redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

Merge branch 'x86/topology' into perf/core, to prepare for new patches 

Signed-off-by: Ingo Molnar <mingo@kernel.org>
alistair/sunxi64-5.4-dsi
Ingo Molnar 2019-06-03 11:58:45 +02:00
parent 6a9f4efe78 eb876fbc24
commit 3384c78631
19 changed files with 422 additions and 214 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
Documentation/cputopology.txt
View File

@ -12,6 +12,12 @@ physical_package_id:
socket number, but the actual value is architecture and platform
dependent.
die_id:
the CPU die ID of cpuX. Typically it is the hardware platform's
identifier (rather than the kernel's). The actual value is
architecture and platform dependent.
core_id:
the CPU core ID of cpuX. Typically it is the hardware platform's
@ -30,25 +36,33 @@ drawer_id:
identifier (rather than the kernel's). The actual value is
architecture and platform dependent.
thread_siblings:
core_cpus:
internal kernel map of cpuX's hardware threads within the same
core as cpuX.
internal kernel map of CPUs within the same core.
(deprecated name: "thread_siblings")
thread_siblings_list:
core_cpus_list:
human-readable list of cpuX's hardware threads within the same
core as cpuX.
human-readable list of CPUs within the same core.
(deprecated name: "thread_siblings_list");
core_siblings:
package_cpus:
internal kernel map of cpuX's hardware threads within the same
physical_package_id.
internal kernel map of the CPUs sharing the same physical_package_id.
(deprecated name: "core_siblings")
core_siblings_list:
package_cpus_list:
human-readable list of cpuX's hardware threads within the same
physical_package_id.
human-readable list of CPUs sharing the same physical_package_id.
(deprecated name: "core_siblings_list")
die_cpus:
internal kernel map of CPUs within the same die.
die_cpus_list:
human-readable list of CPUs within the same die.
book_siblings:
@ -81,11 +95,13 @@ For an architecture to support this feature, it must define some of
these macros in include/asm-XXX/topology.h::
#define topology_physical_package_id(cpu)
#define topology_die_id(cpu)
#define topology_core_id(cpu)
#define topology_book_id(cpu)
#define topology_drawer_id(cpu)
#define topology_sibling_cpumask(cpu)
#define topology_core_cpumask(cpu)
#define topology_die_cpumask(cpu)
#define topology_book_cpumask(cpu)
#define topology_drawer_cpumask(cpu)
@ -99,9 +115,11 @@ provides default definitions for any of the above macros that are
not defined by include/asm-XXX/topology.h:
1) topology_physical_package_id: -1
2) topology_core_id: 0
3) topology_sibling_cpumask: just the given CPU
4) topology_core_cpumask: just the given CPU
2) topology_die_id: -1
3) topology_core_id: 0
4) topology_sibling_cpumask: just the given CPU
5) topology_core_cpumask: just the given CPU
6) topology_die_cpumask: just the given CPU
For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
default definitions for topology_book_id() and topology_book_cpumask().

4
Documentation/x86/topology.rst
View File

@ -49,6 +49,10 @@ Package-related topology information in the kernel:
The number of cores in a package. This information is retrieved via CPUID.
- cpuinfo_x86.x86_max_dies:
The number of dies in a package. This information is retrieved via CPUID.
- cpuinfo_x86.phys_proc_id:
The physical ID of the package. This information is retrieved via CPUID

14
arch/x86/events/intel/cstate.c
View File

@ -302,7 +302,7 @@ static int cstate_pmu_event_init(struct perf_event *event)
return -EINVAL;
event->hw.event_base = pkg_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
topology_core_cpumask(event->cpu));
topology_die_cpumask(event->cpu));
} else {
return -ENOENT;
}
@ -385,7 +385,7 @@ static int cstate_cpu_exit(unsigned int cpu)
if (has_cstate_pkg &&
cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) {
target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate events if there is a valid target */
if (target < nr_cpu_ids) {
cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
@ -414,7 +414,7 @@ static int cstate_cpu_init(unsigned int cpu)
* in the package cpu mask as the designated reader.
*/
target = cpumask_any_and(&cstate_pkg_cpu_mask,
topology_core_cpumask(cpu));
topology_die_cpumask(cpu));
if (has_cstate_pkg && target >= nr_cpu_ids)
cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
@ -663,7 +663,13 @@ static int __init cstate_init(void)
}
if (has_cstate_pkg) {
err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1);
if (topology_max_die_per_package() > 1) {
err = perf_pmu_register(&cstate_pkg_pmu,
"cstate_die", -1);
} else {
err = perf_pmu_register(&cstate_pkg_pmu,
cstate_pkg_pmu.name, -1);
}
if (err) {
has_cstate_pkg = false;
pr_info("Failed to register cstate pkg pmu\n");

20
arch/x86/events/intel/rapl.c
View File

@ -149,7 +149,7 @@ struct rapl_pmu {
struct rapl_pmus {
struct pmu pmu;
unsigned int maxpkg;
unsigned int maxdie;
struct rapl_pmu *pmus[];
};
@ -162,13 +162,13 @@ static u64 rapl_timer_ms;
static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
{
unsigned int pkgid = topology_logical_package_id(cpu);
unsigned int dieid = topology_logical_die_id(cpu);
/*
* The unsigned check also catches the '-1' return value for non
* existent mappings in the topology map.
*/
return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL;
}
static inline u64 rapl_read_counter(struct perf_event *event)
@ -572,7 +572,7 @@ static int rapl_cpu_offline(unsigned int cpu)
pmu->cpu = -1;
/* Find a new cpu to collect rapl events */
target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate rapl events to the new target */
if (target < nr_cpu_ids) {
@ -599,14 +599,14 @@ static int rapl_cpu_online(unsigned int cpu)
pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
rapl_hrtimer_init(pmu);
rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu;
}
/*
* Check if there is an online cpu in the package which collects rapl
* events already.
*/
target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu));
if (target < nr_cpu_ids)
return 0;
@ -669,22 +669,22 @@ static void cleanup_rapl_pmus(void)
{
int i;
for (i = 0; i < rapl_pmus->maxpkg; i++)
for (i = 0; i < rapl_pmus->maxdie; i++)
kfree(rapl_pmus->pmus[i]);
kfree(rapl_pmus);
}
static int __init init_rapl_pmus(void)
{
int maxpkg = topology_max_packages();
int maxdie = topology_max_packages() * topology_max_die_per_package();
size_t size;
size = sizeof(*rapl_pmus) + maxpkg * sizeof(struct rapl_pmu *);
size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
rapl_pmus = kzalloc(size, GFP_KERNEL);
if (!rapl_pmus)
return -ENOMEM;
rapl_pmus->maxpkg = maxpkg;
rapl_pmus->maxdie = maxdie;
rapl_pmus->pmu.attr_groups = rapl_attr_groups;
rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
rapl_pmus->pmu.event_init = rapl_pmu_event_init;

