summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/amd.c49
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c9
-rw-r--r--arch/x86/kernel/cpu/bugs.c33
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c5
-rw-r--r--arch/x86/kernel/cpu/common.c86
-rw-r--r--arch/x86/kernel/cpu/cpu.h2
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c2
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c12
-rw-r--r--arch/x86/kernel/cpu/mce/core.c32
-rw-r--r--arch/x86/kernel/cpu/mce/dev-mcelog.c3
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h44
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c76
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c45
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c44
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c72
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c54
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c13
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h28
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c30
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c307
-rw-r--r--arch/x86/kernel/cpu/scattered.c2
-rw-r--r--arch/x86/kernel/cpu/tsx.c1
-rw-r--r--arch/x86/kernel/cpu/vmware.c2
23 files changed, 733 insertions, 218 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f769d6d08b43..380753b14cab 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -956,7 +956,7 @@ static void init_amd(struct cpuinfo_x86 *c)
init_amd_cacheinfo(c);
- if (cpu_has(c, X86_FEATURE_XMM2)) {
+ if (!cpu_has(c, X86_FEATURE_LFENCE_RDTSC) && cpu_has(c, X86_FEATURE_XMM2)) {
/*
* Use LFENCE for execution serialization. On families which
* don't have that MSR, LFENCE is already serializing.
@@ -1158,24 +1158,43 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
return false;
}
-void set_dr_addr_mask(unsigned long mask, int dr)
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[4], amd_dr_addr_mask);
+
+static unsigned int amd_msr_dr_addr_masks[] = {
+ MSR_F16H_DR0_ADDR_MASK,
+ MSR_F16H_DR1_ADDR_MASK,
+ MSR_F16H_DR1_ADDR_MASK + 1,
+ MSR_F16H_DR1_ADDR_MASK + 2
+};
+
+void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr)
{
- if (!boot_cpu_has(X86_FEATURE_BPEXT))
+ int cpu = smp_processor_id();
+
+ if (!cpu_feature_enabled(X86_FEATURE_BPEXT))
return;
- switch (dr) {
- case 0:
- wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0);
- break;
- case 1:
- case 2:
- case 3:
- wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0);
- break;
- default:
- break;
- }
+ if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks)))
+ return;
+
+ if (per_cpu(amd_dr_addr_mask, cpu)[dr] == mask)
+ return;
+
+ wrmsr(amd_msr_dr_addr_masks[dr], mask, 0);
+ per_cpu(amd_dr_addr_mask, cpu)[dr] = mask;
+}
+
+unsigned long amd_get_dr_addr_mask(unsigned int dr)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_BPEXT))
+ return 0;
+
+ if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks)))
+ return 0;
+
+ return per_cpu(amd_dr_addr_mask[dr], smp_processor_id());
}
+EXPORT_SYMBOL_GPL(amd_get_dr_addr_mask);
u32 amd_get_highest_perf(void)
{
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 1f60a2b27936..fdbb5f07448f 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void)
static void disable_freq_invariance_workfn(struct work_struct *work)
{
+ int cpu;
+
static_branch_disable(&arch_scale_freq_key);
+
+ /*
+ * Set arch_freq_scale to a default value on all cpus
+ * This negates the effect of scaling
+ */
+ for_each_possible_cpu(cpu)
+ per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE;
}
static DECLARE_WORK(disable_freq_invariance_work,
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bca0bd8f4846..cf81848b72f4 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -33,6 +33,7 @@
#include <asm/e820/api.h>
#include <asm/hypervisor.h>
#include <asm/tlbflush.h>
+#include <asm/cpu.h>
#include "cpu.h"
@@ -86,7 +87,7 @@ void update_spec_ctrl_cond(u64 val)
wrmsrl(MSR_IA32_SPEC_CTRL, val);
}
-u64 spec_ctrl_current(void)
+noinstr u64 spec_ctrl_current(void)
{
return this_cpu_read(x86_spec_ctrl_current);
}
@@ -144,9 +145,17 @@ void __init check_bugs(void)
* 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))
+ if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) {
rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+ /*
+ * Previously running kernel (kexec), may have some controls
+ * turned ON. Clear them and let the mitigations setup below
+ * rediscover them based on configuration.
+ */
+ x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK;
+ }
+
/* Select the proper CPU mitigations before patching alternatives: */
spectre_v1_select_mitigation();
spectre_v2_select_mitigation();
@@ -1229,9 +1238,9 @@ static const char * const spectre_v2_strings[] = {
[SPECTRE_V2_NONE] = "Vulnerable",
[SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines",
[SPECTRE_V2_LFENCE] = "Mitigation: LFENCE",
- [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS",
- [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE",
- [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines",
+ [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS",
+ [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced / Automatic IBRS + LFENCE",
+ [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced / Automatic IBRS + Retpolines",
[SPECTRE_V2_IBRS] = "Mitigation: IBRS",
};
@@ -1300,7 +1309,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
cmd == SPECTRE_V2_CMD_EIBRS_LFENCE ||
cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) &&
!boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
- pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n",
+ pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n",
mitigation_options[i].option);
return SPECTRE_V2_CMD_AUTO;
}
@@ -1486,8 +1495,12 @@ static void __init spectre_v2_select_mitigation(void)
pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);
if (spectre_v2_in_ibrs_mode(mode)) {
- x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
- update_spec_ctrl(x86_spec_ctrl_base);
+ if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
+ msr_set_bit(MSR_EFER, _EFER_AUTOIBRS);
+ } else {
+ x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
+ update_spec_ctrl(x86_spec_ctrl_base);
+ }
}
switch (mode) {
@@ -1571,8 +1584,8 @@ static void __init spectre_v2_select_mitigation(void)
/*
* Retpoline protects the kernel, but doesn't protect firmware. IBRS
* and Enhanced IBRS protect firmware too, so enable IBRS around
- * firmware calls only when IBRS / Enhanced IBRS aren't otherwise
- * enabled.
+ * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't
+ * otherwise enabled.
