summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/amd.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu/amd.c')
-rw-r--r--arch/x86/kernel/cpu/amd.c802
1 files changed, 507 insertions, 295 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f769d6d08b43..bc94ff1e250a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -3,16 +3,18 @@
#include <linux/bitops.h>
#include <linux/elf.h>
#include <linux/mm.h>
-
+#include <linux/kvm_types.h>
#include <linux/io.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <linux/random.h>
#include <linux/topology.h>
+#include <linux/platform_data/x86/amd-fch.h>
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cacheinfo.h>
#include <asm/cpu.h>
+#include <asm/cpu_device_id.h>
#include <asm/spec-ctrl.h>
#include <asm/smp.h>
#include <asm/numa.h>
@@ -20,6 +22,8 @@
#include <asm/delay.h>
#include <asm/debugreg.h>
#include <asm/resctrl.h>
+#include <asm/msr.h>
+#include <asm/sev.h>
#ifdef CONFIG_X86_64
# include <asm/mmconfig.h>
@@ -27,19 +31,9 @@
#include "cpu.h"
-static const int amd_erratum_383[];
-static const int amd_erratum_400[];
-static const int amd_erratum_1054[];
-static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
-
-/*
- * nodes_per_socket: Stores the number of nodes per socket.
- * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
- * Node Identifiers[10:8]
- */
-static u32 nodes_per_socket = 1;
+u16 invlpgb_count_max __ro_after_init = 1;
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+static inline int rdmsrq_amd_safe(unsigned msr, u64 *p)
{
u32 gprs[8] = { 0 };
int err;
@@ -57,7 +51,7 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
return err;
}
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+static inline int wrmsrq_amd_safe(unsigned msr, u64 val)
{
u32 gprs[8] = { 0 };
@@ -305,111 +299,16 @@ static int nearby_node(int apicid)
}
#endif
-/*
- * Fix up cpu_core_id for pre-F17h systems to be in the
- * [0 .. cores_per_node - 1] range. Not really needed but
- * kept so as not to break existing setups.
- */
-static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
-{
- u32 cus_per_node;
-
- if (c->x86 >= 0x17)
- return;
-
- cus_per_node = c->x86_max_cores / nodes_per_socket;
- c->cpu_core_id %= cus_per_node;
-}
-
-/*
- * Fixup core topology information for
- * (1) AMD multi-node processors
- * Assumption: Number of cores in each internal node is the same.
- * (2) AMD processors supporting compute units
- */
-static void amd_get_topology(struct cpuinfo_x86 *c)
-{
- int cpu = smp_processor_id();
-
- /* get information required for multi-node processors */
- if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
- int err;
- u32 eax, ebx, ecx, edx;
-
- cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-
- c->cpu_die_id = ecx & 0xff;
-
- if (c->x86 == 0x15)
- c->cu_id = ebx & 0xff;
-
- if (c->x86 >= 0x17) {
- c->cpu_core_id = ebx & 0xff;
-
- if (smp_num_siblings > 1)
- c->x86_max_cores /= smp_num_siblings;
- }
-
- /*
- * In case leaf B is available, use it to derive
- * topology information.
- */
- err = detect_extended_topology(c);
- if (!err)
- c->x86_coreid_bits = get_count_order(c->x86_max_cores);
-
- cacheinfo_amd_init_llc_id(c, cpu);
-
- } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
- u64 value;
-
- rdmsrl(MSR_FAM10H_NODE_ID, value);
- c->cpu_die_id = value & 7;
-
- per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
- } else
- return;
-
- if (nodes_per_socket > 1) {
- set_cpu_cap(c, X86_FEATURE_AMD_DCM);
- legacy_fixup_core_id(c);
- }
-}
-
-/*
- * On a AMD dual core setup the lower bits of the APIC id distinguish the cores.
- * Assumes number of cores is a power of two.
- */
-static void amd_detect_cmp(struct cpuinfo_x86 *c)
-{
- unsigned bits;
- int cpu = smp_processor_id();
-
- bits = c->x86_coreid_bits;
- /* Low order bits define the core id (index of core in socket) */
- c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
- /* Convert the initial APIC ID into the socket ID */
- c->phys_proc_id = c->initial_apicid >> bits;
- /* use socket ID also for last level cache */
- per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id;
-}
-
-u32 amd_get_nodes_per_socket(void)
-{
- return nodes_per_socket;
-}
-EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket);
-
static void srat_detect_node(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_NUMA
int cpu = smp_processor_id();
int node;
- unsigned apicid = c->apicid;
+ unsigned apicid = c->topo.apicid;
node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
- node = get_llc_id(cpu);
+ node = per_cpu_llc_id(cpu);
/*
* On multi-fabric platform (e.g. Numascale NumaChip) a
@@ -439,7 +338,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
* through CPU mapping may alter the outcome, directly
* access __apicid_to_node[].
