summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/mips/Makefile3
-rw-r--r--arch/mips/boot/compressed/Makefile2
-rw-r--r--arch/mips/boot/compressed/calc_vmlinuz_load_addr.c2
-rw-r--r--arch/mips/include/asm/mach-ath79/ar933x_uart.h4
-rw-r--r--arch/mips/mm/mmap.c2
-rw-r--r--arch/mips/mm/tlbex.c29
-rw-r--r--arch/x86/Kconfig.cpu13
-rw-r--r--arch/x86/entry/entry_64.S6
-rw-r--r--arch/x86/events/Makefile2
-rw-r--r--arch/x86/events/core.c106
-rw-r--r--arch/x86/events/intel/core.c185
-rw-r--r--arch/x86/events/intel/cstate.c167
-rw-r--r--arch/x86/events/intel/rapl.c399
-rw-r--r--arch/x86/events/intel/uncore.c191
-rw-r--r--arch/x86/events/intel/uncore.h45
-rw-r--r--arch/x86/events/intel/uncore_snb.c101
-rw-r--r--arch/x86/events/intel/uncore_snbep.c605
-rw-r--r--arch/x86/events/msr.c110
-rw-r--r--arch/x86/events/perf_event.h7
-rw-r--r--arch/x86/events/probe.c45
-rw-r--r--arch/x86/events/probe.h29
-rw-r--r--arch/x86/include/asm/cpufeature.h4
-rw-r--r--arch/x86/include/asm/cpufeatures.h21
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/msr-index.h9
-rw-r--r--arch/x86/include/asm/processor.h7
-rw-r--r--arch/x86/include/asm/smp.h1
-rw-r--r--arch/x86/include/asm/topology.h17
-rw-r--r--arch/x86/kernel/acpi/cstate.c15
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c12
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c3
-rw-r--r--arch/x86/kernel/cpu/common.c59
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c4
-rw-r--r--arch/x86/kernel/cpu/intel.c27
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c15
-rw-r--r--arch/x86/kernel/cpu/scattered.c4
-rw-r--r--arch/x86/kernel/cpu/topology.c88
-rw-r--r--arch/x86/kernel/cpu/umwait.c200
-rw-r--r--arch/x86/kernel/cpu/zhaoxin.c167
-rw-r--r--arch/x86/kernel/ptrace.c14
-rw-r--r--arch/x86/kernel/smpboot.c69
-rw-r--r--arch/x86/kvm/cpuid.h2
-rw-r--r--arch/x86/xen/smp_pv.c1
44 files changed, 2111 insertions, 685 deletions
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 8f4486c4415b..eceff9b75b22 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -17,6 +17,7 @@ archscripts: scripts_basic
$(Q)$(MAKE) $(build)=arch/mips/boot/tools relocs
KBUILD_DEFCONFIG := 32r2el_defconfig
+KBUILD_DTBS := dtbs
#
# Select the object file format to substitute into the linker script.
@@ -384,7 +385,7 @@ quiet_cmd_64 = OBJCOPY $@
vmlinux.64: vmlinux
$(call cmd,64)
-all: $(all-y)
+all: $(all-y) $(KBUILD_DTBS)
# boot
$(boot-y): $(vmlinux-32) FORCE
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index 3c453a1f1ff1..172801ed35b8 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -78,6 +78,8 @@ OBJCOPYFLAGS_piggy.o := --add-section=.image=$(obj)/vmlinux.bin.z \
$(obj)/piggy.o: $(obj)/dummy.o $(obj)/vmlinux.bin.z FORCE
$(call if_changed,objcopy)
+HOSTCFLAGS_calc_vmlinuz_load_addr.o += $(LINUXINCLUDE)
+
# Calculate the load address of the compressed kernel image
hostprogs-y := calc_vmlinuz_load_addr
diff --git a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
index 240f1d12df75..080b926d2623 100644
--- a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
+++ b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c
@@ -9,7 +9,7 @@
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
-#include "../../../../include/linux/sizes.h"
+#include <linux/sizes.h>
int main(int argc, char *argv[])
{
diff --git a/arch/mips/include/asm/mach-ath79/ar933x_uart.h b/arch/mips/include/asm/mach-ath79/ar933x_uart.h
index b8f8af7dc47c..cacf3545e018 100644
--- a/arch/mips/include/asm/mach-ath79/ar933x_uart.h
+++ b/arch/mips/include/asm/mach-ath79/ar933x_uart.h
@@ -24,8 +24,8 @@
#define AR933X_UART_CS_PARITY_S 0
#define AR933X_UART_CS_PARITY_M 0x3
#define AR933X_UART_CS_PARITY_NONE 0
-#define AR933X_UART_CS_PARITY_ODD 1
-#define AR933X_UART_CS_PARITY_EVEN 2
+#define AR933X_UART_CS_PARITY_ODD 2
+#define AR933X_UART_CS_PARITY_EVEN 3
#define AR933X_UART_CS_IF_MODE_S 2
#define AR933X_UART_CS_IF_MODE_M 0x3
#define AR933X_UART_CS_IF_MODE_NONE 0
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 50ee7213b432..d79f2b432318 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -203,7 +203,7 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
bool __virt_addr_valid(const volatile void *kaddr)
{
- unsigned long vaddr = (unsigned long)vaddr;
+ unsigned long vaddr = (unsigned long)kaddr;
if ((vaddr < PAGE_OFFSET) || (vaddr >= MAP_BASE))
return false;
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 65b6e85447b1..144ceb0fba88 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -391,6 +391,7 @@ static struct work_registers build_get_work_registers(u32 **p)
static void build_restore_work_registers(u32 **p)
{
if (scratch_reg >= 0) {
+ uasm_i_ehb(p);
UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg);
return;
}
@@ -668,10 +669,12 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r,
uasm_i_mtc0(p, 0, C0_PAGEMASK);
uasm_il_b(p, r, lid);
}
- if (scratch_reg >= 0)
+ if (scratch_reg >= 0) {
+ uasm_i_ehb(p);
UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg);
- else
+ } else {
UASM_i_LW(p, 1, scratchpad_offset(0), 0);
+ }
} else {
/* Reset default page size */
if (PM_DEFAULT_MASK >> 16) {
@@ -938,10 +941,12 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
uasm_i_jr(p, ptr);
if (mode == refill_scratch) {
- if (scratch_reg >= 0)
+ if (scratch_reg >= 0) {
+ uasm_i_ehb(p);
UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg);
- else
+ } else {
UASM_i_LW(p, 1, scratchpad_offset(0), 0);
+ }
} else {
uasm_i_nop(p);
}
@@ -1258,6 +1263,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
UASM_i_MTC0(p, odd, C0_ENTRYLO1); /* load it */
if (c0_scratch_reg >= 0) {
+ uasm_i_ehb(p);
UASM_i_MFC0(p, scratch, c0_kscratch(), c0_scratch_reg);
build_tlb_write_entry(p, l, r, tlb_random);
uasm_l_leave(l, *p);
@@ -1603,15 +1609,17 @@ static void build_setup_pgd(void)
uasm_i_dinsm(&p, a0, 0, 29, 64 - 29);
uasm_l_tlbl_goaround1(&l, p);
UASM_i_SLL(&p, a0, a0, 11);
- uasm_i_jr(&p, 31);
UASM_i_MTC0(&p, a0, C0_CONTEXT);
+ uasm_i_jr(&p, 31);
+ uasm_i_ehb(&p);
} else {
/* PGD in c0_KScratch */
- uasm_i_jr(&p, 31);
if (cpu_has_ldpte)
UASM_i_MTC0(&p, a0, C0_PWBASE);
else
UASM_i_MTC0(&p, a0, c0_kscratch(), pgd_reg);
+ uasm_i_jr(&p, 31);
+ uasm_i_ehb(&p);
}
#else
#ifdef CONFIG_SMP
@@ -1625,13 +1633,16 @@ static void build_setup_pgd(void)
UASM_i_LA_mostly(&p, a2, pgdc);
UASM_i_SW(&p, a0, uasm_rel_lo(pgdc), a2);
#endif /* SMP */
- uasm_i_jr(&p, 31);
/* if pgd_reg is allocated, save PGD also to scratch register */
- if (pgd_reg != -1)
+ if (pgd_reg != -1) {
UASM_i_MTC0(&p, a0, c0_kscratch(), pgd_reg);
- else
+ uasm_i_jr(&p, 31);
+ uasm_i_ehb(&p);
+ } else {
+ uasm_i_jr(&p, 31);
uasm_i_nop(&p);
+ }
#endif
if (p >= (u32 *)tlbmiss_handler_setup_pgd_end)
panic("tlbmiss_handler_setup_pgd space exceeded");
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 6adce15268bd..8e29c991ba3e 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -480,3 +480,16 @@ config CPU_SUP_UMC_32
CPU might render the kernel unbootable.
If unsure, say N.
+
+config CPU_SUP_ZHAOXIN
+ default y
+ bool "Support Zhaoxin processors" if PROCESSOR_SELECT
+ help
+ This enables detection, tunings and quirks for Zhaoxin processors
+
+ You need this enabled if you want your kernel to run on a
+ Zhaoxin CPU. Disabling this option on other types of CPUs
+ makes the kernel a tiny bit smaller. Disabling it on a Zhaoxin
+ CPU might render the kernel unbootable.
+
+ If unsure, say N.
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 11aa3b2afa4d..3b7a0e8d3bc0 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1670,11 +1670,17 @@ nmi_restore:
iretq
END(nmi)
+#ifndef CONFIG_IA32_EMULATION
+/*
+ * This handles SYSCALL from 32-bit code. There is no way to program
+ * MSRs to fully disable 32-bit SYSCALL.
+ */
ENTRY(ignore_sysret)
UNWIND_HINT_EMPTY
mov $-ENOSYS, %eax
sysret
END(ignore_sysret)
+#endif
ENTRY(rewind_stack_do_exit)
UNWIND_HINT_FUNC
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 9cbfd34042d5..9e07f554333f 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
-obj-y += core.o
+obj-y += core.o probe.o
obj-y += amd/
obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 3cd94a21bd53..ffc015bd257e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1618,68 +1618,6 @@ static struct attribute_group x86_pmu_format_group __ro_after_init = {
.attrs = NULL,
};
-/*
- * Remove all undefined events (x86_pmu.event_map(id) == 0)
- * out of events_attr attributes.
- */
-static void __init filter_events(struct attribute **attrs)
-{
- struct device_attribute *d;
- struct perf_pmu_events_attr *pmu_attr;
- int offset = 0;
- int i, j;
-
- for (i = 0; attrs[i]; i++) {
- d = (struct device_attribute *)attrs[i];
- pmu_attr = container_of(d, struct perf_pmu_events_attr, attr);
- /* str trumps id */
- if (pmu_attr->event_str)
- continue;
- if (x86_pmu.event_map(i + offset))
- continue;
-
- for (j = i; attrs[j]; j++)
- attrs[j] = attrs[j + 1];
-
- /* Check the shifted attr. */
- i--;
-
- /*
- * event_map() is index based, the attrs array is organized
- * by increasing event index. If we shift the events, then
- * we need to compensate for the event_map(), otherwise
- * we are looking up the wrong event in the map
- */
- offset++;
- }
-}
-
-/* Merge two pointer arrays */
-__init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
-{
- struct attribute **new;
- int j, i;
-
- for (j = 0; a && a[j]; j++)
- ;
- for (i = 0; b && b[i]; i++)
- j++;
- j++;
-
- new = kmalloc_array(j, sizeof(struct attribute *), GFP_KERNEL);
- if (!new)
- return NULL;
-
- j = 0;
- for (i = 0; a && a[i]; i++)
- new[j++] = a[i];
- for (i = 0; b && b[i]; i++)
- new[j++] = b[i];
- new[j] = NULL;
-
- return new;
-}
-
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page)
{
struct perf_pmu_events_attr *pmu_attr = \
@@ -1744,9 +1682,24 @@ static struct attribute *events_attr[] = {
NULL,
};
+/*
+ * Remove all undefined events (x86_pmu.event_map(id) == 0)
+ * out of events_attr attributes.