*
* Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
* the user might select retpoline on the kernel command line and if
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index f4e5aa27eec6..4063e8991211 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -734,7 +734,7 @@ void init_hygon_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;
+ unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0;
unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
@@ -835,9 +835,6 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
case LVL_3:
l3 += cache_table[k].size;
break;
- case LVL_TRACE:
- trace += cache_table[k].size;
- break;
}
break;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9cfca3d7d0e2..a394bbba7a4b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -567,7 +567,7 @@ static __init int setup_disable_pku(char *arg)
return 1;
}
__setup("nopku", setup_disable_pku);
-#endif /* CONFIG_X86_64 */
+#endif
#ifdef CONFIG_X86_KERNEL_IBT
@@ -1093,6 +1093,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
if (c->extended_cpuid_level >= 0x8000001f)
c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f);
+ if (c->extended_cpuid_level >= 0x80000021)
+ c->x86_capability[CPUID_8000_0021_EAX] = cpuid_eax(0x80000021);
+
init_scattered_cpuid_features(c);
init_speculation_control(c);
@@ -1226,8 +1229,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
- VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
+ VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
/* Zhaoxin Family 7 */
VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
@@ -1256,6 +1259,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define MMIO_SBDS BIT(2)
/* CPU is affected by RETbleed, speculating where you would not expect it */
#define RETBLEED BIT(3)
+/* CPU is affected by SMT (cross-thread) return predictions */
+#define SMT_RSB BIT(4)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
@@ -1287,8 +1292,8 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
- VULNBL_AMD(0x17, RETBLEED),
- VULNBL_HYGON(0x18, RETBLEED),
+ VULNBL_AMD(0x17, RETBLEED | SMT_RSB),
+ VULNBL_HYGON(0x18, RETBLEED | SMT_RSB),
{}
};
@@ -1338,8 +1343,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
!cpu_has(c, X86_FEATURE_AMD_SSB_NO))
setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
- if (ia32_cap & ARCH_CAP_IBRS_ALL)
+ /*
+ * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature
+ * flag and protect from vendor-specific bugs via the whitelist.
+ */
+ if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) {
setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
+ if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
+ !(ia32_cap & ARCH_CAP_PBRSB_NO))
+ setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
+ }
if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) &&
!(ia32_cap & ARCH_CAP_MDS_NO)) {
@@ -1401,10 +1414,8 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_RETBLEED);
}
- if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) &&
- !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
- !(ia32_cap & ARCH_CAP_PBRSB_NO))
- setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
+ if (cpu_matches(cpu_vuln_blacklist, SMT_RSB))
+ setup_force_cpu_bug(X86_BUG_SMT_RSB);
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
@@ -1682,9 +1693,7 @@ void check_null_seg_clears_base(struct cpuinfo_x86 *c)
if (!IS_ENABLED(CONFIG_X86_64))
return;
- /* Zen3 CPUs advertise Null Selector Clears Base in CPUID. */
- if (c->extended_cpuid_level >= 0x80000021 &&
- cpuid_eax(0x80000021) & BIT(6))
+ if (cpu_has(c, X86_FEATURE_NULL_SEL_CLR_BASE))
return;
/*
@@ -1953,13 +1962,13 @@ void __init identify_boot_cpu(void)
if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
pr_info("CET detected: Indirect Branch Tracking enabled\n");
#ifdef CONFIG_X86_32
- sysenter_setup();
enable_sep_cpu();
#endif
cpu_detect_tlb(&boot_cpu_data);
setup_cr_pinning();
tsx_init();
+ lkgs_init();
}
void identify_secondary_cpu(struct cpuinfo_x86 *c)
@@ -2125,7 +2134,6 @@ static void wait_for_master_cpu(int cpu)
#endif
}
-#ifdef CONFIG_X86_64
static inline void setup_getcpu(int cpu)
{
unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
@@ -2147,6 +2155,7 @@ static inline void setup_getcpu(int cpu)
write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S);
}
+#ifdef CONFIG_X86_64
static inline void ucode_cpu_init(int cpu)
{
if (cpu)
@@ -2166,8 +2175,6 @@ static inline void tss_setup_ist(struct tss_struct *tss)
#else /* CONFIG_X86_64 */
-static inline void setup_getcpu(int cpu) { }
-
static inline void ucode_cpu_init(int cpu)
{
show_ucode_info_early();
@@ -2297,30 +2304,45 @@ void cpu_init_secondary(void)
#endif
#ifdef CONFIG_MICROCODE_LATE_LOADING
-/*
+/**
+ * store_cpu_caps() - Store a snapshot of CPU capabilities
+ * @curr_info: Pointer where to store it
+ *
+ * Returns: None
+ */
+void store_cpu_caps(struct cpuinfo_x86 *curr_info)
+{
+ /* Reload CPUID max function as it might've changed. */
+ curr_info->cpuid_level = cpuid_eax(0);
+
+ /* Copy all capability leafs and pick up the synthetic ones. */
+ memcpy(&curr_info->x86_capability, &boot_cpu_data.x86_capability,
+ sizeof(curr_info->x86_capability));
+
+ /* Get the hardware CPUID leafs */
+ get_cpu_cap(curr_info);
+}
+
+/**
+ * microcode_check() - Check if any CPU capabilities changed after an update.
+ * @prev_info: CPU capabilities stored before an update.
+ *
* The microcode loader calls this upon late microcode load to recheck features,
* only when microcode has been updated. Caller holds microcode_mutex and CPU
* hotplug lock.
+ *
+ * Return: None
*/
-void microcode_check(void)
+void microcode_check(struct cpuinfo_x86 *prev_info)
{
- struct cpuinfo_x86 info;
+ struct cpuinfo_x86 curr_info;
perf_check_microcode();
- /* Reload CPUID max function as it might've changed. */
- info.cpuid_level = cpuid_eax(0);
-
- /*
- * Copy all capability leafs to pick up the synthetic ones so that
- * memcmp() below doesn't fail on that. The ones coming from CPUID will
- * get overwritten in get_cpu_cap().
- */
- memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability));
-
- get_cpu_cap(&info);
+ store_cpu_caps(&curr_info);
- if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)))
+ if (!memcmp(&prev_info->x86_capability, &curr_info.x86_capability,
+ sizeof(prev_info->x86_capability)))
return;
pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 7c9b5893c30a..57a5349e6954 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -83,6 +83,4 @@ unsigned int aperfmperf_get_khz(int cpu);
extern void x86_spec_ctrl_setup_ap(void);
extern void update_srbds_msr(void);
-extern u64 x86_read_arch_cap_msr(void);
-
#endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index d95221117129..f6748c8bd647 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -68,6 +68,8 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC },
{ X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
{ X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_BMEC, X86_FEATURE_CQM_MBM_TOTAL },
+ { X86_FEATURE_BMEC, X86_FEATURE_CQM_MBM_LOCAL },
{ X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
{ X86_FEATURE_AVX512_FP16, X86_FEATURE_AVX512BW },
{ X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES },
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 10fb5b5c9efa..23c5072fbbb7 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -306,6 +306,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
if ((low & BIT(5)) && !((high >> 5) & 0x3))
high |= BIT(5);
+ this_cpu_ptr(mce_banks_array)[bank].lsb_in_status = !!(low & BIT(8));
+
wrmsr(smca_config, low, high);
}
@@ -736,15 +738,7 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
if (m.status & MCI_STATUS_ADDRV) {
m.addr = addr;
- /*
- * Extract [55:<lsb>] where lsb is the least significant
- * *valid* bit of the address bits.
