summaryrefslogtreecommitdiffstats
path: root/arch/tile/include
diff options
context:
space:
mode:
authorChristoph Lameter <cl@linux.com>2014-08-17 12:30:50 -0500
committerTejun Heo <tj@kernel.org>2014-08-26 13:45:54 -0400
commitb4f501916ce2ae80c28017814d71d1bf83679271 (patch)
tree0cebabbc13ec4cc5e0609dafe773a7a0bb8adb5f /arch/tile/include
parent5828f666c069af74e00db21559f1535103c9f79a (diff)
downloadop-kernel-dev-b4f501916ce2ae80c28017814d71d1bf83679271.zip
op-kernel-dev-b4f501916ce2ae80c28017814d71d1bf83679271.tar.gz
tile: 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) Acked-by: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'arch/tile/include')
-rw-r--r--arch/tile/include/asm/irqflags.h4
-rw-r--r--arch/tile/include/asm/mmu_context.h6
2 files changed, 5 insertions, 5 deletions
diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h
index 71af574..60d62a2 100644
--- a/arch/tile/include/asm/irqflags.h
+++ b/arch/tile/include/asm/irqflags.h
@@ -140,12 +140,12 @@ extern unsigned int debug_smp_processor_id(void);
/*
* Read the set of maskable interrupts.
- * We avoid the preemption warning here via __this_cpu_ptr since even
+ * We avoid the preemption warning here via raw_cpu_ptr since even
* if irqs are already enabled, it's harmless to read the wrong cpu's
* enabled mask.
*/
#define arch_local_irqs_enabled() \
- (*__this_cpu_ptr(&interrupts_enabled_mask))
+ (*raw_cpu_ptr(&interrupts_enabled_mask))
/* Re-enable all maskable interrupts. */
#define arch_local_irq_enable() \
diff --git a/arch/tile/include/asm/mmu_context.h b/arch/tile/include/asm/mmu_context.h
index 4734215..f67753d 100644
--- a/arch/tile/include/asm/mmu_context.h
+++ b/arch/tile/include/asm/mmu_context.h
@@ -84,7 +84,7 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *t)
* clear any pending DMA interrupts.
*/
if (current->thread.tile_dma_state.enabled)
- install_page_table(mm->pgd, __get_cpu_var(current_asid));
+ install_page_table(mm->pgd, __this_cpu_read(current_asid));
#endif
}
@@ -96,12 +96,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
int cpu = smp_processor_id();
/* Pick new ASID. */
- int asid = __get_cpu_var(current_asid) + 1;
+ int asid = __this_cpu_read(current_asid) + 1;
if (asid > max_asid) {
asid = min_asid;
local_flush_tlb();
}
- __get_cpu_var(current_asid) = asid;
+ __this_cpu_write(current_asid, asid);
/* Clear cpu from the old mm, and set it in the new one. */
cpumask_clear_cpu(cpu, mm_cpumask(prev));
OpenPOWER on IntegriCloud