summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 17:39:57 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 17:39:57 +0000
commitdc50eab76b709d68175a358d6e23a5a3890764d3 (patch)
treec754d0390db060af0213ff994f0ac310e4cfd6e9 /arch/x86/kernel/cpu
parentAdding debian version 6.6.15-2. (diff)
downloadlinux-dc50eab76b709d68175a358d6e23a5a3890764d3.tar.xz
linux-dc50eab76b709d68175a358d6e23a5a3890764d3.zip
Merging upstream version 6.7.7.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/amd.c48
-rw-r--r--arch/x86/kernel/cpu/bugs.c51
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c49
-rw-r--r--arch/x86/kernel/cpu/common.c141
-rw-r--r--arch/x86/kernel/cpu/cpu.h3
-rw-r--r--arch/x86/kernel/cpu/debugfs.c58
-rw-r--r--arch/x86/kernel/cpu/hygon.c45
-rw-r--r--arch/x86/kernel/cpu/intel.c14
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c68
-rw-r--r--arch/x86/kernel/cpu/mce/apei.c4
-rw-r--r--arch/x86/kernel/cpu/mce/core.c52
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c20
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h4
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c188
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c689
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c683
-rw-r--r--arch/x86/kernel/cpu/microcode/internal.h49
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c5
-rw-r--r--arch/x86/kernel/cpu/proc.c8
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c11
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c14
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h31
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c281
-rw-r--r--arch/x86/kernel/cpu/topology.c13
-rw-r--r--arch/x86/kernel/cpu/zhaoxin.c14
26 files changed, 1359 insertions, 1186 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 4350f6bfc0..93eabf5440 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -54,6 +54,8 @@ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o
obj-$(CONFIG_ACRN_GUEST) += acrn.o
+obj-$(CONFIG_DEBUG_FS) += debugfs.o
+
quiet_cmd_mkcapflags = MKCAP $@
cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 6e4f23f314..2055fb308f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -382,7 +382,7 @@ static int nearby_node(int apicid)
#endif
/*
- * Fix up cpu_core_id for pre-F17h systems to be in the
+ * Fix up topo::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.
*/
@@ -394,7 +394,7 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
return;
cus_per_node = c->x86_max_cores / nodes_per_socket;
- c->cpu_core_id %= cus_per_node;
+ c->topo.core_id %= cus_per_node;
}
/*
@@ -405,8 +405,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
*/
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;
@@ -414,13 +412,13 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- c->cpu_die_id = ecx & 0xff;
+ c->topo.die_id = ecx & 0xff;
if (c->x86 == 0x15)
- c->cu_id = ebx & 0xff;
+ c->topo.cu_id = ebx & 0xff;
if (c->x86 >= 0x17) {
- c->cpu_core_id = ebx & 0xff;
+ c->topo.core_id = ebx & 0xff;
if (smp_num_siblings > 1)
c->x86_max_cores /= smp_num_siblings;
@@ -434,15 +432,14 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
if (!err)
c->x86_coreid_bits = get_count_order(c->x86_max_cores);
- cacheinfo_amd_init_llc_id(c, cpu);
+ cacheinfo_amd_init_llc_id(c);
} 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;
+ c->topo.die_id = value & 7;
+ c->topo.llc_id = c->topo.die_id;
} else
return;
@@ -459,15 +456,14 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
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);
+ c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1);
/* Convert the initial APIC ID into the socket ID */
- c->phys_proc_id = c->initial_apicid >> bits;
+ c->topo.pkg_id = c->topo.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;
+ c->topo.llc_id = c->topo.die_id = c->topo.pkg_id;
}
u32 amd_get_nodes_per_socket(void)
@@ -481,11 +477,11 @@ 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
@@ -515,7 +511,7 @@ 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];
@@ -1014,7 +1010,6 @@ static bool cpu_has_zenbleed_microcode(void)
default:
return false;
- break;
}
if (boot_cpu_data.microcode < good_rev)
@@ -1044,6 +1039,8 @@ static void zenbleed_check(struct cpuinfo_x86 *c)
static void init_amd(struct cpuinfo_x86 *c)
{
+ u64 vm_cr;
+
early_init_amd(c);
/*
@@ -1060,7 +1057,7 @@ static void init_amd(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_FSRS);
/* get apicid instead of initial apic id from cpuid */
- c->apicid = read_apic_id();
+ c->topo.apicid = read_apic_id();
/* K6s reports MCEs but don't actually have all the MSRs */
if (c->x86 < 6)
@@ -1095,6 +1092,14 @@ static void init_amd(struct cpuinfo_x86 *c)
init_amd_cacheinfo(c);
+ if (cpu_has(c, X86_FEATURE_SVM)) {
+ rdmsrl(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
@@ -1157,6 +1162,9 @@ static void init_amd(struct cpuinfo_x86 *c)
if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
cpu_has_amd_erratum(c, amd_erratum_1485))
msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+
+ /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 0bc55472f3..bb0ab8466b 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -63,7 +63,7 @@ EXPORT_SYMBOL_GPL(x86_pred_cmd);
static DEFINE_MUTEX(spec_ctrl_mutex);
-void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk;
+void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
/* Update SPEC_CTRL MSR and its cached copy unconditionally */
static void update_spec_ctrl(u64 val)
@@ -717,7 +717,7 @@ void update_gds_msr(void)
case GDS_MITIGATION_UCODE_NEEDED:
case GDS_MITIGATION_HYPERVISOR:
return;
- };
+ }
wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
@@ -1019,7 +1019,6 @@ static void __init retbleed_select_mitigation(void)
do_cmd_auto:
case RETBLEED_CMD_AUTO:
- default:
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY))
@@ -1042,8 +1041,7 @@ do_cmd_auto:
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_UNRET);
- if (IS_ENABLED(CONFIG_RETHUNK))
- x86_return_thunk = retbleed_return_thunk;
+ x86_return_thunk = retbleed_return_thunk;
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -1061,7 +1059,8 @@ do_cmd_auto:
case RETBLEED_MITIGATION_STUFF:
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
- x86_set_skl_return_thunk();
+
+ x86_return_thunk = call_depth_return_thunk;
break;
default:
@@ -1290,6 +1289,8 @@ spectre_v2_user_select_mitigation(void)
spectre_v2_user_ibpb = mode;
switch (cmd) {
+ case SPECTRE_V2_USER_CMD_NONE:
+ break;
case SPECTRE_V2_USER_CMD_FORCE:
case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
@@ -1301,8 +1302,6 @@ spectre_v2_user_select_mitigation(void)
case SPECTRE_V2_USER_CMD_SECCOMP:
static_branch_enable(&switch_mm_cond_ibpb);
break;
- default:
- break;
}
pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
@@ -2160,6 +2159,10 @@ static int l1d_flush_prctl_get(struct task_struct *task)
static int ssb_prctl_get(struct task_struct *task)
{
switch (ssb_mode) {
+ case SPEC_STORE_BYPASS_NONE:
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ return PR_SPEC_ENABLE;
+ return PR_SPEC_NOT_AFFECTED;
case SPEC_STORE_BYPASS_DISABLE:
return PR_SPEC_DISABLE;
case SPEC_STORE_BYPASS_SECCOMP:
@@ -2171,11 +2174,8 @@ static int ssb_prctl_get(struct task_struct *task)
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;
}
+ BUG();
}
static int ib_prctl_get(struct task_struct *task)
@@ -2410,13 +2410,21 @@ static void __init srso_select_mitigation(void)
{
bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE);
- if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off())
- goto pred_cmd;
+ if (cpu_mitigations_off())
+ return;
+
+ if (!boot_cpu_has_bug(X86_BUG_SRSO)) {
+ if (boot_cpu_has(X86_FEATURE_SBPB))
+ x86_pred_cmd = PRED_CMD_SBPB;
+ return;
+ }
if (has_microcode) {
/*
* Zen1/2 with SMT off aren't vulnerable after the right
* IBPB microcode has been applied.
+ *
+ * Zen1/2 don't have SBPB, no need to try to enable it here.
*/
if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
@@ -2437,7 +2445,9 @@ static void __init srso_select_mitigation(void)
switch (srso_cmd) {
case SRSO_CMD_OFF:
- goto pred_cmd;
+ if (boot_cpu_has(X86_FEATURE_SBPB))
+ x86_pred_cmd = PRED_CMD_SBPB;
+ return;
case SRSO_CMD_MICROCODE:
if (has_microcode) {
@@ -2468,7 +2478,6 @@ static void __init srso_select_mitigation(void)
srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED;
} else {
pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
- goto pred_cmd;
}
break;
@@ -2480,7 +2489,6 @@ static void __init srso_select_mitigation(void)
}
} else {
pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n");
- goto pred_cmd;
}
break;
@@ -2492,21 +2500,12 @@ static void __init srso_select_mitigation(void)
}
} else {
pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
- goto pred_cmd;
}
break;
-
- default:
- break;
}
out:
pr_info("%s\n", srso_strings[srso_mitigation]);
-
-pred_cmd:
- if ((!boot_cpu_has_bug(X86_BUG_SRSO) || srso_cmd == SRSO_CMD_OFF) &&
- boot_cpu_has(X86_FEATURE_SBPB))
- x86_pred_cmd = PRED_CMD_SBPB;
}
#undef pr_fmt
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 8f86eacf69..c131c412db 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -661,7 +661,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
return i;
}
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu)
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c)
{
/*
* We may have multiple LLCs if L3 caches exist, so check if we
@@ -672,13 +672,13 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu)
if (c->x86 < 0x17) {
/* LLC is at the node level. */
- per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
+ c->topo.llc_id = c->topo.die_id;
} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
/*
* LLC is at the core complex level.
* Core complex ID is ApicId[3] for these processors.
*/
- per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+ c->topo.llc_id = c->topo.apicid >> 3;
} else {
/*
* LLC ID is calculated from the number of threads sharing the
@@ -694,12 +694,12 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu)
if (num_sharing_cache) {
int bits = get_count_order(num_sharing_cache);
- per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
+ c->topo.llc_id = c->topo.apicid >> bits;
}
}
}
-void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu)
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
{
/*
* We may have multiple LLCs if L3 caches exist, so check if we
@@ -712,7 +712,7 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu)
* LLC is at the core complex level.
* Core complex ID is ApicId[3] for these processors.
*/
- per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+ c->topo.llc_id = c->topo.apicid >> 3;
}
void init_amd_cacheinfo(struct cpuinfo_x86 *c)
@@ -740,9 +740,6 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-#ifdef CONFIG_SMP
- unsigned int cpu = c->cpu_index;
-#endif
if (c->cpuid_level > 3) {
static int is_initialized;
@@ -776,13 +773,13 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
new_l2 = this_leaf.size/1024;
num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
index_msb = get_count_order(num_threads_sharing);
- l2_id = c->apicid & ~((1 << index_msb) - 1);
+ l2_id = c->topo.apicid & ~((1 << index_msb) - 1);
break;
case 3:
new_l3 = this_leaf.size/1024;
num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
index_msb = get_count_order(num_threads_sharing);
- l3_id = c->apicid & ~((1 << index_msb) - 1);
+ l3_id = c->topo.apicid & ~((1 << index_msb) - 1);
break;
default:
break;
@@ -856,30 +853,24 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
if (new_l2) {
l2 = new_l2;
-#ifdef CONFIG_SMP
- per_cpu(cpu_llc_id, cpu) = l2_id;
- per_cpu(cpu_l2c_id, cpu) = l2_id;
-#endif
+ c->topo.llc_id = l2_id;
+ c->topo.l2c_id = l2_id;
}
if (new_l3) {
l3 = new_l3;
-#ifdef CONFIG_SMP
- per_cpu(cpu_llc_id, cpu) = l3_id;
-#endif
+ c->topo.llc_id = l3_id;
}
-#ifdef CONFIG_SMP
/*
- * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
+ * If llc_id is not yet set, this means cpuid_level < 4 which in
* turns means that the only possibility is SMT (as indicated in
* cpuid1). Since cpuid2 doesn't specify shared caches, and we know
* that SMT shares all caches, we can unconditionally set cpu_llc_id to
- * c->phys_proc_id.
+ * c->topo.pkg_id.
*/
- if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
- per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
-#endif
+ if (c->topo.llc_id == BAD_APICID)
+ c->topo.llc_id = c->topo.pkg_id;
c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
@@ -915,7 +906,7 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
unsigned int apicid, nshared, first, last;
nshared = base->eax.split.num_threads_sharing + 1;
- apicid = cpu_data(cpu).apicid;
+ apicid = cpu_data(cpu).topo.apicid;
first = apicid - (apicid % nshared);
last = first + nshared - 1;
@@ -924,14 +915,14 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
if (!this_cpu_ci->info_list)
continue;
- apicid = cpu_data(i).apicid;
+ apicid = cpu_data(i).topo.apicid;
if ((apicid < first) || (apicid > last))
continue;
this_leaf = this_cpu_ci->info_list + index;
for_each_online_cpu(sibling) {
- apicid = cpu_data(sibling).apicid;
+ apicid = cpu_data(sibling).topo.apicid;
if ((apicid < first) || (apicid > last))
continue;
cpumask_set_cpu(sibling,
@@ -969,7 +960,7 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
index_msb = get_count_order(num_threads_sharing);
for_each_online_cpu(i)
- if (cpu_data(i).apicid >> index_msb == c->apicid >> index_msb) {
+ if (cpu_data(i).topo.apicid >> index_msb == c->topo.apicid >> index_msb) {
struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
if (i == cpu || !sib_cpu_ci->info_list)
@@ -1024,7 +1015,7 @@ static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs)
num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing;
index_msb = get_count_order(num_threads_sharing);
- id4_regs->id = c->apicid >> index_msb;
+ id4_regs->id = c->topo.apicid >> index_msb;
}
int populate_cache_leaves(unsigned int cpu)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4e5ffc8b0e..98f7ea6b93 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -62,6 +62,7 @@
#include <asm/intel-family.h>
#include <asm/cpu_device_id.h>
#include <asm/uv/uv.h>
+#include <asm/ia32.h>
#include <asm/set_memory.h>
#include <asm/traps.h>
#include <asm/sev.h>
@@ -74,18 +75,6 @@ u32 elf_hwcap2 __read_mostly;
int smp_num_siblings = 1;
EXPORT_SYMBOL(smp_num_siblings);
-/* Last level cache ID of each logical CPU */
-DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
-
-u16 get_llc_id(unsigned int cpu)
-{
- return per_cpu(cpu_llc_id, cpu);
-}
-EXPORT_SYMBOL_GPL(get_llc_id);
-
-/* L2 cache ID of each logical CPU */
-DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id) = BAD_APICID;
-
static struct ppin_info {
int feature;
int msr_ppin_ctl;
@@ -914,7 +903,7 @@ void detect_ht(struct cpuinfo_x86 *c)
return;
index_msb = get_count_order(smp_num_siblings);
- c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
+ c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb);
smp_num_siblings = smp_num_siblings / c->x86_max_cores;
@@ -922,8 +911,8 @@ void detect_ht(struct cpuinfo_x86 *c)
core_bits = get_count_order(c->x86_max_cores);
- c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
- ((1 << core_bits) - 1);
+ c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb) &
+ ((1 << core_bits) - 1);
#endif
}
@@ -1114,18 +1103,34 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
void get_cpu_address_sizes(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
+ bool vp_bits_from_cpuid = true;
- if (c->extended_cpuid_level >= 0x80000008) {
+ if (!cpu_has(c, X86_FEATURE_CPUID) ||
+ (c->extended_cpuid_level < 0x80000008))
+ vp_bits_from_cpuid = false;
+
+ if (vp_bits_from_cpuid) {
cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
+ } else {
+ if (IS_ENABLED(CONFIG_X86_64)) {
+ c->x86_clflush_size = 64;
+ c->x86_phys_bits = 36;
+ c->x86_virt_bits = 48;
+ } else {
+ c->x86_clflush_size = 32;
+ c->x86_virt_bits = 32;
+ c->x86_phys_bits = 32;
+
+ if (cpu_has(c, X86_FEATURE_PAE) ||
+ cpu_has(c, X86_FEATURE_PSE36))
+ c->x86_phys_bits = 36;
+ }
}
-#ifdef CONFIG_X86_32
- else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
- c->x86_phys_bits = 36;
-#endif
c->x86_cache_bits = c->x86_phys_bits;
+ c->x86_cache_alignment = c->x86_clflush_size;
}
static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -1579,17 +1584,6 @@ static void __init cpu_parse_early_param(void)
*/
static void __init early_identify_cpu(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_64
- c->x86_clflush_size = 64;
- c->x86_phys_bits = 36;
- c->x86_virt_bits = 48;
-#else
- c->x86_clflush_size = 32;
- c->x86_phys_bits = 32;
- c->x86_virt_bits = 32;
-#endif
- c->x86_cache_alignment = c->x86_clflush_size;
-
memset(&c->x86_capability, 0, sizeof(c->x86_capability));
c->extended_cpuid_level = 0;
@@ -1601,7 +1595,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
cpu_detect(c);
get_cpu_vendor(c);
get_cpu_cap(c);
- get_cpu_address_sizes(c);
setup_force_cpu_cap(X86_FEATURE_CPUID);
cpu_parse_early_param();
@@ -1617,6 +1610,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_clear_cpu_cap(X86_FEATURE_CPUID);
}
+ get_cpu_address_sizes(c);
+
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
cpu_set_bug_bits(c);
@@ -1761,15 +1756,15 @@ static void generic_identify(struct cpuinfo_x86 *c)
get_cpu_address_sizes(c);
if (c->cpuid_level >= 0x00000001) {
- c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
+ c->topo.initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
# ifdef CONFIG_SMP
- c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+ c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
# else
- c->apicid = c->initial_apicid;
+ c->topo.apicid = c->topo.initial_apicid;
# endif
#endif
- c->phys_proc_id = c->initial_apicid;
+ c->topo.pkg_id = c->topo.initial_apicid;
}
get_model_name(c); /* Default name */
@@ -1799,18 +1794,19 @@ static void generic_identify(struct cpuinfo_x86 *c)
static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
- unsigned int apicid, cpu = smp_processor_id();
+ unsigned int cpu = smp_processor_id();
+ u32 apicid;
apicid = apic->cpu_present_to_apicid(cpu);
- if (apicid != c->apicid) {
+ if (apicid != c->topo.apicid) {
pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n",
- cpu, apicid, c->initial_apicid);
+ cpu, apicid, c->topo.initial_apicid);
}
- BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
- BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
+ BUG_ON(topology_update_package_map(c->topo.pkg_id, cpu));
+ BUG_ON(topology_update_die_map(c->topo.die_id, cpu));
#else
- c->logical_proc_id = 0;
+ c->topo.logical_pkg_id = 0;
#endif
}
@@ -1829,7 +1825,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
c->x86_model_id[0] = '\0'; /* Unset */
c->x86_max_cores = 1;
c->x86_coreid_bits = 0;
- c->cu_id = 0xff;
+ c->topo.cu_id = 0xff;
+ c->topo.llc_id = BAD_APICID;
+ c->topo.l2c_id = BAD_APICID;
#ifdef CONFIG_X86_64
c->x86_clflush_size = 64;
c->x86_phys_bits = 36;
@@ -1855,9 +1853,16 @@ static void identify_cpu(struct cpuinfo_x86 *c)
apply_forced_caps(c);
#ifdef CONFIG_X86_64
- c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+ c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
#endif
+
+ /*
+ * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and
+ * Hygon will clear it in ->c_init() below.
