FIXED_RANGES + MTRR_MAX_VAR_RANGES * 2) + +static struct cache_map init_cache_map[CACHE_MAP_MAX] __initdata; +static struct cache_map *cache_map __refdata = init_cache_map; +static unsigned int cache_map_size = CACHE_MAP_MAX; +static unsigned int cache_map_n; +static unsigned int cache_map_fixed; + static unsigned long smp_changes_mask; static int mtrr_state_set; u64 mtrr_tom2; @@ -38,6 +89,9 @@ u64 mtrr_tom2; struct mtrr_state_type mtrr_state; EXPORT_SYMBOL_GPL(mtrr_state); +/* Reserved bits in the high portion of the MTRRphysBaseN MSR. */ +u32 phys_hi_rsvd; + /* * BIOS is expected to clear MtrrFixDramModEn bit, see for example * "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD @@ -69,175 +123,370 @@ static u64 get_mtrr_size(u64 mask) { u64 size; - mask >>= PAGE_SHIFT; - mask |= size_or_mask; + mask |= (u64)phys_hi_rsvd << 32; size = -mask; - size <<= PAGE_SHIFT; + return size; } +static u8 get_var_mtrr_state(unsigned int reg, u64 *start, u64 *size) +{ + struct mtrr_var_range *mtrr = mtrr_state.var_ranges + reg; + + if (!(mtrr->mask_lo & MTRR_PHYSMASK_V)) + return MTRR_TYPE_INVALID; + + *start = (((u64)mtrr->base_hi) << 32) + (mtrr->base_lo & PAGE_MASK); + *size = get_mtrr_size((((u64)mtrr->mask_hi) << 32) + + (mtrr->mask_lo & PAGE_MASK)); + + return mtrr->base_lo & MTRR_PHYSBASE_TYPE; +} + +static u8 get_effective_type(u8 type1, u8 type2) +{ + if (type1 == MTRR_TYPE_UNCACHABLE || type2 == MTRR_TYPE_UNCACHABLE) + return MTRR_TYPE_UNCACHABLE; + + if ((type1 == MTRR_TYPE_WRBACK && type2 == MTRR_TYPE_WRTHROUGH) || + (type1 == MTRR_TYPE_WRTHROUGH && type2 == MTRR_TYPE_WRBACK)) + return MTRR_TYPE_WRTHROUGH; + + if (type1 != type2) + return MTRR_TYPE_UNCACHABLE; + + return type1; +} + +static void rm_map_entry_at(int idx) +{ + cache_map_n--; + if (cache_map_n > idx) { + memmove(cache_map + idx, cache_map + idx + 1, + sizeof(*cache_map) * (cache_map_n - idx)); + } +} + /* - * Check and return the effective type for MTRR-MTRR type overlap. - * Returns 1 if the effective type is UNCACHEABLE, else returns 0 + * Add an entry into cache_map at a specific index. Merges adjacent entries if + * appropriate. Return the number of merges for correcting the scan index + * (this is needed as merging will reduce the number of entries, which will + * result in skipping entries in future iterations if the scan index isn't + * corrected). + * Note that the corrected index can never go below -1 (resulting in being 0 in + * the next scan iteration), as "2" is returned only if the current index is + * larger than zero. */ -static int check_type_overlap(u8 *prev, u8 *curr) +static int add_map_entry_at(u64 start, u64 end, u8 type, int idx) { - if (*prev == MTRR_TYPE_UNCACHABLE || *curr == MTRR_TYPE_UNCACHABLE) { - *prev = MTRR_TYPE_UNCACHABLE; - *curr = MTRR_TYPE_UNCACHABLE; - return 1; + bool merge_prev = false, merge_next = false; + + if (start >= end) + return 0; + + if (idx > 0) { + struct cache_map *prev = cache_map + idx - 1; + + if (!prev->fixed && start == prev->end && type == prev->type) + merge_prev = true; } - if ((*prev == MTRR_TYPE_WRBACK && *curr == MTRR_TYPE_WRTHROUGH) || - (*prev == MTRR_TYPE_WRTHROUGH && *curr == MTRR_TYPE_WRBACK)) { - *prev = MTRR_TYPE_WRTHROUGH; - *curr = MTRR_TYPE_WRTHROUGH; + if (idx < cache_map_n) { + struct cache_map *next = cache_map + idx; + + if (!next->fixed && end == next->start && type == next->type) + merge_next = true; } - if (*prev != *curr) { - *prev = MTRR_TYPE_UNCACHABLE; - *curr = MTRR_TYPE_UNCACHABLE; + if (merge_prev && merge_next) { + cache_map[idx - 1].end = cache_map[idx].end; + rm_map_entry_at(idx); + return 2; + } + if (merge_prev) { + cache_map[idx - 1].end = end; return 1; } + if (merge_next) { + cache_map[idx].start = start; + return 1; + } + + /* Sanity check: the array should NEVER be too small! */ + if (cache_map_n == cache_map_size) { + WARN(1, "MTRR cache mode memory map exhausted!\n"); + cache_map_n = cache_map_fixed; + return 0; + } + + if (cache_map_n > idx) { + memmove(cache_map + idx + 1, cache_map + idx, + sizeof(*cache_map) * (cache_map_n - idx)); + } + + cache_map[idx].start = start; + cache_map[idx].end = end; + cache_map[idx].type = type; + cache_map[idx].fixed = 0; + cache_map_n++; return 0; } -/** - * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries - * - * Return the MTRR fixed memory type of 'start'. - * - * MTRR fixed entries are divided into the following ways: - * 0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges - * 0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges - * 0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges - * - * Return Values: - * MTRR_TYPE_(type) - Matched memory type - * MTRR_TYPE_INVALID - Unmatched +/* Clear a part of an entry. Return 1 if start of entry is still valid. */ +static int clr_map_range_at(u64 start, u64 end, int idx) +{ + int ret = start != cache_map[idx].start; + u64 tmp; + + if (start == cache_map[idx].start && end == cache_map[idx].end) { + rm_map_entry_at(idx); + } else if (start == cache_map[idx].start) { + cache_map[idx].start = end; + } else if (end == cache_map[idx].end) { + cache_map[idx].end = start; + } else { + tmp = cache_map[idx].end; + cache_map[idx].end = start; + add_map_entry_at(end, tmp, cache_map[idx].type, idx + 1); + } + + return ret; +} + +/* + * Add MTRR to the map. The current map is scanned and each part of the MTRR + * either overlapping with an existing entry or with a hole in the map is + * handled separately. */ -static u8 mtrr_type_lookup_fixed(u64 start, u64 