+ */
+static umode_t
+is_visible(struct kobject *kobj, struct attribute *attr, int idx)
+{
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+ /* str trumps id */
+ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0;
+}
+
static struct attribute_group x86_pmu_events_group __ro_after_init = {
.name = "events",
.attrs = events_attr,
+ .is_visible = is_visible,
};
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
@@ -1842,37 +1795,10 @@ static int __init init_hw_perf_events(void)
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
- if (x86_pmu.caps_attrs) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_caps_group.attrs, x86_pmu.caps_attrs);
- if (!WARN_ON(!tmp))
- x86_pmu_caps_group.attrs = tmp;
- }
-
- if (x86_pmu.event_attrs)
- x86_pmu_events_group.attrs = x86_pmu.event_attrs;
-
if (!x86_pmu.events_sysfs_show)
x86_pmu_events_group.attrs = &empty_attrs;
- else
- filter_events(x86_pmu_events_group.attrs);
- if (x86_pmu.cpu_events) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events);
- if (!WARN_ON(!tmp))
- x86_pmu_events_group.attrs = tmp;
- }
-
- if (x86_pmu.attrs) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs);
- if (!WARN_ON(!tmp))
- x86_pmu_attr_group.attrs = tmp;
- }
+ pmu.attr_update = x86_pmu.attr_update;
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a5436cee20b1..bda450ff51ee 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -20,6 +20,7 @@
#include <asm/intel-family.h>
#include <asm/apic.h>
#include <asm/cpu_device_id.h>
+#include <asm/hypervisor.h>
#include "../perf_event.h"
@@ -3897,8 +3898,6 @@ static __initconst const struct x86_pmu core_pmu = {
.check_period = intel_pmu_check_period,
};
-static struct attribute *intel_pmu_attrs[];
-
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
@@ -3930,8 +3929,6 @@ static __initconst const struct x86_pmu intel_pmu = {
.format_attrs = intel_arch3_formats_attr,
.events_sysfs_show = intel_event_sysfs_show,
- .attrs = intel_pmu_attrs,
-
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
@@ -4055,6 +4052,13 @@ static bool check_msr(unsigned long msr, u64 mask)
u64 val_old, val_new, val_tmp;
/*
+ * Disable the check for real HW, so we don't
+ * mess with potentionaly enabled registers:
+ */
+ if (hypervisor_is_type(X86_HYPER_NATIVE))
+ return true;
+
+ /*
* Read the current value, change it and read it back to see if it
* matches, this is needed to detect certain hardware emulators
* (qemu/kvm) that don't trap on the MSR access and always return 0s.
@@ -4274,13 +4278,6 @@ static struct attribute *icl_tsx_events_attrs[] = {
NULL,
};
-static __init struct attribute **get_icl_events_attrs(void)
-{
- return boot_cpu_has(X86_FEATURE_RTM) ?
- merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
- icl_events_attrs;
-}
-
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
@@ -4402,43 +4399,111 @@ static DEVICE_ATTR(allow_tsx_force_abort, 0644,
static struct attribute *intel_pmu_attrs[] = {
&dev_attr_freeze_on_smi.attr,
- NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */
+ &dev_attr_allow_tsx_force_abort.attr,
NULL,
};
-static __init struct attribute **
-get_events_attrs(struct attribute **base,
- struct attribute **mem,
- struct attribute **tsx)
+static umode_t
+tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
- struct attribute **attrs = base;
- struct attribute **old;
+ return boot_cpu_has(X86_FEATURE_RTM) ? attr->mode : 0;
+}
- if (mem && x86_pmu.pebs)
- attrs = merge_attr(attrs, mem);
+static umode_t
+pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.pebs ? attr->mode : 0;
+}
- if (tsx && boot_cpu_has(X86_FEATURE_RTM)) {
- old = attrs;
- attrs = merge_attr(attrs, tsx);
- if (old != base)
- kfree(old);
- }
+static umode_t
+lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.lbr_nr ? attr->mode : 0;
+}
- return attrs;
+static umode_t
+exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.version >= 2 ? attr->mode : 0;
}
+static umode_t
+default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ if (attr == &dev_attr_allow_tsx_force_abort.attr)
+ return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
+
+ return attr->mode;
+}
+
+static struct attribute_group group_events_td = {
+ .name = "events",
+};
+
+static struct attribute_group group_events_mem = {
+ .name = "events",
+ .is_visible = pebs_is_visible,
+};
+
+static struct attribute_group group_events_tsx = {
+ .name = "events",
+ .is_visible = tsx_is_visible,
+};
+
+static struct attribute_group group_caps_gen = {
+ .name = "caps",
+ .attrs = intel_pmu_caps_attrs,
+};
+
+static struct attribute_group group_caps_lbr = {
+ .name = "caps",
+ .attrs = lbr_attrs,
+ .is_visible = lbr_is_visible,
+};
+
+static struct attribute_group group_format_extra = {
+ .name = "format",
+ .is_visible = exra_is_visible,
+};
+
+static struct attribute_group group_format_extra_skl = {
+ .name = "format",
+ .is_visible = exra_is_visible,
+};
+
+static struct attribute_group group_default = {
+ .attrs = intel_pmu_attrs,
+ .is_visible = default_is_visible,
+};
+
+static const struct attribute_group *attr_update[] = {
+ &group_events_td,
+ &group_events_mem,
+ &group_events_tsx,
+ &group_caps_gen,
+ &group_caps_lbr,
+ &group_format_extra,
+ &group_format_extra_skl,
+ &group_default,
+ NULL,
+};
+
+static struct attribute *empty_attrs;
+
__init int intel_pmu_init(void)
{
- struct attribute **extra_attr = NULL;
- struct attribute **mem_attr = NULL;
- struct attribute **tsx_attr = NULL;
- struct attribute **to_free = NULL;
+ struct attribute **extra_skl_attr = &empty_attrs;
+ struct attribute **extra_attr = &empty_attrs;
+ struct attribute **td_attr = &empty_attrs;
+ struct attribute **mem_attr = &empty_attrs;
+ struct attribute **tsx_attr = &empty_attrs;
union cpuid10_edx edx;
union cpuid10_eax eax;
union cpuid10_ebx ebx;
struct event_constraint *c;
unsigned int unused;
struct extra_reg *er;
+ bool pmem = false;
int version, i;
char *name;
@@ -4596,7 +4661,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
x86_pmu.extra_regs = intel_slm_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = slm_events_attrs;
+ td_attr = slm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Silvermont events, ");
name = "silvermont";
@@ -4624,7 +4689,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_prec_dist = true;
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = glm_events_attrs;
+ td_attr = glm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Goldmont events, ");
name = "goldmont";
@@ -4651,7 +4716,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_PEBS_ALL;
x86_pmu.get_event_constraints = glp_get_event_constraints;
- x86_pmu.cpu_events = glm_events_attrs;
+ td_attr = glm_events_attrs;
/* Goldmont Plus has 4-wide pipeline */
event_attr_td_total_slots_scale_glm.event_str = "4";
extra_attr = slm_format_attr;
@@ -4740,7 +4805,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.cpu_events = snb_events_attrs;
+ td_attr = snb_events_attrs;
mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
@@ -4781,7 +4846,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.cpu_events = snb_events_attrs;
+ td_attr = snb_events_attrs;
mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
@@ -4818,10 +4883,10 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.lbr_double_abort = true;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
pr_cont("Haswell events, ");
@@ -4860,10 +4925,10 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.limit_period = bdw_limit_period;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
pr_cont("Broadwell events, ");
@@ -4890,9 +4955,10 @@ __init int intel_pmu_init(void)
name = "knights-landing";
break;
+ case INTEL_FAM6_SKYLAKE_X:
+ pmem = true;
case INTEL_FAM6_SKYLAKE_MOBILE:
case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
x86_add_quirk(intel_pebs_isolation_quirk);
@@ -4920,27 +4986,28 @@ __init int intel_pmu_init(void)
x86_pmu.get_event_constraints = hsw_get_event_constraints;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
- extra_attr = merge_attr(extra_attr, skl_format_attr);
- to_free = extra_attr;
- x86_pmu.cpu_events = hsw_events_attrs;
+ extra_skl_attr = skl_format_attr;
+ td_attr = hsw_events_attrs;
mem_attr = hsw_mem_events_attrs;
tsx_attr = hsw_tsx_events_attrs;
- intel_pmu_pebs_data_source_skl(
- boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+ intel_pmu_pebs_data_source_skl(pmem);
if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
x86_pmu.flags |= PMU_FL_TFA;
x86_pmu.get_event_constraints = tfa_get_event_constraints;
x86_pmu.enable_all = intel_tfa_pmu_enable_all;
x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
- intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr;
}
pr_cont("Skylake events, ");
name = "skylake";
break;
+ case INTEL_FAM6_ICELAKE_X:
+ case INTEL_FAM6_ICELAKE_XEON_D:
+ pmem = true;
case INTEL_FAM6_ICELAKE_MOBILE:
+ case INTEL_FAM6_ICELAKE_DESKTOP:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4959,11 +5026,12 @@ __init int intel_pmu_init(void)
x86_pmu.get_event_constraints = icl_get_event_constraints;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
- extra_attr = merge_attr(extra_attr, skl_format_attr);
- x86_pmu.cpu_events = get_icl_events_attrs();
+ extra_skl_attr = skl_format_attr;
+ mem_attr = icl_events_attrs;
+ tsx_attr = icl_tsx_events_attrs;
x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
x86_pmu.lbr_pt_coexist = true;
- intel_pmu_pebs_data_source_skl(false);
+ intel_pmu_pebs_data_source_skl(pmem);
pr_cont("Icelake events, ");
name = "icelake";
break;
@@ -4988,14 +5056,14 @@ __init int intel_pmu_init(void)
snprintf(pmu_name_str, sizeof(pmu_name_str), "%s", name);
- if (version >= 2 && extra_attr) {
- x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
- extra_attr);
- WARN_ON(!x86_pmu.format_attrs);
- }
- x86_pmu.cpu_events = get_events_attrs(x86_pmu.cpu_events,
- mem_attr, tsx_attr);
+ group_events_td.attrs = td_attr;
+ group_events_mem.attrs = mem_attr;
+ group_events_tsx.attrs = tsx_attr;
+ group_format_extra.attrs = extra_attr;
+ group_format_extra_skl.attrs = extra_skl_attr;
+
+ x86_pmu.attr_update = attr_update;
if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
@@ -5043,12 +5111,8 @@ __init int intel_pmu_init(void)
x86_pmu.lbr_nr = 0;
}
- x86_pmu.caps_attrs = intel_pmu_caps_attrs;
-
- if (x86_pmu.lbr_nr) {
- x86_pmu.caps_attrs = merge_attr(x86_pmu.caps_attrs, lbr_attrs);
+ if (x86_pmu.lbr_nr)
pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
- }
/*
* Access extra MSR may cause #GP under certain circumstances.
@@ -5078,7 +5142,6 @@ __init int intel_pmu_init(void)
if (x86_pmu.counter_freezing)
x86_pmu.handle_irq = intel_pmu_handle_irq_v4;
- kfree(to_free);
return 0;
}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 6072f92cb8ea..688592b34564 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -96,6 +96,7 @@
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
+#include "../probe.h"
MODULE_LICENSE("GPL");
@@ -144,25 +145,42 @@ enum perf_cstate_core_events {
PERF_CSTATE_CORE_EVENT_MAX,
};
-PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00");
-PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01");
-PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02");
-PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03");
+PMU_EVENT_ATTR_STRING(c1-residency, attr_cstate_core_c1, "event=0x00");
+PMU_EVENT_ATTR_STRING(c3-residency, attr_cstate_core_c3, "event=0x01");
+PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_core_c6, "event=0x02");
+PMU_EVENT_ATTR_STRING(c7-residency, attr_cstate_core_c7, "event=0x03");
-static struct perf_cstate_msr core_msr[] = {
- [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1 },
- [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3 },
- [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6 },
- [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7 },
+static unsigned long core_msr_mask;
+
+PMU_EVENT_GROUP(events, cstate_core_c1);
+PMU_EVENT_GROUP(events, cstate_core_c3);
+PMU_EVENT_GROUP(events, cstate_core_c6);
+PMU_EVENT_GROUP(events, cstate_core_c7);
+
+static bool test_msr(int idx, void *data)
+{
+ return test_bit(idx, (unsigned long *) data);
+}
+
+static struct perf_msr core_msr[] = {
+ [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &group_cstate_core_c1, test_msr },
+ [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &group_cstate_core_c3, test_msr },
+ [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &group_cstate_core_c6, test_msr },
+ [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &group_cstate_core_c7, test_msr },
};
-static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = {
+static struct attribute *attrs_empty[] = {
NULL,
};
+/*
+ * There are no default events, but we need to create
+ * "events" group (with empty attrs) before updating
+ * it with detected events.
