summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/Makefile6
-rw-r--r--arch/x86/kernel/cpu/amd.c39
-rw-r--r--arch/x86/kernel/cpu/bugs.c20
-rw-r--r--arch/x86/kernel/cpu/common.c35
-rw-r--r--arch/x86/kernel/cpu/cpu.h9
-rw-r--r--arch/x86/kernel/cpu/hypervisor.c3
-rw-r--r--arch/x86/kernel/cpu/intel.c176
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c7
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c69
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c286
-rw-r--r--arch/x86/kernel/cpu/mtrr/cleanup.c6
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c6
-rw-r--r--arch/x86/kernel/cpu/perf_event.c196
-rw-r--r--arch/x86/kernel/cpu/perf_event.h48
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c103
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c16
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c261
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c33
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c3
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c2921
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h619
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c16
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c4
-rw-r--r--arch/x86/kernel/cpu/sched.c55
24 files changed, 4502 insertions, 435 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 6ab6aa2fdfd..d30a6a9a012 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -14,7 +14,7 @@ CFLAGS_common.o := $(nostackp)
obj-y := intel_cacheinfo.o scattered.o topology.o
obj-y += proc.o capflags.o powerflags.o common.o
-obj-y += vmware.o hypervisor.o sched.o mshyperv.o
+obj-y += vmware.o hypervisor.o mshyperv.o
obj-y += rdrand.o
obj-y += match.o
@@ -32,7 +32,9 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o
ifdef CONFIG_PERF_EVENTS
obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o
-obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o
endif
obj-$(CONFIG_X86_MCE) += mcheck/
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 146bb6218ee..9d92e19039f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -19,6 +19,39 @@
#include "cpu.h"
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+ struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+ u32 gprs[8] = { 0 };
+ int err;
+
+ WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__);
+
+ gprs[1] = msr;
+ gprs[7] = 0x9c5a203a;
+
+ err = rdmsr_safe_regs(gprs);
+
+ *p = gprs[0] | ((u64)gprs[2] << 32);
+
+ return err;
+}
+
+static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+{
+ struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+ u32 gprs[8] = { 0 };
+
+ WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__);
+
+ gprs[0] = (u32)val;
+ gprs[1] = msr;
+ gprs[2] = val >> 32;
+ gprs[7] = 0x9c5a203a;
+
+ return wrmsr_safe_regs(gprs);
+}
+
#ifdef CONFIG_X86_32
/*
* B step AMD K6 before B 9730xxxx have hardware bugs that can cause
@@ -586,9 +619,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
!cpu_has(c, X86_FEATURE_TOPOEXT)) {
u64 val;
- if (!rdmsrl_amd_safe(0xc0011005, &val)) {
+ if (!rdmsrl_safe(0xc0011005, &val)) {
val |= 1ULL << 54;
- wrmsrl_amd_safe(0xc0011005, val);
+ wrmsrl_safe(0xc0011005, val);
rdmsrl(0xc0011005, val);
if (val & (1ULL << 54)) {
set_cpu_cap(c, X86_FEATURE_TOPOEXT);
@@ -679,7 +712,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask);
if (err == 0) {
mask |= (1 << 10);
- checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
+ wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask);
}
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 46674fbb62b..c97bb7b5a9f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -55,8 +55,8 @@ static void __init check_fpu(void)
if (!boot_cpu_data.hard_math) {
#ifndef CONFIG_MATH_EMULATION
- printk(KERN_EMERG "No coprocessor found and no math emulation present.\n");
- printk(KERN_EMERG "Giving up.\n");
+ pr_emerg("No coprocessor found and no math emulation present\n");
+ pr_emerg("Giving up\n");
for (;;) ;
#endif
return;
@@ -86,7 +86,7 @@ static void __init check_fpu(void)
boot_cpu_data.fdiv_bug = fdiv_bug;
if (boot_cpu_data.fdiv_bug)
- printk(KERN_WARNING "Hmm, FPU with FDIV bug.\n");
+ pr_warn("Hmm, FPU with FDIV bug\n");
}
static void __init check_hlt(void)
@@ -94,16 +94,16 @@ static void __init check_hlt(void)
if (boot_cpu_data.x86 >= 5 || paravirt_enabled())
return;
- printk(KERN_INFO "Checking 'hlt' instruction... ");
+ pr_info("Checking 'hlt' instruction... ");
if (!boot_cpu_data.hlt_works_ok) {
- printk("disabled\n");
+ pr_cont("disabled\n");
return;
}
halt();
halt();
halt();
halt();
- printk(KERN_CONT "OK.\n");
+ pr_cont("OK\n");
}
/*
@@ -116,7 +116,7 @@ static void __init check_popad(void)
#ifndef CONFIG_X86_POPAD_OK
int res, inp = (int) &res;
- printk(KERN_INFO "Checking for popad bug... ");
+ pr_info("Checking for popad bug... ");
__asm__ __volatile__(
"movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx "
: "=&a" (res)
@@ -127,9 +127,9 @@ static void __init check_popad(void)
* CPU hard. Too bad.
*/
if (res != 12345678)
- printk(KERN_CONT "Buggy.\n");
+ pr_cont("Buggy\n");
else
- printk(KERN_CONT "OK.\n");
+ pr_cont("OK\n");
#endif
}
@@ -161,7 +161,7 @@ void __init check_bugs(void)
{
identify_boot_cpu();
#ifndef CONFIG_SMP
- printk(KERN_INFO "CPU: ");
+ pr_info("CPU: ");
print_cpu_info(&boot_cpu_data);
#endif
check_config();
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6b9333b429b..a5fbc3c5fcc 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -144,6 +144,8 @@ static int __init x86_xsave_setup(char *s)
{
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+ setup_clear_cpu_cap(X86_FEATURE_AVX);
+ setup_clear_cpu_cap(X86_FEATURE_AVX2);
return 1;
}
__setup("noxsave", x86_xsave_setup);
@@ -452,6 +454,35 @@ void __cpuinit cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
c->x86_cache_size = l2size;
}
+u16 __read_mostly tlb_lli_4k[NR_INFO];
+u16 __read_mostly tlb_lli_2m[NR_INFO];
+u16 __read_mostly tlb_lli_4m[NR_INFO];
+u16 __read_mostly tlb_lld_4k[NR_INFO];
+u16 __read_mostly tlb_lld_2m[NR_INFO];
+u16 __read_mostly tlb_lld_4m[NR_INFO];
+
+/*
+ * tlb_flushall_shift shows the balance point in replacing cr3 write
+ * with multiple 'invlpg'. It will do this replacement when
+ * flush_tlb_lines <= active_lines/2^tlb_flushall_shift.
+ * If tlb_flushall_shift is -1, means the replacement will be disabled.
+ */
+s8 __read_mostly tlb_flushall_shift = -1;
+
+void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c)
+{
+ if (this_cpu->c_detect_tlb)
+ this_cpu->c_detect_tlb(c);
+
+ printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
+ "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
+ "tlb_flushall_shift is 0x%x\n",
+ tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
+ tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
+ tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
+ tlb_flushall_shift);
+}
+
void __cpuinit detect_ht(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_HT
@@ -911,6 +942,8 @@ void __init identify_boot_cpu(void)
#else
vgetcpu_set_mode();
#endif
+ if (boot_cpu_data.cpuid_level >= 2)
+ cpu_detect_tlb(&boot_cpu_data);
}
void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
@@ -947,7 +980,7 @@ static void __cpuinit __print_cpu_msr(void)
index_max = msr_range_array[i].max;
for (index = index_min; index < index_max; index++) {
- if (rdmsrl_amd_safe(index, &val))
+ if (rdmsrl_safe(index, &val))
continue;
printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
}
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 8bacc7826fb..4041c24ae7d 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -20,10 +20,19 @@ struct cpu_dev {
void (*c_bsp_init)(struct cpuinfo_x86 *);
void (*c_init)(struct cpuinfo_x86 *);
void (*c_identify)(struct cpuinfo_x86 *);
+ void (*c_detect_tlb)(struct cpuinfo_x86 *);
unsigned int (*c_size_cache)(struct cpuinfo_x86 *, unsigned int);
int c_x86_vendor;
};
+struct _tlb_table {
+ unsigned char descriptor;
+ char tlb_type;
+ unsigned int entries;
+ /* unsigned int ways; */
+ char info[128];
+};
+
#define cpu_dev_register(cpu_devX) \
static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
__attribute__((__section__(".x86_cpu_dev.init"))) = \
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 755f64fb074..a8f8fa9769d 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -37,6 +37,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] =
#endif
&x86_hyper_vmware,
&x86_hyper_ms_hyperv,
+#ifdef CONFIG_KVM_GUEST
+ &x86_hyper_kvm,
+#endif
};
const struct hypervisor_x86 *x86_hyper;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3e6ff6cbf42..0a4ce2980a5 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -491,6 +491,181 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned i
}
#endif
+#define TLB_INST_4K 0x01
+#define TLB_INST_4M 0x02
+#define TLB_INST_2M_4M 0x03
+
+#define TLB_INST_ALL 0x05
+#define TLB_INST_1G 0x06
+
+#define TLB_DATA_4K 0x11
+#define TLB_DATA_4M 0x12
+#define TLB_DATA_2M_4M 0x13
+#define TLB_DATA_4K_4M 0x14
+
+#define TLB_DATA_1G 0x16
+
+#define TLB_DATA0_4K 0x21
+#define TLB_DATA0_4M 0x22
+#define TLB_DATA0_2M_4M 0x23
+
+#define STLB_4K 0x41
+
+static const struct _tlb_table intel_tlb_table[] __cpuinitconst = {
+ { 0x01, TLB_INST_4K, 32, " TLB_INST 4 KByte pages, 4-way set associative" },
+ { 0x02, TLB_INST_4M, 2, " TLB_INST 4 MByte pages, full associative" },
+ { 0x03, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way set associative" },
+ { 0x04, TLB_DATA_4M, 8, " TLB_DATA 4 MByte pages, 4-way set associative" },
+ { 0x05, TLB_DATA_4M, 32, " TLB_DATA 4 MByte pages, 4-way set associative" },
+ { 0x0b, TLB_INST_4M, 4, " TLB_INST 4 MByte pages, 4-way set associative" },
+ { 0x4f, TLB_INST_4K, 32, " TLB_INST 4 KByte pages */" },
+ { 0x50, TLB_INST_ALL, 64, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
+ { 0x51, TLB_INST_ALL, 128, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
+ { 0x52, TLB_INST_ALL, 256, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
+ { 0x55, TLB_INST_2M_4M, 7, " TLB_INST 2-MByte or 4-MByte pages, fully associative" },
+ { 0x56, TLB_DATA0_4M, 16, " TLB_DATA0 4 MByte pages, 4-way set associative" },
+ { 0x57, TLB_DATA0_4K, 16, " TLB_DATA0 4 KByte pages, 4-way associative" },
+ { 0x59, TLB_DATA0_4K, 16, " TLB_DATA0 4 KByte pages, fully associative" },
+ { 0x5a, TLB_DATA0_2M_4M, 32, " TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
+ { 0x5b, TLB_DATA_4K_4M, 64, " TLB_DATA 4 KByte and 4 MByte pages" },
+ { 0x5c, TLB_DATA_4K_4M, 128, " TLB_DATA 4 KByte and 4 MByte pages" },
+ { 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" },
+ { 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" },
+ { 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
+ { 0xb2, TLB_INST_4K, 64, " TLB_INST 4KByte pages, 4-way set associative" },
+ { 0xb3, TLB_DATA_4K, 128, " TLB_DATA 4 KByte pages, 4-way set associative" },
+ { 0xb4, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 4-way associative" },
+ { 0xba, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way associative" },
+ { 0xc0, TLB_DATA_4K_4M, 8, " TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
+ { 0xca, STLB_4K, 512, " STLB 4 KByte pages, 4-way associative" },
+ { 0x00, 0, 0 }
+};
+
+static void __cpuinit intel_tlb_lookup(const unsigned char desc)
+{
+ unsigned char k;
+ if (desc == 0)
+ return;
+
+ /* look up this descriptor in the table */
+ for (k = 0; intel_tlb_table[k].descriptor != desc && \
+ intel_tlb_table[k].descriptor != 0; k++)
+ ;
+
+ if (intel_tlb_table[k].tlb_type == 0)
+ return;
+
+ switch (intel_tlb_table[k].tlb_type) {
+ case STLB_4K:
+ if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+ if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ case TLB_INST_ALL:
+ if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+ if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
+ if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ case TLB_INST_4K:
+ if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ case TLB_INST_4M:
+ if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ case TLB_INST_2M_4M:
+ if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
+ if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ case TLB_DATA_4K:
+ case TLB_DATA0_4K:
+ if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ case TLB_DATA_4M:
+ case TLB_DATA0_4M:
+ if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ case TLB_DATA_2M_4M:
+ case TLB_DATA0_2M_4M:
+ if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
+ if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ case TLB_DATA_4K_4M:
+ if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+ if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
+ tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+ break;
+ }
+}
+
+static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has_invlpg) {
+ tlb_flushall_shift = -1;
+ return;
+ }
+ switch ((c->x86 << 8) + c->x86_model) {
+ case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+ case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
+ case 0x617: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
+ case 0x61d: /* six-core 45 nm xeon "Dunnington" */
+ tlb_flushall_shift = -1;
+ break;
+ case 0x61a: /* 45 nm nehalem, "Bloomfield" */
+ case 0x61e: /* 45 nm nehalem, "Lynnfield" */
+ case 0x625: /* 32 nm nehalem, "Clarkdale" */
+ case 0x62c: /* 32 nm nehalem, "Gulftown" */
+ case 0x62e: /* 45 nm nehalem-ex, "Beckton" */
+ case 0x62f: /* 32 nm Xeon E7 */
+ tlb_flushall_shift = 6;
+ break;
+ case 0x62a: /* SandyBridge */
+ case 0x62d: /* SandyBridge, "Romely-EP" */
+ tlb_flushall_shift = 5;
+ break;
+ case 0x63a: /* Ivybridge */
+ tlb_flushall_shift = 1;
+ break;
+ default:
+ tlb_flushall_shift = 6;
+ }
+}
+
+static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c)
+{
+ int i, j, n;
+ unsigned int regs[4];
+ unsigned char *desc = (unsigned char *)regs;
+ /* Number of times to iterate */
+ n = cpuid_eax(2) & 0xFF;
+
+ for (i = 0 ; i < n ; i++) {
+ cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
+
+ /* If bit 31 is set, this is an unknown format */
+ for (j = 0 ; j < 3 ; j++)
+ if (regs[j] & (1 << 31))
+ regs[j] = 0;
+
+ /* Byte 0 is level count, not a descriptor */
+ for (j = 1 ; j < 16 ; j++)
+ intel_tlb_lookup(desc[j]);
+ }
+ intel_tlb_flushall_shift_set(c);
+}
+
static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
.c_vendor = "Intel",
.c_ident = { "GenuineIntel" },
@@ -546,6 +721,7 @@ static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
},
.c_size_cache = intel_size_cache,
#endif
+ .c_detect_tlb = intel_detect_tlb,
.c_early_init = early_init_intel,
.c_init = init_intel,
.c_x86_vendor = X86_VENDOR_INTEL,
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 413c2ced887..13017626f9a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -55,13 +55,6 @@ static struct severity {
#define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S)
#define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR)
#define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV)
-#define MCACOD 0xffff
-/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
-#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */
-#define MCACOD_SCRUBMSK 0xfff0
-#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */
-#define MCACOD_DATA 0x0134 /* Data Load */
-#define MCACOD_INSTR 0x0150 /* Instruction Fetch */
MCESEV(
NO, "Invalid",
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index c46ed494f00..292d0258311 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -7,6 +7,9 @@
* Copyright 2008 Intel Corporation
* Author: Andi Kleen
*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/thread_info.h>
#include <linux/capability.h>
#include <linux/miscdevice.h>
@@ -57,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex);
int mce_disabled __read_mostly;
-#define MISC_MCELOG_MINOR 227
-
#define SPINUNIT 100 /* 100ns */
atomic_t mce_entry;
@@ -102,6 +103,8 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
static DEFINE_PER_CPU(struct work_struct, mce_work);
+static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
+
/*
* CPU/chipset specific EDAC code can register a notifier call here to print
* MCE errors in a human-readable form.
@@ -210,7 +213,7 @@ static void drain_mcelog_buffer(void)
cpu_relax();
if (!m->finished && retries >= 4) {
- pr_err("MCE: skipping error being logged currently!\n");
+ pr_err("skipping error being logged currently!\n");
break;
}
}
@@ -649,14 +652,18 @@ EXPORT_SYMBOL_GPL(machine_check_poll);
* Do a quick check if any of the events requires a panic.
* This decides if we keep the events around or clear them.
*/
-static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp)
+static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
+ struct pt_regs *regs)
{
int i, ret = 0;
for (i = 0; i < banks; i++) {
m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
- if (m->status & MCI_STATUS_VAL)
+ if (m->status & MCI_STATUS_VAL) {
__set_bit(i, validp);
+ if (quirk_no_way_out)
+ quirk_no_way_out(i, m, regs);
+ }
if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY)
ret = 1;
}
@@ -1039,7 +1046,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
*final = m;
memset(valid_banks, 0, sizeof(valid_banks));
- no_way_out = mce_no_way_out(&m, &msg, valid_banks);
+ no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs);
barrier();
@@ -1167,8 +1174,9 @@ int memory_failure(unsigned long pfn, int vector, int flags)
{
/* mce_severity() should not hand us an ACTION_REQUIRED error */
BUG_ON(flags & MF_ACTION_REQUIRED);
- printk(KERN_ERR "Uncorrected memory error in page 0x%lx ignored\n"
- "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", pfn);
+ pr_err("Uncorrected memory error in page 0x%lx ignored\n"
+ "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n",
+ pfn);
return 0;
}
@@ -1360,11 +1368,10 @@ static int __cpuinit __mcheck_cpu_cap_init(void)
b = cap & MCG_BANKCNT_MASK;
if (!banks)
- printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b);
+ pr_info("CPU supports %d MCE banks\n", b);
if (b > MAX_NR_BANKS) {
- printk(KERN_WARNING
- "MCE: Using only %u machine check banks out of %u\n",
+ pr_warn("Using only %u machine check banks out of %u\n",
MAX_NR_BANKS, b);
b = MAX_NR_BANKS;
}
@@ -1417,11 +1424,39 @@ static void __mcheck_cpu_init_generic(void)
}
}
+/*
+ * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
+ * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
+ * Vol 3B Table 15-20). But this confuses both the code that determines
+ * whether the machine check occurred in kernel or user mode, and also
+ * the severity assessment code. Pretend that EIPV was set, and take the
+ * ip/cs values from the pt_regs that mce_gather_info() ignored earlier.