80
arch/x86/events/intel/uncore.c
View File

@ -15,7 +15,7 @@ struct pci_driver *uncore_pci_driver;
DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
struct pci_extra_dev *uncore_extra_pci_dev;
static int max_packages;
static int max_dies;
/* mask of cpus that collect uncore events */
static cpumask_t uncore_cpu_mask;
@ -101,13 +101,13 @@ ssize_t uncore_event_show(struct kobject *kobj,
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
unsigned int pkgid = topology_logical_package_id(cpu);
unsigned int dieid = topology_logical_die_id(cpu);
/*
* The unsigned check also catches the '-1' return value for non
* existent mappings in the topology map.
*/
return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
return dieid < max_dies ? pmu->boxes[dieid] : NULL;
}
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@ -312,7 +312,7 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
uncore_pmu_init_hrtimer(box);
box->cpu = -1;
box->pci_phys_id = -1;
box->pkgid = -1;
box->dieid = -1;
/* set default hrtimer timeout */
box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
@ -827,10 +827,10 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
{
int pkg;
int die;
for (pkg = 0; pkg < max_packages; pkg++)
kfree(pmu->boxes[pkg]);
for (die = 0; die < max_dies; die++)
kfree(pmu->boxes[die]);
kfree(pmu->boxes);
}
@ -867,7 +867,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
if (!pmus)
return -ENOMEM;
size = max_packages * sizeof(struct intel_uncore_box *);
size = max_dies * sizeof(struct intel_uncore_box *);
for (i = 0; i < type->num_boxes; i++) {
pmus[i].func_id = setid ? i : -1;
@ -937,20 +937,21 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu = NULL;
struct intel_uncore_box *box;
int phys_id, pkg, ret;
int phys_id, die, ret;
phys_id = uncore_pcibus_to_physid(pdev->bus);
if (phys_id < 0)
return -ENODEV;
pkg = topology_phys_to_logical_pkg(phys_id);
if (pkg < 0)
die = (topology_max_die_per_package() > 1) ? phys_id :
topology_phys_to_logical_pkg(phys_id);
if (die < 0)
return -EINVAL;
if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
int idx = UNCORE_PCI_DEV_IDX(id->driver_data);
uncore_extra_pci_dev[pkg].dev[idx] = pdev;
uncore_extra_pci_dev[die].dev[idx] = pdev;
pci_set_drvdata(pdev, NULL);
return 0;
}
@ -989,7 +990,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
}
if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL))
if (WARN_ON_ONCE(pmu->boxes[die] != NULL))
return -EINVAL;
box = uncore_alloc_box(type, NUMA_NO_NODE);
@ -1003,13 +1004,13 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
atomic_inc(&box->refcnt);
box->pci_phys_id = phys_id;
box->pkgid = pkg;
box->dieid = die;
box->pci_dev = pdev;
box->pmu = pmu;
uncore_box_init(box);
pci_set_drvdata(pdev, box);
pmu->boxes[pkg] = box;
pmu->boxes[die] = box;
if (atomic_inc_return(&pmu->activeboxes) > 1)
return 0;
@ -1017,7 +1018,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
ret = uncore_pmu_register(pmu);
if (ret) {
pci_set_drvdata(pdev, NULL);
pmu->boxes[pkg] = NULL;
pmu->boxes[die] = NULL;
uncore_box_exit(box);
kfree(box);
}
@ -1028,16 +1029,17 @@ static void uncore_pci_remove(struct pci_dev *pdev)
{
struct intel_uncore_box *box;
struct intel_uncore_pmu *pmu;
int i, phys_id, pkg;
int i, phys_id, die;
phys_id = uncore_pcibus_to_physid(pdev->bus);
box = pci_get_drvdata(pdev);
if (!box) {
pkg = topology_phys_to_logical_pkg(phys_id);
die = (topology_max_die_per_package() > 1) ? phys_id :
topology_phys_to_logical_pkg(phys_id);
for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
if (uncore_extra_pci_dev[pkg].dev[i] == pdev) {
uncore_extra_pci_dev[pkg].dev[i] = NULL;
if (uncore_extra_pci_dev[die].dev[i] == pdev) {
uncore_extra_pci_dev[die].dev[i] = NULL;
break;
}
}
@ -1050,7 +1052,7 @@ static void uncore_pci_remove(struct pci_dev *pdev)
return;
pci_set_drvdata(pdev, NULL);
pmu->boxes[box->pkgid] = NULL;
pmu->boxes[box->dieid] = NULL;
if (atomic_dec_return(&pmu->activeboxes) == 0)
uncore_pmu_unregister(pmu);
uncore_box_exit(box);
@ -1062,7 +1064,7 @@ static int __init uncore_pci_init(void)
size_t size;
int ret;
size = max_packages * sizeof(struct pci_extra_dev);
size = max_dies * sizeof(struct pci_extra_dev);
uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
if (!uncore_extra_pci_dev) {
ret = -ENOMEM;
@ -1109,11 +1111,11 @@ static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
{
struct intel_uncore_pmu *pmu = type->pmus;
struct intel_uncore_box *box;
int i, pkg;
int i, die;
pkg = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu);
die = topology_logical_die_id(old_cpu < 0 ? new_cpu : old_cpu);
for (i = 0; i < type->num_boxes; i++, pmu++) {
box = pmu->boxes[pkg];
box = pmu->boxes[die];
if (!box)
continue;
@ -1146,13 +1148,13 @@ static int uncore_event_cpu_offline(unsigned int cpu)
struct intel_uncore_type *type, **types = uncore_msr_uncores;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
int i, pkg, target;
int i, die, target;
/* Check if exiting cpu is used for collecting uncore events */
if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
goto unref;
/* Find a new cpu to collect uncore events */
target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate uncore events to the new target */
if (target < nr_cpu_ids)
@ -1165,12 +1167,12 @@ static int uncore_event_cpu_offline(unsigned int cpu)
unref:
/* Clear the references */
pkg = topology_logical_package_id(cpu);
die = topology_logical_die_id(cpu);
for (; *types; types++) {
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
box = pmu->boxes[pkg];
box = pmu->boxes[die];
if (box && atomic_dec_return(&box->refcnt) == 0)
uncore_box_exit(box);
}
@ -1179,7 +1181,7 @@ unref:
}
static int allocate_boxes(struct intel_uncore_type **types,
unsigned int pkg, unsigned int cpu)
unsigned int die, unsigned int cpu)
{
struct intel_uncore_box *box, *tmp;
struct intel_uncore_type *type;
@ -1192,20 +1194,20 @@ static int allocate_boxes(struct intel_uncore_type **types,
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
if (pmu->boxes[pkg])
if (pmu->boxes[die])
continue;
box = uncore_alloc_box(type, cpu_to_node(cpu));
if (!box)
goto cleanup;
box->pmu = pmu;
box->pkgid = pkg;
box->dieid = die;
list_add(&box->active_list, &allocated);
}
}
/* Install them in the pmus */
list_for_each_entry_safe(box, tmp, &allocated, active_list) {
list_del_init(&box->active_list);
box->pmu->boxes[pkg] = box;
box->pmu->boxes[die] = box;
}
return 0;
@ -1222,10 +1224,10 @@ static int uncore_event_cpu_online(unsigned int cpu)
struct intel_uncore_type *type, **types = uncore_msr_uncores;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
int i, ret, pkg, target;
int i, ret, die, target;
pkg = topology_logical_package_id(cpu);
ret = allocate_boxes(types, pkg, cpu);
die = topology_logical_die_id(cpu);
ret = allocate_boxes(types, die, cpu);
if (ret)
return ret;
@ -1233,7 +1235,7 @@ static int uncore_event_cpu_online(unsigned int cpu)
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
box = pmu->boxes[pkg];
box = pmu->boxes[die];
if (box && atomic_inc_return(&box->refcnt) == 1)
uncore_box_init(box);
}
@ -1243,7 +1245,7 @@ static int uncore_event_cpu_online(unsigned int cpu)
* Check if there is an online cpu in the package
* which collects uncore events already.
*/
target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu));
target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
if (target < nr_cpu_ids)
return 0;
@ -1418,7 +1420,7 @@ static int __init intel_uncore_init(void)
if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
return -ENODEV;
max_packages = topology_max_packages();
max_dies = topology_max_packages() * topology_max_die_per_package();
uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
if (uncore_init->pci_init) {

