summaryrefslogtreecommitdiffstats
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.c5
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c6
-rw-r--r--arch/x86/kernel/cpu/bugs.c17
-rw-r--r--arch/x86/kernel/cpu/common.c84
-rw-r--r--arch/x86/kernel/cpu/cpu.h1
-rw-r--r--arch/x86/kernel/cpu/cyrix.c14
-rw-r--r--arch/x86/kernel/cpu/hygon.c5
-rw-r--r--arch/x86/kernel/cpu/intel.c34
-rw-r--r--arch/x86/kernel/cpu/intel_epb.c216
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c52
-rw-r--r--arch/x86/kernel/cpu/mce/core.c102
-rw-r--r--arch/x86/kernel/cpu/mce/genpool.c3
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c16
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h9
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c7
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c71
-rw-r--r--arch/x86/kernel/cpu/proc.c10
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c4
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c3
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c182
21 files changed, 534 insertions, 309 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index cfd24f9f7614..1796d2bdcaaa 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -28,7 +28,7 @@ obj-y += cpuid-deps.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
-obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o
+obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o intel_epb.o
obj-$(CONFIG_CPU_SUP_AMD) += amd.o
obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o
obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 01004bfb1a1b..fb6a64bd765f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -82,11 +82,14 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
* performance at the same time..
*/
+#ifdef CONFIG_X86_32
extern __visible void vide(void);
-__asm__(".globl vide\n"
+__asm__(".text\n"
+ ".globl vide\n"
".type vide, @function\n"
".align 4\n"
"vide: ret\n");
+#endif
static void init_amd_k5(struct cpuinfo_x86 *c)
{
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 804c49493938..64d5aec24203 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -83,7 +83,7 @@ unsigned int aperfmperf_get_khz(int cpu)
if (!cpu_khz)
return 0;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
@@ -99,7 +99,7 @@ void arch_freq_prepare_all(void)
if (!cpu_khz)
return;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return;
for_each_online_cpu(cpu)
@@ -115,7 +115,7 @@ unsigned int arch_freq_get_on_cpu(int cpu)
if (!cpu_khz)
return 0;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 2da82eff0eb4..29630393f300 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -275,7 +275,7 @@ static const struct {
const char *option;
enum spectre_v2_user_cmd cmd;
bool secure;
-} v2_user_options[] __initdata = {
+} v2_user_options[] __initconst = {
{ "auto", SPECTRE_V2_USER_CMD_AUTO, false },
{ "off", SPECTRE_V2_USER_CMD_NONE, false },
{ "on", SPECTRE_V2_USER_CMD_FORCE, true },
@@ -419,7 +419,7 @@ static const struct {
const char *option;
enum spectre_v2_mitigation_cmd cmd;
bool secure;
-} mitigation_options[] __initdata = {
+} mitigation_options[] __initconst = {
{ "off", SPECTRE_V2_CMD_NONE, false },
{ "on", SPECTRE_V2_CMD_FORCE, true },
{ "retpoline", SPECTRE_V2_CMD_RETPOLINE, false },
@@ -440,7 +440,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
char arg[20];
int ret, i;
- if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+ if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") ||
+ cpu_mitigations_off())
return SPECTRE_V2_CMD_NONE;
ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
@@ -658,7 +659,7 @@ static const char * const ssb_strings[] = {
static const struct {
const char *option;
enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[] __initdata = {
+} ssb_mitigation_options[] __initconst = {
{ "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 */
@@ -672,7 +673,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
char arg[20];
int ret, i;
- if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+ if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") ||
+ cpu_mitigations_off()) {
return SPEC_STORE_BYPASS_CMD_NONE;
} else {
ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
@@ -1008,6 +1010,11 @@ static void __init l1tf_select_mitigation(void)
if (!boot_cpu_has_bug(X86_BUG_L1TF))
return;
+ if (cpu_mitigations_off())
+ l1tf_mitigation = L1TF_MITIGATION_OFF;
+ else if (cpu_mitigations_auto_nosmt())
+ l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+
override_cache_bits(&boot_cpu_data);
switch (l1tf_mitigation) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index cb28e98a0659..8739bdfe9bdf 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -372,6 +372,8 @@ static bool pku_disabled;
static __always_inline void setup_pku(struct cpuinfo_x86 *c)
{
+ struct pkru_state *pk;
+
/* check the boot processor, plus compile options for PKU: */
if (!cpu_feature_enabled(X86_FEATURE_PKU))
return;
@@ -382,6 +384,9 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c)
return;
cr4_set_bits(X86_CR4_PKE);
+ pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
+ if (pk)
+ pk->pkru = init_pkru_value;
/*
* Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
* cpuid bit to be set. We need to ensure that we
@@ -507,19 +512,6 @@ void load_percpu_segment(int cpu)
DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
#endif
-#ifdef CONFIG_X86_64
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
- [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
- [DEBUG_STACK - 1] = DEBUG_STKSZ
-};
-#endif
-
/* Load the original GDT from the per-cpu structure */
void load_direct_gdt(int cpu)
{
@@ -1511,9 +1503,9 @@ static __init int setup_clearcpuid(char *arg)
__setup("clearcpuid=", setup_clearcpuid);
#ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(union irq_stack_union,
- irq_stack_union) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union);
+DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
+ fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
+EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
/*
* The following percpu variables are hot. Align current_task to
@@ -1523,9 +1515,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
&init_task;
EXPORT_PER_CPU_SYMBOL(current_task);
-DEFINE_PER_CPU(char *, irq_stack_ptr) =
- init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE;
-
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
@@ -1562,23 +1552,7 @@ void syscall_init(void)
X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
}
-/*
- * Copies of the original ist values from the tss are only accessed during
- * debugging, no special alignment required.
