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/amd.c18
-rw-r--r--arch/x86/kernel/cpu/bugs.c25
-rw-r--r--arch/x86/kernel/cpu/bus_lock.c2
-rw-r--r--arch/x86/kernel/cpu/common.c124
-rw-r--r--arch/x86/kernel/cpu/debugfs.c1
-rw-r--r--arch/x86/kernel/cpu/intel.c5
-rw-r--r--arch/x86/kernel/cpu/match.c30
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c137
-rw-r--r--arch/x86/kernel/cpu/mce/core.c209
-rw-r--r--arch/x86/kernel/cpu/mce/genpool.c29
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c9
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h4
-rw-r--r--arch/x86/kernel/cpu/mce/threshold.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c54
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c60
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c6
-rw-r--r--arch/x86/kernel/cpu/mtrr/mtrr.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c9
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c70
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h11
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c94
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c30
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c43
-rw-r--r--arch/x86/kernel/cpu/topology.c2
-rw-r--r--arch/x86/kernel/cpu/topology_common.c1
25 files changed, 529 insertions, 448 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 79d2e17f6582..54194f5995de 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -355,10 +355,15 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c)
/*
* RMP table entry format is not architectural and is defined by the
* per-processor PPR. Restrict SNP support on the known CPU models
- * for which the RMP table entry format is currently defined for.
+ * for which the RMP table entry format is currently defined or for
+ * processors which support the architecturally defined RMPREAD
+ * instruction.
*/
if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
- c->x86 >= 0x19 && snp_probe_rmptable_info()) {
+ (cpu_feature_enabled(X86_FEATURE_ZEN3) ||
+ cpu_feature_enabled(X86_FEATURE_ZEN4) ||
+ cpu_feature_enabled(X86_FEATURE_RMPREAD)) &&
+ snp_probe_rmptable_info()) {
cc_platform_set(CC_ATTR_HOST_SEV_SNP);
} else {
setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
@@ -795,10 +800,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
clear_rdrand_cpuid_bit(c);
}
-static const struct x86_cpu_desc erratum_1386_microcode[] = {
- AMD_CPU_DESC(0x17, 0x1, 0x2, 0x0800126e),
- AMD_CPU_DESC(0x17, 0x31, 0x0, 0x08301052),
- {},
+static const struct x86_cpu_id erratum_1386_microcode[] = {
+ X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x01), 0x2, 0x2, 0x0800126e),
+ X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x31), 0x0, 0x0, 0x08301052),
};
static void fix_erratum_1386(struct cpuinfo_x86 *c)
@@ -814,7 +818,7 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c)
* Clear the feature flag only on microcode revisions which
* don't have the fix.
*/
- if (x86_cpu_has_min_microcode_rev(erratum_1386_microcode))
+ if (x86_match_min_microcode_rev(erratum_1386_microcode))
return;
clear_cpu_cap(c, X86_FEATURE_XSAVES);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 47a01d4028f6..a5d0998d7604 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1115,6 +1115,8 @@ 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;
/*
* IBPB on entry already obviates the need for
@@ -1124,9 +1126,6 @@ do_cmd_auto:
setup_clear_cpu_cap(X86_FEATURE_UNRET);
setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
- setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
- mitigate_smt = true;
-
/*
* There is no need for RSB filling: entry_ibpb() ensures
* all predictions, including the RSB, are invalidated,
@@ -2615,6 +2614,9 @@ static void __init srso_select_mitigation(void)
break;
case SRSO_CMD_SAFE_RET:
+ if (boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO))
+ goto ibpb_on_vmexit;
+
if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
/*
* Enable the return thunk for generated code
@@ -2643,6 +2645,7 @@ static void __init srso_select_mitigation(void)
if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
if (has_microcode) {
setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+ setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
srso_mitigation = SRSO_MITIGATION_IBPB;
/*
@@ -2652,15 +2655,23 @@ static void __init srso_select_mitigation(void)
*/
setup_clear_cpu_cap(X86_FEATURE_UNRET);
setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
+
+ /*
+ * There is no need for RSB filling: entry_ibpb() ensures
+ * all predictions, including the RSB, are invalidated,
+ * regardless of IBPB implementation.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
}
} else {
pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
}
break;
+ibpb_on_vmexit:
case SRSO_CMD_IBPB_ON_VMEXIT:
- if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
- if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) {
+ if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
+ if (has_microcode) {
setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
@@ -2672,8 +2683,8 @@ static void __init srso_select_mitigation(void)
setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
}
} else {
- pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
- }
+ pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
+ }
break;
default:
break;
diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 704e9241b964..6cba85c79d42 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -49,7 +49,7 @@ static unsigned int sysctl_sld_mitigate = 1;
static DEFINE_SEMAPHORE(buslock_sem, 1);
#ifdef CONFIG_PROC_SYSCTL
-static struct ctl_table sld_sysctls[] = {
+static const struct ctl_table sld_sysctls[] = {
{
.procname = "split_lock_mitigate",
.data = &sysctl_sld_mitigate,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a5c28975c608..7cce91b19fb2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -29,6 +29,7 @@
#include <asm/alternative.h>
#include <asm/cmdline.h>
+#include <asm/cpuid.h>
#include <asm/perf_event.h>
#include <asm/mmu_context.h>
#include <asm/doublefault.h>
@@ -636,9 +637,9 @@ struct cpuid_dependent_feature {
static const struct cpuid_dependent_feature
cpuid_dependent_features[] = {
- { X86_FEATURE_MWAIT, 0x00000005 },
- { X86_FEATURE_DCA, 0x00000009 },
- { X86_FEATURE_XSAVE, 0x0000000d },
+ { X86_FEATURE_MWAIT, CPUID_LEAF_MWAIT },
+ { X86_FEATURE_DCA, CPUID_LEAF_DCA },
+ { X86_FEATURE_XSAVE, CPUID_LEAF_XSTATE },
{ 0, 0 }
};
@@ -867,7 +868,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
}
-static void get_cpu_vendor(struct cpuinfo_x86 *c)
+void get_cpu_vendor(struct cpuinfo_x86 *c)
{
char *v = c->x86_vendor_id;
int i;
@@ -1201,8 +1202,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define VULNBL(vendor, family, model, blacklist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist)
-#define VULNBL_INTEL_STEPPINGS(vfm, steppings, issues) \
- X86_MATCH_VFM_STEPPINGS(vfm, steppings, issues)
+#define VULNBL_INTEL_STEPS(vfm, max_stepping, issues) \
+ X86_MATCH_VFM_STEPS(vfm, X86_STEP_MIN, max_stepping, issues)
#define VULNBL_AMD(family, blacklist) \
VULNBL(AMD, family, X86_MODEL_ANY, blacklist)
