summaryrefslogtreecommitdiff
path: root/arch/sparc/kernel/perf_event.c
diff options
context:
space:
mode:
authorChristoph Lameter <cl@linux.com>2014-08-17 12:30:54 -0500
committerTejun Heo <tj@kernel.org>2014-08-26 13:45:55 -0400
commit494fc42170bf0747ac28e12ef13a7d388d5ff2c7 (patch)
tree2f972ce4df5c2bfa899a60e087b05c531bb70e2a /arch/sparc/kernel/perf_event.c
parent8c23af6122e56ad30e3de259731c31a998ff5b11 (diff)
sparc: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: sparclinux@vger.kernel.org Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'arch/sparc/kernel/perf_event.c')
-rw-r--r--arch/sparc/kernel/perf_event.c26
1 files changed, 13 insertions, 13 deletions
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index d35c490a91cb..264049a6cb74 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1013,7 +1013,7 @@ static void update_pcrs_for_enable(struct cpu_hw_events *cpuc)
static void sparc_pmu_enable(struct pmu *pmu)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int i;
if (cpuc->enabled)
@@ -1031,7 +1031,7 @@ static void sparc_pmu_enable(struct pmu *pmu)
static void sparc_pmu_disable(struct pmu *pmu)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int i;
if (!cpuc->enabled)
@@ -1065,7 +1065,7 @@ static int active_event_index(struct cpu_hw_events *cpuc,
static void sparc_pmu_start(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx = active_event_index(cpuc, event);
if (flags & PERF_EF_RELOAD) {
@@ -1080,7 +1080,7 @@ static void sparc_pmu_start(struct perf_event *event, int flags)
static void sparc_pmu_stop(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx = active_event_index(cpuc, event);
if (!(event->hw.state & PERF_HES_STOPPED)) {
@@ -1096,7 +1096,7 @@ static void sparc_pmu_stop(struct perf_event *event, int flags)
static void sparc_pmu_del(struct perf_event *event, int _flags)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
unsigned long flags;
int i;
@@ -1133,7 +1133,7 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
static void sparc_pmu_read(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx = active_event_index(cpuc, event);
struct hw_perf_event *hwc = &event->hw;
@@ -1145,7 +1145,7 @@ static DEFINE_MUTEX(pmc_grab_mutex);
static void perf_stop_nmi_watchdog(void *unused)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int i;
stop_nmi_watchdog(NULL);
@@ -1356,7 +1356,7 @@ static int collect_events(struct perf_event *group, int max_count,
static int sparc_pmu_add(struct perf_event *event, int ef_flags)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int n0, ret = -EAGAIN;
unsigned long flags;
@@ -1498,7 +1498,7 @@ static int sparc_pmu_event_init(struct perf_event *event)
*/
static void sparc_pmu_start_txn(struct pmu *pmu)
{
- struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
perf_pmu_disable(pmu);
cpuhw->group_flag |= PERF_EVENT_TXN;
@@ -1511,7 +1511,7 @@ static void sparc_pmu_start_txn(struct pmu *pmu)
*/
static void sparc_pmu_cancel_txn(struct pmu *pmu)
{
- struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
cpuhw->group_flag &= ~PERF_EVENT_TXN;
perf_pmu_enable(pmu);
@@ -1524,13 +1524,13 @@ static void sparc_pmu_cancel_txn(struct pmu *pmu)
*/
static int sparc_pmu_commit_txn(struct pmu *pmu)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int n;
if (!sparc_pmu)
return -EINVAL;
- cpuc = &__get_cpu_var(cpu_hw_events);
+ cpuc = this_cpu_ptr(&cpu_hw_events);
n = cpuc->n_events;
if (check_excludes(cpuc->event, 0, n))
return -EINVAL;
@@ -1601,7 +1601,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
regs = args->regs;
- cpuc = &__get_cpu_var(cpu_hw_events);
+ cpuc = this_cpu_ptr(&cpu_hw_events);
/* If the PMU has the TOE IRQ enable bits, we need to do a
* dummy write to the %pcr to clear the overflow bits and thus