+ */
+ set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
/*
* Vendor-specific initialization. In this section we
* canonicalize the feature flags, meaning if there are
@@ -2074,24 +2079,24 @@ void syscall_init(void)
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
-#ifdef CONFIG_IA32_EMULATION
- wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
- /*
- * This only works on Intel CPUs.
- * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
- * This does not cause SYSENTER to jump to the wrong location, because
- * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
- */
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
- (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
-#else
- wrmsrl_cstar((unsigned long)ignore_sysret);
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
-#endif
+ if (ia32_enabled()) {
+ wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
+ /*
+ * This only works on Intel CPUs.
+ * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
+ * This does not cause SYSENTER to jump to the wrong location, because
+ * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
+ */
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+ (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
+ } else {
+ wrmsrl_cstar((unsigned long)entry_SYSCALL32_ignore);
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
+ }
/*
* Flags to clear on syscall; clear as much as possible
@@ -2166,8 +2171,6 @@ static inline void setup_getcpu(int cpu)
}
#ifdef CONFIG_X86_64
-static inline void ucode_cpu_init(int cpu) { }
-
static inline void tss_setup_ist(struct tss_struct *tss)
{
/* Set up the per-CPU TSS IST stacks */
@@ -2178,16 +2181,8 @@ static inline void tss_setup_ist(struct tss_struct *tss)
/* Only mapped when SEV-ES is active */
tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC);
}
-
#else /* CONFIG_X86_64 */
-
-static inline void ucode_cpu_init(int cpu)
-{
- show_ucode_info_early();
-}
-
static inline void tss_setup_ist(struct tss_struct *tss) { }
-
#endif /* !CONFIG_X86_64 */
static inline void tss_setup_io_bitmap(struct tss_struct *tss)
@@ -2243,8 +2238,6 @@ void cpu_init(void)
struct task_struct *cur = current;
int cpu = raw_smp_processor_id();
- ucode_cpu_init(cpu);
-
#ifdef CONFIG_NUMA
if (this_cpu_read(numa_node) == 0 &&
early_cpu_to_node(cpu) != NUMA_NO_NODE)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 1dcd7d4e38..885281ae79 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -78,6 +78,9 @@ extern int detect_ht_early(struct cpuinfo_x86 *c);
extern void detect_ht(struct cpuinfo_x86 *c);
extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c);
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c);
+
unsigned int aperfmperf_get_khz(int cpu);
void cpu_select_mitigations(void);
diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c
new file mode 100644
index 0000000000..0c179d684b
--- /dev/null
+++ b/arch/x86/kernel/cpu/debugfs.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/debugfs.h>
+
+#include <asm/apic.h>
+#include <asm/processor.h>
+
+static int cpu_debug_show(struct seq_file *m, void *p)
+{
+ unsigned long cpu = (unsigned long)m->private;
+ struct cpuinfo_x86 *c = per_cpu_ptr(&cpu_info, cpu);
+
+ seq_printf(m, "online: %d\n", cpu_online(cpu));
+ if (!c->initialized)
+ return 0;
+
+ seq_printf(m, "initial_apicid: %x\n", c->topo.initial_apicid);
+ seq_printf(m, "apicid: %x\n", c->topo.apicid);
+ seq_printf(m, "pkg_id: %u\n", c->topo.pkg_id);
+ seq_printf(m, "die_id: %u\n", c->topo.die_id);
+ seq_printf(m, "cu_id: %u\n", c->topo.cu_id);
+ seq_printf(m, "core_id: %u\n", c->topo.core_id);
+ seq_printf(m, "logical_pkg_id: %u\n", c->topo.logical_pkg_id);
+ seq_printf(m, "logical_die_id: %u\n", c->topo.logical_die_id);
+ seq_printf(m, "llc_id: %u\n", c->topo.llc_id);
+ seq_printf(m, "l2c_id: %u\n", c->topo.l2c_id);
+ seq_printf(m, "max_cores: %u\n", c->x86_max_cores);
+ seq_printf(m, "max_die_per_pkg: %u\n", __max_die_per_package);
+ seq_printf(m, "smp_num_siblings: %u\n", smp_num_siblings);
+ return 0;
+}
+
+static int cpu_debug_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, cpu_debug_show, inode->i_private);
+}
+
+static const struct file_operations dfs_cpu_ops = {
+ .open = cpu_debug_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static __init int cpu_init_debugfs(void)
+{
+ struct dentry *dir, *base = debugfs_create_dir("topo", arch_debugfs_dir);
+ unsigned long id;
+ char name[24];
+
+ dir = debugfs_create_dir("cpus", base);
+ for_each_possible_cpu(id) {
+ sprintf(name, "%lu", id);
+ debugfs_create_file(name, 0444, dir, (void *)id, &dfs_cpu_ops);
+ }
+ return 0;
+}
+late_initcall(cpu_init_debugfs);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index a7b3ef4c4d..f0cd95502f 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -63,8 +63,6 @@ static void hygon_get_topology_early(struct cpuinfo_x86 *c)
*/
static void hygon_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;
@@ -72,9 +70,9 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- c->cpu_die_id = ecx & 0xff;
+ c->topo.die_id = ecx & 0xff;
- c->cpu_core_id = ebx & 0xff;
+ c->topo.core_id = ebx & 0xff;
if (smp_num_siblings > 1)
c->x86_max_cores /= smp_num_siblings;
@@ -92,16 +90,15 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
* when running on host.
*/
if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && c->x86_model <= 0x3)
- c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
+ c->topo.pkg_id = c->topo.apicid >> APICID_SOCKET_ID_BIT;
- cacheinfo_hygon_init_llc_id(c, cpu);
+ cacheinfo_hygon_init_llc_id(c);
} 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;
+ c->topo.die_id = value & 7;
+ c->topo.llc_id = c->topo.die_id;
} else
return;
@@ -116,15 +113,14 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
static void hygon_detect_cmp(struct cpuinfo_x86 *c)
{
unsigned int 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);
+ c->topo.core_id = c->topo.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;
+ c->topo.pkg_id = c->topo.initial_apicid >> bits;
+ /* Use package ID also for last level cache */
+ c->topo.llc_id = c->topo.die_id = c->topo.pkg_id;
}
static void srat_detect_node(struct cpuinfo_x86 *c)
@@ -132,11 +128,11 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#ifdef CONFIG_NUMA
int cpu = smp_processor_id();
int node;
- unsigned int apicid = c->apicid;
+ unsigned int apicid = c->topo.apicid;
node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
- node = per_cpu(cpu_llc_id, cpu);
+ node = c->topo.llc_id;
/*
* On multi-fabric platform (e.g. Numascale NumaChip) a
@@ -165,7 +161,7 @@ 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];
@@ -294,6 +290,8 @@ static void early_init_hygon(struct cpuinfo_x86 *c)
static void init_hygon(struct cpuinfo_x86 *c)
{
+ u64 vm_cr;
+
early_init_hygon(c);
/*
@@ -305,7 +303,7 @@ static void init_hygon(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
/* get apicid instead of initial apic id from cpuid */
- c->apicid = read_apic_id();
+ c->topo.apicid = read_apic_id();
/*
* XXX someone from Hygon needs to confirm this DTRT
@@ -324,6 +322,14 @@ static void init_hygon(struct cpuinfo_x86 *c)
init_hygon_cacheinfo(c);
+ if (cpu_has(c, X86_FEATURE_SVM)) {
+ rdmsrl(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_XMM2)) {
/*
* Use LFENCE for execution serialization. On families which
@@ -348,6 +354,9 @@ static void init_hygon(struct cpuinfo_x86 *c)
set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
check_null_seg_clears_base(c);
+
+ /* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
}
static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index be4045628f..a927a8fc96 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -314,19 +314,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
setup_clear_cpu_cap(X86_FEATURE_PGE);
}
- if (c->cpuid_level >= 0x00000001) {
- u32 eax, ebx, ecx, edx;
-
- cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
- /*
- * If HTT (EDX[28]) is set EBX[16:23] contain the number of
- * apicids which are reserved per package. Store the resulting
- * shift value for the package management code.
- */
- if (edx & (1U << 28))
- c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
- }
-
check_memory_type_self_snoop_errata(c);
/*
@@ -1016,7 +1003,6 @@ static struct ctl_table sld_sysctls[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
- {}
};
static int __init sld_mitigate_sysctl_init(void)
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index c267f43de3..f3517b8a8e 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -713,17 +713,75 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
deferred_error_interrupt_enable(c);
}
-bool amd_mce_is_memory_error(struct mce *m)
+/*
+ * DRAM ECC errors are reported in the Northbridge (bank 4) with
+ * Extended Error Code 8.
+ */
+static bool legacy_mce_is_memory_error(struct mce *m)
+{
+ return m->bank == 4 && XEC(m->status, 0x1f) == 8;
+}
+
+/*
+ * DRAM ECC errors are reported in Unified Memory Controllers with
+ * Extended Error Code 0.
+ */
+static bool smca_mce_is_memory_error(struct mce *m)
{
enum smca_bank_types bank_type;
- /* ErrCodeExt[20:16] */
- u8 xec = (m->status >> 16) & 0x1f;
+
+ if (XEC(m->status, 0x3f))
+ return false;
bank_type = smca_get_bank_type(m->extcpu, m->bank);
+
+ return bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2;
+}
+
+bool amd_mce_is_memory_error(struct mce *m)
+{
if (mce_flags.smca)
- return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0;
+ return smca_mce_is_memory_error(m);
+ else
+ return legacy_mce_is_memory_error(m);
+}
+
+/*
+ * AMD systems do not have an explicit indicator that the value in MCA_ADDR is
+ * a system physical address. Therefore, individual cases need to be detected.
+ * Future cases and checks will be added as needed.
+ *
+ * 1) General case
+ * a) Assume address is not usable.
+ * 2) Poison errors
+ * a) Indicated by MCA_STATUS[43]: poison. Defined for all banks except legacy
+ * northbridge (bank 4).
+ * b) Refers to poison consumption in the core. Does not include "no action",
+ * "action optional", or "deferred" error severities.
+ * c) Will include a usable address so that immediate action can be taken.
+ * 3) Northbridge DRAM ECC errors
+ * a) Reported in legacy bank 4 with extended error code (XEC) 8.
+ * b) MCA_STATUS[43] is *not* defined as poison in legacy bank 4. Therefore,
+ * this bit should not be checked.
+ *
+ * NOTE: SMCA UMC memory errors fall into case #1.
+ */
+bool amd_mce_usable_address(struct mce *m)
+{
+ /* Check special northbridge case 3) first. */
+ if (!mce_flags.smca) {
+ if (legacy_mce_is_memory_error(m))
+ return true;
+ else if (m->bank == 4)
+ return false;
+ }
- return m->bank == 4 && xec == 0x8;
+ /* Check poison bit for all other bank types. */
+ if (m->status & MCI_STATUS_POISON)
+ return true;
+
+ /* Assume address is not usable for all others. */
+ return false;
}
static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c
index 8ed3417146..7f7309ff67 100644
--- a/arch/x86/kernel/cpu/mce/apei.c
+++ b/arch/x86/kernel/cpu/mce/apei.c
@@ -103,9 +103,9 @@ int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id)
m.socketid = -1;
for_each_possible_cpu(cpu) {
- if (cpu_data(cpu).initial_apicid == lapic_id) {
+ if (cpu_data(cpu).topo.initial_apicid == lapic_id) {
m.extcpu = cpu;
- m.socketid = cpu_data(m.extcpu).phys_proc_id;
+ m.socketid = cpu_data(m.extcpu).topo.pkg_id;
break;
}
}
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 6f35f724cc..df8d25e744 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -44,6 +44,7 @@
#include <linux/sync_core.h>
#include <linux/task_work.h>
#include <linux/hardirq.h>
+#include <linux/kexec.h>
#include <asm/intel-family.h>
#include <asm/processor.h>
@@ -123,8 +124,8 @@ void mce_setup(struct mce *m)
m->time = __ktime_get_real_seconds();
m->cpuvendor = boot_cpu_data.x86_vendor;
m->cpuid = cpuid_eax(1);
- m->socketid = cpu_data(m->extcpu).phys_proc_id;
- m->apicid = cpu_data(m->extcpu).initial_apicid;
+ m->socketid = cpu_data(m->extcpu).topo.pkg_id;
+ m->apicid = cpu_data(m->extcpu).topo.initial_apicid;
m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP);
m->ppin = cpu_data(m->extcpu).ppin;
m->microcode = boot_cpu_data.microcode;
@@ -233,6 +234,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
struct llist_node *pending;
struct mce_evt_llist *l;
int apei_err = 0;
+ struct page *p;
/*
* Allow instrumentation around external facilities usage. Not that it
@@ -286,6 +288,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
if (!fake_panic) {
if (panic_timeout == 0)
panic_timeout = mca_cfg.panic_timeout;
+
+ /*
+ * Kdump skips the poisoned page in order to avoid
+ * touching the error bits again. Poison the page even
+ * if the error is fatal and the machine is about to
+ * panic.
+ */
+ if (kexec_crash_loaded()) {
+ if (final && (final->status & MCI_STATUS_ADDRV)) {
+ p = pfn_to_online_page(final->addr >> PAGE_SHIFT);
+ if (p)
+ SetPageHWPoison(p);
+ }
+ }
panic(msg);
} else
pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
@@ -453,32 +469,22 @@ static void mce_irq_work_cb(struct irq_work *entry)
mce_schedule_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
- * be somewhat complicated (e.g. segment offset would require an instruction
- * parser). So only support physical addresses up to page granularity for now.
