aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/Makefile2
-rw-r--r--arch/x86/ia32/ia32_aout.c2
-rw-r--r--arch/x86/include/asm/alternative.h5
-rw-r--r--arch/x86/include/asm/debugreg.h3
-rw-r--r--arch/x86/include/asm/elf.h5
-rw-r--r--arch/x86/include/asm/fb.h4
-rw-r--r--arch/x86/include/asm/nmi.h1
-rw-r--r--arch/x86/include/asm/pci_x86.h1
-rw-r--r--arch/x86/include/asm/perf_event.h16
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/ptrace.h4
-rw-r--r--arch/x86/include/asm/stacktrace.h2
-rw-r--r--arch/x86/include/asm/syscall.h2
-rw-r--r--arch/x86/include/asm/system.h4
-rw-r--r--arch/x86/kernel/acpi/boot.c13
-rw-r--r--arch/x86/kernel/alternative.c18
-rw-r--r--arch/x86/kernel/apic/apic.c17
-rw-r--r--arch/x86/kernel/apic/probe_32.c29
-rw-r--r--arch/x86/kernel/apic/probe_64.c2
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.c3
-rw-r--r--arch/x86/kernel/cpu/perf_event.c1854
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c416
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c971
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c157
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c11
-rw-r--r--arch/x86/kernel/dumpstack_32.c5
-rw-r--r--arch/x86/kernel/dumpstack_64.c6
-rw-r--r--arch/x86/kernel/ftrace.c36
-rw-r--r--arch/x86/kernel/hw_breakpoint.c40
-rw-r--r--arch/x86/kernel/kprobes.c5
-rw-r--r--arch/x86/kernel/mpparse.c7
-rw-r--r--arch/x86/kernel/process_64.c1
-rw-r--r--arch/x86/kernel/ptrace.c31
-rw-r--r--arch/x86/kernel/smpboot.c2
-rw-r--r--arch/x86/kernel/traps.c3
-rw-r--r--arch/x86/kvm/i8254.c3
-rw-r--r--arch/x86/kvm/x86.c7
-rw-r--r--arch/x86/mm/gup.c2
-rw-r--r--arch/x86/mm/kmemcheck/kmemcheck.c2
-rw-r--r--arch/x86/mm/kmemcheck/shadow.c16
-rw-r--r--arch/x86/mm/kmemcheck/shadow.h2
-rw-r--r--arch/x86/mm/mmap.c4
-rw-r--r--arch/x86/oprofile/nmi_int.c17
-rw-r--r--arch/x86/oprofile/op_model_amd.c244
-rw-r--r--arch/x86/oprofile/op_model_p4.c6
-rw-r--r--arch/x86/oprofile/op_model_ppro.c17
-rw-r--r--arch/x86/oprofile/op_x86_model.h20
-rw-r--r--arch/x86/pci/acpi.c82
-rw-r--r--arch/x86/pci/bus_numa.c3
-rw-r--r--arch/x86/pci/bus_numa.h3
-rw-r--r--arch/x86/pci/common.c3
-rw-r--r--arch/x86/pci/i386.c14
-rw-r--r--arch/x86/pci/irq.c2
-rw-r--r--arch/x86/pci/mmconfig-shared.c17
55 files changed, 2505 insertions, 1640 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index eb4092568f9..0896008f750 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -45,6 +45,7 @@ config X86
select HAVE_GENERIC_DMA_COHERENT if X86_32
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select USER_STACKTRACE_SUPPORT
+ select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_DMA_API_DEBUG
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_BZIP2
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 78b32be55e9..0a43dc515e4 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -135,9 +135,7 @@ drivers-$(CONFIG_OPROFILE) += arch/x86/oprofile/
# suspend and hibernation support
drivers-$(CONFIG_PM) += arch/x86/power/
-ifeq ($(CONFIG_X86_32),y)
drivers-$(CONFIG_FB) += arch/x86/video/
-endif
####
# boot loader support. Several targets are kept for legacy purposes
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index f9f47246275..9046e4af66c 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -297,7 +297,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
* size limits imposed on them by creating programs with large
* arrays in the data or bss.
*/
- rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
+ rlim = rlimit(RLIMIT_DATA);
if (rlim >= RLIM_INFINITY)
rlim = ~0;
if (ex.a_data + ex.a_bss > rlim)
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 69b74a7b877..ac80b7d7001 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -65,12 +65,17 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
void *text, void *text_end);
extern void alternatives_smp_module_del(struct module *mod);
extern void alternatives_smp_switch(int smp);
+extern int alternatives_text_reserved(void *start, void *end);
#else
static inline void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
void *text, void *text_end) {}
static inline void alternatives_smp_module_del(struct module *mod) {}
static inline void alternatives_smp_switch(int smp) {}
+static inline int alternatives_text_reserved(void *start, void *end)
+{
+ return 0;
+}
#endif /* CONFIG_SMP */
/* alternative assembly primitive: */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 8240f76b531..b81002f2361 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -14,6 +14,9 @@
which debugging register was responsible for the trap. The other bits
are either reserved or not of interest to us. */
+/* Define reserved bits in DR6 which are always set to 1 */
+#define DR6_RESERVED (0xFFFF0FF0)
+
#define DR_TRAP0 (0x1) /* db0 */
#define DR_TRAP1 (0x2) /* db1 */
#define DR_TRAP2 (0x4) /* db2 */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1994d3f5844..f2ad2163109 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -170,10 +170,7 @@ static inline void elf_common_init(struct thread_struct *t,
}
#define ELF_PLAT_INIT(_r, load_addr) \
-do { \
- elf_common_init(&current->thread, _r, 0); \
- clear_thread_flag(TIF_IA32); \
-} while (0)
+ elf_common_init(&current->thread, _r, 0)
#define COMPAT_ELF_PLAT_INIT(regs, load_addr) \
elf_common_init(&current->thread, regs, __USER_DS)
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
index 53018464aea..2519d0679d9 100644
--- a/arch/x86/include/asm/fb.h
+++ b/arch/x86/include/asm/fb.h
@@ -12,10 +12,6 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
}
-#ifdef CONFIG_X86_32
extern int fb_is_primary_device(struct fb_info *info);
-#else
-static inline int fb_is_primary_device(struct fb_info *info) { return 0; }
-#endif
#endif /* _ASM_X86_FB_H */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 139d4c1a33a..93da9c3f334 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -19,7 +19,6 @@ extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
extern int check_nmi_watchdog(void);
extern int nmi_watchdog_enabled;
extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
-extern int avail_to_resrv_perfctr_nmi(unsigned int);
extern int reserve_perfctr_nmi(unsigned int);
extern void release_perfctr_nmi(unsigned int);
extern int reserve_evntsel_nmi(unsigned int);
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index b4bf9a942ed..05b58ccb2e8 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -29,6 +29,7 @@
#define PCI_CHECK_ENABLE_AMD_MMCONF 0x20000
#define PCI_HAS_IO_ECS 0x40000
#define PCI_NOASSIGN_ROMS 0x80000
+#define PCI_ROOT_NO_CRS 0x100000
extern unsigned int pci_probe;
extern unsigned long pirq_table_addr;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 1380367dabd..befd172c82a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -27,7 +27,14 @@
/*
* Includes eventsel and unit mask as well:
*/
-#define ARCH_PERFMON_EVENT_MASK 0xffff
+
+
+#define INTEL_ARCH_EVTSEL_MASK 0x000000FFULL
+#define INTEL_ARCH_UNIT_MASK 0x0000FF00ULL
+#define INTEL_ARCH_EDGE_MASK 0x00040000ULL
+#define INTEL_ARCH_INV_MASK 0x00800000ULL
+#define INTEL_ARCH_CNT_MASK 0xFF000000ULL
+#define INTEL_ARCH_EVENT_MASK (INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK)
/*
* filter mask to validate fixed counter events.
@@ -38,7 +45,12 @@
* The other filters are supported by fixed counters.
* The any-thread option is supported starting with v3.
*/
-#define ARCH_PERFMON_EVENT_FILTER_MASK 0xff840000
+#define INTEL_ARCH_FIXED_MASK \
+ (INTEL_ARCH_CNT_MASK| \
+ INTEL_ARCH_INV_MASK| \
+ INTEL_ARCH_EDGE_MASK|\
+ INTEL_ARCH_UNIT_MASK|\
+ INTEL_ARCH_EVTSEL_MASK)
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index fc801bab1b3..b753ea59703 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -450,6 +450,8 @@ struct thread_struct {
struct perf_event *ptrace_bps[HBP_NUM];
/* Debug status used for traps, single steps, etc... */
unsigned long debugreg6;
+ /* Keep track of the exact dr7 value set by the user */
+ unsigned long ptrace_dr7;
/* Fault info: */
unsigned long cr2;
unsigned long trap_no;
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 9d369f68032..20102808b19 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -274,10 +274,6 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
return 0;
}
-/* Get Nth argument at function call */
-extern unsigned long regs_get_argument_nth(struct pt_regs *regs,
- unsigned int n);
-
/*
* These are defined as per linux/ptrace.h, which see.
*/
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 35e89122a42..4dab78edbad 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -3,8 +3,6 @@
extern int kstack_depth_to_print;
-int x86_is_stack_id(int id, char *name);
-
struct thread_info;
struct stacktrace_ops;
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 8d33bc5462d..c4a348f7bd4 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,6 +16,8 @@
#include <linux/sched.h>
#include <linux/err.h>
+extern const unsigned long sys_call_table[];
+
/*
* Only the low 32 bits of orig_ax are meaningful, so we return int.
* This importantly ignores the high bits on 64-bit, so comparisons
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index ecb544e6538..e04740f7a0b 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -11,9 +11,9 @@
#include <linux/irqflags.h>
/* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
+#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
# define AT_VECTOR_SIZE_ARCH 2
-#else
+#else /* else it's non-compat x86-64 */
# define AT_VECTOR_SIZE_ARCH 1
#endif
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 036d28adf59..af1c5833ff2 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1185,9 +1185,6 @@ static void __init acpi_process_madt(void)
if (!error) {
acpi_lapic = 1;
-#ifdef CONFIG_X86_BIGSMP
- generic_bigsmp_probe();
-#endif
/*
* Parse MADT IO-APIC entries
*/
@@ -1197,8 +1194,6 @@ static void __init acpi_process_madt(void)
acpi_ioapic = 1;
smp_found_config = 1;
- if (apic->setup_apic_routing)
- apic->setup_apic_routing();
}
}
if (error == -EINVAL) {
@@ -1349,14 +1344,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = {
},
{
.callback = force_acpi_ht,
- .ident = "ASUS P2B-DS",
- .matches = {
- DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
- DMI_MATCH(DMI_BOARD_NAME, "P2B-DS"),
- },
- },
- {
- .callback = force_acpi_ht,
.ident = "ASUS CUR-DLS",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index de7353c0ce9..e63b80e5861 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -390,6 +390,24 @@ void alternatives_smp_switch(int smp)
mutex_unlock(&smp_alt);
}
+/* Return 1 if the address range is reserved for smp-alternatives */
+int alternatives_text_reserved(void *start, void *end)
+{
+ struct smp_alt_module *mod;
+ u8 **ptr;
+ u8 *text_start = start;
+ u8 *text_end = end;
+
+ list_for_each_entry(mod, &smp_alt_modules, next) {
+ if (mod->text > text_end || mod->text_end < text_start)
+ continue;
+ for (ptr = mod->locks; ptr < mod->locks_end; ptr++)
+ if (text_start <= *ptr && text_end >= *ptr)
+ return 1;
+ }
+
+ return 0;
+}
#endif
#ifdef CONFIG_PARAVIRT
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 3987e4408f7..dfca210f6a1 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1641,9 +1641,7 @@ int __init APIC_init_uniprocessor(void)
#endif
enable_IR_x2apic();
-#ifdef CONFIG_X86_64
default_setup_apic_routing();
-#endif
verify_local_APIC();
connect_bsp_APIC();
@@ -1891,21 +1889,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
if (apicid > max_physical_apicid)
max_physical_apicid = apicid;
-#ifdef CONFIG_X86_32
- if (num_processors > 8) {
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_INTEL:
- if (!APIC_XAPIC(version)) {
- def_to_bigsmp = 0;
- break;
- }
- /* If P4 and above fall through */
- case X86_VENDOR_AMD:
- def_to_bigsmp = 1;
- }
- }
-#endif
-
#if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 1a6559f6768..99d2fe01608 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -52,7 +52,32 @@ static int __init print_ipi_mode(void)
}
late_initcall(print_ipi_mode);
-void default_setup_apic_routing(void)
+void __init default_setup_apic_routing(void)
+{
+ int version = apic_version[boot_cpu_physical_apicid];
+
+ if (num_possible_cpus() > 8) {
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_INTEL:
+ if (!APIC_XAPIC(version)) {
+ def_to_bigsmp = 0;
+ break;
+ }
+ /* If P4 and above fall through */
+ case X86_VENDOR_AMD:
+ def_to_bigsmp = 1;
+ }
+ }
+
+#ifdef CONFIG_X86_BIGSMP
+ generic_bigsmp_probe();
+#endif
+
+ if (apic->setup_apic_routing)
+ apic->setup_apic_routing();
+}
+
+static void setup_apic_flat_routing(void)
{
#ifdef CONFIG_X86_IO_APIC
printk(KERN_INFO
@@ -103,7 +128,7 @@ struct apic apic_default = {
.init_apic_ldr = default_init_apic_ldr,
.ioapic_phys_id_map = default_ioapic_phys_id_map,
- .setup_apic_routing = default_setup_apic_routing,
+ .setup_apic_routing = setup_apic_flat_routing,
.multi_timer_check = NULL,
.apicid_to_node = default_apicid_to_node,
.cpu_to_logical_apicid = default_cpu_to_logical_apicid,
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 450fe2064a1..83e9be4778e 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -67,7 +67,7 @@ void __init default_setup_apic_routing(void)
}
#endif
- if (apic == &apic_flat && num_processors > 8)
+ if (apic == &apic_flat && num_possible_cpus() > 8)
apic = &apic_physflat;
printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index f125e5c551c..6e44519960c 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1356,6 +1356,7 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol)
kfree(data->powernow_table);
kfree(data);
+ per_cpu(powernow_data, pol->cpu) = NULL;
return 0;
}
@@ -1375,7 +1376,7 @@ static unsigned int powernowk8_get(unsigned int cpu)
int err;
if (!data)
- return -EINVAL;
+ return 0;
smp_call_function_single(cpu, query_values_on_cpu, &err, true);
if (err)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8c1c07073cc..641ccb9dddb 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -7,6 +7,7 @@
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
* Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
+ * Copyright (C) 2009 Google, Inc., Stephane Eranian
*
* For licencing details see kernel-base/COPYING
*/
@@ -22,6 +23,7 @@
#include <linux/uaccess.h>
#include <linux/highmem.h>
#include <linux/cpu.h>
+#include <linux/bitops.h>
#include <asm/apic.h>
#include <asm/stacktrace.h>
@@ -68,26 +70,59 @@ struct debug_store {
u64 pebs_event_reset[MAX_PEBS_EVENTS];
};
+struct event_constraint {
+ union {
+ unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ u64 idxmsk64[1];
+ };
+ int code;
+ int cmask;
+ int weight;
+};
+
+struct amd_nb {
+ int nb_id; /* NorthBridge id */
+ int refcnt; /* reference count */
+ struct perf_event *owners[X86_PMC_IDX_MAX];
+ struct event_constraint event_constraints[X86_PMC_IDX_MAX];
+};
+
struct cpu_hw_events {
- struct perf_event *events[X86_PMC_IDX_MAX];
- unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */
unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
unsigned long interrupts;
int enabled;
struct debug_store *ds;
-};
-struct event_constraint {
- unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
- int code;
+ int n_events;
+ int n_added;
+ int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
+ u64 tags[X86_PMC_IDX_MAX];
+ struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+ struct amd_nb *amd_nb;
};
-#define EVENT_CONSTRAINT(c, m) { .code = (c), .idxmsk[0] = (m) }
-#define EVENT_CONSTRAINT_END { .code = 0, .idxmsk[0] = 0 }
+#define __EVENT_CONSTRAINT(c, n, m, w) {\
+ { .idxmsk64[0] = (n) }, \
+ .code = (c), \
+ .cmask = (m), \
+ .weight = (w), \
+}
+
+#define EVENT_CONSTRAINT(c, n, m) \
+ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
-#define for_each_event_constraint(e, c) \
- for ((e) = (c); (e)->idxmsk[0]; (e)++)
+#define INTEL_EVENT_CONSTRAINT(c, n) \
+ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)
+#define FIXED_EVENT_CONSTRAINT(c, n) \
+ EVENT_CONSTRAINT(c, n, INTEL_ARCH_FIXED_MASK)
+
+#define EVENT_CONSTRAINT_END \
+ EVENT_CONSTRAINT(0, 0, 0)
+
+#define for_each_event_constraint(e, c) \
+ for ((e) = (c); (e)->cmask; (e)++)
/*
* struct x86_pmu - generic x86 pmu
@@ -114,8 +149,14 @@ struct x86_pmu {
u64 intel_ctrl;
void (*enable_bts)(u64 config);
void (*disable_bts)(void);
- int (*get_event_idx)(struct cpu_hw_events *cpuc,
- struct hw_perf_event *hwc);
+
+ struct event_constraint *
+ (*get_event_constraints)(struct cpu_hw_events *cpuc,
+ struct perf_event *event);
+
+ void (*put_event_constraints)(struct cpu_hw_events *cpuc,
+ struct perf_event *event);
+ struct event_constraint *event_constraints;
};
static struct x86_pmu x86_pmu __read_mostly;
@@ -124,111 +165,8 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
.enabled = 1,
};
-static const struct event_constraint *event_constraints;
-
-/*
- * Not sure about some of these
- */
-static const u64 p6_perfmon_event_map[] =
-{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x0079,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x012e,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
- [PERF_COUNT_HW_BUS_CYCLES] = 0x0062,
-};
-
-static u64 p6_pmu_event_map(int hw_event)
-{
- return p6_perfmon_event_map[hw_event];
-}
-
-/*
- * Event setting that is specified not to count anything.