@@ -1227,49 +1228,50 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define RFDS BIT(7)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
- VULNBL_INTEL_STEPPINGS(INTEL_IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_HASWELL, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_L, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_G, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_X, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_G, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_X, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(INTEL_CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED),
- VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED),
- VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE_L, X86_STEPPING_ANY, GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE, X86_STEPPING_ANY, GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
- VULNBL_INTEL_STEPPINGS(INTEL_ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE_L, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_P, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_S, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO),
+ VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO),
+ VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO),
+ VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS),
+ VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS),
+ VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED),
+ VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_ALDERLAKE, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_D, X86_STEP_MAX, MMIO | RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_D, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEP_MAX, RFDS),
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
VULNBL_AMD(0x19, SRSO),
+ VULNBL_AMD(0x1a, SRSO),
{}
};
@@ -1649,15 +1651,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
detect_nopl();
}
-void __init early_cpu_init(void)
+void __init init_cpu_devs(void)
{
const struct cpu_dev *const *cdev;
int count = 0;
-#ifdef CONFIG_PROCESSOR_SELECT
- pr_info("KERNEL supported cpus:\n");
-#endif
-
for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
const struct cpu_dev *cpudev = *cdev;
@@ -1665,20 +1663,30 @@ void __init early_cpu_init(void)
break;
cpu_devs[count] = cpudev;
count++;
+ }
+}
+void __init early_cpu_init(void)
+{
#ifdef CONFIG_PROCESSOR_SELECT
- {
- unsigned int j;
-
- for (j = 0; j < 2; j++) {
- if (!cpudev->c_ident[j])
- continue;
- pr_info(" %s %s\n", cpudev->c_vendor,
- cpudev->c_ident[j]);
- }
- }
+ unsigned int i, j;
+
+ pr_info("KERNEL supported cpus:\n");
#endif
+
+ init_cpu_devs();
+
+#ifdef CONFIG_PROCESSOR_SELECT
+ for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) {
+ for (j = 0; j < 2; j++) {
+ if (!cpu_devs[i]->c_ident[j])
+ continue;
+ pr_info(" %s %s\n", cpu_devs[i]->c_vendor,
+ cpu_devs[i]->c_ident[j]);
+ }
}
+#endif
+
early_identify_cpu(&boot_cpu_data);
}
diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c
index 10719aba6276..cacfd3f6abef 100644
--- a/arch/x86/kernel/cpu/debugfs.c
+++ b/arch/x86/kernel/cpu/debugfs.c
@@ -25,6 +25,7 @@ static int cpu_debug_show(struct seq_file *m, void *p)
seq_printf(m, "cpu_type: %s\n", get_topology_cpu_type_name(c));
seq_printf(m, "logical_pkg_id: %u\n", c->topo.logical_pkg_id);
seq_printf(m, "logical_die_id: %u\n", c->topo.logical_die_id);
+ seq_printf(m, "logical_core_id: %u\n", c->topo.logical_core_id);
seq_printf(m, "llc_id: %u\n", c->topo.llc_id);
seq_printf(m, "l2c_id: %u\n", c->topo.l2c_id);
seq_printf(m, "amd_node_id: %u\n", c->topo.amd_node_id);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 8ded9f859a3a..3dce22f00dc3 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -599,11 +599,6 @@ static void init_intel(struct cpuinfo_x86 *c)
if (p)
strcpy(c->x86_model_id, p);
}
-
- if (c->x86 == 15)
- set_cpu_cap(c, X86_FEATURE_P4);
- if (c->x86 == 6)
- set_cpu_cap(c, X86_FEATURE_P3);
#endif
/* Work around errata */
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 8e7de733320a..4f3c65429f82 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -6,7 +6,7 @@
#include <linux/slab.h>
/**
- * x86_match_cpu - match current CPU again an array of x86_cpu_ids
+ * x86_match_cpu - match current CPU against an array of x86_cpu_ids
* @match: Pointer to array of x86_cpu_ids. Last entry terminated with
* {}.
*
@@ -56,33 +56,13 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
}
EXPORT_SYMBOL(x86_match_cpu);
-static const struct x86_cpu_desc *
-x86_match_cpu_with_stepping(const struct x86_cpu_desc *match)
+bool x86_match_min_microcode_rev(const struct x86_cpu_id *table)
{
- struct cpuinfo_x86 *c = &boot_cpu_data;
- const struct x86_cpu_desc *m;
-
- for (m = match; m->x86_family | m->x86_model; m++) {
- if (c->x86_vendor != m->x86_vendor)
- continue;
- if (c->x86 != m->x86_family)
- continue;
- if (c->x86_model != m->x86_model)
- continue;
- if (c->x86_stepping != m->x86_stepping)
- continue;
- return m;
- }
- return NULL;
-}
-
-bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table)
-{
- const struct x86_cpu_desc *res = x86_match_cpu_with_stepping(table);
+ const struct x86_cpu_id *res = x86_match_cpu(table);
- if (!res || res->x86_microcode_rev > boot_cpu_data.microcode)
+ if (!res || res->driver_data > boot_cpu_data.microcode)
return false;
return true;
}
-EXPORT_SYMBOL_GPL(x86_cpu_has_min_microcode_rev);
+EXPORT_SYMBOL_GPL(x86_match_min_microcode_rev);
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 6ca80fff1fea..1075a90141da 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -4,8 +4,6 @@
*
* Written by Jacob Shin - AMD, Inc.
* Maintained by: Borislav Petkov <bp@alien8.de>
- *
- * All MC4_MISCi registers are shared between cores on a node.
*/
#include <linux/interrupt.h>
#include <linux/notifier.h>
@@ -20,7 +18,6 @@
#include <linux/smp.h>
#include <linux/string.h>
-#include <asm/amd_nb.h>
#include <asm/traps.h>
#include <asm/apic.h>
#include <asm/mce.h>
@@ -221,6 +218,32 @@ static const struct smca_hwid smca_hwid_mcatypes[] = {
#define MAX_MCATYPE_NAME_LEN 30
static char buf_mcatype[MAX_MCATYPE_NAME_LEN];
+struct threshold_block {
+ /* This block's number within its bank. */
+ unsigned int block;
+ /* MCA bank number that contains this block. */
+ unsigned int bank;
+ /* CPU which controls this block's MCA bank. */
+ unsigned int cpu;
+ /* MCA_MISC MSR address for this block. */
+ u32 address;
+ /* Enable/Disable APIC interrupt. */
+ bool interrupt_enable;
+ /* Bank can generate an interrupt. */
+ bool interrupt_capable;
+ /* Value upon which threshold interrupt is generated. */
+ u16 threshold_limit;
+ /* sysfs object */
+ struct kobject kobj;
+ /* List of threshold blocks within this block's MCA bank. */
+ struct list_head miscj;
+};
+
+struct threshold_bank {
+ struct kobject *kobj;
+ struct threshold_block *blocks;
+};
+
static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
/*
@@ -333,19 +356,6 @@ struct thresh_restart {
u16 old_limit;
};
-static inline bool is_shared_bank(int bank)
-{
- /*
- * Scalable MCA provides for only one core to have access to the MSRs of
- * a shared bank.
