summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/acrn.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c241
-rw-r--r--arch/x86/kernel/cpu/bugs.c371
-rw-r--r--arch/x86/kernel/cpu/common.c89
-rw-r--r--arch/x86/kernel/cpu/cpu.h1
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c1
-rw-r--r--arch/x86/kernel/cpu/hygon.c3
-rw-r--r--arch/x86/kernel/cpu/intel.c176
-rw-r--r--arch/x86/kernel/cpu/intel_epb.c2
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c6
-rw-r--r--arch/x86/kernel/cpu/mce/core.c35
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c3
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c19
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h6
-rw-r--r--arch/x86/kernel/cpu/mce/threshold.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/Makefile4
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c133
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c17
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c304
-rw-r--r--arch/x86/kernel/cpu/microcode/internal.h131
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c4
-rw-r--r--arch/x86/kernel/cpu/proc.c23
22 files changed, 1105 insertions, 468 deletions
diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index 485441b7f030..bfeb18fad63f 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -51,7 +51,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_acrn_hv_callback)
* will block the interrupt whose vector is lower than
* HYPERVISOR_CALLBACK_VECTOR.
*/
- ack_APIC_irq();
+ apic_eoi();
inc_irq_stat(irq_hv_callback_count);
if (acrn_intr_handler)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 571abf808ea3..dd8379d84445 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);
@@ -934,7 +1047,7 @@ static void init_amd(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_FSRS);
/* get apicid instead of initial apic id from cpuid */
- c->apicid = hard_smp_processor_id();
+ c->apicid = read_apic_id();
/* K6s reports MCEs but don't actually have all the MSRs */
if (c->x86 < 6)
@@ -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 9e2a91830f72..f081d26616ac 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -47,6 +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;
@@ -56,8 +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)
{
@@ -160,6 +167,13 @@ void __init cpu_select_mitigations(void)
md_clear_select_mitigation();
srbds_select_mitigation();
l1d_flush_select_mitigation();
+
+ /*
+ * srso_select_mitigation() depends and must run after
+ * retbleed_select_mitigation().
+ */
+ srso_select_mitigation();
+ gds_select_mitigation();
}
/*
@@ -646,6 +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 {
@@ -885,6 +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);
@@ -894,6 +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;
@@ -1150,19 +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;
/*
@@ -2186,6 +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
@@ -2294,7 +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) {
@@ -2382,6 +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)
{
@@ -2431,6 +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;
}
@@ -2495,4 +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/common.c b/arch/x86/kernel/cpu/common.c
index 52683fddafaf..6d75fab10161 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -59,7 +59,6 @@
#include <asm/cacheinfo.h>
#include <asm/memtype.h>
#include <asm/microcode.h>
-#include <asm/microcode_intel.h>
#include <asm/intel-family.h>
#include <asm/cpu_device_id.h>
#include <asm/uv/uv.h>
@@ -588,27 +587,43 @@ __noendbr void ibt_restore(u64 save)
static __always_inline void setup_cet(struct cpuinfo_x86 *c)
{
- u64 msr = CET_ENDBR_EN;
+ bool user_shstk, kernel_ibt;
- if (!HAS_KERNEL_IBT ||
- !cpu_feature_enabled(X86_FEATURE_IBT))
+ if (!IS_ENABLED(CONFIG_X86_CET))
return;
- wrmsrl(MSR_IA32_S_CET, msr);
+ kernel_ibt = HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT);
+ user_shstk = cpu_feature_enabled(X86_FEATURE_SHSTK) &&
+ IS_ENABLED(CONFIG_X86_USER_SHADOW_STACK);
+
+ if (!kernel_ibt && !user_shstk)
+ return;
+
+ if (user_shstk)
+ set_cpu_cap(c, X86_FEATURE_USER_SHSTK);
+
+ if (kernel_ibt)
+ wrmsrl(MSR_IA32_S_CET, CET_ENDBR_EN);
+ else
+ wrmsrl(MSR_IA32_S_CET, 0);
+
cr4_set_bits(X86_CR4_CET);
- if (!ibt_selftest()) {
+ if (kernel_ibt && ibt_selftest()) {
pr_err("IBT selftest: Failed!\n");
wrmsrl(MSR_IA32_S_CET, 0);
setup_clear_cpu_cap(X86_FEATURE_IBT);
- return;
}
}
__noendbr void cet_disable(void)
{
- if (cpu_feature_enabled(X86_FEATURE_IBT))
- wrmsrl(MSR_IA32_S_CET, 0);
+ if (!(cpu_feature_enabled(X86_FEATURE_IBT) ||
+ cpu_feature_enabled(X86_FEATURE_SHSTK)))
+ return;
+
+ wrmsrl(MSR_IA32_S_CET, 0);
+ wrmsrl(MSR_IA32_U_CET, 0);
}
/*
@@ -1250,6 +1265,10 @@ 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),
@@ -1262,27 +1281,30 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
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_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
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(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS),
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),
{}
};
@@ -1406,6 +1428,21 @@ 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;
@@ -1470,6 +1507,9 @@ static void __init cpu_parse_early_param(void)
if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+ if (cmdline_find_option_bool(boot_command_line, "nousershstk"))
+ setup_clear_cpu_cap(X86_FEATURE_USER_SHSTK);
+
arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
if (arglen <= 0)
return;
@@ -1937,7 +1977,7 @@ void enable_sep_cpu(void)
}
#endif
-void __init identify_boot_cpu(void)
+static __init void identify_boot_cpu(void)
{
identify_cpu(&boot_cpu_data);
if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
@@ -1962,6 +2002,8 @@ 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();
}
@@ -2276,8 +2318,7 @@ void store_cpu_caps(struct cpuinfo_x86 *curr_info)
* @prev_info: CPU capabilities stored before an update.
*
* The microcode loader calls this upon late microcode load to recheck features,
- * only when microcode has been updated. Caller holds microcode_mutex and CPU
- * hotplug lock.
+ * only when microcode has been updated. Caller holds and CPU hotplug lock.
*
* Return: None
*/
@@ -2287,6 +2328,8 @@ 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,
@@ -2317,7 +2360,7 @@ void __init arch_cpu_finalize_init(void)
* identify_boot_cpu() initialized SMT support information, let the
* core code know.
*/
- cpu_smt_check_topology();
+ cpu_smt_set_num_threads(smp_num_siblings, smp_num_siblings);
if (!IS_ENABLED(CONFIG_SMP)) {
pr_info("CPU: ");
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 1c44630d4789..1dcd7d4e38ef 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -83,6 +83,7 @@ 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/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index f6748c8bd647..e462c1d3800a 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -81,6 +81,7 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_XFD, X86_FEATURE_XSAVES },
{ X86_FEATURE_XFD, X86_FEATURE_XGETBV1 },
{ X86_FEATURE_AMX_TILE, X86_FEATURE_XFD },
+ { X86_FEATURE_SHSTK, X86_FEATURE_XSAVES },
{}
};
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 5a2962c492d3..defdc594be14 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -8,6 +8,7 @@
*/
#include <linux/io.h>
+#include <asm/apic.h>
#include <asm/cpu.h>
#include <asm/smp.h>
#include <asm/numa.h>
@@ -300,7 +301,7 @@ static void init_hygon(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
/* get apicid instead of initial apic id from cpuid */
- c->apicid = hard_smp_processor_id();
+ c->apicid = read_apic_id();
/*
* XXX someone from Hygon needs to confirm this DTRT
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1c4639588ff9..be4045628fd3 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -20,7 +20,7 @@
#include <asm/bugs.h>
#include <asm/cpu.h>
#include <asm/intel-family.h>
-#include <asm/microcode_intel.h>
+#include <asm/microcode.h>
#include <asm/hwcap2.h>
#include <asm/elf.h>
#include <asm/cpu_device_id.h>
@@ -184,180 +184,6 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
return false;
}
-int intel_cpu_collect_info(struct ucode_cpu_info *uci)
-{
- unsigned int val[2];
- unsigned int family, model;
- struct cpu_signature csig = { 0 };
- unsigned int eax, ebx, ecx, edx;
-
- memset(uci, 0, sizeof(*uci));
-
- eax = 0x00000001;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
- csig.sig = eax;
-
- family = x86_family(eax);
- model = x86_model(eax);
-
- if (model >= 5 || family > 6) {
- /* get processor flags from MSR 0x17 */
- native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
- csig.pf = 1 << ((val[1] >> 18) & 7);
- }
-
- csig.rev = intel_get_microcode_revision();
-
- uci->cpu_sig = csig;
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(intel_cpu_collect_info);
-
-/*
- * Returns 1 if update has been found, 0 otherwise.
- */
-int intel_find_matching_signature(void *mc, unsigned int csig, int cpf)
-{
- struct microcode_header_intel *mc_hdr = mc;
- struct extended_sigtable *ext_hdr;
- struct extended_signature *ext_sig;
- int i;
-
- if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
- return 1;
-
- /* Look for ext. headers: */
- if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE)
- return 0;
-
- ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE;
- ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
-
- for (i = 0; i < ext_hdr->count; i++) {
- if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
- return 1;
- ext_sig++;
- }
- return 0;
-}
-EXPORT_SYMBOL_GPL(intel_find_matching_signature);
-
-/**
- * intel_microcode_sanity_check() - Sanity check microcode file.
- * @mc: Pointer to the microcode file contents.
- * @print_err: Display failure reason if true, silent if false.
- * @hdr_type: Type of file, i.e. normal microcode file or In Field Scan file.
- * Validate if the microcode header type matches with the type
- * specified here.
- *
- * Validate certain header fields and verify if computed checksum matches
- * with the one specified in the header.
- *
- * Return: 0 if the file passes all the checks, -EINVAL if any of the checks
- * fail.
- */
-int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type)
-{
- unsigned long total_size, data_size, ext_table_size;
- struct microcode_header_intel *mc_header = mc;
- struct extended_sigtable *ext_header = NULL;
- u32 sum, orig_sum, ext_sigcount = 0, i;
- struct extended_signature *ext_sig;
-
- total_size = get_totalsize(mc_header);
- data_size = get_datasize(mc_header);
-
- if (data_size + MC_HEADER_SIZE > total_size) {
- if (print_err)
- pr_err("Error: bad microcode data file size.\n");
- return -EINVAL;
- }
-
- if (mc_header->ldrver != 1 || mc_header->hdrver != hdr_type) {
- if (print_err)
- pr_err("Error: invalid/unknown microcode update format. Header type %d\n",
- mc_header->hdrver);
- return -EINVAL;
- }
-
- ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
- if (ext_table_size) {
- u32 ext_table_sum = 0;
- u32 *ext_tablep;
-
- if (ext_table_size < EXT_HEADER_SIZE ||
- ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
- if (print_err)
- pr_err("Error: truncated extended signature table.\n");
- return -EINVAL;
- }
-
- ext_header = mc + MC_HEADER_SIZE + data_size;
- if (ext_table_size != exttable_size(ext_header)) {
- if (print_err)
- pr_err("Error: extended signature table size mismatch.\n");
- return -EFAULT;
- }
-
- ext_sigcount = ext_header->count;
-
- /*
- * Check extended table checksum: the sum of all dwords that
- * comprise a valid table must be 0.
- */
- ext_tablep = (u32 *)ext_header;
-
- i = ext_table_size / sizeof(u32);
- while (i--)
- ext_table_sum += ext_tablep[i];
-
- if (ext_table_sum) {
- if (print_err)
- pr_warn("Bad extended signature table checksum, aborting.\n");
- return -EINVAL;
- }
- }
-
- /*
- * Calculate the checksum of update data and header. The checksum of
- * valid update data and header including the extended signature table
- * must be 0.
- */
- orig_sum = 0;
- i = (MC_HEADER_SIZE + data_size) / sizeof(u32);
- while (i--)
- orig_sum += ((u32 *)mc)[i];
-
- if (orig_sum) {
- if (print_err)
- pr_err("Bad microcode data checksum, aborting.\n");
- return -EINVAL;
- }
-
- if (!ext_table_size)
- return 0;
-
- /*
- * Check extended signature checksum: 0 => valid.
- */
- for (i = 0; i < ext_sigcount; i++) {
- ext_sig = (void *)ext_header + EXT_HEADER_SIZE +
- EXT_SIGNATURE_SIZE * i;
-
- sum = (mc_header->sig + mc_header->pf + mc_header->cksum) -
- (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
- if (sum) {
- if (print_err)
- pr_err("Bad extended signature checksum, aborting.\n");
- return -EINVAL;
- }
- }
- return 0;
-}
-EXPORT_SYMBOL_GPL(intel_microcode_sanity_check);
-
static void early_init_intel(struct cpuinfo_x86 *c)
{
u64 misc_enable;
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index 3b8476158236..e4c3ba91321c 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -206,7 +206,7 @@ static int intel_epb_offline(unsigned int cpu)
static const struct x86_cpu_id intel_epb_normal[] = {
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,
ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,
ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,
ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 5e74610b39e7..c267f43de39e 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -759,7 +759,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_deferred_error)
inc_irq_stat(irq_deferred_error_count);
deferred_error_int_vector();
trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
- ack_APIC_irq();
+ apic_eoi();
}
/*
@@ -1261,10 +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 89e2aab5d34d..6f35f724cc14 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);
@@ -1608,6 +1631,13 @@ static void __start_timer(struct timer_list *t, unsigned long interval)
local_irq_restore(flags);
}
+static void mc_poll_banks_default(void)
+{
+ machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));
+}
+
+void (*mc_poll_banks)(void) = mc_poll_banks_default;
+
static void mce_timer_fn(struct timer_list *t)
{
struct timer_list *cpu_t = this_cpu_ptr(&mce_timer);
@@ -1618,7 +1648,7 @@ static void mce_timer_fn(struct timer_list *t)
iv = __this_cpu_read(mce_next_interval);
if (mce_available(this_cpu_ptr(&cpu_info))) {
- machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));
+ mc_poll_banks();
if (mce_intel_cmci_poll()) {
iv = mce_adjust_timer(iv);
@@ -1842,6 +1872,9 @@ 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/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 12cf2e7ca33c..4d8d4bcf915d 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -270,8 +270,7 @@ static void __maybe_unused raise_mce(struct mce *m)
mce_irq_ipi, NULL, 0);
preempt_enable();
} else if (m->inject_flags & MCJ_NMI_BROADCAST)
- apic->send_IPI_mask(mce_inject_cpumask,
- NMI_VECTOR);
+ __apic_send_IPI_mask(mce_inject_cpumask, NMI_VECTOR);
}
start = jiffies;
while (!cpumask_empty(mce_inject_cpumask)) {
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 95275a5e57e0..f5323551c1a9 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -56,6 +56,13 @@ static DEFINE_PER_CPU(int, cmci_backoff_cnt);
*/
static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
+/*
+ * On systems that do support CMCI but it's disabled, polling for MCEs can
+ * cause the same event to be reported multiple times because IA32_MCi_STATUS
+ * is shared by the same package.