+ */
+static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
+{
+ if (bank != 0)
+ return;
+ if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0)
+ return;
+ if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC|
+ MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV|
+ MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR|
+ MCACOD)) !=
+ (MCI_STATUS_UC|MCI_STATUS_EN|
+ MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S|
+ MCI_STATUS_AR|MCACOD_INSTR))
+ return;
+
+ m->mcgstatus |= MCG_STATUS_EIPV;
+ m->ip = regs->ip;
+ m->cs = regs->cs;
+}
+
/* Add per CPU specific workarounds here */
static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
{
if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
- pr_info("MCE: unknown CPU type - not enabling MCE support.\n");
+ pr_info("unknown CPU type - not enabling MCE support\n");
return -EOPNOTSUPP;
}
@@ -1514,6 +1549,9 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
*/
if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0)
mce_bootlog = 0;
+
+ if (c->x86 == 6 && c->x86_model == 45)
+ quirk_no_way_out = quirk_sandybridge_ifu;
}
if (monarch_timeout < 0)
monarch_timeout = 0;
@@ -1576,7 +1614,7 @@ static void __mcheck_cpu_init_timer(void)
/* Handle unconfigured int18 (should never happen) */
static void unexpected_machine_check(struct pt_regs *regs, long error_code)
{
- printk(KERN_ERR "CPU#%d: Unexpected int18 (Machine Check).\n",
+ pr_err("CPU#%d: Unexpected int18 (Machine Check)\n",
smp_processor_id());
}
@@ -1895,8 +1933,7 @@ static int __init mcheck_enable(char *str)
get_option(&str, &monarch_timeout);
}
} else {
- printk(KERN_INFO "mce argument %s ignored. Please use /sys\n",
- str);
+ pr_info("mce argument %s ignored. Please use /sys\n", str);
return 0;
}
return 1;
@@ -2344,7 +2381,7 @@ static __init int mcheck_init_device(void)
return err;
}
-device_initcall(mcheck_init_device);
+device_initcall_sync(mcheck_init_device);
/*
* Old style boot options parsing. Only for compatibility.
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index f4873a64f46..c4e916d7737 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1,15 +1,17 @@
/*
- * (c) 2005, 2006 Advanced Micro Devices, Inc.
+ * (c) 2005-2012 Advanced Micro Devices, Inc.
* Your use of this code is subject to the terms and conditions of the
* GNU general public license version 2. See "COPYING" or
* http://www.gnu.org/licenses/gpl.html
*
* Written by Jacob Shin - AMD, Inc.
*
- * Support : jacob.shin@amd.com
+ * Support: borislav.petkov@amd.com
*
* April 2006
* - added support for AMD Family 0x10 processors
+ * May 2012
+ * - major scrubbing
*
* All MC4_MISCi registers are shared between multi-cores
*/
@@ -25,6 +27,7 @@
#include <linux/cpu.h>
#include <linux/smp.h>
+#include <asm/amd_nb.h>
#include <asm/apic.h>
#include <asm/idle.h>
#include <asm/mce.h>
@@ -45,23 +48,15 @@
#define MASK_BLKPTR_LO 0xFF000000
#define MCG_XBLK_ADDR 0xC0000400
-struct threshold_block {
- unsigned int block;
- unsigned int bank;
- unsigned int cpu;
- u32 address;
- u16 interrupt_enable;
- bool interrupt_capable;
- u16 threshold_limit;
- struct kobject kobj;
- struct list_head miscj;
+static const char * const th_names[] = {
+ "load_store",
+ "insn_fetch",
+ "combined_unit",
+ "",
+ "northbridge",
+ "execution_unit",
};
-struct threshold_bank {
- struct kobject *kobj;
- struct threshold_block *blocks;
- cpumask_var_t cpus;
-};
static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
static unsigned char shared_bank[NR_BANKS] = {
@@ -84,6 +79,26 @@ struct thresh_restart {
u16 old_limit;
};
+static const char * const bank4_names(struct threshold_block *b)
+{
+ switch (b->address) {
+ /* MSR4_MISC0 */
+ case 0x00000413:
+ return "dram";
+
+ case 0xc0000408:
+ return "ht_links";
+
+ case 0xc0000409:
+ return "l3_cache";
+
+ default:
+ WARN(1, "Funny MSR: 0x%08x\n", b->address);
+ return "";
+ }
+};
+
+
static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits)
{
/*
@@ -224,8 +239,6 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
if (!block)
per_cpu(bank_map, cpu) |= (1 << bank);
- if (shared_bank[bank] && c->cpu_core_id)
- break;
memset(&b, 0, sizeof(b));
b.cpu = cpu;
@@ -326,7 +339,7 @@ struct threshold_attr {
#define SHOW_FIELDS(name) \
static ssize_t show_ ## name(struct threshold_block *b, char *buf) \
{ \
- return sprintf(buf, "%lx\n", (unsigned long) b->name); \
+ return sprintf(buf, "%lu\n", (unsigned long) b->name); \
}
SHOW_FIELDS(interrupt_enable)
SHOW_FIELDS(threshold_limit)
@@ -377,38 +390,21 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
return size;
}
-struct threshold_block_cross_cpu {
- struct threshold_block *tb;
- long retval;
-};
-
-static void local_error_count_handler(void *_tbcc)
-{
- struct threshold_block_cross_cpu *tbcc = _tbcc;
- struct threshold_block *b = tbcc->tb;
- u32 low, high;
-
- rdmsr(b->address, low, high);
- tbcc->retval = (high & 0xFFF) - (THRESHOLD_MAX - b->threshold_limit);
-}
-
static ssize_t show_error_count(struct threshold_block *b, char *buf)
{
- struct threshold_block_cross_cpu tbcc = { .tb = b, };
+ u32 lo, hi;
- smp_call_function_single(b->cpu, local_error_count_handler, &tbcc, 1);
- return sprintf(buf, "%lx\n", tbcc.retval);
-}
-
-static ssize_t store_error_count(struct threshold_block *b,
- const char *buf, size_t count)
-{
- struct thresh_restart tr = { .b = b, .reset = 1, .old_limit = 0 };
+ rdmsr_on_cpu(b->cpu, b->address, &lo, &hi);
- smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
- return 1;
+ return sprintf(buf, "%u\n", ((hi & THRESHOLD_MAX) -
+ (THRESHOLD_MAX - b->threshold_limit)));
}
+static struct threshold_attr error_count = {
+ .attr = {.name = __stringify(error_count), .mode = 0444 },
+ .show = show_error_count,
+};
+
#define RW_ATTR(val) \
static struct threshold_attr val = { \
.attr = {.name = __stringify(val), .mode = 0644 }, \
@@ -418,7 +414,6 @@ static struct threshold_attr val = { \
RW_ATTR(interrupt_enable);
RW_ATTR(threshold_limit);
-RW_ATTR(error_count);
static struct attribute *default_attrs[] = {
&threshold_limit.attr,
@@ -517,7 +512,7 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu,
err = kobject_init_and_add(&b->kobj, &threshold_ktype,
per_cpu(threshold_banks, cpu)[bank]->kobj,
- "misc%i", block);
+ (bank == 4 ? bank4_names(b) : th_names[bank]));
if (err)
goto out_free;
recurse:
@@ -548,98 +543,91 @@ out_free:
return err;
}
-static __cpuinit long
-local_allocate_threshold_blocks(int cpu, unsigned int bank)
+static __cpuinit int __threshold_add_blocks(struct threshold_bank *b)
{
- return allocate_threshold_blocks(cpu, bank, 0,
- MSR_IA32_MC0_MISC + bank * 4);
+ struct list_head *head = &b->blocks->miscj;
+ struct threshold_block *pos = NULL;
+ struct threshold_block *tmp = NULL;
+ int err = 0;
+
+ err = kobject_add(&b->blocks->kobj, b->kobj, b->blocks->kobj.name);
+ if (err)
+ return err;
+
+ list_for_each_entry_safe(pos, tmp, head, miscj) {
+
+ err = kobject_add(&pos->kobj, b->kobj, pos->kobj.name);
+ if (err) {
+ list_for_each_entry_safe_reverse(pos, tmp, head, miscj)
+ kobject_del(&pos->kobj);
+
+ return err;
+ }
+ }
+ return err;
}
-/* symlinks sibling shared banks to first core. first core owns dir/files. */
static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
{
- int i, err = 0;
- struct threshold_bank *b = NULL;
struct device *dev = per_cpu(mce_device, cpu);
- char name[32];
+ struct amd_northbridge *nb = NULL;
+ struct threshold_bank *b = NULL;
+ const char *name = th_names[bank];
+ int err = 0;
- sprintf(name, "threshold_bank%i", bank);
+ if (shared_bank[bank]) {
-#ifdef CONFIG_SMP
- if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
- i = cpumask_first(cpu_llc_shared_mask(cpu));
+ nb = node_to_amd_nb(amd_get_nb_id(cpu));
+ WARN_ON(!nb);
- /* first core not up yet */
- if (cpu_data(i).cpu_core_id)
- goto out;
+ /* threshold descriptor already initialized on this node? */
+ if (nb->bank4) {
+ /* yes, use it */
+ b = nb->bank4;
+ err = kobject_add(b->kobj, &dev->kobj, name);
+ if (err)
+ goto out;
- /* already linked */
- if (per_cpu(threshold_banks, cpu)[bank])
- goto out;
+ per_cpu(threshold_banks, cpu)[bank] = b;
+ atomic_inc(&b->cpus);
- b = per_cpu(threshold_banks, i)[bank];
+ err = __threshold_add_blocks(b);
- if (!b)
goto out;
-
- err = sysfs_create_link(&dev->kobj, b->kobj, name);
- if (err)
- goto out;
-
- cpumask_copy(b->cpus, cpu_llc_shared_mask(cpu));
- per_cpu(threshold_banks, cpu)[bank] = b;
-
- goto out;
+ }
}
-#endif
b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL);
if (!b) {
err = -ENOMEM;
goto out;
}
- if (!zalloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
- kfree(b);
- err = -ENOMEM;
- goto out;
- }
b->kobj = kobject_create_and_add(name, &dev->kobj);
- if (!b->kobj)
+ if (!b->kobj) {
+ err = -EINVAL;
goto out_free;
-
-#ifndef CONFIG_SMP
- cpumask_setall(b->cpus);
-#else
- cpumask_set_cpu(cpu, b->cpus);
-#endif
+ }
per_cpu(threshold_banks, cpu)[bank] = b;
- err = local_allocate_threshold_blocks(cpu, bank);
- if (err)
- goto out_free;
-
- for_each_cpu(i, b->cpus) {
- if (i == cpu)
- continue;
-
- dev = per_cpu(mce_device, i);
- if (dev)
- err = sysfs_create_link(&dev->kobj,b->kobj, name);
- if (err)
- goto out;
+ if (shared_bank[bank]) {
+ atomic_set(&b->cpus, 1);
- per_cpu(threshold_banks, i)[bank] = b;
+ /* nb is already initialized, see above */
+ WARN_ON(nb->bank4);
+ nb->bank4 = b;
}
- goto out;
+ err = allocate_threshold_blocks(cpu, bank, 0,
+ MSR_IA32_MC0_MISC + bank * 4);
+ if (!err)
+ goto out;
-out_free:
- per_cpu(threshold_banks, cpu)[bank] = NULL;
- free_cpumask_var(b->cpus);
+ out_free:
kfree(b);
-out:
+
+ out:
return err;
}
@@ -660,12 +648,6 @@ static __cpuinit int threshold_create_device(unsigned int cpu)
return err;
}
-/*
- * let's be hotplug friendly.
- * in case of multiple core processors, the first core always takes ownership
- * of shared sysfs dir/files, and rest of the cores will be symlinked to it.
- */
-
static void deallocate_threshold_block(unsigned int cpu,
unsigned int bank)
{
@@ -686,41 +668,42 @@ static void deallocate_threshold_block(unsigned int cpu,
per_cpu(threshold_banks, cpu)[bank]->blocks = NULL;
}
+static void __threshold_remove_blocks(struct threshold_bank *b)
+{
+ struct threshold_block *pos = NULL;
+ struct threshold_block *tmp = NULL;
+
+ kobject_del(b->kobj);
+
+ list_for_each_entry_safe(pos, tmp, &b->blocks->miscj, miscj)
+ kobject_del(&pos->kobj);
+}
+
static void threshold_remove_bank(unsigned int cpu, int bank)
{
+ struct amd_northbridge *nb;
struct threshold_bank *b;
- struct device *dev;
- char name[32];
- int i = 0;
b = per_cpu(threshold_banks, cpu)[bank];
if (!b)
return;
+
if (!b->blocks)
goto free_out;
- sprintf(name, "threshold_bank%i", bank);
-
-#ifdef CONFIG_SMP
- /* sibling symlink */
- if (shared_bank[bank] && b->blocks->cpu != cpu) {
- dev = per_cpu(mce_device, cpu);
- sysfs_remove_link(&dev->kobj, name);
- per_cpu(threshold_banks, cpu)[bank] = NULL;
-
- return;
- }
-#endif
-
- /* remove all sibling symlinks before unregistering */
- for_each_cpu(i, b->cpus) {
- if (i == cpu)
- continue;
-
- dev = per_cpu(mce_device, i);
- if (dev)
- sysfs_remove_link(&dev->kobj, name);
- per_cpu(threshold_banks, i)[bank] = NULL;
+ if (shared_bank[bank]) {
+ if (!atomic_dec_and_test(&b->cpus)) {
+ __threshold_remove_blocks(b);
+ per_cpu(threshold_banks, cpu)[bank] = NULL;
+ return;
+ } else {
+ /*
+ * the last CPU on this node using the shared bank is
+ * going away, remove that bank now.
+ */
+ nb = node_to_amd_nb(amd_get_nb_id(cpu));
+ nb->bank4 = NULL;
+ }
}
deallocate_threshold_block(cpu, bank);
@@ -728,7 +711,6 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
free_out:
kobject_del(b->kobj);
kobject_put(b->kobj);
- free_cpumask_var(b->cpus);
kfree(b);
per_cpu(threshold_banks, cpu)[bank] = NULL;
}
@@ -777,4 +759,24 @@ static __init int threshold_init_device(void)
return 0;
}
-device_initcall(threshold_init_device);
+/*
+ * there are 3 funcs which need to be _initcalled in a logic sequence:
+ * 1. xen_late_init_mcelog
+ * 2. mcheck_init_device
+ * 3. threshold_init_device
+ *
+ * xen_late_init_mcelog must register xen_mce_chrdev_device before
+ * native mce_chrdev_device registration if running under xen platform;
+ *
+ * mcheck_init_device should be inited before threshold_init_device to
+ * initialize mce_device, otherwise a NULL ptr dereference will cause panic.
+ *
+ * so we use following _initcalls
+ * 1. device_initcall(xen_late_init_mcelog);
+ * 2. device_initcall_sync(mcheck_init_device);
+ * 3. late_initcall(threshold_init_device);
+ *
+ * when running under xen, the initcall order is 1,2,3;
+ * on baremetal, we skip 1 and we do only 2 and 3.
+ */
+late_initcall(threshold_init_device);
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index bdda2e6c673..35ffda5d072 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -258,11 +258,11 @@ range_to_mtrr(unsigned int reg, unsigned long range_startk,
/* Compute the maximum size with which we can make a range: */
if (range_startk)
- max_align = ffs(range_startk) - 1;
+ max_align = __ffs(range_startk);
else
- max_align = 32;
+ max_align = BITS_PER_LONG - 1;
- align = fls(range_sizek) - 1;
+ align = __fls(range_sizek);
if (align > max_align)
align = max_align;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 75772ae6c65..e9fe907cd24 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -361,11 +361,7 @@ static void __init print_mtrr_state(void)
}
pr_debug("MTRR variable ranges %sabled:\n",
mtrr_state.enabled & 2 ? "en" : "dis");
- if (size_or_mask & 0xffffffffUL)
- high_width = ffs(size_or_mask & 0xffffffffUL) - 1;
- else
- high_width = ffs(size_or_mask>>32) + 32 - 1;
- high_width = (high_width - (32 - PAGE_SHIFT) + 3) / 4;
+ high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4;
for (i = 0; i < num_var_ranges; ++i) {
if (mtrr_state.var_ranges[i].mask_lo & (1 << 11))
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c4706cf9c01..915b876edd1 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -32,20 +32,11 @@
#include <asm/smp.h>
#include <asm/alternative.h>
#include <asm/timer.h>
+#include <asm/desc.h>
+#include <asm/ldt.h>
#include "perf_event.h"
-#if 0
-#undef wrmsrl
-#define wrmsrl(msr, val) \
-do { \
- trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\
- (unsigned long)(val)); \
- native_write_msr((msr), (u32)((u64)(val)), \
- (u32)((u64)(val) >> 32)); \
-} while (0)
-#endif
-
struct x86_pmu x86_pmu __read_mostly;
DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
@@ -74,7 +65,7 @@ u64 x86_perf_event_update(struct perf_event *event)
int idx = hwc->idx;
s64 delta;
- if (idx == X86_PMC_IDX_FIXED_BTS)
+ if (idx == INTEL_PMC_IDX_FIXED_BTS)
return 0;
/*
@@ -86,7 +77,7 @@ u64 x86_perf_event_update(struct perf_event *event)
*/
again:
prev_raw_count = local64_read(&hwc->prev_count);
- rdmsrl(hwc->event_base, new_raw_count);
+ rdpmcl(hwc->event_base_rdpmc, new_raw_count);
if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
new_raw_count) != prev_raw_count)
@@ -189,7 +180,7 @@ static void release_pmc_hardware(void) {}
static bool check_hw_exists(void)
{
- u64 val, val_new = 0;
+ u64 val, val_new = ~0;
int i, reg, ret = 0;
/*
@@ -222,8 +213,9 @@ static bool check_hw_exists(void)
* that don't trap on the MSR access and always return 0s.
*/
val = 0xabcdUL;
- ret = checking_wrmsrl(x86_pmu_event_addr(0), val);
- ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new);
+ reg = x86_pmu_event_addr(0);
+ ret = wrmsrl_safe(reg, val);
+ ret |= rdmsrl_safe(reg, &val_new);
if (ret || val != val_new)
goto msr_fail;
@@ -240,6 +232,7 @@ bios_fail:
msr_fail:
printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+ printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new);
return false;
}
@@ -388,7 +381,7 @@ int x86_pmu_hw_config(struct perf_event *event)
int precise = 0;
/* Support for constant skid */
- if (x86_pmu.pebs_active) {
+ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) {
precise++;
/* Support for IP fixup */
@@ -637,8 +630,8 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
c = sched->constraints[sched->state.event];
/* Prefer fixed purpose counters */
- if (x86_pmu.num_counters_fixed) {
- idx = X86_PMC_IDX_FIXED;
+ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
+ idx = INTEL_PMC_IDX_FIXED;
for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) {
if (!__test_and_set_bit(idx, sched->state.used))
goto done;
@@ -646,7 +639,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
}
/* Grab the first unused counter starting with idx */
idx = sched->state.counter;
- for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_FIXED) {
+ for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
if (!__test_and_set_bit(idx, sched->state.used))
goto done;
}
@@ -704,8 +697,8 @@ static bool perf_sched_next_event(struct perf_sched *sched)
/*
* Assign a counter for each event.