- */
-DEFINE_PER_CPU(struct orig_ist, orig_ist);
-
-static DEFINE_PER_CPU(unsigned long, debug_stack_addr);
DEFINE_PER_CPU(int, debug_stack_usage);
-
-int is_debug_stack(unsigned long addr)
-{
- return __this_cpu_read(debug_stack_usage) ||
- (addr <= __this_cpu_read(debug_stack_addr) &&
- addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ));
-}
-NOKPROBE_SYMBOL(is_debug_stack);
-
DEFINE_PER_CPU(u32, debug_idt_ctr);
void debug_stack_set_zero(void)
@@ -1668,7 +1642,7 @@ static void setup_getcpu(int cpu)
unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
struct desc_struct d = { };
- if (static_cpu_has(X86_FEATURE_RDTSCP))
+ if (boot_cpu_has(X86_FEATURE_RDTSCP))
write_rdtscp_aux(cpudata);
/* Store CPU and node number in limit. */
@@ -1690,17 +1664,14 @@ static void setup_getcpu(int cpu)
* initialized (naturally) in the bootstrap process, such as the GDT
* and IDT. We reload them nevertheless, this function acts as a
* 'CPU state barrier', nothing should get across.
- * A lot of state is already set up in PDA init for 64 bit
*/
#ifdef CONFIG_X86_64
void cpu_init(void)
{
- struct orig_ist *oist;
+ int cpu = raw_smp_processor_id();
struct task_struct *me;
struct tss_struct *t;
- unsigned long v;
- int cpu = raw_smp_processor_id();
int i;
wait_for_master_cpu(cpu);
@@ -1715,7 +1686,6 @@ void cpu_init(void)
load_ucode_ap();
t = &per_cpu(cpu_tss_rw, cpu);
- oist = &per_cpu(orig_ist, cpu);
#ifdef CONFIG_NUMA
if (this_cpu_read(numa_node) == 0 &&
@@ -1753,16 +1723,11 @@ void cpu_init(void)
/*
* set up and load the per-CPU TSS
*/
- if (!oist->ist[0]) {
- char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
-
- for (v = 0; v < N_EXCEPTION_STACKS; v++) {
- estacks += exception_stack_sizes[v];
- oist->ist[v] = t->x86_tss.ist[v] =
- (unsigned long)estacks;
- if (v == DEBUG_STACK-1)
- per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks;
- }
+ if (!t->x86_tss.ist[0]) {
+ t->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF);
+ t->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI);
+ t->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB);
+ t->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE);
}
t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
@@ -1864,23 +1829,6 @@ void cpu_init(void)
}
#endif
-static void bsp_resume(void)
-{
- if (this_cpu->c_bsp_resume)
- this_cpu->c_bsp_resume(&boot_cpu_data);
-}
-
-static struct syscore_ops cpu_syscore_ops = {
- .resume = bsp_resume,
-};
-
-static int __init init_cpu_syscore(void)
-{
- register_syscore_ops(&cpu_syscore_ops);
- return 0;
-}
-core_initcall(init_cpu_syscore);
-
/*
* The microcode loader calls this upon late microcode load to recheck features,
* only when microcode has been updated. Caller holds microcode_mutex and CPU
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 5eb946b9a9f3..c0e2407abdd6 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -14,7 +14,6 @@ struct cpu_dev {
void (*c_init)(struct cpuinfo_x86 *);
void (*c_identify)(struct cpuinfo_x86 *);
void (*c_detect_tlb)(struct cpuinfo_x86 *);
- void (*c_bsp_resume)(struct cpuinfo_x86 *);
int c_x86_vendor;
#ifdef CONFIG_X86_32
/* Optional vendor specific routine to obtain the cache size. */
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index d12226f60168..1d9b8aaea06c 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -124,7 +124,7 @@ static void set_cx86_reorder(void)
setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */
/* Load/Store Serialize to mem access disable (=reorder it) */
- setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80);
+ setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80);
/* set load/store serialize from 1GB to 4GB */
ccr3 |= 0xe0;
setCx86(CX86_CCR3, ccr3);
@@ -135,11 +135,11 @@ static void set_cx86_memwb(void)
pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n");
/* CCR2 bit 2: unlock NW bit */
- setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04);
+ setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04);
/* set 'Not Write-through' */
write_cr0(read_cr0() | X86_CR0_NW);
/* CCR2 bit 2: lock NW bit and set WT1 */
- setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14);
+ setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14);
}
/*
@@ -153,14 +153,14 @@ static void geode_configure(void)
local_irq_save(flags);
/* Suspend on halt power saving and enable #SUSP pin */
- setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88);
+ setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
ccr3 = getCx86(CX86_CCR3);
setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */
/* FPU fast, DTE cache, Mem bypass */
- setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38);
+ setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38);
setCx86(CX86_CCR3, ccr3); /* disable MAPEN */
set_cx86_memwb();
@@ -296,7 +296,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
/* GXm supports extended cpuid levels 'ala' AMD */
if (c->cpuid_level == 2) {
/* Enable cxMMX extensions (GX1 Datasheet 54) */
- setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1);
+ setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1);
/*
* GXm : 0x30 ... 0x5f GXm datasheet 51
@@ -319,7 +319,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
if (dir1 > 7) {
dir0_msn++; /* M II */
/* Enable MMX extensions (App note 108) */
- setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1);
+ setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1);
} else {
/* A 6x86MX - it has the bug. */
set_cpu_bug(c, X86_BUG_COMA);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index cf25405444ab..415621ddb8a2 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -19,6 +19,8 @@
#include "cpu.h"
+#define APICID_SOCKET_ID_BIT 6
+
/*
* nodes_per_socket: Stores the number of nodes per socket.
* Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
@@ -87,6 +89,9 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
if (!err)
c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+ /* Socket ID is ApicId[6] for these processors. */
+ c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
+
cacheinfo_hygon_init_llc_id(c, cpu, node_id);
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fc3c07fe7df5..f17c1a714779 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -596,36 +596,6 @@ detect_keyid_bits:
c->x86_phys_bits -= keyid_bits;
}
-static void init_intel_energy_perf(struct cpuinfo_x86 *c)
-{
- u64 epb;
-
- /*
- * Initialize MSR_IA32_ENERGY_PERF_BIAS if not already initialized.
- * (x86_energy_perf_policy(8) is available to change it at run-time.)
- */
- if (!cpu_has(c, X86_FEATURE_EPB))
- return;
-
- rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
- if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
- return;
-
- pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
- pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
- epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
- wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
-}
-
-static void intel_bsp_resume(struct cpuinfo_x86 *c)
-{
- /*
- * MSR_IA32_ENERGY_PERF_BIAS is lost across suspend/resume,
- * so reinitialize it properly like during bootup:
- */
- init_intel_energy_perf(c);
-}
-
static void init_cpuid_fault(struct cpuinfo_x86 *c)
{
u64 msr;
@@ -763,8 +733,6 @@ static void init_intel(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_TME))
detect_tme(c);
- init_intel_energy_perf(c);
-
init_intel_misc_features(c);
}
@@ -1023,9 +991,7 @@ static const struct cpu_dev intel_cpu_dev = {
.c_detect_tlb = intel_detect_tlb,
.c_early_init = early_init_intel,
.c_init = init_intel,
- .c_bsp_resume = intel_bsp_resume,
.c_x86_vendor = X86_VENDOR_INTEL,
};
cpu_dev_register(intel_cpu_dev);
-
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
new file mode 100644
index 000000000000..f4dd73396f28
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Performance and Energy Bias Hint support.
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author:
+ * Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ */
+
+#include <linux/cpuhotplug.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/syscore_ops.h>
+#include <linux/pm.h>
+
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
+
+/**
+ * DOC: overview
+ *
+ * The Performance and Energy Bias Hint (EPB) allows software to specify its
+ * preference with respect to the power-performance tradeoffs present in the
+ * processor. Generally, the EPB is expected to be set by user space (directly
+ * via sysfs or with the help of the x86_energy_perf_policy tool), but there are
+ * two reasons for the kernel to update it.
+ *
+ * First, there are systems where the platform firmware resets the EPB during
+ * system-wide transitions from sleep states back into the working state
+ * effectively causing the previous EPB updates by user space to be lost.
+ * Thus the kernel needs to save the current EPB values for all CPUs during
+ * system-wide transitions to sleep states and restore them on the way back to
+ * the working state. That can be achieved by saving EPB for secondary CPUs
+ * when they are taken offline during transitions into system sleep states and
+ * for the boot CPU in a syscore suspend operation, so that it can be restored
+ * for the boot CPU in a syscore resume operation and for the other CPUs when
+ * they are brought back online. However, CPUs that are already offline when
+ * a system-wide PM transition is started are not taken offline again, but their
+ * EPB values may still be reset by the platform firmware during the transition,
+ * so in fact it is necessary to save the EPB of any CPU taken offline and to
+ * restore it when the given CPU goes back online at all times.
+ *
+ * Second, on many systems the initial EPB value coming from the platform
+ * firmware is 0 ('performance') and at least on some of them that is because
+ * the platform firmware does not initialize EPB at all with the assumption that
+ * the OS will do that anyway. That sometimes is problematic, as it may cause
+ * the system battery to drain too fast, for example, so it is better to adjust
+ * it on CPU bring-up and if the initial EPB value for a given CPU is 0, the
+ * kernel changes it to 6 ('normal').
+ */
+
+static DEFINE_PER_CPU(u8, saved_epb);
+
+#define EPB_MASK 0x0fULL
+#define EPB_SAVED 0x10ULL
+#define MAX_EPB EPB_MASK
+
+static int intel_epb_save(void)
+{
+ u64 epb;
+
+ rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+ /*
+ * Ensure that saved_epb will always be nonzero after this write even if
+ * the EPB value read from the MSR is 0.
+ */
+ this_cpu_write(saved_epb, (epb & EPB_MASK) | EPB_SAVED);
+
+ return 0;
+}
+
+static void intel_epb_restore(void)
+{
+ u64 val = this_cpu_read(saved_epb);
+ u64 epb;
+
+ rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+ if (val) {
+ val &= EPB_MASK;
+ } else {
+ /*
+ * Because intel_epb_save() has not run for the current CPU yet,
+ * it is going online for the first time, so if its EPB value is
+ * 0 ('performance') at this point, assume that it has not been
+ * initialized by the platform firmware and set it to 6
+ * ('normal').
