aboutsummaryrefslogtreecommitdiff
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/Makefile1
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c11
-rw-r--r--arch/x86/kernel/cpu/common.c58
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c121
-rw-r--r--arch/x86/kernel/cpu/hypervisor.c64
-rw-r--r--arch/x86/kernel/cpu/intel.c15
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.c1
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.h7
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c50
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_monitor.c2
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_rdtgroup.c131
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c9
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c13
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c6
-rw-r--r--arch/x86/kernel/cpu/vmware.c8
15 files changed, 381 insertions, 116 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index c60922a66385..90cb82dbba57 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -23,6 +23,7 @@ obj-y += rdrand.o
obj-y += match.o
obj-y += bugs.o
obj-$(CONFIG_CPU_FREQ) += aperfmperf.o
+obj-y += cpuid-deps.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 0ee83321a313..957813e0180d 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -42,10 +42,6 @@ static void aperfmperf_snapshot_khz(void *dummy)
s64 time_delta = ktime_ms_delta(now, s->time);
unsigned long flags;
- /* Don't bother re-computing within the cache threshold time. */
- if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
- return;
-
local_irq_save(flags);
rdmsrl(MSR_IA32_APERF, aperf);
rdmsrl(MSR_IA32_MPERF, mperf);
@@ -74,6 +70,7 @@ static void aperfmperf_snapshot_khz(void *dummy)
unsigned int arch_freq_get_on_cpu(int cpu)
{
+ s64 time_delta;
unsigned int khz;
if (!cpu_khz)
@@ -82,6 +79,12 @@ unsigned int arch_freq_get_on_cpu(int cpu)
if (!static_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
+ /* Don't bother re-computing within the cache threshold time. */
+ time_delta = ktime_ms_delta(ktime_get(), per_cpu(samples.time, cpu));
+ khz = per_cpu(samples.khz, cpu);
+ if (khz && time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
+ return khz;
+
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
khz = per_cpu(samples.khz, cpu);
if (khz)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c9176bae7fd8..13ae9e5eec2f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -329,6 +329,28 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
}
}
+static __always_inline void setup_umip(struct cpuinfo_x86 *c)
+{
+ /* Check the boot processor, plus build option for UMIP. */
+ if (!cpu_feature_enabled(X86_FEATURE_UMIP))
+ goto out;
+
+ /* Check the current processor's cpuid bits. */
+ if (!cpu_has(c, X86_FEATURE_UMIP))
+ goto out;
+
+ cr4_set_bits(X86_CR4_UMIP);
+
+ return;
+
+out:
+ /*
+ * Make sure UMIP is disabled in case it was enabled in a
+ * previous boot (e.g., via kexec).
+ */
+ cr4_clear_bits(X86_CR4_UMIP);
+}
+
/*
* Protection Keys are not available in 32-bit mode.
*/
@@ -863,8 +885,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
* cache alignment.
* The others are not touched to avoid unwanted side effects.
*
- * WARNING: this function is only called on the BP. Don't add code here
- * that is supposed to run on all CPUs.
+ * WARNING: this function is only called on the boot CPU. Don't add code
+ * here that is supposed to run on all CPUs.
*/
static void __init early_identify_cpu(struct cpuinfo_x86 *c)
{
@@ -1147,9 +1169,10 @@ static void identify_cpu(struct cpuinfo_x86 *c)
/* Disable the PN if appropriate */
squash_the_stupid_serial_number(c);
- /* Set up SMEP/SMAP */
+ /* Set up SMEP/SMAP/UMIP */
setup_smep(c);
setup_smap(c);
+ setup_umip(c);
/*
* The vendor-specific functions might have changed features.
@@ -1301,18 +1324,16 @@ void print_cpu_info(struct cpuinfo_x86 *c)
pr_cont(")\n");
}
-static __init int setup_disablecpuid(char *arg)
+/*
+ * clearcpuid= was already parsed in fpu__init_parse_early_param.
+ * But we need to keep a dummy __setup around otherwise it would
+ * show up as an environment variable for init.