*/
-static int perf_assign_events(struct event_constraint **constraints, int n,
- int wmin, int wmax, int *assign)
+int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int *assign)
{
struct perf_sched sched;
@@ -824,15 +817,17 @@ static inline void x86_assign_hw_event(struct perf_event *event,
hwc->last_cpu = smp_processor_id();
hwc->last_tag = ++cpuc->tags[i];
- if (hwc->idx == X86_PMC_IDX_FIXED_BTS) {
+ if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
hwc->config_base = 0;
hwc->event_base = 0;
- } else if (hwc->idx >= X86_PMC_IDX_FIXED) {
+ } else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED);
+ hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
+ hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
} else {
hwc->config_base = x86_pmu_config_addr(hwc->idx);
hwc->event_base = x86_pmu_event_addr(hwc->idx);
+ hwc->event_base_rdpmc = hwc->idx;
}
}
@@ -930,7 +925,7 @@ int x86_perf_event_set_period(struct perf_event *event)
s64 period = hwc->sample_period;
int ret = 0, idx = hwc->idx;
- if (idx == X86_PMC_IDX_FIXED_BTS)
+ if (idx == INTEL_PMC_IDX_FIXED_BTS)
return 0;
/*
@@ -1316,7 +1311,6 @@ static struct attribute_group x86_pmu_format_group = {
static int __init init_hw_perf_events(void)
{
struct x86_pmu_quirk *quirk;
- struct event_constraint *c;
int err;
pr_info("Performance Events: ");
@@ -1347,21 +1341,8 @@ static int __init init_hw_perf_events(void)
for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
quirk->func();
- if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
- WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
- x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
- x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
- }
- x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
-
- if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
- WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
- x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
- x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
- }
-
- x86_pmu.intel_ctrl |=
- ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
+ if (!x86_pmu.intel_ctrl)
+ x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
perf_events_lapic_init();
register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
@@ -1370,22 +1351,6 @@ static int __init init_hw_perf_events(void)
__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
0, x86_pmu.num_counters, 0);
- if (x86_pmu.event_constraints) {
- /*
- * event on fixed counter2 (REF_CYCLES) only works on this
- * counter, so do not extend mask to generic counters
- */
- for_each_event_constraint(c, x86_pmu.event_constraints) {
- if (c->cmask != X86_RAW_EVENT_MASK
- || c->idxmsk64 == X86_PMC_MSK_FIXED_REF_CYCLES) {
- continue;
- }
-
- c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
- c->weight += x86_pmu.num_counters;
- }
- }
-
x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
@@ -1620,8 +1585,8 @@ static int x86_pmu_event_idx(struct perf_event *event)
if (!x86_pmu.attr_rdpmc)
return 0;
- if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
- idx -= X86_PMC_IDX_FIXED;
+ if (x86_pmu.num_counters_fixed && idx >= INTEL_PMC_IDX_FIXED) {
+ idx -= INTEL_PMC_IDX_FIXED;
idx |= 1 << 30;
}
@@ -1649,7 +1614,12 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
struct device_attribute *attr,
const char *buf, size_t count)
{
- unsigned long val = simple_strtoul(buf, NULL, 0);
+ unsigned long val;
+ ssize_t ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret)
+ return ret;
if (!!val != !!x86_pmu.attr_rdpmc) {
x86_pmu.attr_rdpmc = !!val;
@@ -1682,13 +1652,20 @@ static void x86_pmu_flush_branch_stack(void)
x86_pmu.flush_branch_stack();
}
+void perf_check_microcode(void)
+{
+ if (x86_pmu.check_microcode)
+ x86_pmu.check_microcode();
+}
+EXPORT_SYMBOL_GPL(perf_check_microcode);
+
static struct pmu pmu = {
.pmu_enable = x86_pmu_enable,
.pmu_disable = x86_pmu_disable,
- .attr_groups = x86_pmu_attr_groups,
+ .attr_groups = x86_pmu_attr_groups,
- .event_init = x86_pmu_event_init,
+ .event_init = x86_pmu_event_init,
.add = x86_pmu_add,
.del = x86_pmu_del,
@@ -1696,11 +1673,11 @@ static struct pmu pmu = {
.stop = x86_pmu_stop,
.read = x86_pmu_read,
- .start_txn = x86_pmu_start_txn,
- .cancel_txn = x86_pmu_cancel_txn,
- .commit_txn = x86_pmu_commit_txn,
+ .start_txn = x86_pmu_start_txn,
+ .cancel_txn = x86_pmu_cancel_txn,
+ .commit_txn = x86_pmu_commit_txn,
- .event_idx = x86_pmu_event_idx,
+ .event_idx = x86_pmu_event_idx,
.flush_branch_stack = x86_pmu_flush_branch_stack,
};
@@ -1763,6 +1740,29 @@ valid_user_frame(const void __user *fp, unsigned long size)
return (__range_not_ok(fp, size, TASK_SIZE) == 0);
}
+static unsigned long get_segment_base(unsigned int segment)
+{
+ struct desc_struct *desc;
+ int idx = segment >> 3;
+
+ if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+ if (idx > LDT_ENTRIES)
+ return 0;
+
+ if (idx > current->active_mm->context.size)
+ return 0;
+
+ desc = current->active_mm->context.ldt;
+ } else {
+ if (idx > GDT_ENTRIES)
+ return 0;
+
+ desc = __this_cpu_ptr(&gdt_page.gdt[0]);
+ }
+
+ return get_desc_base(desc + idx);
+}
+
#ifdef CONFIG_COMPAT
#include <asm/compat.h>
@@ -1771,13 +1771,17 @@ static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
/* 32-bit process in 64-bit kernel. */
+ unsigned long ss_base, cs_base;
struct stack_frame_ia32 frame;
const void __user *fp;
if (!test_thread_flag(TIF_IA32))
return 0;
- fp = compat_ptr(regs->bp);
+ cs_base = get_segment_base(regs->cs);
+ ss_base = get_segment_base(regs->ss);
+
+ fp = compat_ptr(ss_base + regs->bp);
while (entry->nr < PERF_MAX_STACK_DEPTH) {
unsigned long bytes;
frame.next_frame = 0;
@@ -1790,8 +1794,8 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
if (!valid_user_frame(fp, sizeof(frame)))
break;
- perf_callchain_store(entry, frame.return_address);
- fp = compat_ptr(frame.next_frame);
+ perf_callchain_store(entry, cs_base + frame.return_address);
+ fp = compat_ptr(ss_base + frame.next_frame);
}
return 1;
}
@@ -1814,6 +1818,12 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
return;
}
+ /*
+ * We don't know what to do with VM86 stacks.. ignore them for now.
+ */
+ if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
+ return;
+
fp = (void __user *)regs->bp;
perf_callchain_store(entry, regs->ip);
@@ -1841,16 +1851,50 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
}
}
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+/*
+ * Deal with code segment offsets for the various execution modes:
+ *
+ * VM86 - the good olde 16 bit days, where the linear address is
+ * 20 bits and we use regs->ip + 0x10 * regs->cs.
+ *
+ * IA32 - Where we need to look at GDT/LDT segment descriptor tables
+ * to figure out what the 32bit base address is.
+ *
+ * X32 - has TIF_X32 set, but is running in x86_64
+ *
+ * X86_64 - CS,DS,SS,ES are all zero based.
+ */
+static unsigned long code_segment_base(struct pt_regs *regs)
{
- unsigned long ip;
+ /*
+ * If we are in VM86 mode, add the segment offset to convert to a
+ * linear address.
+ */
+ if (regs->flags & X86_VM_MASK)
+ return 0x10 * regs->cs;
+
+ /*
+ * For IA32 we look at the GDT/LDT segment base to convert the
+ * effective IP to a linear address.
+ */
+#ifdef CONFIG_X86_32
+ if (user_mode(regs) && regs->cs != __USER_CS)
+ return get_segment_base(regs->cs);
+#else
+ if (test_thread_flag(TIF_IA32)) {
+ if (user_mode(regs) && regs->cs != __USER32_CS)
+ return get_segment_base(regs->cs);
+ }
+#endif
+ return 0;
+}
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
- ip = perf_guest_cbs->get_guest_ip();
- else
- ip = instruction_pointer(regs);
+ return perf_guest_cbs->get_guest_ip();
- return ip;
+ return regs->ip + code_segment_base(regs);
}
unsigned long perf_misc_flags(struct pt_regs *regs)
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 7241e2fc3c1..8b6defe7eef 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -14,6 +14,18 @@
#include <linux/perf_event.h>
+#if 0
+#undef wrmsrl
+#define wrmsrl(msr, val) \
+do { \
+ unsigned int _msr = (msr); \
+ u64 _val = (val); \
+ trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \
+ (unsigned long long)(_val)); \
+ native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \
+} while (0)
+#endif
+
/*
* | NHM/WSM | SNB |
* register -------------------------------
@@ -57,7 +69,7 @@ struct amd_nb {
};
/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS 4
+#define MAX_PEBS_EVENTS 8
/*
* A debug store configuration.
@@ -349,6 +361,8 @@ struct x86_pmu {
void (*cpu_starting)(int cpu);
void (*cpu_dying)(int cpu);
void (*cpu_dead)(int cpu);
+
+ void (*check_microcode)(void);
void (*flush_branch_stack)(void);
/*
@@ -360,12 +374,16 @@ struct x86_pmu {
/*
* Intel DebugStore bits
*/
- int bts, pebs;
- int bts_active, pebs_active;
+ unsigned int bts :1,
+ bts_active :1,
+ pebs :1,
+ pebs_active :1,
+ pebs_broken :1;
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
+ int max_pebs_events;
/*
* Intel LBR
@@ -468,6 +486,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
void x86_pmu_enable_all(int added);
+int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int *assign);
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
void x86_pmu_stop(struct perf_event *event, int flags);
@@ -496,6 +516,26 @@ static inline bool kernel_ip(unsigned long ip)
#endif
}
+/*
+ * Not all PMUs provide the right context information to place the reported IP
+ * into full context. Specifically segment registers are typically not
+ * supplied.
+ *
+ * Assuming the address is a linear address (it is for IBS), we fake the CS and
+ * vm86 mode using the known zero-based code segment and 'fix up' the registers
+ * to reflect this.
+ *
+ * Intel PEBS/LBR appear to typically provide the effective address, nothing
+ * much we can do about that but pray and treat it like a linear address.
+ */
+static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
+{
+ regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS;
+ if (regs->flags & X86_VM_MASK)
+ regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK);
+ regs->ip = ip;
+}
+
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
@@ -546,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[];
extern struct event_constraint intel_snb_pebs_event_constraints[];
+extern struct event_constraint intel_ivb_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 11a4eb9131d..4528ae7b6ec 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -366,7 +366,7 @@ static void amd_pmu_cpu_starting(int cpu)
cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
- if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15)
+ if (boot_cpu_data.x86_max_cores < 2)
return;
nb_id = amd_get_nb_id(cpu);
@@ -422,35 +422,6 @@ static struct attribute *amd_format_attr[] = {
NULL,
};
-static __initconst const struct x86_pmu amd_pmu = {
- .name = "AMD",
- .handle_irq = x86_pmu_handle_irq,
- .disable_all = x86_pmu_disable_all,
- .enable_all = x86_pmu_enable_all,
- .enable = x86_pmu_enable_event,
- .disable = x86_pmu_disable_event,
- .hw_config = amd_pmu_hw_config,
- .schedule_events = x86_schedule_events,
- .eventsel = MSR_K7_EVNTSEL0,
- .perfctr = MSR_K7_PERFCTR0,
- .event_map = amd_pmu_event_map,
- .max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_counters = AMD64_NUM_COUNTERS,
- .cntval_bits = 48,
- .cntval_mask = (1ULL << 48) - 1,
- .apic = 1,
- /* use highest bit to detect overflow */
- .max_period = (1ULL << 47) - 1,
- .get_event_constraints = amd_get_event_constraints,
- .put_event_constraints = amd_put_event_constraints,
-
- .format_attrs = amd_format_attr,
-
- .cpu_prepare = amd_pmu_cpu_prepare,
- .cpu_starting = amd_pmu_cpu_starting,
- .cpu_dead = amd_pmu_cpu_dead,
-};
-
/* AMD Family 15h */
#define AMD_EVENT_TYPE_MASK 0x000000F0ULL
@@ -597,8 +568,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
}
}
-static __initconst const struct x86_pmu amd_pmu_f15h = {
- .name = "AMD Family 15h",
+static __initconst const struct x86_pmu amd_pmu = {
+ .name = "AMD",
.handle_irq = x86_pmu_handle_irq,
.disable_all = x86_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
@@ -606,50 +577,68 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
.disable = x86_pmu_disable_event,
.hw_config = amd_pmu_hw_config,
.schedule_events = x86_schedule_events,
- .eventsel = MSR_F15H_PERF_CTL,
- .perfctr = MSR_F15H_PERF_CTR,
+ .eventsel = MSR_K7_EVNTSEL0,
+ .perfctr = MSR_K7_PERFCTR0,
.event_map = amd_pmu_event_map,
.max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_counters = AMD64_NUM_COUNTERS_F15H,
+ .num_counters = AMD64_NUM_COUNTERS,
.cntval_bits = 48,
.cntval_mask = (1ULL << 48) - 1,
.apic = 1,
/* use highest bit to detect overflow */
.max_period = (1ULL << 47) - 1,
- .get_event_constraints = amd_get_event_constraints_f15h,
- /* nortbridge counters not yet implemented: */
-#if 0
+ .get_event_constraints = amd_get_event_constraints,
.put_event_constraints = amd_put_event_constraints,
+ .format_attrs = amd_format_attr,
+
.cpu_prepare = amd_pmu_cpu_prepare,
- .cpu_dead = amd_pmu_cpu_dead,
-#endif
.cpu_starting = amd_pmu_cpu_starting,
- .format_attrs = amd_format_attr,
+ .cpu_dead = amd_pmu_cpu_dead,
};
+static int setup_event_constraints(void)
+{
+ if (boot_cpu_data.x86 >= 0x15)
+ x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
+ return 0;
+}
+
+static int setup_perfctr_core(void)
+{
+ if (!cpu_has_perfctr_core) {
+ WARN(x86_pmu.get_event_constraints == amd_get_event_constraints_f15h,
+ KERN_ERR "Odd, counter constraints enabled but no core perfctrs detected!");
+ return -ENODEV;
+ }
+
+ WARN(x86_pmu.get_event_constraints == amd_get_event_constraints,
+ KERN_ERR "hw perf events core counters need constraints handler!");
+
+ /*
+ * If core performance counter extensions exists, we must use
+ * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also
+ * x86_pmu_addr_offset().
+ */
+ x86_pmu.eventsel = MSR_F15H_PERF_CTL;
+ x86_pmu.perfctr = MSR_F15H_PERF_CTR;
+ x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE;
+
+ printk(KERN_INFO "perf: AMD core performance counters detected\n");
+
+ return 0;
+}
+
__init int amd_pmu_init(void)
{
/* Performance-monitoring supported from K7 and later: */
if (boot_cpu_data.x86 < 6)
return -ENODEV;
- /*
- * If core performance counter extensions exists, it must be
- * family 15h, otherwise fail. See x86_pmu_addr_offset().
- */
- switch (boot_cpu_data.x86) {
- case 0x15:
- if (!cpu_has_perfctr_core)
- return -ENODEV;
- x86_pmu = amd_pmu_f15h;
- break;
- default:
- if (cpu_has_perfctr_core)
- return -ENODEV;
- x86_pmu = amd_pmu;
- break;
- }
+ x86_pmu = amd_pmu;
+
+ setup_event_constraints();
+ setup_perfctr_core();
/* Events are common for all AMDs */
memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index da9bcdcd985..eebd5ffe1bb 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -13,6 +13,8 @@
#include <asm/apic.h>
+#include "perf_event.h"
+
static u32 ibs_caps;
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
@@ -207,6 +209,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
return -EOPNOTSUPP;
}
+static const struct perf_event_attr ibs_notsupp = {
+ .exclude_user = 1,
+ .exclude_kernel = 1,
+ .exclude_hv = 1,
+ .exclude_idle = 1,
+ .exclude_host = 1,
+ .exclude_guest = 1,
+};
+
static int perf_ibs_init(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
@@ -227,6 +238,9 @@ static int perf_ibs_init(struct perf_event *event)
if (event->pmu != &perf_ibs->pmu)
return -ENOENT;
+ if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp))
+ return -EINVAL;
+
if (config & ~perf_ibs->config_mask)
return -EINVAL;
@@ -536,7 +550,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) {
regs.flags &= ~PERF_EFLAGS_EXACT;
} else {
- instruction_pointer_set(&regs, ibs_data.regs[1]);
+ set_linear_ip(&regs, ibs_data.regs[1]);
regs.flags |= PERF_EFLAGS_EXACT;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 187c294bc65..6bca492b854 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -5,6 +5,8 @@
* among events on a single PMU.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/stddef.h>
#include <linux/types.h>
#include <linux/init.h>
@@ -21,14 +23,14 @@
*/
static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x003c,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x412e,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
- [PERF_COUNT_HW_BUS_CYCLES] = 0x013c,
- [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x003c,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x412e,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
+ [PERF_COUNT_HW_BUS_CYCLES] = 0x013c,
+ [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */
};
static struct event_constraint intel_core_event_constraints[] __read_mostly =
@@ -136,6 +138,84 @@ static u64 intel_pmu_event_map(int hw_event)
return intel_perfmon_event_map[hw_event];
}
+#define SNB_DMND_DATA_RD (1ULL << 0)
+#define SNB_DMND_RFO (1ULL << 1)
+#define SNB_DMND_IFETCH (1ULL << 2)
+#define SNB_DMND_WB (1ULL << 3)
+#define SNB_PF_DATA_RD (1ULL << 4)
+#define SNB_PF_RFO (1ULL << 5)
+#define SNB_PF_IFETCH (1ULL << 6)
+#define SNB_LLC_DATA_RD (1ULL << 7)
+#define SNB_LLC_RFO (1ULL << 8)
+#define SNB_LLC_IFETCH (1ULL << 9)
+#define SNB_BUS_LOCKS (1ULL << 10)
+#define SNB_STRM_ST (1ULL << 11)
+#define SNB_OTHER (1ULL << 15)
+#define SNB_RESP_ANY (1ULL << 16)
+#define SNB_NO_SUPP (1ULL << 17)
+#define SNB_LLC_HITM (1ULL << 18)
+#define SNB_LLC_HITE (1ULL << 19)
+#define SNB_LLC_HITS (1ULL << 20)
+#define SNB_LLC_HITF (1ULL << 21)
+#define SNB_LOCAL (1ULL << 22)
+#define SNB_REMOTE (0xffULL << 23)
+#define SNB_SNP_NONE (1ULL << 31)
+#define SNB_SNP_NOT_NEEDED (1ULL << 32)
+#define SNB_SNP_MISS (1ULL << 33)
+#define SNB_NO_FWD (1ULL << 34)
+#define SNB_SNP_FWD (1ULL << 35)
+#define SNB_HITM (1ULL << 36)
+#define SNB_NON_DRAM (1ULL << 37)
+
+#define SNB_DMND_READ (SNB_DMND_DATA_RD|SNB_LLC_DATA_RD)
+#define SNB_DMND_WRITE (SNB_DMND_RFO|SNB_LLC_RFO)
+#define SNB_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO)
+
+#define SNB_SNP_ANY (SNB_SNP_NONE|SNB_SNP_NOT_NEEDED| \
+ SNB_SNP_MISS|SNB_NO_FWD|SNB_SNP_FWD| \
+ SNB_HITM)
+
+#define SNB_DRAM_ANY (SNB_LOCAL|SNB_REMOTE|SNB_SNP_ANY)
+#define SNB_DRAM_REMOTE (SNB_REMOTE|SNB_SNP_ANY)
+
+#define SNB_L3_ACCESS SNB_RESP_ANY
+#define SNB_L3_MISS (SNB_DRAM_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 snb_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_L3_ACCESS,
+ [ C(RESULT_MISS) ] = SNB_DMND_READ|SNB_L3_MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_L3_ACCESS,
+ [ C(RESULT_MISS) ] = SNB_DMND_WRITE|SNB_L3_MISS,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_L3_ACCESS,
+ [ C(RESULT_MISS) ] = SNB_DMND_PREFETCH|SNB_L3_MISS,
+ },
+ },
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_DRAM_ANY,
+ [ C(RESULT_MISS) ] = SNB_DMND_READ|SNB_DRAM_REMOTE,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_DRAM_ANY,
+ [ C(RESULT_MISS) ] = SNB_DMND_WRITE|SNB_DRAM_REMOTE,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_DRAM_ANY,
+ [ C(RESULT_MISS) ] = SNB_DMND_PREFETCH|SNB_DRAM_REMOTE,
+ },
+ },
+};
+
static __initconst const u64 snb_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -233,16 +313,16 @@ static __initconst const u64 snb_hw_cache_event_ids
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
@@ -747,7 +827,7 @@ static void intel_pmu_disable_all(void)
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
- if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+ if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
intel_pmu_pebs_disable_all();
@@ -763,9 +843,9 @@ static void intel_pmu_enable_all(int added)
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
- if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+ if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
struct perf_event *event =
- cpuc->events[X86_PMC_IDX_FIXED_BTS];
+ cpuc->events[INTEL_PMC_IDX_FIXED_BTS];
if (WARN_ON_ONCE(!event))
return;
@@ -871,7 +951,7 @@ static inline void intel_pmu_ack_status(u64 ack)
static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
{
- int idx = hwc->idx - X86_PMC_IDX_FIXED;
+ int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
u64 ctrl_val, mask;
mask = 0xfULL << (idx * 4);
@@ -886,7 +966,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
+ if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
intel_pmu_disable_bts();
intel_pmu_drain_bts_buffer();
return;
@@ -915,7 +995,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
{
- int idx = hwc->idx - X86_PMC_IDX_FIXED;
+ int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
u64 ctrl_val, bits, mask;
/*
@@ -949,7 +1029,7 @@ static void intel_pmu_enable_event(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
+ if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
if (!__this_cpu_read(cpu_hw_events.enabled))
return;
@@ -1000,14 +1080,14 @@ static void intel_pmu_reset(void)
local_irq_save(flags);
- printk("clearing PMU state on CPU#%d\n", smp_processor_id());
+ pr_info("clearing PMU state on CPU#%d\n", smp_processor_id());
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- checking_wrmsrl(x86_pmu_config_addr(idx), 0ull);
- checking_wrmsrl(x86_pmu_event_addr(idx), 0ull);
+ wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
+ wrmsrl_safe(x86_pmu_event_addr(idx), 0ull);
}
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
- checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+ wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
if (ds)
ds->bts_index = ds->bts_buffer_base;
@@ -1442,8 +1522,16 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
+ /*
+ * If PMU counter has PEBS enabled it is not enough to disable counter
+ * on a guest entry since PEBS memory write can overshoot guest entry
+ * and corrupt guest memory. Disabling PEBS solves the problem.