- */
-int mce_usable_address(struct mce *m)
+bool mce_usable_address(struct mce *m)
{
if (!(m->status & MCI_STATUS_ADDRV))
- return 0;
-
- /* Checks after this one are Intel/Zhaoxin-specific: */
- if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
- boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
- return 1;
-
- if (!(m->status & MCI_STATUS_MISCV))
- return 0;
+ return false;
- if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
- return 0;
+ switch (m->cpuvendor) {
+ case X86_VENDOR_AMD:
+ return amd_mce_usable_address(m);
- if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
- return 0;
+ case X86_VENDOR_INTEL:
+ case X86_VENDOR_ZHAOXIN:
+ return intel_mce_usable_address(m);
- return 1;
+ default:
+ return true;
+ }
}
EXPORT_SYMBOL_GPL(mce_usable_address);
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index f5323551c1..52bce533dd 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -536,3 +536,23 @@ bool intel_filter_mce(struct mce *m)
return false;
}
+
+/*
+ * 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
+ * be somewhat complicated (e.g. segment offset would require an instruction
+ * parser). So only support physical addresses up to page granularity for now.
+ */
+bool intel_mce_usable_address(struct mce *m)
+{
+ if (!(m->status & MCI_STATUS_MISCV))
+ return false;
+
+ if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
+ return false;
+
+ if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
+ return false;
+
+ return true;
+}
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index bcf1b3c66c..e13a26c9c0 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -49,6 +49,7 @@ void intel_init_cmci(void);
void intel_init_lmce(void);
void intel_clear_lmce(void);
bool intel_filter_mce(struct mce *m);
+bool intel_mce_usable_address(struct mce *m);
#else
# define cmci_intel_adjust_timer mce_adjust_timer_default
static inline bool mce_intel_cmci_poll(void) { return false; }
@@ -58,6 +59,7 @@ static inline void intel_init_cmci(void) { }
static inline void intel_init_lmce(void) { }
static inline void intel_clear_lmce(void) { }
static inline bool intel_filter_mce(struct mce *m) { return false; }
+static inline bool intel_mce_usable_address(struct mce *m) { return false; }
#endif
void mce_timer_kick(unsigned long interval);
@@ -210,6 +212,7 @@ extern bool filter_mce(struct mce *m);
#ifdef CONFIG_X86_MCE_AMD
extern bool amd_filter_mce(struct mce *m);
+bool amd_mce_usable_address(struct mce *m);
/*
* If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits
@@ -237,6 +240,7 @@ static __always_inline void smca_extract_err_addr(struct mce *m)
#else
static inline bool amd_filter_mce(struct mce *m) { return false; }
+static inline bool amd_mce_usable_address(struct mce *m) { return false; }
static inline void smca_extract_err_addr(struct mce *m) { }
#endif
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index bbd1dc38ea..13b45b9c80 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -37,6 +37,16 @@
#include "internal.h"
+struct ucode_patch {
+ struct list_head plist;
+ void *data;
+ unsigned int size;
+ u32 patch_id;
+ u16 equiv_cpu;
+};
+
+static LIST_HEAD(microcode_cache);
+
#define UCODE_MAGIC 0x00414d44
#define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000
#define UCODE_UCODE_TYPE 0x00000001
@@ -94,8 +104,6 @@ struct cont_desc {
size_t size;
};
-static u32 ucode_new_rev;
-
/*
* Microcode patch container file is prepended to the initrd in cpio
* format. See Documentation/arch/x86/microcode.rst
@@ -121,24 +129,20 @@ static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig)
/*
* Check whether there is a valid microcode container file at the beginning
- * of @buf of size @buf_size. Set @early to use this function in the early path.
+ * of @buf of size @buf_size.
*/
-static bool verify_container(const u8 *buf, size_t buf_size, bool early)
+static bool verify_container(const u8 *buf, size_t buf_size)
{
u32 cont_magic;
if (buf_size <= CONTAINER_HDR_SZ) {
- if (!early)
- pr_debug("Truncated microcode container header.\n");
-
+ pr_debug("Truncated microcode container header.\n");
return false;
}
cont_magic = *(const u32 *)buf;
if (cont_magic != UCODE_MAGIC) {
- if (!early)
- pr_debug("Invalid magic value (0x%08x).\n", cont_magic);
-
+ pr_debug("Invalid magic value (0x%08x).\n", cont_magic);
return false;
}
@@ -147,23 +151,20 @@ static bool verify_container(const u8 *buf, size_t buf_size, bool early)
/*
* Check whether there is a valid, non-truncated CPU equivalence table at the
- * beginning of @buf of size @buf_size. Set @early to use this function in the
- * early path.
+ * beginning of @buf of size @buf_size.
*/
-static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
+static bool verify_equivalence_table(const u8 *buf, size_t buf_size)
{
const u32 *hdr = (const u32 *)buf;
u32 cont_type, equiv_tbl_len;
- if (!verify_container(buf, buf_size, early))
+ if (!verify_container(buf, buf_size))
return false;
cont_type = hdr[1];
if (cont_type != UCODE_EQUIV_CPU_TABLE_TYPE) {
- if (!early)
- pr_debug("Wrong microcode container equivalence table type: %u.\n",
- cont_type);
-
+ pr_debug("Wrong microcode container equivalence table type: %u.\n",
+ cont_type);
return false;
}
@@ -172,9 +173,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
equiv_tbl_len = hdr[2];
if (equiv_tbl_len < sizeof(struct equiv_cpu_entry) ||
buf_size < equiv_tbl_len) {
- if (!early)
- pr_debug("Truncated equivalence table.\n");
-
+ pr_debug("Truncated equivalence table.\n");
return false;
}
@@ -183,22 +182,19 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
/*
* Check whether there is a valid, non-truncated microcode patch section at the
- * beginning of @buf of size @buf_size. Set @early to use this function in the
- * early path.
+ * beginning of @buf of size @buf_size.
*
* On success, @sh_psize returns the patch size according to the section header,
* to the caller.
*/
static bool
-__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early)
+__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
{
u32 p_type, p_size;
const u32 *hdr;
if (buf_size < SECTION_HDR_SIZE) {
- if (!early)
- pr_debug("Truncated patch section.\n");
-
+ pr_debug("Truncated patch section.\n");
return false;
}
@@ -207,17 +203,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early
p_size = hdr[1];
if (p_type != UCODE_UCODE_TYPE) {
- if (!early)
- pr_debug("Invalid type field (0x%x) in container file section header.\n",
- p_type);
-
+ pr_debug("Invalid type field (0x%x) in container file section header.\n",
+ p_type);
return false;
}
if (p_size < sizeof(struct microcode_header_amd)) {
- if (!early)
- pr_debug("Patch of size %u too short.\n", p_size);
-
+ pr_debug("Patch of size %u too short.\n", p_size);
return false;
}
@@ -269,7 +261,7 @@ static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size
* 0: success
*/
static int
-verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool early)
+verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size)
{
struct microcode_header_amd *mc_hdr;
unsigned int ret;
@@ -277,7 +269,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
u16 proc_id;
u8 patch_fam;
- if (!__verify_patch_section(buf, buf_size, &sh_psize, early))
+ if (!__verify_patch_section(buf, buf_size, &sh_psize))
return -1;
/*
@@ -292,16 +284,13 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
* size sh_psize, as the section claims.
*/
if (buf_size < sh_psize) {
- if (!early)
- pr_debug("Patch of size %u truncated.\n", sh_psize);
-
+ pr_debug("Patch of size %u truncated.\n", sh_psize);
return -1;
}
ret = __verify_patch_size(family, sh_psize, buf_size);
if (!ret) {
- if (!early)
- pr_debug("Per-family patch size mismatch.\n");
+ pr_debug("Per-family patch size mismatch.\n");
return -1;
}
@@ -309,8 +298,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
mc_hdr = (struct microcode_header_amd *)(buf + SECTION_HDR_SIZE);
if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
- if (!early)
- pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id);
+ pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id);
return -1;
}
@@ -337,7 +325,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
u16 eq_id;
u8 *buf;
- if (!verify_equivalence_table(ucode, size, true))
+ if (!verify_equivalence_table(ucode, size))
return 0;
buf = ucode;
@@ -364,7 +352,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
u32 patch_size;
int ret;
- ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true);
+ ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size);
if (ret < 0) {
/*
* Patch verification failed, skip to the next container, if
@@ -452,19 +440,12 @@ static int __apply_microcode_amd(struct microcode_amd *mc)
*
* Returns true if container found (sets @desc), false otherwise.
*/
-static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
+static bool early_apply_microcode(u32 cpuid_1_eax, u32 old_rev, void *ucode, size_t size)
{
struct cont_desc desc = { 0 };
struct microcode_amd *mc;
- u32 rev, dummy, *new_rev;
bool ret = false;
-#ifdef CONFIG_X86_32
- new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
-#else
- new_rev = &ucode_new_rev;
-#endif
-
desc.cpuid_1_eax = cpuid_1_eax;
scan_containers(ucode, size, &desc);
@@ -473,22 +454,15 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
if (!mc)
return ret;
- native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
/*
* Allow application of the same revision to pick up SMT-specific
* changes even if the revision of the other SMT thread is already
* up-to-date.
*/
- if (rev > mc->hdr.patch_id)
+ if (old_rev > mc->hdr.patch_id)
return ret;
- if (!__apply_microcode_amd(mc)) {
- *new_rev = mc->hdr.patch_id;
- ret = true;
- }
-
- return ret;
+ return !__apply_microcode_amd(mc);
}
static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
@@ -501,7 +475,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
if (family >= 0x15)
snprintf(fw_name, sizeof(fw_name),
- "amd-ucode/microcode_amd_fam%.2xh.bin", family);
+ "amd-ucode/microcode_amd_fam%02hhxh.bin", family);
if (firmware_request_builtin(&fw, fw_name)) {
cp->size = fw.size;
@@ -512,57 +486,48 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
return false;
}
-static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret)
+static void __init find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret)
{
- struct ucode_cpu_info *uci;
struct cpio_data cp;
- const char *path;
- bool use_pa;
-
- if (IS_ENABLED(CONFIG_X86_32)) {
- uci = (struct ucode_cpu_info *)__pa_nodebug(ucode_cpu_info);
- path = (const char *)__pa_nodebug(ucode_path);
- use_pa = true;
- } else {
- uci = ucode_cpu_info;
- path = ucode_path;
- use_pa = false;
- }
if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax)))
- cp = find_microcode_in_initrd(path, use_pa);
-
- /* Needed in load_microcode_amd() */
- uci->cpu_sig.sig = cpuid_1_eax;
+ cp = find_microcode_in_initrd(ucode_path);
*ret = cp;
}
-static void apply_ucode_from_containers(unsigned int cpuid_1_eax)
+void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
{
struct cpio_data cp = { };
+ u32 dummy;
+
+ native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->old_rev, dummy);
+
+ /* Needed in load_microcode_amd() */
+ ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
find_blobs_in_containers(cpuid_1_eax, &cp);
if (!(cp.data && cp.size))
return;
- early_apply_microcode(cpuid_1_eax, cp.data, cp.size);
-}
-
-void load_ucode_amd_early(unsigned int cpuid_1_eax)
-{
- return apply_ucode_from_containers(cpuid_1_eax);
+ if (early_apply_microcode(cpuid_1_eax, ed->old_rev, cp.data, cp.size))
+ native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
}
static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
-int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
+static int __init save_microcode_in_initrd(void)
{
+ unsigned int cpuid_1_eax = native_cpuid_eax(1);
+ struct cpuinfo_x86 *c = &boot_cpu_data;
struct cont_desc desc = { 0 };
enum ucode_state ret;
struct cpio_data cp;
- cp = find_microcode_in_initrd(ucode_path, false);
+ if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+ return 0;
+
+ find_blobs_in_containers(cpuid_1_eax, &cp);
if (!(cp.data && cp.size))
return -EINVAL;
@@ -578,6 +543,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
return 0;
}
+early_initcall(save_microcode_in_initrd);
/*
* a small, trivial cache of per-family ucode patches
@@ -631,7 +597,6 @@ static struct ucode_patch *find_patch(unsigned int cpu)
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
u16 equiv_id;
-
equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig);
if (!equiv_id)
return NULL;
@@ -654,10 +619,8 @@ void reload_ucode_amd(unsigned int cpu)
rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
if (rev < mc->hdr.patch_id) {
- if (!__apply_microcode_amd(mc)) {
- ucode_new_rev = mc->hdr.patch_id;
- pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
- }
+ if (!__apply_microcode_amd(mc))
+ pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id);
}
}
@@ -678,8 +641,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
if (p && (p->patch_id == csig->rev))
uci->mc = p->data;
- pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
-
return 0;
}
@@ -720,8 +681,6 @@ static enum ucode_state apply_microcode_amd(int cpu)
rev = mc_amd->hdr.patch_id;
ret = UCODE_UPDATED;
- pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
-
out:
uci->cpu_sig.rev = rev;
c->microcode = rev;
@@ -733,12 +692,20 @@ out:
return ret;
}
+void load_ucode_amd_ap(unsigned int cpuid_1_eax)
+{
+ unsigned int cpu = smp_processor_id();
+
+ ucode_cpu_info[cpu].cpu_sig.sig = cpuid_1_eax;
+ apply_microcode_amd(cpu);
+}
+
static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size)
{
u32 equiv_tbl_len;
const u32 *hdr;
- if (!verify_equivalence_table(buf, buf_size, false))
+ if (!verify_equivalence_table(buf, buf_size))
return 0;
hdr = (const u32 *)buf;
@@ -784,7 +751,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
u16 proc_id;
int ret;
- ret = verify_patch(family, fw, leftover, patch_size, false);
+ ret = verify_patch(family, fw, leftover, patch_size);
if (ret)
return ret;
@@ -909,6 +876,9 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
enum ucode_state ret = UCODE_NFOUND;
const struct firmware *fw;
+ if (force_minrev)
+ return UCODE_NFOUND;
+
if (c->x86 >= 0x15)
snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
@@ -918,7 +888,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
}
ret = UCODE_ERROR;
- if (!verify_container(fw->data, fw->size, false))
+ if (!verify_container(fw->data, fw->size))
goto fw_release;
ret = load_microcode_amd(c->x86, fw->data, fw->size);
@@ -938,10 +908,11 @@ static void microcode_fini_cpu_amd(int cpu)
}
static struct microcode_ops microcode_amd_ops = {
- .request_microcode_fw = request_microcode_amd,
- .collect_cpu_info = collect_cpu_info_amd,
- .apply_microcode = apply_microcode_amd,
- .microcode_fini_cpu = microcode_fini_cpu_amd,
+ .request_microcode_fw = request_microcode_amd,
+ .collect_cpu_info = collect_cpu_info_amd,
+ .apply_microcode = apply_microcode_amd,
+ .microcode_fini_cpu = microcode_fini_cpu_amd,
+ .nmi_safe = true,
};
struct microcode_ops * __init init_amd_microcode(void)
@@ -952,11 +923,6 @@ struct microcode_ops * __init init_amd_microcode(void)
pr_warn("AMD CPU family 0x%x not supported\n", c->x86);
return NULL;
}
-
- if (ucode_new_rev)
- pr_info_once("microcode updated early to new patch_level=0x%08x\n",
- ucode_new_rev);
-
return &microcode_amd_ops;
}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index a4ebd5e0ae..232026a239 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -23,6 +23,7 @@
#include <linux/miscdevice.h>
#include <linux/capability.h>
#include <linux/firmware.h>
+#include <linux/cpumask.h>
#include <linux/kernel.h>
#include <linux/delay.h>
#include <linux/mutex.h>
@@ -31,6 +32,7 @@
#include <linux/fs.h>
#include <linux/mm.h>
+#include <asm/apic.h>
#include <asm/cpu_device_id.h>
#include <asm/perf_event.h>
#include <asm/processor.h>
@@ -39,14 +41,11 @@
#include "internal.h"
-#define DRIVER_VERSION "2.2"
-
static struct microcode_ops *microcode_ops;
-static bool dis_ucode_ldr = true;
-
-bool initrd_gone;
+bool dis_ucode_ldr = true;
-LIST_HEAD(microcode_cache);
+bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
+module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
/*
* Synchronization.
@@ -76,6 +75,8 @@ static u32 final_levels[] = {
0, /* T-101 terminator */
};
+struct early_load_data early_data;
+
/*
* Check the current patch level on this CPU.
