summaryrefslogtreecommitdiffstats
path: root/arch/i386/oprofile
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@g5.osdl.org>2006-09-26 13:07:55 -0700
committerLinus Torvalds <torvalds@g5.osdl.org>2006-09-26 13:07:55 -0700
commitb278240839e20fa9384ea430df463b367b90e04e (patch)
treef99f0c8cdd4cc7f177cd75440e6bd181cded7fb3 /arch/i386/oprofile
parentdd77a4ee0f3981693d4229aa1d57cea9e526ff47 (diff)
parent3f75f42d7733e73aca5c78326489efd4189e0111 (diff)
Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6
* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (225 commits) [PATCH] Don't set calgary iommu as default y [PATCH] i386/x86-64: New Intel feature flags [PATCH] x86: Add a cumulative thermal throttle event counter. [PATCH] i386: Make the jiffies compares use the 64bit safe macros. [PATCH] x86: Refactor thermal throttle processing [PATCH] Add 64bit jiffies compares (for use with get_jiffies_64) [PATCH] Fix unwinder warning in traps.c [PATCH] x86: Allow disabling early pci scans with pci=noearly or disallowing conf1 [PATCH] x86: Move direct PCI scanning functions out of line [PATCH] i386/x86-64: Make all early PCI scans dependent on CONFIG_PCI [PATCH] Don't leak NT bit into next task [PATCH] i386/x86-64: Work around gcc bug with noreturn functions in unwinder [PATCH] Fix some broken white space in ia32_signal.c [PATCH] Initialize argument registers for 32bit signal handlers. [PATCH] Remove all traces of signal number conversion [PATCH] Don't synchronize time reading on single core AMD systems [PATCH] Remove outdated comment in x86-64 mmconfig code [PATCH] Use string instructions for Core2 copy/clear [PATCH] x86: - restore i8259A eoi status on resume [PATCH] i386: Split multi-line printk in oops output. ...
Diffstat (limited to 'arch/i386/oprofile')
-rw-r--r--arch/i386/oprofile/nmi_int.c88
-rw-r--r--arch/i386/oprofile/nmi_timer_int.c35
-rw-r--r--arch/i386/oprofile/op_model_athlon.c54
-rw-r--r--arch/i386/oprofile/op_model_p4.c152
-rw-r--r--arch/i386/oprofile/op_model_ppro.c65
-rw-r--r--arch/i386/oprofile/op_x86_model.h1
6 files changed, 254 insertions, 141 deletions
diff --git a/arch/i386/oprofile/nmi_int.c b/arch/i386/oprofile/nmi_int.c
index 5f8dc8a21bd..3700eef7874 100644
--- a/arch/i386/oprofile/nmi_int.c
+++ b/arch/i386/oprofile/nmi_int.c
@@ -17,14 +17,15 @@
#include <asm/nmi.h>
#include <asm/msr.h>
#include <asm/apic.h>
+#include <asm/kdebug.h>
#include "op_counter.h"
#include "op_x86_model.h"
-
+
static struct op_x86_model_spec const * model;
static struct op_msrs cpu_msrs[NR_CPUS];
static unsigned long saved_lvtpc[NR_CPUS];
-
+
static int nmi_start(void);
static void nmi_stop(void);
@@ -82,13 +83,24 @@ static void exit_driverfs(void)
#define exit_driverfs() do { } while (0)
#endif /* CONFIG_PM */
-
-static int nmi_callback(struct pt_regs * regs, int cpu)
+static int profile_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data)
{
- return model->check_ctrs(regs, &cpu_msrs[cpu]);
+ struct die_args *args = (struct die_args *)data;
+ int ret = NOTIFY_DONE;
+ int cpu = smp_processor_id();
+
+ switch(val) {
+ case DIE_NMI:
+ if (model->check_ctrs(args->regs, &cpu_msrs[cpu]))
+ ret = NOTIFY_STOP;
+ break;
+ default:
+ break;
+ }
+ return ret;
}
-
-
+
static void nmi_cpu_save_registers(struct op_msrs * msrs)
{
unsigned int const nr_ctrs = model->num_counters;
@@ -98,15 +110,19 @@ static void nmi_cpu_save_registers(struct op_msrs * msrs)
unsigned int i;
for (i = 0; i < nr_ctrs; ++i) {
- rdmsr(counters[i].addr,
- counters[i].saved.low,
- counters[i].saved.high);
+ if (counters[i].addr){
+ rdmsr(counters[i].addr,
+ counters[i].saved.low,
+ counters[i].saved.high);
+ }
}
for (i = 0; i < nr_ctrls; ++i) {
- rdmsr(controls[i].addr,
- controls[i].saved.low,
- controls[i].saved.high);
+ if (controls[i].addr){
+ rdmsr(controls[i].addr,
+ controls[i].saved.low,
+ controls[i].saved.high);
+ }
}
}
@@ -170,27 +186,29 @@ 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 = 0
+};
static int nmi_setup(void)
{
+ int err=0;
+
if (!allocate_msrs())
return -ENOMEM;
- /* We walk a thin line between law and rape here.