+ */
+ arr[1].msr = MSR_IA32_PEBS_ENABLE;
+ arr[1].host = cpuc->pebs_enabled;
+ arr[1].guest = 0;
- *nr = 1;
+ *nr = 2;
return arr;
}
@@ -1707,16 +1795,61 @@ static __init void intel_clovertown_quirk(void)
* But taken together it might just make sense to not enable PEBS on
* these chips.
*/
- printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+ pr_warn("PEBS disabled due to CPU errata\n");
x86_pmu.pebs = 0;
x86_pmu.pebs_constraints = NULL;
}
+static int intel_snb_pebs_broken(int cpu)
+{
+ u32 rev = UINT_MAX; /* default to broken for unknown models */
+
+ switch (cpu_data(cpu).x86_model) {
+ case 42: /* SNB */
+ rev = 0x28;
+ break;
+
+ case 45: /* SNB-EP */
+ switch (cpu_data(cpu).x86_mask) {
+ case 6: rev = 0x618; break;
+ case 7: rev = 0x70c; break;
+ }
+ }
+
+ return (cpu_data(cpu).microcode < rev);
+}
+
+static void intel_snb_check_microcode(void)
+{
+ int pebs_broken = 0;
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ if ((pebs_broken = intel_snb_pebs_broken(cpu)))
+ break;
+ }
+ put_online_cpus();
+
+ if (pebs_broken == x86_pmu.pebs_broken)
+ return;
+
+ /*
+ * Serialized by the microcode lock..
+ */
+ if (x86_pmu.pebs_broken) {
+ pr_info("PEBS enabled due to microcode update\n");
+ x86_pmu.pebs_broken = 0;
+ } else {
+ pr_info("PEBS disabled due to CPU errata, please upgrade microcode\n");
+ x86_pmu.pebs_broken = 1;
+ }
+}
+
static __init void intel_sandybridge_quirk(void)
{
- printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
- x86_pmu.pebs = 0;
- x86_pmu.pebs_constraints = NULL;
+ x86_pmu.check_microcode = intel_snb_check_microcode;
+ intel_snb_check_microcode();
}
static const struct { int id; char *name; } intel_arch_events_map[] __initconst = {
@@ -1736,8 +1869,8 @@ static __init void intel_arch_events_quirk(void)
/* disable event that reported as not presend by cpuid */
for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(intel_arch_events_map)) {
intel_perfmon_event_map[intel_arch_events_map[bit].id] = 0;
- printk(KERN_WARNING "CPUID marked event: \'%s\' unavailable\n",
- intel_arch_events_map[bit].name);
+ pr_warn("CPUID marked event: \'%s\' unavailable\n",
+ intel_arch_events_map[bit].name);
}
}
@@ -1756,7 +1889,7 @@ static __init void intel_nehalem_quirk(void)
intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
ebx.split.no_branch_misses_retired = 0;
x86_pmu.events_maskl = ebx.full;
- printk(KERN_INFO "CPU erratum AAJ80 worked around\n");
+ pr_info("CPU erratum AAJ80 worked around\n");
}
}
@@ -1765,6 +1898,7 @@ __init int intel_pmu_init(void)
union cpuid10_edx edx;
union cpuid10_eax eax;
union cpuid10_ebx ebx;
+ struct event_constraint *c;
unsigned int unused;
int version;
@@ -1800,6 +1934,8 @@ __init int intel_pmu_init(void)
x86_pmu.events_maskl = ebx.full;
x86_pmu.events_mask_len = eax.split.mask_length;
+ x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
+
/*
* Quirk: v2 perfmon does not report fixed-purpose events, so
* assume at least 3 events:
@@ -1872,6 +2008,7 @@ __init int intel_pmu_init(void)
break;
case 28: /* Atom */
+ case 54: /* Cedariew */
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -1911,9 +2048,10 @@ __init int intel_pmu_init(void)
case 42: /* SandyBridge */
case 45: /* SandyBridge, "Romely-EP" */
x86_add_quirk(intel_sandybridge_quirk);
- case 58: /* IvyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
intel_pmu_lbr_init_snb();
@@ -1934,6 +2072,29 @@ __init int intel_pmu_init(void)
pr_cont("SandyBridge events, ");
break;
+ case 58: /* IvyBridge */
+ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+
+ intel_pmu_lbr_init_snb();
+
+ x86_pmu.event_constraints = intel_snb_event_constraints;
+ x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+ x86_pmu.extra_regs = intel_snb_extra_regs;
+ /* all extra regs are per-cpu when HT is on */
+ x86_pmu.er_flags |= ERF_HAS_RSP_1;
+ x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+ /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+ X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
+
+ pr_cont("IvyBridge events, ");
+ break;
+
default:
switch (x86_pmu.version) {
@@ -1951,5 +2112,37 @@ __init int intel_pmu_init(void)
}
}
+ if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
+ WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
+ x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
+ x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC;
+ }
+ x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+
+ if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) {
+ WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
+ x86_pmu.num_counters_fixed, INTEL_PMC_MAX_FIXED);
+ x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED;
+ }
+
+ x86_pmu.intel_ctrl |=
+ ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+
+ if (x86_pmu.event_constraints) {
+ /*
+ * event on fixed counter2 (REF_CYCLES) only works on this
+ * counter, so do not extend mask to generic counters
+ */
+ for_each_event_constraint(c, x86_pmu.event_constraints) {
+ if (c->cmask != X86_RAW_EVENT_MASK
+ || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+ continue;
+ }
+
+ c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+ c->weight += x86_pmu.num_counters;
+ }
+ }
+
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 35e2192df9f..826054a4f2e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -248,7 +248,7 @@ void reserve_ds_buffers(void)
*/
struct event_constraint bts_constraint =
- EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
+ EVENT_CONSTRAINT(0, 1ULL << INTEL_PMC_IDX_FIXED_BTS, 0);
void intel_pmu_enable_bts(u64 config)
{
@@ -295,7 +295,7 @@ int intel_pmu_drain_bts_buffer(void)
u64 to;
u64 flags;
};
- struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
+ struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS];
struct bts_record *at, *top;
struct perf_output_handle handle;
struct perf_event_header header;
@@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_ivb_pebs_event_constraints[] = {
+ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+ INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *c;
@@ -499,7 +513,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
* We sampled a branch insn, rewind using the LBR stack
*/
if (ip == to) {
- regs->ip = from;
+ set_linear_ip(regs, from);
return 1;
}
@@ -529,7 +543,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
} while (to < ip);
if (to == ip) {
- regs->ip = old_to;
+ set_linear_ip(regs, old_to);
return 1;
}
@@ -569,7 +583,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
* A possible PERF_SAMPLE_REGS will have to transfer all regs.
*/
regs = *iregs;
- regs.ip = pebs->ip;
+ regs.flags = pebs->flags;
+ set_linear_ip(&regs, pebs->ip);
regs.bp = pebs->bp;
regs.sp = pebs->sp;
@@ -620,7 +635,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
* Should not happen, we program the threshold at 1 and do not
* set a reset value.
*/
- WARN_ON_ONCE(n > 1);
+ WARN_ONCE(n > 1, "bad leftover pebs %d\n", n);
at += n - 1;
__intel_pmu_pebs_event(event, iregs, at);
@@ -651,10 +666,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
* Should not happen, we program the threshold at 1 and do not
* set a reset value.
*/
- WARN_ON_ONCE(n > MAX_PEBS_EVENTS);
+ WARN_ONCE(n > x86_pmu.max_pebs_events, "Unexpected number of pebs records %d\n", n);
for ( ; at < top; at++) {
- for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) {
+ for_each_set_bit(bit, (unsigned long *)&at->status, x86_pmu.max_pebs_events) {
event = cpuc->events[bit];
if (!test_bit(bit, cpuc->active_mask))
continue;
@@ -670,7 +685,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
break;
}
- if (!event || bit >= MAX_PEBS_EVENTS)
+ if (!event || bit >= x86_pmu.max_pebs_events)
continue;
__intel_pmu_pebs_event(event, iregs, at);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b4265fcd..da02e9cc375 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
* to have an operational LBR which can freeze
* on PMU interrupt
*/
- if (boot_cpu_data.x86_mask < 10) {
+ if (boot_cpu_data.x86_model == 28
+ && boot_cpu_data.x86_mask < 10) {
pr_cont("LBR disabled due to erratum");
return;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
new file mode 100644
index 00000000000..38e4894165b
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -0,0 +1,2921 @@
+#include "perf_event_intel_uncore.h"
+
+static struct intel_uncore_type *empty_uncore[] = { NULL, };
+static struct intel_uncore_type **msr_uncores = empty_uncore;
+static struct intel_uncore_type **pci_uncores = empty_uncore;
+/* pci bus to socket mapping */
+static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
+
+static DEFINE_RAW_SPINLOCK(uncore_box_lock);
+
+/* mask of cpus that collect uncore events */
+static cpumask_t uncore_cpu_mask;
+
+/* constraint for the fixed counter */
+static struct event_constraint constraint_fixed =
+ EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL);
+static struct event_constraint constraint_empty =
+ EVENT_CONSTRAINT(0, 0, 0);
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
+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(filter_tid, filter_tid, "config1:0-4");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+
+static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ u64 count;
+
+ rdmsrl(event->hw.event_base, count);
+
+ return count;
+}
+
+/*
+ * generic get constraint function for shared match/mask registers.
+ */
+static struct event_constraint *
+uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct intel_uncore_extra_reg *er;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+ unsigned long flags;
+ bool ok = false;
+
+ /*
+ * reg->alloc can be set due to existing state, so for fake box we
+ * need to ignore this, otherwise we might fail to allocate proper
+ * fake state for this extra reg constraint.
+ */
+ if (reg1->idx == EXTRA_REG_NONE ||
+ (!uncore_box_is_fake(box) && reg1->alloc))
+ return NULL;
+
+ er = &box->shared_regs[reg1->idx];
+ raw_spin_lock_irqsave(&er->lock, flags);
+ if (!atomic_read(&er->ref) ||
+ (er->config1 == reg1->config && er->config2 == reg2->config)) {
+ atomic_inc(&er->ref);
+ er->config1 = reg1->config;
+ er->config2 = reg2->config;
+ ok = true;
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ if (ok) {
+ if (!uncore_box_is_fake(box))
+ reg1->alloc = 1;
+ return NULL;
+ }
+
+ return &constraint_empty;
+}
+
+static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct intel_uncore_extra_reg *er;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+
+ /*
+ * Only put constraint if extra reg was actually allocated. Also
+ * takes care of event which do not use an extra shared reg.
+ *
+ * Also, if this is a fake box we shouldn't touch any event state
+ * (reg->alloc) and we don't care about leaving inconsistent box
+ * state either since it will be thrown out.
+ */
+ if (uncore_box_is_fake(box) || !reg1->alloc)
+ return;
+
+ er = &box->shared_regs[reg1->idx];
+ atomic_dec(&er->ref);
+ reg1->alloc = 0;
+}
+
+/* Sandy Bridge-EP uncore support */
+static struct intel_uncore_type snbep_uncore_cbox;
+static struct intel_uncore_type snbep_uncore_pcu;
+
+static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+ u32 config;
+
+ pci_read_config_dword(pdev, box_ctl, &config);
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ pci_write_config_dword(pdev, box_ctl, config);
+}
+
+static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+ u32 config;
+
+ pci_read_config_dword(pdev, box_ctl, &config);
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ pci_write_config_dword(pdev, box_ctl, config);
+}
+
+static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config);
+}
+
+static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ u64 count;
+
+ pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
+ pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
+
+ return count;
+}
+
+static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+
+ pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+ u64 config;
+ unsigned msr;
+
+ msr = uncore_msr_box_ctl(box);
+ if (msr) {
+ rdmsrl(msr, config);
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ wrmsrl(msr, config);
+ }
+}
+
+static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ u64 config;
+ unsigned msr;
+
+ msr = uncore_msr_box_ctl(box);
+ if (msr) {
+ rdmsrl(msr, config);
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ wrmsrl(msr, config);
+ }
+}
+
+static void snbep_uncore_msr_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 void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ wrmsrl(hwc->config_base, hwc->config);
+}
+
+static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+
+ if (msr)
+ wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static int snbep_uncore_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;
+
+ if (box->pmu->type == &snbep_uncore_cbox) {
+ reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+ SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 &
+ SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK;
+ } else {
+ if (box->pmu->type == &snbep_uncore_pcu) {
+ reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+ reg1->config = event->attr.config1 & SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK;
+ } else {
+ return 0;
+ }
+ }
+ reg1->idx = 0;
+
+ return 0;
+}
+
+static struct attribute *snbep_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_ubox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh5.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_cbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid.attr,
+ &format_attr_filter_nid.attr,
+ &format_attr_filter_state.attr,
+ &format_attr_filter_opc.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_pcu_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_occ_sel.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh5.attr,
+ &format_attr_occ_invert.attr,
+ &format_attr_occ_edge.attr,
+ &format_attr_filter_band0.attr,
+ &format_attr_filter_band1.attr,
+ &format_attr_filter_band2.attr,
+ &format_attr_filter_band3.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_qpi_formats_attr[] = {
+ &format_attr_event_ext.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct uncore_event_desc snbep_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+ { /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc snbep_uncore_qpi_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"),
+ INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
+ INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute_group snbep_uncore_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_ubox_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_cbox_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_pcu_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_qpi_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_qpi_formats_attr,
+};
+
+static struct intel_uncore_ops snbep_uncore_msr_ops = {
+ .init_box = snbep_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 = snbep_uncore_msr_enable_event,
+ .read_counter = uncore_msr_read_counter,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+ .hw_config = snbep_uncore_hw_config,
+};
+
+static struct intel_uncore_ops snbep_uncore_pci_ops = {
+ .init_box = snbep_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 event_constraint snbep_uncore_cbox_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x1b, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
+ EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
+ UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r2pcie_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snbep_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNBEP_U_MSR_PMON_CTR0,
+ .event_ctl = SNBEP_U_MSR_PMON_CTL0,
+ .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+ .ops = &snbep_uncore_msr_ops,
+ .format_group = &snbep_uncore_ubox_format_group,
+};
+
+static struct intel_uncore_type snbep_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .num_boxes = 8,
+ .perf_ctr_bits = 44,
+ .event_ctl = SNBEP_C0_MSR_PMON_CTL0,
+ .perf_ctr = SNBEP_C0_MSR_PMON_CTR0,
+ .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL,
+ .msr_offset = SNBEP_CBO_MSR_OFFSET,
+ .num_shared_regs = 1,
+ .constraints = snbep_uncore_cbox_constraints,
+ .ops = &snbep_uncore_msr_ops,
+ .format_group = &snbep_uncore_cbox_format_group,
+};
+
+static struct intel_uncore_type snbep_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0,
+ .event_ctl = SNBEP_PCU_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snbep_uncore_msr_ops,
+ .format_group = &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *snbep_msr_uncores[] = {
+ &snbep_uncore_ubox,
+ &snbep_uncore_cbox,
+ &snbep_uncore_pcu,
+ NULL,
+};
+
+#define SNBEP_UNCORE_PCI_COMMON_INIT() \
+ .perf_ctr = SNBEP_PCI_PMON_CTR0, \
+ .event_ctl = SNBEP_PCI_PMON_CTL0, \
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \
+ .ops = &snbep_uncore_pci_ops, \
+ .format_group = &snbep_uncore_format_group
+
+static struct intel_uncore_type snbep_uncore_ha = {
+ .name = "ha",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_imc = {
+ .name = "imc",
+ .num_counters = 4,
+ .num_boxes = 4,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+ .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+ .event_descs = snbep_uncore_imc_events,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_qpi = {
+ .name = "qpi",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .ops = &snbep_uncore_pci_ops,
+ .event_descs = snbep_uncore_qpi_events,
+ .format_group = &snbep_uncore_qpi_format_group,
+};
+
+
+static struct intel_uncore_type snbep_uncore_r2pcie = {
+ .name = "r2pcie",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .constraints = snbep_uncore_r2pcie_constraints,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_r3qpi = {
+ .name = "r3qpi",
+ .num_counters = 3,
+ .num_boxes = 2,
+ .perf_ctr_bits = 44,
+ .constraints = snbep_uncore_r3qpi_constraints,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type *snbep_pci_uncores[] = {
+ &snbep_uncore_ha,
+ &snbep_uncore_imc,
+ &snbep_uncore_qpi,
+ &snbep_uncore_r2pcie,
+ &snbep_uncore_r3qpi,
+ NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = {
+ { /* Home Agent */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
+ .driver_data = (unsigned long)&snbep_uncore_ha,
+ },
+ { /* MC Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
+ .driver_data = (unsigned long)&snbep_uncore_imc,
+ },
+ { /* MC Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
+ .driver_data = (unsigned long)&snbep_uncore_imc,
+ },
+ { /* MC Channel 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
+ .driver_data = (unsigned long)&snbep_uncore_imc,
+ },
+ { /* MC Channel 3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
+ .driver_data = (unsigned long)&snbep_uncore_imc,
+ },
+ { /* QPI Port 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
+ .driver_data = (unsigned long)&snbep_uncore_qpi,
+ },
+ { /* QPI Port 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
+ .driver_data = (unsigned long)&snbep_uncore_qpi,
+ },
+ { /* P2PCIe */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
+ .driver_data = (unsigned long)&snbep_uncore_r2pcie,
+ },
+ { /* R3QPI Link 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
+ .driver_data = (unsigned long)&snbep_uncore_r3qpi,
+ },
+ { /* R3QPI Link 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
+ .driver_data = (unsigned long)&snbep_uncore_r3qpi,
+ },
+ { /* end: all zeroes */ }
+};
+
+static struct pci_driver snbep_uncore_pci_driver = {
+ .name = "snbep_uncore",
+ .id_table = snbep_uncore_pci_ids,
+};
+
+/*
+ * build pci bus to socket mapping
+ */
+static void snbep_pci2phy_map_init(void)
+{
+ struct pci_dev *ubox_dev = NULL;
+ int i, bus, nodeid;
+ u32 config;
+
+ while (1) {
+ /* find the UBOX device */
+ ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX,
+ ubox_dev);
+ if (!ubox_dev)
+ break;
+ bus = ubox_dev->bus->number;
+ /* get the Node ID of the local register */
+ pci_read_config_dword(ubox_dev, 0x40, &config);
+ nodeid = config;
+ /* get the Node ID mapping */
+ pci_read_config_dword(ubox_dev, 0x54, &config);
+ /*
+ * every three bits in the Node ID mapping register maps
+ * to a particular node.