4
arch/x86/events/intel/uncore.h
View File

@ -108,7 +108,7 @@ struct intel_uncore_extra_reg {
struct intel_uncore_box {
int pci_phys_id;
int pkgid; /* Logical package ID */
int dieid; /* Logical die ID */
int n_active; /* number of active events */
int n_events;
int cpu; /* cpu to collect events */
@ -467,7 +467,7 @@ static inline void uncore_box_exit(struct intel_uncore_box *box)
static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
{
return (box->pkgid < 0);
return (box->dieid < 0);
}
static inline struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)

4
arch/x86/events/intel/uncore_snbep.c
View File

@ -1058,8 +1058,8 @@ static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_eve
if (reg1->idx != EXTRA_REG_NONE) {
int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
int pkg = box->pkgid;
struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx];
int die = box->dieid;
struct pci_dev *filter_pdev = uncore_extra_pci_dev[die].dev[idx];
if (filter_pdev) {
pci_write_config_dword(filter_pdev, reg1->reg,

4
arch/x86/include/asm/processor.h
View File

@ -105,7 +105,7 @@ struct cpuinfo_x86 {
int x86_power;
unsigned long loops_per_jiffy;
/* cpuid returned max cores value: */
u16 x86_max_cores;
u16 x86_max_cores;
u16 apicid;
u16 initial_apicid;
u16 x86_clflush_size;
@ -117,6 +117,8 @@ struct cpuinfo_x86 {
u16 logical_proc_id;
/* Core id: */
u16 cpu_core_id;
u16 cpu_die_id;
u16 logical_die_id;
/* Index into per_cpu list: */
u16 cpu_index;
u32 microcode;

1
arch/x86/include/asm/smp.h
View File

@ -23,6 +23,7 @@ extern unsigned int num_processors;
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
/* cpus sharing the last level cache: */
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);

17
arch/x86/include/asm/topology.h
View File

@ -106,15 +106,25 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id)
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
#define topology_logical_die_id(cpu) (cpu_data(cpu).logical_die_id)
#define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
#ifdef CONFIG_SMP
#define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu))
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
extern unsigned int __max_logical_packages;
#define topology_max_packages() (__max_logical_packages)
extern unsigned int __max_die_per_package;
static inline int topology_max_die_per_package(void)
{
return __max_die_per_package;
}
extern int __max_smt_threads;
static inline int topology_max_smt_threads(void)
@ -123,14 +133,21 @@ static inline int topology_max_smt_threads(void)
}
int topology_update_package_map(unsigned int apicid, unsigned int cpu);
int topology_update_die_map(unsigned int dieid, unsigned int cpu);
int topology_phys_to_logical_pkg(unsigned int pkg);
int topology_phys_to_logical_die(unsigned int die, unsigned int cpu);
bool topology_is_primary_thread(unsigned int cpu);
bool topology_smt_supported(void);
#else
#define topology_max_packages() (1)
static inline int
topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
static inline int
topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; }
static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
static inline int topology_phys_to_logical_die(unsigned int die,
unsigned int cpu) { return 0; }
static inline int topology_max_die_per_package(void) { return 1; }
static inline int topology_max_smt_threads(void) { return 1; }
static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
static inline bool topology_smt_supported(void) { return false; }

1
arch/x86/kernel/cpu/common.c
View File

@ -1299,6 +1299,7 @@ static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
cpu, apicid, c->initial_apicid);
}
BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
#else
c->logical_proc_id = 0;
#endif

88
arch/x86/kernel/cpu/topology.c
View File

@ -15,33 +15,66 @@
/* leaf 0xb SMT level */
#define SMT_LEVEL 0
/* leaf 0xb sub-leaf types */
/* extended topology sub-leaf types */
#define INVALID_TYPE 0
#define SMT_TYPE 1
#define CORE_TYPE 2
#define DIE_TYPE 5
#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff)
#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f)
#define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff)
#ifdef CONFIG_SMP
unsigned int __max_die_per_package __read_mostly = 1;
EXPORT_SYMBOL(__max_die_per_package);
/*
* Check if given CPUID extended toplogy "leaf" is implemented
*/
static int check_extended_topology_leaf(int leaf)
{
unsigned int eax, ebx, ecx, edx;
cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
return -1;
return 0;
}
/*
* Return best CPUID Extended Toplogy Leaf supported
*/
static int detect_extended_topology_leaf(struct cpuinfo_x86 *c)
{
if (c->cpuid_level >= 0x1f) {
if (check_extended_topology_leaf(0x1f) == 0)
return 0x1f;
}
if (c->cpuid_level >= 0xb) {
if (check_extended_topology_leaf(0xb) == 0)
return 0xb;
}
return -1;
}
#endif
int detect_extended_topology_early(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
unsigned int eax, ebx, ecx, edx;
int leaf;
if (c->cpuid_level < 0xb)
return -1;
cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
/*
* check if the cpuid leaf 0xb is actually implemented.
*/
if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
leaf = detect_extended_topology_leaf(c);
if (leaf < 0)
return -1;
set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
/*
* initial apic id, which also represents 32-bit extended x2apic id.
*/
@ -52,7 +85,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
}
/*
* Check for extended topology enumeration cpuid leaf 0xb and if it
* Check for extended topology enumeration cpuid leaf, and if it
* exists, use it for populating initial_apicid and cpu topology
* detection.
*/
@ -60,22 +93,28 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
unsigned int eax, ebx, ecx, edx, sub_index;
unsigned int ht_mask_width, core_plus_mask_width;
unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
unsigned int core_select_mask, core_level_siblings;
unsigned int die_select_mask, die_level_siblings;
int leaf;
if (detect_extended_topology_early(c) < 0)
leaf = detect_extended_topology_leaf(c);
if (leaf < 0)
return -1;
/*
* Populate HT related information from sub-leaf level 0.
*/
cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
c->initial_apicid = edx;
core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
sub_index = 1;
do {
cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
/*
* Check for the Core type in the implemented sub leaves.
@ -83,23 +122,34 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
break;
die_level_siblings = core_level_siblings;
die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
}
if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) {
die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
}
sub_index++;
} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
die_select_mask = (~(-1 << die_plus_mask_width)) >>
core_plus_mask_width;
c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width)
& core_select_mask;
c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, core_plus_mask_width);
c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid,
ht_mask_width) & core_select_mask;
c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid,
core_plus_mask_width) & die_select_mask;
c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
die_plus_mask_width);
/*
* Reinit the apicid, now that we have extended initial_apicid.
*/
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
c->x86_max_cores = (core_level_siblings / smp_num_siblings);
__max_die_per_package = (die_level_siblings / core_level_siblings);
#endif
return 0;
}

