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/Makefile2
-rw-r--r--arch/x86/kernel/cpu/amd.c58
-rw-r--r--arch/x86/kernel/cpu/bugs.c397
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c (renamed from arch/x86/kernel/cpu/intel_cacheinfo.c)46
-rw-r--r--arch/x86/kernel/cpu/centaur.c53
-rw-r--r--arch/x86/kernel/cpu/common.c108
-rw-r--r--arch/x86/kernel/cpu/cpu.h12
-rw-r--r--arch/x86/kernel/cpu/intel.c40
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.c50
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.h18
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c24
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_monitor.c170
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_rdtgroup.c33
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c18
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c44
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c6
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c2
-rw-r--r--arch/x86/kernel/cpu/mtrr/Makefile2
-rw-r--r--arch/x86/kernel/cpu/mtrr/mtrr.c (renamed from arch/x86/kernel/cpu/mtrr/main.c)37
-rw-r--r--arch/x86/kernel/cpu/topology.c8
21 files changed, 966 insertions, 164 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a66229f51b12..7a40196967cb 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -17,7 +17,7 @@ KCOV_INSTRUMENT_perf_event.o := n
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_common.o := $(nostackp)
-obj-y := intel_cacheinfo.o scattered.o topology.o
+obj-y := cacheinfo.o scattered.o topology.o
obj-y += common.o
obj-y += rdrand.o
obj-y += match.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 12bc0a1139da..082d7875cef8 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,7 +9,9 @@
#include <linux/random.h>
#include <asm/processor.h>
#include <asm/apic.h>
+#include <asm/cacheinfo.h>
#include <asm/cpu.h>
+#include <asm/spec-ctrl.h>
#include <asm/smp.h>
#include <asm/pci-direct.h>
#include <asm/delay.h>
@@ -297,7 +299,6 @@ static int nearby_node(int apicid)
}
#endif
-#ifdef CONFIG_SMP
/*
* Fix up cpu_core_id for pre-F17h systems to be in the
* [0 .. cores_per_node - 1] range. Not really needed but
@@ -327,6 +328,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
/* get information required for multi-node processors */
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ int err;
u32 eax, ebx, ecx, edx;
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
@@ -345,21 +347,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
}
/*
- * We may have multiple LLCs if L3 caches exist, so check if we
- * have an L3 cache by looking at the L3 cache CPUID leaf.
+ * In case leaf B is available, use it to derive
+ * topology information.
*/
- if (cpuid_edx(0x80000006)) {
- if (c->x86 == 0x17) {
- /*
- * LLC is at the core complex level.
- * Core complex id is ApicId[3].
- */
- per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
- } else {
- /* LLC is at the node level. */
- per_cpu(cpu_llc_id, cpu) = node_id;
- }
- }
+ err = detect_extended_topology(c);
+ if (!err)
+ c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+
+ cacheinfo_amd_init_llc_id(c, cpu, node_id);
+
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
@@ -375,7 +371,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
legacy_fixup_core_id(c);
}
}
-#endif
/*
* On a AMD dual core setup the lower bits of the APIC id distinguish the cores.
@@ -383,7 +378,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
*/
static void amd_detect_cmp(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
@@ -394,17 +388,11 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
c->phys_proc_id = c->initial_apicid >> bits;
/* use socket ID also for last level cache */
per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
- amd_get_topology(c);
-#endif
}
u16 amd_get_nb_id(int cpu)
{
- u16 id = 0;
-#ifdef CONFIG_SMP
- id = per_cpu(cpu_llc_id, cpu);
-#endif
- return id;
+ return per_cpu(cpu_llc_id, cpu);
}
EXPORT_SYMBOL_GPL(amd_get_nb_id);
@@ -554,6 +542,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
rdmsrl(MSR_FAM10H_NODE_ID, value);
nodes_per_socket = ((value >> 3) & 7) + 1;
}
+
+ if (c->x86 >= 0x15 && c->x86 <= 0x17) {
+ unsigned int bit;
+
+ switch (c->x86) {
+ case 0x15: bit = 54; break;
+ case 0x16: bit = 33; break;
+ case 0x17: bit = 10; break;
+ default: return;
+ }
+ /*
+ * Try to cache the base value so further operations can
+ * avoid RMW. If that faults, do not enable SSBD.
+ */
+ if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+ setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
+ setup_force_cpu_cap(X86_FEATURE_SSBD);
+ x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
+ }
+ }
}
static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -791,6 +799,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
static void init_amd_zn(struct cpuinfo_x86 *c)
{
+ set_cpu_cap(c, X86_FEATURE_ZEN);
/*
* Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
* all up to and including B1.
@@ -842,6 +851,7 @@ static void init_amd(struct cpuinfo_x86 *c)
/* Multi core CPU? */
if (c->extended_cpuid_level >= 0x80000008) {
amd_detect_cmp(c);
+ amd_get_topology(c);
srat_detect_node(c);
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bfca937bdcc3..7416fc206b4a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,8 +12,10 @@
#include <linux/utsname.h>
#include <linux/cpu.h>
#include <linux/module.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
#include <asm/cmdline.h>
#include <asm/bugs.h>
#include <asm/processor.h>
@@ -27,6 +29,27 @@
#include <asm/intel-family.h>
static void __init spectre_v2_select_mitigation(void);
+static void __init ssb_select_mitigation(void);
+
+/*
+ * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
+ * writes to SPEC_CTRL contain whatever reserved bits have been set.
+ */
+u64 __ro_after_init x86_spec_ctrl_base;
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
+
+/*
+ * The vendor and possibly platform specific bits which can be modified in
+ * x86_spec_ctrl_base.
+ */
+static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
+
+/*
+ * AMD specific MSR info for Speculative Store Bypass control.
+ * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu().
+ */
+u64 __ro_after_init x86_amd_ls_cfg_base;
+u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;
void __init check_bugs(void)
{
@@ -37,9 +60,27 @@ void __init check_bugs(void)
print_cpu_info(&boot_cpu_data);
}
+ /*
+ * Read the SPEC_CTRL MSR to account for reserved bits which may
+ * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
+ * init code as it is not enumerated and depends on the family.
+ */
+ if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+ rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+ /* Allow STIBP in MSR_SPEC_CTRL if supported */
+ if (boot_cpu_has(X86_FEATURE_STIBP))
+ x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
+
/* Select the proper spectre mitigation before patching alternatives */
spectre_v2_select_mitigation();
+ /*
+ * Select proper mitigation for any exposure to the Speculative Store
+ * Bypass vulnerability.
+ */
+ ssb_select_mitigation();
+
#ifdef CONFIG_X86_32
/*
* Check whether we are able to run this kernel safely on SMP.