+ */
static struct attribute_group core_events_attr_group = {
.name = "events",
- .attrs = core_events_attrs,
+ .attrs = attrs_empty,
};
DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63");
@@ -211,31 +229,37 @@ enum perf_cstate_pkg_events {
PERF_CSTATE_PKG_EVENT_MAX,
};
-PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00");
-PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01");
-PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02");
-PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_pkg_c7, "event=0x03");
-PMU_EVENT_ATTR_STRING(c8-residency, evattr_cstate_pkg_c8, "event=0x04");
-PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05");
-PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06");
-
-static struct perf_cstate_msr pkg_msr[] = {
- [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2 },
- [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3 },
- [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6 },
- [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7 },
- [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8 },
- [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9 },
- [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10 },
-};
-
-static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = {
- NULL,
+PMU_EVENT_ATTR_STRING(c2-residency, attr_cstate_pkg_c2, "event=0x00");
+PMU_EVENT_ATTR_STRING(c3-residency, attr_cstate_pkg_c3, "event=0x01");
+PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_pkg_c6, "event=0x02");
+PMU_EVENT_ATTR_STRING(c7-residency, attr_cstate_pkg_c7, "event=0x03");
+PMU_EVENT_ATTR_STRING(c8-residency, attr_cstate_pkg_c8, "event=0x04");
+PMU_EVENT_ATTR_STRING(c9-residency, attr_cstate_pkg_c9, "event=0x05");
+PMU_EVENT_ATTR_STRING(c10-residency, attr_cstate_pkg_c10, "event=0x06");
+
+static unsigned long pkg_msr_mask;
+
+PMU_EVENT_GROUP(events, cstate_pkg_c2);
+PMU_EVENT_GROUP(events, cstate_pkg_c3);
+PMU_EVENT_GROUP(events, cstate_pkg_c6);
+PMU_EVENT_GROUP(events, cstate_pkg_c7);
+PMU_EVENT_GROUP(events, cstate_pkg_c8);
+PMU_EVENT_GROUP(events, cstate_pkg_c9);
+PMU_EVENT_GROUP(events, cstate_pkg_c10);
+
+static struct perf_msr pkg_msr[] = {
+ [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &group_cstate_pkg_c2, test_msr },
+ [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &group_cstate_pkg_c3, test_msr },
+ [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &group_cstate_pkg_c6, test_msr },
+ [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &group_cstate_pkg_c7, test_msr },
+ [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &group_cstate_pkg_c8, test_msr },
+ [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &group_cstate_pkg_c9, test_msr },
+ [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &group_cstate_pkg_c10, test_msr },
};
static struct attribute_group pkg_events_attr_group = {
.name = "events",
- .attrs = pkg_events_attrs,
+ .attrs = attrs_empty,
};
DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63");
@@ -289,7 +313,8 @@ static int cstate_pmu_event_init(struct perf_event *event)
if (event->pmu == &cstate_core_pmu) {
if (cfg >= PERF_CSTATE_CORE_EVENT_MAX)
return -EINVAL;
- if (!core_msr[cfg].attr)
+ cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_CORE_EVENT_MAX);
+ if (!(core_msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.event_base = core_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_core_cpu_mask,
@@ -298,11 +323,11 @@ static int cstate_pmu_event_init(struct perf_event *event)
if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
return -EINVAL;
cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
- if (!pkg_msr[cfg].attr)
+ if (!(pkg_msr_mask & (1 << cfg)))
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 +410,7 @@ 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);
@@ -414,15 +439,35 @@ 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);
return 0;
}
+const struct attribute_group *core_attr_update[] = {
+ &group_cstate_core_c1,
+ &group_cstate_core_c3,
+ &group_cstate_core_c6,
+ &group_cstate_core_c7,
+ NULL,
+};
+
+const struct attribute_group *pkg_attr_update[] = {
+ &group_cstate_pkg_c2,
+ &group_cstate_pkg_c3,
+ &group_cstate_pkg_c6,
+ &group_cstate_pkg_c7,
+ &group_cstate_pkg_c8,
+ &group_cstate_pkg_c9,
+ &group_cstate_pkg_c10,
+ NULL,
+};
+
static struct pmu cstate_core_pmu = {
.attr_groups = core_attr_groups,
+ .attr_update = core_attr_update,
.name = "cstate_core",
.task_ctx_nr = perf_invalid_context,
.event_init = cstate_pmu_event_init,
@@ -437,6 +482,7 @@ static struct pmu cstate_core_pmu = {
static struct pmu cstate_pkg_pmu = {
.attr_groups = pkg_attr_groups,
+ .attr_update = pkg_attr_update,
.name = "cstate_pkg",
.task_ctx_nr = perf_invalid_context,
.event_init = cstate_pmu_event_init,
@@ -580,35 +626,11 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_DESKTOP, snb_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
-/*
- * Probe the cstate events and insert the available one into sysfs attrs
- * Return false if there are no available events.
- */
-static bool __init cstate_probe_msr(const unsigned long evmsk, int max,
- struct perf_cstate_msr *msr,
- struct attribute **attrs)
-{
- bool found = false;
- unsigned int bit;
- u64 val;
-
- for (bit = 0; bit < max; bit++) {
- if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) {
- *attrs++ = &msr[bit].attr->attr.attr;
- found = true;
- } else {
- msr[bit].attr = NULL;
- }
- }
- *attrs = NULL;
-
- return found;
-}
-
static int __init cstate_probe(const struct cstate_model *cm)
{
/* SLM has different MSR for PKG C6 */
@@ -620,13 +642,14 @@ static int __init cstate_probe(const struct cstate_model *cm)
pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY;
- has_cstate_core = cstate_probe_msr(cm->core_events,
- PERF_CSTATE_CORE_EVENT_MAX,
- core_msr, core_events_attrs);
+ core_msr_mask = perf_msr_probe(core_msr, PERF_CSTATE_CORE_EVENT_MAX,
+ true, (void *) &cm->core_events);
- has_cstate_pkg = cstate_probe_msr(cm->pkg_events,
- PERF_CSTATE_PKG_EVENT_MAX,
- pkg_msr, pkg_events_attrs);
+ pkg_msr_mask = perf_msr_probe(pkg_msr, PERF_CSTATE_PKG_EVENT_MAX,
+ true, (void *) &cm->pkg_events);
+
+ has_cstate_core = !!core_msr_mask;
+ has_cstate_pkg = !!pkg_msr_mask;
return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
}
@@ -663,7 +686,13 @@ 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");
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 26c03f5adfb9..64ab51ffdf06 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -55,27 +55,28 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
+#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
+#include "../probe.h"
MODULE_LICENSE("GPL");
/*
* RAPL energy status counters
*/
-#define RAPL_IDX_PP0_NRG_STAT 0 /* all cores */
-#define INTEL_RAPL_PP0 0x1 /* pseudo-encoding */
-#define RAPL_IDX_PKG_NRG_STAT 1 /* entire package */
-#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */
-#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */
-#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */
-#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
-#define RAPL_IDX_PSYS_NRG_STAT 4 /* psys */
-#define INTEL_RAPL_PSYS 0x5 /* pseudo-encoding */
-
-#define NR_RAPL_DOMAINS 0x5
+enum perf_rapl_events {
+ PERF_RAPL_PP0 = 0, /* all cores */
+ PERF_RAPL_PKG, /* entire package */
+ PERF_RAPL_RAM, /* DRAM */
+ PERF_RAPL_PP1, /* gpu */
+ PERF_RAPL_PSYS, /* psys */
+
+ PERF_RAPL_MAX,
+ NR_RAPL_DOMAINS = PERF_RAPL_MAX,
+};
+
static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"pp0-core",
"package",
@@ -84,33 +85,6 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"psys",
};
-/* Clients have PP0, PKG */
-#define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT)
-
-/* Servers have PP0, PKG, RAM */
-#define RAPL_IDX_SRV (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT)
-
-/* Servers have PP0, PKG, RAM, PP1 */
-#define RAPL_IDX_HSW (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT)
-
-/* SKL clients have PP0, PKG, RAM, PP1, PSYS */
-#define RAPL_IDX_SKL_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT|\
- 1<<RAPL_IDX_PSYS_NRG_STAT)
-
-/* Knights Landing has PKG, RAM */
-#define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT)
-
/*
* event code: LSB 8 bits, passed in attr->config
* any other bit is reserved
@@ -149,26 +123,32 @@ struct rapl_pmu {
struct rapl_pmus {
struct pmu pmu;
- unsigned int maxpkg;
+ unsigned int maxdie;
struct rapl_pmu *pmus[];
};
+struct rapl_model {
+ unsigned long events;
+ bool apply_quirk;
+};
+
/* 1/2^hw_unit Joule */
static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
static struct rapl_pmus *rapl_pmus;
static cpumask_t rapl_cpu_mask;
static unsigned int rapl_cntr_mask;
static u64 rapl_timer_ms;
+static struct perf_msr rapl_msrs[];
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)
@@ -350,7 +330,7 @@ static void rapl_pmu_event_del(struct perf_event *event, int flags)
static int rapl_pmu_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config & RAPL_EVENT_MASK;
- int bit, msr, ret = 0;
+ int bit, ret = 0;
struct rapl_pmu *pmu;
/* only look at RAPL events */
@@ -366,33 +346,12 @@ static int rapl_pmu_event_init(struct perf_event *event)
event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
- /*
- * check event is known (determines counter)
- */
- switch (cfg) {
- case INTEL_RAPL_PP0:
- bit = RAPL_IDX_PP0_NRG_STAT;
- msr = MSR_PP0_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PKG:
- bit = RAPL_IDX_PKG_NRG_STAT;
- msr = MSR_PKG_ENERGY_STATUS;
- break;
- case INTEL_RAPL_RAM:
- bit = RAPL_IDX_RAM_NRG_STAT;
- msr = MSR_DRAM_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PP1:
- bit = RAPL_IDX_PP1_NRG_STAT;
- msr = MSR_PP1_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PSYS:
- bit = RAPL_IDX_PSYS_NRG_STAT;
- msr = MSR_PLATFORM_ENERGY_STATUS;
- break;
- default:
+ if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
return -EINVAL;
- }
+
+ cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1);
+ bit = cfg - 1;
+
/* check event supported */
if (!(rapl_cntr_mask & (1 << bit)))
return -EINVAL;
@@ -407,7 +366,7 @@ static int rapl_pmu_event_init(struct perf_event *event)
return -EINVAL;
event->cpu = pmu->cpu;
event->pmu_private = pmu;
- event->hw.event_base = msr;
+ event->hw.event_base = rapl_msrs[bit].msr;
event->hw.config = cfg;
event->hw.idx = bit;
@@ -457,110 +416,111 @@ RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890
RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10");
-static struct attribute *rapl_events_srv_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_ram),
+/*
+ * There are no default events, but we need to create
+ * "events" group (with empty attrs) before updating
+ * it with detected events.