+ */
+ for (i = 0; i < 8; i++) {
+ if (nodeid == ((config >> (3 * i)) & 0x7)) {
+ pcibus_to_physid[bus] = i;
+ break;
+ }
+ }
+ };
+ return;
+}
+/* end of Sandy Bridge-EP uncore support */
+
+/* Sandy Bridge uncore support */
+static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+ wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+ else
+ wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+}
+
+static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ wrmsrl(event->hw.config_base, 0);
+}
+
+static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ if (box->pmu->pmu_idx == 0) {
+ wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+ SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+ }
+}
+
+static struct uncore_event_desc snb_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute *snb_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask5.attr,
+ NULL,
+};
+
+static struct attribute_group snb_uncore_format_group = {
+ .name = "format",
+ .attrs = snb_uncore_formats_attr,
+};
+
+static struct intel_uncore_ops snb_uncore_msr_ops = {
+ .init_box = snb_uncore_msr_init_box,
+ .disable_event = snb_uncore_msr_disable_event,
+ .enable_event = snb_uncore_msr_enable_event,
+ .read_counter = uncore_msr_read_counter,
+};
+
+static struct event_constraint snb_uncore_cbox_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snb_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 2,
+ .num_boxes = 4,
+ .perf_ctr_bits = 44,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNB_UNC_CBO_0_PER_CTR0,
+ .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
+ .fixed_ctr = SNB_UNC_FIXED_CTR,
+ .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
+ .single_fixed = 1,
+ .event_mask = SNB_UNC_RAW_EVENT_MASK,
+ .msr_offset = SNB_UNC_CBO_MSR_OFFSET,
+ .constraints = snb_uncore_cbox_constraints,
+ .ops = &snb_uncore_msr_ops,
+ .format_group = &snb_uncore_format_group,
+ .event_descs = snb_uncore_events,
+};
+
+static struct intel_uncore_type *snb_msr_uncores[] = {
+ &snb_uncore_cbox,
+ NULL,
+};
+/* end of Sandy Bridge uncore support */
+
+/* Nehalem uncore support */
+static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+}
+
+static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+}
+
+static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+ wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+ else
+ wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+}
+
+static struct attribute *nhm_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask8.attr,
+ NULL,
+};
+
+static struct attribute_group nhm_uncore_format_group = {
+ .name = "format",
+ .attrs = nhm_uncore_formats_attr,
+};
+
+static struct uncore_event_desc nhm_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhm_uncore_msr_ops = {
+ .disable_box = nhm_uncore_msr_disable_box,
+ .enable_box = nhm_uncore_msr_enable_box,
+ .disable_event = snb_uncore_msr_disable_event,
+ .enable_event = nhm_uncore_msr_enable_event,
+ .read_counter = uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type nhm_uncore = {
+ .name = "",
+ .num_counters = 8,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .event_ctl = NHM_UNC_PERFEVTSEL0,
+ .perf_ctr = NHM_UNC_UNCORE_PMC0,
+ .fixed_ctr = NHM_UNC_FIXED_CTR,
+ .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL,
+ .event_mask = NHM_UNC_RAW_EVENT_MASK,
+ .event_descs = nhm_uncore_events,
+ .ops = &nhm_uncore_msr_ops,
+ .format_group = &nhm_uncore_format_group,
+};
+
+static struct intel_uncore_type *nhm_msr_uncores[] = {
+ &nhm_uncore,
+ NULL,
+};
+/* end of Nehalem uncore support */
+
+/* Nehalem-EX uncore support */
+#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \
+ ((1ULL << (n)) - 1)))
+
+DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
+DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
+DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
+
+static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
+}
+
+static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+ u64 config;
+
+ if (msr) {
+ rdmsrl(msr, config);
+ config &= ~((1ULL << uncore_num_counters(box)) - 1);
+ /* WBox has a fixed counter */
+ if (uncore_msr_fixed_ctl(box))
+ config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
+ wrmsrl(msr, config);
+ }
+}
+
+static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+ u64 config;
+
+ if (msr) {
+ rdmsrl(msr, config);
+ config |= (1ULL << uncore_num_counters(box)) - 1;
+ /* WBox has a fixed counter */
+ if (uncore_msr_fixed_ctl(box))
+ config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
+ wrmsrl(msr, config);
+ }
+}
+
+static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ wrmsrl(event->hw.config_base, 0);
+}
+
+static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+ wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
+ else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
+ wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+ else
+ wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+#define NHMEX_UNCORE_OPS_COMMON_INIT() \
+ .init_box = nhmex_uncore_msr_init_box, \
+ .disable_box = nhmex_uncore_msr_disable_box, \
+ .enable_box = nhmex_uncore_msr_enable_box, \
+ .disable_event = nhmex_uncore_msr_disable_event, \
+ .read_counter = uncore_msr_read_counter
+
+static struct intel_uncore_ops nhmex_uncore_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_uncore_msr_enable_event,
+};
+
+static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_edge.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_ubox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_ubox_formats_attr,
+};
+
+static struct intel_uncore_type nhmex_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 1,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_U_MSR_PMON_EV_SEL,
+ .perf_ctr = NHMEX_U_MSR_PMON_CTR,
+ .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL,
+ .ops = &nhmex_uncore_ops,
+ .format_group = &nhmex_uncore_ubox_format_group
+};
+
+static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_cbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_cbox_formats_attr,
+};
+
+/* msr offset for each instance of cbox */
+static unsigned nhmex_cbox_msr_offsets[] = {
+ 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
+};
+
+static struct intel_uncore_type nhmex_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 6,
+ .num_boxes = 10,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0,
+ .perf_ctr = NHMEX_C0_MSR_PMON_CTR0,
+ .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL,
+ .msr_offsets = nhmex_cbox_msr_offsets,
+ .pair_ctr_ctl = 1,
+ .ops = &nhmex_uncore_ops,
+ .format_group = &nhmex_uncore_cbox_format_group
+};
+
+static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type nhmex_uncore_wbox = {
+ .name = "wbox",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_W_MSR_PMON_CNT0,
+ .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0,
+ .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR,
+ .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL,
+ .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_W_MSR_GLOBAL_CTL,
+ .pair_ctr_ctl = 1,
+ .event_descs = nhmex_uncore_wbox_events,
+ .ops = &nhmex_uncore_ops,
+ .format_group = &nhmex_uncore_cbox_format_group
+};
+
+static int nhmex_bbox_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;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+ int ctr, ev_sel;
+
+ ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
+ NHMEX_B_PMON_CTR_SHIFT;
+ ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
+ NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
+
+ /* events that do not use the match/mask registers */
+ if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
+ (ctr == 2 && ev_sel != 0x4) || ctr == 3)
+ return 0;
+
+ if (box->pmu->pmu_idx == 0)
+ reg1->reg = NHMEX_B0_MSR_MATCH;
+ else
+ reg1->reg = NHMEX_B1_MSR_MATCH;
+ reg1->idx = 0;
+ reg1->config = event->attr.config1;
+ reg2->config = event->attr.config2;
+ return 0;
+}
+
+static void nhmex_bbox_msr_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;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ wrmsrl(reg1->reg, reg1->config);
+ wrmsrl(reg1->reg + 1, reg2->config);
+ }
+ wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+ (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
+}
+
+/*
+ * The Bbox has 4 counters, but each counter monitors different events.
+ * Use bits 6-7 in the event config to select counter.
+ */
+static struct event_constraint nhmex_uncore_bbox_constraints[] = {
+ EVENT_CONSTRAINT(0 , 1, 0xc0),
+ EVENT_CONSTRAINT(0x40, 2, 0xc0),
+ EVENT_CONSTRAINT(0x80, 4, 0xc0),
+ EVENT_CONSTRAINT(0xc0, 8, 0xc0),
+ EVENT_CONSTRAINT_END,
+};
+
+static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
+ &format_attr_event5.attr,
+ &format_attr_counter.attr,
+ &format_attr_match.attr,
+ &format_attr_mask.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_bbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_bbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_bbox_msr_enable_event,
+ .hw_config = nhmex_bbox_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_bbox = {
+ .name = "bbox",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_B0_MSR_PMON_CTL0,
+ .perf_ctr = NHMEX_B0_MSR_PMON_CTR0,
+ .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL,
+ .msr_offset = NHMEX_B_MSR_OFFSET,
+ .pair_ctr_ctl = 1,
+ .num_shared_regs = 1,
+ .constraints = nhmex_uncore_bbox_constraints,
+ .ops = &nhmex_uncore_bbox_ops,
+ .format_group = &nhmex_uncore_bbox_format_group
+};
+
+static int nhmex_sbox_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;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ /* only TO_R_PROG_EV event uses the match/mask register */
+ if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
+ NHMEX_S_EVENT_TO_R_PROG_EV)
+ return 0;
+
+ if (box->pmu->pmu_idx == 0)
+ reg1->reg = NHMEX_S0_MSR_MM_CFG;
+ else
+ reg1->reg = NHMEX_S1_MSR_MM_CFG;
+ reg1->idx = 0;
+ reg1->config = event->attr.config1;
+ reg2->config = event->attr.config2;
+ return 0;
+}
+
+static void nhmex_sbox_msr_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;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ wrmsrl(reg1->reg, 0);
+ wrmsrl(reg1->reg + 1, reg1->config);
+ wrmsrl(reg1->reg + 2, reg2->config);
+ wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
+ }
+ wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+}
+
+static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_match.attr,
+ &format_attr_mask.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_sbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_sbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_sbox_msr_enable_event,
+ .hw_config = nhmex_sbox_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_sbox = {
+ .name = "sbox",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_S0_MSR_PMON_CTL0,
+ .perf_ctr = NHMEX_S0_MSR_PMON_CTR0,
+ .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL,
+ .msr_offset = NHMEX_S_MSR_OFFSET,
+ .pair_ctr_ctl = 1,
+ .num_shared_regs = 1,
+ .ops = &nhmex_uncore_sbox_ops,
+ .format_group = &nhmex_uncore_sbox_format_group
+};
+
+enum {
+ EXTRA_REG_NHMEX_M_FILTER,
+ EXTRA_REG_NHMEX_M_DSP,
+ EXTRA_REG_NHMEX_M_ISS,
+ EXTRA_REG_NHMEX_M_MAP,
+ EXTRA_REG_NHMEX_M_MSC_THR,
+ EXTRA_REG_NHMEX_M_PGT,
+ EXTRA_REG_NHMEX_M_PLD,
+ EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
+};
+
+static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
+ MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
+ MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
+ MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
+ MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
+ /* event 0xa uses two extra registers */
+ MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
+ MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
+ MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
+ /* events 0xd ~ 0x10 use the same extra register */
+ MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
+ MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
+ MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
+ MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
+ MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
+ MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
+ MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
+ MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
+ MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
+ EVENT_EXTRA_END
+};
+
+/* Nehalem-EX or Westmere-EX ? */
+bool uncore_nhmex;
+
+static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
+{
+ struct intel_uncore_extra_reg *er;
+ unsigned long flags;
+ bool ret = false;
+ u64 mask;
+
+ if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+ er = &box->shared_regs[idx];
+ raw_spin_lock_irqsave(&er->lock, flags);
+ if (!atomic_read(&er->ref) || er->config == config) {
+ atomic_inc(&er->ref);
+ er->config = config;
+ ret = true;
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ return ret;
+ }
+ /*
+ * The ZDP_CTL_FVC MSR has 4 fields which are used to control
+ * events 0xd ~ 0x10. Besides these 4 fields, there are additional
+ * fields which are shared.
+ */
+ idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ if (WARN_ON_ONCE(idx >= 4))
+ return false;
+
+ /* mask of the shared fields */
+ if (uncore_nhmex)
+ mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+ else
+ mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
+ er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+
+ raw_spin_lock_irqsave(&er->lock, flags);
+ /* add mask of the non-shared field if it's in use */
+ if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
+ if (uncore_nhmex)
+ mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ else
+ mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ }
+
+ if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
+ atomic_add(1 << (idx * 8), &er->ref);
+ if (uncore_nhmex)
+ mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+ NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ else
+ mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
+ WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ er->config &= ~mask;
+ er->config |= (config & mask);
+ ret = true;
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ return ret;
+}
+
+static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
+{
+ struct intel_uncore_extra_reg *er;
+
+ if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+ er = &box->shared_regs[idx];
+ atomic_dec(&er->ref);
+ return;
+ }
+
+ idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+ atomic_sub(1 << (idx * 8), &er->ref);
+}
+
+u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ int idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
+ u64 config = reg1->config;
+
+ /* get the non-shared control bits and shift them */
+ idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ if (uncore_nhmex)
+ config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ else
+ config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ if (new_idx > orig_idx) {
+ idx = new_idx - orig_idx;
+ config <<= 3 * idx;
+ } else {
+ idx = orig_idx - new_idx;
+ config >>= 3 * idx;
+ }
+
+ /* add the shared control bits back */
+ if (uncore_nhmex)
+ config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+ else
+ config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+ config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+ if (modify) {
+ /* adjust the main event selector */
+ if (new_idx > orig_idx)
+ hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+ else
+ hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+ reg1->config = config;
+ reg1->idx = ~0xff | new_idx;
+ }
+ return config;
+}
+
+static struct event_constraint *
+nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+ int i, idx[2], alloc = 0;
+ u64 config1 = reg1->config;
+
+ idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
+ idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
+again:
+ for (i = 0; i < 2; i++) {
+ if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+ idx[i] = 0xff;
+
+ if (idx[i] == 0xff)
+ continue;
+
+ if (!nhmex_mbox_get_shared_reg(box, idx[i],
+ __BITS_VALUE(config1, i, 32)))
+ goto fail;
+ alloc |= (0x1 << i);
+ }
+
+ /* for the match/mask registers */
+ if (reg2->idx != EXTRA_REG_NONE &&
+ (uncore_box_is_fake(box) || !reg2->alloc) &&
+ !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
+ goto fail;
+
+ /*
+ * If it's a fake box -- as per validate_{group,event}() we
+ * shouldn't touch event state and we can avoid doing so
+ * since both will only call get_event_constraints() once
+ * on each event, this avoids the need for reg->alloc.
+ */
+ if (!uncore_box_is_fake(box)) {
+ if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
+ nhmex_mbox_alter_er(event, idx[0], true);
+ reg1->alloc |= alloc;
+ if (reg2->idx != EXTRA_REG_NONE)
+ reg2->alloc = 1;
+ }
+ return NULL;
+fail:
+ if (idx[0] != 0xff && !(alloc & 0x1) &&
+ idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+ /*
+ * events 0xd ~ 0x10 are functional identical, but are
+ * controlled by different fields in the ZDP_CTL_FVC
+ * register. If we failed to take one field, try the
+ * rest 3 choices.
+ */
+ BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
+ idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ idx[0] = (idx[0] + 1) % 4;
+ idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
+ config1 = nhmex_mbox_alter_er(event, idx[0], false);
+ goto again;
+ }
+ }
+
+ if (alloc & 0x1)
+ nhmex_mbox_put_shared_reg(box, idx[0]);
+ if (alloc & 0x2)
+ nhmex_mbox_put_shared_reg(box, idx[1]);
+ return &constraint_empty;
+}
+
+static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+
+ if (uncore_box_is_fake(box))
+ return;
+
+ if (reg1->alloc & 0x1)
+ nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
+ if (reg1->alloc & 0x2)
+ nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
+ reg1->alloc = 0;
+
+ if (reg2->alloc) {
+ nhmex_mbox_put_shared_reg(box, reg2->idx);
+ reg2->alloc = 0;
+ }
+}
+
+static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
+{
+ if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+ return er->idx;
+ return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
+}
+
+static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct intel_uncore_type *type = box->pmu->type;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+ struct extra_reg *er;
+ unsigned msr;
+ int reg_idx = 0;
+ /*
+ * The mbox events may require 2 extra MSRs at the most. But only
+ * the lower 32 bits in these MSRs are significant, so we can use
+ * config1 to pass two MSRs' config.
+ */
+ for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
+ if (er->event != (event->hw.config & er->config_mask))
+ continue;
+ if (event->attr.config1 & ~er->valid_mask)
+ return -EINVAL;
+
+ msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
+ if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
+ return -EINVAL;
+
+ /* always use the 32~63 bits to pass the PLD config */
+ if (er->idx == EXTRA_REG_NHMEX_M_PLD)
+ reg_idx = 1;
+ else if (WARN_ON_ONCE(reg_idx > 0))
+ return -EINVAL;
+
+ reg1->idx &= ~(0xff << (reg_idx * 8));
+ reg1->reg &= ~(0xffff << (reg_idx * 16));
+ reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
+ reg1->reg |= msr << (reg_idx * 16);
+ reg1->config = event->attr.config1;
+ reg_idx++;
+ }
+ /*
+ * The mbox only provides ability to perform address matching
+ * for the PLD events.