+ */
+static __init int setup_clearcpuid(char *arg)
{
- int bit;
-
- if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32)
- setup_clear_cpu_cap(bit);
- else
- return 0;
-
return 1;
}
-__setup("clearcpuid=", setup_disablecpuid);
+__setup("clearcpuid=", setup_clearcpuid);
#ifdef CONFIG_X86_64
DEFINE_PER_CPU_FIRST(union irq_stack_union,
@@ -1572,9 +1593,13 @@ void cpu_init(void)
initialize_tlbstate_and_flush();
enter_lazy_tlb(&init_mm, me);
- load_sp0(t, &current->thread);
+ /*
+ * Initialize the TSS. Don't bother initializing sp0, as the initial
+ * task never enters user mode.
+ */
set_tss_desc(cpu, t);
load_TR_desc();
+
load_mm_ldt(&init_mm);
clear_all_debug_regs();
@@ -1596,7 +1621,6 @@ void cpu_init(void)
int cpu = smp_processor_id();
struct task_struct *curr = current;
struct tss_struct *t = &per_cpu(cpu_tss, cpu);
- struct thread_struct *thread = &curr->thread;
wait_for_master_cpu(cpu);
@@ -1627,9 +1651,13 @@ void cpu_init(void)
initialize_tlbstate_and_flush();
enter_lazy_tlb(&init_mm, curr);
- load_sp0(t, thread);
+ /*
+ * Initialize the TSS. Don't bother initializing sp0, as the initial
+ * task never enters user mode.
+ */
set_tss_desc(cpu, t);
load_TR_desc();
+
load_mm_ldt(&init_mm);
t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
new file mode 100644
index 000000000000..904b0a3c4e53
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -0,0 +1,121 @@
+/* Declare dependencies between CPUIDs */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <asm/cpufeature.h>
+
+struct cpuid_dep {
+ unsigned int feature;
+ unsigned int depends;
+};
+
+/*
+ * Table of CPUID features that depend on others.
+ *
+ * This only includes dependencies that can be usefully disabled, not
+ * features part of the base set (like FPU).
+ *
+ * Note this all is not __init / __initdata because it can be
+ * called from cpu hotplug. It shouldn't do anything in this case,
+ * but it's difficult to tell that to the init reference checker.
+ */
+const static struct cpuid_dep cpuid_deps[] = {
+ { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE },
+ { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE },
+ { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE },
+ { X86_FEATURE_AVX, X86_FEATURE_XSAVE },
+ { X86_FEATURE_PKU, X86_FEATURE_XSAVE },
+ { X86_FEATURE_MPX, X86_FEATURE_XSAVE },
+ { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE },
+ { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR },
+ { X86_FEATURE_XMM, X86_FEATURE_FXSR },
+ { X86_FEATURE_XMM2, X86_FEATURE_XMM },
+ { X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
+ { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 },
+ { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 },
+ { X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
+ { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 },
+ { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, },
+ { X86_FEATURE_F16C, X86_FEATURE_XMM2, },
+ { X86_FEATURE_AES, X86_FEATURE_XMM2 },
+ { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 },
+ { X86_FEATURE_FMA, X86_FEATURE_AVX },
+ { X86_FEATURE_AVX2, X86_FEATURE_AVX, },
+ { X86_FEATURE_AVX512F, X86_FEATURE_AVX, },
+ { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_VAES, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
+ {}
+};
+
+static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature)
+{
+ /*
+ * Note: This could use the non atomic __*_bit() variants, but the
+ * rest of the cpufeature code uses atomics as well, so keep it for
+ * consistency. Cleanup all of it separately.