- * We use this to effectively disable a counter.
- *
- * L2_RQSTS with 0 MESI unit mask.
- */
-#define P6_NOP_EVENT 0x0000002EULL
-
-static u64 p6_pmu_raw_event(u64 hw_event)
-{
-#define P6_EVNTSEL_EVENT_MASK 0x000000FFULL
-#define P6_EVNTSEL_UNIT_MASK 0x0000FF00ULL
-#define P6_EVNTSEL_EDGE_MASK 0x00040000ULL
-#define P6_EVNTSEL_INV_MASK 0x00800000ULL
-#define P6_EVNTSEL_REG_MASK 0xFF000000ULL
-
-#define P6_EVNTSEL_MASK \
- (P6_EVNTSEL_EVENT_MASK | \
- P6_EVNTSEL_UNIT_MASK | \
- P6_EVNTSEL_EDGE_MASK | \
- P6_EVNTSEL_INV_MASK | \
- P6_EVNTSEL_REG_MASK)
-
- return hw_event & P6_EVNTSEL_MASK;
-}
-
-static const struct event_constraint intel_p6_event_constraints[] =
-{
- EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */
- EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
- EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */
- EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
- EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
- EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
- EVENT_CONSTRAINT_END
-};
-
-/*
- * Intel PerfMon v3. Used on Core2 and later.
- */
-static const u64 intel_perfmon_event_map[] =
-{
- [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,
-};
-
-static const struct event_constraint intel_core_event_constraints[] =
-{
- EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
- EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
- EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
- EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
- EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
- EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */
- EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
- EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */
- EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */
- EVENT_CONSTRAINT_END
-};
-
-static const struct event_constraint intel_nehalem_event_constraints[] =
-{
- EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
- EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
- EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
- EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */
- EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */
- EVENT_CONSTRAINT(0x4c, 0x3), /* LOAD_HIT_PRE */
- EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
- EVENT_CONSTRAINT(0x52, 0x3), /* L1D_CACHE_PREFETCH_LOCK_FB_HIT */
- EVENT_CONSTRAINT(0x53, 0x3), /* L1D_CACHE_LOCK_FB_HIT */
- EVENT_CONSTRAINT(0xc5, 0x3), /* CACHE_LOCK_CYCLES */
- EVENT_CONSTRAINT_END
-};
-
-static u64 intel_pmu_event_map(int hw_event)
-{
- return intel_perfmon_event_map[hw_event];
-}
+static int x86_perf_event_set_period(struct perf_event *event,
+ struct hw_perf_event *hwc, int idx);
/*
* Generalized hw caching related hw_event table, filled
@@ -245,424 +183,6 @@ static u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
-static __initconst u64 nehalem_hw_cache_event_ids
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */
- [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */
- [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */
- [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */
- },
- },
- [ C(L1I ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */
- [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x0,
- [ C(RESULT_MISS) ] = 0x0,
- },
- },
- [ C(LL ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
- [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
- [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
- [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
- },
- },
- [ C(DTLB) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI (alias) */
- [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI (alias) */
- [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x0,
- [ C(RESULT_MISS) ] = 0x0,
- },
- },
- [ C(ITLB) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */
- [ C(RESULT_MISS) ] = 0x20c8, /* ITLB_MISS_RETIRED */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- },
- [ C(BPU ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
- [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- },
-};
-
-static __initconst u64 core2_hw_cache_event_ids
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */
- [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */
- [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x104e, /* L1D_PREFETCH.REQUESTS */
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(L1I ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0080, /* L1I.READS */
- [ C(RESULT_MISS) ] = 0x0081, /* L1I.MISSES */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(LL ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI */
- [ C(RESULT_MISS) ] = 0x4129, /* L2_LD.ISTATE */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI */
- [ C(RESULT_MISS) ] = 0x412A, /* L2_ST.ISTATE */
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(DTLB) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI (alias) */
- [ C(RESULT_MISS) ] = 0x0208, /* DTLB_MISSES.MISS_LD */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI (alias) */
- [ C(RESULT_MISS) ] = 0x0808, /* DTLB_MISSES.MISS_ST */
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(ITLB) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
- [ C(RESULT_MISS) ] = 0x1282, /* ITLBMISSES */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- },
- [ C(BPU ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */
- [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- },
-};
-
-static __initconst u64 atom_hw_cache_event_ids
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE.LD */
- [ C(RESULT_MISS) ] = 0,
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE.ST */
- [ C(RESULT_MISS) ] = 0,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(L1I ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */
- [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(LL ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI */
- [ C(RESULT_MISS) ] = 0x4129, /* L2_LD.ISTATE */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI */
- [ C(RESULT_MISS) ] = 0x412A, /* L2_ST.ISTATE */
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(DTLB) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE_LD.MESI (alias) */
- [ C(RESULT_MISS) ] = 0x0508, /* DTLB_MISSES.MISS_LD */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE_ST.MESI (alias) */
- [ C(RESULT_MISS) ] = 0x0608, /* DTLB_MISSES.MISS_ST */
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(ITLB) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
- [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- },
- [ C(BPU ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */
- [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- },
-};
-
-static u64 intel_pmu_raw_event(u64 hw_event)
-{
-#define CORE_EVNTSEL_EVENT_MASK 0x000000FFULL
-#define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL
-#define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL
-#define CORE_EVNTSEL_INV_MASK 0x00800000ULL
-#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL
-
-#define CORE_EVNTSEL_MASK \
- (CORE_EVNTSEL_EVENT_MASK | \
- CORE_EVNTSEL_UNIT_MASK | \
- CORE_EVNTSEL_EDGE_MASK | \
- CORE_EVNTSEL_INV_MASK | \
- CORE_EVNTSEL_REG_MASK)
-
- return hw_event & CORE_EVNTSEL_MASK;
-}
-
-static __initconst u64 amd_hw_cache_event_ids
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */
- [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
- [ C(RESULT_MISS) ] = 0,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x0267, /* Data Prefetcher :attempts */
- [ C(RESULT_MISS) ] = 0x0167, /* Data Prefetcher :cancelled */
- },
- },
- [ C(L1I ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction cache fetches */
- [ C(RESULT_MISS) ] = 0x0081, /* Instruction cache misses */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x014B, /* Prefetch Instructions :Load */
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(LL ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x037D, /* Requests to L2 Cache :IC+DC */
- [ C(RESULT_MISS) ] = 0x037E, /* L2 Cache Misses : IC+DC */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x017F, /* L2 Fill/Writeback */
- [ C(RESULT_MISS) ] = 0,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(DTLB) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */
- [ C(RESULT_MISS) ] = 0x0046, /* L1 DTLB and L2 DLTB Miss */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0,
- [ C(RESULT_MISS) ] = 0,
- },
- },
- [ C(ITLB) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes */
- [ C(RESULT_MISS) ] = 0x0085, /* Instr. fetch ITLB misses */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- },
- [ C(BPU ) ] = {
- [ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x00c2, /* Retired Branch Instr. */
- [ C(RESULT_MISS) ] = 0x00c3, /* Retired Mispredicted BI */
- },
- [ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- [ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = -1,
- [ C(RESULT_MISS) ] = -1,
- },
- },
-};
-
-/*
- * AMD Performance Monitor K7 and later.
- */
-static const u64 amd_perfmon_event_map[] =
-{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
-};
-
-static u64 amd_pmu_event_map(int hw_event)
-{
- return amd_perfmon_event_map[hw_event];
-}
-
-static u64 amd_pmu_raw_event(u64 hw_event)
-{
-#define K7_EVNTSEL_EVENT_MASK 0x7000000FFULL
-#define K7_EVNTSEL_UNIT_MASK 0x00000FF00ULL
-#define K7_EVNTSEL_EDGE_MASK 0x000040000ULL
-#define K7_EVNTSEL_INV_MASK 0x000800000ULL
-#define K7_EVNTSEL_REG_MASK 0x0FF000000ULL
-
-#define K7_EVNTSEL_MASK \
- (K7_EVNTSEL_EVENT_MASK | \
- K7_EVNTSEL_UNIT_MASK | \
- K7_EVNTSEL_EDGE_MASK | \
- K7_EVNTSEL_INV_MASK | \
- K7_EVNTSEL_REG_MASK)
-
- return hw_event & K7_EVNTSEL_MASK;
-}
-
/*
* Propagate event elapsed time into the generic event.
* Can only be executed on the CPU where the event is active.
@@ -914,42 +434,6 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
return 0;
}
-static void intel_pmu_enable_bts(u64 config)
-{
- unsigned long debugctlmsr;
-
- debugctlmsr = get_debugctlmsr();
-
- debugctlmsr |= X86_DEBUGCTL_TR;
- debugctlmsr |= X86_DEBUGCTL_BTS;
- debugctlmsr |= X86_DEBUGCTL_BTINT;
-
- if (!(config & ARCH_PERFMON_EVENTSEL_OS))
- debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
-
- if (!(config & ARCH_PERFMON_EVENTSEL_USR))
- debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
-
- update_debugctlmsr(debugctlmsr);
-}
-
-static void intel_pmu_disable_bts(void)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- unsigned long debugctlmsr;
-
- if (!cpuc->ds)
- return;
-
- debugctlmsr = get_debugctlmsr();
-
- debugctlmsr &=
- ~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
- X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
-
- update_debugctlmsr(debugctlmsr);
-}
-
/*
* Setup the hardware configuration for a given attr_type
*/
@@ -988,6 +472,8 @@ static int __hw_perf_event_init(struct perf_event *event)
hwc->config = ARCH_PERFMON_EVENTSEL_INT;
hwc->idx = -1;
+ hwc->last_cpu = -1;
+ hwc->last_tag = ~0ULL;
/*
* Count user and OS events unless requested not to.
@@ -1056,216 +542,323 @@ static int __hw_perf_event_init(struct perf_event *event)
return 0;
}
-static void p6_pmu_disable_all(void)
+static void x86_pmu_disable_all(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- u64 val;
-
- if (!cpuc->enabled)
- return;
+ int idx;
- cpuc->enabled = 0;
- barrier();
+ for (idx = 0; idx < x86_pmu.num_events; idx++) {
+ u64 val;
- /* p6 only has one enable register */
- rdmsrl(MSR_P6_EVNTSEL0, val);
- val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
- wrmsrl(MSR_P6_EVNTSEL0, val);
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+ rdmsrl(x86_pmu.eventsel + idx, val);
+ if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE))
+ continue;
+ val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+ wrmsrl(x86_pmu.eventsel + idx, val);
+ }
}
-static void intel_pmu_disable_all(void)
+void hw_perf_disable(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ if (!x86_pmu_initialized())
+ return;
+
if (!cpuc->enabled)
return;
+ cpuc->n_added = 0;
cpuc->enabled = 0;
barrier();
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
-
- if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
- intel_pmu_disable_bts();
+ x86_pmu.disable_all();
}
-static void amd_pmu_disable_all(void)
+static void x86_pmu_enable_all(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
int idx;
- if (!cpuc->enabled)
- return;
-
- cpuc->enabled = 0;
- /*
- * ensure we write the disable before we start disabling the
- * events proper, so that amd_pmu_enable_event() does the
- * right thing.
- */
- barrier();
-
for (idx = 0; idx < x86_pmu.num_events; idx++) {
+ struct perf_event *event = cpuc->events[idx];
u64 val;
if (!test_bit(idx, cpuc->active_mask))
continue;
- rdmsrl(MSR_K7_EVNTSEL0 + idx, val);
- if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE))
- continue;
- val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
- wrmsrl(MSR_K7_EVNTSEL0 + idx, val);
+
+ val = event->hw.config;
+ val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ wrmsrl(x86_pmu.eventsel + idx, val);
}
}
-void hw_perf_disable(void)
+static const struct pmu pmu;
+
+static inline int is_x86_event(struct perf_event *event)
{
- if (!x86_pmu_initialized())
- return;
- return x86_pmu.disable_all();
+ return event->pmu == &pmu;
}
-static void p6_pmu_enable_all(void)
+static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- unsigned long val;
+ struct event_constraint *c, *constraints[X86_PMC_IDX_MAX];
+ unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ int i, j, w, wmax, num = 0;
+ struct hw_perf_event *hwc;
- if (cpuc->enabled)
- return;
+ bitmap_zero(used_mask, X86_PMC_IDX_MAX);
- cpuc->enabled = 1;
- barrier();
+ for (i = 0; i < n; i++) {
+ constraints[i] =
+ x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
+ }
- /* p6 only has one enable register */
- rdmsrl(MSR_P6_EVNTSEL0, val);
- val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
- wrmsrl(MSR_P6_EVNTSEL0, val);
-}
+ /*
+ * fastpath, try to reuse previous register
+ */
+ for (i = 0; i < n; i++) {
+ hwc = &cpuc->event_list[i]->hw;
+ c = constraints[i];
-static void intel_pmu_enable_all(void)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ /* never assigned */
+ if (hwc->idx == -1)
+ break;
- if (cpuc->enabled)
- return;
+ /* constraint still honored */
+ if (!test_bit(hwc->idx, c->idxmsk))
+ break;
- cpuc->enabled = 1;
- barrier();
+ /* not already used */
+ if (test_bit(hwc->idx, used_mask))
+ break;
+
+ set_bit(hwc->idx, used_mask);
+ if (assign)
+ assign[i] = hwc->idx;
+ }
+ if (i == n)
+ goto done;
+
+ /*
+ * begin slow path
+ */
+
+ bitmap_zero(used_mask, X86_PMC_IDX_MAX);
+
+ /*
+ * weight = number of possible counters
+ *
+ * 1 = most constrained, only works on one counter
+ * wmax = least constrained, works on any counter
+ *
+ * assign events to counters starting with most
+ * constrained events.
+ */
+ wmax = x86_pmu.num_events;
+
+ /*
+ * when fixed event counters are present,
+ * wmax is incremented by 1 to account
+ * for one more choice
+ */
+ if (x86_pmu.num_events_fixed)
+ wmax++;
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+ for (w = 1, num = n; num && w <= wmax; w++) {
+ /* for each event */
+ for (i = 0; num && i < n; i++) {
+ c = constraints[i];
+ hwc = &cpuc->event_list[i]->hw;
- if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
- struct perf_event *event =
- cpuc->events[X86_PMC_IDX_FIXED_BTS];
+ if (c->weight != w)
+ continue;
- if (WARN_ON_ONCE(!event))
- return;
+ for_each_bit(j, c->idxmsk, X86_PMC_IDX_MAX) {
+ if (!test_bit(j, used_mask))
+ break;
+ }
+
+ if (j == X86_PMC_IDX_MAX)
+ break;
+
+ set_bit(j, used_mask);
- intel_pmu_enable_bts(event->hw.config);
+ if (assign)
+ assign[i] = j;
+ num--;
+ }
+ }
+done:
+ /*
+ * scheduling failed or is just a simulation,
+ * free resources if necessary
+ */
+ if (!assign || num) {
+ for (i = 0; i < n; i++) {
+ if (x86_pmu.put_event_constraints)
+ x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
+ }
}
+ return num ? -ENOSPC : 0;
}
-static void amd_pmu_enable_all(void)
+/*
+ * dogrp: true if must collect siblings events (group)
+ * returns total number of events and error code
+ */
+static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- int idx;
+ struct perf_event *event;
+ int n, max_count;
- if (cpuc->enabled)
- return;
+ max_count = x86_pmu.num_events + x86_pmu.num_events_fixed;
- cpuc->enabled = 1;
- barrier();
+ /* current number of events already accepted */
+ n = cpuc->n_events;
- for (idx = 0; idx < x86_pmu.num_events; idx++) {
- struct perf_event *event = cpuc->events[idx];
- u64 val;
+ if (is_x86_event(leader)) {
+ if (n >= max_count)
+ return -ENOSPC;
+ cpuc->event_list[n] = leader;
+ n++;
+ }
+ if (!dogrp)
+ return n;
- if (!test_bit(idx, cpuc->active_mask))
+ list_for_each_entry(event, &leader->sibling_list, group_entry) {
+ if (!is_x86_event(event) ||
+ event->state <= PERF_EVENT_STATE_OFF)
continue;
- val = event->hw.config;
- val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
- wrmsrl(MSR_K7_EVNTSEL0 + idx, val);
- }
-}
+ if (n >= max_count)
+ return -ENOSPC;
-void hw_perf_enable(void)
-{
- if (!x86_pmu_initialized())
- return;
- x86_pmu.enable_all();
+ cpuc->event_list[n] = event;
+ n++;
+ }
+ return n;
}
-static inline u64 intel_pmu_get_status(void)
+static inline void x86_assign_hw_event(struct perf_event *event,
+ struct cpu_hw_events *cpuc, int i)
{
- u64 status;
+ struct hw_perf_event *hwc = &event->hw;
- rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+ hwc->idx = cpuc->assign[i];
+ hwc->last_cpu = smp_processor_id();
+ hwc->last_tag = ++cpuc->tags[i];
- return status;
+ if (hwc->idx == X86_PMC_IDX_FIXED_BTS) {
+ hwc->config_base = 0;
+ hwc->event_base = 0;
+ } else if (hwc->idx >= X86_PMC_IDX_FIXED) {
+ hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
+ /*
+ * We set it so that event_base + idx in wrmsr/rdmsr maps to
+ * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
+ */
+ hwc->event_base =
+ MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
+ } else {
+ hwc->config_base = x86_pmu.eventsel;
+ hwc->event_base = x86_pmu.perfctr;
+ }
}
-static inline void intel_pmu_ack_status(u64 ack)
+static inline int match_prev_assignment(struct hw_perf_event *hwc,
+ struct cpu_hw_events *cpuc,
+ int i)
{
- wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+ return hwc->idx == cpuc->assign[i] &&
+ hwc->last_cpu == smp_processor_id() &&
+ hwc->last_tag == cpuc->tags[i];
}
-static inline void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
- (void)checking_wrmsrl(hwc->config_base + idx,
- hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
-}
+static void x86_pmu_stop(struct perf_event *event);
-static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+void hw_perf_enable(void)
{
- (void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
-}
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct perf_event *event;
+ struct hw_perf_event *hwc;
+ int i;
-static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
-{
- int idx = __idx - X86_PMC_IDX_FIXED;
- u64 ctrl_val, mask;
+ if (!x86_pmu_initialized())
+ return;
- mask = 0xfULL << (idx * 4);
+ if (cpuc->enabled)
+ return;
- rdmsrl(hwc->config_base, ctrl_val);
- ctrl_val &= ~mask;
- (void)checking_wrmsrl(hwc->config_base, ctrl_val);
-}
+ if (cpuc->n_added) {
+ /*
+ * apply assignment obtained either from
+ * hw_perf_group_sched_in() or x86_pmu_enable()
+ *
+ * step1: save events moving to new counters
+ * step2: reprogram moved events into new counters
+ */
+ for (i = 0; i < cpuc->n_events; i++) {
-static inline void
-p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- u64 val = P6_NOP_EVENT;
+ event = cpuc->event_list[i];
+ hwc = &event->hw;
- if (cpuc->enabled)
- val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ /*
+ * we can avoid reprogramming counter if:
+ * - assigned same counter as last time
+ * - running on same CPU as last time
+ * - no other event has used the counter since
+ */
+ if (hwc->idx == -1 ||
+ match_prev_assignment(hwc, cpuc, i))
+ continue;
- (void)checking_wrmsrl(hwc->config_base + idx, val);
-}
+ x86_pmu_stop(event);
-static inline void
-intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
- if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
- intel_pmu_disable_bts();
- return;
- }
+ hwc->idx = -1;
+ }
- if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
- intel_pmu_disable_fixed(hwc, idx);
- return;
+ for (i = 0; i < cpuc->n_events; i++) {
+
+ event = cpuc->event_list[i];
+ hwc = &event->hw;
+
+ if (hwc->idx == -1) {
+ x86_assign_hw_event(event, cpuc, i);
+ x86_perf_event_set_period(event, hwc, hwc->idx);
+ }
+ /*
+ * need to mark as active because x86_pmu_disable()
+ * clear active_mask and events[] yet it preserves
+ * idx
+ */
+ set_bit(hwc->idx, cpuc->active_mask);
+ cpuc->events[hwc->idx] = event;
+
+ x86_pmu.enable(hwc, hwc->idx);
+ perf_event_update_userpage(event);
+ }
+ cpuc->n_added = 0;
+ perf_events_lapic_init();
}
- x86_pmu_disable_event(hwc, idx);
+ cpuc->enabled = 1;
+ barrier();
+
+ x86_pmu.enable_all();
+}
+
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+ (void)checking_wrmsrl(hwc->config_base + idx,
+ hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
}
-static inline void
-amd_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
- x86_pmu_disable_event(hwc, idx);
+ (void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
}
static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -1326,220 +919,60 @@ x86_perf_event_set_period(struct perf_event *event,
return ret;
}
-static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
-{
- int idx = __idx - X86_PMC_IDX_FIXED;
- u64 ctrl_val, bits, mask;
- int err;
-
- /*
- * Enable IRQ generation (0x8),
- * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
- * if requested:
- */
- bits = 0x8ULL;
- if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
- bits |= 0x2;
- if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
- bits |= 0x1;
-
- /*
- * ANY bit is supported in v3 and up
- */
- if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
- bits |= 0x4;
-
- bits <<= (idx * 4);
- mask = 0xfULL << (idx * 4);
-
- rdmsrl(hwc->config_base, ctrl_val);
- ctrl_val &= ~mask;
- ctrl_val |= bits;
- err = checking_wrmsrl(hwc->config_base, ctrl_val);
-}
-
-static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- u64 val;
-
- val = hwc->config;
if (cpuc->enabled)
- val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
-
- (void)checking_wrmsrl(hwc->config_base + idx, val);
+ __x86_pmu_enable_event(hwc, idx);
}
-
-static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
- if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
- if (!__get_cpu_var(cpu_hw_events).enabled)
- return;
-
- intel_pmu_enable_bts(hwc->config);
- return;
- }
-
- if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
- intel_pmu_enable_fixed(hwc, idx);
- return;
- }
-
- x86_pmu_enable_event(hwc, idx);
-}
-
-static void amd_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+/*
+ * activate a single event
+ *
+ * The event is added to the group of enabled events
+ * but only if it can be scehduled with existing events.
+ *
+ * Called with PMU disabled. If successful and return value 1,
+ * then guaranteed to call perf_enable() and hw_perf_enable()
+ */
+static int x86_pmu_enable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct hw_perf_event *hwc;
+ int assign[X86_PMC_IDX_MAX];
+ int n, n0, ret;
- if (cpuc->enabled)
- x86_pmu_enable_event(hwc, idx);
-}
-
-static int fixed_mode_idx(struct hw_perf_event *hwc)
-{
- unsigned int hw_event;
-
- hw_event = hwc->config & ARCH_PERFMON_EVENT_MASK;
-
- if (unlikely((hw_event ==
- x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
- (hwc->sample_period == 1)))
- return X86_PMC_IDX_FIXED_BTS;
+ hwc = &event->hw;
- if (!x86_pmu.num_events_fixed)
- return -1;
+ n0 = cpuc->n_events;
+ n = collect_events(cpuc, event, false);
+ if (n < 0)
+ return n;
+ ret = x86_schedule_events(cpuc, n, assign);
+ if (ret)
+ return ret;
/*
- * fixed counters do not take all possible filters
+ * copy new assignment, now we know it is possible
+ * will be used by hw_perf_enable()
*/
- if (hwc->config & ARCH_PERFMON_EVENT_FILTER_MASK)
- return -1;
+ memcpy(cpuc->assign, assign, n*sizeof(int));
- if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
- return X86_PMC_IDX_FIXED_INSTRUCTIONS;
- if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES)))
- return X86_PMC_IDX_FIXED_CPU_CYCLES;
- if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_BUS_CYCLES)))
- return X86_PMC_IDX_FIXED_BUS_CYCLES;
+ cpuc->n_events = n;
+ cpuc->n_added = n - n0;
- return -1;
-}
-
-/*
- * generic counter allocator: get next free counter
- */
-static int
-gen_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
-{
- int idx;
-
- idx = find_first_zero_bit(cpuc->used_mask, x86_pmu.num_events);
- return idx == x86_pmu.num_events ? -1 : idx;
-}
-
-/*
- * intel-specific counter allocator: check event constraints
- */
-static int
-intel_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
-{
- const struct event_constraint *event_constraint;
- int i, code;
-
- if (!event_constraints)
- goto skip;
-
- code = hwc->config & CORE_EVNTSEL_EVENT_MASK;
-
- for_each_event_constraint(event_constraint, event_constraints) {
- if (code == event_constraint->code) {
- for_each_bit(i, event_constraint->idxmsk, X86_PMC_IDX_MAX) {
- if (!test_and_set_bit(i, cpuc->used_mask))
- return i;
- }
- return -1;
- }
- }
-skip:
- return gen_get_event_idx(cpuc, hwc);
-}
-
-static int
-x86_schedule_event(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
-{
- int idx;
-
- idx = fixed_mode_idx(hwc);
- if (idx == X86_PMC_IDX_FIXED_BTS) {
- /* BTS is already occupied. */
- if (test_and_set_bit(idx, cpuc->used_mask))
- return -EAGAIN;
-
- hwc->config_base = 0;
- hwc->event_base = 0;
- hwc->idx = idx;
- } else if (idx >= 0) {
- /*
- * Try to get the fixed event, if that is already taken
- * then try to get a generic event:
- */
- if (test_and_set_bit(idx, cpuc->used_mask))
- goto try_generic;
-
- hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- /*
- * We set it so that event_base + idx in wrmsr/rdmsr maps to
- * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
- */
- hwc->event_base =
- MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
- hwc->idx = idx;
- } else {
- idx = hwc->idx;
- /* Try to get the previous generic event again */
- if (idx == -1 || test_and_set_bit(idx, cpuc->used_mask)) {
-try_generic:
- idx = x86_pmu.get_event_idx(cpuc, hwc);
- if (idx == -1)
- return -EAGAIN;
-
- set_bit(idx, cpuc->used_mask);
- hwc->idx = idx;
- }
- hwc->config_base = x86_pmu.eventsel;
- hwc->event_base = x86_pmu.perfctr;
- }
-
- return idx;
+ return 0;
}
-/*
- * Find a PMC slot for the freshly enabled / scheduled in event:
- */
-static int x86_pmu_enable(struct perf_event *event)
+static int x86_pmu_start(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- int idx;
-
- idx = x86_schedule_event(cpuc, hwc);
- if (idx < 0)
- return idx;
- perf_events_lapic_init();
-
- x86_pmu.disable(hwc, idx);
+ if (hwc->idx == -1)
+ return -EAGAIN;
- cpuc->events[idx] = event;
- set_bit(idx, cpuc->active_mask);
-
- x86_perf_event_set_period(event, hwc, idx);
- x86_pmu.enable(hwc, idx);
-
- perf_event_update_userpage(event);
+ x86_perf_event_set_period(event, hwc, hwc->idx);
+ x86_pmu.enable(hwc, hwc->idx);
return 0;
}
@@ -1583,7 +1016,7 @@ void perf_event_print_debug(void)
pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow);
pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed);
}
- pr_info("CPU#%d: used: %016llx\n", cpu, *(u64 *)cpuc->used_mask);
+ pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
for (idx = 0; idx < x86_pmu.num_events; idx++) {
rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
@@ -1607,67 +1040,7 @@ void perf_event_print_debug(void)
local_irq_restore(flags);
}
-static void intel_pmu_drain_bts_buffer(struct cpu_hw_events *cpuc)
-{
- struct debug_store *ds = cpuc->ds;
- struct bts_record {
- u64 from;
- u64 to;
- u64 flags;
- };
- struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
- struct bts_record *at, *top;
- struct perf_output_handle handle;
- struct perf_event_header header;
- struct perf_sample_data data;
- struct pt_regs regs;
-
- if (!event)
- return;
-
- if (!ds)
- return;
-
- at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
- top = (struct bts_record *)(unsigned long)ds->bts_index;
-
- if (top <= at)
- return;
-
- ds->bts_index = ds->bts_buffer_base;
-
-
- data.period = event->hw.last_period;
- data.addr = 0;
- data.raw = NULL;
- regs.ip = 0;
-
- /*
- * Prepare a generic sample, i.e. fill in the invariant fields.
- * We will overwrite the from and to address before we output
- * the sample.
- */
- perf_prepare_sample(&header, &data, event, &regs);
-
- if (perf_output_begin(&handle, event,
- header.size * (top - at), 1, 1))
- return;
-
- for (; at < top; at++) {
- data.ip = at->from;
- data.addr = at->to;
-
- perf_output_sample(&handle, &header, &data, event);
- }
-
- perf_output_end(&handle);
-
- /* There's new data available. */
- event->hw.interrupts++;
- event->pending_kill = POLL_IN;
-}
-
-static void x86_pmu_disable(struct perf_event *event)
+static void x86_pmu_stop(struct perf_event *event)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
@@ -1681,183 +1054,38 @@ static void x86_pmu_disable(struct perf_event *event)
x86_pmu.disable(hwc, idx);
/*
- * Make sure the cleared pointer becomes visible before we
- * (potentially) free the event:
- */
- barrier();
-
- /*
* Drain the remaining delta count out of a event
* that we are disabling:
*/
x86_perf_event_update(event, hwc, idx);
- /* Drain the remaining BTS records. */
- if (unlikely(idx == X86_PMC_IDX_FIXED_BTS))
- intel_pmu_drain_bts_buffer(cpuc);
-
cpuc->events[idx] = NULL;
- clear_bit(idx, cpuc->used_mask);
-
- perf_event_update_userpage(event);
-}
-
-/*
- * Save and restart an expired event. Called by NMI contexts,
- * so it has to be careful about preempting normal event ops:
- */
-static int intel_pmu_save_and_restart(struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx;
- int ret;
-
- x86_perf_event_update(event, hwc, idx);
- ret = x86_perf_event_set_period(event, hwc, idx);
-
- if (event->state == PERF_EVENT_STATE_ACTIVE)
- intel_pmu_enable_event(hwc, idx);
-
- return ret;
}
-static void intel_pmu_reset(void)
-{
- struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds;
- unsigned long flags;
- int idx;
-
- if (!x86_pmu.num_events)
- return;
-
- local_irq_save(flags);
-
- printk("clearing PMU state on CPU#%d\n", smp_processor_id());
-
- for (idx = 0; idx < x86_pmu.num_events; idx++) {
- checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
- checking_wrmsrl(x86_pmu.perfctr + idx, 0ull);
- }
- for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
- checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
- }
- if (ds)
- ds->bts_index = ds->bts_buffer_base;
-
- local_irq_restore(flags);
-}
-
-static int p6_pmu_handle_irq(struct pt_regs *regs)
-{
- struct perf_sample_data data;
- struct cpu_hw_events *cpuc;
- struct perf_event *event;
- struct hw_perf_event *hwc;
- int idx, handled = 0;
- u64 val;
-
- data.addr = 0;
- data.raw = NULL;
-
- cpuc = &__get_cpu_var(cpu_hw_events);
-
- for (idx = 0; idx < x86_pmu.num_events; idx++) {
- if (!test_bit(idx, cpuc->active_mask))
- continue;
-
- event = cpuc->events[idx];
- hwc = &event->hw;
-
- val = x86_perf_event_update(event, hwc, idx);
- if (val & (1ULL << (x86_pmu.event_bits - 1)))
- continue;
-
- /*
- * event overflow
- */
- handled = 1;
- data.period = event->hw.last_period;
-
- if (!x86_perf_event_set_period(event, hwc, idx))
- continue;
-
- if (perf_event_overflow(event, 1, &data, regs))
- p6_pmu_disable_event(hwc, idx);
- }
-
- if (handled)
- inc_irq_stat(apic_perf_irqs);
-
- return handled;
-}
-
-/*
- * This handler is triggered by the local APIC, so the APIC IRQ handling
- * rules apply:
- */
-static int intel_pmu_handle_irq(struct pt_regs *regs)
+static void x86_pmu_disable(struct perf_event *event)
{
- struct perf_sample_data data;
- struct cpu_hw_events *cpuc;
- int bit, loops;
- u64 ack, status;
-
- data.addr = 0;
- data.raw = NULL;
-
- cpuc = &__get_cpu_var(cpu_hw_events);
-
- perf_disable();
- intel_pmu_drain_bts_buffer(cpuc);
- status = intel_pmu_get_status();
- if (!status) {
- perf_enable();
- return 0;
- }
-
- loops = 0;
-again:
- if (++loops > 100) {
- WARN_ONCE(1, "perfevents: irq loop stuck!\n");
- perf_event_print_debug();
- intel_pmu_reset();
- perf_enable();
- return 1;
- }
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ int i;
- inc_irq_stat(apic_perf_irqs);
- ack = status;
- for_each_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
- struct perf_event *event = cpuc->events[bit];
+ x86_pmu_stop(event);
- clear_bit(bit, (unsigned long *) &status);
- if (!test_bit(bit, cpuc->active_mask))
- continue;
+ for (i = 0; i < cpuc->n_events; i++) {
+ if (event == cpuc->event_list[i]) {
- if (!intel_pmu_save_and_restart(event))
- continue;
+ if (x86_pmu.put_event_constraints)
+ x86_pmu.put_event_constraints(cpuc, event);
- data.period = event->hw.last_period;
+ while (++i < cpuc->n_events)
+ cpuc->event_list[i-1] = cpuc->event_list[i];
- if (perf_event_overflow(event, 1, &data, regs))
- intel_pmu_disable_event(&event->hw, bit);
+ --cpuc->n_events;
+ break;
+ }
}
-
- intel_pmu_ack_status(ack);
-
- /*
- * Repeat if there is more work to be done:
- */
- status = intel_pmu_get_status();
- if (status)
- goto again;
-
- perf_enable();
-
- return 1;
+ perf_event_update_userpage(event);
}
-static int amd_pmu_handle_irq(struct pt_regs *regs)
+static int x86_pmu_handle_irq(struct pt_regs *regs)
{
struct perf_sample_data data;
struct cpu_hw_events *cpuc;
@@ -1892,7 +1120,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
continue;
if (perf_event_overflow(event, 1, &data, regs))
- amd_pmu_disable_event(hwc, idx);
+ x86_pmu.disable(hwc, idx);
}
if (handled)
@@ -1975,194 +1203,137 @@ static __read_mostly struct notifier_block perf_event_nmi_notifier = {
.priority = 1
};
-static __initconst struct x86_pmu p6_pmu = {
- .name = "p6",
- .handle_irq = p6_pmu_handle_irq,
- .disable_all = p6_pmu_disable_all,
- .enable_all = p6_pmu_enable_all,
- .enable = p6_pmu_enable_event,
- .disable = p6_pmu_disable_event,
- .eventsel = MSR_P6_EVNTSEL0,
- .perfctr = MSR_P6_PERFCTR0,
- .event_map = p6_pmu_event_map,
- .raw_event = p6_pmu_raw_event,
- .max_events = ARRAY_SIZE(p6_perfmon_event_map),
- .apic = 1,
- .max_period = (1ULL << 31) - 1,
- .version = 0,
- .num_events = 2,
- /*
- * Events have 40 bits implemented. However they are designed such
- * that bits [32-39] are sign extensions of bit 31. As such the
- * effective width of a event for P6-like PMU is 32 bits only.