+ */
+static DEFINE_SPINLOCK(cmci_poll_lock);
+
#define CMCI_THRESHOLD 1
#define CMCI_POLL_INTERVAL (30 * HZ)
#define CMCI_STORM_INTERVAL (HZ)
@@ -426,12 +433,22 @@ void cmci_disable_bank(int bank)
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
+/* Bank polling function when CMCI is disabled. */
+static void cmci_mc_poll_banks(void)
+{
+ spin_lock(&cmci_poll_lock);
+ machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));
+ spin_unlock(&cmci_poll_lock);
+}
+
void intel_init_cmci(void)
{
int banks;
- if (!cmci_supported(&banks))
+ if (!cmci_supported(&banks)) {
+ mc_poll_banks = cmci_mc_poll_banks;
return;
+ }
mce_threshold_vector = intel_threshold_interrupt;
cmci_discover(banks);
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index d2412ce2d312..bcf1b3c66c9c 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;
@@ -274,4 +277,5 @@ static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg)
return 0;
}
+extern void (*mc_poll_banks)(void);
#endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index 6a059a035021..ef4e7bb5fd88 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -27,5 +27,5 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_threshold)
inc_irq_stat(irq_threshold_count);
mce_threshold_vector();
trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR);
- ack_APIC_irq();
+ apic_eoi();
}
diff --git a/arch/x86/kernel/cpu/microcode/Makefile b/arch/x86/kernel/cpu/microcode/Makefile
index 34098d48c48f..193d98b33a0a 100644
--- a/arch/x86/kernel/cpu/microcode/Makefile
+++ b/arch/x86/kernel/cpu/microcode/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
microcode-y := core.o
obj-$(CONFIG_MICROCODE) += microcode.o
-microcode-$(CONFIG_MICROCODE_INTEL) += intel.o
-microcode-$(CONFIG_MICROCODE_AMD) += amd.o
+microcode-$(CONFIG_CPU_SUP_INTEL) += intel.o
+microcode-$(CONFIG_CPU_SUP_AMD) += amd.o
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 87208e46f7ed..bbd1dc38ea03 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -29,13 +29,53 @@
#include <linux/kernel.h>
#include <linux/pci.h>
-#include <asm/microcode_amd.h>
#include <asm/microcode.h>
#include <asm/processor.h>
#include <asm/setup.h>
#include <asm/cpu.h>
#include <asm/msr.h>
+#include "internal.h"
+
+#define UCODE_MAGIC 0x00414d44
+#define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000
+#define UCODE_UCODE_TYPE 0x00000001
+
+#define SECTION_HDR_SIZE 8
+#define CONTAINER_HDR_SZ 12
+
+struct equiv_cpu_entry {
+ u32 installed_cpu;
+ u32 fixed_errata_mask;
+ u32 fixed_errata_compare;
+ u16 equiv_cpu;
+ u16 res;
+} __packed;
+
+struct microcode_header_amd {
+ u32 data_code;
+ u32 patch_id;
+ u16 mc_patch_data_id;
+ u8 mc_patch_data_len;
+ u8 init_flag;
+ u32 mc_patch_data_checksum;
+ u32 nb_dev_id;
+ u32 sb_dev_id;
+ u16 processor_rev_id;
+ u8 nb_rev_id;
+ u8 sb_rev_id;
+ u8 bios_api_rev;
+ u8 reserved1[3];
+ u32 match_reg[8];
+} __packed;
+
+struct microcode_amd {
+ struct microcode_header_amd hdr;
+ unsigned int mpb[];
+};
+
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
+
static struct equiv_cpu_table {
unsigned int num_entries;
struct equiv_cpu_entry *entry;
@@ -56,9 +96,6 @@ struct cont_desc {
static u32 ucode_new_rev;
-/* One blob per node. */
-static u8 amd_ucode_patch[MAX_NUMNODES][PATCH_MAX_SIZE];
-
/*
* Microcode patch container file is prepended to the initrd in cpio
* format. See Documentation/arch/x86/microcode.rst
@@ -415,20 +452,17 @@ static int __apply_microcode_amd(struct microcode_amd *mc)
*
* Returns true if container found (sets @desc), false otherwise.
*/
-static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch)
+static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
{
struct cont_desc desc = { 0 };
- u8 (*patch)[PATCH_MAX_SIZE];
struct microcode_amd *mc;
u32 rev, dummy, *new_rev;
bool ret = false;
#ifdef CONFIG_X86_32
new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
- patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch);
#else
new_rev = &ucode_new_rev;
- patch = &amd_ucode_patch[0];
#endif
desc.cpuid_1_eax = cpuid_1_eax;
@@ -452,9 +486,6 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size, boo
if (!__apply_microcode_amd(mc)) {
*new_rev = mc->hdr.patch_id;
ret = true;
-
- if (save_patch)
- memcpy(patch, mc, min_t(u32, desc.psize, PATCH_MAX_SIZE));
}
return ret;
@@ -507,7 +538,7 @@ static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data
*ret = cp;
}
-void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
+static void apply_ucode_from_containers(unsigned int cpuid_1_eax)
{
struct cpio_data cp = { };
@@ -515,42 +546,12 @@ void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
if (!(cp.data && cp.size))
return;
- early_apply_microcode(cpuid_1_eax, cp.data, cp.size, true);
+ early_apply_microcode(cpuid_1_eax, cp.data, cp.size);
}
-void load_ucode_amd_ap(unsigned int cpuid_1_eax)
+void load_ucode_amd_early(unsigned int cpuid_1_eax)
{
- struct microcode_amd *mc;
- struct cpio_data cp;
- u32 *new_rev, rev, dummy;
-
- if (IS_ENABLED(CONFIG_X86_32)) {
- mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
- new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
- } else {
- mc = (struct microcode_amd *)amd_ucode_patch;
- new_rev = &ucode_new_rev;
- }
-
- native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
- /*
- * Check whether a new patch has been saved already. Also, allow application of
- * the same revision in order to pick up SMT-thread-specific configuration even
- * if the sibling SMT thread already has an up-to-date revision.