+ */
+ if (!c) {
+ clear_cpu_cap(&boot_cpu_data, feature);
+ set_bit(feature, (unsigned long *)cpu_caps_cleared);
+ } else {
+ clear_bit(feature, (unsigned long *)c->x86_capability);
+ }
+}
+
+/* Take the capabilities and the BUG bits into account */
+#define MAX_FEATURE_BITS ((NCAPINTS + NBUGINTS) * sizeof(u32) * 8)
+
+static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature)
+{
+ DECLARE_BITMAP(disable, MAX_FEATURE_BITS);
+ const struct cpuid_dep *d;
+ bool changed;
+
+ if (WARN_ON(feature >= MAX_FEATURE_BITS))
+ return;
+
+ clear_feature(c, feature);
+
+ /* Collect all features to disable, handling dependencies */
+ memset(disable, 0, sizeof(disable));
+ __set_bit(feature, disable);
+
+ /* Loop until we get a stable state. */
+ do {
+ changed = false;
+ for (d = cpuid_deps; d->feature; d++) {
+ if (!test_bit(d->depends, disable))
+ continue;
+ if (__test_and_set_bit(d->feature, disable))
+ continue;
+
+ changed = true;
+ clear_feature(c, d->feature);
+ }
+ } while (changed);
+}
+
+void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature)
+{
+ do_clear_cpu_cap(c, feature);
+}
+
+void setup_clear_cpu_cap(unsigned int feature)
+{
+ do_clear_cpu_cap(NULL, feature);
+}
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 4fa90006ac68..bea8d3e24f50 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -26,6 +26,12 @@
#include <asm/processor.h>
#include <asm/hypervisor.h>
+extern const struct hypervisor_x86 x86_hyper_vmware;
+extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
+extern const struct hypervisor_x86 x86_hyper_xen_pv;
+extern const struct hypervisor_x86 x86_hyper_xen_hvm;
+extern const struct hypervisor_x86 x86_hyper_kvm;
+
static const __initconst struct hypervisor_x86 * const hypervisors[] =
{
#ifdef CONFIG_XEN_PV
@@ -41,54 +47,52 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] =
#endif
};
-const struct hypervisor_x86 *x86_hyper;
-EXPORT_SYMBOL(x86_hyper);
+enum x86_hypervisor_type x86_hyper_type;
+EXPORT_SYMBOL(x86_hyper_type);
-static inline void __init
+static inline const struct hypervisor_x86 * __init
detect_hypervisor_vendor(void)
{
- const struct hypervisor_x86 *h, * const *p;
+ const struct hypervisor_x86 *h = NULL, * const *p;
uint32_t pri, max_pri = 0;
for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) {
- h = *p;
- pri = h->detect();
- if (pri != 0 && pri > max_pri) {
+ pri = (*p)->detect();
+ if (pri > max_pri) {
max_pri = pri;
- x86_hyper = h;
+ h = *p;
}
}
- if (max_pri)
- pr_info("Hypervisor detected: %s\n", x86_hyper->name);
+ if (h)
+ pr_info("Hypervisor detected: %s\n", h->name);
+
+ return h;
}
-void __init init_hypervisor_platform(void)
+static void __init copy_array(const void *src, void *target, unsigned int size)
{
+ unsigned int i, n = size / sizeof(void *);
+ const void * const *from = (const void * const *)src;
+ const void **to = (const void **)target;
- detect_hypervisor_vendor();
-
- if (!x86_hyper)
- return;
-
- if (x86_hyper->init_platform)
- x86_hyper->init_platform();
+ for (i = 0; i < n; i++)
+ if (from[i])
+ to[i] = from[i];
}
-bool __init hypervisor_x2apic_available(void)
+void __init init_hypervisor_platform(void)
{
- return x86_hyper &&
- x86_hyper->x2apic_available &&
- x86_hyper->x2apic_available();
-}
+ const struct hypervisor_x86 *h;
-void hypervisor_pin_vcpu(int cpu)
-{
- if (!x86_hyper)
+ h = detect_hypervisor_vendor();
+
+ if (!h)
return;
- if (x86_hyper->pin_vcpu)
- x86_hyper->pin_vcpu(cpu);
- else
- WARN_ONCE(1, "vcpu pinning requested but not supported!\n");
+ copy_array(&h->init, &x86_init.hyper, sizeof(h->init));
+ copy_array(&h->runtime, &x86_platform.hyper, sizeof(h->runtime));
+
+ x86_hyper_type = h->type;
+ x86_init.hyper.init_platform();
}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b720dacac051..b1af22073e28 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -187,21 +187,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
if (c->x86 == 6 && c->x86_model < 15)
clear_cpu_cap(c, X86_FEATURE_PAT);
-#ifdef CONFIG_KMEMCHECK
- /*
- * P4s have a "fast strings" feature which causes single-
- * stepping REP instructions to only generate a #DB on
- * cache-line boundaries.