69
arch/x86/kernel/smpboot.c
View File

@ -89,6 +89,10 @@ EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
/* representing HT, core, and die siblings of each logical CPU */
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
EXPORT_PER_CPU_SYMBOL(cpu_die_map);
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
/* Per CPU bogomips and other parameters */
@ -99,6 +103,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
static unsigned int logical_packages __read_mostly;
static unsigned int logical_die __read_mostly;
/* Maximum number of SMT threads on any online core */
int __read_mostly __max_smt_threads = 1;
@ -300,6 +305,26 @@ int topology_phys_to_logical_pkg(unsigned int phys_pkg)
return -1;
}
EXPORT_SYMBOL(topology_phys_to_logical_pkg);
/**
* topology_phys_to_logical_die - Map a physical die id to logical
*
* Returns logical die id or -1 if not found
*/
int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
{
int cpu;
int proc_id = cpu_data(cur_cpu).phys_proc_id;
for_each_possible_cpu(cpu) {
struct cpuinfo_x86 *c = &cpu_data(cpu);
if (c->initialized && c->cpu_die_id == die_id &&
c->phys_proc_id == proc_id)
return c->logical_die_id;
}
return -1;
}
EXPORT_SYMBOL(topology_phys_to_logical_die);
/**
* topology_update_package_map - Update the physical to logical package map
@ -324,6 +349,29 @@ found:
cpu_data(cpu).logical_proc_id = new;
return 0;
}
/**
* topology_update_die_map - Update the physical to logical die map
* @die: The die id as retrieved via CPUID
* @cpu: The cpu for which this is updated
*/
int topology_update_die_map(unsigned int die, unsigned int cpu)
{
int new;
/* Already available somewhere? */
new = topology_phys_to_logical_die(die, cpu);
if (new >= 0)
goto found;
new = logical_die++;
if (new != die) {
pr_info("CPU %u Converting physical %u to logical die %u\n",
cpu, die, new);
}
found:
cpu_data(cpu).logical_die_id = new;
return 0;
}
void __init smp_store_boot_cpu_info(void)
{
@ -333,6 +381,7 @@ void __init smp_store_boot_cpu_info(void)
*c = boot_cpu_data;
c->cpu_index = id;
topology_update_package_map(c->phys_proc_id, id);
topology_update_die_map(c->cpu_die_id, id);
c->initialized = true;
}
@ -387,6 +436,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
if (c->phys_proc_id == o->phys_proc_id &&
c->cpu_die_id == o->cpu_die_id &&
per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
if (c->cpu_core_id == o->cpu_core_id)
return topology_sane(c, o, "smt");
@ -398,6 +448,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
}
} else if (c->phys_proc_id == o->phys_proc_id &&
c->cpu_die_id == o->cpu_die_id &&
c->cpu_core_id == o->cpu_core_id) {
return topology_sane(c, o, "smt");
}
@ -460,6 +511,15 @@ static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
return false;
}
static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
if ((c->phys_proc_id == o->phys_proc_id) &&
(c->cpu_die_id == o->cpu_die_id))
return true;
return false;
}
#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
static inline int x86_sched_itmt_flags(void)
{
@ -522,6 +582,7 @@ void set_cpu_sibling_map(int cpu)
cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
cpumask_set_cpu(cpu, topology_die_cpumask(cpu));
c->booted_cores = 1;
return;
}
@ -570,6 +631,9 @@ void set_cpu_sibling_map(int cpu)
}
if (match_pkg(c, o) && !topology_same_node(c, o))
x86_has_numa_in_package = true;
if ((i == cpu) || (has_mp && match_die(c, o)))
link_mask(topology_die_cpumask, cpu, i);
}
threads = cpumask_weight(topology_sibling_cpumask(cpu));
@ -1174,6 +1238,7 @@ static __init void disable_smp(void)
physid_set_mask_of_physid(0, &phys_cpu_present_map);
cpumask_set_cpu(0, topology_sibling_cpumask(0));
cpumask_set_cpu(0, topology_core_cpumask(0));
cpumask_set_cpu(0, topology_die_cpumask(0));
}
/*
@ -1269,6 +1334,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
@ -1489,6 +1555,8 @@ static void remove_siblinginfo(int cpu)
cpu_data(sibling).booted_cores--;
}
for_each_cpu(sibling, topology_die_cpumask(cpu))
cpumask_clear_cpu(cpu, topology_die_cpumask(sibling));
for_each_cpu(sibling, topology_sibling_cpumask(cpu))
cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
@ -1496,6 +1564,7 @@ static void remove_siblinginfo(int cpu)
cpumask_clear(cpu_llc_shared_mask(cpu));
cpumask_clear(topology_sibling_cpumask(cpu));
cpumask_clear(topology_core_cpumask(cpu));
cpumask_clear(topology_die_cpumask(cpu));
c->cpu_core_id = 0;
c->booted_cores = 0;
cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);

1
arch/x86/xen/smp_pv.c
View File

@ -251,6 +251,7 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
set_cpu_sibling_map(0);

22
drivers/base/topology.c
View File

@ -43,6 +43,9 @@ static ssize_t name##_list_show(struct device *dev, \
define_id_show_func(physical_package_id);
static DEVICE_ATTR_RO(physical_package_id);
define_id_show_func(die_id);
static DEVICE_ATTR_RO(die_id);
define_id_show_func(core_id);
static DEVICE_ATTR_RO(core_id);
@ -50,10 +53,22 @@ define_siblings_show_func(thread_siblings, sibling_cpumask);
static DEVICE_ATTR_RO(thread_siblings);
static DEVICE_ATTR_RO(thread_siblings_list);
define_siblings_show_func(core_cpus, sibling_cpumask);
static DEVICE_ATTR_RO(core_cpus);
static DEVICE_ATTR_RO(core_cpus_list);
define_siblings_show_func(core_siblings, core_cpumask);
static DEVICE_ATTR_RO(core_siblings);
static DEVICE_ATTR_RO(core_siblings_list);
define_siblings_show_func(die_cpus, die_cpumask);
static DEVICE_ATTR_RO(die_cpus);
static DEVICE_ATTR_RO(die_cpus_list);
define_siblings_show_func(package_cpus, core_cpumask);
static DEVICE_ATTR_RO(package_cpus);
static DEVICE_ATTR_RO(package_cpus_list);
#ifdef CONFIG_SCHED_BOOK
define_id_show_func(book_id);
static DEVICE_ATTR_RO(book_id);
@ -72,11 +87,18 @@ static DEVICE_ATTR_RO(drawer_siblings_list);
static struct attribute *default_attrs[] = {
&dev_attr_physical_package_id.attr,
&dev_attr_die_id.attr,
&dev_attr_core_id.attr,
&dev_attr_thread_siblings.attr,
&dev_attr_thread_siblings_list.attr,
&dev_attr_core_cpus.attr,
&dev_attr_core_cpus_list.attr,
&dev_attr_core_siblings.attr,
&dev_attr_core_siblings_list.attr,
&dev_attr_die_cpus.attr,
&dev_attr_die_cpus_list.attr,
&dev_attr_package_cpus.attr,
&dev_attr_package_cpus_list.attr,
#ifdef CONFIG_SCHED_BOOK
&dev_attr_book_id.attr,
&dev_attr_book_siblings.attr,