+ */
+ val = epb & EPB_MASK;
+ if (val == ENERGY_PERF_BIAS_PERFORMANCE) {
+ val = ENERGY_PERF_BIAS_NORMAL;
+ pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
+ }
+ }
+ wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
+}
+
+static struct syscore_ops intel_epb_syscore_ops = {
+ .suspend = intel_epb_save,
+ .resume = intel_epb_restore,
+};
+
+static const char * const energy_perf_strings[] = {
+ "performance",
+ "balance-performance",
+ "normal",
+ "balance-power",
+ "power"
+};
+static const u8 energ_perf_values[] = {
+ ENERGY_PERF_BIAS_PERFORMANCE,
+ ENERGY_PERF_BIAS_BALANCE_PERFORMANCE,
+ ENERGY_PERF_BIAS_NORMAL,
+ ENERGY_PERF_BIAS_BALANCE_POWERSAVE,
+ ENERGY_PERF_BIAS_POWERSAVE
+};
+
+static ssize_t energy_perf_bias_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ unsigned int cpu = dev->id;
+ u64 epb;
+ int ret;
+
+ ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+ if (ret < 0)
+ return ret;
+
+ return sprintf(buf, "%llu\n", epb);
+}
+
+static ssize_t energy_perf_bias_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned int cpu = dev->id;
+ u64 epb, val;
+ int ret;
+
+ ret = __sysfs_match_string(energy_perf_strings,
+ ARRAY_SIZE(energy_perf_strings), buf);
+ if (ret >= 0)
+ val = energ_perf_values[ret];
+ else if (kstrtou64(buf, 0, &val) || val > MAX_EPB)
+ return -EINVAL;
+
+ ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+ if (ret < 0)
+ return ret;
+
+ ret = wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
+ (epb & ~EPB_MASK) | val);
+ if (ret < 0)
+ return ret;
+
+ return count;
+}
+
+static DEVICE_ATTR_RW(energy_perf_bias);
+
+static struct attribute *intel_epb_attrs[] = {
+ &dev_attr_energy_perf_bias.attr,
+ NULL
+};
+
+static const struct attribute_group intel_epb_attr_group = {
+ .name = power_group_name,
+ .attrs = intel_epb_attrs
+};
+
+static int intel_epb_online(unsigned int cpu)
+{
+ struct device *cpu_dev = get_cpu_device(cpu);
+
+ intel_epb_restore();
+ if (!cpuhp_tasks_frozen)
+ sysfs_merge_group(&cpu_dev->kobj, &intel_epb_attr_group);
+
+ return 0;
+}
+
+static int intel_epb_offline(unsigned int cpu)
+{
+ struct device *cpu_dev = get_cpu_device(cpu);
+
+ if (!cpuhp_tasks_frozen)
+ sysfs_unmerge_group(&cpu_dev->kobj, &intel_epb_attr_group);
+
+ intel_epb_save();
+ return 0;
+}
+
+static __init int intel_epb_init(void)
+{
+ int ret;
+
+ if (!boot_cpu_has(X86_FEATURE_EPB))
+ return -ENODEV;
+
+ ret = cpuhp_setup_state(CPUHP_AP_X86_INTEL_EPB_ONLINE,
+ "x86/intel/epb:online", intel_epb_online,
+ intel_epb_offline);
+ if (ret < 0)
+ goto err_out_online;
+
+ register_syscore_ops(&intel_epb_syscore_ops);
+ return 0;
+
+err_out_online:
+ cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE);
+ return ret;
+}
+subsys_initcall(intel_epb_init);
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index e64de5149e50..d904aafe6409 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -563,33 +563,59 @@ out:
return offset;
}
+bool amd_filter_mce(struct mce *m)
+{
+ enum smca_bank_types bank_type = smca_get_bank_type(m->bank);
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+ u8 xec = (m->status >> 16) & 0x3F;
+
+ /* See Family 17h Models 10h-2Fh Erratum #1114. */
+ if (c->x86 == 0x17 &&
+ c->x86_model >= 0x10 && c->x86_model <= 0x2F &&
+ bank_type == SMCA_IF && xec == 10)
+ return true;
+
+ return false;
+}
+
/*
- * Turn off MC4_MISC thresholding banks on all family 0x15 models since
- * they're not supported there.
+ * Turn off thresholding banks for the following conditions:
+ * - MC4_MISC thresholding is not supported on Family 0x15.
+ * - Prevent possible spurious interrupts from the IF bank on Family 0x17
+ * Models 0x10-0x2F due to Erratum #1114.
*/
-void disable_err_thresholding(struct cpuinfo_x86 *c)
+void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
{
- int i;
+ int i, num_msrs;
u64 hwcr;
bool need_toggle;
- u32 msrs[] = {
- 0x00000413, /* MC4_MISC0 */
- 0xc0000408, /* MC4_MISC1 */
- };
+ u32 msrs[NR_BLOCKS];
+
+ if (c->x86 == 0x15 && bank == 4) {
+ msrs[0] = 0x00000413; /* MC4_MISC0 */
+ msrs[1] = 0xc0000408; /* MC4_MISC1 */
+ num_msrs = 2;
+ } else if (c->x86 == 0x17 &&
+ (c->x86_model >= 0x10 && c->x86_model <= 0x2F)) {
- if (c->x86 != 0x15)
+ if (smca_get_bank_type(bank) != SMCA_IF)
+ return;
+
+ msrs[0] = MSR_AMD64_SMCA_MCx_MISC(bank);
+ num_msrs = 1;
+ } else {
return;
+ }
rdmsrl(MSR_K7_HWCR, hwcr);
/* McStatusWrEn has to be set */
need_toggle = !(hwcr & BIT(18));
-
if (need_toggle)
wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
/* Clear CntP bit safely */
- for (i = 0; i < ARRAY_SIZE(msrs); i++)
+ for (i = 0; i < num_msrs; i++)
msr_clear_bit(msrs[i], 62);
/* restore old settings */
@@ -604,12 +630,12 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
unsigned int bank, block, cpu = smp_processor_id();
int offset = -1;
- disable_err_thresholding(c);
-
for (bank = 0; bank < mca_cfg.banks; ++bank) {
if (mce_flags.smca)
smca_configure(bank, cpu);
+ disable_err_thresholding(c, bank);
+
for (block = 0; block < NR_BLOCKS; ++block) {
address = get_block_address(address, low, high, bank, block);
if (!address)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index b7fb541a4873..5112a50e6486 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -460,23 +460,6 @@ static void mce_irq_work_cb(struct irq_work *entry)
mce_schedule_work();
}
-static void mce_report_event(struct pt_regs *regs)
-{
- if (regs->flags & (X86_VM_MASK|X86_EFLAGS_IF)) {
- mce_notify_irq();
- /*
- * Triggering the work queue here is just an insurance
- * policy in case the syscall exit notify handler
- * doesn't run soon enough or ends up running on the
- * wrong CPU (can happen when audit sleeps)
- */
- mce_schedule_work();
- return;
- }
-
- irq_work_queue(&mce_irq_work);
-}
-
/*
* Check if the address reported by the CPU is in a format we can parse.
* It would be possible to add code for most other cases, but all would
@@ -712,19 +695,49 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
barrier();
m.status = mce_rdmsrl(msr_ops.status(i));
+
+ /* If this entry is not valid, ignore it */
if (!(m.status & MCI_STATUS_VAL))
continue;
/*
- * Uncorrected or signalled events are handled by the exception
- * handler when it is enabled, so don't process those here.
- *
- * TBD do the same check for MCI_STATUS_EN here?
+ * If we are logging everything (at CPU online) or this
+ * is a corrected error, then we must log it.
*/
- if (!(flags & MCP_UC) &&
- (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
- continue;
+ if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC))
+ goto log_it;
+
+ /*
+ * Newer Intel systems that support software error
+ * recovery need to make additional checks. Other
+ * CPUs should skip over uncorrected errors, but log
+ * everything else.
+ */
+ if (!mca_cfg.ser) {
+ if (m.status & MCI_STATUS_UC)
+ continue;
+ goto log_it;
+ }
+ /* Log "not enabled" (speculative) errors */
+ if (!(m.status & MCI_STATUS_EN))
+ goto log_it;
+
+ /*
+ * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
+ * UC == 1 && PCC == 0 && S == 0
+ */
+ if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S))
+ goto log_it;
+
+ /*
+ * Skip anything else. Presumption is that our read of this
+ * bank is racing with a machine check. Leave the log alone
+ * for do_machine_check() to deal with it.
+ */
+ continue;
+
+log_it:
error_seen = true;
mce_read_aux(&m, i);
@@ -1301,7 +1314,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
mce_panic("Fatal machine check on current CPU", &m, msg);
if (worst > 0)
- mce_report_event(regs);
+ irq_work_queue(&mce_irq_work);
+
mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
sync_core();
@@ -1451,13 +1465,12 @@ EXPORT_SYMBOL_GPL(mce_notify_irq);
static int __mcheck_cpu_mce_banks_init(void)
{
int i;
- u8 num_banks = mca_cfg.banks;
- mce_banks = kcalloc(num_banks, sizeof(struct mce_bank), GFP_KERNEL);
+ mce_banks = kcalloc(MAX_NR_BANKS, sizeof(struct mce_bank), GFP_KERNEL);
if (!mce_banks)
return -ENOMEM;
- for (i = 0; i < num_banks; i++) {
+ for (i = 0; i < MAX_NR_BANKS; i++) {
struct mce_bank *b = &mce_banks[i];
b->ctl = -1ULL;
@@ -1471,28 +1484,19 @@ static int __mcheck_cpu_mce_banks_init(void)
*/
static int __mcheck_cpu_cap_init(void)
{
- unsigned b;
u64 cap;
+ u8 b;
rdmsrl(MSR_IA32_MCG_CAP, cap);
b = cap & MCG_BANKCNT_MASK;
- if (!mca_cfg.banks)
- pr_info("CPU supports %d MCE banks\n", b);
-
- if (b > MAX_NR_BANKS) {
- pr_warn("Using only %u machine check banks out of %u\n",
- MAX_NR_BANKS, b);
+ if (WARN_ON_ONCE(b > MAX_NR_BANKS))
b = MAX_NR_BANKS;
- }
- /* Don't support asymmetric configurations today */
- WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks);
- mca_cfg.banks = b;
+ mca_cfg.banks = max(mca_cfg.banks, b);
if (!mce_banks) {
int err = __mcheck_cpu_mce_banks_init();
-
if (err)
return err;
}
@@ -1771,6 +1775,14 @@ static void __mcheck_cpu_init_timer(void)
mce_start_timer(t);
}
+bool filter_mce(struct mce *m)
+{
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ return amd_filter_mce(m);
+
+ return false;
+}
+