*/
- int ht_nodeid = c->initial_apicid;
+ int ht_nodeid = c->topo.initial_apicid;
if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
node = __apicid_to_node[ht_nodeid];
@@ -451,30 +350,72 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#endif
}
-static void early_init_amd_mc(struct cpuinfo_x86 *c)
+static void bsp_determine_snp(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_SMP
- unsigned bits, ecx;
-
- /* Multi core CPU? */
- if (c->extended_cpuid_level < 0x80000008)
- return;
+#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+ cc_vendor = CC_VENDOR_AMD;
- ecx = cpuid_ecx(0x80000008);
+ if (cpu_has(c, X86_FEATURE_SEV_SNP)) {
+ /*
+ * RMP table entry format is not architectural and is defined by the
+ * per-processor PPR. Restrict SNP support on the known CPU models
+ * for which the RMP table entry format is currently defined or for
+ * processors which support the architecturally defined RMPREAD
+ * instruction.
+ */
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
+ (cpu_feature_enabled(X86_FEATURE_ZEN3) ||
+ cpu_feature_enabled(X86_FEATURE_ZEN4) ||
+ cpu_feature_enabled(X86_FEATURE_RMPREAD)) &&
+ snp_probe_rmptable_info()) {
+ cc_platform_set(CC_ATTR_HOST_SEV_SNP);
+ } else {
+ setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
+ cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
+ }
+ }
+#endif
+}
- c->x86_max_cores = (ecx & 0xff) + 1;
+#define ZEN_MODEL_STEP_UCODE(fam, model, step, ucode) \
+ X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, fam, model), \
+ step, step, ucode)
+
+static const struct x86_cpu_id amd_tsa_microcode[] = {
+ ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x1, 0x0a0011d7),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x2, 0x0a00123b),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x08, 0x2, 0x0a00820d),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x1, 0x0a10114c),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x2, 0x0a10124c),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x18, 0x1, 0x0a108109),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x0, 0x0a20102e),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x2, 0x0a201211),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x44, 0x1, 0x0a404108),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x50, 0x0, 0x0a500012),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x61, 0x2, 0x0a60120a),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x74, 0x1, 0x0a704108),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x75, 0x2, 0x0a705208),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x78, 0x0, 0x0a708008),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x7c, 0x0, 0x0a70c008),
+ ZEN_MODEL_STEP_UCODE(0x19, 0xa0, 0x2, 0x0aa00216),
+ {},
+};
- /* CPU telling us the core id bits shift? */
- bits = (ecx >> 12) & 0xF;
+static void tsa_init(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+ return;
- /* Otherwise recompute */
- if (bits == 0) {
- while ((1 << bits) < c->x86_max_cores)
- bits++;
+ if (cpu_has(c, X86_FEATURE_ZEN3) ||
+ cpu_has(c, X86_FEATURE_ZEN4)) {
+ if (x86_match_min_microcode_rev(amd_tsa_microcode))
+ setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR);
+ else
+ pr_debug("%s: current revision: 0x%x\n", __func__, c->microcode);
+ } else {
+ setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO);
+ setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO);
}
-
- c->x86_coreid_bits = bits;
-#endif
}
static void bsp_init_amd(struct cpuinfo_x86 *c)
@@ -485,7 +426,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
(c->x86 == 0x10 && c->x86_model >= 0x2)) {
u64 val;
- rdmsrl(MSR_K7_HWCR, val);
+ rdmsrq(MSR_K7_HWCR, val);
if (!(val & BIT(24)))
pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
}
@@ -509,18 +450,6 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_MWAITX))
use_mwaitx_delay();
- if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
- u32 ecx;
-
- ecx = cpuid_ecx(0x8000001e);
- __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1;
- } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
- u64 value;
-
- rdmsrl(MSR_FAM10H_NODE_ID, value);
- __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1;
- }
-
if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
!boot_cpu_has(X86_FEATURE_VIRT_SSBD) &&
c->x86 >= 0x15 && c->x86 <= 0x17) {
@@ -536,7 +465,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
* Try to cache the base value so further operations can
* avoid RMW. If that faults, do not enable SSBD.