+ */
+ if (reg_idx == 2) {
+ reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+ if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+ reg2->config = event->attr.config2;
+ else
+ reg2->config = ~0ULL;
+ if (box->pmu->pmu_idx == 0)
+ reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+ else
+ reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+ }
+ return 0;
+}
+
+static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+ struct intel_uncore_extra_reg *er;
+ unsigned long flags;
+ u64 config;
+
+ if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+ return box->shared_regs[idx].config;
+
+ er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+ raw_spin_lock_irqsave(&er->lock, flags);
+ config = er->config;
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+ return config;
+}
+
+static void nhmex_mbox_msr_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;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+ int idx;
+
+ idx = __BITS_VALUE(reg1->idx, 0, 8);
+ if (idx != 0xff)
+ wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
+ nhmex_mbox_shared_reg_config(box, idx));
+ idx = __BITS_VALUE(reg1->idx, 1, 8);
+ if (idx != 0xff)
+ wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
+ nhmex_mbox_shared_reg_config(box, idx));
+
+ if (reg2->idx != EXTRA_REG_NONE) {
+ wrmsrl(reg2->reg, 0);
+ if (reg2->config != ~0ULL) {
+ wrmsrl(reg2->reg + 1,
+ reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+ wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+ (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+ wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+ }
+ }
+
+ wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63");
+
+static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
+ &format_attr_count_mode.attr,
+ &format_attr_storage_mode.attr,
+ &format_attr_wrap_mode.attr,
+ &format_attr_flag_mode.attr,
+ &format_attr_inc_sel.attr,
+ &format_attr_set_flag_sel.attr,
+ &format_attr_filter_cfg_en.attr,
+ &format_attr_filter_match.attr,
+ &format_attr_filter_mask.attr,
+ &format_attr_dsp.attr,
+ &format_attr_thr.attr,
+ &format_attr_fvc.attr,
+ &format_attr_pgt.attr,
+ &format_attr_map.attr,
+ &format_attr_iss.attr,
+ &format_attr_pld.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_mbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_mbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
+ INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
+ INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
+ { /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
+ INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
+ INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_mbox_msr_enable_event,
+ .hw_config = nhmex_mbox_hw_config,
+ .get_constraint = nhmex_mbox_get_constraint,
+ .put_constraint = nhmex_mbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_mbox = {
+ .name = "mbox",
+ .num_counters = 6,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_M0_MSR_PMU_CTL0,
+ .perf_ctr = NHMEX_M0_MSR_PMU_CNT0,
+ .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL,
+ .msr_offset = NHMEX_M_MSR_OFFSET,
+ .pair_ctr_ctl = 1,
+ .num_shared_regs = 8,
+ .event_descs = nhmex_uncore_mbox_events,
+ .ops = &nhmex_uncore_mbox_ops,
+ .format_group = &nhmex_uncore_mbox_format_group,
+};
+
+void nhmex_rbox_alter_er(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 port;
+
+ /* adjust the main event selector and extra register index */
+ if (reg1->idx % 2) {
+ reg1->idx--;
+ hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+ } else {
+ reg1->idx++;
+ hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+ }
+
+ /* adjust extra register config */
+ port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
+ switch (reg1->idx % 6) {
+ case 2:
+ /* shift the 8~15 bits to the 0~7 bits */
+ reg1->config >>= 8;
+ break;
+ case 3:
+ /* shift the 0~7 bits to the 8~15 bits */
+ reg1->config <<= 8;
+ break;
+ };
+}
+
+/*
+ * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
+ * An event set consists of 6 events, the 3rd and 4th events in
+ * an event set use the same extra register. So an event set uses
+ * 5 extra registers.
+ */
+static struct event_constraint *
+nhmex_rbox_get_constraint(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;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+ struct intel_uncore_extra_reg *er;
+ unsigned long flags;
+ int idx, er_idx;
+ u64 config1;
+ bool ok = false;
+
+ if (!uncore_box_is_fake(box) && reg1->alloc)
+ return NULL;
+
+ idx = reg1->idx % 6;
+ config1 = reg1->config;
+again:
+ er_idx = idx;
+ /* the 3rd and 4th events use the same extra register */
+ if (er_idx > 2)
+ er_idx--;
+ er_idx += (reg1->idx / 6) * 5;
+
+ er = &box->shared_regs[er_idx];
+ raw_spin_lock_irqsave(&er->lock, flags);
+ if (idx < 2) {
+ if (!atomic_read(&er->ref) || er->config == reg1->config) {
+ atomic_inc(&er->ref);
+ er->config = reg1->config;
+ ok = true;
+ }
+ } else if (idx == 2 || idx == 3) {
+ /*
+ * these two events use different fields in a extra register,
+ * the 0~7 bits and the 8~15 bits respectively.
+ */
+ u64 mask = 0xff << ((idx - 2) * 8);
+ if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
+ !((er->config ^ config1) & mask)) {
+ atomic_add(1 << ((idx - 2) * 8), &er->ref);
+ er->config &= ~mask;
+ er->config |= config1 & mask;
+ ok = true;
+ }
+ } else {
+ if (!atomic_read(&er->ref) ||
+ (er->config == (hwc->config >> 32) &&
+ er->config1 == reg1->config &&
+ er->config2 == reg2->config)) {
+ atomic_inc(&er->ref);
+ er->config = (hwc->config >> 32);
+ er->config1 = reg1->config;
+ er->config2 = reg2->config;
+ ok = true;
+ }
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ if (!ok) {
+ /*
+ * The Rbox events are always in pairs. The paired
+ * events are functional identical, but use different
+ * extra registers. If we failed to take an extra
+ * register, try the alternative.
+ */
+ if (idx % 2)
+ idx--;
+ else
+ idx++;
+ if (idx != reg1->idx % 6) {
+ if (idx == 2)
+ config1 >>= 8;
+ else if (idx == 3)
+ config1 <<= 8;
+ goto again;
+ }
+ } else {
+ if (!uncore_box_is_fake(box)) {
+ if (idx != reg1->idx % 6)
+ nhmex_rbox_alter_er(box, event);
+ reg1->alloc = 1;
+ }
+ return NULL;
+ }
+ return &constraint_empty;
+}
+
+static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct intel_uncore_extra_reg *er;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ int idx, er_idx;
+
+ if (uncore_box_is_fake(box) || !reg1->alloc)
+ return;
+
+ idx = reg1->idx % 6;
+ er_idx = idx;
+ if (er_idx > 2)
+ er_idx--;
+ er_idx += (reg1->idx / 6) * 5;
+
+ er = &box->shared_regs[er_idx];
+ if (idx == 2 || idx == 3)
+ atomic_sub(1 << ((idx - 2) * 8), &er->ref);
+ else
+ atomic_dec(&er->ref);
+
+ reg1->alloc = 0;
+}
+
+static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+ int idx;
+
+ idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
+ NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+ if (idx >= 0x18)
+ return -EINVAL;
+
+ reg1->idx = idx;
+ reg1->config = event->attr.config1;
+
+ switch (idx % 6) {
+ case 4:
+ case 5:
+ hwc->config |= event->attr.config & (~0ULL << 32);
+ reg2->config = event->attr.config2;
+ break;
+ };
+ return 0;
+}
+
+static u64 nhmex_rbox_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+ struct intel_uncore_extra_reg *er;
+ unsigned long flags;
+ u64 config;
+
+ er = &box->shared_regs[idx];
+
+ raw_spin_lock_irqsave(&er->lock, flags);
+ config = er->config;
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ return config;
+}
+
+static void nhmex_rbox_msr_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;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+ int idx, port;
+
+ idx = reg1->idx;
+ port = idx / 6 + box->pmu->pmu_idx * 4;
+
+ switch (idx % 6) {
+ case 0:
+ wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+ break;
+ case 1:
+ wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
+ break;
+ case 2:
+ case 3:
+ wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+ nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5));
+ break;
+ case 4:
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+ hwc->config >> 32);
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+ break;
+ case 5:
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+ hwc->config >> 32);
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
+ break;
+ };
+
+ wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+ (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
+DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
+
+static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
+ &format_attr_event5.attr,
+ &format_attr_xbr_mm_cfg.attr,
+ &format_attr_xbr_match.attr,
+ &format_attr_xbr_mask.attr,
+ &format_attr_qlx_cfg.attr,
+ &format_attr_iperf_cfg.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_rbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_rbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
+ INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"),
+ INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"),
+ INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"),
+ INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"),
+ INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"),
+ INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_rbox_msr_enable_event,
+ .hw_config = nhmex_rbox_hw_config,
+ .get_constraint = nhmex_rbox_get_constraint,
+ .put_constraint = nhmex_rbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_rbox = {
+ .name = "rbox",
+ .num_counters = 8,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_R_MSR_PMON_CTL0,
+ .perf_ctr = NHMEX_R_MSR_PMON_CNT0,
+ .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_R_MSR_GLOBAL_CTL,
+ .msr_offset = NHMEX_R_MSR_OFFSET,
+ .pair_ctr_ctl = 1,
+ .num_shared_regs = 20,
+ .event_descs = nhmex_uncore_rbox_events,
+ .ops = &nhmex_uncore_rbox_ops,
+ .format_group = &nhmex_uncore_rbox_format_group
+};
+
+static struct intel_uncore_type *nhmex_msr_uncores[] = {
+ &nhmex_uncore_ubox,
+ &nhmex_uncore_cbox,
+ &nhmex_uncore_bbox,
+ &nhmex_uncore_sbox,
+ &nhmex_uncore_mbox,
+ &nhmex_uncore_rbox,
+ &nhmex_uncore_wbox,
+ NULL,
+};
+/* end of Nehalem-EX uncore support */
+
+static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ hwc->idx = idx;
+ hwc->last_tag = ++box->tags[idx];
+
+ if (hwc->idx == UNCORE_PMC_IDX_FIXED) {
+ hwc->event_base = uncore_fixed_ctr(box);
+ hwc->config_base = uncore_fixed_ctl(box);
+ return;
+ }
+
+ hwc->config_base = uncore_event_ctl(box, hwc->idx);
+ hwc->event_base = uncore_perf_ctr(box, hwc->idx);
+}
+
+static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
+{
+ u64 prev_count, new_count, delta;
+ int shift;
+
+ if (event->hw.idx >= UNCORE_PMC_IDX_FIXED)
+ shift = 64 - uncore_fixed_ctr_bits(box);
+ else
+ shift = 64 - uncore_perf_ctr_bits(box);
+
+ /* the hrtimer might modify the previous event value */
+again:
+ prev_count = local64_read(&event->hw.prev_count);
+ new_count = uncore_read_counter(box, event);
+ if (local64_xchg(&event->hw.prev_count, new_count) != prev_count)
+ goto again;
+
+ delta = (new_count << shift) - (prev_count << shift);
+ delta >>= shift;
+
+ local64_add(delta, &event->count);
+}
+
+/*
+ * The overflow interrupt is unavailable for SandyBridge-EP, is broken
+ * for SandyBridge. So we use hrtimer to periodically poll the counter
+ * to avoid overflow.
+ */
+static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
+{
+ struct intel_uncore_box *box;
+ unsigned long flags;
+ int bit;
+
+ box = container_of(hrtimer, struct intel_uncore_box, hrtimer);
+ if (!box->n_active || box->cpu != smp_processor_id())
+ return HRTIMER_NORESTART;
+ /*
+ * disable local interrupt to prevent uncore_pmu_event_start/stop
+ * to interrupt the update process
+ */
+ local_irq_save(flags);
+
+ for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
+ uncore_perf_event_update(box, box->events[bit]);
+
+ local_irq_restore(flags);
+
+ hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL));
+ return HRTIMER_RESTART;
+}
+
+static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
+{
+ __hrtimer_start_range_ns(&box->hrtimer,
+ ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0,
+ HRTIMER_MODE_REL_PINNED, 0);
+}
+
+static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
+{
+ hrtimer_cancel(&box->hrtimer);
+}
+
+static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
+{
+ hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ box->hrtimer.function = uncore_pmu_hrtimer;
+}
+
+struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
+{
+ struct intel_uncore_box *box;
+ int i, size;
+
+ size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
+
+ box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu));
+ if (!box)
+ return NULL;
+
+ for (i = 0; i < type->num_shared_regs; i++)
+ raw_spin_lock_init(&box->shared_regs[i].lock);
+
+ uncore_pmu_init_hrtimer(box);
+ atomic_set(&box->refcnt, 1);
+ box->cpu = -1;
+ box->phys_id = -1;
+
+ return box;
+}
+
+static struct intel_uncore_box *
+uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+{
+ static struct intel_uncore_box *box;
+
+ box = *per_cpu_ptr(pmu->box, cpu);
+ if (box)
+ return box;
+
+ raw_spin_lock(&uncore_box_lock);
+ list_for_each_entry(box, &pmu->box_list, list) {
+ if (box->phys_id == topology_physical_package_id(cpu)) {
+ atomic_inc(&box->refcnt);
+ *per_cpu_ptr(pmu->box, cpu) = box;
+ break;
+ }
+ }
+ raw_spin_unlock(&uncore_box_lock);
+
+ return *per_cpu_ptr(pmu->box, cpu);
+}
+
+static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+{
+ return container_of(event->pmu, struct intel_uncore_pmu, pmu);
+}
+
+static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+{
+ /*
+ * perf core schedules event on the basis of cpu, uncore events are
+ * collected by one of the cpus inside a physical package.
+ */
+ return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+}
+
+static int
+uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
+{
+ struct perf_event *event;
+ int n, max_count;
+
+ max_count = box->pmu->type->num_counters;
+ if (box->pmu->type->fixed_ctl)
+ max_count++;
+
+ if (box->n_events >= max_count)
+ return -EINVAL;
+
+ n = box->n_events;
+ box->event_list[n] = leader;
+ n++;
+ if (!dogrp)
+ return n;
+
+ list_for_each_entry(event, &leader->sibling_list, group_entry) {
+ if (event->state <= PERF_EVENT_STATE_OFF)
+ continue;
+
+ if (n >= max_count)
+ return -EINVAL;
+
+ box->event_list[n] = event;
+ n++;
+ }
+ return n;
+}
+
+static struct event_constraint *
+uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct intel_uncore_type *type = box->pmu->type;
+ struct event_constraint *c;
+
+ if (type->ops->get_constraint) {
+ c = type->ops->get_constraint(box, event);
+ if (c)
+ return c;
+ }
+
+ if (event->hw.config == ~0ULL)
+ return &constraint_fixed;
+
+ if (type->constraints) {
+ for_each_event_constraint(c, type->constraints) {
+ if ((event->hw.config & c->cmask) == c->code)
+ return c;
+ }
+ }
+
+ return &type->unconstrainted;
+}
+
+static void uncore_put_event_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ if (box->pmu->type->ops->put_constraint)
+ box->pmu->type->ops->put_constraint(box, event);
+}
+
+static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int n)
+{
+ unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
+ struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX];
+ int i, wmin, wmax, ret = 0;
+ struct hw_perf_event *hwc;
+
+ bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
+
+ for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
+ c = uncore_get_event_constraint(box, box->event_list[i]);
+ constraints[i] = c;
+ wmin = min(wmin, c->weight);
+ wmax = max(wmax, c->weight);
+ }
+
+ /* fastpath, try to reuse previous register */
+ for (i = 0; i < n; i++) {
+ hwc = &box->event_list[i]->hw;
+ c = constraints[i];
+
+ /* never assigned */
+ if (hwc->idx == -1)
+ break;
+
+ /* constraint still honored */
+ if (!test_bit(hwc->idx, c->idxmsk))
+ break;
+
+ /* not already used */
+ if (test_bit(hwc->idx, used_mask))
+ break;
+
+ __set_bit(hwc->idx, used_mask);
+ if (assign)
+ assign[i] = hwc->idx;
+ }
+ /* slow path */
+ if (i != n)
+ ret = perf_assign_events(constraints, n, wmin, wmax, assign);
+
+ if (!assign || ret) {
+ for (i = 0; i < n; i++)
+ uncore_put_event_constraint(box, box->event_list[i]);
+ }
+ return ret ? -EINVAL : 0;
+}
+
+static void uncore_pmu_event_start(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ int idx = event->hw.idx;
+
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ return;
+
+ if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
+ return;
+
+ event->hw.state = 0;
+ box->events[idx] = event;
+ box->n_active++;
+ __set_bit(idx, box->active_mask);
+
+ local64_set(&event->hw.prev_count, uncore_read_counter(box, event));
+ uncore_enable_event(box, event);
+
+ if (box->n_active == 1) {
+ uncore_enable_box(box);
+ uncore_pmu_start_hrtimer(box);
+ }
+}
+
+static void uncore_pmu_event_stop(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (__test_and_clear_bit(hwc->idx, box->active_mask)) {
+ uncore_disable_event(box, event);
+ box->n_active--;
+ box->events[hwc->idx] = NULL;
+ WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+ hwc->state |= PERF_HES_STOPPED;
+
+ if (box->n_active == 0) {
+ uncore_disable_box(box);
+ uncore_pmu_cancel_hrtimer(box);
+ }
+ }
+
+ if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+ /*
+ * Drain the remaining delta count out of a event
+ * that we are disabling:
+ */
+ uncore_perf_event_update(box, event);
+ hwc->state |= PERF_HES_UPTODATE;
+ }
+}
+
+static int uncore_pmu_event_add(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ struct hw_perf_event *hwc = &event->hw;
+ int assign[UNCORE_PMC_IDX_MAX];
+ int i, n, ret;
+
+ if (!box)
+ return -ENODEV;
+
+ ret = n = uncore_collect_events(box, event, false);
+ if (ret < 0)
+ return ret;
+
+ hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+ if (!(flags & PERF_EF_START))
+ hwc->state |= PERF_HES_ARCH;
+
+ ret = uncore_assign_events(box, assign, n);
+ if (ret)
+ return ret;
+
+ /* save events moving to new counters */
+ for (i = 0; i < box->n_events; i++) {
+ event = box->event_list[i];
+ hwc = &event->hw;
+
+ if (hwc->idx == assign[i] &&
+ hwc->last_tag == box->tags[assign[i]])
+ continue;
+ /*
+ * Ensure we don't accidentally enable a stopped
+ * counter simply because we rescheduled.
+ */
+ if (hwc->state & PERF_HES_STOPPED)
+ hwc->state |= PERF_HES_ARCH;
+
+ uncore_pmu_event_stop(event, PERF_EF_UPDATE);
+ }
+
+ /* reprogram moved events into new counters */
+ for (i = 0; i < n; i++) {
+ event = box->event_list[i];
+ hwc = &event->hw;
+
+ if (hwc->idx != assign[i] ||
+ hwc->last_tag != box->tags[assign[i]])
+ uncore_assign_hw_event(box, event, assign[i]);
+ else if (i < box->n_events)
+ continue;
+
+ if (hwc->state & PERF_HES_ARCH)
+ continue;
+
+ uncore_pmu_event_start(event, 0);
+ }
+ box->n_events = n;
+
+ return 0;
+}
+
+static void uncore_pmu_event_del(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ int i;
+
+ uncore_pmu_event_stop(event, PERF_EF_UPDATE);
+
+ for (i = 0; i < box->n_events; i++) {
+ if (event == box->event_list[i]) {
+ uncore_put_event_constraint(box, event);
+
+ while (++i < box->n_events)
+ box->event_list[i - 1] = box->event_list[i];
+
+ --box->n_events;
+ break;
+ }
+ }
+
+ event->hw.idx = -1;
+ event->hw.last_tag = ~0ULL;
+}
+
+static void uncore_pmu_event_read(struct perf_event *event)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ uncore_perf_event_update(box, event);
+}
+
+/*
+ * validation ensures the group can be loaded onto the
+ * PMU if it was the only group available.
+ */
+static int uncore_validate_group(struct intel_uncore_pmu *pmu,
+ struct perf_event *event)
+{
+ struct perf_event *leader = event->group_leader;
+ struct intel_uncore_box *fake_box;
+ int ret = -EINVAL, n;
+
+ fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+ if (!fake_box)
+ return -ENOMEM;
+
+ fake_box->pmu = pmu;
+ /*
+ * the event is not yet connected with its
+ * siblings therefore we must first collect
+ * existing siblings, then add the new event
+ * before we can simulate the scheduling
+ */
+ n = uncore_collect_events(fake_box, leader, true);
+ if (n < 0)
+ goto out;
+
+ fake_box->n_events = n;
+ n = uncore_collect_events(fake_box, event, false);
+ if (n < 0)
+ goto out;
+
+ fake_box->n_events = n;
+
+ ret = uncore_assign_events(fake_box, NULL, n);
+out:
+ kfree(fake_box);
+ return ret;
+}
+
+int uncore_pmu_event_init(struct perf_event *event)
+{
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ struct hw_perf_event *hwc = &event->hw;
+ int ret;
+
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ pmu = uncore_event_to_pmu(event);
+ /* no device found for this pmu */
+ if (pmu->func_id < 0)
+ return -ENOENT;
+
+ /*
+ * Uncore PMU does measure at all privilege level all the time.
