static void ssb_select_mitigation(void)
{
ssb_mode = __ssb_select_mitigation();
if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
pr_info("%s\n", ssb_strings[ssb_mode]);
}
ssize_t cpu_show_spectre_v1(struct device *dev,
struct device_attribute *attr, char *buf)
{
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
return sprintf(buf, "Not affected\n");
return sprintf(buf, "Vulnerable\n");
}
static enum ssb_mitigation __init __ssb_select_mitigation(void)
{
enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
enum ssb_mitigation_cmd cmd;
if (!boot_cpu_has(X86_FEATURE_SSBD))
return mode;
cmd = ssb_parse_cmdline();
if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
(cmd == SPEC_STORE_BYPASS_CMD_NONE ||
cmd == SPEC_STORE_BYPASS_CMD_AUTO))
return mode;
switch (cmd) {
case SPEC_STORE_BYPASS_CMD_AUTO:
case SPEC_STORE_BYPASS_CMD_SECCOMP:
/*
* Choose prctl+seccomp as the default mode if seccomp is
* enabled.
*/
if (IS_ENABLED(CONFIG_SECCOMP))
mode = SPEC_STORE_BYPASS_SECCOMP;
else
mode = SPEC_STORE_BYPASS_PRCTL;
break;
case SPEC_STORE_BYPASS_CMD_ON:
mode = SPEC_STORE_BYPASS_DISABLE;
break;
case SPEC_STORE_BYPASS_CMD_PRCTL:
mode = SPEC_STORE_BYPASS_PRCTL;
break;
case SPEC_STORE_BYPASS_CMD_NONE:
break;
}
/*
* We have three CPU feature flags that are in play here:
* - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
* - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
* - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
*/
if (mode == SPEC_STORE_BYPASS_DISABLE) {
setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
/*
* Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may
* use a completely different MSR and bit dependent on family.
*/
if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) &&
!static_cpu_has(X86_FEATURE_AMD_SSBD)) {
x86_amd_ssb_disable();
} else {
x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
}
}
return mode;
}
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
/*
* If the CPU is not affected and the command line mode is NONE or AUTO
* then nothing to do.
*/
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
(cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
return;
switch (cmd) {
case SPECTRE_V2_CMD_NONE:
return;
case SPECTRE_V2_CMD_FORCE:
/* FALLTRHU */
case SPECTRE_V2_CMD_AUTO:
goto retpoline_auto;
case SPECTRE_V2_CMD_RETPOLINE_AMD:
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_amd;
break;
case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_generic;
break;
case SPECTRE_V2_CMD_RETPOLINE:
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_auto;
break;
}
pr_err("kernel not compiled with retpoline; no mitigation available!");
return;
retpoline_auto:
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
retpoline_amd:
if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
pr_err("LFENCE not serializing. Switching to generic retpoline\n");
goto retpoline_generic;
}
mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
SPECTRE_V2_RETPOLINE_MINIMAL_AMD;
setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
} else {
retpoline_generic:
mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC :
SPECTRE_V2_RETPOLINE_MINIMAL;
setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
}
spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
}
ssize_t cpu_show_spectre_v2(struct device *dev,
struct device_attribute *attr, char *buf)
{
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
return sprintf(buf, "Not affected\n");
return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]);
}
ssize_t cpu_show_meltdown(struct device *dev,
struct device_attribute *attr, char *buf)
{
if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
return sprintf(buf, "Not affected\n");
if (boot_cpu_has(X86_FEATURE_PTI))
return sprintf(buf, "Mitigation: PTI\n");
return sprintf(buf, "Vulnerable\n");
}
void amd_e400_c1e_apic_setup(void)
{
if (boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
pr_info("Switch to broadcast mode on CPU%d\n", smp_processor_id());
local_irq_disable();
tick_broadcast_force();
local_irq_enable();
}
}
/*
* Only allow root to set high MMIO mappings to PROT_NONE.
* This prevents an unpriv. user to set them to PROT_NONE and invert
* them, then pointing to valid memory for L1TF speculation.
*
* Note: for locked down kernels may want to disable the root override.