- * We need to be careful to install our NMI handler
- * without actually triggering any NMIs as this will
- * break the core code horrifically.
- */
- if (reserve_lapic_nmi() < 0) {
+ if ((err = register_die_notifier(&profile_exceptions_nb))){
free_msrs();
- return -EBUSY;
+ return err;
}
+
/* We need to serialize save and setup for HT because the subset
* of msrs are distinct for save and setup operations
*/
on_each_cpu(nmi_save_registers, NULL, 0, 1);
on_each_cpu(nmi_cpu_setup, NULL, 0, 1);
- set_nmi_callback(nmi_callback);
nmi_enabled = 1;
return 0;
}
@@ -205,15 +223,19 @@ static void nmi_restore_registers(struct op_msrs * msrs)
unsigned int i;
for (i = 0; i < nr_ctrls; ++i) {
- wrmsr(controls[i].addr,
- controls[i].saved.low,
- controls[i].saved.high);
+ if (controls[i].addr){
+ wrmsr(controls[i].addr,
+ controls[i].saved.low,
+ controls[i].saved.high);
+ }
}
for (i = 0; i < nr_ctrs; ++i) {
- wrmsr(counters[i].addr,
- counters[i].saved.low,
- counters[i].saved.high);
+ if (counters[i].addr){
+ wrmsr(counters[i].addr,
+ counters[i].saved.low,
+ counters[i].saved.high);
+ }
}
}
@@ -234,6 +256,7 @@ static void nmi_cpu_shutdown(void * dummy)
apic_write(APIC_LVTPC, saved_lvtpc[cpu]);
apic_write(APIC_LVTERR, v);
nmi_restore_registers(msrs);
+ model->shutdown(msrs);
}
@@ -241,8 +264,7 @@ static void nmi_shutdown(void)
{
nmi_enabled = 0;
on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
- unset_nmi_callback();
- release_lapic_nmi();
+ unregister_die_notifier(&profile_exceptions_nb);
free_msrs();
}
@@ -284,6 +306,14 @@ static int nmi_create_files(struct super_block * sb, struct dentry * root)
struct dentry * dir;
char buf[4];
+ /* quick little hack to _not_ expose a counter if it is not
+ * available for use. This should protect userspace app.
+ * NOTE: assumes 1:1 mapping here (that counters are organized
+ * sequentially in their struct assignment).
+ */
+ if (unlikely(!avail_to_resrv_perfctr_nmi_bit(i)))
+ continue;
+
snprintf(buf, sizeof(buf), "%d", i);
dir = oprofilefs_mkdir(sb, root, buf);
oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
diff --git a/arch/i386/oprofile/nmi_timer_int.c b/arch/i386/oprofile/nmi_timer_int.c
index 930a1127bb3..abf0ba52a63 100644
--- a/arch/i386/oprofile/nmi_timer_int.c
+++ b/arch/i386/oprofile/nmi_timer_int.c
@@ -17,34 +17,49 @@
#include <asm/nmi.h>
#include <asm/apic.h>
#include <asm/ptrace.h>
+#include <asm/kdebug.h>
-static int nmi_timer_callback(struct pt_regs * regs, int cpu)
+static int profile_timer_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data)
{
- oprofile_add_sample(regs, 0);
- return 1;
+ 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;
}
+static struct notifier_block profile_timer_exceptions_nb = {
+ .notifier_call = profile_timer_exceptions_notify,
+ .next = NULL,
+ .priority = 0
+};
+
static int timer_start(void)
{
- disable_timer_nmi_watchdog();
- set_nmi_callback(nmi_timer_callback);
+ if (register_die_notifier(&profile_timer_exceptions_nb))
+ return 1;
return 0;
}
static void timer_stop(void)
{
- enable_timer_nmi_watchdog();
- unset_nmi_callback();
+ unregister_die_notifier(&profile_timer_exceptions_nb);
synchronize_sched(); /* Allow already-started NMIs to complete. */
}
int __init op_nmi_timer_init(struct oprofile_operations * ops)
{
- extern int nmi_active;
-
- if (nmi_active <= 0)