- */
- if (mce_flags.smca) {
- u8 lsb = (m.addr >> 56) & 0x3f;
-
- m.addr &= GENMASK_ULL(55, lsb);
- }
+ smca_extract_err_addr(&m);
}
if (mce_flags.smca) {
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2c8ec5c71712..7832a69d170e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -67,13 +67,7 @@ DEFINE_PER_CPU(unsigned, mce_exception_count);
DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks);
-struct mce_bank {
- u64 ctl; /* subevents to enable */
-
- __u64 init : 1, /* initialise bank? */
- __reserved_1 : 63;
-};
-static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array);
+DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array);
#define ATTR_LEN 16
/* One object for each MCE bank, shared by all CPUs */
@@ -579,7 +573,7 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
mce->severity != MCE_DEFERRED_SEVERITY)
return NOTIFY_DONE;
- pfn = mce->addr >> PAGE_SHIFT;
+ pfn = (mce->addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT;
if (!memory_failure(pfn, 0)) {
set_mce_nospec(pfn);
mce->kflags |= MCE_HANDLED_UC;
@@ -633,15 +627,7 @@ static noinstr void mce_read_aux(struct mce *m, int i)
m->addr <<= shift;
}
- /*
- * Extract [55:<lsb>] where lsb is the least significant
- * *valid* bit of the address bits.
- */
- if (mce_flags.smca) {
- u8 lsb = (m->addr >> 56) & 0x3f;
-
- m->addr &= GENMASK_ULL(55, lsb);
- }
+ smca_extract_err_addr(m);
}
if (mce_flags.smca) {
@@ -1308,6 +1294,7 @@ static void kill_me_maybe(struct callback_head *cb)
{
struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
int flags = MF_ACTION_REQUIRED;
+ unsigned long pfn;
int ret;
p->mce_count = 0;
@@ -1316,9 +1303,10 @@ static void kill_me_maybe(struct callback_head *cb)
if (!p->mce_ripv)
flags |= MF_MUST_KILL;
- ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags);
+ pfn = (p->mce_addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT;
+ ret = memory_failure(pfn, flags);
if (!ret) {
- set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
+ set_mce_nospec(pfn);
sync_core();
return;
}
@@ -1340,11 +1328,13 @@ static void kill_me_maybe(struct callback_head *cb)
static void kill_me_never(struct callback_head *cb)
{
struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
+ unsigned long pfn;
p->mce_count = 0;
pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr);
- if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0))
- set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
+ pfn = (p->mce_addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT;
+ if (!memory_failure(pfn, 0))
+ set_mce_nospec(pfn);
}
static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *))
diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c
index 100fbeebdc72..a05ac0716ecf 100644
--- a/arch/x86/kernel/cpu/mce/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c
@@ -105,8 +105,7 @@ static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
{
char *p;
- strncpy(mce_helper, buf, sizeof(mce_helper));
- mce_helper[sizeof(mce_helper)-1] = 0;
+ strscpy(mce_helper, buf, sizeof(mce_helper));
p = strchr(mce_helper, '\n');
if (p)
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 7e03f5b7f6bd..91a415553c27 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -177,6 +177,24 @@ struct mce_vendor_flags {
extern struct mce_vendor_flags mce_flags;
+struct mce_bank {
+ /* subevents to enable */
+ u64 ctl;
+
+ /* initialise bank? */
+ __u64 init : 1,
+
+ /*
+ * (AMD) MCA_CONFIG[McaLsbInStatusSupported]: When set, this bit indicates
+ * the LSB field is found in MCA_STATUS and not in MCA_ADDR.
+ */
+ lsb_in_status : 1,
+
+ __reserved_1 : 62;
+};
+
+DECLARE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array);
+
enum mca_msr {
MCA_CTL,
MCA_STATUS,
@@ -189,8 +207,34 @@ extern bool filter_mce(struct mce *m);
#ifdef CONFIG_X86_MCE_AMD
extern bool amd_filter_mce(struct mce *m);
+
+/*
+ * If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits
+ * [56:0] of MCA_STATUS, else in bits [55:0] of MCA_ADDR.
+ */
+static __always_inline void smca_extract_err_addr(struct mce *m)
+{
+ u8 lsb;
+
+ if (!mce_flags.smca)
+ return;
+
+ if (this_cpu_ptr(mce_banks_array)[m->bank].lsb_in_status) {
+ lsb = (m->status >> 24) & 0x3f;
+
+ m->addr &= GENMASK_ULL(56, lsb);
+
+ return;
+ }
+
+ lsb = (m->addr >> 56) & 0x3f;
+
+ m->addr &= GENMASK_ULL(55, lsb);
+}
+
#else
static inline bool amd_filter_mce(struct mce *m) { return false; }
+static inline void smca_extract_err_addr(struct mce *m) { }
#endif
#ifdef CONFIG_X86_ANCIENT_MCE
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 56471f750762..9eb457b10341 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -55,7 +55,9 @@ struct cont_desc {
};
static u32 ucode_new_rev;
-static u8 amd_ucode_patch[PATCH_MAX_SIZE];
+
+/* One blob per node. */
+static u8 amd_ucode_patch[MAX_NUMNODES][PATCH_MAX_SIZE];
/*
* Microcode patch container file is prepended to the initrd in cpio
@@ -330,8 +332,9 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true);
if (ret < 0) {
/*
- * Patch verification failed, skip to the next
- * container, if there's one:
+ * Patch verification failed, skip to the next container, if
+ * there is one. Before exit, check whether that container has
+ * found a patch already. If so, use it.
*/
goto out;
} else if (ret > 0) {
@@ -350,6 +353,7 @@ skip:
size -= patch_size + SECTION_HDR_SIZE;
}
+out:
/*
* If we have found a patch (desc->mc), it means we're looking at the
* container which has a patch for this CPU so return 0 to mean, @ucode
@@ -364,7 +368,6 @@ skip:
return 0;
}
-out:
return orig_size - size;
}
@@ -414,8 +417,7 @@ static int __apply_microcode_amd(struct microcode_amd *mc)
*
* Returns true if container found (sets @desc), false otherwise.