@@ -93,7 +134,76 @@ static const char *spectre_v2_strings[] = {
#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
-static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
+ SPECTRE_V2_NONE;
+
+void
+x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
+{
+ u64 msrval, guestval, hostval = x86_spec_ctrl_base;
+ struct thread_info *ti = current_thread_info();
+
+ /* Is MSR_SPEC_CTRL implemented ? */
+ if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
+ /*
+ * Restrict guest_spec_ctrl to supported values. Clear the
+ * modifiable bits in the host base value and or the
+ * modifiable bits from the guest value.
+ */
+ guestval = hostval & ~x86_spec_ctrl_mask;
+ guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
+
+ /* SSBD controlled in MSR_SPEC_CTRL */
+ if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
+ hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
+
+ if (hostval != guestval) {
+ msrval = setguest ? guestval : hostval;
+ wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
+ }
+ }
+
+ /*
+ * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update
+ * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported.
+ */
+ if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) &&
+ !static_cpu_has(X86_FEATURE_VIRT_SSBD))
+ return;
+
+ /*
+ * If the host has SSBD mitigation enabled, force it in the host's
+ * virtual MSR value. If its not permanently enabled, evaluate
+ * current's TIF_SSBD thread flag.
+ */
+ if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE))
+ hostval = SPEC_CTRL_SSBD;
+ else
+ hostval = ssbd_tif_to_spec_ctrl(ti->flags);
+
+ /* Sanitize the guest value */
+ guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD;
+
+ if (hostval != guestval) {
+ unsigned long tif;
+
+ tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) :
+ ssbd_spec_ctrl_to_tif(hostval);
+
+ speculative_store_bypass_update(tif);
+ }
+}
+EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl);
+
+static void x86_amd_ssb_disable(void)
+{
+ u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
+
+ if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+ wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+ else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+ wrmsrl(MSR_AMD64_LS_CFG, msrval);
+}
#ifdef RETPOLINE
static bool spectre_v2_bad_module;
@@ -312,32 +422,289 @@ retpoline_auto:
}
#undef pr_fmt
+#define pr_fmt(fmt) "Speculative Store Bypass: " fmt
+
+static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE;
+
+/* The kernel command line selection */
+enum ssb_mitigation_cmd {
+ SPEC_STORE_BYPASS_CMD_NONE,
+ SPEC_STORE_BYPASS_CMD_AUTO,
+ SPEC_STORE_BYPASS_CMD_ON,
+ SPEC_STORE_BYPASS_CMD_PRCTL,
+ SPEC_STORE_BYPASS_CMD_SECCOMP,
+};
+
+static const char *ssb_strings[] = {
+ [SPEC_STORE_BYPASS_NONE] = "Vulnerable",
+ [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled",
+ [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl",
+ [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp",
+};
+
+static const struct {
+ const char *option;
+ enum ssb_mitigation_cmd cmd;
+} ssb_mitigation_options[] = {
+ { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
+ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */
+ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
+ { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */
+ { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */
+};
+
+static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
+{
+ enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO;
+ char arg[20];
+ int ret, i;
+
+ if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+ return SPEC_STORE_BYPASS_CMD_NONE;
+ } else {
+ ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
+ arg, sizeof(arg));
+ if (ret < 0)
+ return SPEC_STORE_BYPASS_CMD_AUTO;
+
+ for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) {
+ if (!match_option(arg, ret, ssb_mitigation_options[i].option))
+ continue;
+
+ cmd = ssb_mitigation_options[i].cmd;
+ break;
+ }
+
+ if (i >= ARRAY_SIZE(ssb_mitigation_options)) {
+ pr_err("unknown option (%s). Switching to AUTO select\n", arg);
+ return SPEC_STORE_BYPASS_CMD_AUTO;
+ }
+ }
+
+ return cmd;
+}
+
+static enum ssb_mitigation __init __ssb_select_mitigation(void)
+{
+ enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
+ enum ssb_mitigation_cmd cmd;
+
+ if (!boot_cpu_has(X86_FEATURE_SSBD))
+ return mode;
+
+ cmd = ssb_parse_cmdline();
+ if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
+ (cmd == SPEC_STORE_BYPASS_CMD_NONE ||
+ cmd == SPEC_STORE_BYPASS_CMD_AUTO))
+ return mode;
+
+ switch (cmd) {
+ case SPEC_STORE_BYPASS_CMD_AUTO:
+ case SPEC_STORE_BYPASS_CMD_SECCOMP:
+ /*
+ * Choose prctl+seccomp as the default mode if seccomp is
+ * enabled.
+ */
+ if (IS_ENABLED(CONFIG_SECCOMP))
+ mode = SPEC_STORE_BYPASS_SECCOMP;
+ else
+ mode = SPEC_STORE_BYPASS_PRCTL;
+ break;
+ case SPEC_STORE_BYPASS_CMD_ON:
+ mode = SPEC_STORE_BYPASS_DISABLE;
+ break;
+ case SPEC_STORE_BYPASS_CMD_PRCTL:
+ mode = SPEC_STORE_BYPASS_PRCTL;
+ break;
+ case SPEC_STORE_BYPASS_CMD_NONE:
+ break;
+ }
+
+ /*
+ * We have three CPU feature flags that are in play here:
+ * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
+ * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
+ * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
+ */
+ if (mode == SPEC_STORE_BYPASS_DISABLE) {
+ setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
+ /*
+ * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses
+ * a completely different MSR and bit dependent on family.
+ */
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_INTEL:
+ x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
+ x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
+ wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+ break;
+ case X86_VENDOR_AMD:
+ x86_amd_ssb_disable();
+ break;
+ }
+ }
+
+ return mode;
+}
+
+static void ssb_select_mitigation(void)
+{
+ ssb_mode = __ssb_select_mitigation();
+
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ pr_info("%s\n", ssb_strings[ssb_mode]);
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Speculation prctl: " fmt
+
+static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+ bool update;
+
+ if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
+ ssb_mode != SPEC_STORE_BYPASS_SECCOMP)
+ return -ENXIO;
+
+ switch (ctrl) {
+ case PR_SPEC_ENABLE:
+ /* If speculation is force disabled, enable is not allowed */
+ if (task_spec_ssb_force_disable(task))
+ return -EPERM;
+ task_clear_spec_ssb_disable(task);
+ update = test_and_clear_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ case PR_SPEC_DISABLE:
+ task_set_spec_ssb_disable(task);
+ update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ case PR_SPEC_FORCE_DISABLE:
+ task_set_spec_ssb_disable(task);
+ task_set_spec_ssb_force_disable(task);
+ update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ /*
+ * If being set on non-current task, delay setting the CPU
+ * mitigation until it is next scheduled.