- */
- if (mce_flags.smca)
- return false;
-
- /* Bank 4 is for northbridge reporting and is thus shared */
- return (bank == 4);
-}
-
static const char *bank4_names(const struct threshold_block *b)
{
switch (b->address) {
@@ -381,7 +391,7 @@ static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits)
return msr_high_bits & BIT(28);
}
-static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
+static bool lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
{
int msr = (hi & MASK_LVTOFF_HI) >> 20;
@@ -389,7 +399,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
"for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
b->bank, b->block, b->address, hi, lo);
- return 0;
+ return false;
}
if (apic != msr) {
@@ -399,15 +409,15 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
* was set is reserved. Return early here:
*/
if (mce_flags.smca)
- return 0;
+ return false;
pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
"for bank %d, block %d (MSR%08X=0x%x%08x)\n",
b->cpu, apic, b->bank, b->block, b->address, hi, lo);
- return 0;
+ return false;
}
- return 1;
+ return true;
};
/* Reprogram MCx_MISC MSR behind this threshold bank. */
@@ -1198,35 +1208,10 @@ out_free:
return err;
}
-static int __threshold_add_blocks(struct threshold_bank *b)
-{
- struct list_head *head = &b->blocks->miscj;
- struct threshold_block *pos = NULL;
- struct threshold_block *tmp = NULL;
- int err = 0;
-
- err = kobject_add(&b->blocks->kobj, b->kobj, b->blocks->kobj.name);
- if (err)
- return err;
-
- list_for_each_entry_safe(pos, tmp, head, miscj) {
-
- err = kobject_add(&pos->kobj, b->kobj, pos->kobj.name);
- if (err) {
- list_for_each_entry_safe_reverse(pos, tmp, head, miscj)
- kobject_del(&pos->kobj);
-
- return err;
- }
- }
- return err;
-}
-
static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
unsigned int bank)
{
struct device *dev = this_cpu_read(mce_device);
- struct amd_northbridge *nb = NULL;
struct threshold_bank *b = NULL;
const char *name = get_name(cpu, bank, NULL);
int err = 0;
@@ -1234,26 +1219,6 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
if (!dev)
return -ENODEV;
- if (is_shared_bank(bank)) {
- nb = node_to_amd_nb(topology_amd_node_id(cpu));
-
- /* threshold descriptor already initialized on this node? */
- if (nb && nb->bank4) {
- /* yes, use it */
- b = nb->bank4;
- err = kobject_add(b->kobj, &dev->kobj, name);
- if (err)
- goto out;
-
- bp[bank] = b;
- refcount_inc(&b->cpus);
-
- err = __threshold_add_blocks(b);
-
- goto out;
- }
- }
-
b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL);
if (!b) {
err = -ENOMEM;
@@ -1267,17 +1232,6 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
goto out_free;
}
- if (is_shared_bank(bank)) {
- b->shared = 1;
- refcount_set(&b->cpus, 1);
-
- /* nb is already initialized, see above */
- if (nb) {
- WARN_ON(nb->bank4);
- nb->bank4 = b;
- }
- }
-
err = allocate_threshold_blocks(cpu, b, bank, 0, mca_msr_reg(bank, MCA_MISC));
if (err)
goto out_kobj;
@@ -1310,40 +1264,11 @@ static void deallocate_threshold_blocks(struct threshold_bank *bank)
kobject_put(&bank->blocks->kobj);
}
-static void __threshold_remove_blocks(struct threshold_bank *b)
-{
- struct threshold_block *pos = NULL;
- struct threshold_block *tmp = NULL;
-
- kobject_put(b->kobj);
-
- list_for_each_entry_safe(pos, tmp, &b->blocks->miscj, miscj)
- kobject_put(b->kobj);
-}
-
static void threshold_remove_bank(struct threshold_bank *bank)
{
- struct amd_northbridge *nb;
-
if (!bank->blocks)
goto out_free;
- if (!bank->shared)
- goto out_dealloc;
-
- if (!refcount_dec_and_test(&bank->cpus)) {
- __threshold_remove_blocks(bank);
- return;
- } else {
- /*
- * The last CPU on this node using the shared bank is going
- * away, remove that bank now.
- */
- nb = node_to_amd_nb(topology_amd_node_id(smp_processor_id()));
- nb->bank4 = NULL;
- }
-
-out_dealloc:
deallocate_threshold_blocks(bank);
out_free:
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 7fb5556a0b53..0dc00c9894c7 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -151,7 +151,7 @@ EXPORT_PER_CPU_SYMBOL_GPL(injectm);
void mce_log(struct mce_hw_err *err)
{
- if (!mce_gen_pool_add(err))
+ if (mce_gen_pool_add(err))
irq_work_queue(&mce_irq_work);
}
EXPORT_SYMBOL_GPL(mce_log);
@@ -492,10 +492,10 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
}
}
-int mce_available(struct cpuinfo_x86 *c)
+bool mce_available(struct cpuinfo_x86 *c)
{
if (mca_cfg.disabled)
- return 0;
+ return false;
return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA);
}
@@ -1778,7 +1778,7 @@ static void mce_timer_delete_all(void)
* Can be called from interrupt context, but not from machine check/NMI
* context.
*/
-int mce_notify_irq(void)
+bool mce_notify_irq(void)
{
/* Not more than two messages every minute */
static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
@@ -1789,9 +1789,9 @@ int mce_notify_irq(void)
if (__ratelimit(&ratelimit))
pr_info(HW_ERR "Machine check events logged\n");
- return 1;
+ return true;
}
- return 0;
+ return false;
}
EXPORT_SYMBOL_GPL(mce_notify_irq);
@@ -1910,101 +1910,120 @@ static void __mcheck_cpu_check_banks(void)
}
}
-/* Add per CPU specific workarounds here */
-static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
+static void apply_quirks_amd(struct cpuinfo_x86 *c)
{
struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
- struct mca_config *cfg = &mca_cfg;
-
- if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
- pr_info("unknown CPU type - not enabling MCE support\n");
- return -EOPNOTSUPP;
- }
/* This should be disabled by the BIOS, but isn't always */
- if (c->x86_vendor == X86_VENDOR_AMD) {
- if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
- /*
- * disable GART TBL walk error reporting, which
- * trips off incorrectly with the IOMMU & 3ware
- * & Cerberus:
- */
- clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
- }
- if (c->x86 < 0x11 && cfg->bootlog < 0) {
- /*
- * Lots of broken BIOS around that don't clear them
- * by default and leave crap in there. Don't log:
- */
- cfg->bootlog = 0;
- }
+ if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
/*
- * Various K7s with broken bank 0 around. Always disable
- * by default.