*
@@ -90,10 +91,7 @@ static bool amd_check_current_patch_level(void)
native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
- if (IS_ENABLED(CONFIG_X86_32))
- levels = (u32 *)__pa_nodebug(&final_levels);
- else
- levels = final_levels;
+ levels = final_levels;
for (i = 0; levels[i]; i++) {
if (lvl == levels[i])
@@ -105,17 +103,8 @@ static bool amd_check_current_patch_level(void)
static bool __init check_loader_disabled_bsp(void)
{
static const char *__dis_opt_str = "dis_ucode_ldr";
-
-#ifdef CONFIG_X86_32
- const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
- const char *option = (const char *)__pa_nodebug(__dis_opt_str);
- bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr);
-
-#else /* CONFIG_X86_64 */
const char *cmdline = boot_command_line;
const char *option = __dis_opt_str;
- bool *res = &dis_ucode_ldr;
-#endif
/*
* CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
@@ -123,17 +112,17 @@ static bool __init check_loader_disabled_bsp(void)
* that's good enough as they don't land on the BSP path anyway.
*/
if (native_cpuid_ecx(1) & BIT(31))
- return *res;
+ return true;
if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
if (amd_check_current_patch_level())
- return *res;
+ return true;
}
if (cmdline_find_option_bool(cmdline, option) <= 0)
- *res = false;
+ dis_ucode_ldr = false;
- return *res;
+ return dis_ucode_ldr;
}
void __init load_ucode_bsp(void)
@@ -166,25 +155,16 @@ void __init load_ucode_bsp(void)
return;
if (intel)
- load_ucode_intel_bsp();
+ load_ucode_intel_bsp(&early_data);
else
- load_ucode_amd_early(cpuid_1_eax);
-}
-
-static bool check_loader_disabled_ap(void)
-{
-#ifdef CONFIG_X86_32
- return *((bool *)__pa_nodebug(&dis_ucode_ldr));
-#else
- return dis_ucode_ldr;
-#endif
+ load_ucode_amd_bsp(&early_data, cpuid_1_eax);
}
void load_ucode_ap(void)
{
unsigned int cpuid_1_eax;
- if (check_loader_disabled_ap())
+ if (dis_ucode_ldr)
return;
cpuid_1_eax = native_cpuid_eax(1);
@@ -196,103 +176,44 @@ void load_ucode_ap(void)
break;
case X86_VENDOR_AMD:
if (x86_family(cpuid_1_eax) >= 0x10)
- load_ucode_amd_early(cpuid_1_eax);
+ load_ucode_amd_ap(cpuid_1_eax);
break;
default:
break;
}
}
-static int __init save_microcode_in_initrd(void)
-{
- struct cpuinfo_x86 *c = &boot_cpu_data;
- int ret = -EINVAL;
-
- if (dis_ucode_ldr) {
- ret = 0;
- goto out;
- }
-
- switch (c->x86_vendor) {
- case X86_VENDOR_INTEL:
- if (c->x86 >= 6)
- ret = save_microcode_in_initrd_intel();
- break;
- case X86_VENDOR_AMD:
- if (c->x86 >= 0x10)
- ret = save_microcode_in_initrd_amd(cpuid_eax(1));
- break;
- default:
- break;
- }
-
-out:
- initrd_gone = true;
-
- return ret;
-}
-
-struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
+struct cpio_data __init find_microcode_in_initrd(const char *path)
{
#ifdef CONFIG_BLK_DEV_INITRD
unsigned long start = 0;
size_t size;
#ifdef CONFIG_X86_32
- struct boot_params *params;
-
- if (use_pa)
- params = (struct boot_params *)__pa_nodebug(&boot_params);
- else
- params = &boot_params;
-
- size = params->hdr.ramdisk_size;
-
- /*
- * Set start only if we have an initrd image. We cannot use initrd_start
- * because it is not set that early yet.
- */
+ size = boot_params.hdr.ramdisk_size;
+ /* Early load on BSP has a temporary mapping. */
if (size)
- start = params->hdr.ramdisk_image;
+ start = initrd_start_early;
-# else /* CONFIG_X86_64 */
+#else /* CONFIG_X86_64 */
size = (unsigned long)boot_params.ext_ramdisk_size << 32;
size |= boot_params.hdr.ramdisk_size;
if (size) {
start = (unsigned long)boot_params.ext_ramdisk_image << 32;
start |= boot_params.hdr.ramdisk_image;
-
start += PAGE_OFFSET;
}
-# endif
+#endif
/*
* Fixup the start address: after reserve_initrd() runs, initrd_start
* has the virtual address of the beginning of the initrd. It also
* possibly relocates the ramdisk. In either case, initrd_start contains
* the updated address so use that instead.
- *
- * initrd_gone is for the hotplug case where we've thrown out initrd
- * already.
*/
- if (!use_pa) {
- if (initrd_gone)
- return (struct cpio_data){ NULL, 0, "" };
- if (initrd_start)
- start = initrd_start;
- } else {
- /*
- * The picture with physical addresses is a bit different: we
- * need to get the *physical* address to which the ramdisk was
- * relocated, i.e., relocated_ramdisk (not initrd_start) and
- * since we're running from physical addresses, we need to access
- * relocated_ramdisk through its *physical* address too.
- */
- u64 *rr = (u64 *)__pa_nodebug(&relocated_ramdisk);
- if (*rr)
- start = *rr;
- }
+ if (initrd_start)
+ start = initrd_start;
return find_cpio_data(path, (void *)start, size, NULL);
#else /* !CONFIG_BLK_DEV_INITRD */
@@ -336,117 +257,298 @@ static struct platform_device *microcode_pdev;
* requirement can be relaxed in the future. Right now, this is conservative
* and good.
*/
-#define SPINUNIT 100 /* 100 nsec */
+enum sibling_ctrl {
+ /* Spinwait with timeout */
+ SCTRL_WAIT,
+ /* Invoke the microcode_apply() callback */
+ SCTRL_APPLY,
+ /* Proceed without invoking the microcode_apply() callback */
+ SCTRL_DONE,
+};
+
+struct microcode_ctrl {
+ enum sibling_ctrl ctrl;
+ enum ucode_state result;
+ unsigned int ctrl_cpu;
+ bool nmi_enabled;
+};
-static int check_online_cpus(void)
+DEFINE_STATIC_KEY_FALSE(microcode_nmi_handler_enable);
+static DEFINE_PER_CPU(struct microcode_ctrl, ucode_ctrl);
+static atomic_t late_cpus_in, offline_in_nmi;
+static unsigned int loops_per_usec;
+static cpumask_t cpu_offline_mask;
+
+static noinstr bool wait_for_cpus(atomic_t *cnt)
{
- unsigned int cpu;
+ unsigned int timeout, loops;
- /*
- * Make sure all CPUs are online. It's fine for SMT to be disabled if
- * all the primary threads are still online.
- */
- for_each_present_cpu(cpu) {
- if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) {
- pr_err("Not all CPUs online, aborting microcode update.\n");
- return -EINVAL;
+ WARN_ON_ONCE(raw_atomic_dec_return(cnt) < 0);
+
+ for (timeout = 0; timeout < USEC_PER_SEC; timeout++) {
+ if (!raw_atomic_read(cnt))
+ return true;
+
+ for (loops = 0; loops < loops_per_usec; loops++)
+ cpu_relax();
+
+ /* If invoked directly, tickle the NMI watchdog */
+ if (!microcode_ops->use_nmi && !(timeout % USEC_PER_MSEC)) {
+ instrumentation_begin();
+ touch_nmi_watchdog();
+ instrumentation_end();
}
}
-
- return 0;
+ /* Prevent the late comers from making progress and let them time out */
+ raw_atomic_inc(cnt);
+ return false;
}
-static atomic_t late_cpus_in;
-static atomic_t late_cpus_out;
-
-static int __wait_for_cpus(atomic_t *t, long long timeout)
+static noinstr bool wait_for_ctrl(void)
{
- int all_cpus = num_online_cpus();
+ unsigned int timeout, loops;
- atomic_inc(t);
-
- while (atomic_read(t) < all_cpus) {
- if (timeout < SPINUNIT) {
- pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
- all_cpus - atomic_read(t));
- return 1;
- }
+ for (timeout = 0; timeout < USEC_PER_SEC; timeout++) {
+ if (raw_cpu_read(ucode_ctrl.ctrl) != SCTRL_WAIT)
+ return true;
- ndelay(SPINUNIT);
- timeout -= SPINUNIT;
+ for (loops = 0; loops < loops_per_usec; loops++)
+ cpu_relax();
- touch_nmi_watchdog();
+ /* If invoked directly, tickle the NMI watchdog */
+ if (!microcode_ops->use_nmi && !(timeout % USEC_PER_MSEC)) {
+ instrumentation_begin();
+ touch_nmi_watchdog();
+ instrumentation_end();
+ }
}
- return 0;
+ return false;
}
/*
- * Returns:
- * < 0 - on error
- * 0 - success (no update done or microcode was updated)
+ * Protected against instrumentation up to the point where the primary
+ * thread completed the update. See microcode_nmi_handler() for details.
*/
-static int __reload_late(void *info)
+static noinstr bool load_secondary_wait(unsigned int ctrl_cpu)
{
- int cpu = smp_processor_id();
- enum ucode_state err;
- int ret = 0;
+ /* Initial rendezvous to ensure that all CPUs have arrived */
+ if (!wait_for_cpus(&late_cpus_in)) {
+ raw_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT);
+ return false;
+ }
/*
- * Wait for all CPUs to arrive. A load will not be attempted unless all
- * CPUs show up.
- * */
- if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
- return -1;
+ * Wait for primary threads to complete. If one of them hangs due
+ * to the update, there is no way out. This is non-recoverable
+ * because the CPU might hold locks or resources and confuse the
+ * scheduler, watchdogs etc. There is no way to safely evacuate the
+ * machine.
+ */
+ if (wait_for_ctrl())
+ return true;
+
+ instrumentation_begin();
+ panic("Microcode load: Primary CPU %d timed out\n", ctrl_cpu);
+ instrumentation_end();
+}
+
+/*
+ * Protected against instrumentation up to the point where the primary
+ * thread completed the update. See microcode_nmi_handler() for details.
+ */
+static noinstr void load_secondary(unsigned int cpu)
+{
+ unsigned int ctrl_cpu = raw_cpu_read(ucode_ctrl.ctrl_cpu);
+ enum ucode_state ret;
+
+ if (!load_secondary_wait(ctrl_cpu)) {
+ instrumentation_begin();
+ pr_err_once("load: %d CPUs timed out\n",
+ atomic_read(&late_cpus_in) - 1);
+ instrumentation_end();
+ return;
+ }
+ /* Primary thread completed. Allow to invoke instrumentable code */
+ instrumentation_begin();
/*
- * On an SMT system, it suffices to load the microcode on one sibling of
- * the core because the microcode engine is shared between the threads.
- * Synchronization still needs to take place so that no concurrent
- * loading attempts happen on multiple threads of an SMT core. See
- * below.
+ * If the primary succeeded then invoke the apply() callback,
+ * otherwise copy the state from the primary thread.
*/
- if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu)
- err = microcode_ops->apply_microcode(cpu);
+ if (this_cpu_read(ucode_ctrl.ctrl) == SCTRL_APPLY)
+ ret = microcode_ops->apply_microcode(cpu);
else
- goto wait_for_siblings;
+ ret = per_cpu(ucode_ctrl.result, ctrl_cpu);
- if (err >= UCODE_NFOUND) {
- if (err == UCODE_ERROR) {
- pr_warn("Error reloading microcode on CPU %d\n", cpu);
- ret = -1;
- }
+ this_cpu_write(ucode_ctrl.result, ret);
+ this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE);
+ instrumentation_end();
+}
+
+static void __load_primary(unsigned int cpu)
+{
+ struct cpumask *secondaries = topology_sibling_cpumask(cpu);
+ enum sibling_ctrl ctrl;
+ enum ucode_state ret;
+ unsigned int sibling;
+
+ /* Initial rendezvous to ensure that all CPUs have arrived */
+ if (!wait_for_cpus(&late_cpus_in)) {
+ this_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT);
+ pr_err_once("load: %d CPUs timed out\n", atomic_read(&late_cpus_in) - 1);
+ return;
}
-wait_for_siblings:
- if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC))
- panic("Timeout during microcode update!\n");
+ ret = microcode_ops->apply_microcode(cpu);
+ this_cpu_write(ucode_ctrl.result, ret);
+ this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE);
/*
- * At least one thread has completed update on each core.
- * For others, simply call the update to make sure the
- * per-cpu cpuinfo can be updated with right microcode
- * revision.
+ * If the update was successful, let the siblings run the apply()
+ * callback. If not, tell them it's done. This also covers the
+ * case where the CPU has uniform loading at package or system
+ * scope implemented but does not advertise it.
*/
- if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu)
- err = microcode_ops->apply_microcode(cpu);
+ if (ret == UCODE_UPDATED || ret == UCODE_OK)
+ ctrl = SCTRL_APPLY;
+ else
+ ctrl = SCTRL_DONE;
+
+ for_each_cpu(sibling, secondaries) {
+ if (sibling != cpu)
+ per_cpu(ucode_ctrl.ctrl, sibling) = ctrl;
+ }
+}
+
+static bool kick_offline_cpus(unsigned int nr_offl)
+{
+ unsigned int cpu, timeout;
+
+ for_each_cpu(cpu, &cpu_offline_mask) {
+ /* Enable the rendezvous handler and send NMI */
+ per_cpu(ucode_ctrl.nmi_enabled, cpu) = true;
+ apic_send_nmi_to_offline_cpu(cpu);
+ }
+
+ /* Wait for them to arrive */
+ for (timeout = 0; timeout < (USEC_PER_SEC / 2); timeout++) {
+ if (atomic_read(&offline_in_nmi) == nr_offl)
+ return true;
+ udelay(1);
+ }
+ /* Let the others time out */
+ return false;
+}
+
+static void release_offline_cpus(void)
+{
+ unsigned int cpu;
+
+ for_each_cpu(cpu, &cpu_offline_mask)
+ per_cpu(ucode_ctrl.ctrl, cpu) = SCTRL_DONE;
+}
+
+static void load_primary(unsigned int cpu)
+{
+ unsigned int nr_offl = cpumask_weight(&cpu_offline_mask);
+ bool proceed = true;
+
+ /* Kick soft-offlined SMT siblings if required */
+ if (!cpu && nr_offl)
+ proceed = kick_offline_cpus(nr_offl);
- return ret;
+ /* If the soft-offlined CPUs did not respond, abort */
+ if (proceed)
+ __load_primary(cpu);
+
+ /* Unconditionally release soft-offlined SMT siblings if required */
+ if (!cpu && nr_offl)
+ release_offline_cpus();
}
/*
- * Reload microcode late on all CPUs. Wait for a sec until they
- * all gather together.
+ * Minimal stub rendezvous handler for soft-offlined CPUs which participate
+ * in the NMI rendezvous to protect against a concurrent NMI on affected
+ * CPUs.
*/
-static int microcode_reload_late(void)
+void noinstr microcode_offline_nmi_handler(void)
{
- int old = boot_cpu_data.microcode, ret;
+ if (!raw_cpu_read(ucode_ctrl.nmi_enabled))
+ return;
+ raw_cpu_write(ucode_ctrl.nmi_enabled, false);
+ raw_cpu_write(ucode_ctrl.result, UCODE_OFFLINE);
+ raw_atomic_inc(&offline_in_nmi);
+ wait_for_ctrl();
+}
+
+static noinstr bool microcode_update_handler(void)
+{
+ unsigned int cpu = raw_smp_processor_id();
+
+ if (raw_cpu_read(ucode_ctrl.ctrl_cpu) == cpu) {
+ instrumentation_begin();
+ load_primary(cpu);
+ instrumentation_end();
+ } else {
+ load_secondary(cpu);
+ }
+
+ instrumentation_begin();
+ touch_nmi_watchdog();
+ instrumentation_end();
+
+ return true;
+}
+
+/*
+ * Protection against instrumentation is required for CPUs which are not
+ * safe against an NMI which is delivered to the secondary SMT sibling
+ * while the primary thread updates the microcode. Instrumentation can end
+ * up in #INT3, #DB and #PF. The IRET from those exceptions reenables NMI
+ * which is the opposite of what the NMI rendezvous is trying to achieve.
+ *
+ * The primary thread is safe versus instrumentation as the actual
+ * microcode update handles this correctly. It's only the sibling code
+ * path which must be NMI safe until the primary thread completed the
+ * update.