+ */
+ if (task == current && update)
+ speculative_store_bypass_update_current();
+
+ return 0;
+}
+
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+ unsigned long ctrl)
+{
+ switch (which) {
+ case PR_SPEC_STORE_BYPASS:
+ return ssb_prctl_set(task, ctrl);
+ default:
+ return -ENODEV;
+ }
+}
+
+#ifdef CONFIG_SECCOMP
+void arch_seccomp_spec_mitigate(struct task_struct *task)
+{
+ if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
+ ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+}
+#endif
+
+static int ssb_prctl_get(struct task_struct *task)
+{
+ switch (ssb_mode) {
+ case SPEC_STORE_BYPASS_DISABLE:
+ return PR_SPEC_DISABLE;
+ case SPEC_STORE_BYPASS_SECCOMP:
+ case SPEC_STORE_BYPASS_PRCTL:
+ if (task_spec_ssb_force_disable(task))
+ return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+ if (task_spec_ssb_disable(task))
+ return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+ return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+ default:
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ return PR_SPEC_ENABLE;
+ return PR_SPEC_NOT_AFFECTED;
+ }
+}
+
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
+{
+ switch (which) {
+ case PR_SPEC_STORE_BYPASS:
+ return ssb_prctl_get(task);
+ default:
+ return -ENODEV;
+ }
+}
+
+void x86_spec_ctrl_setup_ap(void)
+{
+ if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+ wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+ if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
+ x86_amd_ssb_disable();
+}
#ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+
+static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
+ char *buf, unsigned int bug)
{
- if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ if (!boot_cpu_has_bug(bug))
return sprintf(buf, "Not affected\n");
- if (boot_cpu_has(X86_FEATURE_PTI))
- return sprintf(buf, "Mitigation: PTI\n");
+
+ switch (bug) {
+ case X86_BUG_CPU_MELTDOWN:
+ if (boot_cpu_has(X86_FEATURE_PTI))
+ return sprintf(buf, "Mitigation: PTI\n");
+
+ break;
+
+ case X86_BUG_SPECTRE_V1:
+ return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+
+ case X86_BUG_SPECTRE_V2:
+ return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+ boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+ boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+ spectre_v2_module_string());
+
+ case X86_BUG_SPEC_STORE_BYPASS:
+ return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
+
+ default:
+ break;
+ }
+
return sprintf(buf, "Vulnerable\n");
}
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN);
+}
+
ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
{
- if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
- return sprintf(buf, "Not affected\n");
- return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1);
}
ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
{
- if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
- return sprintf(buf, "Not affected\n");
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2);
+}
- return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
- boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
- boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
- spectre_v2_module_string());
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
}
#endif
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 54d04d574148..38354c66df81 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -20,6 +20,8 @@
#include <asm/amd_nb.h>
#include <asm/smp.h>
+#include "cpu.h"
+
#define LVL_1_INST 1
#define LVL_1_DATA 2
#define LVL_2 3
@@ -637,6 +639,45 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
return i;
}
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+{
+ /*
+ * We may have multiple LLCs if L3 caches exist, so check if we
+ * have an L3 cache by looking at the L3 cache CPUID leaf.
+ */
+ if (!cpuid_edx(0x80000006))
+ return;
+
+ if (c->x86 < 0x17) {
+ /* LLC is at the node level. */
+ per_cpu(cpu_llc_id, cpu) = node_id;
+ } else if (c->x86 == 0x17 &&
+ c->x86_model >= 0 && c->x86_model <= 0x1F) {
+ /*
+ * LLC is at the core complex level.
+ * Core complex ID is ApicId[3] for these processors.
+ */
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+ } else {
+ /*
+ * LLC ID is calculated from the number of threads sharing the
+ * cache.
+ * */
+ u32 eax, ebx, ecx, edx, num_sharing_cache = 0;
+ u32 llc_index = find_num_cache_leaves(c) - 1;
+
+ cpuid_count(0x8000001d, llc_index, &eax, &ebx, &ecx, &edx);
+ if (eax)
+ num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
+
+ if (num_sharing_cache) {
+ int bits = get_count_order(num_sharing_cache) - 1;
+
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
+ }
+ }
+}
+
void init_amd_cacheinfo(struct cpuinfo_x86 *c)
{
@@ -650,7 +691,7 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
}
}
-unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
+void init_intel_cacheinfo(struct cpuinfo_x86 *c)
{
/* Cache sizes */
unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0;
@@ -802,7 +843,8 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
- return l2;
+ if (!l2)
+ cpu_detect_cache_sizes(c);
}
static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index e5ec0f11c0de..14433ff5b828 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -18,6 +18,13 @@
#define RNG_ENABLED (1 << 3)
#define RNG_ENABLE (1 << 6) /* MSR_VIA_RNG */
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020
+
static void init_c3(struct cpuinfo_x86 *c)
{
u32 lo, hi;
@@ -112,6 +119,31 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
}
}
+static void centaur_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+ u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+ msr_ctl = vmx_msr_high | vmx_msr_low;
+
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+ set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+ set_cpu_cap(c, X86_FEATURE_VNMI);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+ vmx_msr_low, vmx_msr_high);
+ msr_ctl2 = vmx_msr_high | vmx_msr_low;
+ if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+ (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+ set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+ set_cpu_cap(c, X86_FEATURE_EPT);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+ set_cpu_cap(c, X86_FEATURE_VPID);
+ }
+}
+
static void init_centaur(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_32
@@ -128,6 +160,24 @@ static void init_centaur(struct cpuinfo_x86 *c)
clear_cpu_cap(c, 0*32+31);
#endif
early_init_centaur(c);
+ init_intel_cacheinfo(c);
+ detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+ detect_ht(c);
+#endif
+
+ if (c->cpuid_level > 9) {
+ unsigned int eax = cpuid_eax(10);
+
+ /*
+ * Check for version and the number of counters
+ * Version(eax[7:0]) can't be 0;
+ * Counters(eax[15:8]) should be greater than 1;
+ */
+ if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+ set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+ }
+
switch (c->x86) {
#ifdef CONFIG_X86_32
case 5:
@@ -199,6 +249,9 @@ static void init_centaur(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_64
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
#endif
+
+ if (cpu_has(c, X86_FEATURE_VMX))
+ centaur_detect_vmx_virtcap(c);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8a5b185735e1..95c8e507580d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -66,6 +66,13 @@ cpumask_var_t cpu_callin_mask;
/* representing cpus for which sibling maps can be computed */
cpumask_var_t cpu_sibling_setup_mask;
+/* Number of siblings per CPU package */
+int smp_num_siblings = 1;
+EXPORT_SYMBOL(smp_num_siblings);
+
+/* Last level cache ID of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
+
/* correctly size the local cpu masks */
void __init setup_cpu_local_masks(void)
{
@@ -577,6 +584,19 @@ static void get_model_name(struct cpuinfo_x86 *c)
*(s + 1) = '\0';
}
+void detect_num_cpu_cores(struct cpuinfo_x86 *c)
+{
+ unsigned int eax, ebx, ecx, edx;
+
+ c->x86_max_cores = 1;
+ if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
+ return;
+
+ cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
+ if (eax & 0x1f)
+ c->x86_max_cores = (eax >> 26) + 1;
+}
+
void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
{
unsigned int n, dummy, ebx, ecx, edx, l2size;
@@ -757,17 +777,32 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
* and they also have a different bit for STIBP support. Also,
* a hypervisor might have set the individual AMD bits even on
* Intel CPUs, for finer-grained selection of what's available.