*/
- if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+ if (!rdmsrq_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
setup_force_cpu_cap(X86_FEATURE_SSBD);
x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
@@ -544,6 +473,72 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
}
resctrl_cpu_detect(c);
+
+ /* Figure out Zen generations: */
+ switch (c->x86) {
+ case 0x17:
+ switch (c->x86_model) {
+ case 0x00 ... 0x2f:
+ case 0x50 ... 0x5f:
+ setup_force_cpu_cap(X86_FEATURE_ZEN1);
+ break;
+ case 0x30 ... 0x4f:
+ case 0x60 ... 0x7f:
+ case 0x90 ... 0x91:
+ case 0xa0 ... 0xaf:
+ setup_force_cpu_cap(X86_FEATURE_ZEN2);
+ break;
+ default:
+ goto warn;
+ }
+ break;
+
+ case 0x19:
+ switch (c->x86_model) {
+ case 0x00 ... 0x0f:
+ case 0x20 ... 0x5f:
+ setup_force_cpu_cap(X86_FEATURE_ZEN3);
+ break;
+ case 0x10 ... 0x1f:
+ case 0x60 ... 0xaf:
+ setup_force_cpu_cap(X86_FEATURE_ZEN4);
+ break;
+ default:
+ goto warn;
+ }
+ break;
+
+ case 0x1a:
+ switch (c->x86_model) {
+ case 0x00 ... 0x2f:
+ case 0x40 ... 0x4f:
+ case 0x60 ... 0x7f:
+ setup_force_cpu_cap(X86_FEATURE_ZEN5);
+ break;
+ case 0x50 ... 0x5f:
+ case 0x80 ... 0xaf:
+ case 0xc0 ... 0xcf:
+ setup_force_cpu_cap(X86_FEATURE_ZEN6);
+ break;
+ default:
+ goto warn;
+ }
+ break;
+
+ default:
+ break;
+ }
+
+ bsp_determine_snp(c);
+ tsa_init(c);
+
+ if (cpu_has(c, X86_FEATURE_GP_ON_USER_CPUID))
+ setup_force_cpu_cap(X86_FEATURE_CPUID_FAULT);
+
+ return;
+
+warn:
+ WARN_ONCE(1, "Family 0x%x, model: 0x%x??\n", c->x86, c->x86_model);
}
static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -551,6 +546,23 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
u64 msr;
/*
+ * Mark using WBINVD is needed during kexec on processors that
+ * support SME. This provides support for performing a successful
+ * kexec when going from SME inactive to SME active (or vice-versa).
+ *
+ * The cache must be cleared so that if there are entries with the
+ * same physical address, both with and without the encryption bit,
+ * they don't race each other when flushed and potentially end up
+ * with the wrong entry being committed to memory.
+ *
+ * Test the CPUID bit directly because with mem_encrypt=off the
+ * BSP will clear the X86_FEATURE_SME bit and the APs will not
+ * see it set after that.
+ */
+ if (c->extended_cpuid_level >= 0x8000001f && (cpuid_eax(0x8000001f) & BIT(0)))
+ __this_cpu_write(cache_state_incoherent, true);
+
+ /*
* BIOS support is required for SME and SEV.
* For SME: If BIOS has enabled SME then adjust x86_phys_bits by
* the SME physical address space reduction value.
@@ -558,15 +570,15 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
* SME feature (set in scattered.c).
* If the kernel has not enabled SME via any means then
* don't advertise the SME feature.
- * For SEV: If BIOS has not enabled SEV then don't advertise the
- * SEV and SEV_ES feature (set in scattered.c).
+ * For SEV: If BIOS has not enabled SEV then don't advertise SEV and
+ * any additional functionality based on it.
*
* In all cases, since support for SME and SEV requires long mode,
* don't advertise the feature under CONFIG_X86_32.