- */
- if (*new_rev && rev <= mc->hdr.patch_id) {
- if (!__apply_microcode_amd(mc)) {
- *new_rev = mc->hdr.patch_id;
- return;
- }
- }
-
- find_blobs_in_containers(cpuid_1_eax, &cp);
- if (!(cp.data && cp.size))
- return;
-
- early_apply_microcode(cpuid_1_eax, cp.data, cp.size, false);
+ return apply_ucode_from_containers(cpuid_1_eax);
}
static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
@@ -578,23 +579,6 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
return 0;
}
-void reload_ucode_amd(unsigned int cpu)
-{
- u32 rev, dummy __always_unused;
- struct microcode_amd *mc;
-
- mc = (struct microcode_amd *)amd_ucode_patch[cpu_to_node(cpu)];
-
- rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
- if (rev < mc->hdr.patch_id) {
- if (!__apply_microcode_amd(mc)) {
- ucode_new_rev = mc->hdr.patch_id;
- pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
- }
- }
-}
-
/*
* a small, trivial cache of per-family ucode patches
*/
@@ -655,6 +639,28 @@ static struct ucode_patch *find_patch(unsigned int cpu)
return cache_find_patch(equiv_id);
}
+void reload_ucode_amd(unsigned int cpu)
+{
+ u32 rev, dummy __always_unused;
+ struct microcode_amd *mc;
+ struct ucode_patch *p;
+
+ p = find_patch(cpu);
+ if (!p)
+ return;
+
+ mc = p->data;
+
+ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
+ if (rev < mc->hdr.patch_id) {
+ if (!__apply_microcode_amd(mc)) {
+ ucode_new_rev = mc->hdr.patch_id;
+ pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
+ }
+ }
+}
+
static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -875,9 +881,6 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
continue;
ret = UCODE_NEW;
-
- memset(&amd_ucode_patch[nid], 0, PATCH_MAX_SIZE);
- memcpy(&amd_ucode_patch[nid], p->data, min_t(u32, p->size, PATCH_MAX_SIZE));
}
return ret;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 3afcf3de0dd4..6cc7a2c181da 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -31,15 +31,14 @@
#include <linux/fs.h>
#include <linux/mm.h>
-#include <asm/microcode_intel.h>
#include <asm/cpu_device_id.h>
-#include <asm/microcode_amd.h>
#include <asm/perf_event.h>
-#include <asm/microcode.h>
#include <asm/processor.h>
#include <asm/cmdline.h>
#include <asm/setup.h>
+#include "internal.h"
+
#define DRIVER_VERSION "2.2"
static struct microcode_ops *microcode_ops;
@@ -54,15 +53,12 @@ LIST_HEAD(microcode_cache);
*
* All non cpu-hotplug-callback call sites use:
*
- * - microcode_mutex to synchronize with each other;
* - cpus_read_lock/unlock() to synchronize with
* the cpu-hotplug-callback call sites.
*
* We guarantee that only a single cpu is being
* updated at any particular moment of time.
*/
-static DEFINE_MUTEX(microcode_mutex);
-
struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
struct cpu_info_ctx {
@@ -172,7 +168,7 @@ void __init load_ucode_bsp(void)
if (intel)
load_ucode_intel_bsp();
else
- load_ucode_amd_bsp(cpuid_1_eax);
+ load_ucode_amd_early(cpuid_1_eax);
}
static bool check_loader_disabled_ap(void)
@@ -200,7 +196,7 @@ void load_ucode_ap(void)
break;
case X86_VENDOR_AMD:
if (x86_family(cpuid_1_eax) >= 0x10)
- load_ucode_amd_ap(cpuid_1_eax);
+ load_ucode_amd_early(cpuid_1_eax);
break;
default:
break;
@@ -298,7 +294,7 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
#endif
}
-void reload_early_microcode(unsigned int cpu)
+static void reload_early_microcode(unsigned int cpu)
{
int vendor, family;
@@ -488,10 +484,7 @@ static ssize_t reload_store(struct device *dev,
if (tmp_ret != UCODE_NEW)
goto put;
- mutex_lock(&microcode_mutex);
ret = microcode_reload_late();
- mutex_unlock(&microcode_mutex);
-
put:
cpus_read_unlock();
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 467cf37ea90a..94dd6af9c963 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -10,15 +10,7 @@
* Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
* H Peter Anvin" <hpa@zytor.com>
*/
-
-/*
- * This needs to be before all headers so that pr_debug in printk.h doesn't turn
- * printk calls into no_printk().