/* Handle unconfigured int18 (should never happen) */
static void unexpected_machine_check(struct pt_regs *regs, long error_code)
{
@@ -2425,8 +2437,8 @@ static int fake_panic_set(void *data, u64 val)
return 0;
}
-DEFINE_SIMPLE_ATTRIBUTE(fake_panic_fops, fake_panic_get,
- fake_panic_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fake_panic_fops, fake_panic_get, fake_panic_set,
+ "%llu\n");
static int __init mcheck_debugfs_init(void)
{
@@ -2435,8 +2447,8 @@ static int __init mcheck_debugfs_init(void)
dmce = mce_get_debugfs_dir();
if (!dmce)
return -ENOMEM;
- ffake_panic = debugfs_create_file("fake_panic", 0444, dmce, NULL,
- &fake_panic_fops);
+ ffake_panic = debugfs_create_file_unsafe("fake_panic", 0444, dmce,
+ NULL, &fake_panic_fops);
if (!ffake_panic)
return -ENOMEM;
@@ -2451,6 +2463,8 @@ EXPORT_SYMBOL_GPL(mcsafe_key);
static int __init mcheck_late_init(void)
{
+ pr_info("Using %d MCE banks\n", mca_cfg.banks);
+
if (mca_cfg.recovery)
static_branch_inc(&mcsafe_key);
diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index 3395549c51d3..64d1d5a00f39 100644
--- a/arch/x86/kernel/cpu/mce/genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -99,6 +99,9 @@ int mce_gen_pool_add(struct mce *mce)
{
struct mce_evt_llist *node;
+ if (filter_mce(mce))
+ return -EINVAL;
+
if (!mce_evt_pool)
return -EINVAL;
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 8492ef7d9015..a6026170af92 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -46,8 +46,6 @@
static struct mce i_mce;
static struct dentry *dfs_inj;
-static u8 n_banks;
-
#define MAX_FLAG_OPT_SIZE 4
#define NBCFG 0x44
@@ -528,7 +526,7 @@ static void do_inject(void)
* only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for
* Fam10h and later BKDGs.
*/
- if (static_cpu_has(X86_FEATURE_AMD_DCM) &&
+ if (boot_cpu_has(X86_FEATURE_AMD_DCM) &&
b == 4 &&
boot_cpu_data.x86 < 0x17) {
toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu));
@@ -570,9 +568,15 @@ err:
static int inj_bank_set(void *data, u64 val)
{
struct mce *m = (struct mce *)data;
+ u8 n_banks;
+ u64 cap;
+
+ /* Get bank count on target CPU so we can handle non-uniform values. */
+ rdmsrl_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
+ n_banks = cap & MCG_BANKCNT_MASK;
if (val >= n_banks) {
- pr_err("Non-existent MCE bank: %llu\n", val);
+ pr_err("MCA bank %llu non-existent on CPU%d\n", val, m->extcpu);
return -EINVAL;
}
@@ -665,10 +669,6 @@ static struct dfs_node {
static int __init debugfs_init(void)
{
unsigned int i;
- u64 cap;
-
- rdmsrl(MSR_IA32_MCG_CAP, cap);
- n_banks = cap & MCG_BANKCNT_MASK;
dfs_inj = debugfs_create_dir("mce-inject", NULL);
if (!dfs_inj)
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index af5eab1e65e2..a34b55baa7aa 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -173,4 +173,13 @@ struct mca_msr_regs {
extern struct mca_msr_regs msr_ops;
+/* Decide whether to add MCE record to MCE event pool or filter it out. */
+extern bool filter_mce(struct mce *m);
+
+#ifdef CONFIG_X86_MCE_AMD
+extern bool amd_filter_mce(struct mce *m);
+#else
+static inline bool amd_filter_mce(struct mce *m) { return false; };
+#endif
+
#endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 97f9ada9ceda..c321f4f513f9 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -418,8 +418,9 @@ static int do_microcode_update(const void __user *buf, size_t size)
if (ustate == UCODE_ERROR) {
error = -1;
break;
- } else if (ustate == UCODE_OK)
+ } else if (ustate == UCODE_NEW) {
apply_microcode_on_target(cpu);
+ }
}
return error;
@@ -427,7 +428,7 @@ static int do_microcode_update(const void __user *buf, size_t size)
static int microcode_open(struct inode *inode, struct file *file)
{
- return capable(CAP_SYS_RAWIO) ? nonseekable_open(inode, file) : -EPERM;
+ return capable(CAP_SYS_RAWIO) ? stream_open(inode, file) : -EPERM;
}
static ssize_t microcode_write(struct file *file, const char __user *buf,
@@ -608,6 +609,8 @@ static int microcode_reload_late(void)
if (ret > 0)
microcode_check();
+ pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode);
+
return ret;
}
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 16936a24795c..a44bdbe7c55e 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -31,6 +31,7 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/cpu.h>
+#include <linux/uio.h>
#include <linux/mm.h>
#include <asm/microcode_intel.h>
@@ -861,32 +862,33 @@ out:
return ret;
}
-static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
- int (*get_ucode_data)(void *, const void *, size_t))
+static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
- int new_rev = uci->cpu_sig.rev;
- unsigned int leftover = size;
unsigned int curr_mc_size = 0, new_mc_size = 0;
- unsigned int csig, cpf;
enum ucode_state ret = UCODE_OK;
+ int new_rev = uci->cpu_sig.rev;
+ u8 *new_mc = NULL, *mc = NULL;
+ unsigned int csig, cpf;
- while (leftover) {
+ while (iov_iter_count(iter)) {
struct microcode_header_intel mc_header;
- unsigned int mc_size;
+ unsigned int mc_size, data_size;
+ u8 *data;
- if (leftover < sizeof(mc_header)) {
- pr_err("error! Truncated header in microcode data file\n");
+ if (!copy_from_iter_full(&mc_header, sizeof(mc_header), iter)) {
+ pr_err("error! Truncated or inaccessible header in microcode data file\n");
break;
}
- if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header)))
- break;
-
mc_size = get_totalsize(&mc_header);