36
drivers/hwmon/coretemp.c
View File

@ -96,10 +96,10 @@ struct platform_data {
struct device_attribute name_attr;
};
/* Keep track of how many package pointers we allocated in init() */
static int max_packages __read_mostly;
/* Array of package pointers. Serialized by cpu hotplug lock */
static struct platform_device **pkg_devices;
/* Keep track of how many zone pointers we allocated in init() */
static int max_zones __read_mostly;
/* Array of zone pointers. Serialized by cpu hotplug lock */
static struct platform_device **zone_devices;
static ssize_t show_label(struct device *dev,
struct device_attribute *devattr, char *buf)
@ -422,10 +422,10 @@ static int chk_ucode_version(unsigned int cpu)
static struct platform_device *coretemp_get_pdev(unsigned int cpu)
{
int pkgid = topology_logical_package_id(cpu);
int id = topology_logical_die_id(cpu);
if (pkgid >= 0 && pkgid < max_packages)
return pkg_devices[pkgid];
if (id >= 0 && id < max_zones)
return zone_devices[id];
return NULL;
}
@ -531,7 +531,7 @@ static int coretemp_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct platform_data *pdata;
/* Initialize the per-package data structures */
/* Initialize the per-zone data structures */
pdata = devm_kzalloc(dev, sizeof(struct platform_data), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
@ -566,13 +566,13 @@ static struct platform_driver coretemp_driver = {
static struct platform_device *coretemp_device_add(unsigned int cpu)
{
int err, pkgid = topology_logical_package_id(cpu);
int err, zoneid = topology_logical_die_id(cpu);
struct platform_device *pdev;
if (pkgid < 0)
if (zoneid < 0)
return ERR_PTR(-ENOMEM);
pdev = platform_device_alloc(DRVNAME, pkgid);
pdev = platform_device_alloc(DRVNAME, zoneid);
if (!pdev)
return ERR_PTR(-ENOMEM);
@ -582,7 +582,7 @@ static struct platform_device *coretemp_device_add(unsigned int cpu)
return ERR_PTR(err);
}
pkg_devices[pkgid] = pdev;
zone_devices[zoneid] = pdev;
return pdev;
}
@ -690,7 +690,7 @@ static int coretemp_cpu_offline(unsigned int cpu)
* the rest.
*/
if (cpumask_empty(&pd->cpumask)) {
pkg_devices[topology_logical_package_id(cpu)] = NULL;
zone_devices[topology_logical_die_id(cpu)] = NULL;
platform_device_unregister(pdev);
return 0;
}
@ -728,10 +728,10 @@ static int __init coretemp_init(void)
if (!x86_match_cpu(coretemp_ids))
return -ENODEV;
max_packages = topology_max_packages();
pkg_devices = kcalloc(max_packages, sizeof(struct platform_device *),
max_zones = topology_max_packages() * topology_max_die_per_package();
zone_devices = kcalloc(max_zones, sizeof(struct platform_device *),
GFP_KERNEL);
if (!pkg_devices)
if (!zone_devices)
return -ENOMEM;
err = platform_driver_register(&coretemp_driver);
@ -747,7 +747,7 @@ static int __init coretemp_init(void)
outdrv:
platform_driver_unregister(&coretemp_driver);
kfree(pkg_devices);
kfree(zone_devices);
return err;
}
module_init(coretemp_init)
@ -756,7 +756,7 @@ static void __exit coretemp_exit(void)
{
cpuhp_remove_state(coretemp_hp_online);
platform_driver_unregister(&coretemp_driver);
kfree(pkg_devices);
kfree(zone_devices);
}
module_exit(coretemp_exit)

75
drivers/powercap/intel_rapl.c
View File

@ -178,12 +178,15 @@ struct rapl_domain {
#define power_zone_to_rapl_domain(_zone) \
container_of(_zone, struct rapl_domain, power_zone)
/* maximum rapl package domain name: package-%d-die-%d */
#define PACKAGE_DOMAIN_NAME_LENGTH 30
/* Each physical package contains multiple domains, these are the common
/* Each rapl package contains multiple domains, these are the common
* data across RAPL domains within a package.
*/
struct rapl_package {
unsigned int id; /* physical package/socket id */
unsigned int id; /* logical die id, equals physical 1-die systems */
unsigned int nr_domains;
unsigned long domain_map; /* bit map of active domains */
unsigned int power_unit;
@ -198,6 +201,7 @@ struct rapl_package {
int lead_cpu; /* one active cpu per package for access */
/* Track active cpus */
struct cpumask cpumask;
char name[PACKAGE_DOMAIN_NAME_LENGTH];
};
struct rapl_defaults {
@ -264,8 +268,9 @@ static struct powercap_control_type *control_type; /* PowerCap Controller */
static struct rapl_domain *platform_rapl_domain; /* Platform (PSys) domain */
/* caller to ensure CPU hotplug lock is held */
static struct rapl_package *find_package_by_id(int id)
static struct rapl_package *rapl_find_package_domain(int cpu)
{
int id = topology_logical_die_id(cpu);
struct rapl_package *rp;
list_for_each_entry(rp, &rapl_packages, plist) {
@ -925,8 +930,8 @@ static int rapl_check_unit_core(struct rapl_package *rp, int cpu)
value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
rp->time_unit = 1000000 / (1 << value);
pr_debug("Core CPU package %d energy=%dpJ, time=%dus, power=%duW\n",
rp->id, rp->energy_unit, rp->time_unit, rp->power_unit);
pr_debug("Core CPU %s energy=%dpJ, time=%dus, power=%duW\n",
rp->name, rp->energy_unit, rp->time_unit, rp->power_unit);
return 0;
}
@ -950,8 +955,8 @@ static int rapl_check_unit_atom(struct rapl_package *rp, int cpu)
value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
rp->time_unit = 1000000 / (1 << value);
pr_debug("Atom package %d energy=%dpJ, time=%dus, power=%duW\n",
rp->id, rp->energy_unit, rp->time_unit, rp->power_unit);
pr_debug("Atom %s energy=%dpJ, time=%dus, power=%duW\n",
rp->name, rp->energy_unit, rp->time_unit, rp->power_unit);
return 0;
}
@ -1180,7 +1185,7 @@ static void rapl_update_domain_data(struct rapl_package *rp)
u64 val;
for (dmn = 0; dmn < rp->nr_domains; dmn++) {
pr_debug("update package %d domain %s data\n", rp->id,
pr_debug("update %s domain %s data\n", rp->name,
rp->domains[dmn].name);
/* exclude non-raw primitives */
for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++) {
@ -1205,7 +1210,6 @@ static void rapl_unregister_powercap(void)
static int rapl_package_register_powercap(struct rapl_package *rp)
{
struct rapl_domain *rd;
char dev_name[17]; /* max domain name = 7 + 1 + 8 for int + 1 for null*/
struct powercap_zone *power_zone = NULL;
int nr_pl, ret;
@ -1216,20 +1220,16 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
if (rd->id == RAPL_DOMAIN_PACKAGE) {
nr_pl = find_nr_power_limit(rd);
pr_debug("register socket %d package domain %s\n",
rp->id, rd->name);
memset(dev_name, 0, sizeof(dev_name));
snprintf(dev_name, sizeof(dev_name), "%s-%d",
rd->name, rp->id);
pr_debug("register package domain %s\n", rp->name);
power_zone = powercap_register_zone(&rd->power_zone,
control_type,
dev_name, NULL,
rp->name, NULL,
&zone_ops[rd->id],
nr_pl,
&constraint_ops);
if (IS_ERR(power_zone)) {
pr_debug("failed to register package, %d\n",
rp->id);
pr_debug("failed to register power zone %s\n",
rp->name);
return PTR_ERR(power_zone);
}
/* track parent zone in per package/socket data */
@ -1255,8 +1255,8 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
&constraint_ops);
if (IS_ERR(power_zone)) {
pr_debug("failed to register power_zone, %d:%s:%s\n",
rp->id, rd->name, dev_name);
pr_debug("failed to register power_zone, %s:%s\n",
rp->name, rd->name);
ret = PTR_ERR(power_zone);
goto err_cleanup;
}
@ -1269,7 +1269,7 @@ err_cleanup:
* failed after the first domain setup.
*/
while (--rd >= rp->domains) {
pr_debug("unregister package %d domain %s\n", rp->id, rd->name);
pr_debug("unregister %s domain %s\n", rp->name, rd->name);
powercap_unregister_zone(control_type, &rd->power_zone);
}
@ -1300,7 +1300,7 @@ static int __init rapl_register_psys(void)
rd->rpl[0].name = pl1_name;
rd->rpl[1].prim_id = PL2_ENABLE;
rd->rpl[1].name = pl2_name;
rd->rp = find_package_by_id(0);
rd->rp = rapl_find_package_domain(0);
power_zone = powercap_register_zone(&rd->power_zone, control_type,
"psys", NULL,
@ -1379,8 +1379,8 @@ static void rapl_detect_powerlimit(struct rapl_domain *rd)
/* check if the domain is locked by BIOS, ignore if MSR doesn't exist */
if (!rapl_read_data_raw(rd, FW_LOCK, false, &val64)) {
if (val64) {
pr_info("RAPL package %d domain %s locked by BIOS\n",
rd->rp->id, rd->name);
pr_info("RAPL %s domain %s locked by BIOS\n",
rd->rp->name, rd->name);
rd->state |= DOMAIN_STATE_BIOS_LOCKED;
}
}
@ -1409,10 +1409,10 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
}
rp->nr_domains = bitmap_weight(&rp->domain_map, RAPL_DOMAIN_MAX);
if (!rp->nr_domains) {
pr_debug("no valid rapl domains found in package %d\n", rp->id);
pr_debug("no valid rapl domains found in %s\n", rp->name);
return -ENODEV;
}
pr_debug("found %d domains on package %d\n", rp->nr_domains, rp->id);
pr_debug("found %d domains on %s\n", rp->nr_domains, rp->name);
rp->domains = kcalloc(rp->nr_domains + 1, sizeof(struct rapl_domain),
GFP_KERNEL);
@ -1445,8 +1445,8 @@ static void rapl_remove_package(struct rapl_package *rp)
rd_package = rd;
continue;
}
pr_debug("remove package, undo power limit on %d: %s\n",
rp->id, rd->name);
pr_debug("remove package, undo power limit on %s: %s\n",
rp->name, rd->name);
powercap_unregister_zone(control_type, &rd->power_zone);
}
/* do parent zone last */
@ -1456,9 +1456,11 @@ static void rapl_remove_package(struct rapl_package *rp)
}
/* called from CPU hotplug notifier, hotplug lock held */
static struct rapl_package *rapl_add_package(int cpu, int pkgid)
static struct rapl_package *rapl_add_package(int cpu)
{
int id = topology_logical_die_id(cpu);
struct rapl_package *rp;
struct cpuinfo_x86 *c = &cpu_data(cpu);
int ret;
rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL);
@ -1466,9 +1468,16 @@ static struct rapl_package *rapl_add_package(int cpu, int pkgid)
return ERR_PTR(-ENOMEM);
/* add the new package to the list */
rp->id = pkgid;
rp->id = id;
rp->lead_cpu = cpu;
if (topology_max_die_per_package() > 1)
snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH,
"package-%d-die-%d", c->phys_proc_id, c->cpu_die_id);
else
snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d",
c->phys_proc_id);
/* check if the package contains valid domains */
if (rapl_detect_domains(rp, cpu) ||
rapl_defaults->check_unit(rp, cpu)) {
@ -1497,12 +1506,11 @@ err_free_package:
*/
static int rapl_cpu_online(unsigned int cpu)
{
int pkgid = topology_physical_package_id(cpu);
struct rapl_package *rp;
rp = find_package_by_id(pkgid);
rp = rapl_find_package_domain(cpu);
if (!rp) {
rp = rapl_add_package(cpu, pkgid);
rp = rapl_add_package(cpu);
if (IS_ERR(rp))
return PTR_ERR(rp);
}
@ -1512,11 +1520,10 @@ static int rapl_cpu_online(unsigned int cpu)
static int rapl_cpu_down_prep(unsigned int cpu)
{
int pkgid = topology_physical_package_id(cpu);
struct rapl_package *rp;
int lead_cpu;
rp = find_package_by_id(pkgid);
rp = rapl_find_package_domain(cpu);
if (!rp)
return 0;