*/
if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) {
/* Check if memory encryption is enabled */
- rdmsrl(MSR_AMD64_SYSCFG, msr);
+ rdmsrq(MSR_AMD64_SYSCFG, msr);
if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
goto clear_all;
@@ -583,7 +595,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
if (!sme_me_mask)
setup_clear_cpu_cap(X86_FEATURE_SME);
- rdmsrl(MSR_K7_HWCR, msr);
+ rdmsrq(MSR_K7_HWCR, msr);
if (!(msr & MSR_K7_HWCR_SMMLOCK))
goto clear_sev;
@@ -594,16 +606,14 @@ clear_all:
clear_sev:
setup_clear_cpu_cap(X86_FEATURE_SEV);
setup_clear_cpu_cap(X86_FEATURE_SEV_ES);
+ setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
}
}
static void early_init_amd(struct cpuinfo_x86 *c)
{
- u64 value;
u32 dummy;
- early_init_amd_mc(c);
-
if (c->x86 >= 0xf)
set_cpu_cap(c, X86_FEATURE_K8);
@@ -667,33 +677,16 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (c->x86 == 0x16 && c->x86_model <= 0xf)
msr_set_bit(MSR_AMD64_LS_CFG, 15);
- /*
- * Check whether the machine is affected by erratum 400. This is
- * used to select the proper idle routine and to enable the check
- * whether the machine is affected in arch_post_acpi_init(), which
- * sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
- */
- if (cpu_has_amd_erratum(c, amd_erratum_400))
- set_cpu_bug(c, X86_BUG_AMD_E400);
-
early_detect_mem_encrypt(c);
- /* Re-enable TopologyExtensions if switched off by BIOS */
- if (c->x86 == 0x15 &&
- (c->x86_model >= 0x10 && c->x86_model <= 0x6f) &&
- !cpu_has(c, X86_FEATURE_TOPOEXT)) {
-
- if (msr_set_bit(0xc0011005, 54) > 0) {
- rdmsrl(0xc0011005, value);
- if (value & BIT_64(54)) {
- set_cpu_cap(c, X86_FEATURE_TOPOEXT);
- pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
- }
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) {
+ if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB))
+ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
+ else if (c->x86 >= 0x19 && !wrmsrq_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
+ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
+ setup_force_cpu_cap(X86_FEATURE_SBPB);
}
}
-
- if (cpu_has(c, X86_FEATURE_TOPOEXT))
- smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
}
static void init_amd_k8(struct cpuinfo_x86 *c)
@@ -711,16 +704,16 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
* (model = 0x14) and later actually support it.
* (AMD Erratum #110, docId: 25759).
*/
- if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+ if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM) && !cpu_has(c, X86_FEATURE_HYPERVISOR)) {
clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
- if (!rdmsrl_amd_safe(0xc001100d, &value)) {
+ if (!rdmsrq_amd_safe(0xc001100d, &value)) {
value &= ~BIT_64(32);
- wrmsrl_amd_safe(0xc001100d, value);
+ wrmsrq_amd_safe(0xc001100d, value);
}
}
if (!c->x86_model_id[0])
- strcpy(c->x86_model_id, "Hammer");
+ strscpy(c->x86_model_id, "Hammer");
#ifdef CONFIG_SMP
/*
@@ -733,6 +726,16 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
msr_set_bit(MSR_K7_HWCR, 6);
#endif
set_cpu_bug(c, X86_BUG_SWAPGS_FENCE);
+
+ /*
+ * Check models and steppings affected by erratum 400. This is
+ * used to select the proper idle routine and to enable the
+ * check whether the machine is affected in arch_post_acpi_subsys_init()
+ * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+ */
+ if (c->x86_model > 0x41 ||
+ (c->x86_model == 0x41 && c->x86_stepping >= 0x2))
+ setup_force_cpu_bug(X86_BUG_AMD_E400);
}
static void init_amd_gh(struct cpuinfo_x86 *c)
@@ -766,8 +769,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
*/
msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
- if (cpu_has_amd_erratum(c, amd_erratum_383))
- set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+ set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+
+ /*
+ * Check models and steppings affected by erratum 400. This is
+ * used to select the proper idle routine and to enable the
+ * check whether the machine is affected in arch_post_acpi_subsys_init()
+ * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+ */
+ if (c->x86_model > 0x2 ||
+ (c->x86_model == 0x2 && c->x86_stepping >= 0x1))
+ setup_force_cpu_bug(X86_BUG_AMD_E400);
}
static void init_amd_ln(struct cpuinfo_x86 *c)
@@ -846,9 +858,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
* Disable it on the affected CPUs.