+ */
+static struct attribute *attrs_empty[] = {
+ NULL,
+};
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_ram_unit),
+static struct attribute_group rapl_pmu_events_group = {
+ .name = "events",
+ .attrs = attrs_empty,
+};
- EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_ram_scale),
+DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
+static struct attribute *rapl_formats_attr[] = {
+ &format_attr_event.attr,
NULL,
};
-static struct attribute *rapl_events_cln_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
-
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
+static struct attribute_group rapl_pmu_format_group = {
+ .name = "format",
+ .attrs = rapl_formats_attr,
+};
- EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
+static const struct attribute_group *rapl_attr_groups[] = {
+ &rapl_pmu_attr_group,
+ &rapl_pmu_format_group,
+ &rapl_pmu_events_group,
NULL,
};
-static struct attribute *rapl_events_hsw_attr[] = {
+static struct attribute *rapl_events_cores[] = {
EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
- EVENT_PTR(rapl_ram),
-
EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
- EVENT_PTR(rapl_ram_unit),
-
EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
- EVENT_PTR(rapl_ram_scale),
NULL,
};
-static struct attribute *rapl_events_skl_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
- EVENT_PTR(rapl_ram),
- EVENT_PTR(rapl_psys),
+static struct attribute_group rapl_events_cores_group = {
+ .name = "events",
+ .attrs = rapl_events_cores,
+};
- EVENT_PTR(rapl_cores_unit),
+static struct attribute *rapl_events_pkg[] = {
+ EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
- EVENT_PTR(rapl_ram_unit),
- EVENT_PTR(rapl_psys_unit),
-
- EVENT_PTR(rapl_cores_scale),
EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
- EVENT_PTR(rapl_ram_scale),
- EVENT_PTR(rapl_psys_scale),
NULL,
};
-static struct attribute *rapl_events_knl_attr[] = {
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_ram),
+static struct attribute_group rapl_events_pkg_group = {
+ .name = "events",
+ .attrs = rapl_events_pkg,
+};
- EVENT_PTR(rapl_pkg_unit),
+static struct attribute *rapl_events_ram[] = {
+ EVENT_PTR(rapl_ram),
EVENT_PTR(rapl_ram_unit),
-
- EVENT_PTR(rapl_pkg_scale),
EVENT_PTR(rapl_ram_scale),
NULL,
};
-static struct attribute_group rapl_pmu_events_group = {
- .name = "events",
- .attrs = NULL, /* patched at runtime */
+static struct attribute_group rapl_events_ram_group = {
+ .name = "events",
+ .attrs = rapl_events_ram,
};
-DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
-static struct attribute *rapl_formats_attr[] = {
- &format_attr_event.attr,
+static struct attribute *rapl_events_gpu[] = {
+ EVENT_PTR(rapl_gpu),
+ EVENT_PTR(rapl_gpu_unit),
+ EVENT_PTR(rapl_gpu_scale),
NULL,
};
-static struct attribute_group rapl_pmu_format_group = {
- .name = "format",
- .attrs = rapl_formats_attr,
+static struct attribute_group rapl_events_gpu_group = {
+ .name = "events",
+ .attrs = rapl_events_gpu,
};
-static const struct attribute_group *rapl_attr_groups[] = {
- &rapl_pmu_attr_group,
- &rapl_pmu_format_group,
- &rapl_pmu_events_group,
+static struct attribute *rapl_events_psys[] = {
+ EVENT_PTR(rapl_psys),
+ EVENT_PTR(rapl_psys_unit),
+ EVENT_PTR(rapl_psys_scale),
NULL,
};
+static struct attribute_group rapl_events_psys_group = {
+ .name = "events",
+ .attrs = rapl_events_psys,
+};
+
+static bool test_msr(int idx, void *data)
+{
+ return test_bit(idx, (unsigned long *) data);
+}
+
+static struct perf_msr rapl_msrs[] = {
+ [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr },
+ [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr },
+ [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr },
+ [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr },
+ [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr },
+};
+
static int rapl_cpu_offline(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
@@ -572,7 +532,7 @@ 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 +559,14 @@ 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;
@@ -633,7 +593,7 @@ static int rapl_check_hw_unit(bool apply_quirk)
* of 2. Datasheet, September 2014, Reference Number: 330784-001 "
*/
if (apply_quirk)
- rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16;
+ rapl_hw_unit[PERF_RAPL_RAM] = 16;
/*
* Calculate the timer rate:
@@ -669,23 +629,33 @@ 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);
}
+const struct attribute_group *rapl_attr_update[] = {
+ &rapl_events_cores_group,
+ &rapl_events_pkg_group,
+ &rapl_events_ram_group,
+ &rapl_events_gpu_group,
+ &rapl_events_gpu_group,
+ NULL,
+};
+
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.attr_update = rapl_attr_update;
rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
rapl_pmus->pmu.event_init = rapl_pmu_event_init;
rapl_pmus->pmu.add = rapl_pmu_event_add;
@@ -701,105 +671,96 @@ static int __init init_rapl_pmus(void)
#define X86_RAPL_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
-struct intel_rapl_init_fun {
- bool apply_quirk;
- int cntr_mask;
- struct attribute **attrs;
-};
-
-static const struct intel_rapl_init_fun snb_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_CLN,
- .attrs = rapl_events_cln_attr,
+static struct rapl_model model_snb = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun hsx_rapl_init __initconst = {
- .apply_quirk = true,
- .cntr_mask = RAPL_IDX_SRV,
- .attrs = rapl_events_srv_attr,
+static struct rapl_model model_snbep = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun hsw_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_HSW,
- .attrs = rapl_events_hsw_attr,
+static struct rapl_model model_hsw = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun snbep_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_SRV,
- .attrs = rapl_events_srv_attr,
+static struct rapl_model model_hsx = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
};
-static const struct intel_rapl_init_fun knl_rapl_init __initconst = {
- .apply_quirk = true,
- .cntr_mask = RAPL_IDX_KNL,
- .attrs = rapl_events_knl_attr,
+static struct rapl_model model_knl = {
+ .events = BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
};
-static const struct intel_rapl_init_fun skl_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_SKL_CLN,
- .attrs = rapl_events_skl_attr,
+static struct rapl_model model_skl = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1) |
+ BIT(PERF_RAPL_PSYS),
+ .apply_quirk = false,
};
-static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, snb_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, snb_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, skl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init),
+static const struct x86_cpu_id rapl_model_match[] __initconst = {
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, model_skl),
{},
};
-MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match);
+MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
static int __init rapl_pmu_init(void)
{
const struct x86_cpu_id *id;
- struct intel_rapl_init_fun *rapl_init;
- bool apply_quirk;
+ struct rapl_model *rm;
int ret;
- id = x86_match_cpu(rapl_cpu_match);
+ id = x86_match_cpu(rapl_model_match);
if (!id)
return -ENODEV;
- rapl_init = (struct intel_rapl_init_fun *)id->driver_data;
- apply_quirk = rapl_init->apply_quirk;
- rapl_cntr_mask = rapl_init->cntr_mask;
- rapl_pmu_events_group.attrs = rapl_init->attrs;
+ rm = (struct rapl_model *) id->driver_data;
+ rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
+ false, (void *) &rm->events);
- ret = rapl_check_hw_unit(apply_quirk);
+ ret = rapl_check_hw_unit(rm->apply_quirk);
if (ret)
return ret;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 9e3fbd47cb56..3694a5d0703d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -8,6 +8,7 @@
static struct intel_uncore_type *empty_uncore[] = { NULL, };
struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
+struct intel_uncore_type **uncore_mmio_uncores = empty_uncore;
static bool pcidrv_registered;
struct pci_driver *uncore_pci_driver;
@@ -15,7 +16,7 @@ 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;
@@ -28,7 +29,7 @@ struct event_constraint uncore_constraint_empty =
MODULE_LICENSE("GPL");
-static int uncore_pcibus_to_physid(struct pci_bus *bus)
+int uncore_pcibus_to_physid(struct pci_bus *bus)
{
struct pci2phy_map *map;
int phys_id = -1;
@@ -101,13 +102,13 @@ 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)
@@ -119,6 +120,21 @@ u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *eve
return count;
}
+void uncore_mmio_exit_box(struct intel_uncore_box *box)
+{
+ if (box->io_addr)
+ iounmap(box->io_addr);
+}
+
+u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ if (!box->io_addr)
+ return 0;
+
+ return readq(box->io_addr + event->hw.event_base);
+}
+
/*
* generic get constraint function for shared match/mask registers.
*/
@@ -312,7 +328,7 @@ 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 +843,10 @@ 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 +883,7 @@ 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 +953,21 @@ 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 +1006,7 @@ 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 +1020,13 @@ 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 +1034,7 @@ 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 +1045,17 @@ 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 +1068,7 @@ 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 +1080,7 @@ 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 +1127,11 @@ 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;
@@ -1141,18 +1159,33 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
}
-static int uncore_event_cpu_offline(unsigned int cpu)
+static void uncore_box_unref(struct intel_uncore_type **types, int id)
{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
- int i, pkg, target;
+ int i;
+
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ box = pmu->boxes[id];
+ if (box && atomic_dec_return(&box->refcnt) == 0)
+ uncore_box_exit(box);
+ }
+ }
+}
+
+static int uncore_event_cpu_offline(unsigned int cpu)
+{
+ int 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)
@@ -1161,25 +1194,19 @@ static int uncore_event_cpu_offline(unsigned int cpu)
target = -1;
uncore_change_context(uncore_msr_uncores, cpu, target);
+ uncore_change_context(uncore_mmio_uncores, cpu, target);
uncore_change_context(uncore_pci_uncores, cpu, target);
unref:
/* Clear the references */
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (box && atomic_dec_return(&box->refcnt) == 0)
- uncore_box_exit(box);
- }
- }
+ die = topology_logical_die_id(cpu);
+ uncore_box_unref(uncore_msr_uncores, die);
+ uncore_box_unref(uncore_mmio_uncores, die);
return 0;
}
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 +1219,20 @@ 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;
@@ -1217,15 +1244,15 @@ cleanup:
return -ENOMEM;
}
-static int uncore_event_cpu_online(unsigned int cpu)
+static int uncore_box_ref(struct intel_uncore_type **types,
+ int id, unsigned int cpu)
{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
- int i, ret, pkg, target;
+ int i, ret;
- pkg = topology_logical_package_id(cpu);
- ret = allocate_boxes(types, pkg, cpu);
+ ret = allocate_boxes(types, id, cpu);
if (ret)
return ret;
@@ -1233,23 +1260,38 @@ 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[id];
if (box && atomic_inc_return(&box->refcnt) == 1)
uncore_box_init(box);
}
}
+ return 0;
+}
+
+static int uncore_event_cpu_online(unsigned int cpu)
+{
+ int die, target, msr_ret, mmio_ret;
+
+ die = topology_logical_die_id(cpu);
+ msr_ret = uncore_box_ref(uncore_msr_uncores, die, cpu);
+ mmio_ret = uncore_box_ref(uncore_mmio_uncores, die, cpu);
+ if (msr_ret && mmio_ret)
+ return -ENOMEM;
/*
* 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;
cpumask_set_cpu(cpu, &uncore_cpu_mask);
- uncore_change_context(uncore_msr_uncores, -1, cpu);
+ if (!msr_ret)
+ uncore_change_context(uncore_msr_uncores, -1, cpu);
+ if (!mmio_ret)
+ uncore_change_context(uncore_mmio_uncores, -1, cpu);
uncore_change_context(uncore_pci_uncores, -1, cpu);
return 0;
}
@@ -1297,12 +1339,35 @@ err:
return ret;
}
+static int __init uncore_mmio_init(void)
+{
+ struct intel_uncore_type **types = uncore_mmio_uncores;
+ int ret;
+
+ ret = uncore_types_init(types, true);
+ if (ret)
+ goto err;
+
+ for (; *types; types++) {
+ ret = type_pmu_register(*types);
+ if (ret)
+ goto err;
+ }
+ return 0;
+err:
+ uncore_types_exit(uncore_mmio_uncores);
+ uncore_mmio_uncores = empty_uncore;
+ return ret;
+}
+
+
#define X86_UNCORE_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
struct intel_uncore_init_fun {
void (*cpu_init)(void);
int (*pci_init)(void);
+ void (*mmio_init)(void);
};
static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
@@ -1373,6 +1438,12 @@ static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
.pci_init = skl_uncore_pci_init,
};
+static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
+ .cpu_init = snr_uncore_cpu_init,
+ .pci_init = snr_uncore_pci_init,
+ .mmio_init = snr_uncore_mmio_init,
+};
+
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
@@ -1400,6 +1471,9 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_X, snr_uncore_init),
{},
};
@@ -1409,7 +1483,7 @@ static int __init intel_uncore_init(void)
{
const struct x86_cpu_id *id;
struct intel_uncore_init_fun *uncore_init;
- int pret = 0, cret = 0, ret;
+ int pret = 0, cret = 0, mret = 0, ret;
id = x86_match_cpu(intel_uncore_match);
if (!id)
@@ -1418,7 +1492,7 @@ 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) {
@@ -1432,7 +1506,12 @@ static int __init intel_uncore_init(void)
cret = uncore_cpu_init();
}
- if (cret && pret)
+ if (uncore_init->mmio_init) {
+ uncore_init->mmio_init();
+ mret = uncore_mmio_init();
+ }
+
+ if (cret && pret && mret)
return -ENODEV;
/* Install hotplug callbacks to setup the targets for each package */
@@ -1446,6 +1525,7 @@ static int __init intel_uncore_init(void)
err:
uncore_types_exit(uncore_msr_uncores);
+ uncore_types_exit(uncore_mmio_uncores);
uncore_pci_exit();
return ret;
}
@@ -1455,6 +1535,7 @@ static void __exit intel_uncore_exit(void)
{
cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
uncore_types_exit(uncore_msr_uncores);
+ uncore_types_exit(uncore_mmio_uncores);
uncore_pci_exit();
}
module_exit(intel_uncore_exit);
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 79eb2e21e4f0..f36f7bebbc1b 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -2,6 +2,7 @@
#include <linux/slab.h>
#include <linux/pci.h>
#include <asm/apicdef.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/perf_event.h>
#include "../perf_event.h"
@@ -56,7 +57,10 @@ struct intel_uncore_type {
unsigned fixed_ctr;
unsigned fixed_ctl;
unsigned box_ctl;
- unsigned msr_offset;
+ union {
+ unsigned msr_offset;
+ unsigned mmio_offset;
+ };
unsigned num_shared_regs:8;
unsigned single_fixed:1;
unsigned pair_ctr_ctl:1;
@@ -108,7 +112,7 @@ 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 */
@@ -125,7 +129,7 @@ struct intel_uncore_box {
struct hrtimer hrtimer;
struct list_head list;
struct list_head active_list;
- void *io_addr;
+ void __iomem *io_addr;
struct intel_uncore_extra_reg shared_regs[0];
};
@@ -159,6 +163,7 @@ struct pci2phy_map {
};
struct pci2phy_map *__find_pci2phy_map(int segment);
+int uncore_pcibus_to_physid(struct pci_bus *bus);
ssize_t uncore_event_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf);
@@ -190,6 +195,13 @@ static inline bool uncore_pmc_freerunning(int idx)
return idx == UNCORE_PMC_IDX_FREERUNNING;
}
+static inline
+unsigned int uncore_mmio_box_ctl(struct intel_uncore_box *box)
+{
+ return box->pmu->type->box_ctl +
+ box->pmu->type->mmio_offset * box->pmu->pmu_idx;
+}
+
static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
{
return box->pmu->type->box_ctl;
@@ -330,7 +342,7 @@ unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
static inline
unsigned uncore_fixed_ctl(struct intel_uncore_box *box)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_fixed_ctl(box);
else
return uncore_msr_fixed_ctl(box);
@@ -339,7 +351,7 @@ unsigned uncore_fixed_ctl(struct intel_uncore_box *box)
static inline
unsigned uncore_fixed_ctr(struct intel_uncore_box *box)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_fixed_ctr(box);
else
return uncore_msr_fixed_ctr(box);
@@ -348,7 +360,7 @@ unsigned uncore_fixed_ctr(struct intel_uncore_box *box)
static inline
unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_event_ctl(box, idx);
else
return uncore_msr_event_ctl(box, idx);
@@ -357,7 +369,7 @@ unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx)
static inline
unsigned uncore_perf_ctr(struct intel_uncore_box *box, int idx)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_perf_ctr(box, idx);
else
return uncore_msr_perf_ctr(box, idx);
@@ -419,6 +431,16 @@ static inline bool is_freerunning_event(struct perf_event *event)
(((cfg >> 8) & 0xff) >= UNCORE_FREERUNNING_UMASK_START);
}
+/* Check and reject invalid config */
+static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ if (is_freerunning_event(event))
+ return 0;
+
+ return -EINVAL;
+}
+
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
@@ -467,7 +489,7 @@ 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)
@@ -482,6 +504,9 @@ static inline struct intel_uncore_box *uncore_event_to_box(struct perf_event *ev
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_mmio_exit_box(struct intel_uncore_box *box);
+u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event);
void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_event_start(struct perf_event *event, int flags);
@@ -497,6 +522,7 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx);
extern struct intel_uncore_type **uncore_msr_uncores;
extern struct intel_uncore_type **uncore_pci_uncores;
+extern struct intel_uncore_type **uncore_mmio_uncores;
extern struct pci_driver *uncore_pci_driver;
extern raw_spinlock_t pci2phy_map_lock;
extern struct list_head pci2phy_map_head;
@@ -528,6 +554,9 @@ int knl_uncore_pci_init(void);
void knl_uncore_cpu_init(void);
int skx_uncore_pci_init(void);
void skx_uncore_cpu_init(void);
+int snr_uncore_pci_init(void);
+void snr_uncore_cpu_init(void);
+void snr_uncore_mmio_init(void);
/* uncore_nhmex.c */
void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index f8431819b3e1..dbaa1b088a30 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -3,27 +3,29 @@
#include "uncore.h"
/* Uncore IMC PCI IDs */
-#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100
-#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154
-#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
-#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
-#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
-#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
-#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
-#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
-#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
-#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
-#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
-#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
-#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
-#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
-#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
-#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
-#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
-#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
-#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
-#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
-#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
+#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
+#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
+#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
+#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
+#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
+#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
+#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
+#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
+#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
+#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
+#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
+#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
+#define PCI_DEVICE_ID_INTEL_KBL_HQ_IMC 0x5910
+#define PCI_DEVICE_ID_INTEL_KBL_WQ_IMC 0x5918
+#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
+#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
+#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
+#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC 0x3e0f
#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC 0x3e1f
#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC 0x3ec2
@@ -34,9 +36,15 @@
#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
+#define PCI_DEVICE_ID_INTEL_AML_YD_IMC 0x590c
+#define PCI_DEVICE_ID_INTEL_AML_YQ_IMC 0x590d
+#define PCI_DEVICE_ID_INTEL_WHL_UQ_IMC 0x3ed0
+#define PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC 0x3e34
+#define PCI_DEVICE_ID_INTEL_WHL_UD_IMC 0x3e35
#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
+
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00
@@ -420,11 +428,6 @@ static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
}
-static void snb_uncore_imc_exit_box(struct intel_uncore_box *box)
-{
- iounmap(box->io_addr);
-}
-
static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
{}
@@ -437,13 +440,6 @@ static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct per
static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
{}
-static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
-}
-
/*
* Keep the custom event_init() function compatible with old event
* encoding for free running counters.