- *
- * Ingo Molnar reported a Pentium D (model 6) and a Xeon
- * (model 2) with the same problem.
- */
- if (c->x86 == 15)
- if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
- MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0)
- pr_info("kmemcheck: Disabling fast string operations\n");
-#endif
-
/*
* If fast string is not enabled in IA32_MISC_ENABLE for any reason,
* clear the fast string and enhanced fast string CPU capabilities.
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index cd5fc61ba450..88dcf8479013 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -267,6 +267,7 @@ static void rdt_get_cdp_l3_config(int type)
r->num_closid = r_l3->num_closid / 2;
r->cache.cbm_len = r_l3->cache.cbm_len;
r->default_ctrl = r_l3->default_ctrl;
+ r->cache.shareable_bits = r_l3->cache.shareable_bits;
r->data_width = (r->cache.cbm_len + 3) / 4;
r->alloc_capable = true;
/*
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index a43a72d8e88e..3397244984f5 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -127,12 +127,15 @@ struct rdtgroup {
#define RFTYPE_BASE BIT(1)
#define RF_CTRLSHIFT 4
#define RF_MONSHIFT 5
+#define RF_TOPSHIFT 6
#define RFTYPE_CTRL BIT(RF_CTRLSHIFT)
#define RFTYPE_MON BIT(RF_MONSHIFT)
+#define RFTYPE_TOP BIT(RF_TOPSHIFT)
#define RFTYPE_RES_CACHE BIT(8)
#define RFTYPE_RES_MB BIT(9)
#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL)
#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON)
+#define RF_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP)
#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL)
/* List of all resource groups */
@@ -409,6 +412,10 @@ union cpuid_0x10_x_edx {
unsigned int full;
};
+void rdt_last_cmd_clear(void);
+void rdt_last_cmd_puts(const char *s);
+void rdt_last_cmd_printf(const char *fmt, ...);
+
void rdt_ctrl_update(void *arg);
struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
void rdtgroup_kn_unlock(struct kernfs_node *kn);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index f6ea94f8954a..23e1d5c249c6 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -42,15 +42,22 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
/*
* Only linear delay values is supported for current Intel SKUs.
*/
- if (!r->membw.delay_linear)
+ if (!r->membw.delay_linear) {
+ rdt_last_cmd_puts("No support for non-linear MB domains\n");
return false;
+ }
ret = kstrtoul(buf, 10, &bw);
- if (ret)
+ if (ret) {
+ rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
return false;
+ }
- if (bw < r->membw.min_bw || bw > r->default_ctrl)
+ if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+ rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
+ r->membw.min_bw, r->default_ctrl);
return false;
+ }
*data = roundup(bw, (unsigned long)r->membw.bw_gran);
return true;
@@ -60,8 +67,10 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
{
unsigned long data;
- if (d->have_new_ctrl)
+ if (d->have_new_ctrl) {
+ rdt_last_cmd_printf("duplicate domain %d\n", d->id);
return -EINVAL;
+ }
if (!bw_validate(buf, &data, r))
return -EINVAL;
@@ -84,20 +93,29 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
int ret;
ret = kstrtoul(buf, 16, &val);
- if (ret)
+ if (ret) {
+ rdt_last_cmd_printf("non-hex character in mask %s\n", buf);
return false;
+ }
- if (val == 0 || val > r->default_ctrl)
+ if (val == 0 || val > r->default_ctrl) {
+ rdt_last_cmd_puts("mask out of range\n");
return false;
+ }
first_bit = find_first_bit(&val, cbm_len);
zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
- if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)
+ if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) {
+ rdt_last_cmd_printf("mask %lx has non-consecutive 1-bits\n", val);
return false;
+ }
- if ((zero_bit - first_bit) < r->cache.min_cbm_bits)
+ if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
+ rdt_last_cmd_printf("Need at least %d bits in mask\n",
+ r->cache.min_cbm_bits);
return false;
+ }
*data = val;
return true;
@@ -111,8 +129,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
{
unsigned long data;
- if (d->have_new_ctrl)
+ if (d->have_new_ctrl) {
+ rdt_last_cmd_printf("duplicate domain %d\n", d->id);
return -EINVAL;
+ }
if(!cbm_validate(buf, &data, r))
return -EINVAL;
@@ -139,8 +159,10 @@ next:
return 0;
dom = strsep(&line, ";");
id = strsep(&dom, "=");
- if (!dom || kstrtoul(id, 10, &dom_id))
+ if (!dom || kstrtoul(id, 10, &dom_id)) {
+ rdt_last_cmd_puts("Missing '=' or non-numeric domain\n");
return -EINVAL;
+ }
dom = strim(dom);
list_for_each_entry(d, &r->domains, list) {
if (d->id == dom_id) {
@@ -196,6 +218,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
if (!strcmp(resname, r->name) && closid < r->num_closid)
return parse_line(tok, r);
}
+ rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname);
return -EINVAL;
}
@@ -218,6 +241,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
rdtgroup_kn_unlock(of->kn);
return -ENOENT;
}
+ rdt_last_cmd_clear();
closid = rdtgrp->closid;
@@ -229,6 +253,12 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
while ((tok = strsep(&buf, "\n")) != NULL) {
resname = strim(strsep(&tok, ":"));
if (!tok) {
+ rdt_last_cmd_puts("Missing ':'\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (tok[0] == '\0') {
+ rdt_last_cmd_printf("Missing '%s' value\n", resname);
ret = -EINVAL;
goto out;
}
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
index 30827510094b..681450eee428 100644
--- a/arch/x86/kernel/cpu/intel_rdt_monitor.c
+++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -51,7 +51,7 @@ static LIST_HEAD(rmid_free_lru);
* may have a occupancy value > intel_cqm_threshold. User can change
* the threshold occupancy value.
*/
-unsigned int rmid_limbo_count;
+static unsigned int rmid_limbo_count;
/**
* @rmid_entry - The entry in the limbo and free lists.
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index a869d4a073c5..64c5ff97ee0d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -24,6 +24,7 @@
#include <linux/fs.h>
#include <linux/sysfs.h>
#include <linux/kernfs.h>
+#include <linux/seq_buf.h>
#include <linux/seq_file.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
@@ -51,6 +52,31 @@ static struct kernfs_node *kn_mongrp;
/* Kernel fs node for "mon_data" directory under root */
static struct kernfs_node *kn_mondata;
+static struct seq_buf last_cmd_status;
+static char last_cmd_status_buf[512];
+
+void rdt_last_cmd_clear(void)
+{
+ lockdep_assert_held(&rdtgroup_mutex);
+ seq_buf_clear(&last_cmd_status);
+}
+
+void rdt_last_cmd_puts(const char *s)
+{
+ lockdep_assert_held(&rdtgroup_mutex);
+ seq_buf_puts(&last_cmd_status, s);
+}
+
+void rdt_last_cmd_printf(const char *fmt, ...)
+{
+ va_list ap;
+
+ va_start(ap, fmt);
+ lockdep_assert_held(&rdtgroup_mutex);
+ seq_buf_vprintf(&last_cmd_status, fmt, ap);
+ va_end(ap);
+}
+
/*
* Trivial allocator for CLOSIDs. Since h/w only supports a small number,
* we can keep a bitmap of free CLOSIDs in a single integer.