+ if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0))
return -ENODEV;
ops->start = timer_start;
diff --git a/arch/i386/oprofile/op_model_athlon.c b/arch/i386/oprofile/op_model_athlon.c
index 693bdea4a52..3057a19e464 100644
--- a/arch/i386/oprofile/op_model_athlon.c
+++ b/arch/i386/oprofile/op_model_athlon.c
@@ -21,10 +21,12 @@
#define NUM_COUNTERS 4
#define NUM_CONTROLS 4
+#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0)
#define CTR_READ(l,h,msrs,c) do {rdmsr(msrs->counters[(c)].addr, (l), (h));} while (0)
#define CTR_WRITE(l,msrs,c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1);} while (0)
#define CTR_OVERFLOWED(n) (!((n) & (1U<<31)))
+#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0)
#define CTRL_READ(l,h,msrs,c) do {rdmsr(msrs->controls[(c)].addr, (l), (h));} while (0)
#define CTRL_WRITE(l,h,msrs,c) do {wrmsr(msrs->controls[(c)].addr, (l), (h));} while (0)
#define CTRL_SET_ACTIVE(n) (n |= (1<<22))
@@ -40,15 +42,21 @@ static unsigned long reset_value[NUM_COUNTERS];
static void athlon_fill_in_addresses(struct op_msrs * const msrs)
{
- msrs->counters[0].addr = MSR_K7_PERFCTR0;
- msrs->counters[1].addr = MSR_K7_PERFCTR1;
- msrs->counters[2].addr = MSR_K7_PERFCTR2;
- msrs->counters[3].addr = MSR_K7_PERFCTR3;
-
- msrs->controls[0].addr = MSR_K7_EVNTSEL0;
- msrs->controls[1].addr = MSR_K7_EVNTSEL1;
- msrs->controls[2].addr = MSR_K7_EVNTSEL2;
- msrs->controls[3].addr = MSR_K7_EVNTSEL3;
+ int i;
+
+ 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;
+ }
}
@@ -59,19 +67,23 @@ static void athlon_setup_ctrs(struct op_msrs const * const msrs)
/* clear all counters */
for (i = 0 ; i < NUM_CONTROLS; ++i) {
+ if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+ continue;
CTRL_READ(low, high, msrs, i);
CTRL_CLEAR(low);
CTRL_WRITE(low, high, msrs, i);
}
-
+
/* avoid a false detection of ctr overflows in NMI handler */
for (i = 0; i < NUM_COUNTERS; ++i) {
+ if (unlikely(!CTR_IS_RESERVED(msrs,i)))
+ continue;
CTR_WRITE(1, msrs, i);
}
/* enable active counters */
for (i = 0; i < NUM_COUNTERS; ++i) {
- if (counter_config[i].enabled) {
+ if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs,i))) {
reset_value[i] = counter_config[i].count;
CTR_WRITE(counter_config[i].count, msrs, i);
@@ -98,6 +110,8 @@ static int athlon_check_ctrs(struct pt_regs * const regs,
int i;
for (i = 0 ; i < NUM_COUNTERS; ++i) {
+ if (!reset_value[i])
+ continue;
CTR_READ(low, high, msrs, i);
if (CTR_OVERFLOWED(low)) {
oprofile_add_sample(regs, i);
@@ -132,12 +146,27 @@ static void athlon_stop(struct op_msrs const * const msrs)
/* Subtle: stop on all counters to avoid race with
* setting our pm callback */
for (i = 0 ; i < NUM_COUNTERS ; ++i) {
+ if (!reset_value[i])
+ continue;
CTRL_READ(low, high, msrs, i);
CTRL_SET_INACTIVE(low);
CTRL_WRITE(low, high, msrs, i);
}
}
+static void athlon_shutdown(struct op_msrs const * const msrs)
+{
+ int i;
+
+ for (i = 0 ; i < NUM_COUNTERS ; ++i) {
+ if (CTR_IS_RESERVED(msrs,i))
+ release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+ }
+ for (i = 0 ; i < NUM_CONTROLS ; ++i) {
+ if (CTRL_IS_RESERVED(msrs,i))
+ release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+ }
+}
struct op_x86_model_spec const op_athlon_spec = {
.num_counters = NUM_COUNTERS,
@@ -146,5 +175,6 @@ struct op_x86_model_spec const op_athlon_spec = {
.setup_ctrs = &athlon_setup_ctrs,
.check_ctrs = &athlon_check_ctrs,
.start = &athlon_start,
- .stop = &athlon_stop
+ .stop = &athlon_stop,
+ .shutdown = &athlon_shutdown
};
diff --git a/arch/i386/oprofile/op_model_p4.c b/arch/i386/oprofile/op_model_p4.c
index 7c61d357b82..47925927b12 100644
--- a/arch/i386/oprofile/op_model_p4.c
+++ b/arch/i386/oprofile/op_model_p4.c
@@ -32,7 +32,7 @@
#define NUM_CONTROLS_HT2 (NUM_ESCRS_HT2 + NUM_CCCRS_HT2)
static unsigned int num_counters = NUM_COUNTERS_NON_HT;
-
+static unsigned int num_controls = NUM_CONTROLS_NON_HT;
/* this has to be checked dynamically since the
hyper-threadedness of a chip is discovered at
@@ -40,8 +40,10 @@ static unsigned int num_counters = NUM_COUNTERS_NON_HT;
static inline void setup_num_counters(void)
{
#ifdef CONFIG_SMP
- if (smp_num_siblings == 2)
+ if (smp_num_siblings == 2){
num_counters = NUM_COUNTERS_HT2;
+ num_controls = NUM_CONTROLS_HT2;
+ }
#endif
}
@@ -97,15 +99,6 @@ static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = {
#define NUM_UNUSED_CCCRS NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT
-/* All cccr we don't use. */
-static int p4_unused_cccr[NUM_UNUSED_CCCRS] = {
- MSR_P4_BPU_CCCR1, MSR_P4_BPU_CCCR3,
- MSR_P4_MS_CCCR1, MSR_P4_MS_CCCR3,
- MSR_P4_FLAME_CCCR1, MSR_P4_FLAME_CCCR3,
- MSR_P4_IQ_CCCR0, MSR_P4_IQ_CCCR1,
- MSR_P4_IQ_CCCR2, MSR_P4_IQ_CCCR3
-};
-
/* p4 event codes in libop/op_event.h are indices into this table. */
static struct p4_event_binding p4_events[NUM_EVENTS] = {
@@ -372,6 +365,8 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
#define CCCR_OVF_P(cccr) ((cccr) & (1U<<31))
#define CCCR_CLEAR_OVF(cccr) ((cccr) &= (~(1U<<31)))
+#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0)
+#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0)
#define CTR_READ(l,h,i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h));} while (0)
#define CTR_WRITE(l,i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1);} while (0)
#define CTR_OVERFLOW_P(ctr) (!((ctr) & 0x80000000))
@@ -401,29 +396,34 @@ static unsigned long reset_value[NUM_COUNTERS_NON_HT];
static void p4_fill_in_addresses(struct op_msrs * const msrs)
{
unsigned int i;
- unsigned int addr, stag;
+ unsigned int addr, cccraddr, stag;
setup_num_counters();
stag = get_stagger();
- /* the counter registers we pay attention to */
+ /* initialize some registers */
for (i = 0; i < num_counters; ++i) {
- msrs->counters[i].addr =
- p4_counters[VIRT_CTR(stag, i)].counter_address;
+ msrs->counters[i].addr = 0;
}
-
- /* FIXME: bad feeling, we don't save the 10 counters we don't use. */
-
- /* 18 CCCR registers */
- for (i = 0, addr = MSR_P4_BPU_CCCR0 + stag;
- addr <= MSR_P4_IQ_CCCR5; ++i, addr += addr_increment()) {
- msrs->controls[i].addr = addr;
+ 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;
+ cccraddr = p4_counters[VIRT_CTR(stag, i)].cccr_address;
+ if (reserve_perfctr_nmi(addr)){
+ msrs->counters[i].addr = addr;
+ msrs->controls[i].addr = cccraddr;
+ }
+ }
+
/* 43 ESCR registers in three or four discontiguous group */
for (addr = MSR_P4_BSU_ESCR0 + stag;
addr < MSR_P4_IQ_ESCR0; ++i, addr += addr_increment()) {
- msrs->controls[i].addr = addr;
+ if (reserve_evntsel_nmi(addr))
+ msrs->controls[i].addr = addr;
}
/* no IQ_ESCR0/1 on some models, we save a seconde time BSU_ESCR0/1
@@ -431,47 +431,57 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs)
if (boot_cpu_data.x86_model >= 0x3) {
for (addr = MSR_P4_BSU_ESCR0 + stag;
addr <= MSR_P4_BSU_ESCR1; ++i, addr += addr_increment()) {
- msrs->controls[i].addr = addr;
+ if (reserve_evntsel_nmi(addr))
+ msrs->controls[i].addr = addr;
}
} else {
for (addr = MSR_P4_IQ_ESCR0 + stag;
addr <= MSR_P4_IQ_ESCR1; ++i, addr += addr_increment()) {
- msrs->controls[i].addr = addr;
+ if (reserve_evntsel_nmi(addr))
+ msrs->controls[i].addr = addr;
}
}
for (addr = MSR_P4_RAT_ESCR0 + stag;
addr <= MSR_P4_SSU_ESCR0; ++i, addr += addr_increment()) {
- msrs->controls[i].addr = addr;
+ if (reserve_evntsel_nmi(addr))
+ msrs->controls[i].addr = addr;
}
for (addr = MSR_P4_MS_ESCR0 + stag;
addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) {
- msrs->controls[i].addr = addr;
+ if (reserve_evntsel_nmi(addr))
+ msrs->controls[i].addr = addr;
}
for (addr = MSR_P4_IX_ESCR0 + stag;
addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) {
- msrs->controls[i].addr = addr;
+ if (reserve_evntsel_nmi(addr))
+ msrs->controls[i].addr = addr;
}
/* there are 2 remaining non-contiguously located ESCRs */
if (num_counters == NUM_COUNTERS_NON_HT) {
/* standard non-HT CPUs handle both remaining ESCRs*/
- msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
- msrs->controls[i++].addr = MSR_P4_CRU_ESCR4;
+ if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5))
+ msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
+ if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR4))
+ msrs->controls[i++].addr = MSR_P4_CRU_ESCR4;
} else if (stag == 0) {
/* HT CPUs give the first remainder to the even thread, as
the 32nd control register */
- msrs->controls[i++].addr = MSR_P4_CRU_ESCR4;
+ if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR4))
+ msrs->controls[i++].addr = MSR_P4_CRU_ESCR4;
} else {
/* and two copies of the second to the odd thread,
for the 22st and 23nd control registers */
- msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
- msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
+ if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5)) {
+ msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
+ msrs->controls[i++].addr = MSR_P4_CRU_ESCR5;
+ }
}
}
@@ -544,7 +554,6 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs)
{
unsigned int i;
unsigned int low, high;
- unsigned int addr;
unsigned int stag;
stag = get_stagger();
@@ -557,59 +566,24 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs)
/* clear the cccrs we will use */
for (i = 0 ; i < num_counters ; i++) {
+ if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+ continue;
rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
CCCR_CLEAR(low);
CCCR_SET_REQUIRED_BITS(low);
wrmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
}
- /* clear cccrs outside our concern */
- for (i = stag ; i < NUM_UNUSED_CCCRS ; i += addr_increment()) {
- rdmsr(p4_unused_cccr[i], low, high);
- CCCR_CLEAR(low);
- CCCR_SET_REQUIRED_BITS(low);
- wrmsr(p4_unused_cccr[i], low, high);
- }
-
/* clear all escrs (including those outside our concern) */
- for (addr = MSR_P4_BSU_ESCR0 + stag;
- addr < MSR_P4_IQ_ESCR0; addr += addr_increment()) {
- wrmsr(addr, 0, 0);
- }
-
- /* On older models clear also MSR_P4_IQ_ESCR0/1 */
- if (boot_cpu_data.x86_model < 0x3) {
- wrmsr(MSR_P4_IQ_ESCR0, 0, 0);
- wrmsr(MSR_P4_IQ_ESCR1, 0, 0);
- }
-
- for (addr = MSR_P4_RAT_ESCR0 + stag;