- *
- * See IA-32 Intel Architecture Software developer manual Vol 3B
- */
- .event_bits = 32,
- .event_mask = (1ULL << 32) - 1,
- .get_event_idx = intel_get_event_idx,
-};
+static struct event_constraint unconstrained;
+static struct event_constraint emptyconstraint;
-static __initconst struct x86_pmu intel_pmu = {
- .name = "Intel",
- .handle_irq = intel_pmu_handle_irq,
- .disable_all = intel_pmu_disable_all,
- .enable_all = intel_pmu_enable_all,
- .enable = intel_pmu_enable_event,
- .disable = intel_pmu_disable_event,
- .eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
- .perfctr = MSR_ARCH_PERFMON_PERFCTR0,
- .event_map = intel_pmu_event_map,
- .raw_event = intel_pmu_raw_event,
- .max_events = ARRAY_SIZE(intel_perfmon_event_map),
- .apic = 1,
- /*
- * Intel PMCs cannot be accessed sanely above 32 bit width,
- * so we install an artificial 1<<31 period regardless of
- * the generic event period:
- */
- .max_period = (1ULL << 31) - 1,
- .enable_bts = intel_pmu_enable_bts,
- .disable_bts = intel_pmu_disable_bts,
- .get_event_idx = intel_get_event_idx,
-};
+static struct event_constraint *
+x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+ struct event_constraint *c;
-static __initconst struct x86_pmu amd_pmu = {
- .name = "AMD",
- .handle_irq = amd_pmu_handle_irq,
- .disable_all = amd_pmu_disable_all,
- .enable_all = amd_pmu_enable_all,
- .enable = amd_pmu_enable_event,
- .disable = amd_pmu_disable_event,
- .eventsel = MSR_K7_EVNTSEL0,
- .perfctr = MSR_K7_PERFCTR0,
- .event_map = amd_pmu_event_map,
- .raw_event = amd_pmu_raw_event,
- .max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_events = 4,
- .event_bits = 48,
- .event_mask = (1ULL << 48) - 1,
- .apic = 1,
- /* use highest bit to detect overflow */
- .max_period = (1ULL << 47) - 1,
- .get_event_idx = gen_get_event_idx,
-};
+ if (x86_pmu.event_constraints) {
+ for_each_event_constraint(c, x86_pmu.event_constraints) {
+ if ((event->hw.config & c->cmask) == c->code)
+ return c;
+ }
+ }
+
+ return &unconstrained;
+}
-static __init int p6_pmu_init(void)
+static int x86_event_sched_in(struct perf_event *event,
+ struct perf_cpu_context *cpuctx)
{
- switch (boot_cpu_data.x86_model) {
- case 1:
- case 3: /* Pentium Pro */
- case 5:
- case 6: /* Pentium II */
- case 7:
- case 8:
- case 11: /* Pentium III */
- event_constraints = intel_p6_event_constraints;
- break;
- case 9:
- case 13:
- /* Pentium M */
- event_constraints = intel_p6_event_constraints;
- break;
- default:
- pr_cont("unsupported p6 CPU model %d ",
- boot_cpu_data.x86_model);
- return -ENODEV;
- }
+ int ret = 0;
- x86_pmu = p6_pmu;
+ event->state = PERF_EVENT_STATE_ACTIVE;
+ event->oncpu = smp_processor_id();
+ event->tstamp_running += event->ctx->time - event->tstamp_stopped;
- return 0;
+ if (!is_x86_event(event))
+ ret = event->pmu->enable(event);
+
+ if (!ret && !is_software_event(event))
+ cpuctx->active_oncpu++;
+
+ if (!ret && event->attr.exclusive)
+ cpuctx->exclusive = 1;
+
+ return ret;
}
-static __init int intel_pmu_init(void)
+static void x86_event_sched_out(struct perf_event *event,
+ struct perf_cpu_context *cpuctx)
{
- union cpuid10_edx edx;
- union cpuid10_eax eax;
- unsigned int unused;
- unsigned int ebx;
- int version;
-
- if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
- /* check for P6 processor family */
- if (boot_cpu_data.x86 == 6) {
- return p6_pmu_init();
- } else {
- return -ENODEV;
- }
- }
+ event->state = PERF_EVENT_STATE_INACTIVE;
+ event->oncpu = -1;
- /*
- * Check whether the Architectural PerfMon supports
- * Branch Misses Retired hw_event or not.
- */
- cpuid(10, &eax.full, &ebx, &unused, &edx.full);
- if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
- return -ENODEV;
+ if (!is_x86_event(event))
+ event->pmu->disable(event);
- version = eax.split.version_id;
- if (version < 2)
- return -ENODEV;
+ event->tstamp_running -= event->ctx->time - event->tstamp_stopped;
- x86_pmu = intel_pmu;
- x86_pmu.version = version;
- x86_pmu.num_events = eax.split.num_events;
- x86_pmu.event_bits = eax.split.bit_width;
- x86_pmu.event_mask = (1ULL << eax.split.bit_width) - 1;
+ if (!is_software_event(event))
+ cpuctx->active_oncpu--;
- /*
- * Quirk: v2 perfmon does not report fixed-purpose events, so
- * assume at least 3 events:
- */
- x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3);
+ if (event->attr.exclusive || !cpuctx->active_oncpu)
+ cpuctx->exclusive = 0;
+}
+/*
+ * Called to enable a whole group of events.
+ * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
+ * Assumes the caller has disabled interrupts and has
+ * frozen the PMU with hw_perf_save_disable.
+ *
+ * called with PMU disabled. If successful and return value 1,
+ * then guaranteed to call perf_enable() and hw_perf_enable()
+ */
+int hw_perf_group_sched_in(struct perf_event *leader,
+ struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct perf_event *sub;
+ int assign[X86_PMC_IDX_MAX];
+ int n0, n1, ret;
+
+ /* n0 = total number of events */
+ n0 = collect_events(cpuc, leader, true);
+ if (n0 < 0)
+ return n0;
+
+ ret = x86_schedule_events(cpuc, n0, assign);
+ if (ret)
+ return ret;
+
+ ret = x86_event_sched_in(leader, cpuctx);
+ if (ret)
+ return ret;
+
+ n1 = 1;
+ list_for_each_entry(sub, &leader->sibling_list, group_entry) {
+ if (sub->state > PERF_EVENT_STATE_OFF) {
+ ret = x86_event_sched_in(sub, cpuctx);
+ if (ret)
+ goto undo;
+ ++n1;
+ }
+ }
/*
- * Install the hw-cache-events table:
+ * copy new assignment, now we know it is possible
+ * will be used by hw_perf_enable()
*/
- switch (boot_cpu_data.x86_model) {
- case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
- case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
- case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
- case 29: /* six-core 45 nm xeon "Dunnington" */
- memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
-
- pr_cont("Core2 events, ");
- event_constraints = intel_core_event_constraints;
- break;
- default:
- case 26:
- memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
+ memcpy(cpuc->assign, assign, n0*sizeof(int));
- event_constraints = intel_nehalem_event_constraints;
- pr_cont("Nehalem/Corei7 events, ");
- break;
- case 28:
- memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
+ cpuc->n_events = n0;
+ cpuc->n_added = n1;
+ ctx->nr_active += n1;
- pr_cont("Atom events, ");
- break;
+ /*
+ * 1 means successful and events are active
+ * This is not quite true because we defer
+ * actual activation until hw_perf_enable() but
+ * this way we* ensure caller won't try to enable
+ * individual events
+ */
+ return 1;
+undo:
+ x86_event_sched_out(leader, cpuctx);
+ n0 = 1;
+ list_for_each_entry(sub, &leader->sibling_list, group_entry) {
+ if (sub->state == PERF_EVENT_STATE_ACTIVE) {
+ x86_event_sched_out(sub, cpuctx);
+ if (++n0 == n1)
+ break;
+ }
}
- return 0;
+ return ret;
}
-static __init int amd_pmu_init(void)
-{
- /* Performance-monitoring supported from K7 and later: */
- if (boot_cpu_data.x86 < 6)
- return -ENODEV;
-
- x86_pmu = amd_pmu;
-
- /* Events are common for all AMDs */
- memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
-
- return 0;
-}
+#include "perf_event_amd.c"
+#include "perf_event_p6.c"
+#include "perf_event_intel.c"
static void __init pmu_check_apic(void)
{
@@ -2220,6 +1391,10 @@ void __init init_hw_perf_events(void)
perf_events_lapic_init();
register_die_notifier(&perf_event_nmi_notifier);
+ unconstrained = (struct event_constraint)
+ __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
+ 0, x86_pmu.num_events);
+
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.event_bits);
pr_info("... generic registers: %d\n", x86_pmu.num_events);
@@ -2237,50 +1412,79 @@ static inline void x86_pmu_read(struct perf_event *event)
static const struct pmu pmu = {
.enable = x86_pmu_enable,
.disable = x86_pmu_disable,
+ .start = x86_pmu_start,
+ .stop = x86_pmu_stop,
.read = x86_pmu_read,
.unthrottle = x86_pmu_unthrottle,
};
-static int
-validate_event(struct cpu_hw_events *cpuc, struct perf_event *event)
-{
- struct hw_perf_event fake_event = event->hw;
-
- if (event->pmu && event->pmu != &pmu)
- return 0;
-
- return x86_schedule_event(cpuc, &fake_event) >= 0;
-}
-
+/*
+ * validate a single event group
+ *
+ * validation include:
+ * - check events are compatible which each other
+ * - events do not compete for the same counter
+ * - number of events <= number of counters
+ *
+ * validation ensures the group can be loaded onto the
+ * PMU if it was the only group available.
+ */
static int validate_group(struct perf_event *event)
{
- struct perf_event *sibling, *leader = event->group_leader;
- struct cpu_hw_events fake_pmu;
+ struct perf_event *leader = event->group_leader;
+ struct cpu_hw_events *fake_cpuc;
+ int ret, n;
- memset(&fake_pmu, 0, sizeof(fake_pmu));
+ ret = -ENOMEM;
+ fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO);
+ if (!fake_cpuc)
+ goto out;
+
+ /*
+ * 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
+ */
+ ret = -ENOSPC;
+ n = collect_events(fake_cpuc, leader, true);
+ if (n < 0)
+ goto out_free;
- if (!validate_event(&fake_pmu, leader))
- return -ENOSPC;
+ fake_cpuc->n_events = n;
+ n = collect_events(fake_cpuc, event, false);
+ if (n < 0)
+ goto out_free;
- list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
- if (!validate_event(&fake_pmu, sibling))
- return -ENOSPC;
- }
+ fake_cpuc->n_events = n;
- if (!validate_event(&fake_pmu, event))
- return -ENOSPC;
+ ret = x86_schedule_events(fake_cpuc, n, NULL);
- return 0;
+out_free:
+ kfree(fake_cpuc);
+out:
+ return ret;
}
const struct pmu *hw_perf_event_init(struct perf_event *event)
{
+ const struct pmu *tmp;
int err;
err = __hw_perf_event_init(event);
if (!err) {
+ /*
+ * we temporarily connect event to its pmu
+ * such that validate_group() can classify
+ * it as an x86 event using is_x86_event()
+ */
+ tmp = event->pmu;
+ event->pmu = &pmu;
+
if (event->group_leader != event)
err = validate_group(event);
+
+ event->pmu = tmp;
}
if (err) {
if (event->destroy)
@@ -2304,7 +1508,6 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
-static DEFINE_PER_CPU(int, in_ignored_frame);
static void
@@ -2320,10 +1523,6 @@ static void backtrace_warning(void *data, char *msg)
static int backtrace_stack(void *data, char *name)
{
- per_cpu(in_ignored_frame, smp_processor_id()) =
- x86_is_stack_id(NMI_STACK, name) ||
- x86_is_stack_id(DEBUG_STACK, name);
-
return 0;
}
@@ -2331,9 +1530,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
{
struct perf_callchain_entry *entry = data;
- if (per_cpu(in_ignored_frame, smp_processor_id()))
- return;
-
if (reliable)
callchain_store(entry, addr);
}
@@ -2440,9 +1636,6 @@ perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
is_user = user_mode(regs);
- if (!current || current->pid == 0)
- return;
-
if (is_user && current->state != TASK_RUNNING)
return;
@@ -2472,4 +1665,25 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
void hw_perf_event_setup_online(int cpu)
{
init_debug_store_on_cpu(cpu);
+
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_AMD:
+ amd_pmu_cpu_online(cpu);
+ break;
+ default:
+ return;
+ }
+}
+
+void hw_perf_event_setup_offline(int cpu)
+{
+ init_debug_store_on_cpu(cpu);
+
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_AMD:
+ amd_pmu_cpu_offline(cpu);
+ break;
+ default:
+ return;
+ }
}
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
new file mode 100644
index 00000000000..8f3dbfda3c4
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -0,0 +1,416 @@
+#ifdef CONFIG_CPU_SUP_AMD
+
+static DEFINE_RAW_SPINLOCK(amd_nb_lock);
+
+static __initconst u64 amd_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */
+ [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0267, /* Data Prefetcher :attempts */
+ [ C(RESULT_MISS) ] = 0x0167, /* Data Prefetcher :cancelled */
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction cache fetches */
+ [ C(RESULT_MISS) ] = 0x0081, /* Instruction cache misses */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x014B, /* Prefetch Instructions :Load */
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x037D, /* Requests to L2 Cache :IC+DC */
+ [ C(RESULT_MISS) ] = 0x037E, /* L2 Cache Misses : IC+DC */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x017F, /* L2 Fill/Writeback */
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */
+ [ C(RESULT_MISS) ] = 0x0046, /* L1 DTLB and L2 DLTB Miss */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes */
+ [ C(RESULT_MISS) ] = 0x0085, /* Instr. fetch ITLB misses */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c2, /* Retired Branch Instr. */
+ [ C(RESULT_MISS) ] = 0x00c3, /* Retired Mispredicted BI */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
+/*
+ * AMD Performance Monitor K7 and later.
+ */
+static const u64 amd_perfmon_event_map[] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
+};
+
+static u64 amd_pmu_event_map(int hw_event)
+{
+ return amd_perfmon_event_map[hw_event];
+}
+
+static u64 amd_pmu_raw_event(u64 hw_event)
+{
+#define K7_EVNTSEL_EVENT_MASK 0xF000000FFULL
+#define K7_EVNTSEL_UNIT_MASK 0x00000FF00ULL
+#define K7_EVNTSEL_EDGE_MASK 0x000040000ULL
+#define K7_EVNTSEL_INV_MASK 0x000800000ULL
+#define K7_EVNTSEL_REG_MASK 0x0FF000000ULL
+
+#define K7_EVNTSEL_MASK \
+ (K7_EVNTSEL_EVENT_MASK | \
+ K7_EVNTSEL_UNIT_MASK | \
+ K7_EVNTSEL_EDGE_MASK | \
+ K7_EVNTSEL_INV_MASK | \
+ K7_EVNTSEL_REG_MASK)
+
+ return hw_event & K7_EVNTSEL_MASK;
+}
+
+/*
+ * AMD64 events are detected based on their event codes.
