summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/amd_nb.c2
-rw-r--r--arch/x86/kernel/apic/apic.c14
-rw-r--r--arch/x86/kernel/cpu/amd.c3
-rw-r--r--arch/x86/kernel/cpu/bugs.c32
-rw-r--r--arch/x86/kernel/cpu/common.c3
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c4
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c23
-rw-r--r--arch/x86/kernel/kvm.c4
-rw-r--r--arch/x86/kernel/reboot.c4
9 files changed, 74 insertions, 15 deletions
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index dc5d3216af24..9fe9972d2071 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -44,6 +44,7 @@
#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4
#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc
#define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4
+#define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4 0x16fc
#define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4 0x124c
#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4 0x12bc
#define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4
@@ -127,6 +128,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) },
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6513c53c9459..c5fb28e6451a 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -440,7 +440,19 @@ static int lapic_timer_shutdown(struct clock_event_device *evt)
v = apic_read(APIC_LVTT);
v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
apic_write(APIC_LVTT, v);
- apic_write(APIC_TMICT, 0);
+
+ /*
+ * Setting APIC_LVT_MASKED (above) should be enough to tell
+ * the hardware that this timer will never fire. But AMD
+ * erratum 411 and some Intel CPU behavior circa 2024 say
+ * otherwise. Time for belt and suspenders programming: mask
+ * the timer _and_ zero the counter registers:
+ */
+ if (v & APIC_LVT_TIMER_TSCDEADLINE)
+ wrmsrl(MSR_IA32_TSC_DEADLINE, 0);
+ else
+ apic_write(APIC_TMICT, 0);
+
return 0;
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 015971adadfc..fab5caec0b72 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1202,5 +1202,6 @@ void amd_check_microcode(void)
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
return;
- on_each_cpu(zenbleed_check_cpu, NULL, 1);
+ if (cpu_feature_enabled(X86_FEATURE_ZEN2))
+ on_each_cpu(zenbleed_check_cpu, NULL, 1);
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d1915427b4ff..47a01d4028f6 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1115,8 +1115,25 @@ do_cmd_auto:
case RETBLEED_MITIGATION_IBPB:
setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+
+ /*
+ * IBPB on entry already obviates the need for
+ * software-based untraining so clear those in case some
+ * other mitigation like SRSO has selected them.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_UNRET);
+ setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
+
setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
mitigate_smt = true;
+
+ /*
+ * There is no need for RSB filling: entry_ibpb() ensures
+ * all predictions, including the RSB, are invalidated,
+ * regardless of IBPB implementation.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
+
break;
case RETBLEED_MITIGATION_STUFF:
@@ -2627,6 +2644,14 @@ static void __init srso_select_mitigation(void)
if (has_microcode) {
setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
srso_mitigation = SRSO_MITIGATION_IBPB;
+
+ /*
+ * IBPB on entry already obviates the need for
+ * software-based untraining so clear those in case some
+ * other mitigation like Retbleed has selected them.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_UNRET);
+ setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
}
} else {
pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
@@ -2638,6 +2663,13 @@ static void __init srso_select_mitigation(void)
if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) {
setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
+
+ /*
+ * There is no need for RSB filling: entry_ibpb() ensures
+ * all predictions, including the RSB, are invalidated,
+ * regardless of IBPB implementation.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
}
} else {
pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 07a34d723505..f1040cb64841 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1443,6 +1443,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
boot_cpu_has(X86_FEATURE_HYPERVISOR)))
setup_force_cpu_bug(X86_BUG_BHI);
+ if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET))
+ setup_force_cpu_bug(X86_BUG_IBPB_NO_RET);
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 8591d53c144b..b681c2e07dbf 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -207,7 +207,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r)
return false;
}
-static bool __get_mem_config_intel(struct rdt_resource *r)
+static __init bool __get_mem_config_intel(struct rdt_resource *r)
{
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
union cpuid_0x10_3_eax eax;
@@ -241,7 +241,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
return true;
}
-static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
+static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r)
{
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
u32 eax, ebx, ecx, edx, subleaf;
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 50fa1fe9a073..200d89a64027 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -29,10 +29,10 @@
* hardware. The allocated bandwidth percentage is rounded to the next
* control step available on the hardware.
*/
-static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
{
- unsigned long bw;
int ret;
+ u32 bw;
/*
* Only linear delay values is supported for current Intel SKUs.
@@ -42,16 +42,21 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
return false;
}
- ret = kstrtoul(buf, 10, &bw);
+ ret = kstrtou32(buf, 10, &bw);
if (ret) {
- rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
+ rdt_last_cmd_printf("Invalid MB value %s\n", buf);
return false;
}
- if ((bw < r->membw.min_bw || bw > r->default_ctrl) &&
- !is_mba_sc(r)) {
- rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
- r->membw.min_bw, r->default_ctrl);
+ /* Nothing else to do if software controller is enabled. */
+ if (is_mba_sc(r)) {
+ *data = bw;
+ return true;
+ }
+
+ if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+ rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n",
+ bw, r->membw.min_bw, r->default_ctrl);
return false;
}
@@ -65,7 +70,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
struct resctrl_staged_config *cfg;
u32 closid = data->rdtgrp->closid;
struct rdt_resource *r = s->res;
- unsigned long bw_val;
+ u32 bw_val;
cfg = &d->staged_config[s->conf_type];
if (cfg->have_new_ctrl) {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 263f8aed4e2c..21e9e4845354 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -37,6 +37,7 @@
#include <asm/apic.h>
#include <asm/apicdef.h>
#include <asm/hypervisor.h>
+#include <asm/mtrr.h>
#include <asm/tlb.h>
#include <asm/cpuidle_haltpoll.h>
#include <asm/ptrace.h>
@@ -980,6 +981,9 @@ static void __init kvm_init_platform(void)
}
kvmclock_init();
x86_platform.apic_post_init = kvm_apic_init;
+
+ /* Set WB as the default cache mode for SEV-SNP and TDX */
+ mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK);
}
#if defined(CONFIG_AMD_MEM_ENCRYPT)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 0e0a4cf6b5eb..615922838c51 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -530,7 +530,7 @@ static inline void kb_wait(void)
static inline void nmi_shootdown_cpus_on_restart(void);
-#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD)
+#if IS_ENABLED(CONFIG_KVM_X86)
/* RCU-protected callback to disable virtualization prior to reboot. */
static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback;
@@ -600,7 +600,7 @@ static void emergency_reboot_disable_virtualization(void)
}
#else
static void emergency_reboot_disable_virtualization(void) { }
-#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */
+#endif /* CONFIG_KVM_X86 */
void __attribute__((weak)) mach_reboot_fixups(void)
{