*/
bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
{
if (!boot_cpu_has_bug(X86_BUG_L1TF))
return true;
if (!__pte_needs_invert(pgprot_val(prot)))
return true;
/* If it's real memory always allow */
if (pfn_valid(pfn))
return true;
if (pfn >= l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
return false;
return true;
}
void select_idle_routine(const struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1)
pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n");
#endif
if (x86_idle || boot_option_idle_override == IDLE_POLL)
return;
if (boot_cpu_has_bug(X86_BUG_AMD_E400)) {
pr_info("using AMD E400 aware idle routine\n");
x86_idle = amd_e400_idle;
} else if (prefer_mwait_c1_over_halt(c)) {
pr_info("using mwait in idle threads\n");
x86_idle = mwait_idle;
} else
x86_idle = default_idle;
}
static int ssb_prctl_get(struct task_struct *task)
{
switch (ssb_mode) {
case SPEC_STORE_BYPASS_DISABLE:
return PR_SPEC_DISABLE;
case SPEC_STORE_BYPASS_SECCOMP:
case SPEC_STORE_BYPASS_PRCTL:
if (task_spec_ssb_force_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
if (task_spec_ssb_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
default:
if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
return PR_SPEC_ENABLE;
return PR_SPEC_NOT_AFFECTED;
}
}
static void __init l1tf_select_mitigation(void)
{
u64 half_pa;
if (!boot_cpu_has_bug(X86_BUG_L1TF))
return;
override_cache_bits(&boot_cpu_data);
switch (l1tf_mitigation) {
case L1TF_MITIGATION_OFF:
case L1TF_MITIGATION_FLUSH_NOWARN:
case L1TF_MITIGATION_FLUSH:
break;
case L1TF_MITIGATION_FLUSH_NOSMT:
case L1TF_MITIGATION_FULL:
cpu_smt_disable(false);
break;
case L1TF_MITIGATION_FULL_FORCE:
cpu_smt_disable(true);
break;
}
#if CONFIG_PGTABLE_LEVELS == 2
pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
return;
#endif
half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
half_pa);
pr_info("However, doing so will make a part of your RAM unusable.\n");
pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n");
return;
}
setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
}
void __init arch_post_acpi_subsys_init(void)
{
u32 lo, hi;
if (!boot_cpu_has_bug(X86_BUG_AMD_E400))
return;
/*
* AMD E400 detection needs to happen after ACPI has been enabled. If
* the machine is affected K8_INTP_C1E_ACTIVE_MASK bits are set in
* MSR_K8_INT_PENDING_MSG.
*/
rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
if (!(lo & K8_INTP_C1E_ACTIVE_MASK))
return;
boot_cpu_set_bug(X86_BUG_AMD_APIC_C1E);
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
mark_tsc_unstable("TSC halt in AMD C1E");
pr_info("System has AMD C1E enabled\n");
}
/*
* Some BIOS implementations switch to C3 in the published C2 state.
* This seems to be a common problem on AMD boxen, but other vendors
* are affected too. We pick the most conservative approach: we assume
* that the local APIC stops in both C2 and C3.
*/
static void lapic_timer_check_state(int state, struct acpi_processor *pr,
struct acpi_processor_cx *cx)
{
struct acpi_processor_power *pwr = &pr->power;
u8 type = local_apic_timer_c2_ok ? ACPI_STATE_C3 : ACPI_STATE_C2;
if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT))
return;
if (boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E))
type = ACPI_STATE_C1;
/*
* Check, if one of the previous states already marked the lapic
* unstable
*/
if (pwr->timer_broadcast_on_state < state)
return;
if (cx->type >= type)
pr->power.timer_broadcast_on_state = state;
}
static void __init l1tf_select_mitigation(void)
{
u64 half_pa;
if (!boot_cpu_has_bug(X86_BUG_L1TF))
return;
switch (l1tf_mitigation) {
case L1TF_MITIGATION_OFF:
case L1TF_MITIGATION_FLUSH_NOWARN:
case L1TF_MITIGATION_FLUSH:
break;
case L1TF_MITIGATION_FLUSH_NOSMT:
case L1TF_MITIGATION_FULL:
cpu_smt_disable(false);
break;
case L1TF_MITIGATION_FULL_FORCE:
cpu_smt_disable(true);
break;
}
#if CONFIG_PGTABLE_LEVELS == 2
pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
return;
#endif
/*
* This is extremely unlikely to happen because almost all
* systems have far more MAX_PA/2 than RAM can be fit into
* DIMM slots.