*/
-static bool
-apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch)
+static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch)
{
struct cont_desc desc = { 0 };
u8 (*patch)[PATCH_MAX_SIZE];
@@ -428,7 +430,7 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p
patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch);
#else
new_rev = &ucode_new_rev;
- patch = &amd_ucode_patch;
+ patch = &amd_ucode_patch[0];
#endif
desc.cpuid_1_eax = cpuid_1_eax;
@@ -481,7 +483,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
return false;
}
-static void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret)
+static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret)
{
struct ucode_cpu_info *uci;
struct cpio_data cp;
@@ -511,11 +513,11 @@ void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
{
struct cpio_data cp = { };
- __load_ucode_amd(cpuid_1_eax, &cp);
+ find_blobs_in_containers(cpuid_1_eax, &cp);
if (!(cp.data && cp.size))
return;
- apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, true);
+ early_apply_microcode(cpuid_1_eax, cp.data, cp.size, true);
}
void load_ucode_amd_ap(unsigned int cpuid_1_eax)
@@ -546,15 +548,14 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
}
}
- __load_ucode_amd(cpuid_1_eax, &cp);
+ find_blobs_in_containers(cpuid_1_eax, &cp);
if (!(cp.data && cp.size))
return;
- apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false);
+ early_apply_microcode(cpuid_1_eax, cp.data, cp.size, false);
}
-static enum ucode_state
-load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
+static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
{
@@ -572,19 +573,19 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
if (!desc.mc)
return -EINVAL;
- ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
+ ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
if (ret > UCODE_UPDATED)
return -EINVAL;
return 0;
}
-void reload_ucode_amd(void)
+void reload_ucode_amd(unsigned int cpu)
{
- struct microcode_amd *mc;
u32 rev, dummy __always_unused;
+ struct microcode_amd *mc;
- mc = (struct microcode_amd *)amd_ucode_patch;
+ mc = (struct microcode_amd *)amd_ucode_patch[cpu_to_node(cpu)];
rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
@@ -816,6 +817,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
return 0;
}
+/* Scan the blob in @data and add microcode patches to the cache. */
static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
size_t size)
{
@@ -850,9 +852,10 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
return UCODE_OK;
}
-static enum ucode_state
-load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
+static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
{
+ struct cpuinfo_x86 *c;
+ unsigned int nid, cpu;
struct ucode_patch *p;
enum ucode_state ret;
@@ -865,22 +868,22 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
return ret;
}
- p = find_patch(0);
- if (!p) {
- return ret;
- } else {
- if (boot_cpu_data.microcode >= p->patch_id)
- return ret;
+ for_each_node(nid) {
+ cpu = cpumask_first(cpumask_of_node(nid));
+ c = &cpu_data(cpu);
- ret = UCODE_NEW;
- }
+ p = find_patch(cpu);
+ if (!p)
+ continue;
- /* save BSP's matching patch for early load */
- if (!save)
- return ret;
+ if (c->microcode >= p->patch_id)
+ continue;
- memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
- memcpy(amd_ucode_patch, p->data, min_t(u32, p->size, PATCH_MAX_SIZE));
+ ret = UCODE_NEW;
+
+ memset(&amd_ucode_patch[nid], 0, PATCH_MAX_SIZE);
+ memcpy(&amd_ucode_patch[nid], p->data, min_t(u32, p->size, PATCH_MAX_SIZE));
+ }
return ret;
}
@@ -905,14 +908,9 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
{
char fw_name[36] = "amd-ucode/microcode_amd.bin";
struct cpuinfo_x86 *c = &cpu_data(cpu);
- bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
enum ucode_state ret = UCODE_NFOUND;
const struct firmware *fw;
- /* reload ucode container only on the boot cpu */
- if (!bsp)
- return UCODE_OK;
-
if (c->x86 >= 0x15)
snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
@@ -925,7 +923,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
if (!verify_container(fw->data, fw->size, false))
goto fw_release;
- ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
+ ret = load_microcode_amd(c->x86, fw->data, fw->size);
fw_release:
release_firmware(fw);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 712aafff96e0..7a329e561354 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -298,7 +298,7 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
#endif
}
-void reload_early_microcode(void)
+void reload_early_microcode(unsigned int cpu)
{
int vendor, family;
@@ -312,7 +312,7 @@ void reload_early_microcode(void)
break;
case X86_VENDOR_AMD:
if (family >= 0x10)
- reload_ucode_amd();
+ reload_ucode_amd(cpu);
break;
default:
break;
@@ -409,10 +409,10 @@ static int __reload_late(void *info)
goto wait_for_siblings;
if (err >= UCODE_NFOUND) {
- if (err == UCODE_ERROR)
+ if (err == UCODE_ERROR) {
pr_warn("Error reloading microcode on CPU %d\n", cpu);
-
- ret = -1;
+ ret = -1;
+ }
}
wait_for_siblings:
@@ -438,6 +438,7 @@ wait_for_siblings:
static int microcode_reload_late(void)
{
int old = boot_cpu_data.microcode, ret;
+ struct cpuinfo_x86 prev_info;
pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
pr_err("You should switch to early loading, if possible.\n");
@@ -445,12 +446,21 @@ static int microcode_reload_late(void)
atomic_set(&late_cpus_in, 0);
atomic_set(&late_cpus_out, 0);
- ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
- if (ret == 0)
- microcode_check();
+ /*
+ * Take a snapshot before the microcode update in order to compare and
+ * check whether any bits changed after an update.
+ */
+ store_cpu_caps(&prev_info);
- pr_info("Reload completed, microcode revision: 0x%x -> 0x%x\n",
- old, boot_cpu_data.microcode);
+ ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+ if (!ret) {
+ pr_info("Reload succeeded, microcode revision: 0x%x -> 0x%x\n",
+ old, boot_cpu_data.microcode);
+ microcode_check(&prev_info);
+ } else {
+ pr_info("Reload failed, current microcode revision: 0x%x\n",
+ boot_cpu_data.microcode);
+ }
return ret;
}
@@ -465,11 +475,8 @@ static ssize_t reload_store(struct device *dev,
ssize_t ret = 0;
ret = kstrtoul(buf, 0, &val);
- if (ret)
- return ret;
-
- if (val != 1)
- return size;
+ if (ret || val != 1)
+ return -EINVAL;
cpus_read_lock();
@@ -507,7 +514,7 @@ static ssize_t version_show(struct device *dev,
return sprintf(buf, "0x%x\n", uci->cpu_sig.rev);
}
-static ssize_t pf_show(struct device *dev,
+static ssize_t processor_flags_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
@@ -515,8 +522,8 @@ static ssize_t pf_show(struct device *dev,
return sprintf(buf, "0x%x\n", uci->cpu_sig.pf);
}
-static DEVICE_ATTR(version, 0444, version_show, NULL);
-static DEVICE_ATTR(processor_flags, 0444, pf_show, NULL);
+static DEVICE_ATTR_RO(version);
+static DEVICE_ATTR_RO(processor_flags);
static struct attribute *mc_default_attrs[] = {
&dev_attr_version.attr,
@@ -557,7 +564,7 @@ void microcode_bsp_resume(void)
if (uci->mc)
microcode_ops->apply_microcode(cpu);
else
- reload_early_microcode();
+ reload_early_microcode(cpu);
}
static struct syscore_ops mc_syscore_ops = {
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index cac2bdb57f0b..467cf37ea90a 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -305,14 +305,11 @@ static bool load_builtin_intel_microcode(struct cpio_data *cp)
return false;
}
-/*
- * Print ucode update info.