*/
if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
- if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
+ if (!rdmsrq_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
value |= 0x1E;
- wrmsrl_safe(MSR_F15H_IC_CFG, value);
+ wrmsrq_safe(MSR_F15H_IC_CFG, value);
}
}
@@ -860,9 +872,34 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
clear_rdrand_cpuid_bit(c);
}
+static const struct x86_cpu_id erratum_1386_microcode[] = {
+ X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x01), 0x2, 0x2, 0x0800126e),
+ X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x31), 0x0, 0x0, 0x08301052),
+ {}
+};
+
+static void fix_erratum_1386(struct cpuinfo_x86 *c)
+{
+ /*
+ * Work around Erratum 1386. The XSAVES instruction malfunctions in
+ * certain circumstances on Zen1/2 uarch, and not all parts have had
+ * updated microcode at the time of writing (March 2023).
+ *
+ * Affected parts all have no supervisor XSAVE states, meaning that
+ * the XSAVEC instruction (which works fine) is equivalent.
+ *
+ * Clear the feature flag only on microcode revisions which
+ * don't have the fix.
+ */
+ if (x86_match_min_microcode_rev(erratum_1386_microcode))
+ return;
+
+ clear_cpu_cap(c, X86_FEATURE_XSAVES);
+}
+
void init_spectral_chicken(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
u64 value;
/*
@@ -870,25 +907,27 @@ void init_spectral_chicken(struct cpuinfo_x86 *c)
*
* This suppresses speculation from the middle of a basic block, i.e. it
* suppresses non-branch predictions.
- *
- * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H
*/
- if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) {
- if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
+ if (!rdmsrq_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
- wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
+ wrmsrq_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
}
}
#endif
}
-static void init_amd_zn(struct cpuinfo_x86 *c)
+static void init_amd_zen_common(void)
{
- set_cpu_cap(c, X86_FEATURE_ZEN);
-
+ setup_force_cpu_cap(X86_FEATURE_ZEN);
#ifdef CONFIG_NUMA
node_reclaim_distance = 32;
#endif
+}
+
+static void init_amd_zen1(struct cpuinfo_x86 *c)
+{
+ fix_erratum_1386(c);
/* Fix up CPUID bits, but only if not virtualised. */
if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
@@ -896,19 +935,132 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
/* Erratum 1076: CPB feature bit not being set in CPUID. */
if (!cpu_has(c, X86_FEATURE_CPB))
set_cpu_cap(c, X86_FEATURE_CPB);
+ }
+
+ pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
+ setup_force_cpu_bug(X86_BUG_DIV0);
+
+ /*
+ * Turn off the Instructions Retired free counter on machines that are
+ * susceptible to erratum #1054 "Instructions Retired Performance
+ * Counter May Be Inaccurate".
+ */
+ if (c->x86_model < 0x30) {
+ msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
+ clear_cpu_cap(c, X86_FEATURE_IRPERF);
+ }
+}
+
+static bool cpu_has_zenbleed_microcode(void)
+{
+ u32 good_rev = 0;
+
+ switch (boot_cpu_data.x86_model) {
+ case 0x30 ... 0x3f: good_rev = 0x0830107b; break;
+ case 0x60 ... 0x67: good_rev = 0x0860010c; break;
+ case 0x68 ... 0x6f: good_rev = 0x08608107; break;
+ case 0x70 ... 0x7f: good_rev = 0x08701033; break;
+ case 0xa0 ... 0xaf: good_rev = 0x08a00009; break;
+
+ default:
+ return false;
+ }
+
+ if (boot_cpu_data.microcode < good_rev)
+ return false;
+
+ return true;
+}
+
+static void zen2_zenbleed_check(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+ return;
+
+ if (!cpu_has(c, X86_FEATURE_AVX))
+ return;
+
+ if (!cpu_has_zenbleed_microcode()) {
+ pr_notice_once("Zenbleed: please update your microcode for the most optimal fix\n");
+ msr_set_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT);
+ } else {
+ msr_clear_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT);
+ }
+}
+
+static void init_amd_zen2(struct cpuinfo_x86 *c)
+{
+ init_spectral_chicken(c);
+ fix_erratum_1386(c);
+ zen2_zenbleed_check(c);
+
+ /* Disable RDSEED on AMD Cyan Skillfish because of an error. */
+ if (c->x86_model == 0x47 && c->x86_stepping == 0x0) {
+ clear_cpu_cap(c, X86_FEATURE_RDSEED);
+ msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
+ pr_emerg("RDSEED is not reliable on this platform; disabling.\n");
+ }
+
+ /* Correct misconfigured CPUID on some clients. */
+ clear_cpu_cap(c, X86_FEATURE_INVLPGB);
+}
+static void init_amd_zen3(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
/*
* Zen3 (Fam19 model < 0x10) parts are not susceptible to
* Branch Type Confusion, but predate the allocation of the
* BTC_NO bit.