- if (!mc_size || mc_size > leftover) {
- pr_err("error! Bad data in microcode data file\n");
+ if (mc_size < sizeof(mc_header)) {
+ pr_err("error! Bad data in microcode data file (totalsize too small)\n");
+ break;
+ }
+ data_size = mc_size - sizeof(mc_header);
+ if (data_size > iov_iter_count(iter)) {
+ pr_err("error! Bad data in microcode data file (truncated file?)\n");
break;
}
@@ -899,7 +901,9 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
curr_mc_size = mc_size;
}
- if (get_ucode_data(mc, ucode_ptr, mc_size) ||
+ memcpy(mc, &mc_header, sizeof(mc_header));
+ data = mc + sizeof(mc_header);
+ if (!copy_from_iter_full(data, data_size, iter) ||
microcode_sanity_check(mc, 1) < 0) {
break;
}
@@ -914,14 +918,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
mc = NULL; /* trigger new vmalloc */
ret = UCODE_NEW;
}
-
- ucode_ptr += mc_size;
- leftover -= mc_size;
}
vfree(mc);
- if (leftover) {
+ if (iov_iter_count(iter)) {
vfree(new_mc);
return UCODE_ERROR;
}
@@ -945,12 +946,6 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
return ret;
}
-static int get_ucode_fw(void *to, const void *from, size_t n)
-{
- memcpy(to, from, n);
- return 0;
-}
-
static bool is_blacklisted(unsigned int cpu)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -977,10 +972,12 @@ static bool is_blacklisted(unsigned int cpu)
static enum ucode_state request_microcode_fw(int cpu, struct device *device,
bool refresh_fw)
{
- char name[30];
struct cpuinfo_x86 *c = &cpu_data(cpu);
const struct firmware *firmware;
+ struct iov_iter iter;
enum ucode_state ret;
+ struct kvec kvec;
+ char name[30];
if (is_blacklisted(cpu))
return UCODE_NFOUND;
@@ -993,26 +990,30 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
return UCODE_NFOUND;
}
- ret = generic_load_microcode(cpu, (void *)firmware->data,
- firmware->size, &get_ucode_fw);
+ kvec.iov_base = (void *)firmware->data;
+ kvec.iov_len = firmware->size;
+ iov_iter_kvec(&iter, WRITE, &kvec, 1, firmware->size);
+ ret = generic_load_microcode(cpu, &iter);
release_firmware(firmware);
return ret;
}
-static int get_ucode_user(void *to, const void *from, size_t n)
-{
- return copy_from_user(to, from, n);
-}
-
static enum ucode_state
request_microcode_user(int cpu, const void __user *buf, size_t size)
{
+ struct iov_iter iter;
+ struct iovec iov;
+
if (is_blacklisted(cpu))
return UCODE_NFOUND;
- return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
+ iov.iov_base = (void __user *)buf;
+ iov.iov_len = size;
+ iov_iter_init(&iter, WRITE, &iov, 1, size);
+
+ return generic_load_microcode(cpu, &iter);
}
static struct microcode_ops microcode_intel_ops = {
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 2c8522a39ed5..cb2e49810d68 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -35,11 +35,11 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
"fpu_exception\t: %s\n"
"cpuid level\t: %d\n"
"wp\t\t: yes\n",
- static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
- static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
- static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
- static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
- static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
+ boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+ boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
c->cpuid_level);
}
#else
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 2dbd990a2eb7..89320c0396b1 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -342,10 +342,10 @@ int update_domains(struct rdt_resource *r, int closid)
if (cpumask_empty(cpu_mask) || mba_sc)
goto done;
cpu = get_cpu();
- /* Update CBM on this cpu if it's in cpu_mask. */
+ /* 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 CBM on other cpus. */
+ /* Update resource control msr on other CPUs. */
smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
put_cpu();
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f33f11f69078..1573a0a6b525 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -501,11 +501,8 @@ out_unlock:
void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
- struct rdt_resource *r;
int cpu;
- r = &rdt_resources_all[RDT_RESOURCE_L3];
-
cpu = cpumask_any(&dom->cpu_mask);
dom->cqm_work_cpu = cpu;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 399601eda8e4..333c177a2471 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2039,14 +2039,14 @@ out:
enum rdt_param {
Opt_cdp,
Opt_cdpl2,
- Opt_mba_mpbs,
+ Opt_mba_mbps,
nr__rdt_params
};
static const struct fs_parameter_spec rdt_param_specs[] = {
fsparam_flag("cdp", Opt_cdp),
fsparam_flag("cdpl2", Opt_cdpl2),
- fsparam_flag("mba_mpbs", Opt_mba_mpbs),
+ fsparam_flag("mba_MBps", Opt_mba_mbps),
{}
};
@@ -2072,7 +2072,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
case Opt_cdpl2:
ctx->enable_cdpl2 = true;
return 0;
- case Opt_mba_mpbs:
+ case Opt_mba_mbps:
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return -EINVAL;
ctx->enable_mba_mbps = true;
@@ -2516,103 +2516,131 @@ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
bitmap_clear(val, zero_bit, cbm_len - zero_bit);
}
-/**
- * rdtgroup_init_alloc - Initialize the new RDT group's allocations
- *
- * A new RDT group is being created on an allocation capable (CAT)
- * supporting system. Set this group up to start off with all usable
- * allocations. That is, all shareable and unused bits.