+ */
+static inline int amd_is_nb_event(struct hw_perf_event *hwc)
+{
+ return (hwc->config & 0xe0) == 0xe0;
+}
+
+static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct amd_nb *nb = cpuc->amd_nb;
+ int i;
+
+ /*
+ * only care about NB events
+ */
+ if (!(nb && amd_is_nb_event(hwc)))
+ return;
+
+ /*
+ * need to scan whole list because event may not have
+ * been assigned during scheduling
+ *
+ * no race condition possible because event can only
+ * be removed on one CPU at a time AND PMU is disabled
+ * when we come here
+ */
+ for (i = 0; i < x86_pmu.num_events; i++) {
+ if (nb->owners[i] == event) {
+ cmpxchg(nb->owners+i, event, NULL);
+ break;
+ }
+ }
+}
+
+ /*
+ * AMD64 NorthBridge events need special treatment because
+ * counter access needs to be synchronized across all cores
+ * of a package. Refer to BKDG section 3.12
+ *
+ * NB events are events measuring L3 cache, Hypertransport
+ * traffic. They are identified by an event code >= 0xe00.
+ * They measure events on the NorthBride which is shared
+ * by all cores on a package. NB events are counted on a
+ * shared set of counters. When a NB event is programmed
+ * in a counter, the data actually comes from a shared
+ * counter. Thus, access to those counters needs to be
+ * synchronized.
+ *
+ * We implement the synchronization such that no two cores
+ * can be measuring NB events using the same counters. Thus,
+ * we maintain a per-NB allocation table. The available slot
+ * is propagated using the event_constraint structure.
+ *
+ * We provide only one choice for each NB event based on
+ * the fact that only NB events have restrictions. Consequently,
+ * if a counter is available, there is a guarantee the NB event
+ * will be assigned to it. If no slot is available, an empty
+ * constraint is returned and scheduling will eventually fail
+ * for this event.
+ *
+ * Note that all cores attached the same NB compete for the same
+ * counters to host NB events, this is why we use atomic ops. Some
+ * multi-chip CPUs may have more than one NB.
+ *
+ * Given that resources are allocated (cmpxchg), they must be
+ * eventually freed for others to use. This is accomplished by
+ * calling amd_put_event_constraints().
+ *
+ * Non NB events are not impacted by this restriction.
+ */
+static struct event_constraint *
+amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct amd_nb *nb = cpuc->amd_nb;
+ struct perf_event *old = NULL;
+ int max = x86_pmu.num_events;
+ int i, j, k = -1;
+
+ /*
+ * if not NB event or no NB, then no constraints
+ */
+ if (!(nb && amd_is_nb_event(hwc)))
+ return &unconstrained;
+
+ /*
+ * detect if already present, if so reuse
+ *
+ * cannot merge with actual allocation
+ * because of possible holes
+ *
+ * event can already be present yet not assigned (in hwc->idx)
+ * because of successive calls to x86_schedule_events() from
+ * hw_perf_group_sched_in() without hw_perf_enable()
+ */
+ for (i = 0; i < max; i++) {
+ /*
+ * keep track of first free slot
+ */
+ if (k == -1 && !nb->owners[i])
+ k = i;
+
+ /* already present, reuse */
+ if (nb->owners[i] == event)
+ goto done;
+ }
+ /*
+ * not present, so grab a new slot
+ * starting either at:
+ */
+ if (hwc->idx != -1) {
+ /* previous assignment */
+ i = hwc->idx;
+ } else if (k != -1) {
+ /* start from free slot found */
+ i = k;
+ } else {
+ /*
+ * event not found, no slot found in
+ * first pass, try again from the
+ * beginning
+ */
+ i = 0;
+ }
+ j = i;
+ do {
+ old = cmpxchg(nb->owners+i, NULL, event);
+ if (!old)
+ break;
+ if (++i == max)
+ i = 0;
+ } while (i != j);
+done:
+ if (!old)
+ return &nb->event_constraints[i];
+
+ return &emptyconstraint;
+}
+
+static __initconst 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,
+ .eventsel = MSR_K7_EVNTSEL0,
+ .perfctr = MSR_K7_PERFCTR0,
+ .event_map = amd_pmu_event_map,
+ .raw_event = amd_pmu_raw_event,
+ .max_events = ARRAY_SIZE(amd_perfmon_event_map),
+ .num_events = 4,
+ .event_bits = 48,
+ .event_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
+};
+
+static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
+{
+ struct amd_nb *nb;
+ int i;
+
+ nb = kmalloc(sizeof(struct amd_nb), GFP_KERNEL);
+ if (!nb)
+ return NULL;
+
+ memset(nb, 0, sizeof(*nb));
+ nb->nb_id = nb_id;
+
+ /*
+ * initialize all possible NB constraints
+ */
+ for (i = 0; i < x86_pmu.num_events; i++) {
+ set_bit(i, nb->event_constraints[i].idxmsk);
+ nb->event_constraints[i].weight = 1;
+ }
+ return nb;
+}
+
+static void amd_pmu_cpu_online(int cpu)
+{
+ struct cpu_hw_events *cpu1, *cpu2;
+ struct amd_nb *nb = NULL;
+ int i, nb_id;
+
+ if (boot_cpu_data.x86_max_cores < 2)
+ return;
+
+ /*
+ * function may be called too early in the
+ * boot process, in which case nb_id is bogus
+ */
+ nb_id = amd_get_nb_id(cpu);
+ if (nb_id == BAD_APICID)
+ return;
+
+ cpu1 = &per_cpu(cpu_hw_events, cpu);
+ cpu1->amd_nb = NULL;
+
+ raw_spin_lock(&amd_nb_lock);
+
+ for_each_online_cpu(i) {
+ cpu2 = &per_cpu(cpu_hw_events, i);
+ nb = cpu2->amd_nb;
+ if (!nb)
+ continue;
+ if (nb->nb_id == nb_id)
+ goto found;
+ }
+
+ nb = amd_alloc_nb(cpu, nb_id);
+ if (!nb) {
+ pr_err("perf_events: failed NB allocation for CPU%d\n", cpu);
+ raw_spin_unlock(&amd_nb_lock);
+ return;
+ }
+found:
+ nb->refcnt++;
+ cpu1->amd_nb = nb;
+
+ raw_spin_unlock(&amd_nb_lock);
+}
+
+static void amd_pmu_cpu_offline(int cpu)
+{
+ struct cpu_hw_events *cpuhw;
+
+ if (boot_cpu_data.x86_max_cores < 2)
+ return;
+
+ cpuhw = &per_cpu(cpu_hw_events, cpu);
+
+ raw_spin_lock(&amd_nb_lock);
+
+ if (--cpuhw->amd_nb->refcnt == 0)
+ kfree(cpuhw->amd_nb);
+
+ cpuhw->amd_nb = NULL;
+
+ raw_spin_unlock(&amd_nb_lock);
+}
+
+static __init int amd_pmu_init(void)
+{
+ /* Performance-monitoring supported from K7 and later: */
+ if (boot_cpu_data.x86 < 6)
+ return -ENODEV;
+
+ x86_pmu = amd_pmu;
+
+ /* Events are common for all AMDs */
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ /*
+ * explicitly initialize the boot cpu, other cpus will get
+ * the cpu hotplug callbacks from smp_init()
+ */
+ amd_pmu_cpu_online(smp_processor_id());
+ return 0;
+}
+
+#else /* CONFIG_CPU_SUP_AMD */
+
+static int amd_pmu_init(void)
+{
+ return 0;
+}
+
+static void amd_pmu_cpu_online(int cpu)
+{
+}
+
+static void amd_pmu_cpu_offline(int cpu)
+{
+}
+
+#endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
new file mode 100644
index 00000000000..cf6590cf4a5
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -0,0 +1,971 @@
+#ifdef CONFIG_CPU_SUP_INTEL
+
+/*
+ * Intel PerfMon v3. Used on Core2 and later.
+ */
+static const u64 intel_perfmon_event_map[] =
+{
+ [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,
+};
+
+static struct event_constraint intel_core_event_constraints[] =
+{
+ INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
+ INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
+ INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
+ INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
+ INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
+ INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FP_COMP_INSTR_RET */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_core2_event_constraints[] =
+{
+ FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+ FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
+ INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
+ INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
+ INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
+ INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
+ INTEL_EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */
+ INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
+ INTEL_EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_nehalem_event_constraints[] =
+{
+ FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+ FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
+ INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
+ INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
+ INTEL_EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */
+ INTEL_EVENT_CONSTRAINT(0x48, 0x3), /* L1D_PEND_MISS */
+ INTEL_EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */
+ INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
+ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_westmere_event_constraints[] =
+{
+ FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+ FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
+ INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
+ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_gen_event_constraints[] =
+{
+ FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+ FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+ EVENT_CONSTRAINT_END
+};
+
+static u64 intel_pmu_event_map(int hw_event)
+{
+ return intel_perfmon_event_map[hw_event];
+}
+
+static __initconst u64 westmere_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */
+ [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */
+ [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
+ [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
+ [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
+ [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */
+ [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+ [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
+static __initconst u64 nehalem_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */
+ [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */
+ [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */
+ [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */
+ [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
+ [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
+ [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
+ [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI (alias) */
+ [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI (alias) */
+ [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */
+ [ C(RESULT_MISS) ] = 0x20c8, /* ITLB_MISS_RETIRED */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+ [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
+static __initconst u64 core2_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */
+ [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */
+ [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x104e, /* L1D_PREFETCH.REQUESTS */
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0080, /* L1I.READS */
+ [ C(RESULT_MISS) ] = 0x0081, /* L1I.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI */
+ [ C(RESULT_MISS) ] = 0x4129, /* L2_LD.ISTATE */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI */
+ [ C(RESULT_MISS) ] = 0x412A, /* L2_ST.ISTATE */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI (alias) */
+ [ C(RESULT_MISS) ] = 0x0208, /* DTLB_MISSES.MISS_LD */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI (alias) */
+ [ C(RESULT_MISS) ] = 0x0808, /* DTLB_MISSES.MISS_ST */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
+ [ C(RESULT_MISS) ] = 0x1282, /* ITLBMISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */
+ [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
+static __initconst u64 atom_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE.LD */
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE.ST */
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */
+ [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI */
+ [ C(RESULT_MISS) ] = 0x4129, /* L2_LD.ISTATE */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI */
+ [ C(RESULT_MISS) ] = 0x412A, /* L2_ST.ISTATE */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE_LD.MESI (alias) */
+ [ C(RESULT_MISS) ] = 0x0508, /* DTLB_MISSES.MISS_LD */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE_ST.MESI (alias) */
+ [ C(RESULT_MISS) ] = 0x0608, /* DTLB_MISSES.MISS_ST */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
+ [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */
+ [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
+static u64 intel_pmu_raw_event(u64 hw_event)
+{
+#define CORE_EVNTSEL_EVENT_MASK 0x000000FFULL
+#define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL
+#define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL
+#define CORE_EVNTSEL_INV_MASK 0x00800000ULL
+#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL
+
+#define CORE_EVNTSEL_MASK \
+ (INTEL_ARCH_EVTSEL_MASK | \
+ INTEL_ARCH_UNIT_MASK | \
+ INTEL_ARCH_EDGE_MASK | \
+ INTEL_ARCH_INV_MASK | \
+ INTEL_ARCH_CNT_MASK)
+
+ return hw_event & CORE_EVNTSEL_MASK;
+}
+
+static void intel_pmu_enable_bts(u64 config)
+{
+ unsigned long debugctlmsr;
+
+ debugctlmsr = get_debugctlmsr();
+
+ debugctlmsr |= X86_DEBUGCTL_TR;
+ debugctlmsr |= X86_DEBUGCTL_BTS;
+ debugctlmsr |= X86_DEBUGCTL_BTINT;
+
+ if (!(config & ARCH_PERFMON_EVENTSEL_OS))
+ debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
+
+ if (!(config & ARCH_PERFMON_EVENTSEL_USR))
+ debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
+
+ update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_bts(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ unsigned long debugctlmsr;
+
+ if (!cpuc->ds)
+ return;
+
+ debugctlmsr = get_debugctlmsr();
+
+ debugctlmsr &=
+ ~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
+ X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
+
+ update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_all(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+
+ if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+ intel_pmu_disable_bts();
+}
+
+static void intel_pmu_enable_all(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+
+ if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+ struct perf_event *event =
+ cpuc->events[X86_PMC_IDX_FIXED_BTS];
+
+ if (WARN_ON_ONCE(!event))
+ return;
+
+ intel_pmu_enable_bts(event->hw.config);
+ }
+}
+
+static inline u64 intel_pmu_get_status(void)
+{
+ u64 status;
+
+ rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+
+ return status;
+}
+
+static inline void intel_pmu_ack_status(u64 ack)
+{
+ wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+}
+
+static inline void
+intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
+{
+ int idx = __idx - X86_PMC_IDX_FIXED;
+ u64 ctrl_val, mask;
+
+ mask = 0xfULL << (idx * 4);
+
+ rdmsrl(hwc->config_base, ctrl_val);
+ ctrl_val &= ~mask;
+ (void)checking_wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void intel_pmu_drain_bts_buffer(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct bts_record {
+ u64 from;
+ u64 to;
+ u64 flags;
+ };
+ struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
+ struct bts_record *at, *top;
+ struct perf_output_handle handle;
+ struct perf_event_header header;
+ struct perf_sample_data data;
+ struct pt_regs regs;
+
+ if (!event)
+ return;
+
+ if (!ds)
+ return;
+
+ at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+ top = (struct bts_record *)(unsigned long)ds->bts_index;
+
+ if (top <= at)
+ return;
+
+ ds->bts_index = ds->bts_buffer_base;
+
+
+ data.period = event->hw.last_period;
+ data.addr = 0;
+ data.raw = NULL;
+ regs.ip = 0;
+
+ /*
+ * Prepare a generic sample, i.e. fill in the invariant fields.
+ * We will overwrite the from and to address before we output
+ * the sample.
