summaryrefslogtreecommitdiffstats
path: root/arch/x86/oprofile
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2011-10-26 17:03:38 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2011-10-26 17:03:38 +0200
commit7115e3fcf45514db7525a05365b10454ff7f345e (patch)
tree17450e6337d559cc35dae6a7a73abab01ac63f00 /arch/x86/oprofile
parent1f6e05171bb5cc32a4d6437ab2269fc21d169ca7 (diff)
parentc752d04066a36ae30b29795f3fa3f536292c1f8c (diff)
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (121 commits) perf symbols: Increase symbol KSYM_NAME_LEN size perf hists browser: Refuse 'a' hotkey on non symbolic views perf ui browser: Use libslang to read keys perf tools: Fix tracing info recording perf hists browser: Elide DSO column when it is set to just one DSO, ditto for threads perf hists: Don't consider filtered entries when calculating column widths perf hists: Don't decay total_period for filtered entries perf hists browser: Honour symbol_conf.show_{nr_samples,total_period} perf hists browser: Do not exit on tab key with single event perf annotate browser: Don't change selection line when returning from callq perf tools: handle endianness of feature bitmap perf tools: Add prelink suggestion to dso update message perf script: Fix unknown feature comment perf hists browser: Apply the dso and thread filters when merging new batches perf hists: Move the dso and thread filters from hist_browser perf ui browser: Honour the xterm colors perf top tui: Give color hints just on the percentage, like on --stdio perf ui browser: Make the colors configurable and change the defaults perf tui: Remove unneeded call to newtCls on startup perf hists: Don't format the percentage on hist_entry__snprintf ... Fix up conflicts in arch/x86/kernel/kprobes.c manually. Ingo's tree did the insane "add volatile to const array", which just doesn't make sense ("volatile const"?). But we could remove the const *and* make the array volatile to make doubly sure that gcc doesn't optimize it away.. Also fix up kernel/trace/ring_buffer.c non-data-conflicts manually: the reader_lock has been turned into a raw lock by the core locking merge, and there was a new user of it introduced in this perf core merge. Make sure that new use also uses the raw accessor functions.
Diffstat (limited to 'arch/x86/oprofile')
-rw-r--r--arch/x86/oprofile/nmi_int.c40
-rw-r--r--arch/x86/oprofile/nmi_timer_int.c28
-rw-r--r--arch/x86/oprofile/op_model_amd.c234
-rw-r--r--arch/x86/oprofile/op_model_ppro.c27
-rw-r--r--arch/x86/oprofile/op_x86_model.h1
5 files changed, 22 insertions, 308 deletions
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 96646b3aeca..75f9528e037 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -61,26 +61,15 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
}
-static int profile_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs)
{
- struct die_args *args = (struct die_args *)data;
- int ret = NOTIFY_DONE;
-
- switch (val) {
- case DIE_NMI:
- if (ctr_running)
- model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
- else if (!nmi_enabled)
- break;
- else
- model->stop(&__get_cpu_var(cpu_msrs));
- ret = NOTIFY_STOP;
- break;
- default:
- break;
- }
- return ret;
+ if (ctr_running)
+ model->check_ctrs(regs, &__get_cpu_var(cpu_msrs));
+ else if (!nmi_enabled)
+ return NMI_DONE;
+ else
+ model->stop(&__get_cpu_var(cpu_msrs));
+ return NMI_HANDLED;
}
static void nmi_cpu_save_registers(struct op_msrs *msrs)
@@ -363,12 +352,6 @@ static void nmi_cpu_setup(void *dummy)
apic_write(APIC_LVTPC, APIC_DM_NMI);
}
-static struct notifier_block profile_exceptions_nb = {
- .notifier_call = profile_exceptions_notify,