142
drivers/thermal/intel/x86_pkg_temp_thermal.c
View File

@ -55,7 +55,7 @@ MODULE_PARM_DESC(notify_delay_ms,
*/
#define MAX_NUMBER_OF_TRIPS 2
struct pkg_device {
struct zone_device {
int cpu;
bool work_scheduled;
u32 tj_max;
@ -70,10 +70,10 @@ static struct thermal_zone_params pkg_temp_tz_params = {
.no_hwmon = true,
};
/* Keep track of how many package pointers we allocated in init() */
static int max_packages __read_mostly;
/* Array of package pointers */
static struct pkg_device **packages;
/* Keep track of how many zone pointers we allocated in init() */
static int max_id __read_mostly;
/* Array of zone pointers */
static struct zone_device **zones;
/* Serializes interrupt notification, work and hotplug */
static DEFINE_SPINLOCK(pkg_temp_lock);
/* Protects zone operation in the work function against hotplug removal */
@ -120,12 +120,12 @@ err_out:
*
* - Other callsites: Must hold pkg_temp_lock
*/
static struct pkg_device *pkg_temp_thermal_get_dev(unsigned int cpu)
static struct zone_device *pkg_temp_thermal_get_dev(unsigned int cpu)
{
int pkgid = topology_logical_package_id(cpu);
int id = topology_logical_die_id(cpu);
if (pkgid >= 0 && pkgid < max_packages)
return packages[pkgid];
if (id >= 0 && id < max_id)
return zones[id];
return NULL;
}
@ -150,12 +150,13 @@ static int get_tj_max(int cpu, u32 *tj_max)
static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp)
{
struct pkg_device *pkgdev = tzd->devdata;
struct zone_device *zonedev = tzd->devdata;
u32 eax, edx;
rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_STATUS, &eax, &edx);
rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_STATUS,
&eax, &edx);
if (eax & 0x80000000) {
*temp = pkgdev->tj_max - ((eax >> 16) & 0x7f) * 1000;
*temp = zonedev->tj_max - ((eax >> 16) & 0x7f) * 1000;
pr_debug("sys_get_curr_temp %d\n", *temp);
return 0;
}
@ -165,7 +166,7 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp)
static int sys_get_trip_temp(struct thermal_zone_device *tzd,
int trip, int *temp)
{
struct pkg_device *pkgdev = tzd->devdata;
struct zone_device *zonedev = tzd->devdata;
unsigned long thres_reg_value;
u32 mask, shift, eax, edx;
int ret;
@ -181,14 +182,14 @@ static int sys_get_trip_temp(struct thermal_zone_device *tzd,
shift = THERM_SHIFT_THRESHOLD0;
}
ret = rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
ret = rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
&eax, &edx);
if (ret < 0)
return ret;
thres_reg_value = (eax & mask) >> shift;
if (thres_reg_value)
*temp = pkgdev->tj_max - thres_reg_value * 1000;
*temp = zonedev->tj_max - thres_reg_value * 1000;
else
*temp = 0;
pr_debug("sys_get_trip_temp %d\n", *temp);
@ -199,14 +200,14 @@ static int sys_get_trip_temp(struct thermal_zone_device *tzd,
static int
sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp)
{
struct pkg_device *pkgdev = tzd->devdata;
struct zone_device *zonedev = tzd->devdata;
u32 l, h, mask, shift, intr;
int ret;
if (trip >= MAX_NUMBER_OF_TRIPS || temp >= pkgdev->tj_max)
if (trip >= MAX_NUMBER_OF_TRIPS || temp >= zonedev->tj_max)
return -EINVAL;
ret = rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
ret = rdmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
&l, &h);
if (ret < 0)
return ret;
@ -228,11 +229,12 @@ sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp)
if (!temp) {
l &= ~intr;
} else {
l |= (pkgdev->tj_max - temp)/1000 << shift;
l |= (zonedev->tj_max - temp)/1000 << shift;
l |= intr;
}
return wrmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
return wrmsr_on_cpu(zonedev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
l, h);
}
static int sys_get_trip_type(struct thermal_zone_device *thermal, int trip,
@ -287,26 +289,26 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
{
struct thermal_zone_device *tzone = NULL;
int cpu = smp_processor_id();
struct pkg_device *pkgdev;
struct zone_device *zonedev;
u64 msr_val, wr_val;
mutex_lock(&thermal_zone_mutex);
spin_lock_irq(&pkg_temp_lock);
++pkg_work_cnt;
pkgdev = pkg_temp_thermal_get_dev(cpu);
if (!pkgdev) {
zonedev = pkg_temp_thermal_get_dev(cpu);
if (!zonedev) {
spin_unlock_irq(&pkg_temp_lock);
mutex_unlock(&thermal_zone_mutex);
return;
}
pkgdev->work_scheduled = false;
zonedev->work_scheduled = false;
rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
wr_val = msr_val & ~(THERM_LOG_THRESHOLD0 | THERM_LOG_THRESHOLD1);
if (wr_val != msr_val) {
wrmsrl(MSR_IA32_PACKAGE_THERM_STATUS, wr_val);
tzone = pkgdev->tzone;
tzone = zonedev->tzone;
}
enable_pkg_thres_interrupt();
@ -332,7 +334,7 @@ static void pkg_thermal_schedule_work(int cpu, struct delayed_work *work)
static int pkg_thermal_notify(u64 msr_val)
{
int cpu = smp_processor_id();
struct pkg_device *pkgdev;
struct zone_device *zonedev;
unsigned long flags;
spin_lock_irqsave(&pkg_temp_lock, flags);
@ -341,10 +343,10 @@ static int pkg_thermal_notify(u64 msr_val)
disable_pkg_thres_interrupt();
/* Work is per package, so scheduling it once is enough. */
pkgdev = pkg_temp_thermal_get_dev(cpu);
if (pkgdev && !pkgdev->work_scheduled) {
pkgdev->work_scheduled = true;
pkg_thermal_schedule_work(pkgdev->cpu, &pkgdev->work);
zonedev = pkg_temp_thermal_get_dev(cpu);
if (zonedev && !zonedev->work_scheduled) {
zonedev->work_scheduled = true;
pkg_thermal_schedule_work(zonedev->cpu, &zonedev->work);
}
spin_unlock_irqrestore(&pkg_temp_lock, flags);
@ -353,12 +355,12 @@ static int pkg_thermal_notify(u64 msr_val)
static int pkg_temp_thermal_device_add(unsigned int cpu)
{
int pkgid = topology_logical_package_id(cpu);
int id = topology_logical_die_id(cpu);
u32 tj_max, eax, ebx, ecx, edx;
struct pkg_device *pkgdev;
struct zone_device *zonedev;
int thres_count, err;
if (pkgid >= max_packages)
if (id >= max_id)
return -ENOMEM;
cpuid(6, &eax, &ebx, &ecx, &edx);
@ -372,51 +374,51 @@ static int pkg_temp_thermal_device_add(unsigned int cpu)
if (err)
return err;
pkgdev = kzalloc(sizeof(*pkgdev), GFP_KERNEL);
if (!pkgdev)
zonedev = kzalloc(sizeof(*zonedev), GFP_KERNEL);
if (!zonedev)
return -ENOMEM;