- */
-static void
-print_ucode_info(struct ucode_cpu_info *uci, unsigned int date)
+static void print_ucode_info(int old_rev, int new_rev, unsigned int date)
{
- pr_info_once("microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n",
- uci->cpu_sig.rev,
+ pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n",
+ old_rev,
+ new_rev,
date & 0xffff,
date >> 24,
(date >> 16) & 0xff);
@@ -322,6 +319,7 @@ print_ucode_info(struct ucode_cpu_info *uci, unsigned int date)
static int delay_ucode_info;
static int current_mc_date;
+static int early_old_rev;
/*
* Print early updated ucode info after printk works. This is delayed info dump.
@@ -332,7 +330,7 @@ void show_ucode_info_early(void)
if (delay_ucode_info) {
intel_cpu_collect_info(&uci);
- print_ucode_info(&uci, current_mc_date);
+ print_ucode_info(early_old_rev, uci.cpu_sig.rev, current_mc_date);
delay_ucode_info = 0;
}
}
@@ -341,40 +339,32 @@ void show_ucode_info_early(void)
* At this point, we can not call printk() yet. Delay printing microcode info in
* show_ucode_info_early() until printk() works.
*/
-static void print_ucode(struct ucode_cpu_info *uci)
+static void print_ucode(int old_rev, int new_rev, int date)
{
- struct microcode_intel *mc;
int *delay_ucode_info_p;
int *current_mc_date_p;
-
- mc = uci->mc;
- if (!mc)
- return;
+ int *early_old_rev_p;
delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
+ early_old_rev_p = (int *)__pa_nodebug(&early_old_rev);
*delay_ucode_info_p = 1;
- *current_mc_date_p = mc->hdr.date;
+ *current_mc_date_p = date;
+ *early_old_rev_p = old_rev;
}
#else
-static inline void print_ucode(struct ucode_cpu_info *uci)
+static inline void print_ucode(int old_rev, int new_rev, int date)
{
- struct microcode_intel *mc;
-
- mc = uci->mc;
- if (!mc)
- return;
-
- print_ucode_info(uci, mc->hdr.date);
+ print_ucode_info(old_rev, new_rev, date);
}
#endif
static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
{
struct microcode_intel *mc;
- u32 rev;
+ u32 rev, old_rev;
mc = uci->mc;
if (!mc)
@@ -391,6 +381,8 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
return UCODE_OK;
}
+ old_rev = rev;
+
/*
* Writeback and invalidate caches before updating microcode to avoid
* internal issues depending on what the microcode is updating.
@@ -407,9 +399,9 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
uci->cpu_sig.rev = rev;
if (early)
- print_ucode(uci);
+ print_ucode(old_rev, uci->cpu_sig.rev, mc->hdr.date);
else
- print_ucode_info(uci, mc->hdr.date);
+ print_ucode_info(old_rev, uci->cpu_sig.rev, mc->hdr.date);
return 0;
}
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 46668e255421..f924a76c6923 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -37,9 +37,76 @@
/* Is Linux running as the root partition? */
bool hv_root_partition;
+/* Is Linux running on nested Microsoft Hypervisor */
+bool hv_nested;
struct ms_hyperv_info ms_hyperv;
#if IS_ENABLED(CONFIG_HYPERV)
+static inline unsigned int hv_get_nested_reg(unsigned int reg)
+{
+ if (hv_is_sint_reg(reg))
+ return reg - HV_REGISTER_SINT0 + HV_REGISTER_NESTED_SINT0;
+
+ switch (reg) {
+ case HV_REGISTER_SIMP:
+ return HV_REGISTER_NESTED_SIMP;
+ case HV_REGISTER_SIEFP:
+ return HV_REGISTER_NESTED_SIEFP;
+ case HV_REGISTER_SVERSION:
+ return HV_REGISTER_NESTED_SVERSION;
+ case HV_REGISTER_SCONTROL:
+ return HV_REGISTER_NESTED_SCONTROL;
+ case HV_REGISTER_EOM:
+ return HV_REGISTER_NESTED_EOM;
+ default:
+ return reg;
+ }
+}
+
+u64 hv_get_non_nested_register(unsigned int reg)
+{
+ u64 value;
+
+ if (hv_is_synic_reg(reg) && hv_isolation_type_snp())
+ hv_ghcb_msr_read(reg, &value);
+ else
+ rdmsrl(reg, value);
+ return value;
+}
+EXPORT_SYMBOL_GPL(hv_get_non_nested_register);
+
+void hv_set_non_nested_register(unsigned int reg, u64 value)
+{
+ if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) {
+ hv_ghcb_msr_write(reg, value);
+
+ /* Write proxy bit via wrmsl instruction */
+ if (hv_is_sint_reg(reg))
+ wrmsrl(reg, value | 1 << 20);
+ } else {
+ wrmsrl(reg, value);
+ }
+}
+EXPORT_SYMBOL_GPL(hv_set_non_nested_register);
+
+u64 hv_get_register(unsigned int reg)
+{
+ if (hv_nested)
+ reg = hv_get_nested_reg(reg);
+
+ return hv_get_non_nested_register(reg);
+}
+EXPORT_SYMBOL_GPL(hv_get_register);
+
+void hv_set_register(unsigned int reg, u64 value)
+{
+ if (hv_nested)
+ reg = hv_get_nested_reg(reg);
+
+ hv_set_non_nested_register(reg, value);
+}
+EXPORT_SYMBOL_GPL(hv_set_register);
+
static void (*vmbus_handler)(void);
static void (*hv_stimer0_handler)(void);
static void (*hv_kexec_handler)(void);
@@ -301,6 +368,11 @@ static void __init ms_hyperv_init_platform(void)
pr_info("Hyper-V: running as root partition\n");
}
+ if (ms_hyperv.hints & HV_X64_HYPERV_NESTED) {
+ hv_nested = true;
+ pr_info("Hyper-V: running on a nested hypervisor\n");
+ }
+
/*
* Extract host information.