+ * disable GART TBL walk error reporting, which
+ * trips off incorrectly with the IOMMU & 3ware
+ * & Cerberus:
*/
- if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0)
- mce_banks[0].ctl = 0;
+ clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
+ }
+ if (c->x86 < 0x11 && mca_cfg.bootlog < 0) {
/*
- * overflow_recov is supported for F15h Models 00h-0fh
- * even though we don't have a CPUID bit for it.
+ * Lots of broken BIOS around that don't clear them
+ * by default and leave crap in there. Don't log:
*/
- if (c->x86 == 0x15 && c->x86_model <= 0xf)
- mce_flags.overflow_recov = 1;
+ mca_cfg.bootlog = 0;
+ }
- if (c->x86 >= 0x17 && c->x86 <= 0x1A)
- mce_flags.zen_ifu_quirk = 1;
+ /*
+ * Various K7s with broken bank 0 around. Always disable
+ * by default.
+ */
+ if (c->x86 == 6 && this_cpu_read(mce_num_banks))
+ mce_banks[0].ctl = 0;
- }
+ /*
+ * overflow_recov is supported for F15h Models 00h-0fh
+ * even though we don't have a CPUID bit for it.
+ */
+ if (c->x86 == 0x15 && c->x86_model <= 0xf)
+ mce_flags.overflow_recov = 1;
- if (c->x86_vendor == X86_VENDOR_INTEL) {
- /*
- * SDM documents that on family 6 bank 0 should not be written
- * because it aliases to another special BIOS controlled
- * register.
- * But it's not aliased anymore on model 0x1a+
- * Don't ignore bank 0 completely because there could be a
- * valid event later, merely don't write CTL0.
- */
+ if (c->x86 >= 0x17 && c->x86 <= 0x1A)
+ mce_flags.zen_ifu_quirk = 1;
+}
- if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0)
- mce_banks[0].init = false;
+static void apply_quirks_intel(struct cpuinfo_x86 *c)
+{
+ struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
- /*
- * All newer Intel systems support MCE broadcasting. Enable
- * synchronization with a one second timeout.
- */
- if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) &&
- cfg->monarch_timeout < 0)
- cfg->monarch_timeout = USEC_PER_SEC;
+ /* Older CPUs (prior to family 6) don't need quirks. */
+ if (c->x86_vfm < INTEL_PENTIUM_PRO)
+ return;
- /*
- * There are also broken BIOSes on some Pentium M and
- * earlier systems:
- */
- if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0)
- cfg->bootlog = 0;
+ /*
+ * SDM documents that on family 6 bank 0 should not be written
+ * because it aliases to another special BIOS controlled
+ * register.
+ * But it's not aliased anymore on model 0x1a+
+ * Don't ignore bank 0 completely because there could be a
+ * valid event later, merely don't write CTL0.
+ */
+ if (c->x86_vfm < INTEL_NEHALEM_EP && this_cpu_read(mce_num_banks))
+ mce_banks[0].init = false;
- if (c->x86_vfm == INTEL_SANDYBRIDGE_X)
- mce_flags.snb_ifu_quirk = 1;
+ /*
+ * All newer Intel systems support MCE broadcasting. Enable
+ * synchronization with a one second timeout.
+ */
+ if (c->x86_vfm >= INTEL_CORE_YONAH && mca_cfg.monarch_timeout < 0)
+ mca_cfg.monarch_timeout = USEC_PER_SEC;
- /*
- * Skylake, Cascacde Lake and Cooper Lake require a quirk on
- * rep movs.
- */
- if (c->x86_vfm == INTEL_SKYLAKE_X)
- mce_flags.skx_repmov_quirk = 1;
+ /*
+ * There are also broken BIOSes on some Pentium M and
+ * earlier systems:
+ */
+ if (c->x86_vfm < INTEL_CORE_YONAH && mca_cfg.bootlog < 0)
+ mca_cfg.bootlog = 0;
+
+ if (c->x86_vfm == INTEL_SANDYBRIDGE_X)
+ mce_flags.snb_ifu_quirk = 1;
+
+ /*
+ * Skylake, Cascacde Lake and Cooper Lake require a quirk on
+ * rep movs.
+ */
+ if (c->x86_vfm == INTEL_SKYLAKE_X)
+ mce_flags.skx_repmov_quirk = 1;
+}
+
+static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c)
+{
+ /*
+ * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+ * synchronization with a one second timeout.
+ */
+ if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+ if (mca_cfg.monarch_timeout < 0)
+ mca_cfg.monarch_timeout = USEC_PER_SEC;
}
+}
- if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
- /*
- * All newer Zhaoxin CPUs support MCE broadcasting. Enable
- * synchronization with a one second timeout.