+ * So it doesn't make sense to specify any exclude bits.
+ */
+ if (event->attr.exclude_user || event->attr.exclude_kernel ||
+ event->attr.exclude_hv || event->attr.exclude_idle)
+ return -EINVAL;
+
+ /* Sampling not supported yet */
+ if (hwc->sample_period)
+ return -EINVAL;
+
+ /*
+ * Place all uncore events for a particular physical package
+ * onto a single cpu
+ */
+ if (event->cpu < 0)
+ return -EINVAL;
+ box = uncore_pmu_to_box(pmu, event->cpu);
+ if (!box || box->cpu < 0)
+ return -EINVAL;
+ event->cpu = box->cpu;
+
+ event->hw.idx = -1;
+ event->hw.last_tag = ~0ULL;
+ event->hw.extra_reg.idx = EXTRA_REG_NONE;
+ event->hw.branch_reg.idx = EXTRA_REG_NONE;
+
+ if (event->attr.config == UNCORE_FIXED_EVENT) {
+ /* no fixed counter */
+ if (!pmu->type->fixed_ctl)
+ return -EINVAL;
+ /*
+ * if there is only one fixed counter, only the first pmu
+ * can access the fixed counter
+ */
+ if (pmu->type->single_fixed && pmu->pmu_idx > 0)
+ return -EINVAL;
+ hwc->config = ~0ULL;
+ } else {
+ hwc->config = event->attr.config & pmu->type->event_mask;
+ if (pmu->type->ops->hw_config) {
+ ret = pmu->type->ops->hw_config(box, event);
+ if (ret)
+ return ret;
+ }
+ }
+
+ if (event->group_leader != event)
+ ret = uncore_validate_group(pmu, event);
+ else
+ ret = 0;
+
+ return ret;
+}
+
+static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
+{
+ int ret;
+
+ pmu->pmu = (struct pmu) {
+ .attr_groups = pmu->type->attr_groups,
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = uncore_pmu_event_init,
+ .add = uncore_pmu_event_add,
+ .del = uncore_pmu_event_del,
+ .start = uncore_pmu_event_start,
+ .stop = uncore_pmu_event_stop,
+ .read = uncore_pmu_event_read,
+ };
+
+ if (pmu->type->num_boxes == 1) {
+ if (strlen(pmu->type->name) > 0)
+ sprintf(pmu->name, "uncore_%s", pmu->type->name);
+ else
+ sprintf(pmu->name, "uncore");
+ } else {
+ sprintf(pmu->name, "uncore_%s_%d", pmu->type->name,
+ pmu->pmu_idx);
+ }
+
+ ret = perf_pmu_register(&pmu->pmu, pmu->name, -1);
+ return ret;
+}
+
+static void __init uncore_type_exit(struct intel_uncore_type *type)
+{
+ int i;
+
+ for (i = 0; i < type->num_boxes; i++)
+ free_percpu(type->pmus[i].box);
+ kfree(type->pmus);
+ type->pmus = NULL;
+ kfree(type->attr_groups[1]);
+ type->attr_groups[1] = NULL;
+}
+
+static void __init uncore_types_exit(struct intel_uncore_type **types)
+{
+ int i;
+ for (i = 0; types[i]; i++)
+ uncore_type_exit(types[i]);
+}
+
+static int __init uncore_type_init(struct intel_uncore_type *type)
+{
+ struct intel_uncore_pmu *pmus;
+ struct attribute_group *events_group;
+ struct attribute **attrs;
+ int i, j;
+
+ pmus = kzalloc(sizeof(*pmus) * type->num_boxes, GFP_KERNEL);
+ if (!pmus)
+ return -ENOMEM;
+
+ type->unconstrainted = (struct event_constraint)
+ __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
+ 0, type->num_counters, 0);
+
+ for (i = 0; i < type->num_boxes; i++) {
+ pmus[i].func_id = -1;
+ pmus[i].pmu_idx = i;
+ pmus[i].type = type;
+ INIT_LIST_HEAD(&pmus[i].box_list);
+ pmus[i].box = alloc_percpu(struct intel_uncore_box *);
+ if (!pmus[i].box)
+ goto fail;
+ }
+
+ if (type->event_descs) {
+ i = 0;
+ while (type->event_descs[i].attr.attr.name)
+ i++;
+
+ events_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
+ sizeof(*events_group), GFP_KERNEL);
+ if (!events_group)
+ goto fail;
+
+ attrs = (struct attribute **)(events_group + 1);
+ events_group->name = "events";
+ events_group->attrs = attrs;
+
+ for (j = 0; j < i; j++)
+ attrs[j] = &type->event_descs[j].attr.attr;
+
+ type->attr_groups[1] = events_group;
+ }
+
+ type->pmus = pmus;
+ return 0;
+fail:
+ uncore_type_exit(type);
+ return -ENOMEM;
+}
+
+static int __init uncore_types_init(struct intel_uncore_type **types)
+{
+ int i, ret;
+
+ for (i = 0; types[i]; i++) {
+ ret = uncore_type_init(types[i]);
+ if (ret)
+ goto fail;
+ }
+ return 0;
+fail:
+ while (--i >= 0)
+ uncore_type_exit(types[i]);
+ return ret;
+}
+
+static struct pci_driver *uncore_pci_driver;
+static bool pcidrv_registered;
+
+/*
+ * add a pci uncore device
+ */
+static int __devinit uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
+{
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, phys_id;
+
+ phys_id = pcibus_to_physid[pdev->bus->number];
+ if (phys_id < 0)
+ return -ENODEV;
+
+ box = uncore_alloc_box(type, 0);
+ if (!box)
+ return -ENOMEM;
+
+ /*
+ * for performance monitoring unit with multiple boxes,
+ * each box has a different function id.
+ */
+ for (i = 0; i < type->num_boxes; i++) {
+ pmu = &type->pmus[i];
+ if (pmu->func_id == pdev->devfn)
+ break;
+ if (pmu->func_id < 0) {
+ pmu->func_id = pdev->devfn;
+ break;
+ }
+ pmu = NULL;
+ }
+
+ if (!pmu) {
+ kfree(box);
+ return -EINVAL;
+ }
+
+ box->phys_id = phys_id;
+ box->pci_dev = pdev;
+ box->pmu = pmu;
+ uncore_box_init(box);
+ pci_set_drvdata(pdev, box);
+
+ raw_spin_lock(&uncore_box_lock);
+ list_add_tail(&box->list, &pmu->box_list);
+ raw_spin_unlock(&uncore_box_lock);
+
+ return 0;
+}
+
+static void uncore_pci_remove(struct pci_dev *pdev)
+{
+ struct intel_uncore_box *box = pci_get_drvdata(pdev);
+ struct intel_uncore_pmu *pmu = box->pmu;
+ int cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+
+ if (WARN_ON_ONCE(phys_id != box->phys_id))
+ return;
+
+ raw_spin_lock(&uncore_box_lock);
+ list_del(&box->list);
+ raw_spin_unlock(&uncore_box_lock);
+
+ for_each_possible_cpu(cpu) {
+ if (*per_cpu_ptr(pmu->box, cpu) == box) {
+ *per_cpu_ptr(pmu->box, cpu) = NULL;
+ atomic_dec(&box->refcnt);
+ }
+ }
+
+ WARN_ON_ONCE(atomic_read(&box->refcnt) != 1);
+ kfree(box);
+}
+
+static int __devinit uncore_pci_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ struct intel_uncore_type *type;
+
+ type = (struct intel_uncore_type *)id->driver_data;
+
+ return uncore_pci_add(type, pdev);
+}
+
+static int __init uncore_pci_init(void)
+{
+ int ret;
+
+ switch (boot_cpu_data.x86_model) {
+ case 45: /* Sandy Bridge-EP */
+ pci_uncores = snbep_pci_uncores;
+ uncore_pci_driver = &snbep_uncore_pci_driver;
+ snbep_pci2phy_map_init();
+ break;
+ default:
+ return 0;
+ }
+
+ ret = uncore_types_init(pci_uncores);
+ if (ret)
+ return ret;
+
+ uncore_pci_driver->probe = uncore_pci_probe;
+ uncore_pci_driver->remove = uncore_pci_remove;
+
+ ret = pci_register_driver(uncore_pci_driver);
+ if (ret == 0)
+ pcidrv_registered = true;
+ else
+ uncore_types_exit(pci_uncores);
+
+ return ret;
+}
+
+static void __init uncore_pci_exit(void)
+{
+ if (pcidrv_registered) {
+ pcidrv_registered = false;
+ pci_unregister_driver(uncore_pci_driver);
+ uncore_types_exit(pci_uncores);
+ }
+}
+
+static void __cpuinit uncore_cpu_dying(int cpu)
+{
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, j;
+
+ for (i = 0; msr_uncores[i]; i++) {
+ type = msr_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ box = *per_cpu_ptr(pmu->box, cpu);
+ *per_cpu_ptr(pmu->box, cpu) = NULL;
+ if (box && atomic_dec_and_test(&box->refcnt))
+ kfree(box);
+ }
+ }
+}
+
+static int __cpuinit uncore_cpu_starting(int cpu)
+{
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box, *exist;
+ int i, j, k, phys_id;
+
+ phys_id = topology_physical_package_id(cpu);
+
+ for (i = 0; msr_uncores[i]; i++) {
+ type = msr_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ box = *per_cpu_ptr(pmu->box, cpu);
+ /* called by uncore_cpu_init? */
+ if (box && box->phys_id >= 0) {
+ uncore_box_init(box);
+ continue;
+ }
+
+ for_each_online_cpu(k) {
+ exist = *per_cpu_ptr(pmu->box, k);
+ if (exist && exist->phys_id == phys_id) {
+ atomic_inc(&exist->refcnt);
+ *per_cpu_ptr(pmu->box, cpu) = exist;
+ kfree(box);
+ box = NULL;
+ break;
+ }
+ }
+
+ if (box) {
+ box->phys_id = phys_id;
+ uncore_box_init(box);
+ }
+ }
+ }
+ return 0;
+}
+
+static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id)
+{
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, j;
+
+ for (i = 0; msr_uncores[i]; i++) {
+ type = msr_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ if (pmu->func_id < 0)
+ pmu->func_id = j;
+
+ box = uncore_alloc_box(type, cpu);
+ if (!box)
+ return -ENOMEM;
+
+ box->pmu = pmu;
+ box->phys_id = phys_id;
+ *per_cpu_ptr(pmu->box, cpu) = box;
+ }
+ }
+ return 0;
+}
+
+static void __cpuinit
+uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_cpu)
+{
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, j;
+
+ for (i = 0; uncores[i]; i++) {
+ type = uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ if (old_cpu < 0)
+ box = uncore_pmu_to_box(pmu, new_cpu);
+ else
+ box = uncore_pmu_to_box(pmu, old_cpu);
+ if (!box)
+ continue;
+
+ if (old_cpu < 0) {
+ WARN_ON_ONCE(box->cpu != -1);
+ box->cpu = new_cpu;
+ continue;
+ }
+
+ WARN_ON_ONCE(box->cpu != old_cpu);
+ if (new_cpu >= 0) {
+ uncore_pmu_cancel_hrtimer(box);
+ perf_pmu_migrate_context(&pmu->pmu,
+ old_cpu, new_cpu);
+ box->cpu = new_cpu;
+ } else {
+ box->cpu = -1;
+ }
+ }
+ }
+}
+
+static void __cpuinit uncore_event_exit_cpu(int cpu)
+{
+ int i, phys_id, target;
+
+ /* if exiting cpu is used for collecting uncore events */
+ if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
+ return;
+
+ /* find a new cpu to collect uncore events */
+ phys_id = topology_physical_package_id(cpu);
+ target = -1;
+ for_each_online_cpu(i) {
+ if (i == cpu)
+ continue;
+ if (phys_id == topology_physical_package_id(i)) {
+ target = i;
+ break;
+ }
+ }
+
+ /* migrate uncore events to the new cpu */
+ if (target >= 0)
+ cpumask_set_cpu(target, &uncore_cpu_mask);
+
+ uncore_change_context(msr_uncores, cpu, target);
+ uncore_change_context(pci_uncores, cpu, target);
+}
+
+static void __cpuinit uncore_event_init_cpu(int cpu)
+{
+ int i, phys_id;
+
+ phys_id = topology_physical_package_id(cpu);
+ for_each_cpu(i, &uncore_cpu_mask) {
+ if (phys_id == topology_physical_package_id(i))
+ return;
+ }
+
+ cpumask_set_cpu(cpu, &uncore_cpu_mask);
+
+ uncore_change_context(msr_uncores, -1, cpu);
+ uncore_change_context(pci_uncores, -1, cpu);
+}
+
+static int
+ __cpuinit uncore_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+ unsigned int cpu = (long)hcpu;
+
+ /* allocate/free data structure for uncore box */
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_UP_PREPARE:
+ uncore_cpu_prepare(cpu, -1);
+ break;
+ case CPU_STARTING:
+ uncore_cpu_starting(cpu);
+ break;
+ case CPU_UP_CANCELED:
+ case CPU_DYING:
+ uncore_cpu_dying(cpu);
+ break;
+ default:
+ break;
+ }
+
+ /* select the cpu that collects uncore events */
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DOWN_FAILED:
+ case CPU_STARTING:
+ uncore_event_init_cpu(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ uncore_event_exit_cpu(cpu);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block uncore_cpu_nb __cpuinitdata = {
+ .notifier_call = uncore_cpu_notifier,
+ /*
+ * to migrate uncore events, our notifier should be executed
+ * before perf core's notifier.