- *
- * We use the AMD bits in 0x8000_0008 EBX as the generic hardware
- * features, which are visible in /proc/cpuinfo and used by the
- * kernel. So set those accordingly from the Intel bits.
*/
if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
set_cpu_cap(c, X86_FEATURE_IBRS);
set_cpu_cap(c, X86_FEATURE_IBPB);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
}
+
if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
set_cpu_cap(c, X86_FEATURE_STIBP);
+
+ if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) ||
+ cpu_has(c, X86_FEATURE_VIRT_SSBD))
+ set_cpu_cap(c, X86_FEATURE_SSBD);
+
+ if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
+ set_cpu_cap(c, X86_FEATURE_IBRS);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+ }
+
+ if (cpu_has(c, X86_FEATURE_AMD_IBPB))
+ set_cpu_cap(c, X86_FEATURE_IBPB);
+
+ if (cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+ set_cpu_cap(c, X86_FEATURE_STIBP);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+ }
}
void get_cpu_cap(struct cpuinfo_x86 *c)
@@ -848,6 +883,11 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_power = edx;
}
+ if (c->extended_cpuid_level >= 0x80000008) {
+ cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[CPUID_8000_0008_EBX] = ebx;
+ }
+
if (c->extended_cpuid_level >= 0x8000000a)
c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
@@ -871,7 +911,6 @@ static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
- c->x86_capability[CPUID_8000_0008_EBX] = ebx;
}
#ifdef CONFIG_X86_32
else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
@@ -923,21 +962,47 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
{}
};
-static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+/* Only list CPUs which speculate but are non susceptible to SSB */
+static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
+ { X86_VENDOR_AMD, 0x12, },
+ { X86_VENDOR_AMD, 0x11, },
+ { X86_VENDOR_AMD, 0x10, },
+ { X86_VENDOR_AMD, 0xf, },
+ {}
+};
+
+static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 ia32_cap = 0;
- if (x86_match_cpu(cpu_no_meltdown))
- return false;
+ if (x86_match_cpu(cpu_no_speculation))
+ return;
+
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+ if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
+ !(ia32_cap & ARCH_CAP_SSB_NO))
+ setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
+
+ if (x86_match_cpu(cpu_no_meltdown))
+ return;
+
/* Rogue Data Cache Load? No! */
if (ia32_cap & ARCH_CAP_RDCL_NO)
- return false;
+ return;
- return true;
+ setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
}
/*
@@ -988,12 +1053,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
- if (!x86_match_cpu(cpu_no_speculation)) {
- if (cpu_vulnerable_to_meltdown(c))
- setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
- setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
- setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
- }
+ cpu_set_bug_bits(c);
fpu__init_system(c);
@@ -1004,6 +1064,21 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
*/
setup_clear_cpu_cap(X86_FEATURE_PCID);
#endif
+
+ /*
+ * Later in the boot process pgtable_l5_enabled() relies on
+ * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not
+ * enabled by this point we need to clear the feature bit to avoid
+ * false-positives at the later stage.
+ *
+ * pgtable_l5_enabled() can be false here for several reasons:
+ * - 5-level paging is disabled compile-time;
+ * - it's 32-bit kernel;
+ * - machine doesn't support 5-level paging;
+ * - user specified 'no5lvl' in kernel command line.
+ */
+ if (!pgtable_l5_enabled())
+ setup_clear_cpu_cap(X86_FEATURE_LA57);
}
void __init early_cpu_init(void)
@@ -1355,6 +1430,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
#endif
mtrr_ap_init();
validate_apic_and_package_id(c);
+ x86_spec_ctrl_setup_ap();
}
static __init int setup_noclflush(char *arg)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index e806b11a99af..38216f678fc3 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -47,7 +47,19 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
extern void get_cpu_cap(struct cpuinfo_x86 *c);
extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
+extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+ unsigned int sub_leaf,
+ enum cpuid_regs_idx reg);
+extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
+
+extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
+extern int detect_extended_topology(struct cpuinfo_x86 *c);
+extern void detect_ht(struct cpuinfo_x86 *c);
unsigned int aperfmperf_get_khz(int cpu);
+extern void x86_spec_ctrl_setup_ap(void);
+
#endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b9693b80fc21..eb75564f2d25 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -188,7 +188,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
setup_clear_cpu_cap(X86_FEATURE_IBPB);
setup_clear_cpu_cap(X86_FEATURE_STIBP);
setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL);
+ setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL);
setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
+ setup_clear_cpu_cap(X86_FEATURE_SSBD);
+ setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD);
}
/*
@@ -453,24 +456,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#endif
}
-/*
- * find out the number of processor cores on the die
- */
-static int intel_num_cpu_cores(struct cpuinfo_x86 *c)
-{
- unsigned int eax, ebx, ecx, edx;
-
- if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
- return 1;
-
- /* Intel has a non-standard dependency on %ecx for this CPUID level. */
- cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
- if (eax & 0x1f)
- return (eax >> 26) + 1;
- else
- return 1;
-}
-
static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
{
/* Intel VMX MSR indicated features */
@@ -653,8 +638,6 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
static void init_intel(struct cpuinfo_x86 *c)
{
- unsigned int l2 = 0;
-
early_init_intel(c);
intel_workarounds(c);
@@ -671,19 +654,13 @@ static void init_intel(struct cpuinfo_x86 *c)
* let's use the legacy cpuid vector 0x1 and 0x4 for topology
* detection.
*/
- c->x86_max_cores = intel_num_cpu_cores(c);
+ detect_num_cpu_cores(c);
#ifdef CONFIG_X86_32
detect_ht(c);
#endif
}
- l2 = init_intel_cacheinfo(c);
-
- /* Detect legacy cache sizes if init_intel_cacheinfo did not */
- if (l2 == 0) {
- cpu_detect_cache_sizes(c);
- l2 = c->x86_cache_size;
- }
+ init_intel_cacheinfo(c);
if (c->cpuid_level > 9) {
unsigned eax = cpuid_eax(10);
@@ -696,7 +673,8 @@ static void init_intel(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
if (boot_cpu_has(X86_FEATURE_DS)) {
- unsigned int l1;
+ unsigned int l1, l2;
+
rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
if (!(l1 & (1<<11)))
set_cpu_cap(c, X86_FEATURE_BTS);
@@ -724,6 +702,7 @@ static void init_intel(struct cpuinfo_x86 *c)
* Dixon is NOT a Celeron.
*/
if (c->x86 == 6) {
+ unsigned int l2 = c->x86_cache_size;
char *p = NULL;
switch (c->x86_model) {
@@ -835,6 +814,9 @@ static const struct _tlb_table intel_tlb_table[] = {
{ 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" },
{ 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" },
{ 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" },
+ { 0x6b, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 8-way associative" },
+ { 0x6c, TLB_DATA_2M_4M, 128, " TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
+ { 0x6d, TLB_DATA_1G, 16, " TLB_DATA 1 GByte pages, fully associative" },
{ 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" },
{ 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" },
{ 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 589b948e6e01..24bfa63e86cf 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -33,8 +33,8 @@
#include <asm/intel_rdt_sched.h>
#include "intel_rdt.h"
-#define MAX_MBA_BW 100u
#define MBA_IS_LINEAR 0x4
+#define MBA_MAX_MBPS U32_MAX
/* Mutex to protect rdtgroup access. */
DEFINE_MUTEX(rdtgroup_mutex);
@@ -178,7 +178,7 @@ struct rdt_resource rdt_resources_all[] = {
.msr_update = mba_wrmsr,
.cache_level = 3,
.parse_ctrlval = parse_bw,
- .format_str = "%d=%*d",
+ .format_str = "%d=%*u",
.fflags = RFTYPE_RES_MB,
},
};
@@ -230,6 +230,14 @@ static inline void cache_alloc_hsw_probe(void)
rdt_alloc_capable = true;
}
+bool is_mba_sc(struct rdt_resource *r)
+{
+ if (!r)
+ return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc;
+
+ return r->membw.mba_sc;
+}
+
/*
* rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
* exposed to user interface and the h/w understandable delay values.
@@ -341,7 +349,7 @@ static int get_cache_id(int cpu, int level)
* that can be written to QOS_MSRs.
* There are currently no SKUs which support non linear delay values.
*/
-static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
+u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
{
if (r->membw.delay_linear)
return MAX_MBA_BW - bw;
@@ -431,25 +439,40 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
return NULL;
}
+void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
+{
+ int i;
+
+ /*
+ * Initialize the Control MSRs to having no control.
+ * For Cache Allocation: Set all bits in cbm
+ * For Memory Allocation: Set b/w requested to 100%
+ * and the bandwidth in MBps to U32_MAX
+ */
+ for (i = 0; i < r->num_closid; i++, dc++, dm++) {
+ *dc = r->default_ctrl;
+ *dm = MBA_MAX_MBPS;
+ }
+}
+
static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
{
struct msr_param m;
- u32 *dc;
- int i;
+ u32 *dc, *dm;
dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
if (!dc)
return -ENOMEM;
- d->ctrl_val = dc;
+ dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL);
+ if (!dm) {
+ kfree(dc);
+ return -ENOMEM;
+ }
- /*
- * Initialize the Control MSRs to having no control.
- * For Cache Allocation: Set all bits in cbm
- * For Memory Allocation: Set b/w requested to 100
- */
- for (i = 0; i < r->num_closid; i++, dc++)
- *dc = r->default_ctrl;
+ d->ctrl_val = dc;
+ d->mbps_val = dm;
+ setup_default_ctrlval(r, dc, dm);
m.low = 0;
m.high = r->num_closid;
@@ -588,6 +611,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
}
kfree(d->ctrl_val);
+ kfree(d->mbps_val);
kfree(d->rmid_busy_llc);
kfree(d->mbm_total);
kfree(d->mbm_local);
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 3fd7a70ee04a..39752825e376 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -28,6 +28,7 @@
#define MBM_CNTR_WIDTH 24
#define MBM_OVERFLOW_INTERVAL 1000
+#define MAX_MBA_BW 100u
#define RMID_VAL_ERROR BIT_ULL(63)
#define RMID_VAL_UNAVAIL BIT_ULL(62)
@@ -180,10 +181,20 @@ struct rftype {
* struct mbm_state - status for each MBM counter in each domain
* @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes)
* @prev_msr Value of IA32_QM_CTR for this RMID last time we read it
+ * @chunks_bw Total local data moved. Used for bandwidth calculation
+ * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
+ * @prev_bw The most recent bandwidth in MBps
+ * @delta_bw Difference between the current and previous bandwidth
+ * @delta_comp Indicates whether to compute the delta_bw
*/
struct mbm_state {
u64 chunks;
u64 prev_msr;
+ u64 chunks_bw;
+ u64 prev_bw_msr;
+ u32 prev_bw;
+ u32 delta_bw;
+ bool delta_comp;
};
/**
@@ -202,6 +213,7 @@ struct mbm_state {
* @cqm_work_cpu:
* worker cpu for CQM h/w counters
* @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID)
+ * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps
* @new_ctrl: new ctrl value to be loaded
* @have_new_ctrl: did user provide new_ctrl for this domain
*/
@@ -217,6 +229,7 @@ struct rdt_domain {
int mbm_work_cpu;
int cqm_work_cpu;
u32 *ctrl_val;
+ u32 *mbps_val;
u32 new_ctrl;
bool have_new_ctrl;
};
@@ -259,6 +272,7 @@ struct rdt_cache {
* @min_bw: Minimum memory bandwidth percentage user can request
* @bw_gran: Granularity at which the memory bandwidth is allocated
* @delay_linear: True if memory B/W delay is in linear scale
+ * @mba_sc: True if MBA software controller(mba_sc) is enabled
* @mb_map: Mapping of memory B/W percentage to memory B/W delay
*/
struct rdt_membw {
@@ -266,6 +280,7 @@ struct rdt_membw {
u32 min_bw;
u32 bw_gran;
u32 delay_linear;
+ bool mba_sc;
u32 *mb_map;
};
@@ -445,6 +460,9 @@ void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
void mbm_setup_overflow_handler(struct rdt_domain *dom,
unsigned long delay_ms);
void mbm_handle_overflow(struct work_struct *work);
+bool is_mba_sc(struct rdt_resource *r);
+void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm);
+u32 delay_bw_map(unsigned long bw, struct rdt_resource *r);
void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
void cqm_handle_limbo(struct work_struct *work);
bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 23e1d5c249c6..116d57b248d3 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -53,7 +53,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
return false;
}
- if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+ if ((bw < r->membw.min_bw || bw > r->default_ctrl) &&
+ !is_mba_sc(r)) {
rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
r->membw.min_bw, r->default_ctrl);
return false;
@@ -179,6 +180,8 @@ static int update_domains(struct rdt_resource *r, int closid)
struct msr_param msr_param;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
+ bool mba_sc;
+ u32 *dc;
int cpu;
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
@@ -188,13 +191,20 @@ static int update_domains(struct rdt_resource *r, int closid)
msr_param.high = msr_param.low + 1;
msr_param.res = r;
+ mba_sc = is_mba_sc(r);
list_for_each_entry(d, &r->domains, list) {
- if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) {