*/
half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
return;
}
setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
}
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
char *buf, unsigned int bug)
{
if (!boot_cpu_has_bug(bug))
return sprintf(buf, "Not affected\n");
switch (bug) {
case X86_BUG_CPU_MELTDOWN:
if (boot_cpu_has(X86_FEATURE_PTI))
return sprintf(buf, "Mitigation: PTI\n");
if (hypervisor_is_type(X86_HYPER_XEN_PV))
return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n");
break;
case X86_BUG_SPECTRE_V1:
return sprintf(buf, "Mitigation: __user pointer sanitization\n");
case X86_BUG_SPECTRE_V2:
return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
spectre_v2_module_string());
case X86_BUG_SPEC_STORE_BYPASS:
return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
case X86_BUG_L1TF:
if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
return l1tf_show_state(buf);
break;
default:
break;
}
return sprintf(buf, "Vulnerable\n");
}
static int __init l1tf_cmdline(char *str)
{
if (!boot_cpu_has_bug(X86_BUG_L1TF))
return 0;
if (!str)
return -EINVAL;
if (!strcmp(str, "off"))
l1tf_mitigation = L1TF_MITIGATION_OFF;
else if (!strcmp(str, "flush,nowarn"))
l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOWARN;
else if (!strcmp(str, "flush"))
l1tf_mitigation = L1TF_MITIGATION_FLUSH;
else if (!strcmp(str, "flush,nosmt"))
l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
else if (!strcmp(str, "full"))
l1tf_mitigation = L1TF_MITIGATION_FULL;
else if (!strcmp(str, "full,force"))
l1tf_mitigation = L1TF_MITIGATION_FULL_FORCE;
return 0;
}
/*
* AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
* states (local apic timer and TSC stop).
*/
static void amd_e400_idle(void)
{
/*
* We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E
* gets set after static_cpu_has() places have been converted via
* alternatives.
*/
if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
default_idle();
return;
}
tick_broadcast_enter();
default_idle();
/*
* The switch back from broadcast mode needs to be called with
* interrupts disabled.
*/
local_irq_disable();
tick_broadcast_exit();
local_irq_enable();
}
static void __init spec2_print_if_secure(const char *reason)
{
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
pr_info("%s selected on command line.\n", reason);
}
static void __init spec2_print_if_insecure(const char *reason)
{
if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
pr_info("%s\n", reason);
}
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
/*
* If the CPU is not affected and the command line mode is NONE or AUTO
* then nothing to do.
*/
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
(cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
return;
switch (cmd) {
case SPECTRE_V2_CMD_NONE:
return;
case SPECTRE_V2_CMD_FORCE:
case SPECTRE_V2_CMD_AUTO:
if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
mode = SPECTRE_V2_IBRS_ENHANCED;
/* Force it so VMEXIT will restore correctly */
x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
goto specv2_set_mode;
}
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_auto;
break;
case SPECTRE_V2_CMD_RETPOLINE_AMD:
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_amd;
break;
case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_generic;
break;
case SPECTRE_V2_CMD_RETPOLINE:
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_auto;
break;
}
pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!");
return;
retpoline_auto:
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
retpoline_amd:
if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
goto retpoline_generic;
}
mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
SPECTRE_V2_RETPOLINE_MINIMAL_AMD;
setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
} else {
retpoline_generic:
mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC :
SPECTRE_V2_RETPOLINE_MINIMAL;
setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
}
specv2_set_mode:
spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
/*
* If spectre v2 protection has been enabled, unconditionally fill
* RSB during a context switch; this protects against two independent
* issues:
*
* - RSB underflow (and switch to BTB) on Skylake+
* - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
*/
setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
/* Initialize Indirect Branch Prediction Barrier if supported */
if (boot_cpu_has(X86_FEATURE_IBPB)) {
setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
}
/*
* Retpoline means the kernel is safe because it has no indirect
* branches. Enhanced IBRS protects firmware too, so, enable restricted
* speculation around firmware calls only when Enhanced IBRS isn't
* supported.
*
* Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
* the user might select retpoline on the kernel command line and if
* the CPU supports Enhanced IBRS, kernel might un-intentionally not
* enable IBRS around firmware calls.
*/
if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) {
setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
pr_info("Enabling Restricted Speculation for firmware calls\n");
}
}