- .next = NULL,
- .priority = NMI_LOCAL_LOW_PRIOR,
-};
-
static void nmi_cpu_restore_registers(struct op_msrs *msrs)
{
struct op_msr *counters = msrs->counters;
@@ -402,8 +385,6 @@ static void nmi_cpu_shutdown(void *dummy)
apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu));
apic_write(APIC_LVTERR, v);
nmi_cpu_restore_registers(msrs);
- if (model->cpu_down)
- model->cpu_down();
}
static void nmi_cpu_up(void *dummy)
@@ -508,7 +489,8 @@ static int nmi_setup(void)
ctr_running = 0;
/* make variables visible to the nmi handler: */
smp_mb();
- err = register_die_notifier(&profile_exceptions_nb);
+ err = register_nmi_handler(NMI_LOCAL, profile_exceptions_notify,
+ 0, "oprofile");
if (err)
goto fail;
@@ -538,7 +520,7 @@ static void nmi_shutdown(void)
put_online_cpus();
/* make variables visible to the nmi handler: */
smp_mb();
- unregister_die_notifier(&profile_exceptions_nb);
+ unregister_nmi_handler(NMI_LOCAL, "oprofile");
msrs = &get_cpu_var(cpu_msrs);
model->shutdown(msrs);
free_msrs();
diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
index 720bf5a53c5..7f8052cd662 100644
--- a/arch/x86/oprofile/nmi_timer_int.c
+++ b/arch/x86/oprofile/nmi_timer_int.c
@@ -18,32 +18,16 @@
#include <asm/apic.h>
#include <asm/ptrace.h>
-static int profile_timer_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static int profile_timer_exceptions_notify(unsigned int val, struct pt_regs *regs)
{
- struct die_args *args = (struct die_args *)data;
- int ret = NOTIFY_DONE;
-
- switch (val) {
- case DIE_NMI:
- oprofile_add_sample(args->regs, 0);
- ret = NOTIFY_STOP;
- break;
- default:
- break;
- }
- return ret;
+ oprofile_add_sample(regs, 0);
+ return NMI_HANDLED;
}
-static struct notifier_block profile_timer_exceptions_nb = {
- .notifier_call = profile_timer_exceptions_notify,
- .next = NULL,
- .priority = NMI_LOW_PRIOR,
-};
-
static int timer_start(void)
{
- if (register_die_notifier(&profile_timer_exceptions_nb))
+ if (register_nmi_handler(NMI_LOCAL, profile_timer_exceptions_notify,
+ 0, "oprofile-timer"))
return 1;
return 0;
}
@@ -51,7 +35,7 @@ static int timer_start(void)
static void timer_stop(void)
{
- unregister_die_notifier(&profile_timer_exceptions_nb);
+ unregister_nmi_handler(NMI_LOCAL, "oprofile-timer");
synchronize_sched(); /* Allow already-started NMIs to complete. */
}
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 9cbb710dc94..303f0863782 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -29,8 +29,6 @@
#include "op_x86_model.h"
#include "op_counter.h"
-#define NUM_COUNTERS 4
-#define NUM_COUNTERS_F15H 6
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
#define NUM_VIRT_COUNTERS 32
#else
@@ -70,62 +68,12 @@ static struct ibs_config ibs_config;
static struct ibs_state ibs_state;
/*
- * IBS cpuid feature detection
- */
-
-#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 (1U<<0)
-#define IBS_CAPS_FETCHSAM (1U<<1)
-#define IBS_CAPS_OPSAM (1U<<2)
-#define IBS_CAPS_RDWROPCNT (1U<<3)
-#define IBS_CAPS_OPCNT (1U<<4)
-#define IBS_CAPS_BRNTRGT (1U<<5)
-#define IBS_CAPS_OPCNTEXT (1U<<6)
-
-#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \
- | IBS_CAPS_FETCHSAM \
- | IBS_CAPS_OPSAM)
-
-/*
- * IBS APIC setup
- */
-#define IBSCTL 0x1cc
-#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8)
-#define IBSCTL_LVT_OFFSET_MASK 0x0F
-
-/*
* 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 u32 get_ibs_caps(void)
-{
- u32 ibs_caps;
- unsigned int max_level;
-
- 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_DEFAULT;
-
- ibs_caps = cpuid_eax(IBS_CPUID_FEATURES);
- if (!(ibs_caps & IBS_CAPS_AVAIL))
- /* cpuid flags not valid */