- *
- *#define DEBUG
- */
#define pr_fmt(fmt) "microcode: " fmt
-
#include <linux/earlycpio.h>
#include <linux/firmware.h>
#include <linux/uaccess.h>
@@ -30,13 +22,14 @@
#include <linux/uio.h>
#include <linux/mm.h>
-#include <asm/microcode_intel.h>
#include <asm/intel-family.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/setup.h>
#include <asm/msr.h>
+#include "internal.h"
+
static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
/* Current microcode patch used in early patching on the APs. */
@@ -45,6 +38,208 @@ static struct microcode_intel *intel_ucode_patch;
/* last level cache size per core */
static int llc_size_per_core;
+/* microcode format is extended from prescott processors */
+struct extended_signature {
+ unsigned int sig;
+ unsigned int pf;
+ unsigned int cksum;
+};
+
+struct extended_sigtable {
+ unsigned int count;
+ unsigned int cksum;
+ unsigned int reserved[3];
+ struct extended_signature sigs[];
+};
+
+#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE)
+#define EXT_HEADER_SIZE (sizeof(struct extended_sigtable))
+#define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature))
+
+static inline unsigned int get_totalsize(struct microcode_header_intel *hdr)
+{
+ return hdr->datasize ? hdr->totalsize : DEFAULT_UCODE_TOTALSIZE;
+}
+
+static inline unsigned int exttable_size(struct extended_sigtable *et)
+{
+ return et->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE;
+}
+
+int intel_cpu_collect_info(struct ucode_cpu_info *uci)
+{
+ unsigned int val[2];
+ unsigned int family, model;
+ struct cpu_signature csig = { 0 };
+ unsigned int eax, ebx, ecx, edx;
+
+ memset(uci, 0, sizeof(*uci));
+
+ eax = 0x00000001;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ csig.sig = eax;
+
+ family = x86_family(eax);
+ model = x86_model(eax);
+
+ if (model >= 5 || family > 6) {
+ /* get processor flags from MSR 0x17 */
+ native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
+ csig.pf = 1 << ((val[1] >> 18) & 7);
+ }
+
+ csig.rev = intel_get_microcode_revision();
+
+ uci->cpu_sig = csig;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(intel_cpu_collect_info);
+
+/*
+ * Returns 1 if update has been found, 0 otherwise.
+ */
+int intel_find_matching_signature(void *mc, unsigned int csig, int cpf)
+{
+ struct microcode_header_intel *mc_hdr = mc;
+ struct extended_sigtable *ext_hdr;
+ struct extended_signature *ext_sig;
+ int i;
+
+ if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
+ return 1;
+
+ /* Look for ext. headers: */
+ if (get_totalsize(mc_hdr) <= intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE)
+ return 0;
+
+ ext_hdr = mc + intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE;
+ ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
+
+ for (i = 0; i < ext_hdr->count; i++) {
+ if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
+ return 1;
+ ext_sig++;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(intel_find_matching_signature);
+
+/**
+ * intel_microcode_sanity_check() - Sanity check microcode file.
+ * @mc: Pointer to the microcode file contents.
+ * @print_err: Display failure reason if true, silent if false.
+ * @hdr_type: Type of file, i.e. normal microcode file or In Field Scan file.
+ * Validate if the microcode header type matches with the type
+ * specified here.
+ *
+ * Validate certain header fields and verify if computed checksum matches
+ * with the one specified in the header.
+ *
+ * Return: 0 if the file passes all the checks, -EINVAL if any of the checks
+ * fail.
+ */
+int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type)
+{
+ unsigned long total_size, data_size, ext_table_size;
+ struct microcode_header_intel *mc_header = mc;
+ struct extended_sigtable *ext_header = NULL;
+ u32 sum, orig_sum, ext_sigcount = 0, i;
+ struct extended_signature *ext_sig;
+
+ total_size = get_totalsize(mc_header);
+ data_size = intel_microcode_get_datasize(mc_header);
+
+ if (data_size + MC_HEADER_SIZE > total_size) {
+ if (print_err)
+ pr_err("Error: bad microcode data file size.\n");
+ return -EINVAL;
+ }
+
+ if (mc_header->ldrver != 1 || mc_header->hdrver != hdr_type) {
+ if (print_err)
+ pr_err("Error: invalid/unknown microcode update format. Header type %d\n",
+ mc_header->hdrver);
+ return -EINVAL;
+ }
+
+ ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
+ if (ext_table_size) {
+ u32 ext_table_sum = 0;
+ u32 *ext_tablep;
+
+ if (ext_table_size < EXT_HEADER_SIZE ||
+ ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
+ if (print_err)
+ pr_err("Error: truncated extended signature table.\n");
+ return -EINVAL;
+ }
+
+ ext_header = mc + MC_HEADER_SIZE + data_size;
+ if (ext_table_size != exttable_size(ext_header)) {
+ if (print_err)
+ pr_err("Error: extended signature table size mismatch.\n");
+ return -EFAULT;
+ }
+
+ ext_sigcount = ext_header->count;
+
+ /*
+ * Check extended table checksum: the sum of all dwords that
+ * comprise a valid table must be 0.
+ */
+ ext_tablep = (u32 *)ext_header;
+
+ i = ext_table_size / sizeof(u32);
+ while (i--)
+ ext_table_sum += ext_tablep[i];
+
+ if (ext_table_sum) {
+ if (print_err)
+ pr_warn("Bad extended signature table checksum, aborting.\n");
+ return -EINVAL;
+ }
+ }
+
+ /*
+ * Calculate the checksum of update data and header. The checksum of
+ * valid update data and header including the extended signature table
+ * must be 0.