+ */
+ perf_prepare_sample(&header, &data, event, &regs);
+
+ if (perf_output_begin(&handle, event,
+ header.size * (top - at), 1, 1))
+ return;
+
+ for (; at < top; at++) {
+ data.ip = at->from;
+ data.addr = at->to;
+
+ perf_output_sample(&handle, &header, &data, event);
+ }
+
+ perf_output_end(&handle);
+
+ /* There's new data available. */
+ event->hw.interrupts++;
+ event->pending_kill = POLL_IN;
+}
+
+static inline void
+intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+ if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+ intel_pmu_disable_bts();
+ intel_pmu_drain_bts_buffer();
+ return;
+ }
+
+ if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+ intel_pmu_disable_fixed(hwc, idx);
+ return;
+ }
+
+ x86_pmu_disable_event(hwc, idx);
+}
+
+static inline void
+intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
+{
+ int idx = __idx - X86_PMC_IDX_FIXED;
+ u64 ctrl_val, bits, mask;
+ int err;
+
+ /*
+ * Enable IRQ generation (0x8),
+ * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
+ * if requested:
+ */
+ bits = 0x8ULL;
+ if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
+ bits |= 0x2;
+ if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+ bits |= 0x1;
+
+ /*
+ * ANY bit is supported in v3 and up
+ */
+ if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
+ bits |= 0x4;
+
+ bits <<= (idx * 4);
+ mask = 0xfULL << (idx * 4);
+
+ rdmsrl(hwc->config_base, ctrl_val);
+ ctrl_val &= ~mask;
+ ctrl_val |= bits;
+ err = checking_wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+ if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+ if (!__get_cpu_var(cpu_hw_events).enabled)
+ return;
+
+ intel_pmu_enable_bts(hwc->config);
+ return;
+ }
+
+ if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+ intel_pmu_enable_fixed(hwc, idx);
+ return;
+ }
+
+ __x86_pmu_enable_event(hwc, idx);
+}
+
+/*
+ * Save and restart an expired event. Called by NMI contexts,
+ * so it has to be careful about preempting normal event ops:
+ */
+static int intel_pmu_save_and_restart(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+ int ret;
+
+ x86_perf_event_update(event, hwc, idx);
+ ret = x86_perf_event_set_period(event, hwc, idx);
+
+ return ret;
+}
+
+static void intel_pmu_reset(void)
+{
+ struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds;
+ unsigned long flags;
+ int idx;
+
+ if (!x86_pmu.num_events)
+ return;
+
+ local_irq_save(flags);
+
+ printk("clearing PMU state on CPU#%d\n", smp_processor_id());
+
+ for (idx = 0; idx < x86_pmu.num_events; idx++) {
+ checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
+ checking_wrmsrl(x86_pmu.perfctr + idx, 0ull);
+ }
+ for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
+ checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+ }
+ if (ds)
+ ds->bts_index = ds->bts_buffer_base;
+
+ local_irq_restore(flags);
+}
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static int intel_pmu_handle_irq(struct pt_regs *regs)
+{
+ struct perf_sample_data data;
+ struct cpu_hw_events *cpuc;
+ int bit, loops;
+ u64 ack, status;
+
+ data.addr = 0;
+ data.raw = NULL;
+
+ cpuc = &__get_cpu_var(cpu_hw_events);
+
+ perf_disable();
+ intel_pmu_drain_bts_buffer();
+ status = intel_pmu_get_status();
+ if (!status) {
+ perf_enable();
+ return 0;
+ }
+
+ loops = 0;
+again:
+ if (++loops > 100) {
+ WARN_ONCE(1, "perfevents: irq loop stuck!\n");
+ perf_event_print_debug();
+ intel_pmu_reset();
+ perf_enable();
+ return 1;
+ }
+
+ inc_irq_stat(apic_perf_irqs);
+ ack = status;
+ for_each_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+ struct perf_event *event = cpuc->events[bit];
+
+ clear_bit(bit, (unsigned long *) &status);
+ if (!test_bit(bit, cpuc->active_mask))
+ continue;
+
+ if (!intel_pmu_save_and_restart(event))
+ continue;
+
+ data.period = event->hw.last_period;
+
+ if (perf_event_overflow(event, 1, &data, regs))
+ intel_pmu_disable_event(&event->hw, bit);
+ }
+
+ intel_pmu_ack_status(ack);
+
+ /*
+ * Repeat if there is more work to be done:
+ */
+ status = intel_pmu_get_status();
+ if (status)
+ goto again;
+
+ perf_enable();
+
+ return 1;
+}
+
+static struct event_constraint bts_constraint =
+ EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
+
+static struct event_constraint *
+intel_special_constraints(struct perf_event *event)
+{
+ unsigned int hw_event;
+
+ hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK;
+
+ if (unlikely((hw_event ==
+ x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
+ (event->hw.sample_period == 1))) {
+
+ return &bts_constraint;
+ }
+ return NULL;
+}
+
+static struct event_constraint *
+intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+ struct event_constraint *c;
+
+ c = intel_special_constraints(event);
+ if (c)
+ return c;
+
+ return x86_get_event_constraints(cpuc, event);
+}
+
+static __initconst struct x86_pmu core_pmu = {
+ .name = "core",
+ .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,
+ .eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
+ .perfctr = MSR_ARCH_PERFMON_PERFCTR0,
+ .event_map = intel_pmu_event_map,
+ .raw_event = intel_pmu_raw_event,
+ .max_events = ARRAY_SIZE(intel_perfmon_event_map),
+ .apic = 1,
+ /*
+ * Intel PMCs cannot be accessed sanely above 32 bit width,
+ * so we install an artificial 1<<31 period regardless of
+ * the generic event period:
+ */
+ .max_period = (1ULL << 31) - 1,
+ .get_event_constraints = intel_get_event_constraints,
+ .event_constraints = intel_core_event_constraints,
+};
+
+static __initconst struct x86_pmu intel_pmu = {
+ .name = "Intel",
+ .handle_irq = intel_pmu_handle_irq,
+ .disable_all = intel_pmu_disable_all,
+ .enable_all = intel_pmu_enable_all,
+ .enable = intel_pmu_enable_event,
+ .disable = intel_pmu_disable_event,
+ .eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
+ .perfctr = MSR_ARCH_PERFMON_PERFCTR0,
+ .event_map = intel_pmu_event_map,
+ .raw_event = intel_pmu_raw_event,
+ .max_events = ARRAY_SIZE(intel_perfmon_event_map),
+ .apic = 1,
+ /*
+ * Intel PMCs cannot be accessed sanely above 32 bit width,
+ * so we install an artificial 1<<31 period regardless of
+ * the generic event period:
+ */
+ .max_period = (1ULL << 31) - 1,
+ .enable_bts = intel_pmu_enable_bts,
+ .disable_bts = intel_pmu_disable_bts,
+ .get_event_constraints = intel_get_event_constraints
+};
+
+static __init int intel_pmu_init(void)
+{
+ union cpuid10_edx edx;
+ union cpuid10_eax eax;
+ unsigned int unused;
+ unsigned int ebx;
+ int version;
+
+ if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+ /* check for P6 processor family */
+ if (boot_cpu_data.x86 == 6) {
+ return p6_pmu_init();
+ } else {
+ return -ENODEV;
+ }
+ }
+
+ /*
+ * Check whether the Architectural PerfMon supports
+ * Branch Misses Retired hw_event or not.
+ */
+ cpuid(10, &eax.full, &ebx, &unused, &edx.full);
+ if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
+ return -ENODEV;
+
+ version = eax.split.version_id;
+ if (version < 2)
+ x86_pmu = core_pmu;
+ else
+ x86_pmu = intel_pmu;
+
+ x86_pmu.version = version;
+ x86_pmu.num_events = eax.split.num_events;
+ x86_pmu.event_bits = eax.split.bit_width;
+ x86_pmu.event_mask = (1ULL << eax.split.bit_width) - 1;
+
+ /*
+ * Quirk: v2 perfmon does not report fixed-purpose events, so
+ * assume at least 3 events:
+ */
+ if (version > 1)
+ x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3);
+
+ /*
+ * Install the hw-cache-events table:
+ */
+ switch (boot_cpu_data.x86_model) {
+ case 14: /* 65 nm core solo/duo, "Yonah" */
+ pr_cont("Core events, ");
+ break;
+
+ case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+ case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
+ case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
+ case 29: /* six-core 45 nm xeon "Dunnington" */
+ memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ x86_pmu.event_constraints = intel_core2_event_constraints;
+ pr_cont("Core2 events, ");
+ break;
+
+ case 26: /* 45 nm nehalem, "Bloomfield" */
+ case 30: /* 45 nm nehalem, "Lynnfield" */
+ memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ x86_pmu.event_constraints = intel_nehalem_event_constraints;
+ pr_cont("Nehalem/Corei7 events, ");
+ break;
+ case 28:
+ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ x86_pmu.event_constraints = intel_gen_event_constraints;
+ pr_cont("Atom events, ");
+ break;
+
+ case 37: /* 32 nm nehalem, "Clarkdale" */
+ case 44: /* 32 nm nehalem, "Gulftown" */
+ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ x86_pmu.event_constraints = intel_westmere_event_constraints;
+ pr_cont("Westmere events, ");
+ break;
+ default:
+ /*
+ * default constraints for v2 and up
+ */
+ x86_pmu.event_constraints = intel_gen_event_constraints;
+ pr_cont("generic architected perfmon, ");
+ }
+ return 0;
+}
+
+#else /* CONFIG_CPU_SUP_INTEL */
+
+static int intel_pmu_init(void)
+{
+ return 0;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
new file mode 100644
index 00000000000..1ca5ba078af
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -0,0 +1,157 @@
+#ifdef CONFIG_CPU_SUP_INTEL
+
+/*
+ * Not sure about some of these
+ */
+static const u64 p6_perfmon_event_map[] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0079,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x012e,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
+ [PERF_COUNT_HW_BUS_CYCLES] = 0x0062,
+};
+
+static u64 p6_pmu_event_map(int hw_event)
+{
+ return p6_perfmon_event_map[hw_event];
+}
+
+/*
+ * Event setting that is specified not to count anything.
+ * We use this to effectively disable a counter.
+ *
+ * L2_RQSTS with 0 MESI unit mask.
+ */
+#define P6_NOP_EVENT 0x0000002EULL
+
+static u64 p6_pmu_raw_event(u64 hw_event)
+{
+#define P6_EVNTSEL_EVENT_MASK 0x000000FFULL
+#define P6_EVNTSEL_UNIT_MASK 0x0000FF00ULL
+#define P6_EVNTSEL_EDGE_MASK 0x00040000ULL
+#define P6_EVNTSEL_INV_MASK 0x00800000ULL
+#define P6_EVNTSEL_REG_MASK 0xFF000000ULL
+
+#define P6_EVNTSEL_MASK \
+ (P6_EVNTSEL_EVENT_MASK | \
+ P6_EVNTSEL_UNIT_MASK | \
+ P6_EVNTSEL_EDGE_MASK | \
+ P6_EVNTSEL_INV_MASK | \
+ P6_EVNTSEL_REG_MASK)
+
+ return hw_event & P6_EVNTSEL_MASK;
+}
+
+static struct event_constraint p6_event_constraints[] =
+{
+ INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */
+ INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
+ INTEL_EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */
+ INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
+ INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
+ INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
+ EVENT_CONSTRAINT_END
+};
+
+static void p6_pmu_disable_all(void)
+{
+ u64 val;
+
+ /* p6 only has one enable register */
+ rdmsrl(MSR_P6_EVNTSEL0, val);
+ val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+ wrmsrl(MSR_P6_EVNTSEL0, val);
+}
+
+static void p6_pmu_enable_all(void)
+{
+ unsigned long val;
+
+ /* p6 only has one enable register */
+ rdmsrl(MSR_P6_EVNTSEL0, val);
+ val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ wrmsrl(MSR_P6_EVNTSEL0, val);
+}
+
+static inline void
+p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ u64 val = P6_NOP_EVENT;
+
+ if (cpuc->enabled)
+ val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+
+ (void)checking_wrmsrl(hwc->config_base + idx, val);
+}
+
+static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ u64 val;
+
+ val = hwc->config;
+ if (cpuc->enabled)
+ val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+
+ (void)checking_wrmsrl(hwc->config_base + idx, val);
+}
+
+static __initconst struct x86_pmu p6_pmu = {
+ .name = "p6",
+ .handle_irq = x86_pmu_handle_irq,
+ .disable_all = p6_pmu_disable_all,
+ .enable_all = p6_pmu_enable_all,
+ .enable = p6_pmu_enable_event,
+ .disable = p6_pmu_disable_event,
+ .eventsel = MSR_P6_EVNTSEL0,
+ .perfctr = MSR_P6_PERFCTR0,
+ .event_map = p6_pmu_event_map,
+ .raw_event = p6_pmu_raw_event,
+ .max_events = ARRAY_SIZE(p6_perfmon_event_map),
+ .apic = 1,
+ .max_period = (1ULL << 31) - 1,
+ .version = 0,
+ .num_events = 2,
+ /*
+ * Events have 40 bits implemented. However they are designed such
+ * that bits [32-39] are sign extensions of bit 31. As such the
+ * effective width of a event for P6-like PMU is 32 bits only.
+ *
+ * See IA-32 Intel Architecture Software developer manual Vol 3B
+ */
+ .event_bits = 32,
+ .event_mask = (1ULL << 32) - 1,
+ .get_event_constraints = x86_get_event_constraints,
+ .event_constraints = p6_event_constraints,
+};
+
+static __init int p6_pmu_init(void)
+{
+ switch (boot_cpu_data.x86_model) {
+ case 1:
+ case 3: /* Pentium Pro */
+ case 5:
+ case 6: /* Pentium II */
+ case 7:
+ case 8:
+ case 11: /* Pentium III */
+ case 9:
+ case 13:
+ /* Pentium M */
+ break;
+ default:
+ pr_cont("unsupported p6 CPU model %d ",
+ boot_cpu_data.x86_model);
+ return -ENODEV;
+ }
+
+ x86_pmu = p6_pmu;
+
+ return 0;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 898df9719af..74f4e85a572 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -115,17 +115,6 @@ int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
return !test_bit(counter, perfctr_nmi_owner);
}
-
-/* checks the an msr for availability */
-int avail_to_resrv_perfctr_nmi(unsigned int msr)
-{
- unsigned int counter;
-
- counter = nmi_perfctr_msr_to_bit(msr);
- BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
- return !test_bit(counter, perfctr_nmi_owner);
-}
EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
int reserve_perfctr_nmi(unsigned int msr)
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index ae775ca47b2..11540a189d9 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -18,11 +18,6 @@
#include "dumpstack.h"
-/* Just a stub for now */
-int x86_is_stack_id(int id, char *name)
-{
- return 0;
-}
void dump_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp,
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 0ad9597073f..dce99abb449 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -33,11 +33,6 @@ static char x86_stack_ids[][8] = {
#endif
};
-int x86_is_stack_id(int id, char *name)
-{
- return x86_stack_ids[id - 1] == name;
-}
-
static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
unsigned *usedp, char **idp)
{
@@ -291,6 +286,7 @@ void show_registers(struct pt_regs *regs)
sp = regs->sp;
printk("CPU %d ", cpu);
+ print_modules();
__show_regs(regs, 1);
printk("Process %s (pid: %d, threadinfo %p, task %p)\n",
cur->comm, cur->pid, task_thread_info(cur), cur);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 30968924543..cd37469b54e 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -30,14 +30,32 @@
#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * modifying_code is set to notify NMIs that they need to use
+ * memory barriers when entering or exiting. But we don't want
+ * to burden NMIs with unnecessary memory barriers when code
+ * modification is not being done (which is most of the time).
+ *
+ * A mutex is already held when ftrace_arch_code_modify_prepare
+ * and post_process are called. No locks need to be taken here.
+ *
+ * Stop machine will make sure currently running NMIs are done
+ * and new NMIs will see the updated variable before we need
+ * to worry about NMIs doing memory barriers.
+ */
+static int modifying_code __read_mostly;
+static DEFINE_PER_CPU(int, save_modifying_code);
+
int ftrace_arch_code_modify_prepare(void)
{
set_kernel_text_rw();
+ modifying_code = 1;
return 0;
}
int ftrace_arch_code_modify_post_process(void)
{
+ modifying_code = 0;
set_kernel_text_ro();
return 0;
}
@@ -149,6 +167,11 @@ static void ftrace_mod_code(void)
void ftrace_nmi_enter(void)
{
+ __get_cpu_var(save_modifying_code) = modifying_code;
+
+ if (!__get_cpu_var(save_modifying_code))
+ return;
+
if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
smp_rmb();
ftrace_mod_code();
@@ -160,6 +183,9 @@ void ftrace_nmi_enter(void)
void ftrace_nmi_exit(void)
{
+ if (!__get_cpu_var(save_modifying_code))
+ return;
+
/* Finish all executions before clearing nmi_running */
smp_mb();
atomic_dec(&nmi_running);
@@ -484,13 +510,3 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
}
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_FTRACE_SYSCALLS
-
-extern unsigned long *sys_call_table;
-
-unsigned long __init arch_syscall_addr(int nr)
-{
- return (unsigned long)(&sys_call_table)[nr];
-}
-#endif
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 05d5fec64a9..dca2802c666 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -212,25 +212,6 @@ static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
}
-/*
- * Store a breakpoint's encoded address, length, and type.
- */
-static int arch_store_info(struct perf_event *bp)
-{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
- /*
- * For kernel-addresses, either the address or symbol name can be
- * specified.
- */
- if (info->name)
- info->address = (unsigned long)
- kallsyms_lookup_name(info->name);
- if (info->address)
- return 0;
-
- return -EINVAL;
-}
-
int arch_bp_generic_fields(int x86_len, int x86_type,
int *gen_len, int *gen_type)
{
@@ -362,10 +343,13 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
return ret;
}
- ret = arch_store_info(bp);
-
- if (ret < 0)
- return ret;
+ /*
+ * For kernel-addresses, either the address or symbol name can be
+ * specified.
+ */
+ if (info->name)
+ info->address = (unsigned long)
+ kallsyms_lookup_name(info->name);
/*
* Check that the low-order bits of the address are appropriate
* for the alignment implied by len.
@@ -502,8 +486,6 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
rcu_read_lock();
bp = per_cpu(bp_per_reg[i], cpu);
- if (bp)
- rc = NOTIFY_DONE;
/*
* Reset the 'i'th TRAP bit in dr6 to denote completion of
* exception handling
@@ -522,7 +504,13 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
rcu_read_unlock();
}
- if (dr6 & (~DR_TRAP_BITS))
+ /*
+ * Further processing in do_debug() is needed for a) user-space
+ * breakpoints (to generate signals) and b) when the system has
+ * taken exception due to multiple causes
+ */
+ if ((current->thread.debugreg6 & DR_TRAP_BITS) ||
+ (dr6 & (~DR_TRAP_BITS)))
rc = NOTIFY_DONE;
set_debugreg(dr7, 7);
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 5b8c7505b3b..5de9f4a9c3f 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -337,6 +337,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
+ if (alternatives_text_reserved(p->addr, p->addr))
+ return -EINVAL;
+
if (!can_probe((unsigned long)p->addr))
return -EILSEQ;
/* insn: must be on special executable page on x86. */
@@ -429,7 +432,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
-#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER)
+#if !defined(CONFIG_PREEMPT)
if (p->ainsn.boostable == 1 && !p->post_handler) {
/* Boost up -- we can execute copied instructions directly */
reset_current_kprobe();
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 40b54ceb68b..a2c1edd2d3a 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -359,13 +359,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
x86_init.mpparse.mpc_record(1);
}
-#ifdef CONFIG_X86_BIGSMP
- generic_bigsmp_probe();
-#endif
-
- if (apic->setup_apic_routing)
- apic->setup_apic_routing();
-
if (!num_processors)
printk(KERN_ERR "MPTABLE: no processors registered!\n");
return num_processors;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 41a26a82470..126f0b493d0 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -527,6 +527,7 @@ void set_personality_ia32(void)
/* Make sure to be in 32bit mode */
set_thread_flag(TIF_IA32);
+ current->personality |= force_personality32;
/* Prepare the first "return" to user space */
current_thread_info()->status |= TS_COMPAT;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 017d937639f..d03146f71b2 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -140,30 +140,6 @@ static const int arg_offs_table[] = {
#endif
};
-/**
- * regs_get_argument_nth() - get Nth argument at function call
- * @regs: pt_regs which contains registers at function entry.