+ */
+bool noinstr microcode_nmi_handler(void)
+{
+ if (!raw_cpu_read(ucode_ctrl.nmi_enabled))
+ return false;
+
+ raw_cpu_write(ucode_ctrl.nmi_enabled, false);
+ return microcode_update_handler();
+}
+
+static int load_cpus_stopped(void *unused)
+{
+ if (microcode_ops->use_nmi) {
+ /* Enable the NMI handler and raise NMI */
+ this_cpu_write(ucode_ctrl.nmi_enabled, true);
+ apic->send_IPI(smp_processor_id(), NMI_VECTOR);
+ } else {
+ /* Just invoke the handler directly */
+ microcode_update_handler();
+ }
+ return 0;
+}
+
+static int load_late_stop_cpus(bool is_safe)
+{
+ unsigned int cpu, updated = 0, failed = 0, timedout = 0, siblings = 0;
+ unsigned int nr_offl, offline = 0;
+ int old_rev = boot_cpu_data.microcode;
struct cpuinfo_x86 prev_info;
- pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
- pr_err("You should switch to early loading, if possible.\n");
+ if (!is_safe) {
+ pr_err("Late microcode loading without minimal revision check.\n");
+ pr_err("You should switch to early loading, if possible.\n");
+ }
- atomic_set(&late_cpus_in, 0);
- atomic_set(&late_cpus_out, 0);
+ atomic_set(&late_cpus_in, num_online_cpus());
+ atomic_set(&offline_in_nmi, 0);
+ loops_per_usec = loops_per_jiffy / (TICK_NSEC / 1000);
/*
* Take a snapshot before the microcode update in order to compare and
@@ -454,52 +556,162 @@ static int microcode_reload_late(void)
*/
store_cpu_caps(&prev_info);
- ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
- if (!ret) {
- pr_info("Reload succeeded, microcode revision: 0x%x -> 0x%x\n",
- old, boot_cpu_data.microcode);
- microcode_check(&prev_info);
- } else {
- pr_info("Reload failed, current microcode revision: 0x%x\n",
- boot_cpu_data.microcode);
+ if (microcode_ops->use_nmi)
+ static_branch_enable_cpuslocked(&microcode_nmi_handler_enable);
+
+ stop_machine_cpuslocked(load_cpus_stopped, NULL, cpu_online_mask);
+
+ if (microcode_ops->use_nmi)
+ static_branch_disable_cpuslocked(&microcode_nmi_handler_enable);
+
+ /* Analyze the results */
+ for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) {
+ switch (per_cpu(ucode_ctrl.result, cpu)) {
+ case UCODE_UPDATED: updated++; break;
+ case UCODE_TIMEOUT: timedout++; break;
+ case UCODE_OK: siblings++; break;
+ case UCODE_OFFLINE: offline++; break;
+ default: failed++; break;
+ }
+ }
+
+ if (microcode_ops->finalize_late_load)
+ microcode_ops->finalize_late_load(!updated);
+
+ if (!updated) {
+ /* Nothing changed. */
+ if (!failed && !timedout)
+ return 0;
+
+ nr_offl = cpumask_weight(&cpu_offline_mask);
+ if (offline < nr_offl) {
+ pr_warn("%u offline siblings did not respond.\n",
+ nr_offl - atomic_read(&offline_in_nmi));
+ return -EIO;
+ }
+ pr_err("update failed: %u CPUs failed %u CPUs timed out\n",
+ failed, timedout);
+ return -EIO;
+ }
+
+ if (!is_safe || failed || timedout)
+ add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+
+ pr_info("load: updated on %u primary CPUs with %u siblings\n", updated, siblings);
+ if (failed || timedout) {
+ pr_err("load incomplete. %u CPUs timed out or failed\n",
+ num_online_cpus() - (updated + siblings));
+ }
+ pr_info("revision: 0x%x -> 0x%x\n", old_rev, boot_cpu_data.microcode);
+ microcode_check(&prev_info);
+
+ return updated + siblings == num_online_cpus() ? 0 : -EIO;
+}
+
+/*
+ * This function does two things:
+ *
+ * 1) Ensure that all required CPUs which are present and have been booted
+ * once are online.
+ *
+ * To pass this check, all primary threads must be online.
+ *
+ * If the microcode load is not safe against NMI then all SMT threads
+ * must be online as well because they still react to NMIs when they are
+ * soft-offlined and parked in one of the play_dead() variants. So if a
+ * NMI hits while the primary thread updates the microcode the resulting
+ * behaviour is undefined. The default play_dead() implementation on
+ * modern CPUs uses MWAIT, which is also not guaranteed to be safe
+ * against a microcode update which affects MWAIT.
+ *
+ * As soft-offlined CPUs still react on NMIs, the SMT sibling
+ * restriction can be lifted when the vendor driver signals to use NMI
+ * for rendezvous and the APIC provides a mechanism to send an NMI to a
+ * soft-offlined CPU. The soft-offlined CPUs are then able to
+ * participate in the rendezvous in a trivial stub handler.
+ *
+ * 2) Initialize the per CPU control structure and create a cpumask
+ * which contains "offline"; secondary threads, so they can be handled
+ * correctly by a control CPU.
+ */
+static bool setup_cpus(void)
+{
+ struct microcode_ctrl ctrl = { .ctrl = SCTRL_WAIT, .result = -1, };
+ bool allow_smt_offline;
+ unsigned int cpu;
+
+ allow_smt_offline = microcode_ops->nmi_safe ||
+ (microcode_ops->use_nmi && apic->nmi_to_offline_cpu);
+
+ cpumask_clear(&cpu_offline_mask);
+
+ for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) {
+ /*
+ * Offline CPUs sit in one of the play_dead() functions
+ * with interrupts disabled, but they still react on NMIs
+ * and execute arbitrary code. Also MWAIT being updated
+ * while the offline CPU sits there is not necessarily safe
+ * on all CPU variants.
+ *
+ * Mark them in the offline_cpus mask which will be handled
+ * by CPU0 later in the update process.
+ *
+ * Ensure that the primary thread is online so that it is
+ * guaranteed that all cores are updated.
+ */
+ if (!cpu_online(cpu)) {
+ if (topology_is_primary_thread(cpu) || !allow_smt_offline) {
+ pr_err("CPU %u not online, loading aborted\n", cpu);
+ return false;
+ }
+ cpumask_set_cpu(cpu, &cpu_offline_mask);
+ per_cpu(ucode_ctrl, cpu) = ctrl;
+ continue;
+ }
+
+ /*
+ * Initialize the per CPU state. This is core scope for now,
+ * but prepared to take package or system scope into account.
+ */
+ ctrl.ctrl_cpu = cpumask_first(topology_sibling_cpumask(cpu));
+ per_cpu(ucode_ctrl, cpu) = ctrl;
}
+ return true;
+}
- return ret;
+static int load_late_locked(void)
+{
+ if (!setup_cpus())
+ return -EBUSY;
+
+ switch (microcode_ops->request_microcode_fw(0, &microcode_pdev->dev)) {
+ case UCODE_NEW:
+ return load_late_stop_cpus(false);
+ case UCODE_NEW_SAFE:
+ return load_late_stop_cpus(true);
+ case UCODE_NFOUND:
+ return -ENOENT;
+ default:
+ return -EBADFD;
+ }
}
static ssize_t reload_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t size)
{
- enum ucode_state tmp_ret = UCODE_OK;
- int bsp = boot_cpu_data.cpu_index;
unsigned long val;
- ssize_t ret = 0;
+ ssize_t ret;
ret = kstrtoul(buf, 0, &val);
if (ret || val != 1)
return -EINVAL;
cpus_read_lock();
-
- ret = check_online_cpus();
- if (ret)
- goto put;
-
- tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev);
- if (tmp_ret != UCODE_NEW)
- goto put;
-
- ret = microcode_reload_late();
-put:
+ ret = load_late_locked();
cpus_read_unlock();
- if (ret == 0)
- ret = size;
-
- add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
-
- return ret;
+ return ret ? : size;
}
static DEVICE_ATTR_WO(reload);
@@ -541,17 +753,6 @@ static void microcode_fini_cpu(int cpu)
microcode_ops->microcode_fini_cpu(cpu);
}
-static enum ucode_state microcode_init_cpu(int cpu)
-{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
- memset(uci, 0, sizeof(*uci));
-
- microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig);
-
- return microcode_ops->apply_microcode(cpu);
-}
-
/**
* microcode_bsp_resume - Update boot CPU microcode during resume.
*/
@@ -570,19 +771,18 @@ static struct syscore_ops mc_syscore_ops = {
.resume = microcode_bsp_resume,
};
-static int mc_cpu_starting(unsigned int cpu)
-{
- enum ucode_state err = microcode_ops->apply_microcode(cpu);
-
- pr_debug("%s: CPU%d, err: %d\n", __func__, cpu, err);
-
- return err == UCODE_ERROR;
-}
-
static int mc_cpu_online(unsigned int cpu)
{
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
struct device *dev = get_cpu_device(cpu);
+ memset(uci, 0, sizeof(*uci));
+
+ microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig);
+ cpu_data(cpu).microcode = uci->cpu_sig.rev;
+ if (!cpu)
+ boot_cpu_data.microcode = uci->cpu_sig.rev;
+
if (sysfs_create_group(&dev->kobj, &mc_attr_group))
pr_err("Failed to create group for CPU%d\n", cpu);
return 0;
@@ -590,33 +790,13 @@ static int mc_cpu_online(unsigned int cpu)
static int mc_cpu_down_prep(unsigned int cpu)
{
- struct device *dev;
-
- dev = get_cpu_device(cpu);
+ struct device *dev = get_cpu_device(cpu);
microcode_fini_cpu(cpu);
-
- /* Suspend is in progress, only remove the interface */
sysfs_remove_group(&dev->kobj, &mc_attr_group);
- pr_debug("%s: CPU%d\n", __func__, cpu);
-
return 0;
}
-static void setup_online_cpu(struct work_struct *work)
-{
- int cpu = smp_processor_id();
- enum ucode_state err;
-
- err = microcode_init_cpu(cpu);
- if (err == UCODE_ERROR) {
- pr_err("Error applying microcode on CPU%d\n", cpu);
- return;
- }
-
- mc_cpu_online(cpu);
-}
-
static struct attribute *cpu_root_microcode_attrs[] = {
#ifdef CONFIG_MICROCODE_LATE_LOADING
&dev_attr_reload.attr,
@@ -648,6 +828,11 @@ static int __init microcode_init(void)
if (!microcode_ops)
return -ENODEV;
+ pr_info_once("Current revision: 0x%08x\n", (early_data.new_rev ?: early_data.old_rev));
+
+ if (early_data.new_rev)
+ pr_info_once("Updated early from: 0x%08x\n", early_data.old_rev);
+
microcode_pdev = platform_device_register_simple("microcode", -1, NULL, 0);
if (IS_ERR(microcode_pdev))
return PTR_ERR(microcode_pdev);
@@ -662,16 +847,9 @@ static int __init microcode_init(void)
}
}
- /* Do per-CPU setup */
- schedule_on_each_cpu(setup_online_cpu);
-
register_syscore_ops(&mc_syscore_ops);
- cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting",
- mc_cpu_starting, NULL);
- cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
- mc_cpu_online, mc_cpu_down_prep);
-
- pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION);
+ cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
+ mc_cpu_online, mc_cpu_down_prep);
return 0;
@@ -680,5 +858,4 @@ static int __init microcode_init(void)
return error;
}
-fs_initcall(save_microcode_in_initrd);
late_initcall(microcode_init);
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 94dd6af9c9..334972c097 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -14,7 +14,6 @@
#include <linux/earlycpio.h>
#include <linux/firmware.h>
#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
#include <linux/initrd.h>
#include <linux/kernel.h>
#include <linux/slab.h>
@@ -32,11 +31,14 @@
static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
+#define UCODE_BSP_LOADED ((struct microcode_intel *)0x1UL)
+
/* Current microcode patch used in early patching on the APs. */
-static struct microcode_intel *intel_ucode_patch;
+static struct microcode_intel *ucode_patch_va __read_mostly;
+static struct microcode_intel *ucode_patch_late __read_mostly;
/* last level cache size per core */
-static int llc_size_per_core;
+static unsigned int llc_size_per_core __ro_after_init;
/* microcode format is extended from prescott processors */
struct extended_signature {
@@ -66,60 +68,52 @@ static inline unsigned int exttable_size(struct extended_sigtable *et)
return et->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE;
}
-int intel_cpu_collect_info(struct ucode_cpu_info *uci)
+void intel_collect_cpu_info(struct cpu_signature *sig)
{
- unsigned int val[2];
- unsigned int family, model;
- struct cpu_signature csig = { 0 };
- unsigned int eax, ebx, ecx, edx;
-
- memset(uci, 0, sizeof(*uci));
-
- eax = 0x00000001;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
- csig.sig = eax;
+ sig->sig = cpuid_eax(1);
+ sig->pf = 0;
+ sig->rev = intel_get_microcode_revision();
- family = x86_family(eax);
- model = x86_model(eax);
+ if (x86_model(sig->sig) >= 5 || x86_family(sig->sig) > 6) {
+ unsigned int val[2];
- if (model >= 5 || family > 6) {
/* get processor flags from MSR 0x17 */
native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
- csig.pf = 1 << ((val[1] >> 18) & 7);
+ sig->pf = 1 << ((val[1] >> 18) & 7);
}
+}
+EXPORT_SYMBOL_GPL(intel_collect_cpu_info);
- csig.rev = intel_get_microcode_revision();
-
- uci->cpu_sig = csig;
+static inline bool cpu_signatures_match(struct cpu_signature *s1, unsigned int sig2,
+ unsigned int pf2)
+{
+ if (s1->sig != sig2)
+ return false;
- return 0;
+ /* Processor flags are either both 0 or they intersect. */
+ return ((!s1->pf && !pf2) || (s1->pf & pf2));
}
-EXPORT_SYMBOL_GPL(intel_cpu_collect_info);
-/*
- * Returns 1 if update has been found, 0 otherwise.
- */
-int intel_find_matching_signature(void *mc, unsigned int csig, int cpf)
+bool intel_find_matching_signature(void *mc, struct cpu_signature *sig)
{
struct microcode_header_intel *mc_hdr = mc;
- struct extended_sigtable *ext_hdr;
struct extended_signature *ext_sig;
+ struct extended_sigtable *ext_hdr;
int i;
- if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
- return 1;
+ if (cpu_signatures_match(sig, mc_hdr->sig, mc_hdr->pf))
+ return true;
/* Look for ext. headers: */
if (get_totalsize(mc_hdr) <= intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE)
- return 0;
+ return false;
ext_hdr = mc + intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE;
ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
for (i = 0; i < ext_hdr->count; i++) {
- if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
- return 1;
+ if (cpu_signatures_match(sig, ext_sig->sig, ext_sig->pf))
+ return true;
ext_sig++;
}
return 0;
@@ -240,264 +234,91 @@ int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type)
}
EXPORT_SYMBOL_GPL(intel_microcode_sanity_check);
-/*
- * Returns 1 if update has been found, 0 otherwise.
- */
-static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
-{
- struct microcode_header_intel *mc_hdr = mc;
-
- if (mc_hdr->rev <= new_rev)
- return 0;
-
- return intel_find_matching_signature(mc, csig, cpf);
-}
-
-static struct ucode_patch *memdup_patch(void *data, unsigned int size)
-{
- struct ucode_patch *p;
-
- p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL);
- if (!p)
- return NULL;
-
- p->data = kmemdup(data, size, GFP_KERNEL);
- if (!p->data) {
- kfree(p);
- return NULL;
- }
-
- return p;
-}
-
-static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size)
+static void update_ucode_pointer(struct microcode_intel *mc)
{
- struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
- struct ucode_patch *iter, *tmp, *p = NULL;
- bool prev_found = false;
- unsigned int sig, pf;
-
- mc_hdr = (struct microcode_header_intel *)data;
-
- list_for_each_entry_safe(iter, tmp, &microcode_cache, plist) {
- mc_saved_hdr = (struct microcode_header_intel *)iter->data;
- sig = mc_saved_hdr->sig;
- pf = mc_saved_hdr->pf;
-
- if (intel_find_matching_signature(data, sig, pf)) {
- prev_found = true;
-
- if (mc_hdr->rev <= mc_saved_hdr->rev)
- continue;
-
- p = memdup_patch(data, size);
- if (!p)
- pr_err("Error allocating buffer %p\n", data);
- else {
- list_replace(&iter->plist, &p->plist);
- kfree(iter->data);
- kfree(iter);
- }
- }
- }
+ kvfree(ucode_patch_va);
/*
- * There weren't any previous patches found in the list cache; save the
- * newly found.