- */
- if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
- if (cfg->monarch_timeout < 0)
- cfg->monarch_timeout = USEC_PER_SEC;
- }
+/* Add per CPU specific workarounds here */
+static bool __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
+{
+ struct mca_config *cfg = &mca_cfg;
+
+ switch (c->x86_vendor) {
+ case X86_VENDOR_UNKNOWN:
+ pr_info("unknown CPU type - not enabling MCE support\n");
+ return false;
+ case X86_VENDOR_AMD:
+ apply_quirks_amd(c);
+ break;
+ case X86_VENDOR_INTEL:
+ apply_quirks_intel(c);
+ break;
+ case X86_VENDOR_ZHAOXIN:
+ apply_quirks_zhaoxin(c);
+ break;
}
if (cfg->monarch_timeout < 0)
@@ -2012,28 +2031,28 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
if (cfg->bootlog != 0)
cfg->panic_timeout = 30;
- return 0;
+ return true;
}
-static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
+static bool __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
{
if (c->x86 != 5)
- return 0;
+ return false;
switch (c->x86_vendor) {
case X86_VENDOR_INTEL:
intel_p5_mcheck_init(c);
mce_flags.p5 = 1;
- return 1;
+ return true;
case X86_VENDOR_CENTAUR:
winchip_mcheck_init(c);
mce_flags.winchip = 1;
- return 1;
+ return true;
default:
- return 0;
+ return false;
}
- return 0;
+ return false;
}
/*
@@ -2099,13 +2118,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
mce_intel_feature_init(c);
break;
- case X86_VENDOR_AMD: {
- mce_amd_feature_init(c);
- break;
- }
-
+ case X86_VENDOR_AMD:
case X86_VENDOR_HYGON:
- mce_hygon_feature_init(c);
+ mce_amd_feature_init(c);
break;
case X86_VENDOR_CENTAUR:
@@ -2279,12 +2294,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
__mcheck_cpu_cap_init();
- if (__mcheck_cpu_apply_quirks(c) < 0) {
+ if (!__mcheck_cpu_apply_quirks(c)) {
mca_cfg.disabled = 1;
return;
}
- if (mce_gen_pool_init()) {
+ if (!mce_gen_pool_init()) {
mca_cfg.disabled = 1;
pr_emerg("Couldn't allocate MCE records pool!\n");
return;
diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index d0be6dda0c14..3ca9c007a666 100644
--- a/arch/x86/kernel/cpu/mce/genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -94,64 +94,63 @@ bool mce_gen_pool_empty(void)
return llist_empty(&mce_event_llist);
}
-int mce_gen_pool_add(struct mce_hw_err *err)
+bool mce_gen_pool_add(struct mce_hw_err *err)
{
struct mce_evt_llist *node;
if (filter_mce(&err->m))
- return -EINVAL;
+ return false;
if (!mce_evt_pool)
- return -EINVAL;
+ return false;
node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node));
if (!node) {
pr_warn_ratelimited("MCE records pool full!\n");
- return -ENOMEM;
+ return false;
}
memcpy(&node->err, err, sizeof(*err));
llist_add(&node->llnode, &mce_event_llist);
- return 0;
+ return true;
}
-static int mce_gen_pool_create(void)
+static bool mce_gen_pool_create(void)
{
int mce_numrecords, mce_poolsz, order;
struct gen_pool *gpool;
- int ret = -ENOMEM;
void *mce_pool;
order = order_base_2(sizeof(struct mce_evt_llist));
gpool = gen_pool_create(order, -1);
if (!gpool)
- return ret;
+ return false;
mce_numrecords = max(MCE_MIN_ENTRIES, num_possible_cpus() * MCE_PER_CPU);
mce_poolsz = mce_numrecords * (1 << order);
mce_pool = kmalloc(mce_poolsz, GFP_KERNEL);
if (!mce_pool) {
gen_pool_destroy(gpool);
- return ret;
+ return false;
}
- ret = gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1);
- if (ret) {
+
+ if (gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1)) {
gen_pool_destroy(gpool);
kfree(mce_pool);
- return ret;
+ return false;
}
mce_evt_pool = gpool;
- return ret;
+ return true;
}
-int mce_gen_pool_init(void)
+bool mce_gen_pool_init(void)
{
/* Just init mce_gen_pool once. */
if (mce_evt_pool)
- return 0;
+ return true;
return mce_gen_pool_create();
}
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index b3cd2c61b11d..f863df0ff42c 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -75,12 +75,12 @@ static u16 cmci_threshold[MAX_NR_BANKS];
*/
#define CMCI_STORM_THRESHOLD 32749
-static int cmci_supported(int *banks)
+static bool cmci_supported(int *banks)
{
u64 cap;
if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce)
- return 0;
+ return false;
/*
* Vendor check is not strictly needed, but the initial
@@ -89,10 +89,11 @@ static int cmci_supported(int *banks)
*/
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
- return 0;
+ return false;
if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
- return 0;
+ return false;
+
rdmsrl(MSR_IA32_MCG_CAP, cap);
*banks = min_t(unsigned, MAX_NR_BANKS, cap & MCG_BANKCNT_MASK);
return !!(cap & MCG_CMCI_P);
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 84f810598231..95a504ece43e 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -31,8 +31,8 @@ struct mce_evt_llist {
void mce_gen_pool_process(struct work_struct *__unused);
bool mce_gen_pool_empty(void);
-int mce_gen_pool_add(struct mce_hw_err *err);
-int mce_gen_pool_init(void);
+bool mce_gen_pool_add(struct mce_hw_err *err);
+bool mce_gen_pool_init(void);
struct llist_node *mce_gen_pool_prepare_records(void);
int mce_severity(struct mce *a, struct pt_regs *regs, char **msg, bool is_excp);
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index 89e31e1e5c9c..f4a007616468 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -90,7 +90,7 @@ void cmci_storm_end(unsigned int bank)
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))
+ if (!--storm->stormy_bank_count)
mce_timer_kick(false);
}
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index fb5d0c67fbab..a5dac7f3c0a0 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -283,13 +283,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
* exceed the per-family maximum). @sh_psize is the size read from the section
* header.
*/
-static unsigned int __verify_patch_size(u32 sh_psize, size_t buf_size)
+static bool __verify_patch_size(u32 sh_psize, size_t buf_size)
{
u8 family = x86_family(bsp_cpuid_1_eax);
u32 max_size;
if (family >= 0x15)
- return min_t(u32, sh_psize, buf_size);
+ goto ret;
#define F1XH_MPB_MAX_SIZE 2048
#define F14H_MPB_MAX_SIZE 1824
@@ -303,13 +303,15 @@ static unsigned int __verify_patch_size(u32 sh_psize, size_t buf_size)
break;
default:
WARN(1, "%s: WTF family: 0x%x\n", __func__, family);
- return 0;
+ return false;
}
- if (sh_psize > min_t(u32, buf_size, max_size))
- return 0;
+ if (sh_psize > max_size)
+ return false;
- return sh_psize;
+ret:
+ /* Working with the whole buffer so < is ok. */
+ return sh_psize <= buf_size;
}
/*
@@ -324,7 +326,6 @@ static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size)
{
u8 family = x86_family(bsp_cpuid_1_eax);
struct microcode_header_amd *mc_hdr;
- unsigned int ret;
u32 sh_psize;
u16 proc_id;
u8 patch_fam;
@@ -348,8 +349,7 @@ static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size)
return -1;
}
- ret = __verify_patch_size(sh_psize, buf_size);
- if (!ret) {
+ if (!__verify_patch_size(sh_psize, buf_size)) {
pr_debug("Per-family patch size mismatch.\n");
return -1;
}
@@ -381,8 +381,8 @@ static bool mc_patch_matches(struct microcode_amd *mc, u16 eq_id)
/*
* This scans the ucode blob for the proper container as we can have multiple
- * containers glued together. Returns the equivalence ID from the equivalence
- * table or 0 if none found.
+ * containers glued together.
+ *
* Returns the amount of bytes consumed while scanning. @desc contains all the
* data we're going to use in later stages of the application.
*/
@@ -484,7 +484,7 @@ static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
}
}
-static int __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
+static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
{
unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
u32 rev, dummy;
@@ -508,9 +508,9 @@ static int __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
if (rev != mc->hdr.patch_id)
- return -1;
+ return false;
- return 0;
+ return true;
}
/*
@@ -528,13 +528,12 @@ static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size)
{
struct cont_desc desc = { 0 };
struct microcode_amd *mc;
- bool ret = false;
scan_containers(ucode, size, &desc);
mc = desc.mc;
if (!mc)
- return ret;
+ return false;
/*
* Allow application of the same revision to pick up SMT-specific
@@ -542,9 +541,9 @@ static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size)
* up-to-date.