- * @n: argument number.
- *
- * regs_get_argument_nth() returns @n th argument of a function call.
- * Since usually the kernel stack will be changed right after function entry,
- * you must use this at function entry. If the @n th entry is NOT in the
- * kernel stack or pt_regs, this returns 0.
- */
-unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n)
-{
- if (n < ARRAY_SIZE(arg_offs_table))
- return *(unsigned long *)((char *)regs + arg_offs_table[n]);
- else {
- /*
- * The typical case: arg n is on the stack.
- * (Note: stack[0] = return address, so skip it)
- */
- n -= ARRAY_SIZE(arg_offs_table);
- return regs_get_kernel_stack_nth(regs, 1 + n);
- }
-}
-
/*
* does not yet catch signals sent when the child dies.
* in exit.c or in signal.c.
@@ -702,7 +678,7 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
} else if (n == 6) {
val = thread->debugreg6;
} else if (n == 7) {
- val = ptrace_get_dr7(thread->ptrace_bps);
+ val = thread->ptrace_dr7;
}
return val;
}
@@ -778,8 +754,11 @@ int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val)
return rc;
}
/* All that's left is DR7 */
- if (n == 7)
+ if (n == 7) {
rc = ptrace_write_dr7(tsk, val);
+ if (!rc)
+ thread->ptrace_dr7 = val;
+ }
ret_path:
return rc;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 678d0b8c26f..b4e870cbdc6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1083,9 +1083,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
set_cpu_sibling_map(0);
enable_IR_x2apic();
-#ifdef CONFIG_X86_64
default_setup_apic_routing();
-#endif
if (smp_sanity_check(max_cpus) < 0) {
printk(KERN_INFO "SMP disabled\n");
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 33399176512..1168e445418 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -534,6 +534,9 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
get_debugreg(dr6, 6);
+ /* Filter out all the reserved bits which are preset to 1 */
+ dr6 &= ~DR6_RESERVED;
+
/* Catch kmemcheck conditions first of all! */
if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
return;
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 296aba49472..15578f180e5 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -467,6 +467,9 @@ static int pit_ioport_read(struct kvm_io_device *this,
return -EOPNOTSUPP;
addr &= KVM_PIT_CHANNEL_MASK;
+ if (addr == 3)
+ return 0;
+
s = &pit_state->channels[addr];
mutex_lock(&pit_state->lock);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1ddcad452ad..a1e1bc9d412 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -670,7 +670,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
{
static int version;
struct pvclock_wall_clock wc;
- struct timespec now, sys, boot;
+ struct timespec boot;
if (!wall_clock)
return;
@@ -685,9 +685,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
* wall clock specified here. guest system time equals host
* system time for us, thus we must fill in host boot time here.
*/
- now = current_kernel_time();
- ktime_get_ts(&sys);
- boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys));
+ getboottime(&boot);
wc.sec = boot.tv_sec;
wc.nsec = boot.tv_nsec;
@@ -762,6 +760,7 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
local_irq_save(flags);
kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp);
ktime_get_ts(&ts);
+ monotonic_to_bootbased(&ts);
local_irq_restore(flags);
/* With all the info we got, fill in the values */
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 71da1bca13c..738e6593799 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -18,7 +18,7 @@ static inline pte_t gup_get_pte(pte_t *ptep)
#else
/*
* With get_user_pages_fast, we walk down the pagetables without taking
- * any locks. For this we would like to load the pointers atoimcally,
+ * any locks. For this we would like to load the pointers atomically,
* but that is not possible (without expensive cmpxchg8b) on PAE. What
* we do have is the guarantee that a pte will only either go from not
* present to present, or present to not present or both -- it will not
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index 8cc18334414..b3b531a4f8e 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -337,7 +337,7 @@ bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size)
if (!shadow)
return true;
- status = kmemcheck_shadow_test(shadow, size);
+ status = kmemcheck_shadow_test_all(shadow, size);
return status == KMEMCHECK_SHADOW_INITIALIZED;
}
diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c
index 3f66b82076a..aec124214d9 100644
--- a/arch/x86/mm/kmemcheck/shadow.c
+++ b/arch/x86/mm/kmemcheck/shadow.c
@@ -125,12 +125,12 @@ void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n)
enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size)
{
+#ifdef CONFIG_KMEMCHECK_PARTIAL_OK
uint8_t *x;
unsigned int i;
x = shadow;
-#ifdef CONFIG_KMEMCHECK_PARTIAL_OK
/*
* Make sure _some_ bytes are initialized. Gcc frequently generates
* code to access neighboring bytes.
@@ -139,13 +139,25 @@ enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size)
if (x[i] == KMEMCHECK_SHADOW_INITIALIZED)
return x[i];
}
+
+ return x[0];
#else
+ return kmemcheck_shadow_test_all(shadow, size);
+#endif
+}
+
+enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, unsigned int size)
+{
+ uint8_t *x;
+ unsigned int i;
+
+ x = shadow;
+
/* All bytes must be initialized. */
for (i = 0; i < size; ++i) {
if (x[i] != KMEMCHECK_SHADOW_INITIALIZED)
return x[i];
}
-#endif
return x[0];
}
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
index af46d9ab9d8..ff0b2f70fbc 100644
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ b/arch/x86/mm/kmemcheck/shadow.h
@@ -11,6 +11,8 @@ enum kmemcheck_shadow {
void *kmemcheck_shadow_lookup(unsigned long address);
enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size);
+enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow,
+ unsigned int size);
void kmemcheck_shadow_set(void *shadow, unsigned int size);
#endif
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index c8191defc38..1dab5194fd9 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -71,7 +71,7 @@ static int mmap_is_legacy(void)
if (current->personality & ADDR_COMPAT_LAYOUT)
return 1;
- if (current->signal->rlim[RLIMIT_STACK].rlim_cur == RLIM_INFINITY)
+ if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
return 1;
return sysctl_legacy_va_layout;
@@ -96,7 +96,7 @@ static unsigned long mmap_rnd(void)
static unsigned long mmap_base(void)
{
- unsigned long gap = current->signal->rlim[RLIMIT_STACK].rlim_cur;
+ unsigned long gap = rlimit(RLIMIT_STACK);
if (gap < MIN_GAP)
gap = MIN_GAP;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 3347f696edc..2c505ee7101 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -159,7 +159,7 @@ static int nmi_setup_mux(void)
for_each_possible_cpu(i) {
per_cpu(cpu_msrs, i).multiplex =
- kmalloc(multiplex_size, GFP_KERNEL);
+ kzalloc(multiplex_size, GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).multiplex)
return 0;
}
@@ -179,7 +179,6 @@ static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs)
if (counter_config[i].enabled) {
multiplex[i].saved = -(u64)counter_config[i].count;
} else {
- multiplex[i].addr = 0;
multiplex[i].saved = 0;
}
}
@@ -189,25 +188,27 @@ static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs)
static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs)
{
+ struct op_msr *counters = msrs->counters;
struct op_msr *multiplex = msrs->multiplex;
int i;
for (i = 0; i < model->num_counters; ++i) {
int virt = op_x86_phys_to_virt(i);
- if (multiplex[virt].addr)
- rdmsrl(multiplex[virt].addr, multiplex[virt].saved);
+ if (counters[i].addr)
+ rdmsrl(counters[i].addr, multiplex[virt].saved);
}
}
static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs)
{
+ struct op_msr *counters = msrs->counters;
struct op_msr *multiplex = msrs->multiplex;
int i;
for (i = 0; i < model->num_counters; ++i) {
int virt = op_x86_phys_to_virt(i);
- if (multiplex[virt].addr)
- wrmsrl(multiplex[virt].addr, multiplex[virt].saved);
+ if (counters[i].addr)
+ wrmsrl(counters[i].addr, multiplex[virt].saved);
}
}
@@ -303,11 +304,11 @@ static int allocate_msrs(void)
int i;
for_each_possible_cpu(i) {
- per_cpu(cpu_msrs, i).counters = kmalloc(counters_size,
+ per_cpu(cpu_msrs, i).counters = kzalloc(counters_size,
GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).counters)
return 0;
- per_cpu(cpu_msrs, i).controls = kmalloc(controls_size,
+ per_cpu(cpu_msrs, i).controls = kzalloc(controls_size,
GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).controls)
return 0;
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 39686c29f03..6a58256dce9 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -22,6 +22,9 @@
#include <asm/ptrace.h>
#include <asm/msr.h>
#include <asm/nmi.h>
+#include <asm/apic.h>
+#include <asm/processor.h>
+#include <asm/cpufeature.h>
#include "op_x86_model.h"
#include "op_counter.h"
@@ -43,15 +46,13 @@
static unsigned long reset_value[NUM_VIRT_COUNTERS];
-#ifdef CONFIG_OPROFILE_IBS
-
/* IbsFetchCtl bits/masks */
#define IBS_FETCH_RAND_EN (1ULL<<57)
#define IBS_FETCH_VAL (1ULL<<49)
#define IBS_FETCH_ENABLE (1ULL<<48)
#define IBS_FETCH_CNT_MASK 0xFFFF0000ULL
-/*IbsOpCtl bits */
+/* IbsOpCtl bits */
#define IBS_OP_CNT_CTL (1ULL<<19)
#define IBS_OP_VAL (1ULL<<18)
#define IBS_OP_ENABLE (1ULL<<17)
@@ -59,7 +60,7 @@ static unsigned long reset_value[NUM_VIRT_COUNTERS];
#define IBS_FETCH_SIZE 6
#define IBS_OP_SIZE 12
-static int has_ibs; /* AMD Family10h and later */
+static u32 ibs_caps;
struct op_ibs_config {
unsigned long op_enabled;
@@ -71,24 +72,52 @@ struct op_ibs_config {
};
static struct op_ibs_config ibs_config;
+static u64 ibs_op_ctl;
-#endif
+/*
+ * IBS cpuid feature detection
+ */
-#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+#define IBS_CPUID_FEATURES 0x8000001b
+
+/*
+ * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
+ * bit 0 is used to indicate the existence of IBS.
+ */
+#define IBS_CAPS_AVAIL (1LL<<0)
+#define IBS_CAPS_RDWROPCNT (1LL<<3)
+#define IBS_CAPS_OPCNT (1LL<<4)
+
+/*
+ * IBS randomization macros
+ */
+#define IBS_RANDOM_BITS 12
+#define IBS_RANDOM_MASK ((1ULL << IBS_RANDOM_BITS) - 1)
+#define IBS_RANDOM_MAXCNT_OFFSET (1ULL << (IBS_RANDOM_BITS - 5))
-static void op_mux_fill_in_addresses(struct op_msrs * const msrs)
+static u32 get_ibs_caps(void)
{
- int i;
+ u32 ibs_caps;
+ unsigned int max_level;
- for (i = 0; i < NUM_VIRT_COUNTERS; i++) {
- int hw_counter = op_x86_virt_to_phys(i);
- if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
- msrs->multiplex[i].addr = MSR_K7_PERFCTR0 + hw_counter;
- else
- msrs->multiplex[i].addr = 0;
- }
+ if (!boot_cpu_has(X86_FEATURE_IBS))
+ return 0;
+
+ /* check IBS cpuid feature flags */
+ max_level = cpuid_eax(0x80000000);
+ if (max_level < IBS_CPUID_FEATURES)
+ return IBS_CAPS_AVAIL;
+
+ ibs_caps = cpuid_eax(IBS_CPUID_FEATURES);
+ if (!(ibs_caps & IBS_CAPS_AVAIL))
+ /* cpuid flags not valid */
+ return IBS_CAPS_AVAIL;
+
+ return ibs_caps;
}
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+
static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
struct op_msrs const * const msrs)
{
@@ -98,7 +127,7 @@ static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
/* enable active counters */
for (i = 0; i < NUM_COUNTERS; ++i) {
int virt = op_x86_phys_to_virt(i);
- if (!counter_config[virt].enabled)
+ if (!reset_value[virt])
continue;
rdmsrl(msrs->controls[i].addr, val);
val &= model->reserved;
@@ -107,10 +136,6 @@ static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
}
}
-#else
-
-static inline void op_mux_fill_in_addresses(struct op_msrs * const msrs) { }
-
#endif
/* functions for op_amd_spec */
@@ -122,18 +147,12 @@ static void op_amd_fill_in_addresses(struct op_msrs * const msrs)
for (i = 0; i < NUM_COUNTERS; i++) {
if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
- else
- msrs->counters[i].addr = 0;
}
for (i = 0; i < NUM_CONTROLS; i++) {
if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i))
msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
- else
- msrs->controls[i].addr = 0;
}
-
- op_mux_fill_in_addresses(msrs);
}
static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
@@ -144,7 +163,8 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
/* setup reset_value */
for (i = 0; i < NUM_VIRT_COUNTERS; ++i) {
- if (counter_config[i].enabled)
+ if (counter_config[i].enabled
+ && msrs->counters[op_x86_virt_to_phys(i)].addr)
reset_value[i] = counter_config[i].count;
else
reset_value[i] = 0;
@@ -152,9 +172,18 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
/* clear all counters */
for (i = 0; i < NUM_CONTROLS; ++i) {
- if (unlikely(!msrs->controls[i].addr))
+ if (unlikely(!msrs->controls[i].addr)) {
+ if (counter_config[i].enabled && !smp_processor_id())
+ /*
+ * counter is reserved, this is on all
+ * cpus, so report only for cpu #0
+ */
+ op_x86_warn_reserved(i);
continue;
+ }
rdmsrl(msrs->controls[i].addr, val);
+ if (val & ARCH_PERFMON_EVENTSEL0_ENABLE)
+ op_x86_warn_in_use(i);
val &= model->reserved;
wrmsrl(msrs->controls[i].addr, val);
}
@@ -169,9 +198,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
/* enable active counters */
for (i = 0; i < NUM_COUNTERS; ++i) {
int virt = op_x86_phys_to_virt(i);
- if (!counter_config[virt].enabled)
- continue;
- if (!msrs->counters[i].addr)
+ if (!reset_value[virt])
continue;
/* setup counter registers */
@@ -185,7 +212,60 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
}
}
-#ifdef CONFIG_OPROFILE_IBS
+/*
+ * 16-bit Linear Feedback Shift Register (LFSR)
+ *
+ * 16 14 13 11
+ * Feedback polynomial = X + X + X + X + 1
+ */
+static unsigned int lfsr_random(void)
+{
+ static unsigned int lfsr_value = 0xF00D;
+ unsigned int bit;
+
+ /* Compute next bit to shift in */
+ bit = ((lfsr_value >> 0) ^
+ (lfsr_value >> 2) ^
+ (lfsr_value >> 3) ^
+ (lfsr_value >> 5)) & 0x0001;
+
+ /* Advance to next register value */
+ lfsr_value = (lfsr_value >> 1) | (bit << 15);
+
+ return lfsr_value;
+}
+
+/*
+ * IBS software randomization
+ *
+ * The IBS periodic op counter is randomized in software. The lower 12
+ * bits of the 20 bit counter are randomized. IbsOpCurCnt is
+ * initialized with a 12 bit random value.
+ */
+static inline u64 op_amd_randomize_ibs_op(u64 val)
+{
+ unsigned int random = lfsr_random();
+
+ if (!(ibs_caps & IBS_CAPS_RDWROPCNT))
+ /*
+ * Work around if the hw can not write to IbsOpCurCnt
+ *
+ * Randomize the lower 8 bits of the 16 bit
+ * IbsOpMaxCnt [15:0] value in the range of -128 to
+ * +127 by adding/subtracting an offset to the
+ * maximum count (IbsOpMaxCnt).
+ *
+ * To avoid over or underflows and protect upper bits
+ * starting at bit 16, the initial value for
+ * IbsOpMaxCnt must fit in the range from 0x0081 to
+ * 0xff80.