@@ -570,13 +566,13 @@ static struct pmu snb_uncore_imc_pmu = {
static struct intel_uncore_ops snb_uncore_imc_ops = {
.init_box = snb_uncore_imc_init_box,
- .exit_box = snb_uncore_imc_exit_box,
+ .exit_box = uncore_mmio_exit_box,
.enable_box = snb_uncore_imc_enable_box,
.disable_box = snb_uncore_imc_disable_box,
.disable_event = snb_uncore_imc_disable_event,
.enable_event = snb_uncore_imc_enable_event,
.hw_config = snb_uncore_imc_hw_config,
- .read_counter = snb_uncore_imc_read_counter,
+ .read_counter = uncore_mmio_read_counter,
};
static struct intel_uncore_type snb_uncore_imc = {
@@ -682,6 +678,14 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_HQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_WQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
@@ -737,6 +741,26 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
{ /* end: all zeroes */ },
};
@@ -807,6 +831,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */
IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Dual Core */
IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Quad Core */
+ IMC_DEV(KBL_HQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core H Quad Core */
+ IMC_DEV(KBL_WQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S 4 cores Work Station */
IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 2 Cores */
IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 4 Cores */
IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 4 Cores */
@@ -821,6 +847,11 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
+ IMC_DEV(AML_YD_IMC, &skl_uncore_pci_driver), /* 8th Gen Core Y Mobile Dual Core */
+ IMC_DEV(AML_YQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core Y Mobile Quad Core */
+ IMC_DEV(WHL_UQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Quad Core */
+ IMC_DEV(WHL_4_UQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Quad Core */
+ IMC_DEV(WHL_UD_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Dual Core */
IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
{ /* end marker */ }
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b10e04387f38..b10a5ec79e48 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -324,12 +324,77 @@
#define SKX_M2M_PCI_PMON_CTR0 0x200
#define SKX_M2M_PCI_PMON_BOX_CTL 0x258
+/* SNR Ubox */
+#define SNR_U_MSR_PMON_CTR0 0x1f98
+#define SNR_U_MSR_PMON_CTL0 0x1f91
+#define SNR_U_MSR_PMON_UCLK_FIXED_CTL 0x1f93
+#define SNR_U_MSR_PMON_UCLK_FIXED_CTR 0x1f94
+
+/* SNR CHA */
+#define SNR_CHA_RAW_EVENT_MASK_EXT 0x3ffffff
+#define SNR_CHA_MSR_PMON_CTL0 0x1c01
+#define SNR_CHA_MSR_PMON_CTR0 0x1c08
+#define SNR_CHA_MSR_PMON_BOX_CTL 0x1c00
+#define SNR_C0_MSR_PMON_BOX_FILTER0 0x1c05
+
+
+/* SNR IIO */
+#define SNR_IIO_MSR_PMON_CTL0 0x1e08
+#define SNR_IIO_MSR_PMON_CTR0 0x1e01
+#define SNR_IIO_MSR_PMON_BOX_CTL 0x1e00
+#define SNR_IIO_MSR_OFFSET 0x10
+#define SNR_IIO_PMON_RAW_EVENT_MASK_EXT 0x7ffff
+
+/* SNR IRP */
+#define SNR_IRP0_MSR_PMON_CTL0 0x1ea8
+#define SNR_IRP0_MSR_PMON_CTR0 0x1ea1
+#define SNR_IRP0_MSR_PMON_BOX_CTL 0x1ea0
+#define SNR_IRP_MSR_OFFSET 0x10
+
+/* SNR M2PCIE */
+#define SNR_M2PCIE_MSR_PMON_CTL0 0x1e58
+#define SNR_M2PCIE_MSR_PMON_CTR0 0x1e51
+#define SNR_M2PCIE_MSR_PMON_BOX_CTL 0x1e50
+#define SNR_M2PCIE_MSR_OFFSET 0x10
+
+/* SNR PCU */
+#define SNR_PCU_MSR_PMON_CTL0 0x1ef1
+#define SNR_PCU_MSR_PMON_CTR0 0x1ef8
+#define SNR_PCU_MSR_PMON_BOX_CTL 0x1ef0
+#define SNR_PCU_MSR_PMON_BOX_FILTER 0x1efc
+
+/* SNR M2M */
+#define SNR_M2M_PCI_PMON_CTL0 0x468
+#define SNR_M2M_PCI_PMON_CTR0 0x440
+#define SNR_M2M_PCI_PMON_BOX_CTL 0x438
+#define SNR_M2M_PCI_PMON_UMASK_EXT 0xff
+
+/* SNR PCIE3 */
+#define SNR_PCIE3_PCI_PMON_CTL0 0x508
+#define SNR_PCIE3_PCI_PMON_CTR0 0x4e8
+#define SNR_PCIE3_PCI_PMON_BOX_CTL 0x4e4
+
+/* SNR IMC */
+#define SNR_IMC_MMIO_PMON_FIXED_CTL 0x54
+#define SNR_IMC_MMIO_PMON_FIXED_CTR 0x38
+#define SNR_IMC_MMIO_PMON_CTL0 0x40
+#define SNR_IMC_MMIO_PMON_CTR0 0x8
+#define SNR_IMC_MMIO_PMON_BOX_CTL 0x22800
+#define SNR_IMC_MMIO_OFFSET 0x4000
+#define SNR_IMC_MMIO_SIZE 0x4000
+#define SNR_IMC_MMIO_BASE_OFFSET 0xd0
+#define SNR_IMC_MMIO_BASE_MASK 0x1FFFFFFF
+#define SNR_IMC_MMIO_MEM0_OFFSET 0xd8
+#define SNR_IMC_MMIO_MEM0_MASK 0x7FF
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39");
DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@@ -343,11 +408,14 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31");
DEFINE_UNCORE_FORMAT_ATTR(ch_mask, ch_mask, "config:36-43");
+DEFINE_UNCORE_FORMAT_ATTR(ch_mask2, ch_mask, "config:36-47");
DEFINE_UNCORE_FORMAT_ATTR(fc_mask, fc_mask, "config:44-46");
+DEFINE_UNCORE_FORMAT_ATTR(fc_mask2, fc_mask, "config:48-50");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid5, filter_tid, "config1:0-9");
DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
@@ -1058,8 +1126,8 @@ 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,
@@ -3585,6 +3653,7 @@ static struct uncore_event_desc skx_uncore_iio_freerunning_events[] = {
static struct intel_uncore_ops skx_uncore_iio_freerunning_ops = {
.read_counter = uncore_msr_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
};
static struct attribute *skx_uncore_iio_freerunning_formats_attr[] = {
@@ -3967,3 +4036,535 @@ int skx_uncore_pci_init(void)
}
/* end of SKX uncore support */
+
+/* SNR uncore support */
+
+static struct intel_uncore_type snr_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNR_U_MSR_PMON_CTR0,
+ .event_ctl = SNR_U_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = SNR_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = SNR_U_MSR_PMON_UCLK_FIXED_CTL,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static struct attribute *snr_uncore_cha_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask_ext2.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid5.attr,
+ NULL,
+};
+static const struct attribute_group snr_uncore_chabox_format_group = {
+ .name = "format",
+ .attrs = snr_uncore_cha_formats_attr,
+};
+
+static int snr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+
+ reg1->reg = SNR_C0_MSR_PMON_BOX_FILTER0 +
+ box->pmu->type->msr_offset * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 & SKX_CHA_MSR_PMON_BOX_FILTER_TID;
+ reg1->idx = 0;
+
+ return 0;
+}
+
+static void snr_cha_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE)
+ wrmsrl(reg1->reg, reg1->config);
+
+ wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snr_uncore_chabox_ops = {
+ .init_box = ivbep_uncore_msr_init_box,
+ .disable_box = snbep_uncore_msr_disable_box,
+ .enable_box = snbep_uncore_msr_enable_box,
+ .disable_event = snbep_uncore_msr_disable_event,
+ .enable_event = snr_cha_enable_event,
+ .read_counter = uncore_msr_read_counter,
+ .hw_config = snr_cha_hw_config,
+};
+
+static struct intel_uncore_type snr_uncore_chabox = {
+ .name = "cha",
+ .num_counters = 4,
+ .num_boxes = 6,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_CHA_MSR_PMON_CTL0,
+ .perf_ctr = SNR_CHA_MSR_PMON_CTR0,
+ .box_ctl = SNR_CHA_MSR_PMON_BOX_CTL,
+ .msr_offset = HSWEP_CBO_MSR_OFFSET,
+ .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_CHA_RAW_EVENT_MASK_EXT,
+ .ops = &snr_uncore_chabox_ops,
+ .format_group = &snr_uncore_chabox_format_group,
+};
+
+static struct attribute *snr_uncore_iio_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh9.attr,
+ &format_attr_ch_mask2.attr,
+ &format_attr_fc_mask2.attr,
+ NULL,
+};
+
+static const struct attribute_group snr_uncore_iio_format_group = {
+ .name = "format",
+ .attrs = snr_uncore_iio_formats_attr,
+};
+
+static struct intel_uncore_type snr_uncore_iio = {
+ .name = "iio",
+ .num_counters = 4,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_IIO_MSR_PMON_CTL0,
+ .perf_ctr = SNR_IIO_MSR_PMON_CTR0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT,
+ .box_ctl = SNR_IIO_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_IIO_MSR_OFFSET,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &snr_uncore_iio_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_irp = {
+ .name = "irp",
+ .num_counters = 2,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_IRP0_MSR_PMON_CTL0,
+ .perf_ctr = SNR_IRP0_MSR_PMON_CTR0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_IRP0_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_IRP_MSR_OFFSET,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_m2pcie = {
+ .name = "m2pcie",
+ .num_counters = 4,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_M2PCIE_MSR_PMON_CTL0,
+ .perf_ctr = SNR_M2PCIE_MSR_PMON_CTR0,
+ .box_ctl = SNR_M2PCIE_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_M2PCIE_MSR_OFFSET,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static int snr_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+ if (ev_sel >= 0xb && ev_sel <= 0xe) {
+ reg1->reg = SNR_PCU_MSR_PMON_BOX_FILTER;
+ reg1->idx = ev_sel - 0xb;
+ reg1->config = event->attr.config1 & (0xff << reg1->idx);
+ }
+ return 0;
+}
+
+static struct intel_uncore_ops snr_uncore_pcu_ops = {
+ IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = snr_pcu_hw_config,
+ .get_constraint = snbep_pcu_get_constraint,
+ .put_constraint = snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type snr_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_PCU_MSR_PMON_CTR0,
+ .event_ctl = SNR_PCU_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snr_uncore_pcu_ops,
+ .format_group = &skx_uncore_pcu_format_group,
+};
+
+enum perf_uncore_snr_iio_freerunning_type_id {
+ SNR_IIO_MSR_IOCLK,
+ SNR_IIO_MSR_BW_IN,
+
+ SNR_IIO_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snr_iio_freerunning[] = {
+ [SNR_IIO_MSR_IOCLK] = { 0x1eac, 0x1, 0x10, 1, 48 },
+ [SNR_IIO_MSR_BW_IN] = { 0x1f00, 0x1, 0x10, 8, 48 },
+};
+
+static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = {
+ /* Free-Running IIO CLOCKS Counter */
+ INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
+ /* Free-Running IIO BANDWIDTH IN Counters */
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type snr_uncore_iio_free_running = {
+ .name = "iio_free_running",
+ .num_counters = 9,
+ .num_boxes = 5,
+ .num_freerunning_types = SNR_IIO_FREERUNNING_TYPE_MAX,
+ .freerunning = snr_iio_freerunning,
+ .ops = &skx_uncore_iio_freerunning_ops,
+ .event_descs = snr_uncore_iio_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
+static struct intel_uncore_type *snr_msr_uncores[] = {
+ &snr_uncore_ubox,
+ &snr_uncore_chabox,
+ &snr_uncore_iio,
+ &snr_uncore_irp,
+ &snr_uncore_m2pcie,
+ &snr_uncore_pcu,
+ &snr_uncore_iio_free_running,
+ NULL,
+};
+
+void snr_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = snr_msr_uncores;
+}
+
+static void snr_m2m_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+
+ __set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+ pci_write_config_dword(pdev, box_ctl, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static struct intel_uncore_ops snr_m2m_uncore_pci_ops = {
+ .init_box = snr_m2m_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_uncore_pci_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+};
+
+static struct attribute *snr_m2m_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask_ext3.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static const struct attribute_group snr_m2m_uncore_format_group = {
+ .name = "format",
+ .attrs = snr_m2m_uncore_formats_attr,
+};
+
+static struct intel_uncore_type snr_uncore_m2m = {
+ .name = "m2m",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_M2M_PCI_PMON_CTR0,
+ .event_ctl = SNR_M2M_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_M2M_PCI_PMON_UMASK_EXT,
+ .box_ctl = SNR_M2M_PCI_PMON_BOX_CTL,
+ .ops = &snr_m2m_uncore_pci_ops,
+ .format_group = &snr_m2m_uncore_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_pcie3 = {
+ .name = "pcie3",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_PCIE3_PCI_PMON_CTR0,
+ .event_ctl = SNR_PCIE3_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_PCIE3_PCI_PMON_BOX_CTL,
+ .ops = &ivbep_uncore_pci_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+enum {
+ SNR_PCI_UNCORE_M2M,
+ SNR_PCI_UNCORE_PCIE3,
+};
+
+static struct intel_uncore_type *snr_pci_uncores[] = {