*/
- if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO))
+ if (!cpu_has(c, X86_FEATURE_BTC_NO))
set_cpu_cap(c, X86_FEATURE_BTC_NO);
}
}
+static void init_amd_zen4(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR))
+ msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+
+ /*
+ * These Zen4 SoCs advertise support for virtualized VMLOAD/VMSAVE
+ * in some BIOS versions but they can lead to random host reboots.
+ */
+ switch (c->x86_model) {
+ case 0x18 ... 0x1f:
+ case 0x60 ... 0x7f:
+ clear_cpu_cap(c, X86_FEATURE_V_VMSAVE_VMLOAD);
+ break;
+ }
+}
+
+static const struct x86_cpu_id zen5_rdseed_microcode[] = {
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x02, 0x1, 0x0b00215a),
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x08, 0x1, 0x0b008121),
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x11, 0x0, 0x0b101054),
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x24, 0x0, 0x0b204037),
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x44, 0x0, 0x0b404035),
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x44, 0x1, 0x0b404108),
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x60, 0x0, 0x0b600037),
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x68, 0x0, 0x0b608038),
+ ZEN_MODEL_STEP_UCODE(0x1a, 0x70, 0x0, 0x0b700037),
+ {},
+};
+
+static void init_amd_zen5(struct cpuinfo_x86 *c)
+{
+ if (!x86_match_min_microcode_rev(zen5_rdseed_microcode)) {
+ clear_cpu_cap(c, X86_FEATURE_RDSEED);
+ msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
+ pr_emerg_once("RDSEED32 is broken. Disabling the corresponding CPUID bit.\n");
+ }
+}
+
static void init_amd(struct cpuinfo_x86 *c)
{
+ u64 vm_cr;
+
early_init_amd(c);
/*
@@ -920,8 +1072,9 @@ static void init_amd(struct cpuinfo_x86 *c)
if (c->x86 >= 0x10)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
- /* get apicid instead of initial apic id from cpuid */
- c->apicid = hard_smp_processor_id();
+ /* AMD FSRM also implies FSRS */
+ if (cpu_has(c, X86_FEATURE_FSRM))
+ set_cpu_cap(c, X86_FEATURE_FSRS);
/* K6s reports MCEs but don't actually have all the MSRs */
if (c->x86 < 6)
@@ -936,12 +1089,27 @@ static void init_amd(struct cpuinfo_x86 *c)
case 0x12: init_amd_ln(c); break;
case 0x15: init_amd_bd(c); break;
case 0x16: init_amd_jg(c); break;
- case 0x17: init_spectral_chicken(c);
- fallthrough;
- case 0x19: init_amd_zn(c); break;
}
/*
+ * Save up on some future enablement work and do common Zen
+ * settings.
+ */
+ if (c->x86 >= 0x17)
+ init_amd_zen_common();
+
+ if (boot_cpu_has(X86_FEATURE_ZEN1))
+ init_amd_zen1(c);
+ else if (boot_cpu_has(X86_FEATURE_ZEN2))
+ init_amd_zen2(c);
+ else if (boot_cpu_has(X86_FEATURE_ZEN3))
+ init_amd_zen3(c);
+ else if (boot_cpu_has(X86_FEATURE_ZEN4))
+ init_amd_zen4(c);
+ else if (boot_cpu_has(X86_FEATURE_ZEN5))
+ init_amd_zen5(c);
+
+ /*
* Enable workaround for FXSAVE leak on CPUs
* without a XSaveErPtr feature
*/
@@ -950,13 +1118,19 @@ static void init_amd(struct cpuinfo_x86 *c)
cpu_detect_cache_sizes(c);
- amd_detect_cmp(c);
- amd_get_topology(c);
srat_detect_node(c);
init_amd_cacheinfo(c);
- if (cpu_has(c, X86_FEATURE_XMM2)) {
+ if (cpu_has(c, X86_FEATURE_SVM)) {
+ rdmsrq(MSR_VM_CR, vm_cr);
+ if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
+ pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
+ clear_cpu_cap(c, X86_FEATURE_SVM);
+ }
+ }
+
+ 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.