+ */
+ orig_sum = 0;
+ i = (MC_HEADER_SIZE + data_size) / sizeof(u32);
+ while (i--)
+ orig_sum += ((u32 *)mc)[i];
+
+ if (orig_sum) {
+ if (print_err)
+ pr_err("Bad microcode data checksum, aborting.\n");
+ return -EINVAL;
+ }
+
+ if (!ext_table_size)
+ return 0;
+
+ /*
+ * Check extended signature checksum: 0 => valid.
+ */
+ for (i = 0; i < ext_sigcount; i++) {
+ ext_sig = (void *)ext_header + EXT_HEADER_SIZE +
+ EXT_SIGNATURE_SIZE * i;
+
+ sum = (mc_header->sig + mc_header->pf + mc_header->cksum) -
+ (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
+ if (sum) {
+ if (print_err)
+ pr_err("Bad extended signature checksum, aborting.\n");
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(intel_microcode_sanity_check);
+
/*
* Returns 1 if update has been found, 0 otherwise.
*/
@@ -202,86 +397,6 @@ next:
return patch;
}
-static void show_saved_mc(void)
-{
-#ifdef DEBUG
- int i = 0, j;
- unsigned int sig, pf, rev, total_size, data_size, date;
- struct ucode_cpu_info uci;
- struct ucode_patch *p;
-
- if (list_empty(&microcode_cache)) {
- pr_debug("no microcode data saved.\n");
- return;
- }
-
- intel_cpu_collect_info(&uci);
-
- sig = uci.cpu_sig.sig;
- pf = uci.cpu_sig.pf;
- rev = uci.cpu_sig.rev;
- pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev);
-
- list_for_each_entry(p, &microcode_cache, plist) {
- struct microcode_header_intel *mc_saved_header;
- struct extended_sigtable *ext_header;
- struct extended_signature *ext_sig;
- int ext_sigcount;
-
- mc_saved_header = (struct microcode_header_intel *)p->data;
-
- sig = mc_saved_header->sig;
- pf = mc_saved_header->pf;
- rev = mc_saved_header->rev;
- date = mc_saved_header->date;
-
- total_size = get_totalsize(mc_saved_header);
- data_size = get_datasize(mc_saved_header);
-
- pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, total size=0x%x, date = %04x-%02x-%02x\n",
- i++, sig, pf, rev, total_size,
- date & 0xffff,
- date >> 24,
- (date >> 16) & 0xff);
-
- /* Look for ext. headers: */
- if (total_size <= data_size + MC_HEADER_SIZE)
- continue;
-
- ext_header = (void *)mc_saved_header + data_size + MC_HEADER_SIZE;
- ext_sigcount = ext_header->count;
- ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
-
- for (j = 0; j < ext_sigcount; j++) {
- sig = ext_sig->sig;
- pf = ext_sig->pf;
-
- pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n",
- j, sig, pf);
-
- ext_sig++;
- }
- }
-#endif
-}
-
-/*
- * Save this microcode patch. It will be loaded early when a CPU is
- * hot-added or resumes.
- */
-static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size)
-{
- /* Synchronization during CPU hotplug. */
- static DEFINE_MUTEX(x86_cpu_microcode_mutex);
-
- mutex_lock(&x86_cpu_microcode_mutex);
-
- save_microcode_patch(uci, mc, size);
- show_saved_mc();
-
- mutex_unlock(&x86_cpu_microcode_mutex);
-}
-
static bool load_builtin_intel_microcode(struct cpio_data *cp)
{
unsigned int eax = 1, ebx, ecx = 0, edx;
@@ -428,9 +543,6 @@ int __init save_microcode_in_initrd_intel(void)
intel_cpu_collect_info(&uci);
scan_microcode(cp.data, cp.size, &uci, true);
-
- show_saved_mc();
-
return 0;
}
@@ -701,12 +813,8 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
vfree(uci->mc);
uci->mc = (struct microcode_intel *)new_mc;
- /*
- * If early loading microcode is supported, save this mc into
- * permanent memory. So it will be loaded early when a CPU is hot added
- * or resumes.
- */
- save_mc_for_early(uci, new_mc, new_mc_size);
+ /* Save for CPU hotplug */
+ save_microcode_patch(uci, new_mc, new_mc_size);
pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
new file mode 100644
index 000000000000..bf883aa71233
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_MICROCODE_INTERNAL_H
+#define _X86_MICROCODE_INTERNAL_H
+
+#include <linux/earlycpio.h>
+#include <linux/initrd.h>
+
+#include <asm/cpu.h>
+#include <asm/microcode.h>
+
+struct ucode_patch {
+ struct list_head plist;
+ void *data; /* Intel uses only this one */
+ unsigned int size;
+ u32 patch_id;
+ u16 equiv_cpu;
+};
+
+extern struct list_head microcode_cache;
+
+struct device;
+
+enum ucode_state {
+ UCODE_OK = 0,
+ UCODE_NEW,
+ UCODE_UPDATED,
+ UCODE_NFOUND,
+ UCODE_ERROR,
+};
+
+struct microcode_ops {
+ enum ucode_state (*request_microcode_fw)(int cpu, struct device *dev);
+
+ void (*microcode_fini_cpu)(int cpu);
+
+ /*
+ * The generic 'microcode_core' part guarantees that
+ * the callbacks below run on a target cpu when they
+ * are being called.