*/
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index c98e52ff5f20..030d3b409768 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -100,6 +100,18 @@ struct rdt_hw_resource rdt_resources_all[] = {
.fflags = RFTYPE_RES_MB,
},
},
+ [RDT_RESOURCE_SMBA] =
+ {
+ .r_resctrl = {
+ .rid = RDT_RESOURCE_SMBA,
+ .name = "SMBA",
+ .cache_level = 3,
+ .domains = domain_init(RDT_RESOURCE_SMBA),
+ .parse_ctrlval = parse_bw,
+ .format_str = "%d=%*u",
+ .fflags = RFTYPE_RES_MB,
+ },
+ },
};
/*
@@ -150,6 +162,13 @@ bool is_mba_sc(struct rdt_resource *r)
if (!r)
return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc;
+ /*
+ * The software controller support is only applicable to MBA resource.
+ * Make sure to check for resource type.
+ */
+ if (r->rid != RDT_RESOURCE_MBA)
+ return false;
+
return r->membw.mba_sc;
}
@@ -213,9 +232,15 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
union cpuid_0x10_3_eax eax;
union cpuid_0x10_x_edx edx;
- u32 ebx, ecx;
+ u32 ebx, ecx, subleaf;
+
+ /*
+ * Query CPUID_Fn80000020_EDX_x01 for MBA and
+ * CPUID_Fn80000020_EDX_x02 for SMBA
+ */
+ subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 : 1;
- cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full);
+ cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full);
hw_res->num_closid = edx.split.cos_max + 1;
r->default_ctrl = MAX_MBA_BW_AMD;
@@ -647,6 +672,8 @@ enum {
RDT_FLAG_L2_CAT,
RDT_FLAG_L2_CDP,
RDT_FLAG_MBA,
+ RDT_FLAG_SMBA,
+ RDT_FLAG_BMEC,
};
#define RDT_OPT(idx, n, f) \
@@ -670,6 +697,8 @@ static struct rdt_options rdt_options[] __initdata = {
RDT_OPT(RDT_FLAG_L2_CAT, "l2cat", X86_FEATURE_CAT_L2),
RDT_OPT(RDT_FLAG_L2_CDP, "l2cdp", X86_FEATURE_CDP_L2),
RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA),
+ RDT_OPT(RDT_FLAG_SMBA, "smba", X86_FEATURE_SMBA),
+ RDT_OPT(RDT_FLAG_BMEC, "bmec", X86_FEATURE_BMEC),
};
#define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options)
@@ -699,7 +728,7 @@ static int __init set_rdt_options(char *str)
}
__setup("rdt", set_rdt_options);
-static bool __init rdt_cpu_has(int flag)
+bool __init rdt_cpu_has(int flag)
{
bool ret = boot_cpu_has(flag);
struct rdt_options *o;
@@ -734,6 +763,19 @@ static __init bool get_mem_config(void)
return false;
}
+static __init bool get_slow_mem_config(void)
+{
+ struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_SMBA];
+
+ if (!rdt_cpu_has(X86_FEATURE_SMBA))
+ return false;
+
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ return __rdt_get_mem_config_amd(&hw_res->r_resctrl);
+
+ return false;
+}
+
static __init bool get_rdt_alloc_resources(void)
{
struct rdt_resource *r;
@@ -764,6 +806,9 @@ static __init bool get_rdt_alloc_resources(void)
if (get_mem_config())
ret = true;
+ if (get_slow_mem_config())
+ ret = true;
+
return ret;
}
@@ -853,6 +898,9 @@ static __init void rdt_init_res_defs_amd(void)
} else if (r->rid == RDT_RESOURCE_MBA) {
hw_res->msr_base = MSR_IA32_MBA_BW_BASE;
hw_res->msr_update = mba_wrmsr_amd;
+ } else if (r->rid == RDT_RESOURCE_SMBA) {
+ hw_res->msr_base = MSR_IA32_SMBA_BW_BASE;
+ hw_res->msr_update = mba_wrmsr_amd;
}
}
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 1df0e3262bca..eb07d4435391 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -209,7 +209,7 @@ static int parse_line(char *line, struct resctrl_schema *s,
unsigned long dom_id;
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
- r->rid == RDT_RESOURCE_MBA) {
+ (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
return -EINVAL;
}
@@ -310,7 +310,6 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
enum resctrl_conf_type t;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
- int cpu;
u32 idx;
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
@@ -341,13 +340,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
if (cpumask_empty(cpu_mask))
goto done;
- cpu = get_cpu();
- /* Update resource control msr on this CPU if it's in cpu_mask. */
- if (cpumask_test_cpu(cpu, cpu_mask))
- rdt_ctrl_update(&msr_param);
- /* Update resource control msr on other CPUs. */
- smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
- put_cpu();
+
+ /* Update resource control msr on all the CPUs. */
+ on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
done:
free_cpumask_var(cpu_mask);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 5ebd28e6aa0c..8edecc5763d8 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -30,6 +30,29 @@
*/
#define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
+/* Reads to Local DRAM Memory */
+#define READS_TO_LOCAL_MEM BIT(0)
+
+/* Reads to Remote DRAM Memory */
+#define READS_TO_REMOTE_MEM BIT(1)
+
+/* Non-Temporal Writes to Local Memory */
+#define NON_TEMP_WRITE_TO_LOCAL_MEM BIT(2)
+
+/* Non-Temporal Writes to Remote Memory */
+#define NON_TEMP_WRITE_TO_REMOTE_MEM BIT(3)
+
+/* Reads to Local Memory the system identifies as "Slow Memory" */
+#define READS_TO_LOCAL_S_MEM BIT(4)
+
+/* Reads to Remote Memory the system identifies as "Slow Memory" */
+#define READS_TO_REMOTE_S_MEM BIT(5)
+
+/* Dirty Victims to All Types of Memory */
+#define DIRTY_VICTIMS_TO_ALL_MEM BIT(6)
+
+/* Max event bits supported */
+#define MAX_EVT_CONFIG_BITS GENMASK(6, 0)
struct rdt_fs_context {
struct kernfs_fs_context kfc;
@@ -52,11 +75,13 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
* struct mon_evt - Entry in the event list of a resource
* @evtid: event id
* @name: name of the event
+ * @configurable: true if the event is configurable
* @list: entry in &rdt_resource->evt_list
*/
struct mon_evt {
enum resctrl_event_id evtid;
char *name;
+ bool configurable;
struct list_head list;
};
@@ -409,6 +434,7 @@ enum resctrl_res_level {
RDT_RESOURCE_L3,
RDT_RESOURCE_L2,
RDT_RESOURCE_MBA,
+ RDT_RESOURCE_SMBA,
/* Must be the last */
RDT_NUM_RESOURCES,
@@ -511,6 +537,7 @@ void closid_free(int closid);
int alloc_rmid(void);
void free_rmid(u32 rmid);
int rdt_get_mon_l3_config(struct rdt_resource *r);
+bool __init rdt_cpu_has(int flag);
void mon_event_count(void *info);
int rdtgroup_mondata_show(struct seq_file *m, void *arg);
void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
@@ -527,5 +554,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
void __check_limbo(struct rdt_domain *d, bool force_free);
void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
void __init thread_throttle_mode_init(void);
+void __init mbm_config_rftype_init(const char *config);
#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 77538abeb72a..7fe51488e136 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -204,6 +204,23 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
}
}
+/*
+ * Assumes that hardware counters are also reset and thus that there is
+ * no need to record initial non-zero counts.