INIT_DELAYED_WORK(&pkgdev->work, pkg_temp_thermal_threshold_work_fn);
pkgdev->cpu = cpu;
pkgdev->tj_max = tj_max;
pkgdev->tzone = thermal_zone_device_register("x86_pkg_temp",
INIT_DELAYED_WORK(&zonedev->work, pkg_temp_thermal_threshold_work_fn);
zonedev->cpu = cpu;
zonedev->tj_max = tj_max;
zonedev->tzone = thermal_zone_device_register("x86_pkg_temp",
thres_count,
(thres_count == MAX_NUMBER_OF_TRIPS) ? 0x03 : 0x01,
pkgdev, &tzone_ops, &pkg_temp_tz_params, 0, 0);
if (IS_ERR(pkgdev->tzone)) {
err = PTR_ERR(pkgdev->tzone);
kfree(pkgdev);
zonedev, &tzone_ops, &pkg_temp_tz_params, 0, 0);
if (IS_ERR(zonedev->tzone)) {
err = PTR_ERR(zonedev->tzone);
kfree(zonedev);
return err;
}
/* Store MSR value for package thermal interrupt, to restore at exit */
rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, pkgdev->msr_pkg_therm_low,
pkgdev->msr_pkg_therm_high);
rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, zonedev->msr_pkg_therm_low,
zonedev->msr_pkg_therm_high);
cpumask_set_cpu(cpu, &pkgdev->cpumask);
cpumask_set_cpu(cpu, &zonedev->cpumask);
spin_lock_irq(&pkg_temp_lock);
packages[pkgid] = pkgdev;
zones[id] = zonedev;
spin_unlock_irq(&pkg_temp_lock);
return 0;
}
static int pkg_thermal_cpu_offline(unsigned int cpu)
{
struct pkg_device *pkgdev = pkg_temp_thermal_get_dev(cpu);
struct zone_device *zonedev = pkg_temp_thermal_get_dev(cpu);
bool lastcpu, was_target;
int target;
if (!pkgdev)
if (!zonedev)
return 0;
target = cpumask_any_but(&pkgdev->cpumask, cpu);
cpumask_clear_cpu(cpu, &pkgdev->cpumask);
target = cpumask_any_but(&zonedev->cpumask, cpu);
cpumask_clear_cpu(cpu, &zonedev->cpumask);
lastcpu = target >= nr_cpu_ids;
/*
* Remove the sysfs files, if this is the last cpu in the package
* before doing further cleanups.
*/
if (lastcpu) {
struct thermal_zone_device *tzone = pkgdev->tzone;
struct thermal_zone_device *tzone = zonedev->tzone;
/*
* We must protect against a work function calling
@ -425,7 +427,7 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
* won't try to call.
*/
mutex_lock(&thermal_zone_mutex);
pkgdev->tzone = NULL;
zonedev->tzone = NULL;
mutex_unlock(&thermal_zone_mutex);
thermal_zone_device_unregister(tzone);
@ -439,8 +441,8 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
* one. When we drop the lock, then the interrupt notify function
* will see the new target.
*/
was_target = pkgdev->cpu == cpu;
pkgdev->cpu = target;
was_target = zonedev->cpu == cpu;
zonedev->cpu = target;
/*
* If this is the last CPU in the package remove the package
@ -449,23 +451,23 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
* worker will see the package anymore.
*/
if (lastcpu) {
packages[topology_logical_package_id(cpu)] = NULL;
zones[topology_logical_die_id(cpu)] = NULL;
/* After this point nothing touches the MSR anymore. */
wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
pkgdev->msr_pkg_therm_low, pkgdev->msr_pkg_therm_high);
zonedev->msr_pkg_therm_low, zonedev->msr_pkg_therm_high);
}
/*
* Check whether there is work scheduled and whether the work is
* targeted at the outgoing CPU.
*/
if (pkgdev->work_scheduled && was_target) {
if (zonedev->work_scheduled && was_target) {
/*
* To cancel the work we need to drop the lock, otherwise
* we might deadlock if the work needs to be flushed.
*/
spin_unlock_irq(&pkg_temp_lock);
cancel_delayed_work_sync(&pkgdev->work);
cancel_delayed_work_sync(&zonedev->work);
spin_lock_irq(&pkg_temp_lock);
/*
* If this is not the last cpu in the package and the work
@ -473,21 +475,21 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
* need to reschedule the work, otherwise the interrupt
* stays disabled forever.
*/
if (!lastcpu && pkgdev->work_scheduled)
pkg_thermal_schedule_work(target, &pkgdev->work);
if (!lastcpu && zonedev->work_scheduled)
pkg_thermal_schedule_work(target, &zonedev->work);
}
spin_unlock_irq(&pkg_temp_lock);
/* Final cleanup if this is the last cpu */
if (lastcpu)
kfree(pkgdev);
kfree(zonedev);
return 0;
}
static int pkg_thermal_cpu_online(unsigned int cpu)
{
struct pkg_device *pkgdev = pkg_temp_thermal_get_dev(cpu);
struct zone_device *zonedev = pkg_temp_thermal_get_dev(cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu);
/* Paranoia check */
@ -495,8 +497,8 @@ static int pkg_thermal_cpu_online(unsigned int cpu)
return -ENODEV;
/* If the package exists, nothing to do */
if (pkgdev) {
cpumask_set_cpu(cpu, &pkgdev->cpumask);
if (zonedev) {
cpumask_set_cpu(cpu, &zonedev->cpumask);
return 0;
}
return pkg_temp_thermal_device_add(cpu);
@ -515,10 +517,10 @@ static int __init pkg_temp_thermal_init(void)
if (!x86_match_cpu(pkg_temp_thermal_ids))
return -ENODEV;
max_packages = topology_max_packages();
packages = kcalloc(max_packages, sizeof(struct pkg_device *),
max_id = topology_max_packages() * topology_max_die_per_package();
zones = kcalloc(max_id, sizeof(struct zone_device *),
GFP_KERNEL);
if (!packages)
if (!zones)
return -ENOMEM;
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "thermal/x86_pkg:online",
@ -537,7 +539,7 @@ static int __init pkg_temp_thermal_init(void)
return 0;
err:
kfree(packages);
kfree(zones);
return ret;
}
module_init(pkg_temp_thermal_init)
@ -549,7 +551,7 @@ static void __exit pkg_temp_thermal_exit(void)
cpuhp_remove_state(pkg_thermal_hp_state);
debugfs_remove_recursive(debugfs);
kfree(packages);
kfree(zones);
}
module_exit(pkg_temp_thermal_exit)

6
include/linux/topology.h
View File

@ -184,6 +184,9 @@ static inline int cpu_to_mem(int cpu)
#ifndef topology_physical_package_id
#define topology_physical_package_id(cpu) ((void)(cpu), -1)
#endif
#ifndef topology_die_id
#define topology_die_id(cpu) ((void)(cpu), -1)
#endif
#ifndef topology_core_id
#define topology_core_id(cpu) ((void)(cpu), 0)
#endif
@ -193,6 +196,9 @@ static inline int cpu_to_mem(int cpu)
#ifndef topology_core_cpumask
#define topology_core_cpumask(cpu) cpumask_of(cpu)
#endif
#ifndef topology_die_cpumask
#define topology_die_cpumask(cpu) cpumask_of(cpu)
#endif
#ifdef CONFIG_SCHED_SMT
static inline const struct cpumask *cpu_smt_mask(int cpu)