- return IBS_CAPS_DEFAULT;
-
- return ibs_caps;
-}
-
/*
* 16-bit Linear Feedback Shift Register (LFSR)
*
@@ -316,81 +264,6 @@ static void op_amd_stop_ibs(void)
wrmsrl(MSR_AMD64_IBSOPCTL, 0);
}
-static inline int get_eilvt(int offset)
-{
- return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
-}
-
-static inline int put_eilvt(int offset)
-{
- return !setup_APIC_eilvt(offset, 0, 0, 1);
-}
-
-static inline int ibs_eilvt_valid(void)
-{
- int offset;
- u64 val;
- int valid = 0;
-
- preempt_disable();
-
- rdmsrl(MSR_AMD64_IBSCTL, val);
- offset = val & IBSCTL_LVT_OFFSET_MASK;
-
- if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
- pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
- smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
- goto out;
- }
-
- if (!get_eilvt(offset)) {
- pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
- smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
- goto out;
- }
-
- valid = 1;
-out:
- preempt_enable();
-
- return valid;
-}
-
-static inline int get_ibs_offset(void)
-{
- u64 val;
-
- rdmsrl(MSR_AMD64_IBSCTL, val);
- if (!(val & IBSCTL_LVT_OFFSET_VALID))
- return -EINVAL;
-
- return val & IBSCTL_LVT_OFFSET_MASK;
-}
-
-static void setup_APIC_ibs(void)
-{
- int offset;
-
- offset = get_ibs_offset();
- if (offset < 0)
- goto failed;
-
- if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
- return;
-failed:
- pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n",
- smp_processor_id());
-}
-
-static void clear_APIC_ibs(void)
-{
- int offset;
-
- offset = get_ibs_offset();
- if (offset >= 0)
- setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
-}
-
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
@@ -439,7 +312,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
goto fail;
}
/* both registers must be reserved */
- if (num_counters == NUM_COUNTERS_F15H) {
+ if (num_counters == AMD64_NUM_COUNTERS_F15H) {
msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1);
msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1);
} else {
@@ -504,15 +377,6 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
val |= op_x86_get_ctrl(model, &counter_config[virt]);
wrmsrl(msrs->controls[i].addr, val);
}
-
- if (ibs_caps)
- setup_APIC_ibs();
-}
-
-static void op_amd_cpu_shutdown(void)
-{
- if (ibs_caps)
- clear_APIC_ibs();
}
static int op_amd_check_ctrs(struct pt_regs * const regs,
@@ -575,86 +439,6 @@ static void op_amd_stop(struct op_msrs const * const msrs)
op_amd_stop_ibs();
}
-static int setup_ibs_ctl(int ibs_eilvt_off)
-{
- struct pci_dev *cpu_cfg;
- int nodes;
- u32 value = 0;
-
- nodes = 0;
- cpu_cfg = NULL;
- do {
- cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD,
- PCI_DEVICE_ID_AMD_10H_NB_MISC,
- cpu_cfg);
- if (!cpu_cfg)
- break;
- ++nodes;
- pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
- | IBSCTL_LVT_OFFSET_VALID);
- pci_read_config_dword(cpu_cfg, IBSCTL, &value);
- if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
- pci_dev_put(cpu_cfg);
- printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
- "IBSCTL = 0x%08x\n", value);
- return -EINVAL;
- }
- } while (1);
-
- if (!nodes) {
- printk(KERN_DEBUG "No CPU node configured for IBS\n");
- return -ENODEV;
- }
-
- return 0;
-}
-
-/*
- * This runs only on the current cpu. We try to find an LVT offset and
- * setup the local APIC. For this we must disable preemption. On
- * success we initialize all nodes with this offset. This updates then
- * the offset in the IBS_CTL per-node msr. The per-core APIC setup of
- * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_-
- * amd_cpu_shutdown() using the new offset.