end) +static void add_map_entry(u64 start, u64 end, u8 type) { - int idx; + u8 new_type, old_type; + u64 tmp; + int i; - if (start >= 0x100000) - return MTRR_TYPE_INVALID; + for (i = 0; i < cache_map_n && start < end; i++) { + if (start >= cache_map[i].end) + continue; + + if (start < cache_map[i].start) { + /* Region start has no overlap. */ + tmp = min(end, cache_map[i].start); + i -= add_map_entry_at(start, tmp, type, i); + start = tmp; + continue; + } - /* 0x0 - 0x7FFFF */ - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state.fixed_ranges[idx]; - /* 0x80000 - 0xBFFFF */ - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state.fixed_ranges[idx]; + new_type = get_effective_type(type, cache_map[i].type); + old_type = cache_map[i].type; + + if (cache_map[i].fixed || new_type == old_type) { + /* Cut off start of new entry. */ + start = cache_map[i].end; + continue; + } + + /* Handle only overlapping part of region. */ + tmp = min(end, cache_map[i].end); + i += clr_map_range_at(start, tmp, i); + i -= add_map_entry_at(start, tmp, new_type, i); + start = tmp; } - /* 0xC0000 - 0xFFFFF */ - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state.fixed_ranges[idx]; + /* Add rest of region after last map entry (rest might be empty). */ + add_map_entry_at(start, end, type, i); } -/** - * mtrr_type_lookup_variable - look up memory type in MTRR variable entries - * - * Return Value: - * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched) - * - * Output Arguments: - * repeat - Set to 1 when [start:end] spanned across MTRR range and type - * returned corresponds only to [start:*partial_end]. Caller has - * to lookup again for [*partial_end:end]. - * - * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the - * region is fully covered by a single MTRR entry or the default - * type. +/* Add variable MTRRs to cache map. */ +static void map_add_var(void) +{ + u64 start, size; + unsigned int i; + u8 type; + + /* + * Add AMD TOP_MEM2 area. Can't be added in mtrr_build_map(), as it + * needs to be added again when rebuilding the map due to potentially + * having moved as a result of variable MTRRs for memory below 4GB. + */ + if (mtrr_tom2) { + add_map_entry(BIT_ULL(32), mtrr_tom2, MTRR_TYPE_WRBACK); + cache_map[cache_map_n - 1].fixed = 1; + } + + for (i = 0; i < num_var_ranges; i++) { + type = get_var_mtrr_state(i, &start, &size); + if (type != MTRR_TYPE_INVALID) + add_map_entry(start, start + size, type); + } +} + +/* + * Rebuild map by replacing variable entries. Needs to be called when MTRR + * registers are being changed after boot, as such changes could include + * removals of registers, which are complicated to handle without rebuild of + * the map. */ -static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, - int *repeat, u8 *uniform) +void generic_rebuild_map(void) { - int i; - u64 base, mask; - u8 prev_match, curr_match; + if (mtrr_if != &generic_mtrr_ops) + return; - *repeat = 0; - *uniform = 1; + cache_map_n = cache_map_fixed; - prev_match = MTRR_TYPE_INVALID; - for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state, inclusive; + map_add_var(); +} - if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11))) - continue; +static unsigned int __init get_cache_map_size(void) +{ + return cache_map_fixed + 2 * num_var_ranges + (mtrr_tom2 != 0); +} - base = (((u64)mtrr_state.var_ranges[i].base_hi) << 32) + - (mtrr_state.var_ranges[i].base_lo & PAGE_MASK); - mask = (((u64)mtrr_state.var_ranges[i].mask_hi) << 32) + - (mtrr_state.var_ranges[i].mask_lo & PAGE_MASK); - - start_state = ((start & mask) == (base & mask)); - end_state = ((end & mask) == (base & mask)); - inclusive = ((start < base) && (end > base)); - - if ((start_state != end_state) || inclusive) { - /* - * We have start:end spanning across an MTRR. - * We split the region into either - * - * - start_state:1 - * (start:mtrr_end)(mtrr_end:end) - * - end_state:1 - * (start:mtrr_start)(mtrr_start:end) - * - inclusive:1 - * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end) - * - * depending on kind of overlap. - * - * Return the type of the first region and a pointer - * to the start of next region so that caller will be - * advised to lookup again after having adjusted start - * and end. - * - * Note: This way we handle overlaps with multiple - * entries and the default type properly. - */ - if (start_state) - *partial_end = base + get_mtrr_size(mask); - else - *partial_end = base; - - if (unlikely(*partial_end <= start)) { - WARN_ON(1); - *partial_end = start + PAGE_SIZE; - } +/* Build the cache_map containing the cache modes per memory range. */ +void __init mtrr_build_map(void) +{ + u64 start, end, size; + unsigned int i; + u8 type; - end = *partial_end - 1; /* end is inclusive */ - *repeat = 1; - *uniform = 0; + /* Add fixed MTRRs, optimize for adjacent entries with same type. */ + if (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED) { + /* + * Start with 64k size fixed entries, preset 1st one (hence the + * loop below is starting with index 1). + */ + start = 0; + end = size = 0x10000; + type = mtrr_state.fixed_ranges[0]; + + for (i = 1; i < MTRR_NUM_FIXED_RANGES; i++) { + /* 8 64k entries, then 16 16k ones, rest 4k. */ + if (i == 8 || i == 24) + size >>= 2; + + if (mtrr_state.fixed_ranges[i] != type) { + add_map_entry(start, end, type); + start = end; + type = mtrr_state.fixed_ranges[i]; + } + end += size; } + add_map_entry(start, end, type); + } - if ((start & mask) != (base & mask)) - continue; + /* Mark fixed, they take precedence. */ + for (i = 0; i < cache_map_n; i++) + cache_map[i].fixed = 1; + cache_map_fixed = cache_map_n; - curr_match = mtrr_state.var_ranges[i].base_lo & 0xff; - if (prev_match == MTRR_TYPE_INVALID) { - prev_match = curr_match; - continue; + map_add_var(); + + pr_info("MTRR map: %u entries (%u fixed + %u variable; max %u), built from %u variable MTRRs\n", + cache_map_n, cache_map_fixed, cache_map_n - cache_map_fixed, + get_cache_map_size(), num_var_ranges + (mtrr_tom2 != 0)); + + if (mtrr_debug) { + for (i = 0; i < cache_map_n; i++) { + pr_info("%3u: %016llx-%016llx %s\n", i, + cache_map[i].start, cache_map[i].end - 1, + mtrr_attrib_to_str(cache_map[i].type)); } + } +} - *uniform = 0; - if (check_type_overlap(&prev_match, &curr_match)) - return curr_match; +/* Copy the cache_map from __initdata memory to dynamically allocated one. */ +void __init mtrr_copy_map(void) +{ + unsigned int new_size = get_cache_map_size(); + + if (!mtrr_state.enabled || !new_size) { + cache_map = NULL; + return; + } + + mutex_lock(&mtrr_mutex); + + cache_map = kcalloc(new_size, sizeof(*cache_map), GFP_KERNEL); + if (cache_map) { + memmove(cache_map, init_cache_map, + cache_map_n * sizeof(*cache_map)); + cache_map_size = new_size; + } else { + mtrr_state.enabled = 0; + pr_err("MTRRs disabled due to allocation failure for lookup map.\n"); + } + + mutex_unlock(&mtrr_mutex); +} + +/** + * mtrr_overwrite_state - set static MTRR state + * + * Used to set MTRR state via different means (e.g. with data obtained from + * a hypervisor). + * Is allowed only for special cases when running virtualized. Must be called + * from the x86_init.hyper.init_platform() hook. It can be called only once. + * The MTRR state can't be changed afterwards. To ensure that, X86_FEATURE_MTRR + * is cleared. + */ +void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type) +{ + unsigned int i; + + /* Only allowed to be called once before mtrr_bp_init(). */ + if (WARN_ON_ONCE(mtrr_state_set)) + return; + + /* Only allowed when running virtualized. */ + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return; + + /* + * Only allowed for special virtualization cases: + * - when running as Hyper-V, SEV-SNP guest using vTOM + * - when running as Xen PV guest + * - when running as SEV-SNP or TDX guest to avoid unnecessary + * VMM communication/Virtualization exceptions (#VC, #VE) + */ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && + !hv_is_isolation_supported() && + !cpu_feature_enabled(X86_FEATURE_XENPV) && + !cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return; + + /* Disable MTRR in order to disable MTRR modifications. */ + setup_clear_cpu_cap(X86_FEATURE_MTRR); + + if (var) { + if (num_var > MTRR_MAX_VAR_RANGES) { + pr_warn("Trying to overwrite MTRR state with %u variable entries\n", + num_var); + num_var = MTRR_MAX_VAR_RANGES; + } + for (i = 0; i < num_var; i++) + mtrr_state.var_ranges[i] = var[i]; + num_var_ranges = num_var; } - if (prev_match != MTRR_TYPE_INVALID) - return prev_match; + mtrr_state.def_type = def_type; + mtrr_state.enabled |= MTRR_STATE_MTRR_ENABLED; - return mtrr_state.def_type; + mtrr_state_set = 1; +} + +static u8 type_merge(u8 type, u8 new_type, u8 *uniform) +{ + u8 effective_type; + + if (type == MTRR_TYPE_INVALID) + return new_type; + + effective_type = get_effective_type(type, new_type); + if (type != effective_type) + *uniform = 0; + + return effective_type; } /** @@ -248,66 +497,49 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, * MTRR_TYPE_INVALID - MTRR is disabled * * Output Argument: - * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the - * region is fully covered by a single MTRR entry or the default - * type. + * uniform - Set to 1 when the returned MTRR type is valid for the whole + * region, set to 0 else. */ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { - u8 type, prev_type, is_uniform = 1, dummy; - int repeat; - u64 partial_end; + u8 type = MTRR_TYPE_INVALID; + unsigned int i; - /* Make end inclusive instead of exclusive */ - end--; + if (!mtrr_state_set) { + /* Uniformity is unknown. */ + *uniform = 0; + return MTRR_TYPE_UNCACHABLE; + } - if (!mtrr_state_set) - return MTRR_TYPE_INVALID; + *uniform = 1; if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED)) - return MTRR_TYPE_INVALID; + return MTRR_TYPE_UNCACHABLE; - /* - * Look up the fixed ranges first, which take priority over - * the variable ranges. - */ - if ((start < 0x100000) && - (mtrr_state.have_fixed) && - (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { - is_uniform = 0; - type = mtrr_type_lookup_fixed(start, end); - goto out; - } + for (i = 0; i < cache_map_n && start < end; i++) { + /* Region after current map entry? -> continue with next one. */ + if (start >= cache_map[i].end) + continue; - /* - * Look up the variable ranges. Look of multiple ranges matching - * this address and pick type as per MTRR precedence. - */ - type = mtrr_type_lookup_variable(start, end, &partial_end, - &repeat, &is_uniform); + /* Start of region not covered by current map entry? */ + if (start < cache_map[i].start) { + /* At least some part of region has default type. */ + type = type_merge(type, mtrr_state.def_type, uniform); + /* End of region not covered, too? -> lookup done. */ + if (end <= cache_map[i].start) + return type; + } - /* - * Common path is with repeat = 0. - * However, we can have cases where [start:end] spans across some - * MTRR ranges and/or the default type. Do repeated lookups for - * that case