+ [SNR_PCI_UNCORE_M2M] = &snr_uncore_m2m,
+ [SNR_PCI_UNCORE_PCIE3] = &snr_uncore_pcie3,
+ NULL,
+};
+
+static const struct pci_device_id snr_uncore_pci_ids[] = {
+ { /* M2M */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0),
+ },
+ { /* PCIe3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0),
+ },
+ { /* end: all zeroes */ }
+};
+
+static struct pci_driver snr_uncore_pci_driver = {
+ .name = "snr_uncore",
+ .id_table = snr_uncore_pci_ids,
+};
+
+int snr_uncore_pci_init(void)
+{
+ /* SNR UBOX DID */
+ int ret = snbep_pci2phy_map_init(0x3460, SKX_CPUNODEID,
+ SKX_GIDNIDMAP, true);
+
+ if (ret)
+ return ret;
+
+ uncore_pci_uncores = snr_pci_uncores;
+ uncore_pci_driver = &snr_uncore_pci_driver;
+ return 0;
+}
+
+static struct pci_dev *snr_uncore_get_mc_dev(int id)
+{
+ struct pci_dev *mc_dev = NULL;
+ int phys_id, pkg;
+
+ while (1) {
+ mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3451, mc_dev);
+ if (!mc_dev)
+ break;
+ phys_id = uncore_pcibus_to_physid(mc_dev->bus);
+ if (phys_id < 0)
+ continue;
+ pkg = topology_phys_to_logical_pkg(phys_id);
+ if (pkg < 0)
+ continue;
+ else if (pkg == id)
+ break;
+ }
+ return mc_dev;
+}
+
+static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid);
+ unsigned int box_ctl = uncore_mmio_box_ctl(box);
+ resource_size_t addr;
+ u32 pci_dword;
+
+ if (!pdev)
+ return;
+
+ pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword);
+ addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
+
+ pci_read_config_dword(pdev, SNR_IMC_MMIO_MEM0_OFFSET, &pci_dword);
+ addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;
+
+ addr += box_ctl;
+
+ box->io_addr = ioremap(addr, SNR_IMC_MMIO_SIZE);
+ if (!box->io_addr)
+ return;
+
+ writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
+}
+
+static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box)
+{
+ u32 config;
+
+ if (!box->io_addr)
+ return;
+
+ config = readl(box->io_addr);
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ writel(config, box->io_addr);
+}
+
+static void snr_uncore_mmio_enable_box(struct intel_uncore_box *box)
+{
+ u32 config;
+
+ if (!box->io_addr)
+ return;
+
+ config = readl(box->io_addr);
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ writel(config, box->io_addr);
+}
+
+static void snr_uncore_mmio_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box->io_addr)
+ return;
+
+ writel(hwc->config | SNBEP_PMON_CTL_EN,
+ box->io_addr + hwc->config_base);
+}
+
+static void snr_uncore_mmio_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box->io_addr)
+ return;
+
+ writel(hwc->config, box->io_addr + hwc->config_base);
+}
+
+static struct intel_uncore_ops snr_uncore_mmio_ops = {
+ .init_box = snr_uncore_mmio_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .disable_box = snr_uncore_mmio_disable_box,
+ .enable_box = snr_uncore_mmio_enable_box,
+ .disable_event = snr_uncore_mmio_disable_event,
+ .enable_event = snr_uncore_mmio_enable_event,
+ .read_counter = uncore_mmio_read_counter,
+};
+
+static struct uncore_event_desc snr_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x30"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type snr_uncore_imc = {
+ .name = "imc",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR,
+ .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL,
+ .event_descs = snr_uncore_imc_events,
+ .perf_ctr = SNR_IMC_MMIO_PMON_CTR0,
+ .event_ctl = SNR_IMC_MMIO_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_IMC_MMIO_PMON_BOX_CTL,
+ .mmio_offset = SNR_IMC_MMIO_OFFSET,
+ .ops = &snr_uncore_mmio_ops,
+ .format_group = &skx_uncore_format_group,
+};
+
+enum perf_uncore_snr_imc_freerunning_type_id {
+ SNR_IMC_DCLK,
+ SNR_IMC_DDR,
+
+ SNR_IMC_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snr_imc_freerunning[] = {
+ [SNR_IMC_DCLK] = { 0x22b0, 0x0, 0, 1, 48 },
+ [SNR_IMC_DDR] = { 0x2290, 0x8, 0, 2, 48 },
+};
+
+static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = {
+ INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"),
+
+ INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"),
+ INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"),
+};
+
+static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = {
+ .init_box = snr_uncore_mmio_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .read_counter = uncore_mmio_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
+};
+
+static struct intel_uncore_type snr_uncore_imc_free_running = {
+ .name = "imc_free_running",
+ .num_counters = 3,
+ .num_boxes = 1,
+ .num_freerunning_types = SNR_IMC_FREERUNNING_TYPE_MAX,
+ .freerunning = snr_imc_freerunning,
+ .ops = &snr_uncore_imc_freerunning_ops,
+ .event_descs = snr_uncore_imc_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
+static struct intel_uncore_type *snr_mmio_uncores[] = {
+ &snr_uncore_imc,
+ &snr_uncore_imc_free_running,
+ NULL,
+};
+
+void snr_uncore_mmio_init(void)
+{
+ uncore_mmio_uncores = snr_mmio_uncores;
+}
+
+/* end of SNR uncore support */
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index f3f4c2263501..9431447541e9 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -1,7 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
+#include <linux/sysfs.h>
#include <linux/nospec.h>
#include <asm/intel-family.h>
+#include "probe.h"
enum perf_msr_id {
PERF_MSR_TSC = 0,
@@ -12,32 +14,30 @@ enum perf_msr_id {
PERF_MSR_PTSC = 5,
PERF_MSR_IRPERF = 6,
PERF_MSR_THERM = 7,
- PERF_MSR_THERM_SNAP = 8,
- PERF_MSR_THERM_UNIT = 9,
PERF_MSR_EVENT_MAX,
};
-static bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_APERFMPERF);
}
-static bool test_ptsc(int idx)
+static bool test_ptsc(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_PTSC);
}
-static bool test_irperf(int idx)
+static bool test_irperf(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_IRPERF);
}
-static bool test_therm_status(int idx)
+static bool test_therm_status(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_DTHERM);
}
-static bool test_intel(int idx)
+static bool test_intel(int idx, void *data)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
boot_cpu_data.x86 != 6)
@@ -98,37 +98,51 @@ static bool test_intel(int idx)
return false;
}
-struct perf_msr {
- u64 msr;
- struct perf_pmu_events_attr *attr;
- bool (*test)(int idx);
+PMU_EVENT_ATTR_STRING(tsc, attr_tsc, "event=0x00" );
+PMU_EVENT_ATTR_STRING(aperf, attr_aperf, "event=0x01" );
+PMU_EVENT_ATTR_STRING(mperf, attr_mperf, "event=0x02" );
+PMU_EVENT_ATTR_STRING(pperf, attr_pperf, "event=0x03" );
+PMU_EVENT_ATTR_STRING(smi, attr_smi, "event=0x04" );
+PMU_EVENT_ATTR_STRING(ptsc, attr_ptsc, "event=0x05" );
+PMU_EVENT_ATTR_STRING(irperf, attr_irperf, "event=0x06" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin, attr_therm, "event=0x07" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, attr_therm_snap, "1" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, attr_therm_unit, "C" );
+
+static unsigned long msr_mask;
+
+PMU_EVENT_GROUP(events, aperf);
+PMU_EVENT_GROUP(events, mperf);
+PMU_EVENT_GROUP(events, pperf);
+PMU_EVENT_GROUP(events, smi);
+PMU_EVENT_GROUP(events, ptsc);
+PMU_EVENT_GROUP(events, irperf);
+
+static struct attribute *attrs_therm[] = {
+ &attr_therm.attr.attr,
+ &attr_therm_snap.attr.attr,
+ &attr_therm_unit.attr.attr,
+ NULL,
};
-PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00" );
-PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01" );
-PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02" );
-PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03" );
-PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04" );
-PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05" );
-PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin, evattr_therm, "event=0x07" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, evattr_therm_snap, "1" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, evattr_therm_unit, "C" );
+static struct attribute_group group_therm = {
+ .name = "events",
+ .attrs = attrs_therm,
+};
static struct perf_msr msr[] = {
- [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, },
- [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, },
- [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, },
- [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, },
- [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, },
- [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, },
- [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, },
- [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &evattr_therm, test_therm_status, },
- [PERF_MSR_THERM_SNAP] = { MSR_IA32_THERM_STATUS, &evattr_therm_snap, test_therm_status, },
- [PERF_MSR_THERM_UNIT] = { MSR_IA32_THERM_STATUS, &evattr_therm_unit, test_therm_status, },
+ [PERF_MSR_TSC] = { .no_check = true, },
+ [PERF_MSR_APERF] = { MSR_IA32_APERF, &group_aperf, test_aperfmperf, },
+ [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &group_mperf, test_aperfmperf, },
+ [PERF_MSR_PPERF] = { MSR_PPERF, &group_pperf, test_intel, },
+ [PERF_MSR_SMI] = { MSR_SMI_COUNT, &group_smi, test_intel, },
+ [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &group_ptsc, test_ptsc, },
+ [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &group_irperf, test_irperf, },
+ [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &group_therm, test_therm_status, },
};
-static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
+static struct attribute *events_attrs[] = {
+ &attr_tsc.attr.attr,
NULL,
};
@@ -153,6 +167,17 @@ static const struct attribute_group *attr_groups[] = {
NULL,
};
+const struct attribute_group *attr_update[] = {
+ &group_aperf,
+ &group_mperf,
+ &group_pperf,
+ &group_smi,
+ &group_ptsc,
+ &group_irperf,
+ &group_therm,
+ NULL,
+};
+
static int msr_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config;
@@ -169,7 +194,7 @@ static int msr_event_init(struct perf_event *event)
cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX);
- if (!msr[cfg].attr)
+ if (!(msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.idx = -1;
@@ -252,32 +277,17 @@ static struct pmu pmu_msr = {
.stop = msr_event_stop,
.read = msr_event_update,
.capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
+ .attr_update = attr_update,
};
static int __init msr_init(void)
{
- int i, j = 0;
-
if (!boot_cpu_has(X86_FEATURE_TSC)) {
pr_cont("no MSR PMU driver.\n");
return 0;
}
- /* Probe the MSRs. */
- for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) {
- u64 val;
-
- /* Virt sucks; you cannot tell if a R/O MSR is present :/ */
- if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
- msr[i].attr = NULL;
- }
-
- /* List remaining MSRs in the sysfs attrs. */
- for (i = 0; i < PERF_MSR_EVENT_MAX; i++) {
- if (msr[i].attr)
- events_attrs[j++] = &msr[i].attr->attr.attr;
- }
- events_attrs[j] = NULL;
+ msr_mask = perf_msr_probe(msr, PERF_MSR_EVENT_MAX, true, NULL);
perf_pmu_register(&pmu_msr, "msr", -1);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 4e346856ee19..8751008fc170 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -613,14 +613,11 @@ struct x86_pmu {
int attr_rdpmc_broken;
int attr_rdpmc;
struct attribute **format_attrs;
- struct attribute **event_attrs;
- struct attribute **caps_attrs;
ssize_t (*events_sysfs_show)(char *page, u64 config);
- struct attribute **cpu_events;
+ const struct attribute_group **attr_update;
unsigned long attr_freeze_on_smi;
- struct attribute **attrs;
/*
* CPU Hotplug hooks
@@ -886,8 +883,6 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
ssize_t intel_event_sysfs_show(char *page, u64 config);
-struct attribute **merge_attr(struct attribute **a, struct attribute **b);
-
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
diff --git a/arch/x86/events/probe.c b/arch/x86/events/probe.c
new file mode 100644
index 000000000000..c2ede2f3b277
--- /dev/null
+++ b/arch/x86/events/probe.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/bits.h>
+#include "probe.h"
+
+static umode_t
+not_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return 0;
+}
+
+unsigned long
+perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
+{
+ unsigned long avail = 0;