+ */
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d)
+{
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+
+ if (is_mbm_total_enabled())
+ memset(hw_dom->arch_mbm_total, 0,
+ sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
+
+ if (is_mbm_local_enabled())
+ memset(hw_dom->arch_mbm_local, 0,
+ sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
+}
+
static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
{
u64 shift = 64 - width, chunks;
@@ -763,7 +780,7 @@ static void l3_mon_evt_init(struct rdt_resource *r)
list_add_tail(&mbm_local_event.list, &r->evt_list);
}
-int rdt_get_mon_l3_config(struct rdt_resource *r)
+int __init rdt_get_mon_l3_config(struct rdt_resource *r)
{
unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
@@ -800,6 +817,17 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
if (ret)
return ret;
+ if (rdt_cpu_has(X86_FEATURE_BMEC)) {
+ if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
+ mbm_total_event.configurable = true;
+ mbm_config_rftype_init("mbm_total_bytes_config");
+ }
+ if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
+ mbm_local_event.configurable = true;
+ mbm_config_rftype_init("mbm_local_bytes_config");
+ }
+ }
+
l3_mon_evt_init(r);
r->mon_capable = true;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 5993da21d822..e2c1599d1b37 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -325,12 +325,7 @@ static void update_cpu_closid_rmid(void *info)
static void
update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
{
- int cpu = get_cpu();
-
- if (cpumask_test_cpu(cpu, cpu_mask))
- update_cpu_closid_rmid(r);
- smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1);
- put_cpu();
+ on_each_cpu_mask(cpu_mask, update_cpu_closid_rmid, r, 1);
}
static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
@@ -1003,8 +998,11 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
struct rdt_resource *r = of->kn->parent->priv;
struct mon_evt *mevt;
- list_for_each_entry(mevt, &r->evt_list, list)
+ list_for_each_entry(mevt, &r->evt_list, list) {
seq_printf(seq, "%s\n", mevt->name);
+ if (mevt->configurable)
+ seq_printf(seq, "%s_config\n", mevt->name);
+ }
return 0;
}
@@ -1215,7 +1213,7 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
- if (r->rid == RDT_RESOURCE_MBA)
+ if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
continue;
has_cache = true;
list_for_each_entry(d, &r->domains, list) {
@@ -1404,7 +1402,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
ctrl = resctrl_arch_get_config(r, d,
closid,
type);
- if (r->rid == RDT_RESOURCE_MBA)
+ if (r->rid == RDT_RESOURCE_MBA ||
+ r->rid == RDT_RESOURCE_SMBA)
size = ctrl;
else
size = rdtgroup_cbm_to_size(r, d, ctrl);
@@ -1421,6 +1420,248 @@ out:
return ret;
}
+struct mon_config_info {
+ u32 evtid;
+ u32 mon_config;
+};
+
+#define INVALID_CONFIG_INDEX UINT_MAX
+
+/**
+ * mon_event_config_index_get - get the hardware index for the
+ * configurable event
+ * @evtid: event id.
+ *
+ * Return: 0 for evtid == QOS_L3_MBM_TOTAL_EVENT_ID
+ * 1 for evtid == QOS_L3_MBM_LOCAL_EVENT_ID
+ * INVALID_CONFIG_INDEX for invalid evtid
+ */
+static inline unsigned int mon_event_config_index_get(u32 evtid)
+{
+ switch (evtid) {
+ case QOS_L3_MBM_TOTAL_EVENT_ID:
+ return 0;
+ case QOS_L3_MBM_LOCAL_EVENT_ID:
+ return 1;
+ default:
+ /* Should never reach here */
+ return INVALID_CONFIG_INDEX;
+ }
+}
+
+static void mon_event_config_read(void *info)
+{
+ struct mon_config_info *mon_info = info;
+ unsigned int index;
+ u64 msrval;
+
+ index = mon_event_config_index_get(mon_info->evtid);
+ if (index == INVALID_CONFIG_INDEX) {
+ pr_warn_once("Invalid event id %d\n", mon_info->evtid);
+ return;
+ }
+ rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);
+
+ /* Report only the valid event configuration bits */
+ mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
+}
+
+static void mondata_config_read(struct rdt_domain *d, struct mon_config_info *mon_info)
+{
+ smp_call_function_any(&d->cpu_mask, mon_event_config_read, mon_info, 1);
+}
+
+static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
+{
+ struct mon_config_info mon_info = {0};
+ struct rdt_domain *dom;
+ bool sep = false;
+
+ mutex_lock(&rdtgroup_mutex);
+
+ list_for_each_entry(dom, &r->domains, list) {
+ if (sep)
+ seq_puts(s, ";");
+
+ memset(&mon_info, 0, sizeof(struct mon_config_info));
+ mon_info.evtid = evtid;
+ mondata_config_read(dom, &mon_info);
+
+ seq_printf(s, "%d=0x%02x", dom->id, mon_info.mon_config);
+ sep = true;
+ }
+ seq_puts(s, "\n");
+
+ mutex_unlock(&rdtgroup_mutex);
+
+ return 0;
+}
+
+static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
+ struct seq_file *seq, void *v)
+{
+ struct rdt_resource *r = of->kn->parent->priv;
+
+ mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);
+
+ return 0;
+}
+
+static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
+ struct seq_file *seq, void *v)
+{
+ struct rdt_resource *r = of->kn->parent->priv;
+
+ mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);
+
+ return 0;
+}
+
+static void mon_event_config_write(void *info)
+{
+ struct mon_config_info *mon_info = info;
+ unsigned int index;
+
+ index = mon_event_config_index_get(mon_info->evtid);
+ if (index == INVALID_CONFIG_INDEX) {
+ pr_warn_once("Invalid event id %d\n", mon_info->evtid);
+ return;
+ }
+ wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0);
+}
+
+static int mbm_config_write_domain(struct rdt_resource *r,
+ struct rdt_domain *d, u32 evtid, u32 val)
+{
+ struct mon_config_info mon_info = {0};
+ int ret = 0;
+
+ /* mon_config cannot be more than the supported set of events */
+ if (val > MAX_EVT_CONFIG_BITS) {
+ rdt_last_cmd_puts("Invalid event configuration\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Read the current config value first. If both are the same then
+ * no need to write it again.