@@ -986,16 +1160,29 @@ static void init_amd(struct cpuinfo_x86 *c)
if (!cpu_feature_enabled(X86_FEATURE_XENPV))
set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
- /*
- * Turn on the Instructions Retired free counter on machines not
- * susceptible to erratum #1054 "Instructions Retired Performance
- * Counter May Be Inaccurate".
- */
- if (cpu_has(c, X86_FEATURE_IRPERF) &&
- !cpu_has_amd_erratum(c, amd_erratum_1054))
+ /* Enable the Instructions Retired free counter */
+ if (cpu_has(c, X86_FEATURE_IRPERF))
msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
check_null_seg_clears_base(c);
+
+ /*
+ * Make sure EFER[AIBRSE - Automatic IBRS Enable] is set. The APs are brought up
+ * using the trampoline code and as part of it, MSR_EFER gets prepared there in
+ * order to be replicated onto them. Regardless, set it here again, if not set,
+ * to protect against any future refactoring/code reorganization which might
+ * miss setting this important bit.
+ */
+ if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
+ cpu_has(c, X86_FEATURE_AUTOIBRS))
+ WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS) < 0);
+
+ /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
+ /* Enable Translation Cache Extension */
+ if (cpu_has(c, X86_FEATURE_TCE))
+ msr_set_bit(MSR_EFER, _EFER_TCE);
}
#ifdef CONFIG_X86_32
@@ -1028,8 +1215,8 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
- tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
- tlb_lli_4k[ENTRIES] = ebx & mask;
+ tlb_lld_4k = (ebx >> 16) & mask;
+ tlb_lli_4k = ebx & mask;
/*
* K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB
@@ -1042,26 +1229,30 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
if (!((eax >> 16) & mask))
- tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+ tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
else
- tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+ tlb_lld_2m = (eax >> 16) & mask;
/* a 4M entry uses two 2M entries */
- tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+ tlb_lld_4m = tlb_lld_2m >> 1;
/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
if (!(eax & mask)) {
/* Erratum 658 */
if (c->x86 == 0x15 && c->x86_model <= 0x1f) {
- tlb_lli_2m[ENTRIES] = 1024;
+ tlb_lli_2m = 1024;
} else {
cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
- tlb_lli_2m[ENTRIES] = eax & 0xff;
+ tlb_lli_2m = eax & 0xff;
}
} else
- tlb_lli_2m[ENTRIES] = eax & mask;
+ tlb_lli_2m = eax & mask;
- tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+ tlb_lli_4m = tlb_lli_2m >> 1;
+
+ /* Max number of pages INVLPGB can invalidate in one shot */
+ if (cpu_has(c, X86_FEATURE_INVLPGB))
+ invlpgb_count_max = (cpuid_edx(0x80000008) & 0xffff) + 1;
}
static const struct cpu_dev amd_cpu_dev = {
@@ -1091,104 +1282,125 @@ static const struct cpu_dev amd_cpu_dev = {
cpu_dev_register(amd_cpu_dev);
-/*
- * AMD errata checking
- *
- * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
- * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
- * have an OSVW id assigned, which it takes as first argument. Both take a
- * variable number of family-specific model-stepping ranges created by
- * AMD_MODEL_RANGE().