+ unsigned int bit;
+ u64 val;
+
+ if (cnt >= BITS_PER_LONG)
+ return 0;
+
+ for (bit = 0; bit < cnt; bit++) {
+ if (!msr[bit].no_check) {
+ struct attribute_group *grp = msr[bit].grp;
+
+ grp->is_visible = not_visible;
+
+ if (msr[bit].test && !msr[bit].test(bit, data))
+ continue;
+ /* Virt sucks; you cannot tell if a R/O MSR is present :/ */
+ if (rdmsrl_safe(msr[bit].msr, &val))
+ continue;
+ /* Disable zero counters if requested. */
+ if (!zero && !val)
+ continue;
+
+ grp->is_visible = NULL;
+ }
+ avail |= BIT(bit);
+ }
+
+ return avail;
+}
+EXPORT_SYMBOL_GPL(perf_msr_probe);
diff --git a/arch/x86/events/probe.h b/arch/x86/events/probe.h
new file mode 100644
index 000000000000..4c8e0afc5fb5
--- /dev/null
+++ b/arch/x86/events/probe.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCH_X86_EVENTS_PROBE_H__
+#define __ARCH_X86_EVENTS_PROBE_H__
+#include <linux/sysfs.h>
+
+struct perf_msr {
+ u64 msr;
+ struct attribute_group *grp;
+ bool (*test)(int idx, void *data);
+ bool no_check;
+};
+
+unsigned long
+perf_msr_probe(struct perf_msr *msr, int cnt, bool no_zero, void *data);
+
+#define __PMU_EVENT_GROUP(_name) \
+static struct attribute *attrs_##_name[] = { \
+ &attr_##_name.attr.attr, \
+ NULL, \
+}
+
+#define PMU_EVENT_GROUP(_grp, _name) \
+__PMU_EVENT_GROUP(_name); \
+static struct attribute_group group_##_name = { \
+ .name = #_grp, \
+ .attrs = attrs_##_name, \
+}
+
+#endif /* __ARCH_X86_EVENTS_PROBE_H__ */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1d337c51f7e6..58acda503817 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -22,8 +22,8 @@ enum cpuid_leafs
CPUID_LNX_3,
CPUID_7_0_EBX,
CPUID_D_1_EAX,
- CPUID_F_0_EDX,
- CPUID_F_1_EDX,
+ CPUID_LNX_4,
+ CPUID_7_1_EAX,
CPUID_8000_0008_EBX,
CPUID_6_EAX,
CPUID_8000_000A_EDX,
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 75f27ee2c263..998c2cc08363 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -239,12 +239,14 @@
#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */
#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */
#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
@@ -269,13 +271,19 @@
#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */
#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
-#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0xf, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring */
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
@@ -322,6 +330,7 @@
#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */
#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 310118805f57..0278aa66ef62 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -56,6 +56,7 @@
#define INTEL_FAM6_ICELAKE_XEON_D 0x6C
#define INTEL_FAM6_ICELAKE_DESKTOP 0x7D
#define INTEL_FAM6_ICELAKE_MOBILE 0x7E
+#define INTEL_FAM6_ICELAKE_NNPI 0x9D
/* "Small Core" Processors (Atom) */
@@ -76,6 +77,7 @@
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */
#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */
#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */
+
#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */
/* Xeon Phi */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 979ef971cc78..6b4fc2788078 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -61,6 +61,15 @@
#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31
#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
+#define MSR_IA32_UMWAIT_CONTROL 0xe1
+#define MSR_IA32_UMWAIT_CONTROL_C02_DISABLE BIT(0)
+#define MSR_IA32_UMWAIT_CONTROL_RESERVED BIT(1)
+/*
+ * The time field is bit[31:2], but representing a 32bit value with
+ * bit[1:0] zero.
+ */
+#define MSR_IA32_UMWAIT_CONTROL_TIME_MASK (~0x03U)
+
#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2
#define NHM_C3_AUTO_DEMOTE (1UL << 25)
#define NHM_C1_AUTO_DEMOTE (1UL << 26)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c34a35c78618..3eab6ece52b4 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -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;
@@ -144,7 +146,8 @@ enum cpuid_regs_idx {
#define X86_VENDOR_TRANSMETA 7
#define X86_VENDOR_NSC 8
#define X86_VENDOR_HYGON 9
-#define X86_VENDOR_NUM 10
+#define X86_VENDOR_ZHAOXIN 10
+#define X86_VENDOR_NUM 11
#define X86_VENDOR_UNKNOWN 0xff
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index da545df207b2..b673a226ad6c 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -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);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 453cf38a1c33..4b14d2318251 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -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; }
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index a5e5484988fd..caf2edccbad2 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -64,6 +64,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
c->x86_stepping >= 0x0e))
flags->bm_check = 1;
}
+
+ if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+ /*
+ * All Zhaoxin CPUs that support C3 share cache.
+ * And caches should not be flushed by software while
+ * entering C3 type state.
+ */
+ flags->bm_check = 1;
+ /*
+ * On all recent Zhaoxin platforms, ARB_DISABLE is a nop.
+ * So, set bm_control to zero to indicate that ARB_DISABLE
+ * is not required while entering C3 type state.
+ */
+ flags->bm_control = 0;
+ }
}
EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 5102bf7c8192..4b4eb06e117c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -24,6 +24,7 @@ obj-y += match.o
obj-y += bugs.o
obj-y += aperfmperf.o
obj-y += cpuid-deps.o
+obj-y += umwait.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
@@ -38,6 +39,7 @@ obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o
obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o
obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o
+obj-$(CONFIG_CPU_SUP_ZHAOXIN) += zhaoxin.o
obj-$(CONFIG_X86_MCE) += mce/
obj-$(CONFIG_MTRR) += mtrr/
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index e71a6ff8a67e..e2f319dc992d 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -13,6 +13,7 @@
#include <linux/percpu.h>
#include <linux/cpufreq.h>
#include <linux/smp.h>
+#include <linux/sched/isolation.h>
#include "cpu.h"
@@ -85,6 +86,9 @@ unsigned int aperfmperf_get_khz(int cpu)
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ return 0;
+
aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
return per_cpu(samples.khz, cpu);
}
@@ -101,9 +105,12 @@ void arch_freq_prepare_all(void)
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return;
- for_each_online_cpu(cpu)
+ for_each_online_cpu(cpu) {
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ continue;
if (!aperfmperf_snapshot_cpu(cpu, now, false))
wait = true;
+ }
if (wait)
msleep(APERFMPERF_REFRESH_DELAY_MS);
@@ -117,6 +124,9 @@ unsigned int arch_freq_get_on_cpu(int cpu)
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
+ if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+ return 0;
+
if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
return per_cpu(samples.khz, cpu);
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 395d46f78582..c7503be92f35 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -658,8 +658,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
if (c->x86 < 0x17) {
/* LLC is at the node level. */
per_cpu(cpu_llc_id, cpu) = node_id;
- } else if (c->x86 == 0x17 &&
- c->x86_model >= 0 && c->x86_model <= 0x1F) {
+ } 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.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2c57fffebf9b..482f74859fb7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -801,6 +801,30 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
}
}
+static void init_cqm(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+ c->x86_cache_max_rmid = -1;
+ c->x86_cache_occ_scale = -1;
+ return;
+ }
+
+ /* will be overridden if occupancy monitoring exists */
+ c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+ if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+ cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+ cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+ u32 eax, ebx, ecx, edx;
+
+ /* QoS sub-leaf, EAX=0Fh, ECX=1 */
+ cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+ c->x86_cache_max_rmid = ecx;
+ c->x86_cache_occ_scale = ebx;
+ }
+}
+
void get_cpu_cap(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
@@ -823,6 +847,12 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_7_0_EBX] = ebx;
c->x86_capability[CPUID_7_ECX] = ecx;
c->x86_capability[CPUID_7_EDX] = edx;
+
+ /* Check valid sub-leaf index before accessing it */
+ if (eax >= 1) {
+ cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[CPUID_7_1_EAX] = eax;
+ }
}
/* Extended state features: level 0x0000000d */
@@ -832,33 +862,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_D_1_EAX] = eax;
}
- /* Additional Intel-defined flags: level 0x0000000F */
- if (c->cpuid_level >= 0x0000000F) {
-
- /* QoS sub-leaf, EAX=0Fh, ECX=0 */
- cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_0_EDX] = edx;
-
- if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
- /* will be overridden if occupancy monitoring exists */
- c->x86_cache_max_rmid = ebx;
-
- /* QoS sub-leaf, EAX=0Fh, ECX=1 */
- cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_F_1_EDX] = edx;
-
- if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
- ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
- (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
- c->x86_cache_max_rmid = ecx;
- c->x86_cache_occ_scale = ebx;
- }
- } else {
- c->x86_cache_max_rmid = -1;
- c->x86_cache_occ_scale = -1;
- }
- }
-
/* AMD-defined flags: level 0x80000001 */
eax = cpuid_eax(0x80000000);
c->extended_cpuid_level = eax;
@@ -889,6 +892,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
init_scattered_cpuid_features(c);
init_speculation_control(c);
+ init_cqm(c);
/*
* Clear/Set all flags overridden by options, after probe.
@@ -1299,6 +1303,7 @@ 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
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 2c0bd38a44ab..a444028d8145 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -59,6 +59,10 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
{}
};
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f17c1a714779..8d6d92ebeb54 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -66,6 +66,32 @@ void check_mpx_erratum(struct cpuinfo_x86 *c)
}
}
+/*
+ * Processors which have self-snooping capability can handle conflicting
+ * memory type across CPUs by snooping its own cache. However, there exists
+ * CPU models in which having conflicting memory types still leads to
+ * unpredictable behavior, machine check errors, or hangs. Clear this
+ * feature to prevent its use on machines with known erratas.
+ */
+static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c)
+{
+ switch (c->x86_model) {
+ case INTEL_FAM6_CORE_YONAH:
+ case INTEL_FAM6_CORE2_MEROM:
+ case INTEL_FAM6_CORE2_MEROM_L:
+ case INTEL_FAM6_CORE2_PENRYN:
+ case INTEL_FAM6_CORE2_DUNNINGTON:
+ case INTEL_FAM6_NEHALEM:
+ case INTEL_FAM6_NEHALEM_G:
+ case INTEL_FAM6_NEHALEM_EP:
+ case INTEL_FAM6_NEHALEM_EX:
+ case INTEL_FAM6_WESTMERE:
+ case INTEL_FAM6_WESTMERE_EP:
+ case INTEL_FAM6_SANDYBRIDGE:
+ setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP);
+ }
+}
+
static bool ring3mwait_disabled __read_mostly;
static int __init ring3mwait_disable(char *__unused)
@@ -304,6 +330,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
}
check_mpx_erratum(c);
+ check_memory_type_self_snoop_errata(c);
/*
* Get the number of SMT siblings early from the extended topology
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9356c1c9024d..aa5c064a6a22 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -743,7 +743,15 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
cr0 = read_cr0() | X86_CR0_CD;
write_cr0(cr0);
- wbinvd();
+
+ /*
+ * Cache flushing is the most time-consuming step when programming
+ * the MTRRs. Fortunately, as per the Intel Software Development
+ * Manual, we can skip it if the processor supports cache self-
+ * snooping.
