aboutsummaryrefslogtreecommitdiffstats
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/amd.c288
-rw-r--r--arch/x86/kernel/cpu/bugs.c15
-rw-r--r--arch/x86/kernel/cpu/common.c63
-rw-r--r--arch/x86/kernel/cpu/hygon.c3
-rw-r--r--arch/x86/kernel/cpu/intel.c178
-rw-r--r--arch/x86/kernel/cpu/intel_epb.c2
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c80
-rw-r--r--arch/x86/kernel/cpu/mce/core.c87
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c1
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c304
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h66
-rw-r--r--arch/x86/kernel/cpu/mce/threshold.c115
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c20
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c14
-rw-r--r--arch/x86/kernel/cpu/sgx/ioctl.c2
15 files changed, 705 insertions, 533 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f322ebd053a9..f3abca334199 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -34,87 +34,6 @@
*/
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 const int amd_erratum_1485[] =
- AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf),
- AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 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 };
@@ -616,6 +535,62 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
}
resctrl_cpu_detect(c);
+
+ /* Figure out Zen generations: */
+ switch (c->x86) {
+ case 0x17:
+ switch (c->x86_model) {
+ case 0x00 ... 0x2f:
+ case 0x50 ... 0x5f:
+ setup_force_cpu_cap(X86_FEATURE_ZEN1);
+ break;
+ case 0x30 ... 0x4f:
+ case 0x60 ... 0x7f:
+ case 0x90 ... 0x91:
+ case 0xa0 ... 0xaf:
+ setup_force_cpu_cap(X86_FEATURE_ZEN2);
+ break;
+ default:
+ goto warn;
+ }
+ break;
+
+ case 0x19:
+ switch (c->x86_model) {
+ case 0x00 ... 0x0f:
+ case 0x20 ... 0x5f:
+ setup_force_cpu_cap(X86_FEATURE_ZEN3);
+ break;
+ case 0x10 ... 0x1f:
+ case 0x60 ... 0xaf:
+ setup_force_cpu_cap(X86_FEATURE_ZEN4);
+ break;
+ default:
+ goto warn;
+ }
+ break;
+
+ case 0x1a:
+ switch (c->x86_model) {
+ case 0x00 ... 0x0f:
+ case 0x20 ... 0x2f:
+ case 0x40 ... 0x4f:
+ case 0x70 ... 0x7f:
+ setup_force_cpu_cap(X86_FEATURE_ZEN5);
+ break;
+ default:
+ goto warn;
+ }
+ break;
+
+ default:
+ break;
+ }
+
+ return;
+
+warn:
+ WARN_ONCE(1, "Family 0x%x, model: 0x%x??\n", c->x86, c->x86_model);
}
static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -739,15 +714,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (c->x86 == 0x16 && c->x86_model <= 0xf)
msr_set_bit(MSR_AMD64_LS_CFG, 15);
- /*
- * Check whether the machine is affected by erratum 400. This is
- * used to select the proper idle routine and to enable the check
- * whether the machine is affected in arch_post_acpi_init(), which
- * sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
- */
- if (cpu_has_amd_erratum(c, amd_erratum_400))
- set_cpu_bug(c, X86_BUG_AMD_E400);
-
early_detect_mem_encrypt(c);
/* Re-enable TopologyExtensions if switched off by BIOS */
@@ -814,6 +780,16 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
msr_set_bit(MSR_K7_HWCR, 6);
#endif
set_cpu_bug(c, X86_BUG_SWAPGS_FENCE);
+
+ /*
+ * Check models and steppings affected by erratum 400. This is
+ * used to select the proper idle routine and to enable the
+ * check whether the machine is affected in arch_post_acpi_subsys_init()
+ * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+ */
+ if (c->x86_model > 0x41 ||
+ (c->x86_model == 0x41 && c->x86_stepping >= 0x2))
+ setup_force_cpu_bug(X86_BUG_AMD_E400);
}
static void init_amd_gh(struct cpuinfo_x86 *c)
@@ -847,8 +823,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
*/
msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
- if (cpu_has_amd_erratum(c, amd_erratum_383))
- set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+ set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+
+ /*
+ * Check models and steppings affected by erratum 400. This is
+ * used to select the proper idle routine and to enable the
+ * check whether the machine is affected in arch_post_acpi_subsys_init()
+ * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+ */
+ if (c->x86_model > 0x2 ||
+ (c->x86_model == 0x2 && c->x86_stepping >= 0x1))
+ setup_force_cpu_bug(X86_BUG_AMD_E400);
}
static void init_amd_ln(struct cpuinfo_x86 *c)
@@ -941,6 +926,19 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
clear_rdrand_cpuid_bit(c);
}
+static void fix_erratum_1386(struct cpuinfo_x86 *c)
+{
+ /*
+ * Work around Erratum 1386. The XSAVES instruction malfunctions in
+ * certain circumstances on Zen1/2 uarch, and not all parts have had
+ * updated microcode at the time of writing (March 2023).
+ *
+ * Affected parts all have no supervisor XSAVE states, meaning that
+ * the XSAVEC instruction (which works fine) is equivalent.
+ */
+ clear_cpu_cap(c, X86_FEATURE_XSAVES);
+}
+
void init_spectral_chicken(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_CPU_UNRET_ENTRY
@@ -951,34 +949,28 @@ void init_spectral_chicken(struct cpuinfo_x86 *c)
*
* This suppresses speculation from the middle of a basic block, i.e. it
* suppresses non-branch predictions.
- *
- * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H
*/
- if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
}
}
#endif
- /*
- * Work around Erratum 1386. The XSAVES instruction malfunctions in
- * certain circumstances on Zen1/2 uarch, and not all parts have had
- * updated microcode at the time of writing (March 2023).
- *
- * Affected parts all have no supervisor XSAVE states, meaning that
- * the XSAVEC instruction (which works fine) is equivalent.
- */
- clear_cpu_cap(c, X86_FEATURE_XSAVES);
}
-static void init_amd_zn(struct cpuinfo_x86 *c)
+static void init_amd_zen_common(void)
{
- set_cpu_cap(c, X86_FEATURE_ZEN);
-
+ setup_force_cpu_cap(X86_FEATURE_ZEN);
#ifdef CONFIG_NUMA
node_reclaim_distance = 32;
#endif
+}
+
+static void init_amd_zen1(struct cpuinfo_x86 *c)
+{
+ init_amd_zen_common();
+ fix_erratum_1386(c);
/* Fix up CPUID bits, but only if not virtualised. */
if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
@@ -986,15 +978,10 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
/* Erratum 1076: CPB feature bit not being set in CPUID. */
if (!cpu_has(c, X86_FEATURE_CPB))
set_cpu_cap(c, X86_FEATURE_CPB);
-
- /*
- * Zen3 (Fam19 model < 0x10) parts are not susceptible to
- * Branch Type Confusion, but predate the allocation of the
- * BTC_NO bit.
- */
- if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO))
- set_cpu_cap(c, X86_FEATURE_BTC_NO);
}
+
+ pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
+ setup_force_cpu_bug(X86_BUG_DIV0);
}
static bool cpu_has_zenbleed_microcode(void)
@@ -1018,11 +1005,8 @@ static bool cpu_has_zenbleed_microcode(void)
return true;
}
-static void zenbleed_check(struct cpuinfo_x86 *c)
+static void zen2_zenbleed_check(struct cpuinfo_x86 *c)
{
- if (!cpu_has_amd_erratum(c, amd_zenbleed))
- return;
-
if (cpu_has(c, X86_FEATURE_HYPERVISOR))
return;
@@ -1037,6 +1021,42 @@ static void zenbleed_check(struct cpuinfo_x86 *c)
}
}
+static void init_amd_zen2(struct cpuinfo_x86 *c)
+{
+ init_amd_zen_common();
+ init_spectral_chicken(c);
+ fix_erratum_1386(c);
+ zen2_zenbleed_check(c);
+}
+
+static void init_amd_zen3(struct cpuinfo_x86 *c)
+{
+ init_amd_zen_common();
+
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
+ /*
+ * Zen3 (Fam19 model < 0x10) parts are not susceptible to
+ * Branch Type Confusion, but predate the allocation of the
+ * BTC_NO bit.
+ */
+ if (!cpu_has(c, X86_FEATURE_BTC_NO))
+ set_cpu_cap(c, X86_FEATURE_BTC_NO);
+ }
+}
+
+static void init_amd_zen4(struct cpuinfo_x86 *c)
+{
+ init_amd_zen_common();
+
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR))
+ msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+}
+
+static void init_amd_zen5(struct cpuinfo_x86 *c)
+{
+ init_amd_zen_common();
+}
+
static void init_amd(struct cpuinfo_x86 *c)
{
u64 vm_cr;
@@ -1072,11 +1092,19 @@ static void init_amd(struct cpuinfo_x86 *c)
case 0x12: init_amd_ln(c); break;
case 0x15: init_amd_bd(c); break;
case 0x16: init_amd_jg(c); break;
- case 0x17: init_spectral_chicken(c);
- fallthrough;
- case 0x19: init_amd_zn(c); break;
}
+ if (boot_cpu_has(X86_FEATURE_ZEN1))
+ init_amd_zen1(c);
+ else if (boot_cpu_has(X86_FEATURE_ZEN2))
+ init_amd_zen2(c);
+ else if (boot_cpu_has(X86_FEATURE_ZEN3))
+ init_amd_zen3(c);
+ else if (boot_cpu_has(X86_FEATURE_ZEN4))
+ init_amd_zen4(c);
+ else if (boot_cpu_has(X86_FEATURE_ZEN5))
+ init_amd_zen5(c);
+
/*
* Enable workaround for FXSAVE leak on CPUs
* without a XSaveErPtr feature
@@ -1136,7 +1164,7 @@ static void init_amd(struct cpuinfo_x86 *c)
* Counter May Be Inaccurate".
*/
if (cpu_has(c, X86_FEATURE_IRPERF) &&
- !cpu_has_amd_erratum(c, amd_erratum_1054))
+ (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f))
msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
check_null_seg_clears_base(c);
@@ -1152,16 +1180,8 @@ static void init_amd(struct cpuinfo_x86 *c)
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);
- }
-
- if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
- cpu_has_amd_erratum(c, amd_erratum_1485))
- msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+ /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
}
#ifdef CONFIG_X86_32
@@ -1315,7 +1335,7 @@ static void zenbleed_check_cpu(void *unused)
{
struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
- zenbleed_check(c);
+ zen2_zenbleed_check(c);
}
void amd_check_microcode(void)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bb0ab8466b91..48d049cd74e7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -111,9 +111,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
/* Control unconditional IBPB in switch_mm() */
DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
-/* Control MDS CPU buffer clear before returning to user space */
-DEFINE_STATIC_KEY_FALSE(mds_user_clear);
-EXPORT_SYMBOL_GPL(mds_user_clear);
/* Control MDS CPU buffer clear before idling (halt, mwait) */
DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
EXPORT_SYMBOL_GPL(mds_idle_clear);
@@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void)
if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
mds_mitigation = MDS_MITIGATION_VMWERV;
- static_branch_enable(&mds_user_clear);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
(mds_nosmt || cpu_mitigations_auto_nosmt()))
@@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void)
* For guests that can't determine whether the correct microcode is
* present on host, enable the mitigation for UCODE_NEEDED as well.
*/
- static_branch_enable(&mds_user_clear);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
if (taa_nosmt || cpu_mitigations_auto_nosmt())
cpu_smt_disable(false);
@@ -424,7 +421,7 @@ static void __init mmio_select_mitigation(void)
*/
if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
boot_cpu_has(X86_FEATURE_RTM)))
- static_branch_enable(&mds_user_clear);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
else
static_branch_enable(&mmio_stale_data_clear);
@@ -484,12 +481,12 @@ static void __init md_clear_update_mitigation(void)
if (cpu_mitigations_off())
return;
- if (!static_key_enabled(&mds_user_clear))
+ if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
goto out;
/*
- * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data
- * mitigation, if necessary.
+ * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO
+ * Stale Data mitigation, if necessary.
*/
if (mds_mitigation == MDS_MITIGATION_OFF &&
boot_cpu_has_bug(X86_BUG_MDS)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b14fc8c1c953..fbc4e60d027c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -66,6 +66,7 @@
#include <asm/set_memory.h>
#include <asm/traps.h>
#include <asm/sev.h>
+#include <asm/tdx.h>
#include "cpu.h"
@@ -188,45 +189,37 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
* TLS descriptors are currently at a different place compared to i386.
* Hopefully nobody expects them at a fixed place (Wine?)
*/
- [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
- [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
- [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER32_CS] = GDT_ENTRY_INIT(0xc0fb, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(0xc0f3, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(0xa0fb, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER32_CS] = GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(DESC_DATA64 | DESC_USER, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(DESC_CODE64 | DESC_USER, 0, 0xfffff),
#else
- [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xc09a, 0, 0xfffff),
- [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(0xc0fa, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(0xc0f2, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(DESC_DATA32 | DESC_USER, 0, 0xfffff),
/*
* Segments used for calling PnP BIOS have byte granularity.
* They code segments and data segments have fixed 64k limits,
* the transfer segment sizes are set at run time.
*/
- /* 32-bit code */
- [GDT_ENTRY_PNPBIOS_CS32] = GDT_ENTRY_INIT(0x409a, 0, 0xffff),
- /* 16-bit code */
- [GDT_ENTRY_PNPBIOS_CS16] = GDT_ENTRY_INIT(0x009a, 0, 0xffff),
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_DS] = GDT_ENTRY_INIT(0x0092, 0, 0xffff),
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_TS1] = GDT_ENTRY_INIT(0x0092, 0, 0),
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_TS2] = GDT_ENTRY_INIT(0x0092, 0, 0),
+ [GDT_ENTRY_PNPBIOS_CS32] = GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff),
+ [GDT_ENTRY_PNPBIOS_CS16] = GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff),
+ [GDT_ENTRY_PNPBIOS_DS] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0xffff),
+ [GDT_ENTRY_PNPBIOS_TS1] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0),
+ [GDT_ENTRY_PNPBIOS_TS2] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0),
/*
* The APM segments have byte granularity and their bases
* are set at run time. All have 64k limits.
*/
- /* 32-bit code */
- [GDT_ENTRY_APMBIOS_BASE] = GDT_ENTRY_INIT(0x409a, 0, 0xffff),
- /* 16-bit code */
- [GDT_ENTRY_APMBIOS_BASE+1] = GDT_ENTRY_INIT(0x009a, 0, 0xffff),
- /* data */
- [GDT_ENTRY_APMBIOS_BASE+2] = GDT_ENTRY_INIT(0x4092, 0, 0xffff),
-
- [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
- [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
+ [GDT_ENTRY_APMBIOS_BASE] = GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff),
+ [GDT_ENTRY_APMBIOS_BASE+1] = GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff),
+ [GDT_ENTRY_APMBIOS_BASE+2] = GDT_ENTRY_INIT(DESC_DATA32_BIOS, 0, 0xffff),
+
+ [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
+ [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
#endif
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
@@ -1596,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
get_cpu_vendor(c);
get_cpu_cap(c);
setup_force_cpu_cap(X86_FEATURE_CPUID);
+ get_cpu_address_sizes(c);
cpu_parse_early_param();
if (this_cpu->c_early_init)
@@ -1608,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
this_cpu->c_bsp_init(c);
} else {
setup_clear_cpu_cap(X86_FEATURE_CPUID);
+ get_cpu_address_sizes(c);
}
- get_cpu_address_sizes(c);
-
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
cpu_set_bug_bits(c);
@@ -1856,6 +1849,13 @@ static void identify_cpu(struct cpuinfo_x86 *c)
c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
#endif
+
+ /*
+ * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and
+ * Hygon will clear it in ->c_init() below.
+ */
+ set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
/*
* Vendor-specific initialization. In this section we
* canonicalize the feature flags, meaning if there are
@@ -1987,6 +1987,7 @@ static __init void identify_boot_cpu(void)
setup_cr_pinning();
tsx_init();
+ tdx_init();
lkgs_init();
}
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 6f247d66758d..f0cd95502faa 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -354,6 +354,9 @@ static void init_hygon(struct cpuinfo_x86 *c)
set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
check_null_seg_clears_base(c);
+
+ /* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
}
static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a927a8fc9624..40dec9b56f87 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
return false;
}
+#define MSR_IA32_TME_ACTIVATE 0x982
+
+/* Helpers to access TME_ACTIVATE MSR */
+#define TME_ACTIVATE_LOCKED(x) (x & 0x1)
+#define TME_ACTIVATE_ENABLED(x) (x & 0x2)
+
+#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */
+#define TME_ACTIVATE_POLICY_AES_XTS_128 0
+
+#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */
+
+#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */
+#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1
+
+/* Values for mktme_status (SW only construct) */
+#define MKTME_ENABLED 0
+#define MKTME_DISABLED 1
+#define MKTME_UNINITIALIZED 2
+static int mktme_status = MKTME_UNINITIALIZED;
+
+static void detect_tme_early(struct cpuinfo_x86 *c)
+{
+ u64 tme_activate, tme_policy, tme_crypto_algs;
+ int keyid_bits = 0, nr_keyids = 0;
+ static u64 tme_activate_cpu0 = 0;
+
+ rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+
+ if (mktme_status != MKTME_UNINITIALIZED) {
+ if (tme_activate != tme_activate_cpu0) {
+ /* Broken BIOS? */
+ pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
+ pr_err_once("x86/tme: MKTME is not usable\n");
+ mktme_status = MKTME_DISABLED;
+
+ /* Proceed. We may need to exclude bits from x86_phys_bits. */
+ }
+ } else {
+ tme_activate_cpu0 = tme_activate;
+ }
+
+ if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
+ pr_info_once("x86/tme: not enabled by BIOS\n");
+ mktme_status = MKTME_DISABLED;
+ return;
+ }
+
+ if (mktme_status != MKTME_UNINITIALIZED)
+ goto detect_keyid_bits;
+
+ pr_info("x86/tme: enabled by BIOS\n");
+
+ tme_policy = TME_ACTIVATE_POLICY(tme_activate);
+ if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
+ pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
+
+ tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
+ if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
+ pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
+ tme_crypto_algs);
+ mktme_status = MKTME_DISABLED;
+ }
+detect_keyid_bits:
+ keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
+ nr_keyids = (1UL << keyid_bits) - 1;
+ if (nr_keyids) {
+ pr_info_once("x86/mktme: enabled by BIOS\n");
+ pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
+ } else {
+ pr_info_once("x86/mktme: disabled by BIOS\n");
+ }
+
+ if (mktme_status == MKTME_UNINITIALIZED) {
+ /* MKTME is usable */
+ mktme_status = MKTME_ENABLED;
+ }
+
+ /*
+ * KeyID bits effectively lower the number of physical address
+ * bits. Update cpuinfo_x86::x86_phys_bits accordingly.
+ */
+ c->x86_phys_bits -= keyid_bits;
+}
+
static void early_init_intel(struct cpuinfo_x86 *c)
{
u64 misc_enable;
@@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
*/
if (detect_extended_topology_early(c) < 0)
detect_ht_early(c);
+
+ /*
+ * Adjust the number of physical bits early because it affects the
+ * valid bits of the MTRR mask registers.
+ */
+ if (cpu_has(c, X86_FEATURE_TME))
+ detect_tme_early(c);
}
static void bsp_init_intel(struct cpuinfo_x86 *c)
@@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#endif
}
-#define MSR_IA32_TME_ACTIVATE 0x982
-
-/* Helpers to access TME_ACTIVATE MSR */
-#define TME_ACTIVATE_LOCKED(x) (x & 0x1)
-#define TME_ACTIVATE_ENABLED(x) (x & 0x2)
-
-#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */
-#define TME_ACTIVATE_POLICY_AES_XTS_128 0
-
-#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */
-
-#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */
-#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1
-
-/* Values for mktme_status (SW only construct) */
-#define MKTME_ENABLED 0
-#define MKTME_DISABLED 1
-#define MKTME_UNINITIALIZED 2
-static int mktme_status = MKTME_UNINITIALIZED;
-
-static void detect_tme(struct cpuinfo_x86 *c)
-{
- u64 tme_activate, tme_policy, tme_crypto_algs;
- int keyid_bits = 0, nr_keyids = 0;
- static u64 tme_activate_cpu0 = 0;
-
- rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
-
- if (mktme_status != MKTME_UNINITIALIZED) {
- if (tme_activate != tme_activate_cpu0) {
- /* Broken BIOS? */
- pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
- pr_err_once("x86/tme: MKTME is not usable\n");
- mktme_status = MKTME_DISABLED;
-
- /* Proceed. We may need to exclude bits from x86_phys_bits. */
- }
- } else {
- tme_activate_cpu0 = tme_activate;
- }
-
- if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
- pr_info_once("x86/tme: not enabled by BIOS\n");
- mktme_status = MKTME_DISABLED;
- return;
- }
-
- if (mktme_status != MKTME_UNINITIALIZED)
- goto detect_keyid_bits;
-
- pr_info("x86/tme: enabled by BIOS\n");
-
- tme_policy = TME_ACTIVATE_POLICY(tme_activate);
- if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
- pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
-
- tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
- if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
- pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
- tme_crypto_algs);
- mktme_status = MKTME_DISABLED;
- }
-detect_keyid_bits:
- keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
- nr_keyids = (1UL << keyid_bits) - 1;
- if (nr_keyids) {
- pr_info_once("x86/mktme: enabled by BIOS\n");
- pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
- } else {
- pr_info_once("x86/mktme: disabled by BIOS\n");
- }
-
- if (mktme_status == MKTME_UNINITIALIZED) {
- /* MKTME is usable */
- mktme_status = MKTME_ENABLED;
- }
-
- /*
- * KeyID bits effectively lower the number of physical address
- * bits. Update cpuinfo_x86::x86_phys_bits accordingly.
- */
- c->x86_phys_bits -= keyid_bits;
-}
-
static void init_cpuid_fault(struct cpuinfo_x86 *c)
{
u64 msr;
@@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c)
init_ia32_feat_ctl(c);
- if (cpu_has(c, X86_FEATURE_TME))
- detect_tme(c);
-
init_intel_misc_features(c);
split_lock_init();
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index e4c3ba91321c..f18d35fe27a9 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -237,4 +237,4 @@ err_out_online:
cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE);
return ret;
}
-subsys_initcall(intel_epb_init);
+late_initcall(intel_epb_init);
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index f3517b8a8e91..2b46eb0fdf3a 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -87,42 +87,40 @@ struct smca_bank {
static DEFINE_PER_CPU_READ_MOSTLY(struct smca_bank[MAX_NR_BANKS], smca_banks);
static DEFINE_PER_CPU_READ_MOSTLY(u8[N_SMCA_BANK_TYPES], smca_bank_counts);
-struct smca_bank_name {
- const char *name; /* Short name for sysfs */
- const char *long_name; /* Long name for pretty-printing */
-};
-
-static struct smca_bank_name smca_names[] = {
- [SMCA_LS ... SMCA_LS_V2] = { "load_store", "Load Store Unit" },
- [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" },
- [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" },
- [SMCA_DE] = { "decode_unit", "Decode Unit" },
- [SMCA_RESERVED] = { "reserved", "Reserved" },
- [SMCA_EX] = { "execution_unit", "Execution Unit" },
- [SMCA_FP] = { "floating_point", "Floating Point Unit" },
- [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" },
- [SMCA_CS ... SMCA_CS_V2] = { "coherent_slave", "Coherent Slave" },
- [SMCA_PIE] = { "pie", "Power, Interrupts, etc." },
+static const char * const smca_names[] = {
+ [SMCA_LS ... SMCA_LS_V2] = "load_store",
+ [SMCA_IF] = "insn_fetch",
+ [SMCA_L2_CACHE] = "l2_cache",
+ [SMCA_DE] = "decode_unit",
+ [SMCA_RESERVED] = "reserved",
+ [SMCA_EX] = "execution_unit",
+ [SMCA_FP] = "floating_point",
+ [SMCA_L3_CACHE] = "l3_cache",
+ [SMCA_CS ... SMCA_CS_V2] = "coherent_slave",
+ [SMCA_PIE] = "pie",
/* UMC v2 is separate because both of them can exist in a single system. */
- [SMCA_UMC] = { "umc", "Unified Memory Controller" },
- [SMCA_UMC_V2] = { "umc_v2", "Unified Memory Controller v2" },
- [SMCA_PB] = { "param_block", "Parameter Block" },
- [SMCA_PSP ... SMCA_PSP_V2] = { "psp", "Platform Security Processor" },
- [SMCA_SMU ... SMCA_SMU_V2] = { "smu", "System Management Unit" },
- [SMCA_MP5] = { "mp5", "Microprocessor 5 Unit" },
- [SMCA_MPDMA] = { "mpdma", "MPDMA Unit" },
- [SMCA_NBIO] = { "nbio", "Northbridge IO Unit" },
- [SMCA_PCIE ... SMCA_PCIE_V2] = { "pcie", "PCI Express Unit" },
- [SMCA_XGMI_PCS] = { "xgmi_pcs", "Ext Global Memory Interconnect PCS Unit" },
- [SMCA_NBIF] = { "nbif", "NBIF Unit" },
- [SMCA_SHUB] = { "shub", "System Hub Unit" },
- [SMCA_SATA] = { "sata", "SATA Unit" },
- [SMCA_USB] = { "usb", "USB Unit" },
- [SMCA_GMI_PCS] = { "gmi_pcs", "Global Memory Interconnect PCS Unit" },
- [SMCA_XGMI_PHY] = { "xgmi_phy", "Ext Global Memory Interconnect PHY Unit" },
- [SMCA_WAFL_PHY] = { "wafl_phy", "WAFL PHY Unit" },
- [SMCA_GMI_PHY] = { "gmi_phy", "Global Memory Interconnect PHY Unit" },
+ [SMCA_UMC] = "umc",
+ [SMCA_UMC_V2] = "umc_v2",
+ [SMCA_MA_LLC] = "ma_llc",
+ [SMCA_PB] = "param_block",
+ [SMCA_PSP ... SMCA_PSP_V2] = "psp",
+ [SMCA_SMU ... SMCA_SMU_V2] = "smu",
+ [SMCA_MP5] = "mp5",
+ [SMCA_MPDMA] = "mpdma",
+ [SMCA_NBIO] = "nbio",
+ [SMCA_PCIE ... SMCA_PCIE_V2] = "pcie",
+ [SMCA_XGMI_PCS] = "xgmi_pcs",
+ [SMCA_NBIF] = "nbif",
+ [SMCA_SHUB] = "shub",
+ [SMCA_SATA] = "sata",
+ [SMCA_USB] = "usb",
+ [SMCA_USR_DP] = "usr_dp",
+ [SMCA_USR_CP] = "usr_cp",
+ [SMCA_GMI_PCS] = "gmi_pcs",
+ [SMCA_XGMI_PHY] = "xgmi_phy",
+ [SMCA_WAFL_PHY] = "wafl_phy",
+ [SMCA_GMI_PHY] = "gmi_phy",
};
static const char *smca_get_name(enum smca_bank_types t)
@@ -130,17 +128,8 @@ static const char *smca_get_name(enum smca_bank_types t)
if (t >= N_SMCA_BANK_TYPES)
return NULL;
- return smca_names[t].name;
-}
-
-const char *smca_get_long_name(enum smca_bank_types t)
-{
- if (t >= N_SMCA_BANK_TYPES)
- return NULL;
-
- return smca_names[t].long_name;
+ return smca_names[t];
}
-EXPORT_SYMBOL_GPL(smca_get_long_name);
enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank)
{
@@ -178,6 +167,7 @@ static const struct smca_hwid smca_hwid_mcatypes[] = {
{ SMCA_CS, HWID_MCATYPE(0x2E, 0x0) },
{ SMCA_PIE, HWID_MCATYPE(0x2E, 0x1) },
{ SMCA_CS_V2, HWID_MCATYPE(0x2E, 0x2) },
+ { SMCA_MA_LLC, HWID_MCATYPE(0x2E, 0x4) },
/* Unified Memory Controller MCA type */
{ SMCA_UMC, HWID_MCATYPE(0x96, 0x0) },
@@ -212,6 +202,8 @@ static const struct smca_hwid smca_hwid_mcatypes[] = {
{ SMCA_SHUB, HWID_MCATYPE(0x80, 0x0) },
{ SMCA_SATA, HWID_MCATYPE(0xA8, 0x0) },
{ SMCA_USB, HWID_MCATYPE(0xAA, 0x0) },
+ { SMCA_USR_DP, HWID_MCATYPE(0x170, 0x0) },
+ { SMCA_USR_CP, HWID_MCATYPE(0x180, 0x0) },
{ SMCA_GMI_PCS, HWID_MCATYPE(0x241, 0x0) },
{ SMCA_XGMI_PHY, HWID_MCATYPE(0x259, 0x0) },
{ SMCA_WAFL_PHY, HWID_MCATYPE(0x267, 0x0) },
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 7b397370b4d6..bc39252bc54f 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -44,6 +44,7 @@
#include <linux/sync_core.h>
#include <linux/task_work.h>
#include <linux/hardirq.h>
+#include <linux/kexec.h>
#include <asm/intel-family.h>
#include <asm/processor.h>
@@ -52,6 +53,7 @@
#include <asm/mce.h>
#include <asm/msr.h>
#include <asm/reboot.h>
+#include <asm/tdx.h>
#include "internal.h"
@@ -228,11 +230,20 @@ static void wait_for_panic(void)
panic("Panicing machine check CPU died");
}
+static const char *mce_dump_aux_info(struct mce *m)
+{
+ if (boot_cpu_has_bug(X86_BUG_TDX_PW_MCE))
+ return tdx_dump_mce_info(m);
+
+ return NULL;
+}
+
static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
{
struct llist_node *pending;
struct mce_evt_llist *l;
int apei_err = 0;
+ const char *memmsg;
/*
* Allow instrumentation around external facilities usage. Not that it
@@ -283,9 +294,29 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
}
if (exp)
pr_emerg(HW_ERR "Machine check: %s\n", exp);
+
+ memmsg = mce_dump_aux_info(final);
+ if (memmsg)
+ pr_emerg(HW_ERR "Machine check: %s\n", memmsg);
+
if (!fake_panic) {
if (panic_timeout == 0)
panic_timeout = mca_cfg.panic_timeout;
+
+ /*
+ * Kdump skips the poisoned page in order to avoid
+ * touching the error bits again. Poison the page even
+ * if the error is fatal and the machine is about to
+ * panic.
+ */
+ if (kexec_crash_loaded()) {
+ if (final && (final->status & MCI_STATUS_ADDRV)) {
+ struct page *p;
+ p = pfn_to_online_page(final->addr >> PAGE_SHIFT);
+ if (p)
+ SetPageHWPoison(p);
+ }
+ }
panic(msg);
} else
pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
@@ -670,6 +701,16 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
barrier();
m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+ /*
+ * Update storm tracking here, before checking for the
+ * MCI_STATUS_VAL bit. Valid corrected errors count
+ * towards declaring, or maintaining, storm status. No
+ * error in a bank counts towards avoiding, or ending,
+ * storm status.
+ */
+ if (!mca_cfg.cmci_disabled)
+ mce_track_storm(&m);
+
/* If this entry is not valid, ignore it */
if (!(m.status & MCI_STATUS_VAL))
continue;
@@ -1601,13 +1642,6 @@ static unsigned long check_interval = INITIAL_CHECK_INTERVAL;
static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);
-static unsigned long mce_adjust_timer_default(unsigned long interval)
-{
- return interval;
-}
-
-static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
-
static void __start_timer(struct timer_list *t, unsigned long interval)
{
unsigned long when = jiffies + interval;
@@ -1637,15 +1671,9 @@ static void mce_timer_fn(struct timer_list *t)
iv = __this_cpu_read(mce_next_interval);
- if (mce_available(this_cpu_ptr(&cpu_info))) {
+ if (mce_available(this_cpu_ptr(&cpu_info)))
mc_poll_banks();
- if (mce_intel_cmci_poll()) {
- iv = mce_adjust_timer(iv);
- goto done;
- }
- }
-
/*
* Alert userspace if needed. If we logged an MCE, reduce the polling
* interval, otherwise increase the polling interval.
@@ -1655,23 +1683,29 @@ static void mce_timer_fn(struct timer_list *t)
else
iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
-done:
- __this_cpu_write(mce_next_interval, iv);
- __start_timer(t, iv);
+ if (mce_get_storm_mode()) {
+ __start_timer(t, HZ);
+ } else {
+ __this_cpu_write(mce_next_interval, iv);
+ __start_timer(t, iv);
+ }
}
/*
- * Ensure that the timer is firing in @interval from now.
+ * When a storm starts on any bank on this CPU, switch to polling
+ * once per second. When the storm ends, revert to the default
+ * polling interval.
*/
-void mce_timer_kick(unsigned long interval)
+void mce_timer_kick(bool storm)
{
struct timer_list *t = this_cpu_ptr(&mce_timer);
- unsigned long iv = __this_cpu_read(mce_next_interval);
- __start_timer(t, interval);
+ mce_set_storm_mode(storm);
- if (interval < iv)
- __this_cpu_write(mce_next_interval, interval);
+ if (storm)
+ __start_timer(t, HZ);
+ else
+ __this_cpu_write(mce_next_interval, check_interval * HZ);
}
/* Must not be called in IRQ context where del_timer_sync() can deadlock */
@@ -1995,7 +2029,6 @@ static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c)
intel_init_cmci();
intel_init_lmce();
- mce_adjust_timer = cmci_intel_adjust_timer;
}
static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c)
@@ -2008,7 +2041,6 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
switch (c->x86_vendor) {
case X86_VENDOR_INTEL:
mce_intel_feature_init(c);
- mce_adjust_timer = cmci_intel_adjust_timer;
break;
case X86_VENDOR_AMD: {
@@ -2568,9 +2600,6 @@ static int mce_device_create(unsigned int cpu)
int err;
int i, j;
- if (!mce_available(&boot_cpu_data))
- return -EIO;
-
dev = per_cpu(mce_device, cpu);
if (dev)
return 0;
@@ -2665,8 +2694,6 @@ static void mce_reenable_cpu(void)
static int mce_cpu_dead(unsigned int cpu)
{
- mce_intel_hcpu_update(cpu);
-
/* intentionally ignoring frozen here */
if (!cpuhp_tasks_frozen)
cmci_rediscover();
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 4d8d4bcf915d..72f0695c3dc1 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -746,6 +746,7 @@ static void check_hw_inj_possible(void)
wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status);
rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status);
+ wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0);
if (!status) {
hw_injection_possible = false;
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 52bce533ddcc..399b62e223d2 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -42,15 +42,6 @@
static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
/*
- * CMCI storm detection backoff counter
- *
- * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've
- * encountered an error. If not, we decrement it by one. We signal the end of
- * the CMCI storm when it reaches 0.
- */
-static DEFINE_PER_CPU(int, cmci_backoff_cnt);
-
-/*
* cmci_discover_lock protects against parallel discovery attempts
* which could race against each other.
*/
@@ -63,22 +54,26 @@ static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
*/
static DEFINE_SPINLOCK(cmci_poll_lock);
+/* Linux non-storm CMCI threshold (may be overridden by BIOS) */
#define CMCI_THRESHOLD 1
-#define CMCI_POLL_INTERVAL (30 * HZ)
-#define CMCI_STORM_INTERVAL (HZ)
-#define CMCI_STORM_THRESHOLD 15
-static DEFINE_PER_CPU(unsigned long, cmci_time_stamp);
-static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt);
-static DEFINE_PER_CPU(unsigned int, cmci_storm_state);
-
-enum {
- CMCI_STORM_NONE,
- CMCI_STORM_ACTIVE,
- CMCI_STORM_SUBSIDED,
-};
+/*
+ * MCi_CTL2 threshold for each bank when there is no storm.
