From 69111bac42f5ceacdd22e30947837ceb2c4493ed Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 21 Oct 2014 15:23:25 -0500 Subject: powerpc: Replace __get_cpu_var uses This still has not been merged and now powerpc is the only arch that does not have this change. Sorry about missing linuxppc-dev before. V2->V2 - Fix up to work against 3.18-rc1 __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 : __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: Benjamin Herrenschmidt CC: Paul Mackerras Signed-off-by: Christoph Lameter [mpe: Fix build errors caused by set/or_softirq_pending(), and rework assignment in __set_breakpoint() to use memcpy().] Signed-off-by: Michael Ellerman --- arch/powerpc/perf/core-book3s.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'arch/powerpc/perf/core-book3s.c') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index a6995d4e93d4..7c4f6690533a 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -339,7 +339,7 @@ static void power_pmu_bhrb_reset(void) static void power_pmu_bhrb_enable(struct perf_event *event) { - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); if (!ppmu->bhrb_nr) return; @@ -354,7 +354,7 @@ static void power_pmu_bhrb_enable(struct perf_event *event) static void power_pmu_bhrb_disable(struct perf_event *event) { - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); if (!ppmu->bhrb_nr) return; @@ -1144,7 +1144,7 @@ static void power_pmu_disable(struct pmu *pmu) if (!ppmu) return; local_irq_save(flags); - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); if (!cpuhw->disabled) { /* @@ -1211,7 +1211,7 @@ static void power_pmu_enable(struct pmu *pmu) return; local_irq_save(flags); - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); if (!cpuhw->disabled) goto out; @@ -1403,7 +1403,7 @@ static int power_pmu_add(struct perf_event *event, int ef_flags) * Add the event to the list (if there is room) * and check whether the total set is still feasible. */ - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); n0 = cpuhw->n_events; if (n0 >= ppmu->n_counter) goto out; @@ -1469,7 +1469,7 @@ static void power_pmu_del(struct perf_event *event, int ef_flags) power_pmu_read(event); - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); for (i = 0; i < cpuhw->n_events; ++i) { if (event == cpuhw->event[i]) { while (++i < cpuhw->n_events) { @@ -1575,7 +1575,7 @@ static void power_pmu_stop(struct perf_event *event, int ef_flags) */ static void power_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; @@ -1589,7 +1589,7 @@ static void power_pmu_start_txn(struct pmu *pmu) */ static void power_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); @@ -1607,7 +1607,7 @@ static int power_pmu_commit_txn(struct pmu *pmu) if (!ppmu) return -EAGAIN; - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); n = cpuhw->n_events; if (check_excludes(cpuhw->event, cpuhw->flags, 0, n)) return -EAGAIN; @@ -1964,7 +1964,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { struct cpu_hw_events *cpuhw; - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); power_pmu_bhrb_read(cpuhw); data.br_stack = &cpuhw->bhrb_stack; } @@ -2037,7 +2037,7 @@ static bool pmc_overflow(unsigned long val) static void perf_event_interrupt(struct pt_regs *regs) { int i, j; - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; unsigned long val[8]; int found, active; -- cgit v1.2.3