+ * Save the virtual address for early loading and for eventual free
+ * on late loading.
*/
- if (!prev_found) {
- p = memdup_patch(data, size);
- if (!p)
- pr_err("Error allocating buffer for %p\n", data);
- else
- list_add_tail(&p->plist, &microcode_cache);
- }
-
- if (!p)
- return;
+ ucode_patch_va = mc;
+}
- if (!intel_find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf))
- return;
+static void save_microcode_patch(struct microcode_intel *patch)
+{
+ unsigned int size = get_totalsize(&patch->hdr);
+ struct microcode_intel *mc;
- /*
- * Save for early loading. On 32-bit, that needs to be a physical
- * address as the APs are running from physical addresses, before
- * paging has been enabled.
- */
- if (IS_ENABLED(CONFIG_X86_32))
- intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data);
+ mc = kvmemdup(patch, size, GFP_KERNEL);
+ if (mc)
+ update_ucode_pointer(mc);
else
- intel_ucode_patch = p->data;
+ pr_err("Unable to allocate microcode memory size: %u\n", size);
}
-/*
- * Get microcode matching with BSP's model. Only CPUs with the same model as
- * BSP can stay in the platform.
- */
-static struct microcode_intel *
-scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save)
+/* Scan blob for microcode matching the boot CPUs family, model, stepping */
+static __init struct microcode_intel *scan_microcode(void *data, size_t size,
+ struct ucode_cpu_info *uci,
+ bool save)
{
struct microcode_header_intel *mc_header;
struct microcode_intel *patch = NULL;
+ u32 cur_rev = uci->cpu_sig.rev;
unsigned int mc_size;
- while (size) {
- if (size < sizeof(struct microcode_header_intel))
- break;
-
+ for (; size >= sizeof(struct microcode_header_intel); size -= mc_size, data += mc_size) {
mc_header = (struct microcode_header_intel *)data;
mc_size = get_totalsize(mc_header);
- if (!mc_size ||
- mc_size > size ||
+ if (!mc_size || mc_size > size ||
intel_microcode_sanity_check(data, false, MC_HEADER_TYPE_MICROCODE) < 0)
break;
- size -= mc_size;
-
- if (!intel_find_matching_signature(data, uci->cpu_sig.sig,
- uci->cpu_sig.pf)) {
- data += mc_size;
+ if (!intel_find_matching_signature(data, &uci->cpu_sig))
continue;
- }
+ /*
+ * For saving the early microcode, find the matching revision which
+ * was loaded on the BSP.
+ *
+ * On the BSP during early boot, find a newer revision than
+ * actually loaded in the CPU.
+ */
if (save) {
- save_microcode_patch(uci, data, mc_size);
- goto next;
- }
-
-
- if (!patch) {
- if (!has_newer_microcode(data,
- uci->cpu_sig.sig,
- uci->cpu_sig.pf,
- uci->cpu_sig.rev))
- goto next;
-
- } else {
- struct microcode_header_intel *phdr = &patch->hdr;
-
- if (!has_newer_microcode(data,
- phdr->sig,
- phdr->pf,
- phdr->rev))
- goto next;
+ if (cur_rev != mc_header->rev)
+ continue;
+ } else if (cur_rev >= mc_header->rev) {
+ continue;
}
- /* We have a newer patch, save it. */
patch = data;
-
-next:
- data += mc_size;
- }
-
- if (size)
- return NULL;
-
- return patch;
-}
-
-static bool load_builtin_intel_microcode(struct cpio_data *cp)
-{
- unsigned int eax = 1, ebx, ecx = 0, edx;
- struct firmware fw;
- char name[30];
-
- if (IS_ENABLED(CONFIG_X86_32))
- return false;
-
- native_cpuid(&eax, &ebx, &ecx, &edx);
-
- sprintf(name, "intel-ucode/%02x-%02x-%02x",
- x86_family(eax), x86_model(eax), x86_stepping(eax));
-
- if (firmware_request_builtin(&fw, name)) {
- cp->size = fw.size;
- cp->data = (void *)fw.data;
- return true;
+ cur_rev = mc_header->rev;
}
- return false;
+ return size ? NULL : patch;
}
-static void print_ucode_info(int old_rev, int new_rev, unsigned int date)
+static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci,
+ struct microcode_intel *mc,
+ u32 *cur_rev)
{
- pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n",
- old_rev,
- new_rev,
- date & 0xffff,
- date >> 24,
- (date >> 16) & 0xff);
-}
-
-#ifdef CONFIG_X86_32
-
-static int delay_ucode_info;
-static int current_mc_date;
-static int early_old_rev;
-
-/*
- * Print early updated ucode info after printk works. This is delayed info dump.
- */
-void show_ucode_info_early(void)
-{
- struct ucode_cpu_info uci;
-
- if (delay_ucode_info) {
- intel_cpu_collect_info(&uci);
- print_ucode_info(early_old_rev, uci.cpu_sig.rev, current_mc_date);
- delay_ucode_info = 0;
- }
-}
-
-/*
- * At this point, we can not call printk() yet. Delay printing microcode info in
- * show_ucode_info_early() until printk() works.
- */
-static void print_ucode(int old_rev, int new_rev, int date)
-{
- int *delay_ucode_info_p;
- int *current_mc_date_p;
- int *early_old_rev_p;
-
- delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
- current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
- early_old_rev_p = (int *)__pa_nodebug(&early_old_rev);
-
- *delay_ucode_info_p = 1;
- *current_mc_date_p = date;
- *early_old_rev_p = old_rev;
-}
-#else
-
-static inline void print_ucode(int old_rev, int new_rev, int date)
-{
- print_ucode_info(old_rev, new_rev, date);
-}
-#endif
-
-static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
-{
- struct microcode_intel *mc;
- u32 rev, old_rev;
+ u32 rev;
- mc = uci->mc;
if (!mc)
- return 0;
+ return UCODE_NFOUND;
/*
* Save us the MSR write below - which is a particular expensive
* operation - when the other hyperthread has updated the microcode
* already.
*/
- rev = intel_get_microcode_revision();
- if (rev >= mc->hdr.rev) {
- uci->cpu_sig.rev = rev;
+ *cur_rev = intel_get_microcode_revision();
+ if (*cur_rev >= mc->hdr.rev) {
+ uci->cpu_sig.rev = *cur_rev;
return UCODE_OK;
}
- old_rev = rev;
-
/*
* Writeback and invalidate caches before updating microcode to avoid
* internal issues depending on what the microcode is updating.
@@ -509,247 +330,179 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
rev = intel_get_microcode_revision();
if (rev != mc->hdr.rev)
- return -1;
+ return UCODE_ERROR;
uci->cpu_sig.rev = rev;
+ return UCODE_UPDATED;
+}
- if (early)
- print_ucode(old_rev, uci->cpu_sig.rev, mc->hdr.date);
- else
- print_ucode_info(old_rev, uci->cpu_sig.rev, mc->hdr.date);
+static enum ucode_state apply_microcode_early(struct ucode_cpu_info *uci)
+{
+ struct microcode_intel *mc = uci->mc;
+ u32 cur_rev;
- return 0;
+ return __apply_microcode(uci, mc, &cur_rev);
}
-int __init save_microcode_in_initrd_intel(void)
+static __init bool load_builtin_intel_microcode(struct cpio_data *cp)
{
- struct ucode_cpu_info uci;
- struct cpio_data cp;
-
- /*
- * initrd is going away, clear patch ptr. We will scan the microcode one
- * last time before jettisoning and save a patch, if found. Then we will
- * update that pointer too, with a stable patch address to use when
- * resuming the cores.
- */
- intel_ucode_patch = NULL;
+ unsigned int eax = 1, ebx, ecx = 0, edx;
+ struct firmware fw;
+ char name[30];
- if (!load_builtin_intel_microcode(&cp))
- cp = find_microcode_in_initrd(ucode_path, false);
+ if (IS_ENABLED(CONFIG_X86_32))
+ return false;
- if (!(cp.data && cp.size))
- return 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
- intel_cpu_collect_info(&uci);
+ sprintf(name, "intel-ucode/%02x-%02x-%02x",
+ x86_family(eax), x86_model(eax), x86_stepping(eax));
- scan_microcode(cp.data, cp.size, &uci, true);
- return 0;
+ if (firmware_request_builtin(&fw, name)) {
+ cp->size = fw.size;
+ cp->data = (void *)fw.data;
+ return true;
+ }
+ return false;
}
-/*
- * @res_patch, output: a pointer to the patch we found.
- */
-static struct microcode_intel *__load_ucode_intel(struct ucode_cpu_info *uci)
+static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info *uci, bool save)
{
- static const char *path;
struct cpio_data cp;
- bool use_pa;
-
- if (IS_ENABLED(CONFIG_X86_32)) {
- path = (const char *)__pa_nodebug(ucode_path);
- use_pa = true;
- } else {
- path = ucode_path;
- use_pa = false;
- }
- /* try built-in microcode first */
+ intel_collect_cpu_info(&uci->cpu_sig);
+
if (!load_builtin_intel_microcode(&cp))
- cp = find_microcode_in_initrd(path, use_pa);
+ cp = find_microcode_in_initrd(ucode_path);
if (!(cp.data && cp.size))
return NULL;
- intel_cpu_collect_info(uci);
-
- return scan_microcode(cp.data, cp.size, uci, false);
+ return scan_microcode(cp.data, cp.size, uci, save);
}
-void __init load_ucode_intel_bsp(void)
+/*
+ * Invoked from an early init call to save the microcode blob which was
+ * selected during early boot when mm was not usable. The microcode must be
+ * saved because initrd is going away. It's an early init call so the APs
+ * just can use the pointer and do not have to scan initrd/builtin firmware
+ * again.
+ */
+static int __init save_builtin_microcode(void)
{
- struct microcode_intel *patch;
struct ucode_cpu_info uci;
- patch = __load_ucode_intel(&uci);
- if (!patch)
- return;
+ if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
+ return 0;
- uci.mc = patch;
+ if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return 0;
- apply_microcode_early(&uci, true);
+ uci.mc = get_microcode_blob(&uci, true);
+ if (uci.mc)
+ save_microcode_patch(uci.mc);
+ return 0;
}
+early_initcall(save_builtin_microcode);
-void load_ucode_intel_ap(void)
+/* Load microcode on BSP from initrd or builtin blobs */
+void __init load_ucode_intel_bsp(struct early_load_data *ed)
{
- struct microcode_intel *patch, **iup;
struct ucode_cpu_info uci;
- if (IS_ENABLED(CONFIG_X86_32))
- iup = (struct microcode_intel **) __pa_nodebug(&intel_ucode_patch);
- else
- iup = &intel_ucode_patch;
-
- if (!*iup) {
- patch = __load_ucode_intel(&uci);
- if (!patch)
- return;
+ uci.mc = get_microcode_blob(&uci, false);
+ ed->old_rev = uci.cpu_sig.rev;
- *iup = patch;
+ if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) {
+ ucode_patch_va = UCODE_BSP_LOADED;
+ ed->new_rev = uci.cpu_sig.rev;
}
-
- uci.mc = *iup;
-
- apply_microcode_early(&uci, true);
}
-static struct microcode_intel *find_patch(struct ucode_cpu_info *uci)
+void load_ucode_intel_ap(void)
{
- struct microcode_header_intel *phdr;
- struct ucode_patch *iter, *tmp;
-
- list_for_each_entry_safe(iter, tmp, &microcode_cache, plist) {
-
- phdr = (struct microcode_header_intel *)iter->data;
-
- if (phdr->rev <= uci->cpu_sig.rev)
- continue;
-
- if (!intel_find_matching_signature(phdr,
- uci->cpu_sig.sig,
- uci->cpu_sig.pf))
- continue;
+ struct ucode_cpu_info uci;
- return iter->data;
- }
- return NULL;
+ uci.mc = ucode_patch_va;
+ if (uci.mc)
+ apply_microcode_early(&uci);
}
+/* Reload microcode on resume */
void reload_ucode_intel(void)
{
- struct microcode_intel *p;
- struct ucode_cpu_info uci;
+ struct ucode_cpu_info uci = { .mc = ucode_patch_va, };
- intel_cpu_collect_info(&uci);
-
- p = find_patch(&uci);
- if (!p)
- return;
-
- uci.mc = p;
-
- apply_microcode_early(&uci, false);
+ if (uci.mc)
+ apply_microcode_early(&uci);
}
static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
{
- struct cpuinfo_x86 *c = &cpu_data(cpu_num);
- unsigned int val[2];
-
- memset(csig, 0, sizeof(*csig));
-
- csig->sig = cpuid_eax(0x00000001);
-
- if ((c->x86_model >= 5) || (c->x86 > 6)) {
- /* get processor flags from MSR 0x17 */
- rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
- csig->pf = 1 << ((val[1] >> 18) & 7);
- }
-
- csig->rev = c->microcode;
-
+ intel_collect_cpu_info(csig);
return 0;
}
-static enum ucode_state apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_late(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- struct cpuinfo_x86 *c = &cpu_data(cpu);
- bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
- struct microcode_intel *mc;
+ struct microcode_intel *mc = ucode_patch_late;
enum ucode_state ret;
- static int prev_rev;
- u32 rev;
+ u32 cur_rev;
- /* We should bind the task to the CPU */
- if (WARN_ON(raw_smp_processor_id() != cpu))
+ if (WARN_ON_ONCE(smp_processor_id() != cpu))
return UCODE_ERROR;
- /* Look for a newer patch in our cache: */
- mc = find_patch(uci);
- if (!mc) {
- mc = uci->mc;
- if (!mc)
- return UCODE_NFOUND;
- }
+ ret = __apply_microcode(uci, mc, &cur_rev);
+ if (ret != UCODE_UPDATED && ret != UCODE_OK)
+ return ret;
- /*
- * Save us the MSR write below - which is a particular expensive
- * operation - when the other hyperthread has updated the microcode
- * already.
- */
- rev = intel_get_microcode_revision();
- if (rev >= mc->hdr.rev) {
- ret = UCODE_OK;
- goto out;
+ if (!cpu && uci->cpu_sig.rev != cur_rev) {
+ pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n",
+ uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24,
+ (mc->hdr.date >> 16) & 0xff);
}
- /*
- * Writeback and invalidate caches before updating microcode to avoid
- * internal issues depending on what the microcode is updating.
- */
- native_wbinvd();
+ cpu_data(cpu).microcode = uci->cpu_sig.rev;
+ if (!cpu)
+ boot_cpu_data.microcode = uci->cpu_sig.rev;
- /* write microcode via MSR 0x79 */
- wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
+ return ret;
+}
- rev = intel_get_microcode_revision();
+static bool ucode_validate_minrev(struct microcode_header_intel *mc_header)
+{
+ int cur_rev = boot_cpu_data.microcode;
- if (rev != mc->hdr.rev) {
- pr_err("CPU%d update to revision 0x%x failed\n",
- cpu, mc->hdr.rev);
- return UCODE_ERROR;
+ /*
+ * When late-loading, ensure the header declares a minimum revision
+ * required to perform a late-load. The previously reserved field
+ * is 0 in older microcode blobs.
+ */
+ if (!mc_header->min_req_ver) {
+ pr_info("Unsafe microcode update: Microcode header does not specify a required min version\n");
+ return false;
}
- if (bsp && rev != prev_rev) {
- pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
- rev,
- mc->hdr.date & 0xffff,
- mc->hdr.date >> 24,
- (mc->hdr.date >> 16) & 0xff);
- prev_rev = rev;
+ /*
+ * Check whether the current revision is either greater or equal to
+ * to the minimum revision specified in the header.
+ */
+ if (cur_rev < mc_header->min_req_ver) {
+ pr_info("Unsafe microcode update: Current revision 0x%x too old\n", cur_rev);
+ pr_info("Current should be at 0x%x or higher. Use early loading instead\n", mc_header->min_req_ver);
+ return false;
}
-
- ret = UCODE_UPDATED;
-
-out:
- uci->cpu_sig.rev = rev;
- c->microcode = rev;
-
- /* Update boot_cpu_data's revision too, if we're on the BSP: */
- if (bsp)
- boot_cpu_data.microcode = rev;
-
- return ret;
+ return true;
}
-static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
+static enum ucode_state parse_microcode_blobs(int cpu, struct iov_iter *iter)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- unsigned int curr_mc_size = 0, new_mc_size = 0;
- enum ucode_state ret = UCODE_OK;
- int new_rev = uci->cpu_sig.rev;
+ bool is_safe, new_is_safe = false;
+ int cur_rev = uci->cpu_sig.rev;
+ unsigned int curr_mc_size = 0;
u8 *new_mc = NULL, *mc = NULL;
- unsigned int csig, cpf;
while (iov_iter_count(iter)) {
struct microcode_header_intel mc_header;
@@ -758,68 +511,66 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
if (!copy_from_iter_full(&mc_header, sizeof(mc_header), iter)) {
pr_err("error! Truncated or inaccessible header in microcode data file\n");
- break;
+ goto fail;
}
mc_size = get_totalsize(&mc_header);
if (mc_size < sizeof(mc_header)) {
pr_err("error! Bad data in microcode data file (totalsize too small)\n");
- break;
+ goto fail;
}
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;
+ goto fail;
}
/* For performance reasons, reuse mc area when possible */
if (!mc || mc_size > curr_mc_size) {
- vfree(mc);
- mc = vmalloc(mc_size);
+ kvfree(mc);
+ mc = kvmalloc(mc_size, GFP_KERNEL);
if (!mc)
- break;
+ goto fail;
curr_mc_size = mc_size;
}
memcpy(mc, &mc_header, sizeof(mc_header));
data = mc + sizeof(mc_header);
if (!copy_from_iter_full(data, data_size, iter) ||
- intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0) {
- break;
- }
+ intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0)
+ goto fail;
- csig = uci->cpu_sig.sig;
- cpf = uci->cpu_sig.pf;
- if (has_newer_microcode(mc, csig, cpf, new_rev)) {
- vfree(new_mc);
- new_rev = mc_header.rev;
- new_mc = mc;
- new_mc_size = mc_size;
- mc = NULL; /* trigger new vmalloc */
- ret = UCODE_NEW;
- }
- }
+ if (cur_rev >= mc_header.rev)
+ continue;
- vfree(mc);
+ if (!intel_find_matching_signature(mc, &uci->cpu_sig))
+ continue;
- if (iov_iter_count(iter)) {
- vfree(new_mc);
- return UCODE_ERROR;
+ is_safe = ucode_validate_minrev(&mc_header);
+ if (force_minrev && !is_safe)
+ continue;
+
+ kvfree(new_mc);
+ cur_rev = mc_header.rev;
+ new_mc = mc;
+ new_is_safe = is_safe;
+ mc = NULL;
}
+ if (iov_iter_count(iter))
+ goto fail;
+
+ kvfree(mc);
if (!new_mc)
return UCODE_NFOUND;
- vfree(uci->mc);
- uci->mc = (struct microcode_intel *)new_mc;
-
- /* Save for CPU hotplug */
- save_microcode_patch(uci, new_mc, new_mc_size);
+ ucode_patch_late = (struct microcode_intel *)new_mc;
+ return new_is_safe ? UCODE_NEW_SAFE : UCODE_NEW;
- pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
- cpu, new_rev, uci->cpu_sig.rev);
-
- return ret;
+fail:
+ kvfree(mc);
+ kvfree(new_mc);
+ return UCODE_ERROR;
}
static bool is_blacklisted(unsigned int cpu)
@@ -868,26 +619,36 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
kvec.iov_base = (void *)firmware->data;
kvec.iov_len = firmware->size;
iov_iter_kvec(&iter, ITER_SOURCE, &kvec, 1, firmware->size);
- ret = generic_load_microcode(cpu, &iter);
+ ret = parse_microcode_blobs(cpu, &iter);
release_firmware(firmware);
return ret;
}
+static void finalize_late_load(int result)
+{
+ if (!result)
+ update_ucode_pointer(ucode_patch_late);
+ else
+ kvfree(ucode_patch_late);
+ ucode_patch_late = NULL;
+}
+
static struct microcode_ops microcode_intel_ops = {
- .request_microcode_fw = request_microcode_fw,
- .collect_cpu_info = collect_cpu_info,
- .apply_microcode = apply_microcode_intel,
+ .request_microcode_fw = request_microcode_fw,
+ .collect_cpu_info = collect_cpu_info,
+ .apply_microcode = apply_microcode_late,
+ .finalize_late_load = finalize_late_load,
+ .use_nmi = IS_ENABLED(CONFIG_X86_64),
};
-static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
+static __init void calc_llc_size_per_core(struct cpuinfo_x86 *c)
{
u64 llc_size = c->x86_cache_size * 1024ULL;
do_div(llc_size, c->x86_max_cores);
-
- return (int)llc_size;
+ llc_size_per_core = (unsigned int)llc_size;
}
struct microcode_ops * __init init_intel_microcode(void)
@@ -900,7 +661,7 @@ struct microcode_ops * __init init_intel_microcode(void)
return NULL;
}
- llc_size_per_core = calc_llc_size_per_core(c);
+ calc_llc_size_per_core(c);
return &microcode_intel_ops;
}
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index bf883aa712..21776c529f 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -8,43 +8,43 @@
#include <asm/cpu.h>
#include <asm/microcode.h>
-struct ucode_patch {
- struct list_head plist;
- void *data; /* Intel uses only this one */
- unsigned int size;
- u32 patch_id;
- u16 equiv_cpu;
-};
-
-extern struct list_head microcode_cache;
-
struct device;
enum ucode_state {
UCODE_OK = 0,
UCODE_NEW,
+ UCODE_NEW_SAFE,
UCODE_UPDATED,
UCODE_NFOUND,
UCODE_ERROR,
+ UCODE_TIMEOUT,
+ UCODE_OFFLINE,
};
struct microcode_ops {
enum ucode_state (*request_microcode_fw)(int cpu, struct device *dev);
-
void (*microcode_fini_cpu)(int cpu);
/*
- * The generic 'microcode_core' part guarantees that
- * the callbacks below run on a target cpu when they
- * are being called.
+ * The generic 'microcode_core' part guarantees that the callbacks
+ * below run on a target CPU when they are being called.
* See also the "Synchronization" section in microcode_core.c.
*/
- enum ucode_state (*apply_microcode)(int cpu);
- int (*collect_cpu_info)(int cpu, struct cpu_signature *csig);
+ enum ucode_state (*apply_microcode)(int cpu);
+ int (*collect_cpu_info)(int cpu, struct cpu_signature *csig);
+ void (*finalize_late_load)(int result);
+ unsigned int nmi_safe : 1,
+ use_nmi : 1;
+};
+
+struct early_load_data {
+ u32 old_rev;
+ u32 new_rev;
};
+extern struct early_load_data early_data;
extern struct ucode_cpu_info ucode_cpu_info[];
-struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa);
+struct cpio_data find_microcode_in_initrd(const char *path);
#define MAX_UCODE_COUNT 128
@@ -94,20 +94,19 @@ static inline unsigned int x86_cpuid_family(void)
return x86_family(eax);
}
-extern bool initrd_gone;
+extern bool dis_ucode_ldr;
+extern bool force_minrev;
#ifdef CONFIG_CPU_SUP_AMD
-void load_ucode_amd_bsp(unsigned int family);
+void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family);
void load_ucode_amd_ap(unsigned int family);
-void load_ucode_amd_early(unsigned int cpuid_1_eax);
int save_microcode_in_initrd_amd(unsigned int family);
void reload_ucode_amd(unsigned int cpu);
struct microcode_ops *init_amd_microcode(void);
void exit_amd_microcode(void);
#else /* CONFIG_CPU_SUP_AMD */
-static inline void load_ucode_amd_bsp(unsigned int family) { }
+static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { }
static inline void load_ucode_amd_ap(unsigned int family) { }
-static inline void load_ucode_amd_early(unsigned int family) { }
static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
static inline void reload_ucode_amd(unsigned int cpu) { }
static inline struct microcode_ops *init_amd_microcode(void) { return NULL; }
@@ -115,15 +114,13 @@ static inline void exit_amd_microcode(void) { }
#endif /* !CONFIG_CPU_SUP_AMD */
#ifdef CONFIG_CPU_SUP_INTEL
-void load_ucode_intel_bsp(void);
+void load_ucode_intel_bsp(struct early_load_data *ed);
void load_ucode_intel_ap(void);
-int save_microcode_in_initrd_intel(void);
void reload_ucode_intel(void);
struct microcode_ops *init_intel_microcode(void);
#else /* CONFIG_CPU_SUP_INTEL */
-static inline void load_ucode_intel_bsp(void) { }
+static inline void load_ucode_intel_bsp(struct early_load_data *ed) { }
static inline void load_ucode_intel_ap(void) { }
-static inline int save_microcode_in_initrd_intel(void) { return -EINVAL; }
static inline void reload_ucode_intel(void) { }
static inline struct microcode_ops *init_intel_microcode(void) { return NULL; }
#endif /* !CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e6bba12c75..01fa06dd06 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -262,11 +262,14 @@ static uint32_t __init ms_hyperv_platform(void)
static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
{
static atomic_t nmi_cpu = ATOMIC_INIT(-1);
+ unsigned int old_cpu, this_cpu;
if (!unknown_nmi_panic)
return NMI_DONE;
- if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1)
+ old_cpu = -1;
+ this_cpu = raw_smp_processor_id();
+ if (!atomic_try_cmpxchg(&nmi_cpu, &old_cpu, this_cpu))
return NMI_HANDLED;
return NMI_DONE;
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 31c0e68f62..e65fae6366 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -20,13 +20,13 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
unsigned int cpu)
{
#ifdef CONFIG_SMP
- seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
+ seq_printf(m, "physical id\t: %d\n", c->topo.pkg_id);
seq_printf(m, "siblings\t: %d\n",
cpumask_weight(topology_core_cpumask(cpu)));
- seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
+ seq_printf(m, "core id\t\t: %d\n", c->topo.core_id);
seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
- seq_printf(m, "apicid\t\t: %d\n", c->apicid);
- seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid);
+ seq_printf(m, "apicid\t\t: %d\n", c->topo.apicid);
+ seq_printf(m, "initial apicid\t: %d\n", c->topo.initial_apicid);
#endif
}
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 030d3b4097..19e0681f04 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -152,6 +152,7 @@ static inline void cache_alloc_hsw_probe(void)
r->cache.cbm_len = 20;
r->cache.shareable_bits = 0xc0000;
r->cache.min_cbm_bits = 2;
+ r->cache.arch_has_sparse_bitmasks = false;
r->alloc_capable = true;
rdt_alloc_capable = true;
@@ -267,15 +268,18 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
{
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
union cpuid_0x10_1_eax eax;
+ union cpuid_0x10_x_ecx ecx;
union cpuid_0x10_x_edx edx;
- u32 ebx, ecx;
+ u32 ebx;
- cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
+ cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full);
hw_res->num_closid = edx.split.cos_max + 1;
r->cache.cbm_len = eax.split.cbm_len + 1;
r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
r->cache.shareable_bits = ebx & r->default_ctrl;
r->data_width = (r->cache.cbm_len + 3) / 4;
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+ r->cache.arch_has_sparse_bitmasks = ecx.split.noncont;
r->alloc_capable = true;
}
@@ -872,7 +876,6 @@ static __init void rdt_init_res_defs_intel(void)
if (r->rid == RDT_RESOURCE_L3 ||
r->rid == RDT_RESOURCE_L2) {
- r->cache.arch_has_sparse_bitmaps = false;
r->cache.arch_has_per_cpu_cfg = false;
r->cache.min_cbm_bits = 1;
} else if (r->rid == RDT_RESOURCE_MBA) {
@@ -892,7 +895,7 @@ static __init void rdt_init_res_defs_amd(void)
if (r->rid == RDT_RESOURCE_L3 ||
r->rid == RDT_RESOURCE_L2) {
- r->cache.arch_has_sparse_bitmaps = true;
+ r->cache.arch_has_sparse_bitmasks = true;
r->cache.arch_has_per_cpu_cfg = true;
r->cache.min_cbm_bits = 0;
} else if (r->rid == RDT_RESOURCE_MBA) {
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index b44c487727..beccb0e87b 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -87,10 +87,12 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
/*
* Check whether a cache bit mask is valid.
- * For Intel the SDM says:
- * Please note that all (and only) contiguous '1' combinations
- * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
- * Additionally Haswell requires at least two bits set.
+ * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID:
+ * - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1
+ * - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1
+ *
+ * Haswell does not support a non-contiguous 1s value and additionally
+ * requires at least two bits set.
* AMD allows non-contiguous bitmasks.
*/
static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
@@ -113,8 +115,8 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
first_bit = find_first_bit(&val, cbm_len);
zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
- /* Are non-contiguous bitmaps allowed? */
- if (!r->cache.arch_has_sparse_bitmaps &&
+ /* Are non-contiguous bitmasks allowed? */
+ if (!r->cache.arch_has_sparse_bitmasks &&
(find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
return false;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 85ceaf9a31..a4f1aa15f0 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -59,6 +59,7 @@ struct rdt_fs_context {
bool enable_cdpl2;
bool enable_cdpl3;
bool enable_mba_mbps;
+ bool enable_debug;
};
static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
@@ -243,18 +244,17 @@ struct rdtgroup {
*/
#define RFTYPE_INFO BIT(0)
#define RFTYPE_BASE BIT(1)
-#define RF_CTRLSHIFT 4
-#define RF_MONSHIFT 5
-#define RF_TOPSHIFT 6
-#define RFTYPE_CTRL BIT(RF_CTRLSHIFT)
-#define RFTYPE_MON BIT(RF_MONSHIFT)
-#define RFTYPE_TOP BIT(RF_TOPSHIFT)
+#define RFTYPE_CTRL BIT(4)
+#define RFTYPE_MON BIT(5)
+#define RFTYPE_TOP BIT(6)
#define RFTYPE_RES_CACHE BIT(8)
#define RFTYPE_RES_MB BIT(9)
-#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL)
-#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON)
-#define RF_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP)
-#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL)
+#define RFTYPE_DEBUG BIT(10)
+#define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL)
+#define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON)
+#define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP)
+#define RFTYPE_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL)
+#define RFTYPE_MON_BASE (RFTYPE_BASE | RFTYPE_MON)
/* List of all resource groups */
extern struct list_head rdt_all_groups;
@@ -270,7 +270,7 @@ void __exit rdtgroup_exit(void);
* @mode: Access mode
* @kf_ops: File operations
* @flags: File specific RFTYPE_FLAGS_* flags
- * @fflags: File specific RF_* or RFTYPE_* flags
+ * @fflags: File specific RFTYPE_* flags
* @seq_show: Show content of the file
* @write: Write to the file
*/
@@ -492,6 +492,15 @@ union cpuid_0x10_3_eax {
unsigned int full;
};
+/* CPUID.(EAX=10H, ECX=ResID).ECX */
+union cpuid_0x10_x_ecx {
+ struct {
+ unsigned int reserved:3;
+ unsigned int noncont:1;
+ } split;
+ unsigned int full;
+};
+
/* CPUID.(EAX=10H, ECX=ResID).EDX */
union cpuid_0x10_x_edx {
struct {
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 725344048f..69a1de9238 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -54,8 +54,13 @@ static struct kernfs_node *kn_mondata;
static struct seq_buf last_cmd_status;
static char last_cmd_status_buf[512];
+static int rdtgroup_setup_root(struct rdt_fs_context *ctx);
+static void rdtgroup_destroy_root(void);
+
struct dentry *debugfs_resctrl;
+static bool resctrl_debug;
+
void rdt_last_cmd_clear(void)
{
lockdep_assert_held(&rdtgroup_mutex);
@@ -696,11 +701,10 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct rdtgroup *rdtgrp;
+ char *pid_str;
int ret = 0;
pid_t pid;
- if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
- return -EINVAL;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (!rdtgrp) {
rdtgroup_kn_unlock(of->kn);
@@ -715,7 +719,27 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
goto unlock;
}
- ret = rdtgroup_move_task(pid, rdtgrp, of);
+ while (buf && buf[0] != '\0' && buf[0] != '\n') {
+ pid_str = strim(strsep(&buf, ","));
+
+ if (kstrtoint(pid_str, 0, &pid)) {
+ rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str);
+ ret = -EINVAL;
+ break;
+ }
+
+ if (pid < 0) {
+ rdt_last_cmd_printf("Invalid pid %d\n", pid);
+ ret = -EINVAL;
+ break;
+ }
+
+ ret = rdtgroup_move_task(pid, rdtgrp, of);
+ if (ret) {
+ rdt_last_cmd_printf("Error while processing task %d\n", pid);
+ break;
+ }
+ }
unlock:
rdtgroup_kn_unlock(of->kn);
@@ -755,6 +779,38 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of,
return ret;
}
+static int rdtgroup_closid_show(struct kernfs_open_file *of,
+ struct seq_file *s, void *v)
+{
+ struct rdtgroup *rdtgrp;
+ int ret = 0;
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (rdtgrp)
+ seq_printf(s, "%u\n", rdtgrp->closid);
+ else
+ ret = -ENOENT;
+ rdtgroup_kn_unlock(of->kn);
+
+ return ret;
+}
+
+static int rdtgroup_rmid_show(struct kernfs_open_file *of,
+ struct seq_file *s, void *v)
+{
+ struct rdtgroup *rdtgrp;
+ int ret = 0;
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (rdtgrp)
+ seq_printf(s, "%u\n", rdtgrp->mon.rmid);
+ else
+ ret = -ENOENT;
+ rdtgroup_kn_unlock(of->kn);
+
+ return ret;
+}
+
#ifdef CONFIG_PROC_CPU_RESCTRL
/*
@@ -895,7 +951,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
return 0;
}
-/**
+/*
* rdt_bit_usage_show - Display current usage of resources
*
* A domain is a shared resource that can now be allocated differently. Here
@@ -1117,12 +1173,24 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
}
}
+static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
+ struct seq_file *seq, void *v)
+{
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
+
+ seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);
+
+ return 0;
+}
+
/**
* __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
* @r: Resource to which domain instance @d belongs.