@@ -238,8 +264,10 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
/* Check whether cpus belong to parent ctrl group */
cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
- if (cpumask_weight(tmpmask))
+ if (cpumask_weight(tmpmask)) {
+ rdt_last_cmd_puts("can only add CPUs to mongroup that belong to parent\n");
return -EINVAL;
+ }
/* Check whether cpus are dropped from this group */
cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
@@ -291,8 +319,10 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
if (cpumask_weight(tmpmask)) {
/* Can't drop from default group */
- if (rdtgrp == &rdtgroup_default)
+ if (rdtgrp == &rdtgroup_default) {
+ rdt_last_cmd_puts("Can't drop CPUs from default group\n");
return -EINVAL;
+ }
/* Give any dropped cpus to rdtgroup_default */
cpumask_or(&rdtgroup_default.cpu_mask,
@@ -357,8 +387,10 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
}
rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ rdt_last_cmd_clear();
if (!rdtgrp) {
ret = -ENOENT;
+ rdt_last_cmd_puts("directory was removed\n");
goto unlock;
}
@@ -367,13 +399,16 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
else
ret = cpumask_parse(buf, newmask);
- if (ret)
+ if (ret) {
+ rdt_last_cmd_puts("bad cpu list/mask\n");
goto unlock;
+ }
/* check that user didn't specify any offline cpus */
cpumask_andnot(tmpmask, newmask, cpu_online_mask);
if (cpumask_weight(tmpmask)) {
ret = -EINVAL;
+ rdt_last_cmd_puts("can only assign online cpus\n");
goto unlock;
}
@@ -452,6 +487,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
*/
atomic_dec(&rdtgrp->waitcount);
kfree(callback);
+ rdt_last_cmd_puts("task exited\n");
} else {
/*
* For ctrl_mon groups move both closid and rmid.
@@ -462,10 +498,12 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
tsk->closid = rdtgrp->closid;
tsk->rmid = rdtgrp->mon.rmid;
} else if (rdtgrp->type == RDTMON_GROUP) {
- if (rdtgrp->mon.parent->closid == tsk->closid)
+ if (rdtgrp->mon.parent->closid == tsk->closid) {
tsk->rmid = rdtgrp->mon.rmid;
- else
+ } else {
+ rdt_last_cmd_puts("Can't move task to different control group\n");
ret = -EINVAL;
+ }
}
}
return ret;
@@ -484,8 +522,10 @@ static int rdtgroup_task_write_permission(struct task_struct *task,
*/
if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
!uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->euid, tcred->suid))
+ !uid_eq(cred->euid, tcred->suid)) {
+ rdt_last_cmd_printf("No permission to move task %d\n", task->pid);
ret = -EPERM;
+ }
put_cred(tcred);
return ret;
@@ -502,6 +542,7 @@ static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
tsk = find_task_by_vpid(pid);
if (!tsk) {
rcu_read_unlock();
+ rdt_last_cmd_printf("No task %d\n", pid);
return -ESRCH;
}
} else {
@@ -529,6 +570,7 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
return -EINVAL;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ rdt_last_cmd_clear();
if (rdtgrp)
ret = rdtgroup_move_task(pid, rdtgrp, of);
@@ -569,6 +611,21 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of,
return ret;
}
+static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
+ struct seq_file *seq, void *v)
+{
+ int len;
+
+ mutex_lock(&rdtgroup_mutex);
+ len = seq_buf_used(&last_cmd_status);
+ if (len)
+ seq_printf(seq, "%.*s", len, last_cmd_status_buf);
+ else
+ seq_puts(seq, "ok\n");
+ mutex_unlock(&rdtgroup_mutex);
+ return 0;
+}
+
static int rdt_num_closids_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
@@ -686,6 +743,13 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
/* rdtgroup information files for one cache resource. */
static struct rftype res_common_files[] = {
{
+ .name = "last_cmd_status",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdt_last_cmd_status_show,
+ .fflags = RF_TOP_INFO,
+ },
+ {
.name = "num_closids",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
@@ -855,6 +919,10 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
return PTR_ERR(kn_info);
kernfs_get(kn_info);
+ ret = rdtgroup_add_files(kn_info, RF_TOP_INFO);
+ if (ret)
+ goto out_destroy;
+
for_each_alloc_enabled_rdt_resource(r) {
fflags = r->fflags | RF_CTRL_INFO;
ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags);
@@ -1081,6 +1149,7 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
struct dentry *dentry;
int ret;
+ cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
/*
* resctrl file system can only be mounted once.