+ dc = !mba_sc ? d->ctrl_val : d->mbps_val;
+ if (d->have_new_ctrl && d->new_ctrl != dc[closid]) {
cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
- d->ctrl_val[closid] = d->new_ctrl;
+ dc[closid] = d->new_ctrl;
}
}
- if (cpumask_empty(cpu_mask))
+
+ /*
+ * Avoid writing the control msr with control values when
+ * MBA software controller is enabled
+ */
+ if (cpumask_empty(cpu_mask) || mba_sc)
goto done;
cpu = get_cpu();
/* Update CBM on this cpu if it's in cpu_mask. */
@@ -282,13 +292,17 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
{
struct rdt_domain *dom;
bool sep = false;
+ u32 ctrl_val;
seq_printf(s, "%*s:", max_name_width, r->name);
list_for_each_entry(dom, &r->domains, list) {
if (sep)
seq_puts(s, ";");
+
+ ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] :
+ dom->mbps_val[closid]);
seq_printf(s, r->format_str, dom->id, max_data_width,
- dom->ctrl_val[closid]);
+ ctrl_val);
sep = true;
}
seq_puts(s, "\n");
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
index 681450eee428..b0f3aed76b75 100644
--- a/arch/x86/kernel/cpu/intel_rdt_monitor.c
+++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -225,10 +225,18 @@ void free_rmid(u32 rmid)
list_add_tail(&entry->list, &rmid_free_lru);
}
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr)
+{
+ u64 shift = 64 - MBM_CNTR_WIDTH, chunks;
+
+ chunks = (cur_msr << shift) - (prev_msr << shift);
+ return chunks >>= shift;
+}
+
static int __mon_event_count(u32 rmid, struct rmid_read *rr)
{
- u64 chunks, shift, tval;
struct mbm_state *m;
+ u64 chunks, tval;
tval = __rmid_read(rmid, rr->evtid);
if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
@@ -254,14 +262,12 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
}
if (rr->first) {
- m->prev_msr = tval;
- m->chunks = 0;
+ memset(m, 0, sizeof(struct mbm_state));
+ m->prev_bw_msr = m->prev_msr = tval;
return 0;
}
- shift = 64 - MBM_CNTR_WIDTH;
- chunks = (tval << shift) - (m->prev_msr << shift);
- chunks >>= shift;
+ chunks = mbm_overflow_count(m->prev_msr, tval);
m->chunks += chunks;
m->prev_msr = tval;
@@ -270,6 +276,32 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
}
/*
+ * Supporting function to calculate the memory bandwidth
+ * and delta bandwidth in MBps.
+ */
+static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
+{
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+ struct mbm_state *m = &rr->d->mbm_local[rmid];
+ u64 tval, cur_bw, chunks;
+
+ tval = __rmid_read(rmid, rr->evtid);
+ if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
+ return;
+
+ chunks = mbm_overflow_count(m->prev_bw_msr, tval);
+ m->chunks_bw += chunks;
+ m->chunks = m->chunks_bw;
+ cur_bw = (chunks * r->mon_scale) >> 20;
+
+ if (m->delta_comp)
+ m->delta_bw = abs(cur_bw - m->prev_bw);
+ m->delta_comp = false;
+ m->prev_bw = cur_bw;
+ m->prev_bw_msr = tval;
+}
+
+/*
* This is called via IPI to read the CQM/MBM counters
* on a domain.
*/
@@ -297,6 +329,118 @@ void mon_event_count(void *info)
}
}
+/*
+ * Feedback loop for MBA software controller (mba_sc)
+ *
+ * mba_sc is a feedback loop where we periodically read MBM counters and
+ * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so
+ * that:
+ *
+ * current bandwdith(cur_bw) < user specified bandwidth(user_bw)
+ *
+ * This uses the MBM counters to measure the bandwidth and MBA throttle
+ * MSRs to control the bandwidth for a particular rdtgrp. It builds on the
+ * fact that resctrl rdtgroups have both monitoring and control.
+ *
+ * The frequency of the checks is 1s and we just tag along the MBM overflow
+ * timer. Having 1s interval makes the calculation of bandwidth simpler.
+ *
+ * Although MBA's goal is to restrict the bandwidth to a maximum, there may
+ * be a need to increase the bandwidth to avoid uncecessarily restricting
+ * the L2 <-> L3 traffic.
+ *
+ * Since MBA controls the L2 external bandwidth where as MBM measures the
+ * L3 external bandwidth the following sequence could lead to such a
+ * situation.
+ *
+ * Consider an rdtgroup which had high L3 <-> memory traffic in initial
+ * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but
+ * after some time rdtgroup has mostly L2 <-> L3 traffic.
+ *
+ * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its
+ * throttle MSRs already have low percentage values. To avoid
+ * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
+ */
+static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+{
+ u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val;
+ struct mbm_state *pmbm_data, *cmbm_data;
+ u32 cur_bw, delta_bw, user_bw;
+ struct rdt_resource *r_mba;
+ struct rdt_domain *dom_mba;
+ struct list_head *head;
+ struct rdtgroup *entry;
+
+ r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
+ closid = rgrp->closid;
+ rmid = rgrp->mon.rmid;
+ pmbm_data = &dom_mbm->mbm_local[rmid];
+
+ dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba);
+ if (!dom_mba) {
+ pr_warn_once("Failure to get domain for MBA update\n");
+ return;
+ }
+
+ cur_bw = pmbm_data->prev_bw;
+ user_bw = dom_mba->mbps_val[closid];
+ delta_bw = pmbm_data->delta_bw;
+ cur_msr_val = dom_mba->ctrl_val[closid];
+
+ /*
+ * For Ctrl groups read data from child monitor groups.
+ */
+ head = &rgrp->mon.crdtgrp_list;
+ list_for_each_entry(entry, head, mon.crdtgrp_list) {
+ cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+ cur_bw += cmbm_data->prev_bw;
+ delta_bw += cmbm_data->delta_bw;
+ }
+
+ /*
+ * Scale up/down the bandwidth linearly for the ctrl group. The
+ * bandwidth step is the bandwidth granularity specified by the
+ * hardware.
+ *
+ * The delta_bw is used when increasing the bandwidth so that we
+ * dont alternately increase and decrease the control values
+ * continuously.
+ *
+ * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if
+ * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep
+ * switching between 90 and 110 continuously if we only check
+ * cur_bw < user_bw.
+ */
+ if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
+ new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
+ } else if (cur_msr_val < MAX_MBA_BW &&
+ (user_bw > (cur_bw + delta_bw))) {
+ new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
+ } else {
+ return;
+ }
+
+ cur_msr = r_mba->msr_base + closid;
+ wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba));
+ dom_mba->ctrl_val[closid] = new_msr_val;
+
+ /*
+ * Delta values are updated dynamically package wise for each
+ * rdtgrp everytime the throttle MSR changes value.
+ *
+ * This is because (1)the increase in bandwidth is not perfectly
+ * linear and only "approximately" linear even when the hardware
+ * says it is linear.(2)Also since MBA is a core specific
+ * mechanism, the delta values vary based on number of cores used
+ * by the rdtgrp.