- */
-static int force_ibs_eilvt_setup(void)
-{
- int offset;
- int ret;
-
- preempt_disable();
- /* find the next free available EILVT entry, skip offset 0 */
- for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
- if (get_eilvt(offset))
- break;
- }
- preempt_enable();
-
- if (offset == APIC_EILVT_NR_MAX) {
- printk(KERN_DEBUG "No EILVT entry available\n");
- return -EBUSY;
- }
-
- ret = setup_ibs_ctl(offset);
- if (ret)
- goto out;
-
- if (!ibs_eilvt_valid()) {
- ret = -EFAULT;
- goto out;
- }
-
- pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
- pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
-
- return 0;
-out:
- preempt_disable();
- put_eilvt(offset);
- preempt_enable();
- return ret;
-}
-
/*
* check and reserve APIC extended interrupt LVT offset for IBS if
* available
@@ -667,17 +451,6 @@ static void init_ibs(void)
if (!ibs_caps)
return;
- if (ibs_eilvt_valid())
- goto out;
-
- if (!force_ibs_eilvt_setup())
- goto out;
-
- /* Failed to setup ibs */
- ibs_caps = 0;
- return;
-
-out:
printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
}
@@ -741,9 +514,9 @@ static int op_amd_init(struct oprofile_operations *ops)
ops->create_files = setup_ibs_files;
if (boot_cpu_data.x86 == 0x15) {
- num_counters = NUM_COUNTERS_F15H;
+ num_counters = AMD64_NUM_COUNTERS_F15H;
} else {
- num_counters = NUM_COUNTERS;
+ num_counters = AMD64_NUM_COUNTERS;
}
op_amd_spec.num_counters = num_counters;
@@ -760,7 +533,6 @@ struct op_x86_model_spec op_amd_spec = {
.init = op_amd_init,
.fill_in_addresses = &op_amd_fill_in_addresses,
.setup_ctrs = &op_amd_setup_ctrs,
- .cpu_down = &op_amd_cpu_shutdown,
.check_ctrs = &op_amd_check_ctrs,
.start = &op_amd_start,
.stop = &op_amd_stop,
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 94b745045e4..d90528ea541 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -28,7 +28,7 @@ static int counter_width = 32;
#define MSR_PPRO_EVENTSEL_RESERVED ((0xFFFFFFFFULL<<32)|(1ULL<<21))
-static u64 *reset_value;
+static u64 reset_value[OP_MAX_COUNTER];
static void ppro_shutdown(struct op_msrs const * const msrs)
{
@@ -40,10 +40,6 @@ static void ppro_shutdown(struct op_msrs const * const msrs)
release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
}
- if (reset_value) {
- kfree(reset_value);
- reset_value = NULL;
- }
}
static int ppro_fill_in_addresses(struct op_msrs * const msrs)
@@ -79,13 +75,6 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
u64 val;
int i;
- if (!reset_value) {
- reset_value = kzalloc(sizeof(reset_value[0]) * num_counters,
- GFP_ATOMIC);
- if (!reset_value)
- return;
- }
-
if (cpu_has_arch_perfmon) {
union cpuid10_eax eax;
eax.full = cpuid_eax(0xa);
@@ -141,13 +130,6 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
u64 val;
int i;
- /*
- * This can happen if perf counters are in use when
- * we steal the die notifier NMI.
- */
- if (unlikely(!reset_value))
- goto out;
-
for (i = 0; i < num_counters; ++i) {
if (!reset_value[i])
continue;
@@ -158,7 +140,6 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
wrmsrl(msrs->counters[i].addr, -reset_value[i]);
}
-out:
/* Only P6 based Pentium M need to re-unmask the apic vector but it
* doesn't hurt other P6 variant */
apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
@@ -179,8 +160,6 @@ static void ppro_start(struct op_msrs const * const msrs)
u64 val;
int i;
- if (!reset_value)
- return;
for (i = 0; i < num_counters; ++i) {
if (reset_value[i]) {
rdmsrl(msrs->controls[i].addr, val);
@@ -196,8 +175,6 @@ static void ppro_stop(struct op_msrs const * const msrs)
u64 val;
int i;
- if (!reset_value)
- return;
for (i = 0; i < num_counters; ++i) {
if (!reset_value[i])
continue;
@@ -242,7 +219,7 @@ static void arch_perfmon_setup_counters(void)
eax.split.bit_width = 40;
}
- num_counters = eax.split.num_counters;
+ num_counters = min((int)eax.split.num_counters, OP_MAX_COUNTER);
op_arch_perfmon_spec.num_counters = num_counters;
op_arch_perfmon_spec.num_controls = num_counters;
diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index 89017fa1fd6..71e8a67337e 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -43,7 +43,6 @@ struct op_x86_model_spec {
int (*fill_in_addresses)(struct op_msrs * const msrs);
void (*setup_ctrs)(struct op_x86_model_spec const *model,
struct op_msrs const * const msrs);
- void (*cpu_down)(void);
int (*check_ctrs)(struct pt_regs * const regs,
struct op_msrs const * const msrs);
void (*start)(struct op_msrs const * const msrs);