+ * Default value for each bank may have been set by BIOS.
+ */
+static u16 cmci_threshold[MAX_NR_BANKS];
-static atomic_t cmci_storm_on_cpus;
+/*
+ * High threshold to limit CMCI rate during storms. Max supported is
+ * 0x7FFF. Use this slightly smaller value so it has a distinctive
+ * signature when some asks "Why am I not seeing all corrected errors?"
+ * A high threshold is used instead of just disabling CMCI for a
+ * bank because both corrected and uncorrected errors may be logged
+ * in the same bank and signalled with CMCI. The threshold only applies
+ * to corrected errors, so keeping CMCI enabled means that uncorrected
+ * errors will still be processed in a timely fashion.
+ */
+#define CMCI_STORM_THRESHOLD 32749
static int cmci_supported(int *banks)
{
@@ -134,204 +129,166 @@ static bool lmce_supported(void)
return tmp & FEAT_CTL_LMCE_ENABLED;
}
-bool mce_intel_cmci_poll(void)
+/*
+ * Set a new CMCI threshold value. Preserve the state of the
+ * MCI_CTL2_CMCI_EN bit in case this happens during a
+ * cmci_rediscover() operation.
+ */
+static void cmci_set_threshold(int bank, int thresh)
{
- if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
- return false;
-
- /*
- * Reset the counter if we've logged an error in the last poll
- * during the storm.
- */
- if (machine_check_poll(0, this_cpu_ptr(&mce_banks_owned)))
- this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL);
- else
- this_cpu_dec(cmci_backoff_cnt);
+ unsigned long flags;
+ u64 val;
- return true;
+ raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
+ wrmsrl(MSR_IA32_MCx_CTL2(bank), val | thresh);
+ raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
-void mce_intel_hcpu_update(unsigned long cpu)
+void mce_intel_handle_storm(int bank, bool on)
{
- if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE)
- atomic_dec(&cmci_storm_on_cpus);
+ if (on)
+ cmci_set_threshold(bank, CMCI_STORM_THRESHOLD);
+ else
+ cmci_set_threshold(bank, cmci_threshold[bank]);
+}
- per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
+/*
+ * The interrupt handler. This is called on every event.
+ * Just call the poller directly to log any events.
+ * This could in theory increase the threshold under high load,
+ * but doesn't for now.
+ */
+static void intel_threshold_interrupt(void)
+{
+ machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
}
-static void cmci_toggle_interrupt_mode(bool on)
+/*
+ * Check all the reasons why current CPU cannot claim
+ * ownership of a bank.
+ * 1: CPU already owns this bank
+ * 2: BIOS owns this bank
+ * 3: Some other CPU owns this bank
+ */
+static bool cmci_skip_bank(int bank, u64 *val)
{
- unsigned long flags, *owned;
- int bank;
- u64 val;
+ unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
- owned = this_cpu_ptr(mce_banks_owned);
- for_each_set_bit(bank, owned, MAX_NR_BANKS) {
- rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ if (test_bit(bank, owned))
+ return true;
- if (on)
- val |= MCI_CTL2_CMCI_EN;
- else
- val &= ~MCI_CTL2_CMCI_EN;
+ /* Skip banks in firmware first mode */
+ if (test_bit(bank, mce_banks_ce_disabled))
+ return true;
- wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
- }
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
-}
+ rdmsrl(MSR_IA32_MCx_CTL2(bank), *val);
-unsigned long cmci_intel_adjust_timer(unsigned long interval)
-{
- if ((this_cpu_read(cmci_backoff_cnt) > 0) &&
- (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) {
- mce_notify_irq();
- return CMCI_STORM_INTERVAL;
+ /* Already owned by someone else? */
+ if (*val & MCI_CTL2_CMCI_EN) {
+ clear_bit(bank, owned);
+ __clear_bit(bank, this_cpu_ptr(mce_poll_banks));
+ return true;
}
- switch (__this_cpu_read(cmci_storm_state)) {
- case CMCI_STORM_ACTIVE:
-
- /*
- * We switch back to interrupt mode once the poll timer has
- * silenced itself. That means no events recorded and the timer
- * interval is back to our poll interval.
- */
- __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED);
- if (!atomic_sub_return(1, &cmci_storm_on_cpus))
- pr_notice("CMCI storm subsided: switching to interrupt mode\n");
+ return false;
+}
- fallthrough;
+/*
+ * Decide which CMCI interrupt threshold to use:
+ * 1: If this bank is in storm mode from whichever CPU was
+ * the previous owner, stay in storm mode.
+ * 2: If ignoring any threshold set by BIOS, set Linux default
+ * 3: Try to honor BIOS threshold (unless buggy BIOS set it at zero).
+ */
+static u64 cmci_pick_threshold(u64 val, int *bios_zero_thresh)
+{
+ if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD)
+ return val;
- case CMCI_STORM_SUBSIDED:
+ if (!mca_cfg.bios_cmci_threshold) {
+ val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
+ val |= CMCI_THRESHOLD;
+ } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) {
/*
- * We wait for all CPUs to go back to SUBSIDED state. When that
- * happens we switch back to interrupt mode.
+ * If bios_cmci_threshold boot option was specified
+ * but the threshold is zero, we'll try to initialize
+ * it to 1.
*/
- if (!atomic_read(&cmci_storm_on_cpus)) {
- __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
- cmci_toggle_interrupt_mode(true);
- cmci_recheck();
- }
- return CMCI_POLL_INTERVAL;
- default:
-
- /* We have shiny weather. Let the poll do whatever it thinks. */
- return interval;
+ *bios_zero_thresh = 1;
+ val |= CMCI_THRESHOLD;
}
+
+ return val;
}
-static bool cmci_storm_detect(void)
+/*
+ * Try to claim ownership of a bank.
+ */
+static void cmci_claim_bank(int bank, u64 val, int bios_zero_thresh, int *bios_wrong_thresh)
{
- unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
- unsigned long ts = __this_cpu_read(cmci_time_stamp);
- unsigned long now = jiffies;
- int r;
+ struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
- if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE)
- return true;
+ val |= MCI_CTL2_CMCI_EN;
+ wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
- if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) {
- cnt++;
- } else {
- cnt = 1;
- __this_cpu_write(cmci_time_stamp, now);
+ /* If the enable bit did not stick, this bank should be polled. */
+ if (!(val & MCI_CTL2_CMCI_EN)) {
+ WARN_ON(!test_bit(bank, this_cpu_ptr(mce_poll_banks)));
+ storm->banks[bank].poll_only = true;
+ return;
}
- __this_cpu_write(cmci_storm_cnt, cnt);
- if (cnt <= CMCI_STORM_THRESHOLD)
- return false;
-
- cmci_toggle_interrupt_mode(false);
- __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
- r = atomic_add_return(1, &cmci_storm_on_cpus);
- mce_timer_kick(CMCI_STORM_INTERVAL);
- this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL);
+ /* This CPU successfully set the enable bit. */
+ set_bit(bank, (void *)this_cpu_ptr(&mce_banks_owned));
- if (r == 1)
- pr_notice("CMCI storm detected: switching to poll mode\n");
- return true;
-}
+ if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD) {
+ pr_notice("CPU%d BANK%d CMCI inherited storm\n", smp_processor_id(), bank);
+ mce_inherit_storm(bank);
+ cmci_storm_begin(bank);
+ } else {
+ __clear_bit(bank, this_cpu_ptr(mce_poll_banks));
+ }
-/*
- * The interrupt handler. This is called on every event.
- * Just call the poller directly to log any events.
- * This could in theory increase the threshold under high load,
- * but doesn't for now.
- */
-static void intel_threshold_interrupt(void)
-{
- if (cmci_storm_detect())
- return;
+ /*
+ * We are able to set thresholds for some banks that
+ * had a threshold of 0. This means the BIOS has not
+ * set the thresholds properly or does not work with
+ * this boot option. Note down now and report later.
+ */
+ if (mca_cfg.bios_cmci_threshold && bios_zero_thresh &&
+ (val & MCI_CTL2_CMCI_THRESHOLD_MASK))
+ *bios_wrong_thresh = 1;
- machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
+ /* Save default threshold for each bank */
+ if (cmci_threshold[bank] == 0)
+ cmci_threshold[bank] = val & MCI_CTL2_CMCI_THRESHOLD_MASK;
}
/*
* Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks
* on this CPU. Use the algorithm recommended in the SDM to discover shared
- * banks.
+ * banks. Called during initial bootstrap, and also for hotplug CPU operations
+ * to rediscover/reassign machine check banks.
*/
static void cmci_discover(int banks)
{
- unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
+ int bios_wrong_thresh = 0;
unsigned long flags;
int i;
- int bios_wrong_thresh = 0;
raw_spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++) {
u64 val;
int bios_zero_thresh = 0;
- if (test_bit(i, owned))
+ if (cmci_skip_bank(i, &val))
continue;
- /* Skip banks in firmware first mode */
- if (test_bit(i, mce_banks_ce_disabled))
- continue;
-
- rdmsrl(MSR_IA32_MCx_CTL2(i), val);
-
- /* Already owned by someone else? */
- if (val & MCI_CTL2_CMCI_EN) {
- clear_bit(i, owned);
- __clear_bit(i, this_cpu_ptr(mce_poll_banks));
- continue;
- }
-
- if (!mca_cfg.bios_cmci_threshold) {
- val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
- val |= CMCI_THRESHOLD;
- } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) {
- /*
- * If bios_cmci_threshold boot option was specified
- * but the threshold is zero, we'll try to initialize
- * it to 1.
- */
- bios_zero_thresh = 1;
- val |= CMCI_THRESHOLD;
- }
-
- val |= MCI_CTL2_CMCI_EN;
- wrmsrl(MSR_IA32_MCx_CTL2(i), val);
- rdmsrl(MSR_IA32_MCx_CTL2(i), val);
-
- /* Did the enable bit stick? -- the bank supports CMCI */
- if (val & MCI_CTL2_CMCI_EN) {
- set_bit(i, owned);
- __clear_bit(i, this_cpu_ptr(mce_poll_banks));
- /*
- * We are able to set thresholds for some banks that
- * had a threshold of 0. This means the BIOS has not
- * set the thresholds properly or does not work with
- * this boot option. Note down now and report later.
- */
- if (mca_cfg.bios_cmci_threshold && bios_zero_thresh &&
- (val & MCI_CTL2_CMCI_THRESHOLD_MASK))
- bios_wrong_thresh = 1;
- } else {
- WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks)));
- }
+ val = cmci_pick_threshold(val, &bios_zero_thresh);
+ cmci_claim_bank(i, val, bios_zero_thresh, &bios_wrong_thresh);
}
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) {
@@ -370,6 +327,9 @@ static void __cmci_disable_bank(int bank)
val &= ~MCI_CTL2_CMCI_EN;
wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
+
+ if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD)
+ cmci_storm_end(bank);
}
/*
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index e13a26c9c0ac..01f8f03969e6 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -41,9 +41,7 @@ struct dentry *mce_get_debugfs_dir(void);
extern mce_banks_t mce_banks_ce_disabled;
#ifdef CONFIG_X86_MCE_INTEL
-unsigned long cmci_intel_adjust_timer(unsigned long interval);
-bool mce_intel_cmci_poll(void);
-void mce_intel_hcpu_update(unsigned long cpu);
+void mce_intel_handle_storm(int bank, bool on);
void cmci_disable_bank(int bank);
void intel_init_cmci(void);
void intel_init_lmce(void);
@@ -51,9 +49,7 @@ void intel_clear_lmce(void);
bool intel_filter_mce(struct mce *m);
bool intel_mce_usable_address(struct mce *m);
#else
-# define cmci_intel_adjust_timer mce_adjust_timer_default
-static inline bool mce_intel_cmci_poll(void) { return false; }
-static inline void mce_intel_hcpu_update(unsigned long cpu) { }
+static inline void mce_intel_handle_storm(int bank, bool on) { }
static inline void cmci_disable_bank(int bank) { }
static inline void intel_init_cmci(void) { }
static inline void intel_init_lmce(void) { }
@@ -62,7 +58,63 @@ static inline bool intel_filter_mce(struct mce *m) { return false; }
static inline bool intel_mce_usable_address(struct mce *m) { return false; }
#endif
-void mce_timer_kick(unsigned long interval);
+void mce_timer_kick(bool storm);
+
+#ifdef CONFIG_X86_MCE_THRESHOLD
+void cmci_storm_begin(unsigned int bank);
+void cmci_storm_end(unsigned int bank);
+void mce_track_storm(struct mce *mce);
+void mce_inherit_storm(unsigned int bank);
+bool mce_get_storm_mode(void);
+void mce_set_storm_mode(bool storm);
+#else
+static inline void cmci_storm_begin(unsigned int bank) {}
+static inline void cmci_storm_end(unsigned int bank) {}
+static inline void mce_track_storm(struct mce *mce) {}
+static inline void mce_inherit_storm(unsigned int bank) {}
+static inline bool mce_get_storm_mode(void) { return false; }
+static inline void mce_set_storm_mode(bool storm) {}
+#endif
+
+/*
+ * history: Bitmask tracking errors occurrence. Each set bit
+ * represents an error seen.
+ *
+ * timestamp: Last time (in jiffies) that the bank was polled.
+ * in_storm_mode: Is this bank in storm mode?
+ * poll_only: Bank does not support CMCI, skip storm tracking.
+ */
+struct storm_bank {
+ u64 history;
+ u64 timestamp;
+ bool in_storm_mode;
+ bool poll_only;
+};
+
+#define NUM_HISTORY_BITS (sizeof(u64) * BITS_PER_BYTE)
+
+/* How many errors within the history buffer mark the start of a storm. */
+#define STORM_BEGIN_THRESHOLD 5
+
+/*
+ * How many polls of machine check bank without an error before declaring
+ * the storm is over. Since it is tracked by the bitmasks in the history
+ * field of struct storm_bank the mask is 30 bits [0 ... 29].