+/*
+ * Initialize cache resources per RDT domain
*
- * All-zero CBM is invalid. If there are no more shareable bits available
- * on any domain then the entire allocation will fail.
+ * Set the RDT domain up to start off with all usable allocations. That is,
+ * all shareable and unused bits. All-zero CBM is invalid.
*/
-static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
+ u32 closid)
{
struct rdt_resource *r_cdp = NULL;
struct rdt_domain *d_cdp = NULL;
u32 used_b = 0, unused_b = 0;
- u32 closid = rdtgrp->closid;
- struct rdt_resource *r;
unsigned long tmp_cbm;
enum rdtgrp_mode mode;
- struct rdt_domain *d;
u32 peer_ctl, *ctrl;
- int i, ret;
+ int i;
- for_each_alloc_enabled_rdt_resource(r) {
- /*
- * Only initialize default allocations for CBM cache
- * resources
- */
- if (r->rid == RDT_RESOURCE_MBA)
- continue;
- list_for_each_entry(d, &r->domains, list) {
- rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
- d->have_new_ctrl = false;
- d->new_ctrl = r->cache.shareable_bits;
- used_b = r->cache.shareable_bits;
- ctrl = d->ctrl_val;
- for (i = 0; i < closids_supported(); i++, ctrl++) {
- if (closid_allocated(i) && i != closid) {
- mode = rdtgroup_mode_by_closid(i);
- if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
- break;
- /*
- * If CDP is active include peer
- * domain's usage to ensure there
- * is no overlap with an exclusive
- * group.
- */
- if (d_cdp)
- peer_ctl = d_cdp->ctrl_val[i];
- else
- peer_ctl = 0;
- used_b |= *ctrl | peer_ctl;
- if (mode == RDT_MODE_SHAREABLE)
- d->new_ctrl |= *ctrl | peer_ctl;
- }
- }
- if (d->plr && d->plr->cbm > 0)
- used_b |= d->plr->cbm;
- unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
- unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
- d->new_ctrl |= unused_b;
- /*
- * Force the initial CBM to be valid, user can
- * modify the CBM based on system availability.
- */
- cbm_ensure_valid(&d->new_ctrl, r);
+ rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
+ d->have_new_ctrl = false;
+ d->new_ctrl = r->cache.shareable_bits;
+ used_b = r->cache.shareable_bits;
+ ctrl = d->ctrl_val;
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
+ if (closid_allocated(i) && i != closid) {
+ mode = rdtgroup_mode_by_closid(i);
+ if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+ break;
/*
- * Assign the u32 CBM to an unsigned long to ensure
- * that bitmap_weight() does not access out-of-bound
- * memory.
+ * If CDP is active include peer domain's
+ * usage to ensure there is no overlap
+ * with an exclusive group.
*/
- tmp_cbm = d->new_ctrl;
- if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
- r->cache.min_cbm_bits) {
- rdt_last_cmd_printf("No space on %s:%d\n",
- r->name, d->id);
- return -ENOSPC;
- }
- d->have_new_ctrl = true;
+ if (d_cdp)
+ peer_ctl = d_cdp->ctrl_val[i];
+ else
+ peer_ctl = 0;
+ used_b |= *ctrl | peer_ctl;
+ if (mode == RDT_MODE_SHAREABLE)
+ d->new_ctrl |= *ctrl | peer_ctl;
}
}
+ if (d->plr && d->plr->cbm > 0)
+ used_b |= d->plr->cbm;
+ unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+ unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+ d->new_ctrl |= unused_b;
+ /*
+ * Force the initial CBM to be valid, user can
+ * modify the CBM based on system availability.
+ */
+ cbm_ensure_valid(&d->new_ctrl, r);
+ /*
+ * Assign the u32 CBM to an unsigned long to ensure that
+ * bitmap_weight() does not access out-of-bound memory.
+ */
+ tmp_cbm = d->new_ctrl;
+ if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
+ rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id);
+ return -ENOSPC;
+ }
+ d->have_new_ctrl = true;
+
+ return 0;
+}
+
+/*
+ * Initialize cache resources with default values.
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations.
+ *
+ * If there are no more shareable bits available on any domain then
+ * the entire allocation will fail.
+ */
+static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid)
+{
+ struct rdt_domain *d;
+ int ret;
+
+ list_for_each_entry(d, &r->domains, list) {
+ ret = __init_one_rdt_domain(d, r, closid);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+/* Initialize MBA resource with default values. */
+static void rdtgroup_init_mba(struct rdt_resource *r)
+{
+ struct rdt_domain *d;
+
+ list_for_each_entry(d, &r->domains, list) {
+ d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+ d->have_new_ctrl = true;
+ }
+}
+
+/* Initialize the RDT group's allocations. */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+ struct rdt_resource *r;
+ int ret;
for_each_alloc_enabled_rdt_resource(r) {
- /*
- * Only initialize default allocations for CBM cache
- * resources
- */
- if (r->rid == RDT_RESOURCE_MBA)
- continue;
+ if (r->rid == RDT_RESOURCE_MBA) {
+ rdtgroup_init_mba(r);
+ } else {
+ ret = rdtgroup_init_cat(r, rdtgrp->closid);
+ if (ret < 0)
+ return ret;
+ }
+
ret = update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("Failed to initialize allocations\n");
return ret;
}
- rdtgrp->mode = RDT_MODE_SHAREABLE;
+
}
+ rdtgrp->mode = RDT_MODE_SHAREABLE;
+
return 0;
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-02 23:34:27 +0100