+ */
+ pmbm_data->delta_comp = true;
+ list_for_each_entry(entry, head, mon.crdtgrp_list) {
+ cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+ cmbm_data->delta_comp = true;
+ }
+}
+
static void mbm_update(struct rdt_domain *d, int rmid)
{
struct rmid_read rr;
@@ -314,7 +458,16 @@ static void mbm_update(struct rdt_domain *d, int rmid)
}
if (is_mbm_local_enabled()) {
rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
- __mon_event_count(rmid, &rr);
+
+ /*
+ * Call the MBA software controller only for the
+ * control groups and when user has enabled
+ * the software controller explicitly.
+ */
+ if (!is_mba_sc(NULL))
+ __mon_event_count(rmid, &rr);
+ else
+ mbm_bw_count(rmid, &rr);
}
}
@@ -385,6 +538,9 @@ void mbm_handle_overflow(struct work_struct *work)
head = &prgrp->mon.crdtgrp_list;
list_for_each_entry(crgrp, head, mon.crdtgrp_list)
mbm_update(d, crgrp->mon.rmid);
+
+ if (is_mba_sc(NULL))
+ update_mba_bw(prgrp, d);
}
schedule_delayed_work_on(cpu, &d->mbm_over, delay);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index fca759d272a1..749856a2e736 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1005,6 +1005,11 @@ static void l2_qos_cfg_update(void *arg)
wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
}
+static inline bool is_mba_linear(void)
+{
+ return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear;
+}
+
static int set_cache_qos_cfg(int level, bool enable)
{
void (*update)(void *arg);
@@ -1041,6 +1046,28 @@ static int set_cache_qos_cfg(int level, bool enable)
return 0;
}
+/*
+ * Enable or disable the MBA software controller
+ * which helps user specify bandwidth in MBps.
+ * MBA software controller is supported only if
+ * MBM is supported and MBA is in linear scale.
+ */
+static int set_mba_sc(bool mba_sc)
+{
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA];
+ struct rdt_domain *d;
+
+ if (!is_mbm_enabled() || !is_mba_linear() ||
+ mba_sc == is_mba_sc(r))
+ return -EINVAL;
+
+ r->membw.mba_sc = mba_sc;
+ list_for_each_entry(d, &r->domains, list)
+ setup_default_ctrlval(r, d->ctrl_val, d->mbps_val);
+
+ return 0;
+}
+
static int cdp_enable(int level, int data_type, int code_type)
{
struct rdt_resource *r_ldata = &rdt_resources_all[data_type];
@@ -1123,6 +1150,10 @@ static int parse_rdtgroupfs_options(char *data)
ret = cdpl2_enable();
if (ret)
goto out;
+ } else if (!strcmp(token, "mba_MBps")) {
+ ret = set_mba_sc(true);
+ if (ret)
+ goto out;
} else {
ret = -EINVAL;
goto out;
@@ -1445,6 +1476,8 @@ static void rdt_kill_sb(struct super_block *sb)
cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
+ set_mba_sc(false);
+
/*Put everything back to default values. */
for_each_alloc_enabled_rdt_resource(r)
reset_all_ctrls(r);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 475cb4f5f14f..c805a06e14c3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -48,7 +48,7 @@ static struct dentry *dfs_inj;
static u8 n_banks;
-#define MAX_FLAG_OPT_SIZE 3
+#define MAX_FLAG_OPT_SIZE 4
#define NBCFG 0x44
enum injection_type {
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 42cf2880d0ed..cd76380af79f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1727,6 +1727,21 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
}
}
+static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
+{
+ struct mca_config *cfg = &mca_cfg;
+
+ /*
+ * All newer Centaur CPUs support MCE broadcasting. Enable
+ * synchronization with a one second timeout.
+ */
+ if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) ||
+ c->x86 > 6) {
+ if (cfg->monarch_timeout < 0)
+ cfg->monarch_timeout = USEC_PER_SEC;
+ }
+}
+
static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
{
switch (c->x86_vendor) {
@@ -1739,6 +1754,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
mce_amd_feature_init(c);
break;
}
+ case X86_VENDOR_CENTAUR:
+ mce_centaur_feature_init(c);
+ break;
default:
break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index f7666eef4a87..f591b01930db 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -94,6 +94,11 @@ static struct smca_bank_name smca_names[] = {
[SMCA_SMU] = { "smu", "System Management Unit" },
};
+static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
+{
+ [0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
+};
+
const char *smca_get_name(enum smca_bank_types t)
{
if (t >= N_SMCA_BANK_TYPES)
@@ -431,8 +436,7 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
wrmsr(MSR_CU_DEF_ERR, low, high);
}
-static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
- unsigned int block)
+static u32 smca_get_block_address(unsigned int bank, unsigned int block)
{
u32 low, high;
u32 addr = 0;
@@ -443,24 +447,30 @@ static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
if (!block)
return MSR_AMD64_SMCA_MCx_MISC(bank);
+ /* Check our cache first: */
+ if (smca_bank_addrs[bank][block] != -1)
+ return smca_bank_addrs[bank][block];
+
/*
* For SMCA enabled processors, BLKPTR field of the first MISC register
* (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
*/
- if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
- return addr;
+ if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+ goto out;
if (!(low & MCI_CONFIG_MCAX))
- return addr;
+ goto out;
- if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+ if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
(low & MASK_BLKPTR_LO))
- return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+ addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+out:
+ smca_bank_addrs[bank][block] = addr;
return addr;
}
-static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high,
+static u32 get_block_address(u32 current_addr, u32 low, u32 high,
unsigned int bank, unsigned int block)
{
u32 addr = 0, offset = 0;
@@ -468,20 +478,8 @@ static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 hi
if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
return addr;
- /* Get address from already initialized block. */
- if (per_cpu(threshold_banks, cpu)) {
- struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank];
-
- if (bankp && bankp->blocks) {
- struct threshold_block *blockp = &bankp->blocks[block];
-
- if (blockp)
- return blockp->address;
- }
- }
-
if (mce_flags.smca)
- return smca_get_block_address(cpu, bank, block);
+ return smca_get_block_address(bank, block);
/* Fall back to method we used for older processors: */
switch (block) {
@@ -559,7 +557,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
smca_configure(bank, cpu);
for (block = 0; block < NR_BLOCKS; ++block) {
- address = get_block_address(cpu, address, low, high, bank, block);
+ address = get_block_address(address, low, high, bank, block);
if (!address)
break;
@@ -1176,7 +1174,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
if (err)
goto out_free;
recurse:
- address = get_block_address(cpu, address, low, high, bank, ++block);
+ address = get_block_address(address, low, high, bank, ++block);
if (!address)
return 0;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 10c4fc2c91f8..77e201301528 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -564,14 +564,12 @@ static int __reload_late(void *info)
apply_microcode_local(&err);
spin_unlock(&update_lock);
+ /* siblings return UCODE_OK because their engine got updated already */
if (err > UCODE_NFOUND) {
pr_warn("Error reloading microcode on CPU %d\n", cpu);
- return -1;
- /* siblings return UCODE_OK because their engine got updated already */
+ ret = -1;
} else if (err == UCODE_UPDATED || err == UCODE_OK) {
ret = 1;
- } else {
- return ret;
}
/*
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 32b8e5724f96..1c2cfa0644aa 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -485,7 +485,6 @@ static void show_saved_mc(void)
*/
static void save_mc_for_early(u8 *mc, unsigned int size)
{
-#ifdef CONFIG_HOTPLUG_CPU
/* Synchronization during CPU hotplug. */
static DEFINE_MUTEX(x86_cpu_microcode_mutex);
@@ -495,7 +494,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size)
show_saved_mc();
mutex_unlock(&x86_cpu_microcode_mutex);
-#endif
}
static bool load_builtin_intel_microcode(struct cpio_data *cp)
diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile
index ad9e5ed81181..2ad9107ee980 100644
--- a/arch/x86/kernel/cpu/mtrr/Makefile
+++ b/arch/x86/kernel/cpu/mtrr/Makefile
@@ -1,3 +1,3 @@
-obj-y := main.o if.o generic.o cleanup.o
+obj-y := mtrr.o if.o generic.o cleanup.o
obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index 7468de429087..9a19c800fe40 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -46,6 +46,7 @@
#include <linux/pci.h>
#include <linux/smp.h>
#include <linux/syscore_ops.h>
+#include <linux/rcupdate.h>
#include <asm/cpufeature.h>
#include <asm/e820/api.h>
@@ -100,7 +101,7 @@ static int have_wrcomb(void)
if (dev->vendor == PCI_VENDOR_ID_SERVERWORKS &&
dev->device == PCI_DEVICE_ID_SERVERWORKS_LE &&
dev->revision <= 5) {
- pr_info("mtrr: Serverworks LE rev < 6 detected. Write-combining disabled.\n");
+ pr_info("Serverworks LE rev < 6 detected. Write-combining disabled.\n");
pci_dev_put(dev);
return 0;
}
@@ -110,7 +111,7 @@ static int have_wrcomb(void)
*/
if (dev->vendor == PCI_VENDOR_ID_INTEL &&
dev->device == PCI_DEVICE_ID_INTEL_82451NX) {
- pr_info("mtrr: Intel 450NX MMC detected. Write-combining disabled.\n");
+ pr_info("Intel 450NX MMC detected. Write-combining disabled.\n");
pci_dev_put(dev);
return 0;
}
@@ -312,24 +313,24 @@ int mtrr_add_page(unsigned long base, unsigned long size,
return error;
if (type >= MTRR_NUM_TYPES) {
- pr_warn("mtrr: type: %u invalid\n", type);
+ pr_warn("type: %u invalid\n", type);
return -EINVAL;
}
/* If the type is WC, check that this processor supports it */
if ((type == MTRR_TYPE_WRCOMB) && !have_wrcomb()) {
- pr_warn("mtrr: your processor doesn't support write-combining\n");
+ pr_warn("your processor doesn't support write-combining\n");
return -ENOSYS;
}
if (!size) {
- pr_warn("mtrr: zero sized request\n");
+ pr_warn("zero sized request\n");
return -EINVAL;
}
if ((base | (base + size - 1)) >>
(boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) {
- pr_warn("mtrr: base or size exceeds the MTRR width\n");
+ pr_warn("base or size exceeds the MTRR width\n");
return -EINVAL;
}
@@ -360,8 +361,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
} else if (types_compatible(type, ltype))
continue;
}
- pr_warn("mtrr: 0x%lx000,0x%lx000 overlaps existing"
- " 0x%lx000,0x%lx000\n", base, size, lbase,
+ pr_warn("0x%lx000,0x%lx000 overlaps existing 0x%lx000,0x%lx000\n", base, size, lbase,
lsize);
goto out;
}
@@ -369,7 +369,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
if (ltype != type) {
if (types_compatible(type, ltype))
continue;
- pr_warn("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n",
+ pr_warn("type mismatch for %lx000,%lx000 old: %s new: %s\n",
base, size, mtrr_attrib_to_str(ltype),
mtrr_attrib_to_str(type));
goto out;
@@ -395,7 +395,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
}
}
} else {
- pr_info("mtrr: no more MTRRs available\n");
+ pr_info("no more MTRRs available\n");
}
error = i;
out:
@@ -407,8 +407,8 @@ int mtrr_add_page(unsigned long base, unsigned long size,
static int mtrr_check(unsigned long base, unsigned long size)
{
if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
- pr_warn("mtrr: size and base must be multiples of 4 kiB\n");
- pr_debug("mtrr: size: 0x%lx base: 0x%lx\n", size, base);
+ pr_warn("size and base must be multiples of 4 kiB\n");
+ pr_debug("size: 0x%lx base: 0x%lx\n", size, base);
dump_stack();
return -1;
}
@@ -499,22 +499,22 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
}
}
if (reg < 0) {
- pr_debug("mtrr: no MTRR for %lx000,%lx000 found\n",
+ pr_debug("no MTRR for %lx000,%lx000 found\n",
base, size);
goto out;
}
}
if (reg >= max) {
- pr_warn("mtrr: register: %d too big\n", reg);
+ pr_warn("register: %d too big\n", reg);
goto out;
}
mtrr_if->get(reg, &lbase, &lsize, &ltype);
if (lsize < 1) {
- pr_warn("mtrr: MTRR %d not used\n", reg);
+ pr_warn("MTRR %d not used\n", reg);
goto out;
}
if (mtrr_usage_table[reg] < 1) {
- pr_warn("mtrr: reg: %d has count=0\n", reg);
+ pr_warn("reg: %d has count=0\n", reg);
goto out;
}
if (--mtrr_usage_table[reg] < 1)
@@ -775,7 +775,7 @@ void __init mtrr_bp_init(void)
}
if (!mtrr_enabled()) {
- pr_info("MTRR: Disabled\n");
+ pr_info("Disabled\n");
/*
* PAT initialization relies on MTRR's rendezvous handler.
@@ -793,6 +793,9 @@ void mtrr_ap_init(void)
if (!use_intel() || mtrr_aps_delayed_init)
return;
+
+ rcu_cpu_starting(smp_processor_id());
+
/*
* Ideally we should hold mtrr_mutex here to avoid mtrr entries
* changed, but this routine will be called in cpu boot time,
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index b099024d339c..81c0afb39d0a 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -27,7 +27,7 @@
* exists, use it for populating initial_apicid and cpu topology
* detection.
*/
-void detect_extended_topology(struct cpuinfo_x86 *c)
+int detect_extended_topology(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
unsigned int eax, ebx, ecx, edx, sub_index;
@@ -36,7 +36,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
static bool printed;
if (c->cpuid_level < 0xb)
- return;
+ return -1;
cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
@@ -44,7 +44,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
* check if the cpuid leaf 0xb is actually implemented.
*/
if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
- return;
+ return -1;
set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
@@ -95,6 +95,6 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
c->cpu_core_id);
printed = 1;
}
- return;
#endif
+ return 0;
}