+ */
+ val += (s8)(random >> 4);
+ else
+ val |= (u64)(random & IBS_RANDOM_MASK) << 32;
+
+ return val;
+}
static inline void
op_amd_handle_ibs(struct pt_regs * const regs,
@@ -194,7 +274,7 @@ op_amd_handle_ibs(struct pt_regs * const regs,
u64 val, ctl;
struct op_entry entry;
- if (!has_ibs)
+ if (!ibs_caps)
return;
if (ibs_config.fetch_enabled) {
@@ -236,8 +316,7 @@ op_amd_handle_ibs(struct pt_regs * const regs,
oprofile_write_commit(&entry);
/* reenable the IRQ */
- ctl &= ~IBS_OP_VAL & 0xFFFFFFFF;
- ctl |= IBS_OP_ENABLE;
+ ctl = op_amd_randomize_ibs_op(ibs_op_ctl);
wrmsrl(MSR_AMD64_IBSOPCTL, ctl);
}
}
@@ -246,41 +325,57 @@ op_amd_handle_ibs(struct pt_regs * const regs,
static inline void op_amd_start_ibs(void)
{
u64 val;
- if (has_ibs && ibs_config.fetch_enabled) {
+
+ if (!ibs_caps)
+ return;
+
+ if (ibs_config.fetch_enabled) {
val = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0;
val |= IBS_FETCH_ENABLE;
wrmsrl(MSR_AMD64_IBSFETCHCTL, val);
}
- if (has_ibs && ibs_config.op_enabled) {
- val = (ibs_config.max_cnt_op >> 4) & 0xFFFF;
- val |= ibs_config.dispatched_ops ? IBS_OP_CNT_CTL : 0;
- val |= IBS_OP_ENABLE;
+ if (ibs_config.op_enabled) {
+ ibs_op_ctl = ibs_config.max_cnt_op >> 4;
+ if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) {
+ /*
+ * IbsOpCurCnt not supported. See
+ * op_amd_randomize_ibs_op() for details.
+ */
+ ibs_op_ctl = clamp(ibs_op_ctl, 0x0081ULL, 0xFF80ULL);
+ } else {
+ /*
+ * The start value is randomized with a
+ * positive offset, we need to compensate it
+ * with the half of the randomized range. Also
+ * avoid underflows.
+ */
+ ibs_op_ctl = min(ibs_op_ctl + IBS_RANDOM_MAXCNT_OFFSET,
+ 0xFFFFULL);
+ }
+ if (ibs_caps & IBS_CAPS_OPCNT && ibs_config.dispatched_ops)
+ ibs_op_ctl |= IBS_OP_CNT_CTL;
+ ibs_op_ctl |= IBS_OP_ENABLE;
+ val = op_amd_randomize_ibs_op(ibs_op_ctl);
wrmsrl(MSR_AMD64_IBSOPCTL, val);
}
}
static void op_amd_stop_ibs(void)
{
- if (has_ibs && ibs_config.fetch_enabled)
+ if (!ibs_caps)
+ return;
+
+ if (ibs_config.fetch_enabled)
/* clear max count and enable */
wrmsrl(MSR_AMD64_IBSFETCHCTL, 0);
- if (has_ibs && ibs_config.op_enabled)
+ if (ibs_config.op_enabled)
/* clear max count and enable */
wrmsrl(MSR_AMD64_IBSOPCTL, 0);
}
-#else
-
-static inline void op_amd_handle_ibs(struct pt_regs * const regs,
- struct op_msrs const * const msrs) { }
-static inline void op_amd_start_ibs(void) { }
-static inline void op_amd_stop_ibs(void) { }
-
-#endif
-
static int op_amd_check_ctrs(struct pt_regs * const regs,
struct op_msrs const * const msrs)
{
@@ -355,8 +450,6 @@ static void op_amd_shutdown(struct op_msrs const * const msrs)
}
}
-#ifdef CONFIG_OPROFILE_IBS
-
static u8 ibs_eilvt_off;
static inline void apic_init_ibs_nmi_per_cpu(void *arg)
@@ -405,45 +498,36 @@ static int init_ibs_nmi(void)
return 1;
}
-#ifdef CONFIG_NUMA
- /* Sanity check */
- /* Works only for 64bit with proper numa implementation. */
- if (nodes != num_possible_nodes()) {
- printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, "
- "found: %d, expected %d",
- nodes, num_possible_nodes());
- return 1;
- }
-#endif
return 0;
}
/* uninitialize the APIC for the IBS interrupts if needed */
static void clear_ibs_nmi(void)
{
- if (has_ibs)
+ if (ibs_caps)
on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
}
/* initialize the APIC for the IBS interrupts if available */
static void ibs_init(void)
{
- has_ibs = boot_cpu_has(X86_FEATURE_IBS);
+ ibs_caps = get_ibs_caps();
- if (!has_ibs)
+ if (!ibs_caps)
return;
if (init_ibs_nmi()) {
- has_ibs = 0;
+ ibs_caps = 0;
return;
}
- printk(KERN_INFO "oprofile: AMD IBS detected\n");
+ printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n",
+ (unsigned)ibs_caps);
}
static void ibs_exit(void)
{
- if (!has_ibs)
+ if (!ibs_caps)
return;
clear_ibs_nmi();
@@ -463,7 +547,7 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
if (ret)
return ret;
- if (!has_ibs)
+ if (!ibs_caps)
return ret;
/* model specific files */
@@ -473,7 +557,7 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
ibs_config.fetch_enabled = 0;
ibs_config.max_cnt_op = 250000;
ibs_config.op_enabled = 0;
- ibs_config.dispatched_ops = 1;
+ ibs_config.dispatched_ops = 0;
dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
oprofilefs_create_ulong(sb, dir, "enable",
@@ -488,8 +572,9 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
&ibs_config.op_enabled);
oprofilefs_create_ulong(sb, dir, "max_count",
&ibs_config.max_cnt_op);
- oprofilefs_create_ulong(sb, dir, "dispatched_ops",
- &ibs_config.dispatched_ops);
+ if (ibs_caps & IBS_CAPS_OPCNT)
+ oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+ &ibs_config.dispatched_ops);
return 0;
}
@@ -507,19 +592,6 @@ static void op_amd_exit(void)
ibs_exit();
}
-#else
-
-/* no IBS support */
-
-static int op_amd_init(struct oprofile_operations *ops)
-{
- return 0;
-}
-
-static void op_amd_exit(void) {}
-
-#endif /* CONFIG_OPROFILE_IBS */
-
struct op_x86_model_spec op_amd_spec = {
.num_counters = NUM_COUNTERS,
.num_controls = NUM_CONTROLS,
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index ac6b354becd..e6a160a4684 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -394,12 +394,6 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs)
setup_num_counters();
stag = get_stagger();
- /* initialize some registers */
- for (i = 0; i < num_counters; ++i)
- msrs->counters[i].addr = 0;
- for (i = 0; i < num_controls; ++i)
- msrs->controls[i].addr = 0;
-
/* the counter & cccr registers we pay attention to */
for (i = 0; i < num_counters; ++i) {
addr = p4_counters[VIRT_CTR(stag, i)].counter_address;
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 8eb05878554..5d1727ba409 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -37,15 +37,11 @@ static void ppro_fill_in_addresses(struct op_msrs * const msrs)
for (i = 0; i < num_counters; i++) {
if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
- else
- msrs->counters[i].addr = 0;
}
for (i = 0; i < num_counters; i++) {
if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i))
msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
- else
- msrs->controls[i].addr = 0;
}
}
@@ -57,7 +53,7 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
int i;
if (!reset_value) {
- reset_value = kmalloc(sizeof(reset_value[0]) * num_counters,
+ reset_value = kzalloc(sizeof(reset_value[0]) * num_counters,
GFP_ATOMIC);
if (!reset_value)
return;
@@ -82,9 +78,18 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
/* clear all counters */
for (i = 0; i < num_counters; ++i) {
- if (unlikely(!msrs->controls[i].addr))
+ if (unlikely(!msrs->controls[i].addr)) {
+ if (counter_config[i].enabled && !smp_processor_id())
+ /*
+ * counter is reserved, this is on all
+ * cpus, so report only for cpu #0
+ */
+ op_x86_warn_reserved(i);
continue;
+ }
rdmsrl(msrs->controls[i].addr, val);
+ if (val & ARCH_PERFMON_EVENTSEL0_ENABLE)
+ op_x86_warn_in_use(i);
val &= model->reserved;
wrmsrl(msrs->controls[i].addr, val);
}
diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index 7b8e75d1608..ff82a755edd 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -57,6 +57,26 @@ struct op_x86_model_spec {
struct op_counter_config;
+static inline void op_x86_warn_in_use(int counter)
+{
+ /*
+ * The warning indicates an already running counter. If
+ * oprofile doesn't collect data, then try using a different
+ * performance counter on your platform to monitor the desired
+ * event. Delete counter #%d from the desired event by editing
+ * the /usr/share/oprofile/%s/<cpu>/events file. If the event
+ * cannot be monitored by any other counter, contact your
+ * hardware or BIOS vendor.
+ */
+ pr_warning("oprofile: counter #%d on cpu #%d may already be used\n",
+ counter, smp_processor_id());
+}
+
+static inline void op_x86_warn_reserved(int counter)
+{
+ pr_warning("oprofile: counter #%d is already reserved\n", counter);
+}
+
extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
struct op_counter_config *counter_config);
extern int op_x86_phys_to_virt(int phys);
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 959e548a703..5f11ff6f538 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -15,6 +15,51 @@ struct pci_root_info {
int busnum;
};
+static bool pci_use_crs = true;
+
+static int __init set_use_crs(const struct dmi_system_id *id)
+{
+ pci_use_crs = true;
+ return 0;
+}
+
+static const struct dmi_system_id pci_use_crs_table[] __initconst = {
+ /* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */
+ {
+ .callback = set_use_crs,
+ .ident = "IBM System x3800",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "x3800"),
+ },
+ },
+ {}
+};
+
+void __init pci_acpi_crs_quirks(void)
+{
+ int year;
+
+ if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
+ pci_use_crs = false;
+
+ dmi_check_system(pci_use_crs_table);
+
+ /*
+ * If the user specifies "pci=use_crs" or "pci=nocrs" explicitly, that
+ * takes precedence over anything we figured out above.
+ */
+ if (pci_probe & PCI_ROOT_NO_CRS)
+ pci_use_crs = false;
+ else if (pci_probe & PCI_USE__CRS)
+ pci_use_crs = true;
+
+ printk(KERN_INFO "PCI: %s host bridge windows from ACPI; "
+ "if necessary, use \"pci=%s\" and report a bug\n",
+ pci_use_crs ? "Using" : "Ignoring",
+ pci_use_crs ? "nocrs" : "use_crs");
+}
+
static acpi_status
resource_to_addr(struct acpi_resource *resource,
struct acpi_resource_address64 *addr)
@@ -45,20 +90,6 @@ count_resource(struct acpi_resource *acpi_res, void *data)
return AE_OK;
}
-static int
-bus_has_transparent_bridge(struct pci_bus *bus)
-{
- struct pci_dev *dev;
-
- list_for_each_entry(dev, &bus->devices, bus_list) {
- u16 class = dev->class >> 8;
-
- if (class == PCI_CLASS_BRIDGE_PCI && dev->transparent)
- return true;
- }
- return false;
-}
-
static void
align_resource(struct acpi_device *bridge, struct resource *res)
{
@@ -92,12 +123,8 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
acpi_status status;
unsigned long flags;
struct resource *root;
- int max_root_bus_resources = PCI_BUS_NUM_RESOURCES;
u64 start, end;
- if (bus_has_transparent_bridge(info->bus))
- max_root_bus_resources -= 3;
-
status = resource_to_addr(acpi_res, &addr);
if (!ACPI_SUCCESS(status))
return AE_OK;
@@ -115,15 +142,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
start = addr.minimum + addr.translation_offset;
end = start + addr.address_length - 1;
- if (info->res_num >= max_root_bus_resources) {
- if (pci_probe & PCI_USE__CRS)
- printk(KERN_WARNING "PCI: Failed to allocate "
- "0x%lx-0x%lx from %s for %s due to _CRS "
- "returning more than %d resource descriptors\n",
- (unsigned long) start, (unsigned long) end,
- root->name, info->name, max_root_bus_resources);
- return AE_OK;
- }
res = &info->res[info->res_num];
res->name = info->name;
@@ -133,7 +151,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
res->child = NULL;
align_resource(info->bridge, res);
- if (!(pci_probe & PCI_USE__CRS)) {
+ if (!pci_use_crs) {
dev_printk(KERN_DEBUG, &info->bridge->dev,
"host bridge window %pR (ignored)\n", res);
return AE_OK;
@@ -143,7 +161,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
dev_err(&info->bridge->dev,
"can't allocate host bridge window %pR\n", res);
} else {
- info->bus->resource[info->res_num] = res;
+ pci_bus_add_resource(info->bus, res, 0);
info->res_num++;
if (addr.translation_offset)
dev_info(&info->bridge->dev, "host bridge window %pR "
@@ -164,10 +182,8 @@ get_current_resources(struct acpi_device *device, int busnum,
struct pci_root_info info;
size_t size;
- if (!(pci_probe & PCI_USE__CRS))
- dev_info(&device->dev,
- "ignoring host bridge windows from ACPI; "
- "boot with \"pci=use_crs\" to use them\n");
+ if (pci_use_crs)
+ pci_bus_remove_resources(bus);
info.bridge = device;
info.bus = bus;
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index f939d603adf..12d54ff3654 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -36,13 +36,14 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n",
b->number);
+ pci_bus_remove_resources(b);
info = &pci_root_info[i];
for (j = 0; j < info->res_num; j++) {
struct resource *res;
struct resource *root;
res = &info->res[j];
- b->resource[j] = res;
+ pci_bus_add_resource(b, res, 0);
if (res->flags & IORESOURCE_IO)
root = &ioport_resource;
else
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
index adbc23fe82a..731b64ee8d8 100644
--- a/arch/x86/pci/bus_numa.h
+++ b/arch/x86/pci/bus_numa.h
@@ -2,8 +2,7 @@
/*
* sub bus (transparent) will use entres from 3 to store extra from
- * root, so need to make sure we have enough slot there, Should we
- * increase PCI_BUS_NUM_RESOURCES?
+ * root, so need to make sure we have enough slot there.
*/
#define RES_NUM 16
struct pci_root_info {
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index d2552c68e94..3736176acaa 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -520,6 +520,9 @@ char * __devinit pcibios_setup(char *str)
} else if (!strcmp(str, "use_crs")) {
pci_probe |= PCI_USE__CRS;
return NULL;
+ } else if (!strcmp(str, "nocrs")) {
+ pci_probe |= PCI_ROOT_NO_CRS;
+ return NULL;
} else if (!strcmp(str, "earlydump")) {
pci_early_dump_regs = 1;
return NULL;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 5dc9e8c63fc..5a8fbf8d4ca 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -60,22 +60,20 @@ skip_isa_ioresource_align(struct pci_dev *dev) {
* but we want to try to avoid allocating at 0x2900-0x2bff
* which might have be mirrored at 0x0100-0x03ff..
*/
-void
-pcibios_align_resource(void *data, struct resource *res,
+resource_size_t
+pcibios_align_resource(void *data, const struct resource *res,
resource_size_t size, resource_size_t align)
{
struct pci_dev *dev = data;
+ resource_size_t start = res->start;
if (res->flags & IORESOURCE_IO) {
- resource_size_t start = res->start;
-
if (skip_isa_ioresource_align(dev))
- return;
- if (start & 0x300) {
+ return start;
+ if (start & 0x300)
start = (start + 0x3ff) & ~0x3ff;
- res->start = start;
- }
}
+ return start;
}
EXPORT_SYMBOL(pcibios_align_resource);
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 0696d506c4a..b02f6d8ac92 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -590,6 +590,8 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route
case PCI_DEVICE_ID_INTEL_ICH10_1:
case PCI_DEVICE_ID_INTEL_ICH10_2:
case PCI_DEVICE_ID_INTEL_ICH10_3:
+ case PCI_DEVICE_ID_INTEL_CPT_LPC1:
+ case PCI_DEVICE_ID_INTEL_CPT_LPC2:
r->name = "PIIX/ICH";
r->get = pirq_piix_get;
r->set = pirq_piix_set;
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index b19d1e54201..8f3f9a50b1e 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -303,22 +303,17 @@ static void __init pci_mmcfg_check_end_bus_number(void)
{
struct pci_mmcfg_region *cfg, *cfgx;
- /* last one*/
- cfg = list_entry(pci_mmcfg_list.prev, typeof(*cfg), list);
- if (cfg)
- if (cfg->end_bus < cfg->start_bus)
- cfg->end_bus = 255;
-
- if (list_is_singular(&pci_mmcfg_list))
- return;
-
- /* don't overlap please */
+ /* Fixup overlaps */
list_for_each_entry(cfg, &pci_mmcfg_list, list) {
if (cfg->end_bus < cfg->start_bus)
cfg->end_bus = 255;
+ /* Don't access the list head ! */
+ if (cfg->list.next == &pci_mmcfg_list)
+ break;
+
cfgx = list_entry(cfg->list.next, typeof(*cfg), list);
- if (cfg != cfgx && cfg->end_bus >= cfgx->start_bus)
+ if (cfg->end_bus >= cfgx->start_bus)
cfg->end_bus = cfgx->start_bus - 1;
}
}