here. - */ - while (repeat) { - prev_type = type; - start = partial_end; - is_uniform = 0; - type = mtrr_type_lookup_variable(start, end, &partial_end, - &repeat, &dummy); + /* At least part of region covered by map entry. */ + type = type_merge(type, cache_map[i].type, uniform); - if (check_type_overlap(&prev_type, &type)) - goto out; + start = cache_map[i].end; } - if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2)) - type = MTRR_TYPE_WRBACK; + /* End of region past last entry in map? -> use default type. */ + if (start < end) + type = type_merge(type, mtrr_state.def_type, uniform); -out: - *uniform = is_uniform; return type; } @@ -363,8 +595,8 @@ static void __init print_fixed_last(void) if (!last_fixed_end) return; - pr_debug(" %05X-%05X %s\n", last_fixed_start, - last_fixed_end - 1, mtrr_attrib_to_str(last_fixed_type)); + pr_info(" %05X-%05X %s\n", last_fixed_start, + last_fixed_end - 1, mtrr_attrib_to_str(last_fixed_type)); last_fixed_end = 0; } @@ -402,10 +634,10 @@ static void __init print_mtrr_state(void) unsigned int i; int high_width; - pr_debug("MTRR default type: %s\n", - mtrr_attrib_to_str(mtrr_state.def_type)); + pr_info("MTRR default type: %s\n", + mtrr_attrib_to_str(mtrr_state.def_type)); if (mtrr_state.have_fixed) { - pr_debug("MTRR fixed ranges %sabled:\n", + pr_info("MTRR fixed ranges %sabled:\n", ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ? "en" : "dis"); @@ -420,26 +652,27 @@ static void __init print_mtrr_state(void) /* tail */ print_fixed_last(); } - pr_debug("MTRR variable ranges %sabled:\n", - mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); - high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4; + pr_info("MTRR variable ranges %sabled:\n", + mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); + high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { - if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) - pr_debug(" %u base %0*X%05X000 mask %0*X%05X000 %s\n", - i, - high_width, - mtrr_state.var_ranges[i].base_hi, - mtrr_state.var_ranges[i].base_lo >> 12, - high_width, - mtrr_state.var_ranges[i].mask_hi, - mtrr_state.var_ranges[i].mask_lo >> 12, - mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & 0xff)); + if (mtrr_state.var_ranges[i].mask_lo & MTRR_PHYSMASK_V) + pr_info(" %u base %0*X%05X000 mask %0*X%05X000 %s\n", + i, + high_width, + mtrr_state.var_ranges[i].base_hi, + mtrr_state.var_ranges[i].base_lo >> 12, + high_width, + mtrr_state.var_ranges[i].mask_hi, + mtrr_state.var_ranges[i].mask_lo >> 12, + mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & + MTRR_PHYSBASE_TYPE)); else - pr_debug(" %u disabled\n", i); + pr_info(" %u disabled\n", i); } if (mtrr_tom2) - pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); + pr_info("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } /* Grab all of the MTRR state for this CPU into *state */ @@ -452,7 +685,7 @@ bool __init get_mtrr_state(void) vrs = mtrr_state.var_ranges; rdmsr(MSR_MTRRcap, lo, dummy); - mtrr_state.have_fixed = (lo >> 8) & 1; + mtrr_state.have_fixed = lo & MTRR_CAP_FIX; for (i = 0; i < num_var_ranges; i++) get_mtrr_var_range(i, &vrs[i]); @@ -460,8 +693,8 @@ bool __init get_mtrr_state(void) get_fixed_ranges(mtrr_state.fixed_ranges); rdmsr(MSR_MTRRdefType, lo, dummy); - mtrr_state.def_type = (lo & 0xff); - mtrr_state.enabled = (lo & 0xc00) >> 10; + mtrr_state.def_type = lo & MTRR_DEF_TYPE_TYPE; + mtrr_state.enabled = (lo & MTRR_DEF_TYPE_ENABLE) >> MTRR_STATE_SHIFT; if (amd_special_default_mtrr()) { unsigned low, high; @@ -474,7 +707,8 @@ bool __init get_mtrr_state(void) mtrr_tom2 &= 0xffffff800000ULL; } - print_mtrr_state(); + if (mtrr_debug) + print_mtrr_state(); mtrr_state_set = 1; @@ -574,7 +808,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); - if ((mask_lo & 0x800) == 0) { + if (!(mask_lo & MTRR_PHYSMASK_V)) { /* Invalid (i.e. free) range */ *base = 0; *size = 0; @@ -585,8 +819,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask: */ - tmp = (u64)mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; - mask = size_or_mask | tmp; + tmp = (u64)mask_hi << 32 | (mask_lo & PAGE_MASK); + mask = (u64)phys_hi_rsvd << 32 | tmp; /* Expand tmp with high bits to all 1s: */ hi = fls64(tmp); @@ -604,9 +838,9 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, * This works correctly if size is a power of two, i.e. a * contiguous range: */ - *size = -mask; + *size = -mask >> PAGE_SHIFT; *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; - *type = base_lo & 0xff; + *type = base_lo & MTRR_PHYSBASE_TYPE; out_put_cpu: put_cpu(); @@ -644,9 +878,8 @@ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) bool changed = false; rdmsr(MTRRphysBase_MSR(index), lo, hi); - if ((vr->base_lo & 0xfffff0ffUL) != (lo & 0xfffff0ffUL) - || (vr->base_hi & (size_and_mask >> (32 - PAGE_SHIFT))) != - (hi & (size_and_mask >> (32 - PAGE_SHIFT)))) { + if ((vr->base_lo & ~MTRR_PHYSBASE_RSVD) != (lo & ~MTRR_PHYSBASE_RSVD) + || (vr->base_hi & ~phys_hi_rsvd) != (hi & ~phys_hi_rsvd)) { mtrr_wrmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi); changed = true; @@ -654,9 +887,8 @@ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) rdmsr(MTRRphysMask_MSR(index), lo, hi); - if ((vr->mask_lo & 0xfffff800UL) != (lo & 0xfffff800UL) - || (vr->mask_hi & (size_and_mask >> (32 - PAGE_SHIFT))) != - (hi & (size_and_mask >> (32 - PAGE_SHIFT)))) { + if ((vr->mask_lo & ~MTRR_PHYSMASK_RSVD) != (lo & ~MTRR_PHYSMASK_RSVD) + || (vr->mask_hi & ~phys_hi_rsvd) != (hi & ~phys_hi_rsvd)) { mtrr_wrmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi); changed = true; } @@ -691,11 +923,12 @@ static unsigned long set_mtrr_state(void) * Set_mtrr_restore restores the old value of MTRRdefType, * so to set it we fiddle with the saved value: */ - if ((deftype_lo & 0xff) != mtrr_state.def_type - || ((deftype_lo & 0xc00) >> 10) != mtrr_state.enabled) { + if ((deftype_lo & MTRR_DEF_TYPE_TYPE) != mtrr_state.def_type || + ((deftype_lo & MTRR_DEF_TYPE_ENABLE) >> MTRR_STATE_SHIFT) != mtrr_state.enabled) { - deftype_lo = (deftype_lo & ~0xcff) | mtrr_state.def_type | - (mtrr_state.enabled << 10); + deftype_lo = (deftype_lo & MTRR_DEF_TYPE_DISABLE) | + mtrr_state.def_type | + (mtrr_state.enabled << MTRR_STATE_SHIFT); change_mask |= MTRR_CHANGE_MASK_DEFTYPE; } @@ -708,7 +941,7 @@ void mtrr_disable(void) rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); /* Disable MTRRs, and set the default type to uncached */ - mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi); + mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & MTRR_DEF_TYPE_DISABLE, deftype_hi); } void mtrr_enable(void) @@ -762,9 +995,9 @@ static void generic_set_mtrr(unsigned int reg, unsigned long base, memset(vr, 0, sizeof(struct mtrr_var_range)); } else { vr->base_lo = base << PAGE_SHIFT | type; - vr->base_hi = (base & size_and_mask) >> (32 - PAGE_SHIFT); - vr->mask_lo = -size << PAGE_SHIFT | 0x800; - vr->mask_hi = (-size & size_and_mask) >> (32 - PAGE_SHIFT); + vr->base_hi = (base >> (32 - PAGE_SHIFT)) & ~phys_hi_rsvd; + vr->mask_lo = -size << PAGE_SHIFT | MTRR_PHYSMASK_V; + vr->mask_hi = (-size >> (32 - PAGE_SHIFT)) & ~phys_hi_rsvd; mtrr_wrmsr(MTRRphysBase_MSR(reg), vr->base_lo, vr->base_hi); mtrr_wrmsr(MTRRphysMask_MSR(reg), vr->mask_lo, vr->mask_hi); @@ -783,7 +1016,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, * For Intel PPro stepping <= 7 * must be 4 MiB aligned and not touch 0x70000000 -> 0x7003FFFF */ - if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 && + if (mtrr_if == &generic_mtrr_ops && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { @@ -817,7 +1050,7 @@ static int generic_have_wrcomb(void) { unsigned long config, dummy; rdmsr(MSR_MTRRcap, config, dummy); - return config & (1 << 10); + return config & MTRR_CAP_WC; } int positive_have_wrcomb(void) diff --git a/arch/x86/kernel/cpu/mtrr/legacy.c b/arch/x86/kernel/cpu/mtrr/legacy.c new file mode 100644 index 000000000000..d25882fcf181 --- /dev/null +++ b/arch/x86/kernel/cpu/mtrr/legacy.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/syscore_ops.h> +#include <asm/cpufeature.h> +#include <asm/mtrr.h> +#include <asm/processor.h> +#include "mtrr.h" + +void mtrr_set_if(void) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + /* Pre-Athlon (K6) AMD CPU MTRRs */ + if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) + mtrr_if = &amd_mtrr_ops; + break; + case X86_VENDOR_CENTAUR: + if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) + mtrr_if = ¢aur_mtrr_ops; + break; + case X86_VENDOR_CYRIX: + if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) + mtrr_if = &cyrix_mtrr_ops; + break; + default: + break; + } +} + +/* + * The suspend/resume methods are only for CPUs without MTRR. CPUs using generic + * MTRR driver don't require this. + */ +struct mtrr_value { + mtrr_type ltype; + unsigned long lbase; + unsigned long lsize; +}; + +static struct mtrr_value *mtrr_value; + +static int mtrr_save(void) +{ + int i; + + if (!mtrr_value) + return -ENOMEM; + + for (i = 0; i < num_var_ranges; i++) { + mtrr_if->get(i, &mtrr_value[i].lbase, + &mtrr_value[i].lsize, + &mtrr_value[i].ltype); + } + return 0; +} + +static void mtrr_restore(void) +{ + int i; + + for (i = 0; i < num_var_ranges; i++) { + if (mtrr_value[i].lsize) { + mtrr_if->set(i, mtrr_value[i].lbase, + mtrr_value[i].lsize, + mtrr_value[i].ltype); + } + } +} + +static struct syscore_ops mtrr_syscore_ops = { + .suspend = mtrr_save, + .resume = mtrr_restore, +}; + +void mtrr_register_syscore(void) +{ + mtrr_value = kcalloc(num_var_ranges, sizeof(*mtrr_value), GFP_KERNEL); + + /* + * The CPU has no MTRR and seems to not support SMP. They have + * specific drivers, we use a tricky method to support + * suspend/resume for them. + * + * TBD: is there any system with such CPU which supports + * suspend/resume? If no, we should remove the code. + */ + register_syscore_ops(&mtrr_syscore_ops); +} diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 783f3210d582..767bf1c71aad 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -59,15 +59,9 @@ #define MTRR_TO_PHYS_WC_OFFSET 1000 u32 num_var_ranges; -static bool mtrr_enabled(void) -{ - return !!mtrr_if; -} unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; -static DEFINE_MUTEX(mtrr_mutex); - -u64 size_or_mask, size_and_mask; +DEFINE_MUTEX(mtrr_mutex); const struct mtrr_ops *mtrr_if; @@ -105,21 +99,6 @@ static int have_wrcomb(void) return mtrr_if->have_wrcomb ? mtrr_if->have_wrcomb() : 0; } -/* This function returns the number of variable MTRRs */ -static void __init set_num_var_ranges(bool use_generic) -{ - unsigned long config = 0, dummy; - - if (use_generic) - rdmsr(MSR_MTRRcap, config, dummy); - else if (is_cpu(AMD) || is_cpu(HYGON)) - config = 2; - else if (is_cpu(CYRIX) || is_cpu(CENTAUR)) - config = 8; - - num_var_ranges = config & 0xff; -} - static void __init init_table(void) { int i, max; @@ -194,20 +173,8 @@ static inline int types_compatible(mtrr_type type1, mtrr_type type2) * Note that the mechanism is the same for UP systems, too; all the SMP stuff * becomes nops. */ -static void -set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) -{ - struct set_mtrr_data data = { .smp_reg = reg, - .smp_base = base, - .smp_size = size, - .smp_type = type - }; - - stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask); -} - -static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base, - unsigned long size, mtrr_type type) +static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, + mtrr_type type) { struct set_mtrr_data data = { .smp_reg = reg, .smp_base = base, @@ -216,6 +183,8 @@ static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base, }; stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask); + + generic_rebuild_map(); } /** @@ -337,7 +306,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* Search for an empty MTRR */ i = mtrr_if->get_free_region(base, size, replace); if (i >= 0) { - set_mtrr_cpuslocked(i, base, size, type); + set_mtrr(i, base, size, type); if (likely(replace < 0)) { mtrr_usage_table[i] = 1; } else { @@ -345,7 +314,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (increment) mtrr_usage_table[i]++; if (unlikely(replace != i)) { - set_mtrr_cpuslocked(replace, 0, 0, 0); + set_mtrr(replace, 0, 0, 0); mtrr_usage_table[replace] = 0; } } @@ -363,7 +332,7 @@ static int mtrr_check(unsigned long base, unsigned long size) { if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { pr_warn("size and base must be multiples of 4 kiB\n"); - pr_debug("size: 0x%lx base: 0x%lx\n", size, base); + Dprintk("size: 0x%lx base: 0x%lx\n", size, base); dump_stack(); return -1; } @@ -454,8 +423,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) } } if (reg < 0) { - pr_debug("no MTRR for %lx000,%lx000 found\n", - base, size); + Dprintk("no MTRR for %lx000,%lx000 found\n", base, size); goto out; } } @@ -473,7 +441,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) goto out; } if (--mtrr_usage_table[reg] < 1) - set_mtrr_cpuslocked(reg, 0, 0, 0); + set_mtrr(reg, 0, 0, 0); error = reg; out: mutex_unlock(&mtrr_mutex); @@ -574,136 +542,54 @@ int arch_phys_wc_index(int handle) } EXPORT_SYMBOL_GPL(arch_phys_wc_index); -/* The suspend/resume methods are only for CPU without MTRR. CPU using generic - * MTRR driver doesn't require this - */ -struct mtrr_value { - mtrr_type ltype; - unsigned long lbase; - unsigned long lsize; -}; - -static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES]; - -static int mtrr_save(void) -{ - int i; - - for (i = 0; i < num_var_ranges; i++) { - mtrr_if->get(i, &mtrr_value[i].lbase, - &mtrr_value[i].lsize, - &mtrr_value[i].ltype); - } - return 0; -} - -static void mtrr_restore(void) -{ - int i; - - for (i = 0; i < num_var_ranges; i++) { - if (mtrr_value[i].lsize) { - set_mtrr(i, mtrr_value[i].lbase, - mtrr_value[i].lsize, - mtrr_value[i].ltype); - } - } -} - - - -static struct syscore_ops mtrr_syscore_ops = { - .suspend = mtrr_save, - .resume = mtrr_restore, -}; - int __initdata changed_by_mtrr_cleanup; -#define SIZE_OR_MASK_BITS(n) (~((1ULL << ((n) - PAGE_SHIFT)) - 1)) /** - * mtrr_bp_init - initialize mtrrs on the boot CPU + * mtrr_bp_init - initialize MTRRs on the boot CPU * * This needs to be called early; before any of the other CPUs are * initialized (i.e. before smp_init()). - * */ void __init mtrr_bp_init(void) { + bool generic_mtrrs = cpu_feature_enabled(X86_FEATURE_MTRR); const char *why = "(not available)"; - u32 phys_addr; - - phys_addr = 32; + unsigned long config, dummy; - if (boot_cpu_has(X86_FEATURE_MTRR)) { - mtrr_if = &generic_mtrr_ops; - size_or_mask = SIZE_OR_MASK_BITS(36); - size_and_mask = 0x00f00000; - phys_addr = 36; + phys_hi_rsvd = GENMASK(31, boot_cpu_data.x86_phys_bits - 32); + if (!generic_mtrrs && mtrr_state.enabled) { /* - * This is an AMD specific MSR, but we assume(hope?) that - * Intel will implement it too when they extend the address - * bus of the Xeon. + * Software overwrite of MTRR state, only for generic case. + * Note that X86_FEATURE_MTRR has been reset in this case. */ - if (cpuid_eax(0x80000000) >= 0x80000008) { - phys_addr = cpuid_eax(0x80000008) & 0xff; - /* CPUID workaround for Intel 0F33/0F34 CPU */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && - boot_cpu_data.x86 == 0xF && - boot_cpu_data.x86_model == 0x3 && - (boot_cpu_data.x86_stepping == 0x3 || - boot_cpu_data.x86_stepping == 0x4)) - phys_addr = 36; - - size_or_mask = SIZE_OR_MASK_BITS(phys_addr); - size_and_mask = ~size_or_mask & 0xfffff00000ULL; - } else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR && - boot_cpu_data.x86 == 6) { - /* - * VIA C* family have Intel style MTRRs, - * but don't support PAE - */ - size_or_mask = SIZE_OR_MASK_BITS(32); - size_and_mask = 0; - phys_addr = 32; - } - } else { - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) { - /* Pre-Athlon (K6) AMD CPU MTRRs */ - mtrr_if = &amd_mtrr_ops; - size_or_mask = SIZE_OR_MASK_BITS(32); - size_and_mask = 0; - } - break; - case X86_VENDOR_CENTAUR: - if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) { - mtrr_if = ¢aur_mtrr_ops; - size_or_mask = SIZE_OR_MASK_BITS(32); - size_and_mask = 0; - } - break; - case X86_VENDOR_CYRIX: - if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) { - mtrr_if = &cyrix_mtrr_ops; - size_or_mask = SIZE_OR_MASK_BITS(32); - size_and_mask = 0; - } - break; - default: - break; - } + init_table(); + mtrr_build_map(); + pr_info("MTRRs set to read-only\n"); + + return; } + if (generic_mtrrs) + mtrr_if = &generic_mtrr_ops; + else + mtrr_set_if(); + if (mtrr_enabled()) { - set_num_var_ranges(mtrr_if == &generic_mtrr_ops); + /* Get the number of variable MTRR ranges. */ + if (mtrr_if == &generic_mtrr_ops) + rdmsr(MSR_MTRRcap, config, dummy); + else + config = mtrr_if->var_regs; + num_var_ranges = config & MTRR_CAP_VCNT; + init_table(); if (mtrr_if == &generic_mtrr_ops) { /* BIOS may override */ if (get_mtrr_state()) { memory_caching_control |= CACHE_MTRR; - changed_by_mtrr_cleanup = mtrr_cleanup(phys_addr); + changed_by_mtrr_cleanup = mtrr_cleanup(); + mtrr_build_map(); } else { mtrr_if = NULL; why = "by BIOS"; @@ -730,8 +616,14 @@ void mtrr_save_state(void) smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); } -static int __init mtrr_init_finialize(void) +static int __init mtrr_init_finalize(void) { + /* + * Map might exist if mtrr_overwrite_state() has been called or if + * mtrr_enabled() returns true. + */ + mtrr_copy_map(); + if (!mtrr_enabled()) return 0; @@ -741,16 +633,8 @@ static int __init mtrr_init_finialize(void) return 0; } - /* - * The CPU has no MTRR and seems to not support SMP. They have - * specific drivers, we use a tricky method to support - * suspend/resume for them. - * - * TBD: is there any system with such CPU which supports - * suspend/resume? If no, we should remove the code. - */ - register_syscore_ops(&mtrr_syscore_ops); + mtrr_register_syscore(); return 0; } -subsys_initcall(mtrr_init_finialize); +subsys_initcall(mtrr_init_finalize); diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 02eb5871492d..5655f253d929 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -10,10 +10,13 @@ #define MTRR_CHANGE_MASK_VARIABLE 0x02 #define MTRR_CHANGE_MASK_DEFTYPE 0x04 +extern bool mtrr_debug; +#define Dprintk(x...) do { if (mtrr_debug) pr_info(x); } while (0) + extern unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; struct mtrr_ops { - u32 vendor; + u32 var_regs; void (*set)(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type); void (*get)(unsigned int reg, unsigned long *base, @@ -51,18 +54,26 @@ void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); -extern u64 size_or_mask, size_and_mask; extern const struct mtrr_ops *mtrr_if; - -#define is_cpu(vnd) (mtrr_if && mtrr_if->vendor == X86_VENDOR_##vnd) +extern struct mutex mtrr_mutex; extern unsigned int num_var_ranges; extern u64 mtrr_tom2; extern struct mtrr_state_type mtrr_state; +extern u32 phys_hi_rsvd; void mtrr_state_warn(void); const char *mtrr_attrib_to_str(int x); void mtrr_wrmsr(unsigned, unsigned, unsigned); +#ifdef CONFIG_X86_32 +void mtrr_set_if(void); +void mtrr_register_syscore(void); +#else +static inline void mtrr_set_if(void) { } +static inline void mtrr_register_syscore(void) { } +#endif +void mtrr_build_map(void); +void mtrr_copy_map(void); /* CPU specific mtrr_ops vectors. */ extern const struct mtrr_ops amd_mtrr_ops; @@ -70,4 +81,14 @@ extern const struct mtrr_ops cyrix_mtrr_ops; extern const struct mtrr_ops centaur_mtrr_ops; extern int changed_by_mtrr_cleanup; -extern int mtrr_cleanup(unsigned address_bits); +extern int mtrr_cleanup(void); + +/* + * Must be used by code which uses mtrr_if to call platform-specific + * MTRR manipulation functions. + */ +static inline bool mtrr_enabled(void) +{ + return !!mtrr_if; +} +void generic_rebuild_map(void); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 6ad33f355861..725344048f85 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -726,11 +726,15 @@ unlock: static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) { struct task_struct *p, *t; + pid_t pid; rcu_read_lock(); for_each_process_thread(p, t) { - if (is_closid_match(t, r) || is_rmid_match(t, r)) - seq_printf(s, "%d\n", t->pid); + if (is_closid_match(t, r) || is_rmid_match(t, r)) { + pid = task_pid_vnr(t); + if (pid) + seq_printf(s, "%d\n", pid); + } } rcu_read_unlock(); } @@ -2301,6 +2305,26 @@ static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) } } +static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn) +{ + atomic_inc(&rdtgrp->waitcount); + kernfs_break_active_protection(kn); +} + +static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn) +{ + if (atomic_dec_and_test(&rdtgrp->waitcount) && + (rdtgrp->flags & RDT_DELETED)) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); + kernfs_unbreak_active_protection(kn); + rdtgroup_remove(rdtgrp); + } else { + kernfs_unbreak_active_protection(kn); + } +} + struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) { struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); @@ -2308,8 +2332,7 @@ struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) if (!rdtgrp) return NULL; - atomic_inc(&rdtgrp->waitcount); - kernfs_break_active_protection(kn); + rdtgroup_kn_get(rdtgrp, kn); mutex_lock(&rdtgroup_mutex); @@ -2328,17 +2351,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) return; mutex_unlock(&rdtgroup_mutex); - - if (atomic_dec_and_test(&rdtgrp->waitcount) && - (rdtgrp->flags & RDT_DELETED)) { - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || - rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) - rdtgroup_pseudo_lock_remove(rdtgrp); - kernfs_unbreak_active_protection(kn); - rdtgroup_remove(rdtgrp); - } else { - kernfs_unbreak_active_protection(kn); - } + rdtgroup_kn_put(rdtgrp, kn); } static int mkdir_mondata_all(struct kernfs_node *parent_kn, @@ -3505,6 +3518,133 @@ out: return ret; } +/** + * mongrp_reparent() - replace parent CTRL_MON group of a MON group + * @rdtgrp: the MON group whose parent should be replaced + * @new_prdtgrp: replacement parent CTRL_MON group for @rdtgrp + * @cpus: cpumask provided