* @d: The domain instance for which @closid is being tested.
* @cbm: Capacity bitmask being tested.
* @closid: Intended closid for @cbm.
+ * @type: CDP type of @r.
* @exclusive: Only check if overlaps with exclusive resource groups
*
* Checks if provided @cbm intended to be used for @closid on domain
@@ -1209,6 +1277,7 @@ bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
/**
* rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
+ * @rdtgrp: Resource group identified through its closid.
*
* An exclusive resource group implies that there should be no sharing of
* its allocated resources. At the time this group is considered to be
@@ -1251,9 +1320,8 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
return true;
}
-/**
+/*
* rdtgroup_mode_write - Modify the resource group's mode
- *
*/
static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
@@ -1357,12 +1425,11 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
return size;
}
-/**
+/*
* rdtgroup_size_show - Display size in bytes of allocated regions
*
* The "size" file mirrors the layout of the "schemata" file, printing the
* size in bytes of each region instead of the capacity bitmask.
- *
*/
static int rdtgroup_size_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
@@ -1686,77 +1753,77 @@ static struct rftype res_common_files[] = {
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_last_cmd_status_show,
- .fflags = RF_TOP_INFO,
+ .fflags = RFTYPE_TOP_INFO,
},
{
.name = "num_closids",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_num_closids_show,
- .fflags = RF_CTRL_INFO,
+ .fflags = RFTYPE_CTRL_INFO,
},
{
.name = "mon_features",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_mon_features_show,
- .fflags = RF_MON_INFO,
+ .fflags = RFTYPE_MON_INFO,
},
{
.name = "num_rmids",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_num_rmids_show,
- .fflags = RF_MON_INFO,
+ .fflags = RFTYPE_MON_INFO,
},
{
.name = "cbm_mask",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_default_ctrl_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
},
{
.name = "min_cbm_bits",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_min_cbm_bits_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
},
{
.name = "shareable_bits",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_shareable_bits_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
},
{
.name = "bit_usage",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_bit_usage_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
},
{
.name = "min_bandwidth",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_min_bw_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_MB,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
},
{
.name = "bandwidth_gran",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_bw_gran_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_MB,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
},
{
.name = "delay_linear",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_delay_linear_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_MB,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
},
/*
* Platform specific which (if any) capabilities are provided by
@@ -1775,7 +1842,7 @@ static struct rftype res_common_files[] = {
.kf_ops = &rdtgroup_kf_single_ops,
.write = max_threshold_occ_write,
.seq_show = max_threshold_occ_show,
- .fflags = RF_MON_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
},
{
.name = "mbm_total_bytes_config",
@@ -1817,12 +1884,19 @@ static struct rftype res_common_files[] = {
.fflags = RFTYPE_BASE,
},
{
+ .name = "mon_hw_id",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdtgroup_rmid_show,
+ .fflags = RFTYPE_MON_BASE | RFTYPE_DEBUG,
+ },
+ {
.name = "schemata",
.mode = 0644,
.kf_ops = &rdtgroup_kf_single_ops,
.write = rdtgroup_schemata_write,
.seq_show = rdtgroup_schemata_show,
- .fflags = RF_CTRL_BASE,
+ .fflags = RFTYPE_CTRL_BASE,
},
{
.name = "mode",
@@ -1830,14 +1904,28 @@ static struct rftype res_common_files[] = {
.kf_ops = &rdtgroup_kf_single_ops,
.write = rdtgroup_mode_write,
.seq_show = rdtgroup_mode_show,
- .fflags = RF_CTRL_BASE,
+ .fflags = RFTYPE_CTRL_BASE,
},
{
.name = "size",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdtgroup_size_show,
- .fflags = RF_CTRL_BASE,
+ .fflags = RFTYPE_CTRL_BASE,
+ },
+ {
+ .name = "sparse_masks",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdt_has_sparse_bitmasks_show,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
+ },
+ {
+ .name = "ctrl_hw_id",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdtgroup_closid_show,
+ .fflags = RFTYPE_CTRL_BASE | RFTYPE_DEBUG,
},
};
@@ -1852,6 +1940,9 @@ static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
lockdep_assert_held(&rdtgroup_mutex);
+ if (resctrl_debug)
+ fflags |= RFTYPE_DEBUG;
+
for (rft = rfts; rft < rfts + len; rft++) {
if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
ret = rdtgroup_add_file(kn, rft);
@@ -1894,7 +1985,7 @@ void __init thread_throttle_mode_init(void)
if (!rft)
return;
- rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB;
+ rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB;
}
void __init mbm_config_rftype_init(const char *config)
@@ -1903,7 +1994,7 @@ void __init mbm_config_rftype_init(const char *config)
rft = rdtgroup_get_rftype_by_name(config);
if (rft)
- rft->fflags = RF_MON_INFO | RFTYPE_RES_CACHE;
+ rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE;
}
/**
@@ -2038,21 +2129,21 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
if (IS_ERR(kn_info))
return PTR_ERR(kn_info);
- ret = rdtgroup_add_files(kn_info, RF_TOP_INFO);
+ ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO);
if (ret)
goto out_destroy;
/* loop over enabled controls, these are all alloc_capable */
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
- fflags = r->fflags | RF_CTRL_INFO;
+ fflags = r->fflags | RFTYPE_CTRL_INFO;
ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
if (ret)
goto out_destroy;
}
for_each_mon_capable_rdt_resource(r) {
- fflags = r->fflags | RF_MON_INFO;
+ fflags = r->fflags | RFTYPE_MON_INFO;
sprintf(name, "%s_MON", r->name);
ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
if (ret)
@@ -2271,14 +2362,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
return 0;
}
-static void cdp_disable_all(void)
-{
- if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
- resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
- if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
- resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
-}
-
/*
* We don't allow rdtgroup directories to be created anywhere
* except the root directory. Thus when looking for the rdtgroup
@@ -2358,19 +2441,47 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
struct rdtgroup *prgrp,
struct kernfs_node **mon_data_kn);
+static void rdt_disable_ctx(void)
+{
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
+ set_mba_sc(false);
+
+ resctrl_debug = false;
+}
+
static int rdt_enable_ctx(struct rdt_fs_context *ctx)
{
int ret = 0;
- if (ctx->enable_cdpl2)
+ if (ctx->enable_cdpl2) {
ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true);
+ if (ret)
+ goto out_done;
+ }
- if (!ret && ctx->enable_cdpl3)
+ if (ctx->enable_cdpl3) {
ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true);
+ if (ret)
+ goto out_cdpl2;
+ }
- if (!ret && ctx->enable_mba_mbps)
+ if (ctx->enable_mba_mbps) {
ret = set_mba_sc(true);
+ if (ret)
+ goto out_cdpl3;
+ }
+
+ if (ctx->enable_debug)
+ resctrl_debug = true;
+ return 0;
+
+out_cdpl3:
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
+out_cdpl2:
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
+out_done:
return ret;
}
@@ -2463,6 +2574,7 @@ static void schemata_list_destroy(void)
static int rdt_get_tree(struct fs_context *fc)
{
struct rdt_fs_context *ctx = rdt_fc2context(fc);
+ unsigned long flags = RFTYPE_CTRL_BASE;
struct rdt_domain *dom;
struct rdt_resource *r;
int ret;
@@ -2477,18 +2589,31 @@ static int rdt_get_tree(struct fs_context *fc)
goto out;
}
+ ret = rdtgroup_setup_root(ctx);
+ if (ret)
+ goto out;
+
ret = rdt_enable_ctx(ctx);
- if (ret < 0)
- goto out_cdp;
+ if (ret)
+ goto out_root;
ret = schemata_list_create();
if (ret) {
schemata_list_destroy();
- goto out_mba;
+ goto out_ctx;
}
closid_init();
+ if (rdt_mon_capable)
+ flags |= RFTYPE_MON;
+
+ ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
+ if (ret)
+ goto out_schemata_free;
+
+ kernfs_activate(rdtgroup_default.kn);
+
ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
if (ret < 0)
goto out_schemata_free;
@@ -2543,11 +2668,10 @@ out_info:
kernfs_remove(kn_info);
out_schemata_free:
schemata_list_destroy();
-out_mba:
- if (ctx->enable_mba_mbps)
- set_mba_sc(false);
-out_cdp:
- cdp_disable_all();
+out_ctx:
+ rdt_disable_ctx();
+out_root:
+ rdtgroup_destroy_root();
out:
rdt_last_cmd_clear();
mutex_unlock(&rdtgroup_mutex);
@@ -2559,6 +2683,7 @@ enum rdt_param {
Opt_cdp,
Opt_cdpl2,
Opt_mba_mbps,
+ Opt_debug,
nr__rdt_params
};
@@ -2566,6 +2691,7 @@ static const struct fs_parameter_spec rdt_fs_parameters[] = {
fsparam_flag("cdp", Opt_cdp),
fsparam_flag("cdpl2", Opt_cdpl2),
fsparam_flag("mba_MBps", Opt_mba_mbps),
+ fsparam_flag("debug", Opt_debug),
{}
};
@@ -2591,6 +2717,9 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
return -EINVAL;
ctx->enable_mba_mbps = true;
return 0;
+ case Opt_debug:
+ ctx->enable_debug = true;
+ return 0;
}
return -EINVAL;
@@ -2618,7 +2747,6 @@ static int rdt_init_fs_context(struct fs_context *fc)
if (!ctx)
return -ENOMEM;
- ctx->kfc.root = rdt_root;
ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
fc->fs_private = &ctx->kfc;
fc->ops = &rdt_fs_context_ops;
@@ -2779,16 +2907,16 @@ static void rdt_kill_sb(struct super_block *sb)
cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
- set_mba_sc(false);
+ rdt_disable_ctx();
/*Put everything back to default values. */
for_each_alloc_capable_rdt_resource(r)
reset_all_ctrls(r);
- cdp_disable_all();
rmdir_all_sub();
rdt_pseudo_lock_release();
rdtgroup_default.mode = RDT_MODE_SHAREABLE;
schemata_list_destroy();
+ rdtgroup_destroy_root();
static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
static_branch_disable_cpuslocked(&rdt_mon_enable_key);
static_branch_disable_cpuslocked(&rdt_enable_key);
@@ -3170,8 +3298,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
enum rdt_group_type rtype, struct rdtgroup **r)
{
struct rdtgroup *prdtgrp, *rdtgrp;
+ unsigned long files = 0;
struct kernfs_node *kn;
- uint files = 0;
int ret;
prdtgrp = rdtgroup_kn_lock_live(parent_kn);
@@ -3223,7 +3351,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
goto out_destroy;
}
- files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype);
+ if (rtype == RDTCTRL_GROUP) {
+ files = RFTYPE_BASE | RFTYPE_CTRL;
+ if (rdt_mon_capable)
+ files |= RFTYPE_MON;
+ } else {
+ files = RFTYPE_BASE | RFTYPE_MON;
+ }
+
ret = rdtgroup_add_files(kn, files);
if (ret) {
rdt_last_cmd_puts("kernfs fill error\n");
@@ -3656,6 +3791,9 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl))
seq_puts(seq, ",mba_MBps");
+ if (resctrl_debug)
+ seq_puts(seq, ",debug");
+
return 0;
}
@@ -3666,10 +3804,8 @@ static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
.show_options = rdtgroup_show_options,
};
-static int __init rdtgroup_setup_root(void)
+static int rdtgroup_setup_root(struct rdt_fs_context *ctx)
{
- int ret;
-
rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
KERNFS_ROOT_CREATE_DEACTIVATED |
KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
@@ -3677,6 +3813,20 @@ static int __init rdtgroup_setup_root(void)
if (IS_ERR(rdt_root))
return PTR_ERR(rdt_root);
+ ctx->kfc.root = rdt_root;
+ rdtgroup_default.kn = kernfs_root_to_node(rdt_root);
+
+ return 0;
+}
+
+static void rdtgroup_destroy_root(void)
+{
+ kernfs_destroy_root(rdt_root);
+ rdtgroup_default.kn = NULL;
+}
+
+static void __init rdtgroup_setup_default(void)
+{
mutex_lock(&rdtgroup_mutex);
rdtgroup_default.closid = 0;
@@ -3686,19 +3836,7 @@ static int __init rdtgroup_setup_root(void)
list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
- ret = rdtgroup_add_files(kernfs_root_to_node(rdt_root), RF_CTRL_BASE);
- if (ret) {
- kernfs_destroy_root(rdt_root);
- goto out;
- }
-
- rdtgroup_default.kn = kernfs_root_to_node(rdt_root);
- kernfs_activate(rdtgroup_default.kn);
-
-out:
mutex_unlock(&rdtgroup_mutex);
-
- return ret;
}
static void domain_destroy_mon_state(struct rdt_domain *d)
@@ -3820,13 +3958,11 @@ int __init rdtgroup_init(void)
seq_buf_init(&last_cmd_status, last_cmd_status_buf,
sizeof(last_cmd_status_buf));
- ret = rdtgroup_setup_root();
- if (ret)
- return ret;
+ rdtgroup_setup_default();
ret = sysfs_create_mount_point(fs_kobj, "resctrl");
if (ret)
- goto cleanup_root;
+ return ret;
ret = register_filesystem(&rdt_fs_type);
if (ret)
@@ -3859,8 +3995,6 @@ int __init rdtgroup_init(void)
cleanup_mountpoint:
sysfs_remove_mount_point(fs_kobj, "resctrl");
-cleanup_root:
- kernfs_destroy_root(rdt_root);
return ret;
}
@@ -3870,5 +4004,4 @@ void __exit rdtgroup_exit(void)
debugfs_remove_recursive(debugfs_resctrl);
unregister_filesystem(&rdt_fs_type);
sysfs_remove_mount_point(fs_kobj, "resctrl");
- kernfs_destroy_root(rdt_root);
}
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 0270925fe0..dc13670356 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -78,7 +78,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
/*
* initial apic id, which also represents 32-bit extended x2apic id.
*/
- c->initial_apicid = edx;
+ c->topo.initial_apicid = edx;
smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
#endif
return 0;
@@ -108,7 +108,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
* Populate HT related information from sub-leaf level 0.
*/
cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
- c->initial_apicid = edx;
+ c->topo.initial_apicid = edx;
core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
@@ -146,20 +146,19 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
die_select_mask = (~(-1 << die_plus_mask_width)) >>
core_plus_mask_width;
- c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid,
+ c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid,
ht_mask_width) & core_select_mask;
if (die_level_present) {
- c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid,
+ c->topo.die_id = apic->phys_pkg_id(c->topo.initial_apicid,
core_plus_mask_width) & die_select_mask;
}
- c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
- pkg_mask_width);
+ c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, pkg_mask_width);
/*
* Reinit the apicid, now that we have extended initial_apicid.
*/
- c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+ c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
c->x86_max_cores = (core_level_siblings / smp_num_siblings);
__max_die_per_package = (die_level_siblings / core_level_siblings);
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index 05fa4ef634..415564a652 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -65,20 +65,6 @@ static void early_init_zhaoxin(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
}
-
- if (c->cpuid_level >= 0x00000001) {
- u32 eax, ebx, ecx, edx;
-
- cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
- /*
- * If HTT (EDX[28]) is set EBX[16:23] contain the number of
- * apicids which are reserved per package. Store the resulting
- * shift value for the package management code.
- */
- if (edx & (1U << 28))
- c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
- }
-
}
static void init_zhaoxin(struct cpuinfo_x86 *c)