+ * See also the "Synchronization" section in microcode_core.c.
+ */
+ enum ucode_state (*apply_microcode)(int cpu);
+ int (*collect_cpu_info)(int cpu, struct cpu_signature *csig);
+};
+
+extern struct ucode_cpu_info ucode_cpu_info[];
+struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa);
+
+#define MAX_UCODE_COUNT 128
+
+#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24))
+#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u')
+#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I')
+#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l')
+#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h')
+#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i')
+#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D')
+
+#define CPUID_IS(a, b, c, ebx, ecx, edx) \
+ (!(((ebx) ^ (a)) | ((edx) ^ (b)) | ((ecx) ^ (c))))
+
+/*
+ * In early loading microcode phase on BSP, boot_cpu_data is not set up yet.
+ * x86_cpuid_vendor() gets vendor id for BSP.
+ *
+ * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify
+ * coding, we still use x86_cpuid_vendor() to get vendor id for AP.
+ *
+ * x86_cpuid_vendor() gets vendor information directly from CPUID.
+ */
+static inline int x86_cpuid_vendor(void)
+{
+ u32 eax = 0x00000000;
+ u32 ebx, ecx = 0, edx;
+
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+
+ if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx))
+ return X86_VENDOR_INTEL;
+
+ if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx))
+ return X86_VENDOR_AMD;
+
+ return X86_VENDOR_UNKNOWN;
+}
+
+static inline unsigned int x86_cpuid_family(void)
+{
+ u32 eax = 0x00000001;
+ u32 ebx, ecx = 0, edx;
+
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+
+ return x86_family(eax);
+}
+
+extern bool initrd_gone;
+
+#ifdef CONFIG_CPU_SUP_AMD
+void load_ucode_amd_bsp(unsigned int family);
+void load_ucode_amd_ap(unsigned int family);
+void load_ucode_amd_early(unsigned int cpuid_1_eax);
+int save_microcode_in_initrd_amd(unsigned int family);
+void reload_ucode_amd(unsigned int cpu);
+struct microcode_ops *init_amd_microcode(void);
+void exit_amd_microcode(void);
+#else /* CONFIG_CPU_SUP_AMD */
+static inline void load_ucode_amd_bsp(unsigned int family) { }
+static inline void load_ucode_amd_ap(unsigned int family) { }
+static inline void load_ucode_amd_early(unsigned int family) { }
+static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
+static inline void reload_ucode_amd(unsigned int cpu) { }
+static inline struct microcode_ops *init_amd_microcode(void) { return NULL; }
+static inline void exit_amd_microcode(void) { }
+#endif /* !CONFIG_CPU_SUP_AMD */
+
+#ifdef CONFIG_CPU_SUP_INTEL
+void load_ucode_intel_bsp(void);
+void load_ucode_intel_ap(void);
+int save_microcode_in_initrd_intel(void);
+void reload_ucode_intel(void);
+struct microcode_ops *init_intel_microcode(void);
+#else /* CONFIG_CPU_SUP_INTEL */
+static inline void load_ucode_intel_bsp(void) { }
+static inline void load_ucode_intel_ap(void) { }
+static inline int save_microcode_in_initrd_intel(void) { return -EINVAL; }
+static inline void reload_ucode_intel(void) { }
+static inline struct microcode_ops *init_intel_microcode(void) { return NULL; }
+#endif /* !CONFIG_CPU_SUP_INTEL */
+
+#endif /* _X86_MICROCODE_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index c7969e806c64..0100468e72ca 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -119,7 +119,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
vmbus_handler();
if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
- ack_APIC_irq();
+ apic_eoi();
set_irq_regs(old_regs);
}
@@ -147,7 +147,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_stimer0)
if (hv_stimer0_handler)
hv_stimer0_handler();
add_interrupt_randomness(HYPERV_STIMER0_VECTOR);
- ack_APIC_irq();
+ apic_eoi();
set_irq_regs(old_regs);
}
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 099b6f0d96bd..31c0e68f6227 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -4,6 +4,8 @@
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/cpufreq.h>
+#include <asm/prctl.h>
+#include <linux/proc_fs.h>
#include "cpu.h"
@@ -175,3 +177,24 @@ const struct seq_operations cpuinfo_op = {
.stop = c_stop,
.show = show_cpuinfo,
};
+
+#ifdef CONFIG_X86_USER_SHADOW_STACK
+static void dump_x86_features(struct seq_file *m, unsigned long features)
+{
+ if (features & ARCH_SHSTK_SHSTK)
+ seq_puts(m, "shstk ");
+ if (features & ARCH_SHSTK_WRSS)
+ seq_puts(m, "wrss ");
+}
+
+void arch_proc_pid_thread_features(struct seq_file *m, struct task_struct *task)
+{
+ seq_puts(m, "x86_Thread_features:\t");
+ dump_x86_features(m, task->thread.features);
+ seq_putc(m, '\n');
+
+ seq_puts(m, "x86_Thread_features_locked:\t");
+ dump_x86_features(m, task->thread.features_locked);
+ seq_putc(m, '\n');
+}
+#endif /* CONFIG_X86_USER_SHADOW_STACK */