@@ -1130,12 +1199,12 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
goto out_mondata;
if (rdt_alloc_capable)
- static_branch_enable(&rdt_alloc_enable_key);
+ static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
if (rdt_mon_capable)
- static_branch_enable(&rdt_mon_enable_key);
+ static_branch_enable_cpuslocked(&rdt_mon_enable_key);
if (rdt_alloc_capable || rdt_mon_capable)
- static_branch_enable(&rdt_enable_key);
+ static_branch_enable_cpuslocked(&rdt_enable_key);
if (is_mbm_enabled()) {
r = &rdt_resources_all[RDT_RESOURCE_L3];
@@ -1156,7 +1225,9 @@ out_info:
out_cdp:
cdp_disable();
out:
+ rdt_last_cmd_clear();
mutex_unlock(&rdtgroup_mutex);
+ cpus_read_unlock();
return dentry;
}
@@ -1295,9 +1366,7 @@ static void rmdir_all_sub(void)
kfree(rdtgrp);
}
/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
- get_online_cpus();
update_closid_rmid(cpu_online_mask, &rdtgroup_default);
- put_online_cpus();
kernfs_remove(kn_info);
kernfs_remove(kn_mongrp);
@@ -1308,6 +1377,7 @@ static void rdt_kill_sb(struct super_block *sb)
{
struct rdt_resource *r;
+ cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
/*Put everything back to default values. */
@@ -1315,11 +1385,12 @@ static void rdt_kill_sb(struct super_block *sb)
reset_all_ctrls(r);
cdp_disable();
rmdir_all_sub();
- static_branch_disable(&rdt_alloc_enable_key);
- static_branch_disable(&rdt_mon_enable_key);
- static_branch_disable(&rdt_enable_key);
+ static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
+ static_branch_disable_cpuslocked(&rdt_mon_enable_key);
+ static_branch_disable_cpuslocked(&rdt_enable_key);
kernfs_kill_sb(sb);
mutex_unlock(&rdtgroup_mutex);
+ cpus_read_unlock();
}
static struct file_system_type rdt_fs_type = {
@@ -1524,8 +1595,10 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
int ret;
prdtgrp = rdtgroup_kn_lock_live(prgrp_kn);
+ rdt_last_cmd_clear();
if (!prdtgrp) {
ret = -ENODEV;
+ rdt_last_cmd_puts("directory was removed\n");
goto out_unlock;
}
@@ -1533,6 +1606,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
if (!rdtgrp) {
ret = -ENOSPC;
+ rdt_last_cmd_puts("kernel out of memory\n");
goto out_unlock;
}
*r = rdtgrp;
@@ -1544,6 +1618,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp);
if (IS_ERR(kn)) {
ret = PTR_ERR(kn);
+ rdt_last_cmd_puts("kernfs create error\n");
goto out_free_rgrp;
}
rdtgrp->kn = kn;
@@ -1557,24 +1632,31 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
kernfs_get(kn);
ret = rdtgroup_kn_set_ugid(kn);
- if (ret)
+ if (ret) {
+ rdt_last_cmd_puts("kernfs perm error\n");
goto out_destroy;
+ }
- files = RFTYPE_BASE | RFTYPE_CTRL;
files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype);
ret = rdtgroup_add_files(kn, files);
- if (ret)
+ if (ret) {
+ rdt_last_cmd_puts("kernfs fill error\n");
goto out_destroy;
+ }
if (rdt_mon_capable) {
ret = alloc_rmid();
- if (ret < 0)
+ if (ret < 0) {
+ rdt_last_cmd_puts("out of RMIDs\n");
goto out_destroy;
+ }
rdtgrp->mon.rmid = ret;
ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
- if (ret)
+ if (ret) {
+ rdt_last_cmd_puts("kernfs subdir error\n");
goto out_idfree;
+ }
}
kernfs_activate(kn);
@@ -1652,8 +1734,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
kn = rdtgrp->kn;
ret = closid_alloc();
- if (ret < 0)
+ if (ret < 0) {
+ rdt_last_cmd_puts("out of CLOSIDs\n");
goto out_common_fail;
+ }
closid = ret;
rdtgrp->closid = closid;
@@ -1665,8 +1749,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
* of tasks and cpus to monitor.