+ */
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+ wbinvd();
/* Save value of CR4 and clear Page Global Enable (bit 7) */
if (boot_cpu_has(X86_FEATURE_PGE)) {
@@ -760,7 +768,10 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
/* Disable MTRRs, and set the default type to uncached */
mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
- wbinvd();
+
+ /* Again, only flush caches if we have to. */
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+ wbinvd();
}
static void post_set(void) __releases(set_atomicity_lock)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 94aa1c72ca98..adf9b71386ef 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,10 @@ struct cpuid_bit {
static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
+ { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
+ { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 },
+ { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },
+ { X86_FEATURE_CQM_MBM_LOCAL, CPUID_EDX, 2, 0x0000000f, 1 },
{ X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 },
{ X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 },
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 8f6c784141d1..ee48c3fc8a65 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -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)
-int detect_extended_topology_early(struct cpuinfo_x86 *c)
-{
#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;
- if (c->cpuid_level < 0xb)
+ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+
+ if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
return -1;
- cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+ 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;
+ }
- /*
- * check if the cpuid leaf 0xb is actually implemented.
- */
- if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
+ 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;
+
+ 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;
-
- 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);
+ 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->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;
}
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
new file mode 100644
index 000000000000..6a204e7336c1
--- /dev/null
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
+#include <linux/cpu.h>
+
+#include <asm/msr.h>
+
+#define UMWAIT_C02_ENABLE 0
+
+#define UMWAIT_CTRL_VAL(max_time, c02_disable) \
+ (((max_time) & MSR_IA32_UMWAIT_CONTROL_TIME_MASK) | \
+ ((c02_disable) & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE))
+
+/*
+ * Cache IA32_UMWAIT_CONTROL MSR. This is a systemwide control. By default,
+ * umwait max time is 100000 in TSC-quanta and C0.2 is enabled
+ */
+static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
+
+/*
+ * Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in
+ * the sysfs write functions.
+ */
+static DEFINE_MUTEX(umwait_lock);
+
+static void umwait_update_control_msr(void * unused)
+{
+ lockdep_assert_irqs_disabled();
+ wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+}
+
+/*
+ * The CPU hotplug callback sets the control MSR to the global control
+ * value.
+ *
+ * Disable interrupts so the read of umwait_control_cached and the WRMSR
+ * are protected against a concurrent sysfs write. Otherwise the sysfs
+ * write could update the cached value after it had been read on this CPU
+ * and issue the IPI before the old value had been written. The IPI would
+ * interrupt, write the new value and after return from IPI the previous
+ * value would be written by this CPU.
+ *
+ * With interrupts disabled the upcoming CPU either sees the new control
+ * value or the IPI is updating this CPU to the new control value after
+ * interrupts have been reenabled.
+ */
+static int umwait_cpu_online(unsigned int cpu)
+{
+ local_irq_disable();
+ umwait_update_control_msr(NULL);
+ local_irq_enable();
+ return 0;
+}
+
+/*
+ * On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
+ * is the only active CPU at this time. The MSR is set up on the APs via the
+ * CPU hotplug callback.
+ *
+ * This function is invoked on resume from suspend and hibernation. On
+ * resume from suspend the restore should be not required, but we neither
+ * trust the firmware nor does it matter if the same value is written
+ * again.
+ */
+static void umwait_syscore_resume(void)
+{
+ umwait_update_control_msr(NULL);
+}
+
+static struct syscore_ops umwait_syscore_ops = {
+ .resume = umwait_syscore_resume,
+};
+
+/* sysfs interface */
+
+/*
+ * When bit 0 in IA32_UMWAIT_CONTROL MSR is 1, C0.2 is disabled.
+ * Otherwise, C0.2 is enabled.
+ */
+static inline bool umwait_ctrl_c02_enabled(u32 ctrl)
+{
+ return !(ctrl & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE);
+}
+
+static inline u32 umwait_ctrl_max_time(u32 ctrl)
+{
+ return ctrl & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+}
+
+static inline void umwait_update_control(u32 maxtime, bool c02_enable)
+{
+ u32 ctrl = maxtime & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+
+ if (!c02_enable)
+ ctrl |= MSR_IA32_UMWAIT_CONTROL_C02_DISABLE;
+
+ WRITE_ONCE(umwait_control_cached, ctrl);
+ /* Propagate to all CPUs */
+ on_each_cpu(umwait_update_control_msr, NULL, 1);
+}
+
+static ssize_t
+enable_c02_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ u32 ctrl = READ_ONCE(umwait_control_cached);
+
+ return sprintf(buf, "%d\n", umwait_ctrl_c02_enabled(ctrl));
+}
+
+static ssize_t enable_c02_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ bool c02_enable;
+ u32 ctrl;
+ int ret;
+
+ ret = kstrtobool(buf, &c02_enable);
+ if (ret)
+ return ret;
+
+ mutex_lock(&umwait_lock);
+
+ ctrl = READ_ONCE(umwait_control_cached);
+ if (c02_enable != umwait_ctrl_c02_enabled(ctrl))
+ umwait_update_control(ctrl, c02_enable);
+
+ mutex_unlock(&umwait_lock);
+
+ return count;
+}
+static DEVICE_ATTR_RW(enable_c02);
+
+static ssize_t
+max_time_show(struct device *kobj, struct device_attribute *attr, char *buf)
+{
+ u32 ctrl = READ_ONCE(umwait_control_cached);
+
+ return sprintf(buf, "%u\n", umwait_ctrl_max_time(ctrl));
+}
+
+static ssize_t max_time_store(struct device *kobj,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ u32 max_time, ctrl;
+ int ret;
+
+ ret = kstrtou32(buf, 0, &max_time);
+ if (ret)
+ return ret;
+
+ /* bits[1:0] must be zero */
+ if (max_time & ~MSR_IA32_UMWAIT_CONTROL_TIME_MASK)
+ return -EINVAL;
+
+ mutex_lock(&umwait_lock);
+
+ ctrl = READ_ONCE(umwait_control_cached);
+ if (max_time != umwait_ctrl_max_time(ctrl))
+ umwait_update_control(max_time, umwait_ctrl_c02_enabled(ctrl));
+
+ mutex_unlock(&umwait_lock);
+
+ return count;
+}
+static DEVICE_ATTR_RW(max_time);
+
+static struct attribute *umwait_attrs[] = {
+ &dev_attr_enable_c02.attr,
+ &dev_attr_max_time.attr,
+ NULL
+};
+
+static struct attribute_group umwait_attr_group = {
+ .attrs = umwait_attrs,
+ .name = "umwait_control",
+};
+
+static int __init umwait_init(void)
+{
+ struct device *dev;
+ int ret;
+
+ if (!boot_cpu_has(X86_FEATURE_WAITPKG))
+ return -ENODEV;
+
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
+ umwait_cpu_online, NULL);
+
+ register_syscore_ops(&umwait_syscore_ops);
+
+ /*
+ * Add umwait control interface. Ignore failure, so at least the
+ * default values are set up in case the machine manages to boot.
+ */
+ dev = cpu_subsys.dev_root;
+ return sysfs_create_group(&dev->kobj, &umwait_attr_group);
+}
+device_initcall(umwait_init);
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
new file mode 100644
index 000000000000..8e6f2f4b4afe
--- /dev/null
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+
+#include <asm/cpufeature.h>
+
+#include "cpu.h"
+
+#define MSR_ZHAOXIN_FCR57 0x00001257
+
+#define ACE_PRESENT (1 << 6)
+#define ACE_ENABLED (1 << 7)
+#define ACE_FCR (1 << 7) /* MSR_ZHAOXIN_FCR */
+
+#define RNG_PRESENT (1 << 2)
+#define RNG_ENABLED (1 << 3)
+#define RNG_ENABLE (1 << 8) /* MSR_ZHAOXIN_RNG */
+
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020
+
+static void init_zhaoxin_cap(struct cpuinfo_x86 *c)
+{
+ u32 lo, hi;
+
+ /* Test for Extended Feature Flags presence */
+ if (cpuid_eax(0xC0000000) >= 0xC0000001) {
+ u32 tmp = cpuid_edx(0xC0000001);
+
+ /* Enable ACE unit, if present and disabled */
+ if ((tmp & (ACE_PRESENT | ACE_ENABLED)) == ACE_PRESENT) {
+ rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ /* Enable ACE unit */
+ lo |= ACE_FCR;
+ wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ pr_info("CPU: Enabled ACE h/w crypto\n");
+ }
+
+ /* Enable RNG unit, if present and disabled */
+ if ((tmp & (RNG_PRESENT | RNG_ENABLED)) == RNG_PRESENT) {
+ rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ /* Enable RNG unit */
+ lo |= RNG_ENABLE;
+ wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+ pr_info("CPU: Enabled h/w RNG\n");
+ }
+
+ /*
+ * Store Extended Feature Flags as word 5 of the CPU
+ * capability bit array
+ */
+ c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001);
+ }
+
+ if (c->x86 >= 0x6)
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+ cpu_detect_cache_sizes(c);
+}
+
+static void early_init_zhaoxin(struct cpuinfo_x86 *c)
+{
+ if (c->x86 >= 0x6)
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+#ifdef CONFIG_X86_64
+ set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+#endif
+ if (c->x86_power & (1 << 8)) {
+ 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 zhaoxin_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+ u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+ msr_ctl = vmx_msr_high | vmx_msr_low;
+
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+ set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+ set_cpu_cap(c, X86_FEATURE_VNMI);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+ vmx_msr_low, vmx_msr_high);
+ msr_ctl2 = vmx_msr_high | vmx_msr_low;
+ if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+ (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+ set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+ set_cpu_cap(c, X86_FEATURE_EPT);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+ set_cpu_cap(c, X86_FEATURE_VPID);
+ }
+}
+
+static void init_zhaoxin(struct cpuinfo_x86 *c)
+{
+ early_init_zhaoxin(c);
+ init_intel_cacheinfo(c);
+ detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+ detect_ht(c);
+#endif
+
+ if (c->cpuid_level > 9) {
+ unsigned int eax = cpuid_eax(10);
+
+ /*
+ * Check for version and the number of counters
+ * Version(eax[7:0]) can't be 0;
+ * Counters(eax[15:8]) should be greater than 1;
+ */
+ if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+ set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+ }
+
+ if (c->x86 >= 0x6)
+ init_zhaoxin_cap(c);
+#ifdef CONFIG_X86_64
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+#endif
+
+ if (cpu_has(c, X86_FEATURE_VMX))
+ zhaoxin_detect_vmx_virtcap(c);
+}
+
+#ifdef CONFIG_X86_32
+static unsigned int
+zhaoxin_size_cache(struct cpuinfo_x86 *c, unsigned int size)
+{
+ return size;
+}
+#endif
+
+static const struct cpu_dev zhaoxin_cpu_dev = {
+ .c_vendor = "zhaoxin",
+ .c_ident = { " Shanghai " },
+ .c_early_init = early_init_zhaoxin,
+ .c_init = init_zhaoxin,
+#ifdef CONFIG_X86_32
+ .legacy_cache_size = zhaoxin_size_cache,
+#endif
+ .c_x86_vendor = X86_VENDOR_ZHAOXIN,
+};
+
+cpu_dev_register(zhaoxin_cpu_dev);
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index a166c960bc9e..3108cdc00b29 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -397,22 +397,12 @@ static int putreg(struct task_struct *child,
case offsetof(struct user_regs_struct,fs_base):
if (value >= TASK_SIZE_MAX)
return -EIO;
- /*
- * When changing the FS base, use do_arch_prctl_64()
- * to set the index to zero and to set the base
- * as requested.
- */
- if (child->thread.fsbase != value)
- return do_arch_prctl_64(child, ARCH_SET_FS, value);
+ x86_fsbase_write_task(child, value);
return 0;
case offsetof(struct user_regs_struct,gs_base):
- /*
- * Exactly the same here as the %fs handling above.
- */
if (value >= TASK_SIZE_MAX)
return -EIO;
- if (child->thread.gsbase != value)
- return do_arch_prctl_64(child, ARCH_SET_GS, value);
+ x86_gsbase_write_task(child, value);
return 0;
#endif
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 362dd8953f48..e4f4f3c5ccd2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -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);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 9a327d5b6d1f..d78a61408243 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -47,8 +47,6 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
[CPUID_7_0_EBX] = { 7, 0, CPUID_EBX},
[CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX},
- [CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX},
- [CPUID_F_1_EDX] = { 0xf, 1, CPUID_EDX},
[CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX},
[CPUID_6_EAX] = { 6, 0, CPUID_EAX},
[CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX},
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 590fcf863006..77d81c1a63e9 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -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);