- *
- * Example:
- *
- * const int amd_erratum_319[] =
- * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
- * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
- * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
- */
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[4], amd_dr_addr_mask);
-#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 }
-#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 }
-#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
- ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
-#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff)
-#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff)
-#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff)
+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
+};
-static const int amd_erratum_400[] =
- AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
- AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
+void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr)
+{
+ int cpu = smp_processor_id();
-static const int amd_erratum_383[] =
- AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
+ if (!cpu_feature_enabled(X86_FEATURE_BPEXT))
+ return;
-/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
-static const int amd_erratum_1054[] =
- AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
+ if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks)))
+ return;
-static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
-{
- int osvw_id = *erratum++;
- u32 range;
- u32 ms;
+ if (per_cpu(amd_dr_addr_mask, cpu)[dr] == mask)
+ return;
- if (osvw_id >= 0 && osvw_id < 65536 &&
- cpu_has(cpu, X86_FEATURE_OSVW)) {
- u64 osvw_len;
+ wrmsrq(amd_msr_dr_addr_masks[dr], mask);
+ per_cpu(amd_dr_addr_mask, cpu)[dr] = mask;
+}
- rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
- if (osvw_id < osvw_len) {
- u64 osvw_bits;
+unsigned long amd_get_dr_addr_mask(unsigned int dr)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_BPEXT))
+ return 0;
- rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
- osvw_bits);
- return osvw_bits & (1ULL << (osvw_id & 0x3f));
- }
- }
+ 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_FOR_KVM(amd_get_dr_addr_mask);
- /* OSVW unavailable or ID unknown, match family-model-stepping range */
- ms = (cpu->x86_model << 4) | cpu->x86_stepping;
- while ((range = *erratum++))
- if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
- (ms >= AMD_MODEL_RANGE_START(range)) &&
- (ms <= AMD_MODEL_RANGE_END(range)))
- return true;
+static void zenbleed_check_cpu(void *unused)
+{
+ struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
- return false;
+ zen2_zenbleed_check(c);
}
-void set_dr_addr_mask(unsigned long mask, int dr)
+void amd_check_microcode(void)
{
- if (!boot_cpu_has(X86_FEATURE_BPEXT))
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
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 (cpu_feature_enabled(X86_FEATURE_ZEN2))
+ on_each_cpu(zenbleed_check_cpu, NULL, 1);
}
-u32 amd_get_highest_perf(void)
+static const char * const s5_reset_reason_txt[] = {
+ [0] = "thermal pin BP_THERMTRIP_L was tripped",
+ [1] = "power button was pressed for 4 seconds",
+ [2] = "shutdown pin was tripped",
+ [4] = "remote ASF power off command was received",
+ [9] = "internal CPU thermal limit was tripped",
+ [16] = "system reset pin BP_SYS_RST_L was tripped",
+ [17] = "software issued PCI reset",
+ [18] = "software wrote 0x4 to reset control register 0xCF9",
+ [19] = "software wrote 0x6 to reset control register 0xCF9",
+ [20] = "software wrote 0xE to reset control register 0xCF9",
+ [21] = "ACPI power state transition occurred",
+ [22] = "keyboard reset pin KB_RST_L was tripped",
+ [23] = "internal CPU shutdown event occurred",
+ [24] = "system failed to boot before failed boot timer expired",
+ [25] = "hardware watchdog timer expired",
+ [26] = "remote ASF reset command was received",
+ [27] = "an uncorrected error caused a data fabric sync flood event",
+ [29] = "FCH and MP1 failed warm reset handshake",
+ [30] = "a parity error occurred",
+ [31] = "a software sync flood event occurred",
+};
+
+static __init int print_s5_reset_status_mmio(void)
{
- struct cpuinfo_x86 *c = &boot_cpu_data;
+ void __iomem *addr;
+ u32 value;
+ int i;
+
+ if (!cpu_feature_enabled(X86_FEATURE_ZEN))
+ return 0;
- if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
- (c->x86_model >= 0x70 && c->x86_model < 0x80)))
- return 166;
+ addr = ioremap(FCH_PM_BASE + FCH_PM_S5_RESET_STATUS, sizeof(value));
+ if (!addr)
+ return 0;
- if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
- (c->x86_model >= 0x40 && c->x86_model < 0x70)))
- return 166;
+ value = ioread32(addr);
+
+ /* Value with "all bits set" is an error response and should be ignored. */
+ if (value == U32_MAX) {
+ iounmap(addr);
+ return 0;
+ }
- return 255;
+ /*
+ * Clear all reason bits so they won't be retained if the next reset
+ * does not update the register. Besides, some bits are never cleared by
+ * hardware so it's software's responsibility to clear them.
+ *
+ * Writing the value back effectively clears all reason bits as they are
+ * write-1-to-clear.
+ */
+ iowrite32(value, addr);
+ iounmap(addr);
+
+ for (i = 0; i < ARRAY_SIZE(s5_reset_reason_txt); i++) {
+ if (!(value & BIT(i)))
+ continue;
+
+ if (s5_reset_reason_txt[i]) {
+ pr_info("x86/amd: Previous system reset reason [0x%08x]: %s\n",
+ value, s5_reset_reason_txt[i]);
+ }
+ }
+
+ return 0;
}
-EXPORT_SYMBOL_GPL(amd_get_highest_perf);
+late_initcall(print_s5_reset_status_mmio);