*/
ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
- if (ret)
+ if (ret) {
+ rdt_last_cmd_puts("kernfs subdir error\n");
goto out_id_free;
+ }
}
goto out_unlock;
@@ -1902,6 +1988,9 @@ int __init rdtgroup_init(void)
{
int ret = 0;
+ seq_buf_init(&last_cmd_status, last_cmd_status_buf,
+ sizeof(last_cmd_status_buf));
+
ret = rdtgroup_setup_root();
if (ret)
return ret;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 87cc9ab7a13c..4ca632a06e0b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -204,7 +204,7 @@ static int error_context(struct mce *m)
return IN_KERNEL;
}
-static int mce_severity_amd_smca(struct mce *m, int err_ctx)
+static int mce_severity_amd_smca(struct mce *m, enum context err_ctx)
{
u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank);
u32 low, high;
@@ -245,6 +245,9 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc
if (m->status & MCI_STATUS_UC) {
+ if (ctx == IN_KERNEL)
+ return MCE_PANIC_SEVERITY;
+
/*
* On older systems where overflow_recov flag is not present, we
* should simply panic if an error overflow occurs. If
@@ -255,10 +258,6 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc
if (mce_flags.smca)
return mce_severity_amd_smca(m, ctx);
- /* software can try to contain */
- if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL))
- return MCE_PANIC_SEVERITY;
-
/* kill current process */
return MCE_AR_SEVERITY;
} else {
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3b413065c613..b1d616d08eee 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1367,13 +1367,12 @@ static void __start_timer(struct timer_list *t, unsigned long interval)
local_irq_restore(flags);
}
-static void mce_timer_fn(unsigned long data)
+static void mce_timer_fn(struct timer_list *t)
{
- struct timer_list *t = this_cpu_ptr(&mce_timer);
- int cpu = smp_processor_id();
+ struct timer_list *cpu_t = this_cpu_ptr(&mce_timer);
unsigned long iv;
- WARN_ON(cpu != data);
+ WARN_ON(cpu_t != t);
iv = __this_cpu_read(mce_next_interval);
@@ -1763,17 +1762,15 @@ static void mce_start_timer(struct timer_list *t)
static void __mcheck_cpu_setup_timer(void)
{
struct timer_list *t = this_cpu_ptr(&mce_timer);
- unsigned int cpu = smp_processor_id();
- setup_pinned_timer(t, mce_timer_fn, cpu);
+ timer_setup(t, mce_timer_fn, TIMER_PINNED);
}
static void __mcheck_cpu_init_timer(void)
{
struct timer_list *t = this_cpu_ptr(&mce_timer);
- unsigned int cpu = smp_processor_id();
- setup_pinned_timer(t, mce_timer_fn, cpu);
+ timer_setup(t, mce_timer_fn, TIMER_PINNED);
mce_start_timer(t);
}
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 236324e83a3a..85eb5fc180c8 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -254,9 +254,9 @@ static void __init ms_hyperv_init_platform(void)
#endif
}
-const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
+const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
.name = "Microsoft Hyper-V",
.detect = ms_hyperv_platform,
- .init_platform = ms_hyperv_init_platform,
+ .type = X86_HYPER_MS_HYPERV,
+ .init.init_platform = ms_hyperv_init_platform,
};
-EXPORT_SYMBOL(x86_hyper_ms_hyperv);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 40ed26852ebd..8e005329648b 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -205,10 +205,10 @@ static bool __init vmware_legacy_x2apic_available(void)
(eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0;
}
-const __refconst struct hypervisor_x86 x86_hyper_vmware = {
+const __initconst struct hypervisor_x86 x86_hyper_vmware = {
.name = "VMware",
.detect = vmware_platform,
- .init_platform = vmware_platform_setup,
- .x2apic_available = vmware_legacy_x2apic_available,
+ .type = X86_HYPER_VMWARE,
+ .init.init_platform = vmware_platform_setup,
+ .init.x2apic_available = vmware_legacy_x2apic_available,
};
-EXPORT_SYMBOL(x86_hyper_vmware);
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-03 20:51:33 +0000