+ */
+ .priority = CPU_PRI_PERF + 1,
+};
+
+static void __init uncore_cpu_setup(void *dummy)
+{
+ uncore_cpu_starting(smp_processor_id());
+}
+
+static int __init uncore_cpu_init(void)
+{
+ int ret, cpu, max_cores;
+
+ max_cores = boot_cpu_data.x86_max_cores;
+ switch (boot_cpu_data.x86_model) {
+ case 26: /* Nehalem */
+ case 30:
+ case 37: /* Westmere */
+ case 44:
+ msr_uncores = nhm_msr_uncores;
+ break;
+ case 42: /* Sandy Bridge */
+ if (snb_uncore_cbox.num_boxes > max_cores)
+ snb_uncore_cbox.num_boxes = max_cores;
+ msr_uncores = snb_msr_uncores;
+ break;
+ case 45: /* Sandy Birdge-EP */
+ if (snbep_uncore_cbox.num_boxes > max_cores)
+ snbep_uncore_cbox.num_boxes = max_cores;
+ msr_uncores = snbep_msr_uncores;
+ break;
+ case 46: /* Nehalem-EX */
+ uncore_nhmex = true;
+ case 47: /* Westmere-EX aka. Xeon E7 */
+ if (!uncore_nhmex)
+ nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
+ if (nhmex_uncore_cbox.num_boxes > max_cores)
+ nhmex_uncore_cbox.num_boxes = max_cores;
+ msr_uncores = nhmex_msr_uncores;
+ break;
+ default:
+ return 0;
+ }
+
+ ret = uncore_types_init(msr_uncores);
+ if (ret)
+ return ret;
+
+ get_online_cpus();
+
+ for_each_online_cpu(cpu) {
+ int i, phys_id = topology_physical_package_id(cpu);
+
+ for_each_cpu(i, &uncore_cpu_mask) {
+ if (phys_id == topology_physical_package_id(i)) {
+ phys_id = -1;
+ break;
+ }
+ }
+ if (phys_id < 0)
+ continue;
+
+ uncore_cpu_prepare(cpu, phys_id);
+ uncore_event_init_cpu(cpu);
+ }
+ on_each_cpu(uncore_cpu_setup, NULL, 1);
+
+ register_cpu_notifier(&uncore_cpu_nb);
+
+ put_online_cpus();
+
+ return 0;
+}
+
+static int __init uncore_pmus_register(void)
+{
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_type *type;
+ int i, j;
+
+ for (i = 0; msr_uncores[i]; i++) {
+ type = msr_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ uncore_pmu_register(pmu);
+ }
+ }
+
+ for (i = 0; pci_uncores[i]; i++) {
+ type = pci_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ uncore_pmu_register(pmu);
+ }
+ }
+
+ return 0;
+}
+
+static int __init intel_uncore_init(void)
+{
+ int ret;
+
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return -ENODEV;
+
+ ret = uncore_pci_init();
+ if (ret)
+ goto fail;
+ ret = uncore_cpu_init();
+ if (ret) {
+ uncore_pci_exit();
+ goto fail;
+ }
+
+ uncore_pmus_register();
+ return 0;
+fail:
+ return ret;
+}
+device_initcall(intel_uncore_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
new file mode 100644
index 00000000000..5b81c1856aa
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -0,0 +1,619 @@
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/perf_event.h>
+#include "perf_event.h"
+
+#define UNCORE_PMU_NAME_LEN 32
+#define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC)
+
+#define UNCORE_FIXED_EVENT 0xff
+#define UNCORE_PMC_IDX_MAX_GENERIC 8
+#define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC
+#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1)
+
+#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
+
+/* SNB event control */
+#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
+#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00
+#define SNB_UNC_CTL_EDGE_DET (1 << 18)
+#define SNB_UNC_CTL_EN (1 << 22)
+#define SNB_UNC_CTL_INVERT (1 << 23)
+#define SNB_UNC_CTL_CMASK_MASK 0x1f000000
+#define NHM_UNC_CTL_CMASK_MASK 0xff000000
+#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0)
+
+#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \
+ SNB_UNC_CTL_UMASK_MASK | \
+ SNB_UNC_CTL_EDGE_DET | \
+ SNB_UNC_CTL_INVERT | \
+ SNB_UNC_CTL_CMASK_MASK)
+
+#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \
+ SNB_UNC_CTL_UMASK_MASK | \
+ SNB_UNC_CTL_EDGE_DET | \
+ SNB_UNC_CTL_INVERT | \
+ NHM_UNC_CTL_CMASK_MASK)
+
+/* SNB global control register */
+#define SNB_UNC_PERF_GLOBAL_CTL 0x391
+#define SNB_UNC_FIXED_CTR_CTRL 0x394
+#define SNB_UNC_FIXED_CTR 0x395
+
+/* SNB uncore global control */
+#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1)
+#define SNB_UNC_GLOBAL_CTL_EN (1 << 29)
+
+/* SNB Cbo register */
+#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700
+#define SNB_UNC_CBO_0_PER_CTR0 0x706
+#define SNB_UNC_CBO_MSR_OFFSET 0x10
+
+/* NHM global control register */
+#define NHM_UNC_PERF_GLOBAL_CTL 0x391
+#define NHM_UNC_FIXED_CTR 0x394
+#define NHM_UNC_FIXED_CTR_CTRL 0x395
+
+/* NHM uncore global control */
+#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1)
+#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32)
+
+/* NHM uncore register */
+#define NHM_UNC_PERFEVTSEL0 0x3c0
+#define NHM_UNC_UNCORE_PMC0 0x3b0
+
+/* SNB-EP Box level control */
+#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0)
+#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1)
+#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8)
+#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16)
+#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \
+ SNBEP_PMON_BOX_CTL_RST_CTRS | \
+ SNBEP_PMON_BOX_CTL_FRZ_EN)
+/* SNB-EP event control */
+#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff
+#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00
+#define SNBEP_PMON_CTL_RST (1 << 17)
+#define SNBEP_PMON_CTL_EDGE_DET (1 << 18)
+#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) /* only for QPI */
+#define SNBEP_PMON_CTL_EN (1 << 22)
+#define SNBEP_PMON_CTL_INVERT (1 << 23)
+#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000
+#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_PMON_CTL_TRESH_MASK)
+
+/* SNB-EP Ubox event control */
+#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000
+#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+
+#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19)
+#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
+ SNBEP_CBO_PMON_CTL_TID_EN)
+
+/* SNB-EP PCU event control */
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000
+#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30)
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31)
+#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+
+#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_RAW_EVENT_MASK | \
+ SNBEP_PMON_CTL_EV_SEL_EXT)
+
+/* SNB-EP pci control register */
+#define SNBEP_PCI_PMON_BOX_CTL 0xf4
+#define SNBEP_PCI_PMON_CTL0 0xd8
+/* SNB-EP pci counter register */
+#define SNBEP_PCI_PMON_CTR0 0xa0
+
+/* SNB-EP home agent register */
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44
+#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48
+/* SNB-EP memory controller register */
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0
+/* SNB-EP QPI register */
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c
+
+/* SNB-EP Ubox register */
+#define SNBEP_U_MSR_PMON_CTR0 0xc16
+#define SNBEP_U_MSR_PMON_CTL0 0xc10
+
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09
+
+/* SNB-EP Cbo register */
+#define SNBEP_C0_MSR_PMON_CTR0 0xd16
+#define SNBEP_C0_MSR_PMON_CTL0 0xd10
+#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04
+#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK 0xfffffc1f
+#define SNBEP_CBO_MSR_OFFSET 0x20
+
+/* SNB-EP PCU register */
+#define SNBEP_PCU_MSR_PMON_CTR0 0xc36
+#define SNBEP_PCU_MSR_PMON_CTL0 0xc30
+#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff
+#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc
+#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd
+
+/* NHM-EX event control */
+#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff
+#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00
+#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0)
+#define NHMEX_PMON_CTL_EDGE_DET (1 << 18)
+#define NHMEX_PMON_CTL_PMI_EN (1 << 20)
+#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22)
+#define NHMEX_PMON_CTL_INVERT (1 << 23)
+#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000
+#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \
+ NHMEX_PMON_CTL_UMASK_MASK | \
+ NHMEX_PMON_CTL_EDGE_DET | \
+ NHMEX_PMON_CTL_INVERT | \
+ NHMEX_PMON_CTL_TRESH_MASK)
+
+/* NHM-EX Ubox */
+#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00
+#define NHMEX_U_MSR_PMON_CTR 0xc11
+#define NHMEX_U_MSR_PMON_EV_SEL 0xc10
+
+#define NHMEX_U_PMON_GLOBAL_EN (1 << 0)
+#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e
+#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28)
+#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29)
+#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31)
+
+#define NHMEX_U_PMON_RAW_EVENT_MASK \
+ (NHMEX_PMON_CTL_EV_SEL_MASK | \
+ NHMEX_PMON_CTL_EDGE_DET)
+
+/* NHM-EX Cbox */
+#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00
+#define NHMEX_C0_MSR_PMON_CTR0 0xd11
+#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10
+#define NHMEX_C_MSR_OFFSET 0x20
+
+/* NHM-EX Bbox */
+#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20
+#define NHMEX_B0_MSR_PMON_CTR0 0xc31
+#define NHMEX_B0_MSR_PMON_CTL0 0xc30
+#define NHMEX_B_MSR_OFFSET 0x40
+#define NHMEX_B0_MSR_MATCH 0xe45
+#define NHMEX_B0_MSR_MASK 0xe46
+#define NHMEX_B1_MSR_MATCH 0xe4d
+#define NHMEX_B1_MSR_MASK 0xe4e
+
+#define NHMEX_B_PMON_CTL_EN (1 << 0)
+#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1
+#define NHMEX_B_PMON_CTL_EV_SEL_MASK \
+ (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_B_PMON_CTR_SHIFT 6
+#define NHMEX_B_PMON_CTR_MASK \
+ (0x3 << NHMEX_B_PMON_CTR_SHIFT)
+#define NHMEX_B_PMON_RAW_EVENT_MASK \
+ (NHMEX_B_PMON_CTL_EV_SEL_MASK | \
+ NHMEX_B_PMON_CTR_MASK)
+
+/* NHM-EX Sbox */
+#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40
+#define NHMEX_S0_MSR_PMON_CTR0 0xc51
+#define NHMEX_S0_MSR_PMON_CTL0 0xc50
+#define NHMEX_S_MSR_OFFSET 0x80
+#define NHMEX_S0_MSR_MM_CFG 0xe48
+#define NHMEX_S0_MSR_MATCH 0xe49
+#define NHMEX_S0_MSR_MASK 0xe4a
+#define NHMEX_S1_MSR_MM_CFG 0xe58
+#define NHMEX_S1_MSR_MATCH 0xe59
+#define NHMEX_S1_MSR_MASK 0xe5a
+
+#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63)
+#define NHMEX_S_EVENT_TO_R_PROG_EV 0
+
+/* NHM-EX Mbox */
+#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0
+#define NHMEX_M0_MSR_PMU_DSP 0xca5
+#define NHMEX_M0_MSR_PMU_ISS 0xca6
+#define NHMEX_M0_MSR_PMU_MAP 0xca7
+#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8
+#define NHMEX_M0_MSR_PMU_PGT 0xca9
+#define NHMEX_M0_MSR_PMU_PLD 0xcaa
+#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab
+#define NHMEX_M0_MSR_PMU_CTL0 0xcb0
+#define NHMEX_M0_MSR_PMU_CNT0 0xcb1
+#define NHMEX_M_MSR_OFFSET 0x40
+#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54
+#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c
+
+#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63)
+#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34
+
+#define NHMEX_M_PMON_CTL_EN (1 << 0)
+#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1)
+#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2
+#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \
+ (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \
+ (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6)
+#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7)
+#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9
+#define NHMEX_M_PMON_CTL_INC_SEL_MASK \
+ (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \
+ (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
+#define NHMEX_M_PMON_RAW_EVENT_MASK \
+ (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \
+ NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \
+ NHMEX_M_PMON_CTL_WRAP_MODE | \
+ NHMEX_M_PMON_CTL_FLAG_MODE | \
+ NHMEX_M_PMON_CTL_INC_SEL_MASK | \
+ NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
+
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23))
+#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (11 + 3 * (n)))
+
+#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24))
+#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (12 + 3 * (n)))
+
+/*
+ * use the 9~13 bits to select event If the 7th bit is not set,
+ * otherwise use the 19~21 bits to select event.
+ */
+#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
+ NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
+ NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
+ NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_EXTAR_REG(c, r) \
+ EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+ MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
+#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
+ EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+ MBOX_SET_FLAG_SEL_MASK, \
+ (u64)-1, NHMEX_M_##r)
+
+/* NHM-EX Rbox */
+#define NHMEX_R_MSR_GLOBAL_CTL 0xe00
+#define NHMEX_R_MSR_PMON_CTL0 0xe10
+#define NHMEX_R_MSR_PMON_CNT0 0xe11
+#define NHMEX_R_MSR_OFFSET 0x20
+
+#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \
+ ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n))
+#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \
+ (((n) < 4 ? 0 : 0x10) + (n) * 4)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \
+ (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \
+ (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \
+ (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \
+ (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \
+ (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \
+ (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
+
+#define NHMEX_R_PMON_CTL_EN (1 << 0)
+#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1
+#define NHMEX_R_PMON_CTL_EV_SEL_MASK \
+ (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6)
+#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK
+
+/* NHM-EX Wbox */
+#define NHMEX_W_MSR_GLOBAL_CTL 0xc80
+#define NHMEX_W_MSR_PMON_CNT0 0xc90
+#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91
+#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394
+#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395
+
+#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31)
+
+struct intel_uncore_ops;
+struct intel_uncore_pmu;
+struct intel_uncore_box;
+struct uncore_event_desc;
+
+struct intel_uncore_type {
+ const char *name;
+ int num_counters;
+ int num_boxes;
+ int perf_ctr_bits;
+ int fixed_ctr_bits;
+ unsigned perf_ctr;
+ unsigned event_ctl;
+ unsigned event_mask;
+ unsigned fixed_ctr;
+ unsigned fixed_ctl;
+ unsigned box_ctl;
+ unsigned msr_offset;
+ unsigned num_shared_regs:8;
+ unsigned single_fixed:1;
+ unsigned pair_ctr_ctl:1;
+ unsigned *msr_offsets;
+ struct event_constraint unconstrainted;
+ struct event_constraint *constraints;
+ struct intel_uncore_pmu *pmus;
+ struct intel_uncore_ops *ops;
+ struct uncore_event_desc *event_descs;
+ const struct attribute_group *attr_groups[3];
+};
+
+#define format_group attr_groups[0]
+
+struct intel_uncore_ops {
+ void (*init_box)(struct intel_uncore_box *);
+ void (*disable_box)(struct intel_uncore_box *);
+ void (*enable_box)(struct intel_uncore_box *);
+ void (*disable_event)(struct intel_uncore_box *, struct perf_event *);
+ void (*enable_event)(struct intel_uncore_box *, struct perf_event *);
+ u64 (*read_counter)(struct intel_uncore_box *, struct perf_event *);
+ int (*hw_config)(struct intel_uncore_box *, struct perf_event *);
+ struct event_constraint *(*get_constraint)(struct intel_uncore_box *,
+ struct perf_event *);
+ void (*put_constraint)(struct intel_uncore_box *, struct perf_event *);
+};
+
+struct intel_uncore_pmu {
+ struct pmu pmu;
+ char name[UNCORE_PMU_NAME_LEN];
+ int pmu_idx;
+ int func_id;
+ struct intel_uncore_type *type;
+ struct intel_uncore_box ** __percpu box;
+ struct list_head box_list;
+};
+
+struct intel_uncore_extra_reg {
+ raw_spinlock_t lock;
+ u64 config, config1, config2;
+ atomic_t ref;
+};
+
+struct intel_uncore_box {
+ int phys_id;
+ int n_active; /* number of active events */
+ int n_events;
+ int cpu; /* cpu to collect events */
+ unsigned long flags;
+ atomic_t refcnt;
+ struct perf_event *events[UNCORE_PMC_IDX_MAX];
+ struct perf_event *event_list[UNCORE_PMC_IDX_MAX];
+ unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
+ u64 tags[UNCORE_PMC_IDX_MAX];
+ struct pci_dev *pci_dev;
+ struct intel_uncore_pmu *pmu;
+ struct hrtimer hrtimer;
+ struct list_head list;
+ struct intel_uncore_extra_reg shared_regs[0];
+};
+
+#define UNCORE_BOX_FLAG_INITIATED 0
+
+struct uncore_event_desc {
+ struct kobj_attribute attr;
+ const char *config;
+};
+
+#define INTEL_UNCORE_EVENT_DESC(_name, _config) \
+{ \
+ .attr = __ATTR(_name, 0444, uncore_event_show, NULL), \
+ .config = _config, \
+}
+
+#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \
+static ssize_t __uncore_##_var##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ char *page) \
+{ \
+ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
+ return sprintf(page, _format "\n"); \
+} \
+static struct kobj_attribute format_attr_##_var = \
+ __ATTR(_name, 0444, __uncore_##_var##_show, NULL)
+
+
+static ssize_t uncore_event_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct uncore_event_desc *event =
+ container_of(attr, struct uncore_event_desc, attr);
+ return sprintf(buf, "%s", event->config);
+}
+
+static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
+{
+ return box->pmu->type->box_ctl;
+}
+
+static inline unsigned uncore_pci_fixed_ctl(struct intel_uncore_box *box)
+{
+ return box->pmu->type->fixed_ctl;
+}
+
+static inline unsigned uncore_pci_fixed_ctr(struct intel_uncore_box *box)
+{
+ return box->pmu->type->fixed_ctr;
+}
+
+static inline
+unsigned uncore_pci_event_ctl(struct intel_uncore_box *box, int idx)
+{
+ return idx * 4 + box->pmu->type->event_ctl;
+}
+
+static inline
+unsigned uncore_pci_perf_ctr(struct intel_uncore_box *box, int idx)
+{
+ return idx * 8 + box->pmu->type->perf_ctr;
+}
+
+static inline unsigned uncore_msr_box_offset(struct intel_uncore_box *box)
+{
+ struct intel_uncore_pmu *pmu = box->pmu;
+ return pmu->type->msr_offsets ?
+ pmu->type->msr_offsets[pmu->pmu_idx] :
+ pmu->type->msr_offset * pmu->pmu_idx;
+}
+
+static inline unsigned uncore_msr_box_ctl(struct intel_uncore_box *box)
+{
+ if (!box->pmu->type->box_ctl)
+ return 0;
+ return box->pmu->type->box_ctl + uncore_msr_box_offset(box);
+}
+
+static inline unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box)
+{
+ if (!box->pmu->type->fixed_ctl)
+ return 0;
+ return box->pmu->type->fixed_ctl + uncore_msr_box_offset(box);
+}
+
+static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
+{
+ return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box);
+}
+
+static inline
+unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
+{
+ return box->pmu->type->event_ctl +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+ uncore_msr_box_offset(box);
+}
+
+static inline
+unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
+{
+ return box->pmu->type->perf_ctr +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+ uncore_msr_box_offset(box);
+}
+
+static inline
+unsigned uncore_fixed_ctl(struct intel_uncore_box *box)
+{
+ if (box->pci_dev)
+ return uncore_pci_fixed_ctl(box);
+ else
+ return uncore_msr_fixed_ctl(box);
+}
+
+static inline
+unsigned uncore_fixed_ctr(struct intel_uncore_box *box)
+{
+ if (box->pci_dev)
+ return uncore_pci_fixed_ctr(box);
+ else
+ return uncore_msr_fixed_ctr(box);
+}
+
+static inline
+unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx)
+{
+ if (box->pci_dev)
+ return uncore_pci_event_ctl(box, idx);
+ else
+ return uncore_msr_event_ctl(box, idx);
+}
+
+static inline
+unsigned uncore_perf_ctr(struct intel_uncore_box *box, int idx)
+{
+ if (box->pci_dev)
+ return uncore_pci_perf_ctr(box, idx);
+ else
+ return uncore_msr_perf_ctr(box, idx);
+}
+
+static inline int uncore_perf_ctr_bits(struct intel_uncore_box *box)
+{
+ return box->pmu->type->perf_ctr_bits;
+}
+
+static inline int uncore_fixed_ctr_bits(struct intel_uncore_box *box)
+{
+ return box->pmu->type->fixed_ctr_bits;
+}
+
+static inline int uncore_num_counters(struct intel_uncore_box *box)
+{
+ return box->pmu->type->num_counters;
+}
+
+static inline void uncore_disable_box(struct intel_uncore_box *box)
+{
+ if (box->pmu->type->ops->disable_box)
+ box->pmu->type->ops->disable_box(box);
+}
+
+static inline void uncore_enable_box(struct intel_uncore_box *box)
+{
+ if (box->pmu->type->ops->enable_box)
+ box->pmu->type->ops->enable_box(box);
+}
+
+static inline void uncore_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ box->pmu->type->ops->disable_event(box, event);
+}
+
+static inline void uncore_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ box->pmu->type->ops->enable_event(box, event);
+}
+
+static inline u64 uncore_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ return box->pmu->type->ops->read_counter(box, event);
+}
+
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+ if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+ if (box->pmu->type->ops->init_box)
+ box->pmu->type->ops->init_box(box);
+ }
+}
+
+static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
+{
+ return (box->phys_id < 0);
+}
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 47124a73dd7..92c7e39a079 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -895,8 +895,8 @@ static void p4_pmu_disable_pebs(void)
* So at moment let leave metrics turned on forever -- it's
* ok for now but need to be revisited!
*
- * (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)0);
- * (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)0);
+ * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)0);
+ * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)0);
*/
}
@@ -909,7 +909,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
* state we need to clear P4_CCCR_OVF, otherwise interrupt get
* asserted again and again
*/
- (void)checking_wrmsrl(hwc->config_base,
+ (void)wrmsrl_safe(hwc->config_base,
(u64)(p4_config_unpack_cccr(hwc->config)) &
~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
}
@@ -943,8 +943,8 @@ static void p4_pmu_enable_pebs(u64 config)
bind = &p4_pebs_bind_map[idx];
- (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs);
- (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert);
+ (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs);
+ (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert);
}
static void p4_pmu_enable_event(struct perf_event *event)
@@ -978,8 +978,8 @@ static void p4_pmu_enable_event(struct perf_event *event)
*/
p4_pmu_enable_pebs(hwc->config);
- (void)checking_wrmsrl(escr_addr, escr_conf);
- (void)checking_wrmsrl(hwc->config_base,
+ (void)wrmsrl_safe(escr_addr, escr_conf);
+ (void)wrmsrl_safe(hwc->config_base,
(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
}
@@ -1325,7 +1325,7 @@ __init int p4_pmu_init(void)
unsigned int low, high;
/* If we get stripped -- indexing fails */
- BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC);
+ BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC);
rdmsr(MSR_IA32_MISC_ENABLE, low, high);
if (!(low & (1 << 7))) {
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 32bcfc7dd23..e4dd0f7a045 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -71,7 +71,7 @@ p6_pmu_disable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base, val);
+ (void)wrmsrl_safe(hwc->config_base, val);
}
static void p6_pmu_enable_event(struct perf_event *event)
@@ -84,7 +84,7 @@ static void p6_pmu_enable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base, val);
+ (void)wrmsrl_safe(hwc->config_base, val);
}
PMU_FORMAT_ATTR(event, "config:0-7" );
diff --git a/arch/x86/kernel/cpu/sched.c b/arch/x86/kernel/cpu/sched.c
deleted file mode 100644
index a640ae5ad20..00000000000
--- a/arch/x86/kernel/cpu/sched.c
+++ /dev/null
@@ -1,55 +0,0 @@
-#include <linux/sched.h>
-#include <linux/math64.h>
-#include <linux/percpu.h>
-#include <linux/irqflags.h>
-
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-
-#ifdef CONFIG_SMP
-
-static DEFINE_PER_CPU(struct aperfmperf, old_perf_sched);
-
-static unsigned long scale_aperfmperf(void)
-{
- struct aperfmperf val, *old = &__get_cpu_var(old_perf_sched);
- unsigned long ratio, flags;
-
- local_irq_save(flags);
- get_aperfmperf(&val);
- local_irq_restore(flags);
-
- ratio = calc_aperfmperf_ratio(old, &val);
- *old = val;
-
- return ratio;
-}
-
-unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
-{
- /*
- * do aperf/mperf on the cpu level because it includes things
- * like turbo mode, which are relevant to full cores.
- */
- if (boot_cpu_has(X86_FEATURE_APERFMPERF))
- return scale_aperfmperf();
-
- /*
- * maybe have something cpufreq here
- */
-
- return default_scale_freq_power(sd, cpu);
-}
-
-unsigned long arch_scale_smt_power(struct sched_domain *sd, int cpu)
-{
- /*
- * aperf/mperf already includes the smt gain
- */
- if (boot_cpu_has(X86_FEATURE_APERFMPERF))
- return SCHED_LOAD_SCALE;
-
- return default_scale_smt_power(sd, cpu);
-}
-
-#endif