From 2999a4b354c24985268f9310bc9522ff358453a8 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Sun, 17 Aug 2014 12:30:48 -0500 Subject: alpha: Replace __get_cpu_var __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: Ivan Kokshaysky Cc: Matt Turner Acked-by: Richard Henderson Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- arch/alpha/kernel/perf_event.c | 16 ++++++++-------- arch/alpha/kernel/time.c | 6 +++--- arch/powerpc/include/asm/cputime.h | 6 +++--- 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index c52e7f0ee5f6..5c218aa3f3df 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -431,7 +431,7 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc) */ static int alpha_pmu_add(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); struct hw_perf_event *hwc = &event->hw; int n0; int ret; @@ -483,7 +483,7 @@ static int alpha_pmu_add(struct perf_event *event, int flags) */ static void alpha_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); struct hw_perf_event *hwc = &event->hw; unsigned long irq_flags; int j; @@ -531,7 +531,7 @@ static void alpha_pmu_read(struct perf_event *event) static void alpha_pmu_stop(struct perf_event *event, int flags) { struct hw_perf_event *hwc = &event->hw; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!(hwc->state & PERF_HES_STOPPED)) { cpuc->idx_mask &= ~(1UL<idx); @@ -551,7 +551,7 @@ static void alpha_pmu_stop(struct perf_event *event, int flags) static void alpha_pmu_start(struct perf_event *event, int flags) { struct hw_perf_event *hwc = &event->hw; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) return; @@ -724,7 +724,7 @@ static int alpha_pmu_event_init(struct perf_event *event) */ static void alpha_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); if (cpuc->enabled) return; @@ -750,7 +750,7 @@ static void alpha_pmu_enable(struct pmu *pmu) static void alpha_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); if (!cpuc->enabled) return; @@ -814,8 +814,8 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr, struct hw_perf_event *hwc; int idx, j; - __get_cpu_var(irq_pmi_count)++; - cpuc = &__get_cpu_var(cpu_hw_events); + __this_cpu_inc(irq_pmi_count); + cpuc = this_cpu_ptr(&cpu_hw_events); /* Completely counting through the PMC's period to trigger a new PMC * overflow interrupt while in this interrupt routine is utterly diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index ee39cee8064c..643a9dcdf093 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -56,9 +56,9 @@ unsigned long est_cycle_freq; DEFINE_PER_CPU(u8, irq_work_pending); -#define set_irq_work_pending_flag() __get_cpu_var(irq_work_pending) = 1 -#define test_irq_work_pending() __get_cpu_var(irq_work_pending) -#define clear_irq_work_pending() __get_cpu_var(irq_work_pending) = 0 +#define set_irq_work_pending_flag() __this_cpu_write(irq_work_pending, 1) +#define test_irq_work_pending() __this_cpu_read(irq_work_pending) +#define clear_irq_work_pending() __this_cpu_write(irq_work_pending, 0) void arch_irq_work_raise(void) { diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 607559ab271f..e5d10ab8463b 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -56,10 +56,10 @@ static inline unsigned long cputime_to_jiffies(const cputime_t ct) static inline cputime_t cputime_to_scaled(const cputime_t ct) { if (cpu_has_feature(CPU_FTR_SPURR) && - __get_cpu_var(cputime_last_delta)) + __this_cpu_read(cputime_last_delta)) return (__force u64) ct * - __get_cpu_var(cputime_scaled_last_delta) / - __get_cpu_var(cputime_last_delta); + __this_cpu_read(cputime_scaled_last_delta) / + __this_cpu_read(cputime_last_delta); return ct; } -- cgit v1.2.3