*/
if (old_rev > mc->hdr.patch_id)
- return ret;
+ return false;
- return !__apply_microcode_amd(mc, desc.psize);
+ return __apply_microcode_amd(mc, desc.psize);
}
static bool get_builtin_microcode(struct cpio_data *cp)
@@ -569,14 +568,19 @@ static bool get_builtin_microcode(struct cpio_data *cp)
return false;
}
-static void __init find_blobs_in_containers(struct cpio_data *ret)
+static bool __init find_blobs_in_containers(struct cpio_data *ret)
{
struct cpio_data cp;
+ bool found;
if (!get_builtin_microcode(&cp))
cp = find_microcode_in_initrd(ucode_path);
- *ret = cp;
+ found = cp.data && cp.size;
+ if (found)
+ *ret = cp;
+
+ return found;
}
void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
@@ -591,8 +595,7 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
/* Needed in load_microcode_amd() */
ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
- find_blobs_in_containers(&cp);
- if (!(cp.data && cp.size))
+ if (!find_blobs_in_containers(&cp))
return;
if (early_apply_microcode(ed->old_rev, cp.data, cp.size))
@@ -612,8 +615,7 @@ static int __init save_microcode_in_initrd(void)
if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
return 0;
- find_blobs_in_containers(&cp);
- if (!(cp.data && cp.size))
+ if (!find_blobs_in_containers(&cp))
return -EINVAL;
scan_containers(cp.data, cp.size, &desc);
@@ -760,7 +762,7 @@ void reload_ucode_amd(unsigned int cpu)
rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
if (rev < mc->hdr.patch_id) {
- if (!__apply_microcode_amd(mc, p->size))
+ if (__apply_microcode_amd(mc, p->size))
pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id);
}
}
@@ -813,7 +815,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
goto out;
}
- if (__apply_microcode_amd(mc_amd, p->size)) {
+ if (!__apply_microcode_amd(mc_amd, p->size)) {
pr_err("CPU%d: update failed for patch_level=0x%08x\n",
cpu, mc_amd->hdr.patch_id);
return UCODE_ERROR;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index d18078834ded..f285757618fc 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -19,7 +19,7 @@
#include <linux/random.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
#include <asm/desc.h>
#include <asm/idtentry.h>
@@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
hyperv_cleanup();
}
#endif /* CONFIG_CRASH_DUMP */
+
+static u64 hv_ref_counter_at_suspend;
+static void (*old_save_sched_clock_state)(void);
+static void (*old_restore_sched_clock_state)(void);
+
+/*
+ * Hyper-V clock counter resets during hibernation. Save and restore clock
+ * offset during suspend/resume, while also considering the time passed
+ * before suspend. This is to make sure that sched_clock using hv tsc page
+ * based clocksource, proceeds from where it left off during suspend and
+ * it shows correct time for the timestamps of kernel messages after resume.
+ */
+static void save_hv_clock_tsc_state(void)
+{
+ hv_ref_counter_at_suspend = hv_read_reference_counter();
+}
+
+static void restore_hv_clock_tsc_state(void)
+{
+ /*
+ * Adjust the offsets used by hv tsc clocksource to
+ * account for the time spent before hibernation.
+ * adjusted value = reference counter (time) at suspend
+ * - reference counter (time) now.
+ */
+ hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter());
+}
+
+/*
+ * Functions to override save_sched_clock_state and restore_sched_clock_state
+ * functions of x86_platform. The Hyper-V clock counter is reset during
+ * suspend-resume and the offset used to measure time needs to be
+ * corrected, post resume.
+ */
+static void hv_save_sched_clock_state(void)
+{
+ old_save_sched_clock_state();
+ save_hv_clock_tsc_state();
+}
+
+static void hv_restore_sched_clock_state(void)
+{
+ restore_hv_clock_tsc_state();
+ old_restore_sched_clock_state();
+}
+
+static void __init x86_setup_ops_for_tsc_pg_clock(void)
+{
+ if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+ return;
+
+ old_save_sched_clock_state = x86_platform.save_sched_clock_state;
+ x86_platform.save_sched_clock_state = hv_save_sched_clock_state;
+
+ old_restore_sched_clock_state = x86_platform.restore_sched_clock_state;
+ x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state;
+}
#endif /* CONFIG_HYPERV */
static uint32_t __init ms_hyperv_platform(void)
@@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void)
/* Register Hyper-V specific clocksource */
hv_init_clocksource();
+ x86_setup_ops_for_tsc_pg_clock();
hv_vtl_init_platform();
#endif
/*
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7b29ebda024f..2fdfda2b60e4 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -423,7 +423,7 @@ void __init mtrr_copy_map(void)
}
/**
- * mtrr_overwrite_state - set static MTRR state
+ * guest_force_mtrr_state - set static MTRR state for a guest
*
* Used to set MTRR state via different means (e.g. with data obtained from
* a hypervisor).
@@ -436,8 +436,8 @@ void __init mtrr_copy_map(void)
* @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)
+void guest_force_mtrr_state(struct mtrr_var_range *var, unsigned int num_var,
+ mtrr_type def_type)
{
unsigned int i;
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index 989d368be04f..ecbda0341a8a 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -625,7 +625,7 @@ void mtrr_save_state(void)
static int __init mtrr_init_finalize(void)
{
/*
- * Map might exist if mtrr_overwrite_state() has been called or if
+ * Map might exist if guest_force_mtrr_state() has been called or if
* mtrr_enabled() returns true.