by the caller for use during this call + * + * Replaces the parent CTRL_MON group for a MON group, resulting in all member + * tasks' CLOSID immediately changing to that of the new parent group. + * Monitoring data for the group is unaffected by this operation. + */ +static void mongrp_reparent(struct rdtgroup *rdtgrp, + struct rdtgroup *new_prdtgrp, + cpumask_var_t cpus) +{ + struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + + WARN_ON(rdtgrp->type != RDTMON_GROUP); + WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP); + + /* Nothing to do when simply renaming a MON group. */ + if (prdtgrp == new_prdtgrp) + return; + + WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); + list_move_tail(&rdtgrp->mon.crdtgrp_list, + &new_prdtgrp->mon.crdtgrp_list); + + rdtgrp->mon.parent = new_prdtgrp; + rdtgrp->closid = new_prdtgrp->closid; + + /* Propagate updated closid to all tasks in this group. */ + rdt_move_group_tasks(rdtgrp, rdtgrp, cpus); + + update_closid_rmid(cpus, NULL); +} + +static int rdtgroup_rename(struct kernfs_node *kn, + struct kernfs_node *new_parent, const char *new_name) +{ + struct rdtgroup *new_prdtgrp; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + int ret; + + rdtgrp = kernfs_to_rdtgroup(kn); + new_prdtgrp = kernfs_to_rdtgroup(new_parent); + if (!rdtgrp || !new_prdtgrp) + return -ENOENT; + + /* Release both kernfs active_refs before obtaining rdtgroup mutex. */ + rdtgroup_kn_get(rdtgrp, kn); + rdtgroup_kn_get(new_prdtgrp, new_parent); + + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + /* + * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if + * either kernfs_node is a file. + */ + if (kernfs_type(kn) != KERNFS_DIR || + kernfs_type(new_parent) != KERNFS_DIR) { + rdt_last_cmd_puts("Source and destination must be directories"); + ret = -EPERM; + goto out; + } + + if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) { + ret = -ENOENT; + goto out; + } + + if (rdtgrp->type != RDTMON_GROUP || !kn->parent || + !is_mon_groups(kn->parent, kn->name)) { + rdt_last_cmd_puts("Source must be a MON group\n"); + ret = -EPERM; + goto out; + } + + if (!is_mon_groups(new_parent, new_name)) { + rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n"); + ret = -EPERM; + goto out; + } + + /* + * If the MON group is monitoring CPUs, the CPUs must be assigned to the + * current parent CTRL_MON group and therefore cannot be assigned to + * the new parent, making the move illegal. + */ + if (!cpumask_empty(&rdtgrp->cpu_mask) && + rdtgrp->mon.parent != new_prdtgrp) { + rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n"); + ret = -EPERM; + goto out; + } + + /* + * Allocate the cpumask for use in mongrp_reparent() to avoid the + * possibility of failing to allocate it after kernfs_rename() has + * succeeded. + */ + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) { + ret = -ENOMEM; + goto out; + } + + /* + * Perform all input validation and allocations needed to ensure + * mongrp_reparent() will succeed before calling kernfs_rename(), + * otherwise it would be necessary to revert this call if + * mongrp_reparent() failed. + */ + ret = kernfs_rename(kn, new_parent, new_name); + if (!ret) + mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask); + + free_cpumask_var(tmpmask); + +out: + mutex_unlock(&rdtgroup_mutex); + rdtgroup_kn_put(rdtgrp, kn); + rdtgroup_kn_put(new_prdtgrp, new_parent); + return ret; +} + static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) @@ -3522,6 +3662,7 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { .mkdir = rdtgroup_mkdir, .rmdir = rdtgroup_rmdir, + .rename = rdtgroup_rename, .show_options = rdtgroup_show_options, }; diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 2a0e90fe2abc..91fa70e51004 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -755,6 +755,7 @@ static void sgx_mmu_notifier_release(struct mmu_notifier *mn, { struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier); struct sgx_encl_mm *tmp = NULL; + bool found = false; /* * The enclave itself can remove encl_mm. Note, objects can't be moved @@ -764,12 +765,13 @@ static void sgx_mmu_notifier_release(struct mmu_notifier *mn, list_for_each_entry(tmp, &encl_mm->encl->mm_list, list) { if (tmp == encl_mm) { list_del_rcu(&encl_mm->list); + found = true; break; } } spin_unlock(&encl_mm->encl->mm_lock); - if (tmp == encl_mm) { + if (found) { synchronize_srcu(&encl_mm->encl->srcu); mmu_notifier_put(mn); } diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 21ca0a831b70..5d390df21440 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -214,7 +214,7 @@ static int __sgx_encl_add_page(struct sgx_encl *encl, if (!(vma->vm_flags & VM_MAYEXEC)) return -EACCES; - ret = get_user_pages(src, 1, 0, &src_page, NULL); + ret = get_user_pages(src, 1, 0, &src_page); if (ret < 1) return -EFAULT; diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c index c3e37eaec8ec..7aaa3652e31d 100644 --- a/arch/x86/kernel/cpu/sgx/virt.c +++ b/arch/x86/kernel/cpu/sgx/virt.c @@ -204,6 +204,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file) continue; xa_erase(&vepc->page_array, index); + cond_resched(); } /* @@ -222,6 +223,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file) list_add_tail(&epc_page->list, &secs_pages); xa_erase(&vepc->page_array, index); + cond_resched(); } /* @@ -243,6 +245,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file) if (sgx_vepc_free_page(epc_page)) list_add_tail(&epc_page->list, &secs_pages); + cond_resched(); } if (!list_empty(&secs_pages)) |