+ */
+#define STORM_END_POLL_THRESHOLD 29
+
+/*
+ * banks: per-cpu, per-bank details
+ * stormy_bank_count: count of MC banks in storm state
+ * poll_mode: CPU is in poll mode
+ */
+struct mca_storm_desc {
+ struct storm_bank banks[MAX_NR_BANKS];
+ u8 stormy_bank_count;
+ bool poll_mode;
+};
+
+DECLARE_PER_CPU(struct mca_storm_desc, storm_desc);
#ifdef CONFIG_ACPI_APEI
int apei_write_mce(struct mce *m);
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index ef4e7bb5fd88..89e31e1e5c9c 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -29,3 +29,118 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_threshold)
trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR);
apic_eoi();
}
+
+DEFINE_PER_CPU(struct mca_storm_desc, storm_desc);
+
+void mce_inherit_storm(unsigned int bank)
+{
+ struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
+
+ /*
+ * Previous CPU owning this bank had put it into storm mode,
+ * but the precise history of that storm is unknown. Assume
+ * the worst (all recent polls of the bank found a valid error
+ * logged). This will avoid the new owner prematurely declaring
+ * the storm has ended.
+ */
+ storm->banks[bank].history = ~0ull;
+ storm->banks[bank].timestamp = jiffies;
+}
+
+bool mce_get_storm_mode(void)
+{
+ return __this_cpu_read(storm_desc.poll_mode);
+}
+
+void mce_set_storm_mode(bool storm)
+{
+ __this_cpu_write(storm_desc.poll_mode, storm);
+}
+
+static void mce_handle_storm(unsigned int bank, bool on)
+{
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_INTEL:
+ mce_intel_handle_storm(bank, on);
+ break;
+ }
+}
+
+void cmci_storm_begin(unsigned int bank)
+{
+ struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
+
+ __set_bit(bank, this_cpu_ptr(mce_poll_banks));
+ storm->banks[bank].in_storm_mode = true;
+
+ /*
+ * If this is the first bank on this CPU to enter storm mode
+ * start polling.
+ */
+ if (++storm->stormy_bank_count == 1)
+ mce_timer_kick(true);
+}
+
+void cmci_storm_end(unsigned int bank)
+{
+ struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
+
+ __clear_bit(bank, this_cpu_ptr(mce_poll_banks));
+ storm->banks[bank].history = 0;
+ storm->banks[bank].in_storm_mode = false;
+
+ /* If no banks left in storm mode, stop polling. */
+ if (!this_cpu_dec_return(storm_desc.stormy_bank_count))
+ mce_timer_kick(false);
+}
+
+void mce_track_storm(struct mce *mce)
+{
+ struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
+ unsigned long now = jiffies, delta;
+ unsigned int shift = 1;
+ u64 history = 0;
+
+ /* No tracking needed for banks that do not support CMCI */
+ if (storm->banks[mce->bank].poll_only)
+ return;
+
+ /*
+ * When a bank is in storm mode it is polled once per second and
+ * the history mask will record about the last minute of poll results.
+ * If it is not in storm mode, then the bank is only checked when
+ * there is a CMCI interrupt. Check how long it has been since
+ * this bank was last checked, and adjust the amount of "shift"
+ * to apply to history.
+ */
+ if (!storm->banks[mce->bank].in_storm_mode) {
+ delta = now - storm->banks[mce->bank].timestamp;
+ shift = (delta + HZ) / HZ;
+ }
+
+ /* If it has been a long time since the last poll, clear history. */
+ if (shift < NUM_HISTORY_BITS)
+ history = storm->banks[mce->bank].history << shift;
+
+ storm->banks[mce->bank].timestamp = now;
+
+ /* History keeps track of corrected errors. VAL=1 && UC=0 */
+ if ((mce->status & MCI_STATUS_VAL) && mce_is_correctable(mce))
+ history |= 1;
+
+ storm->banks[mce->bank].history = history;
+
+ if (storm->banks[mce->bank].in_storm_mode) {
+ if (history & GENMASK_ULL(STORM_END_POLL_THRESHOLD, 0))
+ return;
+ printk_deferred(KERN_NOTICE "CPU%d BANK%d CMCI storm subsided\n", smp_processor_id(), mce->bank);
+ mce_handle_storm(mce->bank, false);
+ cmci_storm_end(mce->bank);
+ } else {
+ if (hweight64(history) < STORM_BEGIN_THRESHOLD)
+ return;
+ printk_deferred(KERN_NOTICE "CPU%d BANK%d CMCI storm detected\n", smp_processor_id(), mce->bank);
+ mce_handle_storm(mce->bank, true);
+ cmci_storm_begin(mce->bank);
+ }
+}
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 070426b9895f..857e608af641 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -370,14 +370,14 @@ static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info *
{
struct cpio_data cp;
+ intel_collect_cpu_info(&uci->cpu_sig);
+
if (!load_builtin_intel_microcode(&cp))
cp = find_microcode_in_initrd(ucode_path);
if (!(cp.data && cp.size))
return NULL;
- intel_collect_cpu_info(&uci->cpu_sig);
-
return scan_microcode(cp.data, cp.size, uci, save);
}
@@ -410,13 +410,13 @@ void __init load_ucode_intel_bsp(struct early_load_data *ed)
{
struct ucode_cpu_info uci;
- ed->old_rev = intel_get_microcode_revision();
-
uci.mc = get_microcode_blob(&uci, false);
- if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED)
- ucode_patch_va = UCODE_BSP_LOADED;
+ ed->old_rev = uci.cpu_sig.rev;
- ed->new_rev = uci.cpu_sig.rev;
+ if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) {
+ ucode_patch_va = UCODE_BSP_LOADED;
+ ed->new_rev = uci.cpu_sig.rev;
+ }
}
void load_ucode_intel_ap(void)
@@ -457,12 +457,6 @@ static enum ucode_state apply_microcode_late(int cpu)
if (ret != UCODE_UPDATED && ret != UCODE_OK)
return ret;
- if (!cpu && uci->cpu_sig.rev != cur_rev) {
- pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n",
- uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24,
- (mc->hdr.date >> 16) & 0xff);
- }
-
cpu_data(cpu).microcode = uci->cpu_sig.rev;
if (!cpu)
boot_cpu_data.microcode = uci->cpu_sig.rev;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 2d6aa5d2e3d7..d3524778a545 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -428,6 +428,10 @@ void __init mtrr_copy_map(void)
* 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.
+ *
+ * @var: MTRR variable range array to use
+ * @num_var: length of the @var array
+ * @def_type: default caching type
*/
void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var,
mtrr_type def_type)
@@ -492,13 +496,15 @@ static u8 type_merge(u8 type, u8 new_type, u8 *uniform)
/**
* mtrr_type_lookup - look up memory type in MTRR
*
+ * @start: Begin of the physical address range
+ * @end: End of the physical address range
+ * @uniform: output argument:
+ * - 1: the returned MTRR type is valid for the whole region
+ * - 0: otherwise
+ *
* Return Values:
* MTRR_TYPE_(type) - The effective MTRR type for the region
* MTRR_TYPE_INVALID - MTRR is disabled
- *
- * Output Argument:
- * 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)
{
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index 5d390df21440..b65ab214bdf5 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -581,7 +581,7 @@ err_out:
*
* Flush any outstanding enqueued EADD operations and perform EINIT. The
* Launch Enclave Public Key Hash MSRs are rewritten as necessary to match
- * the enclave's MRSIGNER, which is caculated from the provided sigstruct.
+ * the enclave's MRSIGNER, which is calculated from the provided sigstruct.
*
* Return:
* - 0: Success.
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-28 07:14:46 +0000