*/
mtrr_copy_map();
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index b681c2e07dbf..3d1735ed8d1f 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -234,7 +234,9 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD;
else
r->membw.throttle_mode = THREAD_THROTTLE_MAX;
- thread_throttle_mode_init();
+
+ resctrl_file_fflags_init("thread_throttle_mode",
+ RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
r->alloc_capable = true;
@@ -961,6 +963,11 @@ static __init bool get_rdt_mon_resources(void)
if (!rdt_mon_features)
return false;
+ if (is_mbm_local_enabled())
+ mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+ else if (is_mbm_total_enabled())
+ mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+
return !rdt_get_mon_l3_config(r);
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 200d89a64027..536351159cc2 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -518,6 +518,76 @@ static int smp_mon_event_count(void *arg)
return 0;
}
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct rdtgroup *rdtgrp;
+ int ret = 0;
+
+ /* Valid input requires a trailing newline */
+ if (nbytes == 0 || buf[nbytes - 1] != '\n')
+ return -EINVAL;
+ buf[nbytes - 1] = '\0';
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (!rdtgrp) {
+ rdtgroup_kn_unlock(of->kn);
+ return -ENOENT;
+ }
+ rdt_last_cmd_clear();
+
+ if (!strcmp(buf, "mbm_local_bytes")) {
+ if (is_mbm_local_enabled())
+ rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+ else
+ ret = -EINVAL;
+ } else if (!strcmp(buf, "mbm_total_bytes")) {
+ if (is_mbm_total_enabled())
+ rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+ else
+ ret = -EINVAL;
+ } else {
+ ret = -EINVAL;
+ }
+
+ if (ret)
+ rdt_last_cmd_printf("Unsupported event id '%s'\n", buf);
+
+ rdtgroup_kn_unlock(of->kn);
+
+ return ret ?: nbytes;
+}
+
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+ struct seq_file *s, void *v)
+{
+ struct rdtgroup *rdtgrp;
+ int ret = 0;
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+ if (rdtgrp) {
+ switch (rdtgrp->mba_mbps_event) {
+ case QOS_L3_MBM_LOCAL_EVENT_ID:
+ seq_puts(s, "mbm_local_bytes\n");
+ break;
+ case QOS_L3_MBM_TOTAL_EVENT_ID:
+ seq_puts(s, "mbm_total_bytes\n");
+ break;
+ default:
+ pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event);
+ ret = -EINVAL;
+ break;
+ }
+ } else {
+ ret = -ENOENT;
+ }
+
+ rdtgroup_kn_unlock(of->kn);
+
+ return ret;
+}
+
void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
cpumask_t *cpumask, int evtid, int first)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 955999aecfca..20c898f09b7e 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -283,6 +283,7 @@ struct pseudo_lock_region {
* monitor only or ctrl_mon group
* @mon: mongroup related data
* @mode: mode of resource group
+ * @mba_mbps_event: input monitoring event id when mba_sc is enabled
* @plr: pseudo-locked region
*/
struct rdtgroup {
@@ -295,6 +296,7 @@ struct rdtgroup {
enum rdt_group_type type;
struct mongroup mon;
enum rdtgrp_mode mode;
+ enum resctrl_event_id mba_mbps_event;
struct pseudo_lock_region *plr;
};
@@ -508,6 +510,7 @@ extern struct mutex rdtgroup_mutex;
extern struct rdt_hw_resource rdt_resources_all[];
extern struct rdtgroup rdtgroup_default;
extern struct dentry *debugfs_resctrl;
+extern enum resctrl_event_id mba_mbps_default_event;
enum resctrl_res_level {
RDT_RESOURCE_L3,
@@ -607,6 +610,10 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off);
int rdtgroup_schemata_show(struct kernfs_open_file *of,
struct seq_file *s, void *v);
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off);
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+ struct seq_file *s, void *v);
bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
unsigned long cbm, int closid, bool exclusive);
unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
@@ -647,10 +654,8 @@ void cqm_handle_limbo(struct work_struct *work);
bool has_busy_rmid(struct rdt_mon_domain *d);
void __check_limbo(struct rdt_mon_domain *d, bool force_free);
void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
-void __init thread_throttle_mode_init(void);
-void __init mbm_config_rftype_init(const char *config);
+void resctrl_file_fflags_init(const char *config, unsigned long fflags);
void rdt_staged_configs_clear(void);
bool closid_allocated(unsigned int closid);
int resctrl_find_cleanest_closid(void);
-
#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 5fcb3d635d91..94a1d9780461 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -663,9 +663,12 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
*/
static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
{
- u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
- struct mbm_state *m = &rr->d->mbm_local[idx];
u64 cur_bw, bytes, cur_bytes;
+ struct mbm_state *m;
+
+ m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+ if (WARN_ON_ONCE(!m))
+ return;
cur_bytes = rr->val;
bytes = cur_bytes - m->prev_bw_bytes;
@@ -752,20 +755,20 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
u32 closid, rmid, cur_msr_val, new_msr_val;
struct mbm_state *pmbm_data, *cmbm_data;
struct rdt_ctrl_domain *dom_mba;
+ enum resctrl_event_id evt_id;
struct rdt_resource *r_mba;
- u32 cur_bw, user_bw, idx;
struct list_head *head;
struct rdtgroup *entry;
-
- if (!is_mbm_local_enabled())
- return;
+ u32 cur_bw, user_bw;
r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+ evt_id = rgrp->mba_mbps_event;
closid = rgrp->closid;
rmid = rgrp->mon.rmid;
- idx = resctrl_arch_rmid_idx_encode(closid, rmid);
- pmbm_data = &dom_mbm->mbm_local[idx];
+ pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
+ if (WARN_ON_ONCE(!pmbm_data))
+ return;
dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
if (!dom_mba) {
@@ -784,7 +787,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
*/
head = &rgrp->mon.crdtgrp_list;
list_for_each_entry(entry, head, mon.crdtgrp_list) {
- cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+ cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
+ if (WARN_ON_ONCE(!cmbm_data))
+ return;
cur_bw += cmbm_data->prev_bw;
}
@@ -813,54 +818,45 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
}
-static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
- u32 closid, u32 rmid)
+static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
+ u32 closid, u32 rmid, enum resctrl_event_id evtid)
{
struct rmid_read rr = {0};
rr.r = r;
rr.d = d;
+ rr.evtid = evtid;
+ rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+ if (IS_ERR(rr.arch_mon_ctx)) {
+ pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+ PTR_ERR(rr.arch_mon_ctx));
+ return;
+ }
+
+ __mon_event_count(closid, rmid, &rr);
/*
- * This is protected from concurrent reads from user
- * as both the user and we hold the global mutex.
+ * If the software controller is enabled, compute the
+ * bandwidth for this event id.
*/
- if (is_mbm_total_enabled()) {
- rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
- rr.val = 0;
- rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
- if (IS_ERR(rr.arch_mon_ctx)) {
- pr_warn_ratelimited("Failed to allocate monitor context: %ld",
- PTR_ERR(rr.arch_mon_ctx));
- return;
- }
-
- __mon_event_count(closid, rmid, &rr);
+ if (is_mba_sc(NULL))
+ mbm_bw_count(closid, rmid, &rr);
- resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
- }
- if (is_mbm_local_enabled()) {
- rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
- rr.val = 0;
- rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
- if (IS_ERR(rr.arch_mon_ctx)) {
- pr_warn_ratelimited("Failed to allocate monitor context: %ld",
- PTR_ERR(rr.arch_mon_ctx));
- return;
- }
-
- __mon_event_count(closid, rmid, &rr);
+ resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+}
- /*
- * Call the MBA software controller only for the
- * control groups and when user has enabled
- * the software controller explicitly.
- */
- if (is_mba_sc(NULL))
- mbm_bw_count(closid, rmid, &rr);
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
+ u32 closid, u32 rmid)
+{
+ /*
+ * This is protected from concurrent reads from user as both
+ * the user and overflow handler hold the global mutex.