- addr <= MSR_P4_SSU_ESCR0; ++i, addr += addr_increment()) {
- wrmsr(addr, 0, 0);
- }
-
- for (addr = MSR_P4_MS_ESCR0 + stag;
- addr <= MSR_P4_TC_ESCR1; addr += addr_increment()){
- wrmsr(addr, 0, 0);
- }
-
- for (addr = MSR_P4_IX_ESCR0 + stag;
- addr <= MSR_P4_CRU_ESCR3; addr += addr_increment()){
- wrmsr(addr, 0, 0);
+ for (i = num_counters; i < num_controls; i++) {
+ if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+ continue;
+ wrmsr(msrs->controls[i].addr, 0, 0);
}
- if (num_counters == NUM_COUNTERS_NON_HT) {
- wrmsr(MSR_P4_CRU_ESCR4, 0, 0);
- wrmsr(MSR_P4_CRU_ESCR5, 0, 0);
- } else if (stag == 0) {
- wrmsr(MSR_P4_CRU_ESCR4, 0, 0);
- } else {
- wrmsr(MSR_P4_CRU_ESCR5, 0, 0);
- }
-
/* setup all counters */
for (i = 0 ; i < num_counters ; ++i) {
- if (counter_config[i].enabled) {
+ if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs,i))) {
reset_value[i] = counter_config[i].count;
pmc_setup_one_p4_counter(i);
CTR_WRITE(counter_config[i].count, VIRT_CTR(stag, i));
@@ -696,12 +670,32 @@ static void p4_stop(struct op_msrs const * const msrs)
stag = get_stagger();
for (i = 0; i < num_counters; ++i) {
+ if (!reset_value[i])
+ continue;
CCCR_READ(low, high, VIRT_CTR(stag, i));
CCCR_SET_DISABLE(low);
CCCR_WRITE(low, high, VIRT_CTR(stag, i));
}
}
+static void p4_shutdown(struct op_msrs const * const msrs)
+{
+ int i;
+
+ for (i = 0 ; i < num_counters ; ++i) {
+ if (CTR_IS_RESERVED(msrs,i))
+ release_perfctr_nmi(msrs->counters[i].addr);
+ }
+ /* some of the control registers are specially reserved in
+ * conjunction with the counter registers (hence the starting offset).
+ * This saves a few bits.
+ */
+ for (i = num_counters ; i < num_controls ; ++i) {
+ if (CTRL_IS_RESERVED(msrs,i))
+ release_evntsel_nmi(msrs->controls[i].addr);
+ }
+}
+
#ifdef CONFIG_SMP
struct op_x86_model_spec const op_p4_ht2_spec = {
@@ -711,7 +705,8 @@ struct op_x86_model_spec const op_p4_ht2_spec = {
.setup_ctrs = &p4_setup_ctrs,
.check_ctrs = &p4_check_ctrs,
.start = &p4_start,
- .stop = &p4_stop
+ .stop = &p4_stop,
+ .shutdown = &p4_shutdown
};
#endif
@@ -722,5 +717,6 @@ struct op_x86_model_spec const op_p4_spec = {
.setup_ctrs = &p4_setup_ctrs,
.check_ctrs = &p4_check_ctrs,
.start = &p4_start,
- .stop = &p4_stop
+ .stop = &p4_stop,
+ .shutdown = &p4_shutdown
};
diff --git a/arch/i386/oprofile/op_model_ppro.c b/arch/i386/oprofile/op_model_ppro.c
index 5c3ab4b027a..f88e05ba8eb 100644
--- a/arch/i386/oprofile/op_model_ppro.c
+++ b/arch/i386/oprofile/op_model_ppro.c
@@ -22,10 +22,12 @@
#define NUM_COUNTERS 2
#define NUM_CONTROLS 2
+#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0)
#define CTR_READ(l,h,msrs,c) do {rdmsr(msrs->counters[(c)].addr, (l), (h));} while (0)
#define CTR_WRITE(l,msrs,c) do {wrmsr(msrs->counters[(c)].addr, -(u32)(l), -1);} while (0)
#define CTR_OVERFLOWED(n) (!((n) & (1U<<31)))
+#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0)
#define CTRL_READ(l,h,msrs,c) do {rdmsr((msrs->controls[(c)].addr), (l), (h));} while (0)
#define CTRL_WRITE(l,h,msrs,c) do {wrmsr((msrs->controls[(c)].addr), (l), (h));} while (0)
#define CTRL_SET_ACTIVE(n) (n |= (1<<22))
@@ -41,11 +43,21 @@ static unsigned long reset_value[NUM_COUNTERS];
static void ppro_fill_in_addresses(struct op_msrs * const msrs)
{
- msrs->counters[0].addr = MSR_P6_PERFCTR0;
- msrs->counters[1].addr = MSR_P6_PERFCTR1;