+ */
+ mon_info.evtid = evtid;
+ mondata_config_read(d, &mon_info);
+ if (mon_info.mon_config == val)
+ goto out;
+
+ mon_info.mon_config = val;
+
+ /*
+ * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the
+ * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE
+ * are scoped at the domain level. Writing any of these MSRs
+ * on one CPU is observed by all the CPUs in the domain.
+ */
+ smp_call_function_any(&d->cpu_mask, mon_event_config_write,
+ &mon_info, 1);
+
+ /*
+ * When an Event Configuration is changed, the bandwidth counters
+ * for all RMIDs and Events will be cleared by the hardware. The
+ * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for
+ * every RMID on the next read to any event for every RMID.
+ * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62)
+ * cleared while it is tracked by the hardware. Clear the
+ * mbm_local and mbm_total counts for all the RMIDs.
+ */
+ resctrl_arch_reset_rmid_all(r, d);
+
+out:
+ return ret;
+}
+
+static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
+{
+ char *dom_str = NULL, *id_str;
+ unsigned long dom_id, val;
+ struct rdt_domain *d;
+ int ret = 0;
+
+next:
+ if (!tok || tok[0] == '\0')
+ return 0;
+
+ /* Start processing the strings for each domain */
+ dom_str = strim(strsep(&tok, ";"));
+ id_str = strsep(&dom_str, "=");
+
+ if (!id_str || kstrtoul(id_str, 10, &dom_id)) {
+ rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n");
+ return -EINVAL;
+ }
+
+ if (!dom_str || kstrtoul(dom_str, 16, &val)) {
+ rdt_last_cmd_puts("Non-numeric event configuration value\n");
+ return -EINVAL;
+ }
+
+ list_for_each_entry(d, &r->domains, list) {
+ if (d->id == dom_id) {
+ ret = mbm_config_write_domain(r, d, evtid, val);
+ if (ret)
+ return -EINVAL;
+ goto next;
+ }
+ }
+
+ return -EINVAL;
+}
+
+static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ struct rdt_resource *r = of->kn->parent->priv;
+ int ret;
+
+ /* Valid input requires a trailing newline */
+ if (nbytes == 0 || buf[nbytes - 1] != '\n')
+ return -EINVAL;
+
+ mutex_lock(&rdtgroup_mutex);
+
+ rdt_last_cmd_clear();
+
+ buf[nbytes - 1] = '\0';
+
+ ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
+
+ mutex_unlock(&rdtgroup_mutex);
+
+ return ret ?: nbytes;
+}
+
+static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ struct rdt_resource *r = of->kn->parent->priv;
+ int ret;
+
+ /* Valid input requires a trailing newline */
+ if (nbytes == 0 || buf[nbytes - 1] != '\n')
+ return -EINVAL;
+
+ mutex_lock(&rdtgroup_mutex);
+
+ rdt_last_cmd_clear();
+
+ buf[nbytes - 1] = '\0';
+
+ ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);
+
+ mutex_unlock(&rdtgroup_mutex);
+
+ return ret ?: nbytes;
+}
+
/* rdtgroup information files for one cache resource. */
static struct rftype res_common_files[] = {
{
@@ -1520,6 +1761,20 @@ static struct rftype res_common_files[] = {
.fflags = RF_MON_INFO | RFTYPE_RES_CACHE,
},
{
+ .name = "mbm_total_bytes_config",
+ .mode = 0644,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = mbm_total_bytes_config_show,
+ .write = mbm_total_bytes_config_write,
+ },
+ {
+ .name = "mbm_local_bytes_config",
+ .mode = 0644,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = mbm_local_bytes_config_show,
+ .write = mbm_local_bytes_config_write,
+ },
+ {
.name = "cpus",
.mode = 0644,
.kf_ops = &rdtgroup_kf_single_ops,
@@ -1625,6 +1880,15 @@ void __init thread_throttle_mode_init(void)
rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB;
}
+void __init mbm_config_rftype_init(const char *config)
+{
+ struct rftype *rft;
+
+ rft = rdtgroup_get_rftype_by_name(config);
+ if (rft)
+ rft->fflags = RF_MON_INFO | RFTYPE_RES_CACHE;
+}
+
/**
* rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
* @r: The resource group with which the file is associated.
@@ -1866,13 +2130,9 @@ static int set_cache_qos_cfg(int level, bool enable)
/* Pick one CPU from each domain instance to update MSR */
cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
}
- cpu = get_cpu();
- /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
- if (cpumask_test_cpu(cpu, cpu_mask))
- update(&enable);
- /* Update QOS_CFG MSR on all other cpus in cpu_mask. */
- smp_call_function_many(cpu_mask, update, &enable, 1);
- put_cpu();
+
+ /* Update QOS_CFG MSR on all the CPUs in cpu_mask */
+ on_each_cpu_mask(cpu_mask, update, &enable, 1);
free_cpumask_var(cpu_mask);
@@ -2349,7 +2609,7 @@ static int reset_all_ctrls(struct rdt_resource *r)
struct msr_param msr_param;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
- int i, cpu;
+ int i;
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
return -ENOMEM;
@@ -2370,13 +2630,9 @@ static int reset_all_ctrls(struct rdt_resource *r)
for (i = 0; i < hw_res->num_closid; i++)
hw_dom->ctrl_val[i] = r->default_ctrl;
}
- cpu = get_cpu();
- /* Update CBM on this cpu if it's in cpu_mask. */
- if (cpumask_test_cpu(cpu, cpu_mask))
- rdt_ctrl_update(&msr_param);
- /* Update CBM on all other cpus in cpu_mask. */
- smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
- put_cpu();
+
+ /* Update CBM on all the CPUs in cpu_mask */
+ on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
free_cpumask_var(cpu_mask);
@@ -2855,7 +3111,8 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
- if (r->rid == RDT_RESOURCE_MBA) {
+ if (r->rid == RDT_RESOURCE_MBA ||
+ r->rid == RDT_RESOURCE_SMBA) {
rdtgroup_init_mba(r, rdtgrp->closid);
if (is_mba_sc(r))
continue;
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index f53944fb8f7f..0dad49a09b7a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -45,6 +45,8 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
{ X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 },
+ { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 },
+ { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
{ X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 },
{ X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 },
{ 0, 0, 0, 0, 0 }
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index 8009c8346d8f..b31ee4f1657a 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -11,6 +11,7 @@
#include <linux/cpufeature.h>
#include <asm/cmdline.h>
+#include <asm/cpu.h>
#include "cpu.h"
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 02039ec3597d..11f83d07925e 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -143,7 +143,7 @@ static __init int parse_no_stealacc(char *arg)
}
early_param("no-steal-acc", parse_no_stealacc);
-static unsigned long long notrace vmware_sched_clock(void)
+static noinstr u64 vmware_sched_clock(void)
{
unsigned long long ns;