+ */
+ if (is_mbm_total_enabled())
+ mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
- resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
- }
+ if (is_mbm_local_enabled())
+ mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
}
/*
@@ -1224,11 +1220,13 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
mbm_total_event.configurable = true;
- mbm_config_rftype_init("mbm_total_bytes_config");
+ resctrl_file_fflags_init("mbm_total_bytes_config",
+ RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
}
if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
mbm_local_event.configurable = true;
- mbm_config_rftype_init("mbm_local_bytes_config");
+ resctrl_file_fflags_init("mbm_local_bytes_config",
+ RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
}
}
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 972e6b6b0481..42cc162f7fc9 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -459,7 +459,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
* increase likelihood that allocated cache portion will be filled
* with associated memory.
*/
- native_wbinvd();
+ wbinvd();
/*
* Always called with interrupts enabled. By disabling interrupts
@@ -1205,20 +1205,14 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
plr->cpu = cpu;
if (sel == 1)
- thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
- cpu_to_node(cpu),
- "pseudo_lock_measure/%u",
- cpu);
+ thread = kthread_run_on_cpu(measure_cycles_lat_fn, plr,
+ cpu, "pseudo_lock_measure/%u");
else if (sel == 2)
- thread = kthread_create_on_node(measure_l2_residency, plr,
- cpu_to_node(cpu),
- "pseudo_lock_measure/%u",
- cpu);
+ thread = kthread_run_on_cpu(measure_l2_residency, plr,
+ cpu, "pseudo_lock_measure/%u");
else if (sel == 3)
- thread = kthread_create_on_node(measure_l3_residency, plr,
- cpu_to_node(cpu),
- "pseudo_lock_measure/%u",
- cpu);
+ thread = kthread_run_on_cpu(measure_l3_residency, plr,
+ cpu, "pseudo_lock_measure/%u");
else
goto out;
@@ -1226,8 +1220,6 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
ret = PTR_ERR(thread);
goto out;
}
- kthread_bind(thread, cpu);
- wake_up_process(thread);
ret = wait_event_interruptible(plr->lock_thread_wq,
plr->thread_done == 1);
@@ -1315,18 +1307,14 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
plr->thread_done = 0;
- thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
- cpu_to_node(plr->cpu),
- "pseudo_lock/%u", plr->cpu);
+ thread = kthread_run_on_cpu(pseudo_lock_fn, rdtgrp,
+ plr->cpu, "pseudo_lock/%u");
if (IS_ERR(thread)) {
ret = PTR_ERR(thread);
rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
goto out_cstates;
}
- kthread_bind(thread, plr->cpu);
- wake_up_process(thread);
-
ret = wait_event_interruptible(plr->lock_thread_wq,
plr->thread_done == 1);
if (ret < 0) {
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index d906a1cd8491..6419e04d8a7b 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -65,6 +65,15 @@ static void rdtgroup_destroy_root(void);
struct dentry *debugfs_resctrl;
+/*
+ * Memory bandwidth monitoring event to use for the default CTRL_MON group
+ * and each new CTRL_MON group created by the user. Only relevant when
+ * the filesystem is mounted with the "mba_MBps" option so it does not
+ * matter that it remains uninitialized on systems that do not support
+ * the "mba_MBps" option.
+ */
+enum resctrl_event_id mba_mbps_default_event;
+
static bool resctrl_debug;
void rdt_last_cmd_clear(void)
@@ -1942,6 +1951,13 @@ static struct rftype res_common_files[] = {
.fflags = RFTYPE_CTRL_BASE,
},
{
+ .name = "mba_MBps_event",
+ .mode = 0644,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .write = rdtgroup_mba_mbps_event_write,
+ .seq_show = rdtgroup_mba_mbps_event_show,
+ },
+ {
.name = "mode",
.mode = 0644,
.kf_ops = &rdtgroup_kf_single_ops,
@@ -2020,24 +2036,13 @@ static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
return NULL;
}
-void __init thread_throttle_mode_init(void)
-{
- struct rftype *rft;
-
- rft = rdtgroup_get_rftype_by_name("thread_throttle_mode");
- if (!rft)
- return;
-
- rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB;
-}
-
-void __init mbm_config_rftype_init(const char *config)
+void resctrl_file_fflags_init(const char *config, unsigned long fflags)
{
struct rftype *rft;
rft = rdtgroup_get_rftype_by_name(config);
if (rft)
- rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE;
+ rft->fflags = fflags;
}
/**
@@ -2343,7 +2348,7 @@ static bool supports_mba_mbps(void)
struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
- return (is_mbm_local_enabled() &&
+ return (is_mbm_enabled() &&
r->alloc_capable && is_mba_linear() &&
r->ctrl_scope == rmbm->mon_scope);
}
@@ -2357,6 +2362,7 @@ static int set_mba_sc(bool mba_sc)
struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
u32 num_closid = resctrl_arch_get_num_closid(r);
struct rdt_ctrl_domain *d;
+ unsigned long fflags;
int i;
if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
@@ -2364,11 +2370,16 @@ static int set_mba_sc(bool mba_sc)
r->membw.mba_sc = mba_sc;
+ rdtgroup_default.mba_mbps_event = mba_mbps_default_event;
+
list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
for (i = 0; i < num_closid; i++)
d->mbps_val[i] = MBA_MAX_MBPS;
}
+ fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0;
+ resctrl_file_fflags_init("mba_MBps_event", fflags);
+
return 0;
}
@@ -2768,7 +2779,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
ctx->enable_cdpl2 = true;
return 0;
case Opt_mba_mbps:
- msg = "mba_MBps requires local MBM and linear scale MBA at L3 scope";
+ msg = "mba_MBps requires MBM and linear scale MBA at L3 scope";
if (!supports_mba_mbps())
return invalfc(fc, msg);
ctx->enable_mba_mbps = true;
@@ -3622,6 +3633,8 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
rdt_last_cmd_puts("kernfs subdir error\n");
goto out_del_list;
}
+ if (is_mba_sc(NULL))
+ rdtgrp->mba_mbps_event = mba_mbps_default_event;
}
goto out_unlock;
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index b2e313ea17bf..01456236a6dd 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -428,7 +428,7 @@ void __init topology_apply_cmdline_limits_early(void)
{
unsigned int possible = nr_cpu_ids;
- /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' */
+ /* 'maxcpus=0' 'nosmp' 'nolapic' */
if (!setup_max_cpus || apic_is_disabled)
possible = 1;
diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c
index 8277c64f88db..b5a5e1411469 100644
--- a/arch/x86/kernel/cpu/topology_common.c
+++ b/arch/x86/kernel/cpu/topology_common.c
@@ -185,6 +185,7 @@ static void topo_set_ids(struct topo_scan *tscan, bool early)
if (!early) {
c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);
c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);
+ c->topo.logical_core_id = topology_get_logical_id(apicid, TOPO_CORE_DOMAIN);
}
/* Package relative core ID */