+ int i;
+
+ 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;
+ }
- msrs->controls[0].addr = MSR_P6_EVNTSEL0;
- msrs->controls[1].addr = MSR_P6_EVNTSEL1;
+ for (i=0; i < NUM_CONTROLS; i++) {
+ if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i))
+ msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
+ else
+ msrs->controls[i].addr = 0;
+ }
}
@@ -56,6 +68,8 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
/* clear all counters */
for (i = 0 ; i < NUM_CONTROLS; ++i) {
+ if (unlikely(!CTRL_IS_RESERVED(msrs,i)))
+ continue;
CTRL_READ(low, high, msrs, i);
CTRL_CLEAR(low);
CTRL_WRITE(low, high, msrs, i);
@@ -63,12 +77,14 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
/* avoid a false detection of ctr overflows in NMI handler */
for (i = 0; i < NUM_COUNTERS; ++i) {
+ if (unlikely(!CTR_IS_RESERVED(msrs,i)))
+ continue;
CTR_WRITE(1, msrs, i);
}
/* enable active counters */
for (i = 0; i < NUM_COUNTERS; ++i) {
- if (counter_config[i].enabled) {
+ if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs,i))) {
reset_value[i] = counter_config[i].count;
CTR_WRITE(counter_config[i].count, msrs, i);
@@ -81,6 +97,8 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
CTRL_SET_UM(low, counter_config[i].unit_mask);
CTRL_SET_EVENT(low, counter_config[i].event);
CTRL_WRITE(low, high, msrs, i);
+ } else {
+ reset_value[i] = 0;
}
}
}
@@ -93,6 +111,8 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
int i;
for (i = 0 ; i < NUM_COUNTERS; ++i) {
+ if (!reset_value[i])
+ continue;
CTR_READ(low, high, msrs, i);
if (CTR_OVERFLOWED(low)) {
oprofile_add_sample(regs, i);
@@ -118,18 +138,38 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
static void ppro_start(struct op_msrs const * const msrs)
{
unsigned int low,high;
- CTRL_READ(low, high, msrs, 0);
- CTRL_SET_ACTIVE(low);
- CTRL_WRITE(low, high, msrs, 0);
+
+ if (reset_value[0]) {
+ CTRL_READ(low, high, msrs, 0);
+ CTRL_SET_ACTIVE(low);
+ CTRL_WRITE(low, high, msrs, 0);
+ }
}
static void ppro_stop(struct op_msrs const * const msrs)
{
unsigned int low,high;
- CTRL_READ(low, high, msrs, 0);
- CTRL_SET_INACTIVE(low);
- CTRL_WRITE(low, high, msrs, 0);
+
+ if (reset_value[0]) {
+ CTRL_READ(low, high, msrs, 0);
+ CTRL_SET_INACTIVE(low);
+ CTRL_WRITE(low, high, msrs, 0);
+ }
+}
+
+static void ppro_shutdown(struct op_msrs const * const msrs)
+{
+ int i;
+
+ for (i = 0 ; i < NUM_COUNTERS ; ++i) {
+ if (CTR_IS_RESERVED(msrs,i))
+ release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
+ }
+ for (i = 0 ; i < NUM_CONTROLS ; ++i) {
+ if (CTRL_IS_RESERVED(msrs,i))
+ release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
+ }
}
@@ -140,5 +180,6 @@ struct op_x86_model_spec const op_ppro_spec = {
.setup_ctrs = &ppro_setup_ctrs,
.check_ctrs = &ppro_check_ctrs,
.start = &ppro_start,
- .stop = &ppro_stop
+ .stop = &ppro_stop,
+ .shutdown = &ppro_shutdown
};
diff --git a/arch/i386/oprofile/op_x86_model.h b/arch/i386/oprofile/op_x86_model.h
index 123b7e90a9e..abb1aa95b97 100644
--- a/arch/i386/oprofile/op_x86_model.h
+++ b/arch/i386/oprofile/op_x86_model.h
@@ -40,6 +40,7 @@ struct op_x86_model_spec {
struct op_msrs const * const msrs);
void (*start)(struct op_msrs const * const msrs);
void (*stop)(struct op_msrs const * const msrs);
+ void (*shutdown)(struct op_msrs const * const msrs);
};
extern struct op_x86_model_spec const op_ppro_spec;