Re: [PATCH 21/31] s390: Replace __get_cpu_var uses
Applied to wq/for-3.17-consistent-ops. If this patch should be routed differently, please holler. Thanks. -- tejun -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 21/31] s390: Replace __get_cpu_var uses
Applied to wq/for-3.17-consistent-ops. If this patch should be routed differently, please holler. Thanks. -- tejun -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[PATCH 21/31] s390: 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(); 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(, this_cpu_ptr(), 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: Martin Schwidefsky CC: linux...@de.ibm.com Acked-by: Heiko Carstens Signed-off-by: Christoph Lameter Index: linux/arch/s390/include/asm/irq.h === --- linux.orig/arch/s390/include/asm/irq.h 2014-06-16 09:50:33.710435809 -0500 +++ linux/arch/s390/include/asm/irq.h 2014-06-16 09:50:33.702435965 -0500 @@ -81,7 +81,7 @@ static __always_inline void inc_irq_stat(enum interruption_class irq) { - __get_cpu_var(irq_stat).irqs[irq]++; + __this_cpu_inc(irq_stat.irqs[irq]); } struct ext_code { Index: linux/arch/s390/include/asm/cputime.h === --- linux.orig/arch/s390/include/asm/cputime.h 2014-06-16 09:50:33.710435809 -0500 +++ linux/arch/s390/include/asm/cputime.h 2014-06-16 09:50:33.706435887 -0500 @@ -184,7 +184,7 @@ static inline int s390_nohz_delay(int cpu) { - return __get_cpu_var(s390_idle).nohz_delay != 0; + return __this_cpu_read(s390_idle.nohz_delay) != 0; } #define arch_needs_cpu(cpu) s390_nohz_delay(cpu) Index: linux/arch/s390/kernel/kprobes.c === --- linux.orig/arch/s390/kernel/kprobes.c 2014-06-16 09:50:33.710435809 -0500 +++ linux/arch/s390/kernel/kprobes.c2014-06-16 09:50:33.706435887 -0500 @@ -366,9 +366,9 @@ */ static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p) { - kcb->prev_kprobe.kp = __get_cpu_var(current_kprobe); + kcb->prev_kprobe.kp = __this_cpu_read(current_kprobe); kcb->prev_kprobe.status = kcb->kprobe_status; - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); } /* @@ -378,7 +378,7 @@ */ static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; } @@ -459,7 +459,7 @@ enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn); return 1; } else if (kprobe_running()) { - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p,
[PATCH 21/31] s390: 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: Martin Schwidefsky schwidef...@de.ibm.com CC: linux...@de.ibm.com Acked-by: Heiko Carstens heiko.carst...@de.ibm.com Signed-off-by: Christoph Lameter c...@linux.com Index: linux/arch/s390/include/asm/irq.h === --- linux.orig/arch/s390/include/asm/irq.h 2014-06-16 09:50:33.710435809 -0500 +++ linux/arch/s390/include/asm/irq.h 2014-06-16 09:50:33.702435965 -0500 @@ -81,7 +81,7 @@ static __always_inline void inc_irq_stat(enum interruption_class irq) { - __get_cpu_var(irq_stat).irqs[irq]++; + __this_cpu_inc(irq_stat.irqs[irq]); } struct ext_code { Index: linux/arch/s390/include/asm/cputime.h === --- linux.orig/arch/s390/include/asm/cputime.h 2014-06-16 09:50:33.710435809 -0500 +++ linux/arch/s390/include/asm/cputime.h 2014-06-16 09:50:33.706435887 -0500 @@ -184,7 +184,7 @@ static inline int s390_nohz_delay(int cpu) { - return __get_cpu_var(s390_idle).nohz_delay != 0; + return __this_cpu_read(s390_idle.nohz_delay) != 0; } #define arch_needs_cpu(cpu) s390_nohz_delay(cpu) Index: linux/arch/s390/kernel/kprobes.c === --- linux.orig/arch/s390/kernel/kprobes.c 2014-06-16 09:50:33.710435809 -0500 +++ linux/arch/s390/kernel/kprobes.c2014-06-16 09:50:33.706435887 -0500 @@ -366,9 +366,9 @@ */ static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p) { - kcb-prev_kprobe.kp = __get_cpu_var(current_kprobe); + kcb-prev_kprobe.kp = __this_cpu_read(current_kprobe); kcb-prev_kprobe.status = kcb-kprobe_status; - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); } /* @@ -378,7 +378,7 @@ */ static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb-prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb-prev_kprobe.kp); kcb-kprobe_status = kcb-prev_kprobe.status; } @@ -459,7 +459,7 @@ enable_singlestep(kcb, regs, (unsigned long) p-ainsn.insn); return 1; } else if (kprobe_running()) { - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe);