From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Lameter Subject: [PATCH 10/10] kernel misc: Replace __get_cpu_var uses Date: Tue, 15 Oct 2013 12:59:02 -0500 Message-ID: <20131015180054.785696220@linux.com> References: <20131015175852.122827685@linux.com> Return-path: Content-Disposition: inline; filename=this_misc Sender: linux-kernel-owner@vger.kernel.org To: Tejun Heo Cc: akpm@linuxfoundation.org, linux-arch@vger.kernel.org, Steven Rostedt , linux-kernel@vger.kernel.org, Ingo Molnar , Peter Zijlstra List-Id: linux-arch.vger.kernel.org __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) Signed-off-by: Christoph Lameter Index: linux/kernel/printk/printk.c =================================================================== --- linux.orig/kernel/printk/printk.c 2013-09-19 15:16:05.428149660 -0500 +++ linux/kernel/printk/printk.c 2013-09-19 15:16:05.404149909 -0500 @@ -2448,7 +2448,7 @@ static void wake_up_klogd_work_func(stru int pending = __this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_SCHED) { - char *buf = __get_cpu_var(printk_sched_buf); + char *buf = this_cpu_ptr(printk_sched_buf); printk(KERN_WARNING "[sched_delayed] %s", buf); } @@ -2466,7 +2466,7 @@ void wake_up_klogd(void) preempt_disable(); if (waitqueue_active(&log_wait)) { this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); - irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } @@ -2479,14 +2479,14 @@ int printk_sched(const char *fmt, ...) int r; local_irq_save(flags); - buf = __get_cpu_var(printk_sched_buf); + buf = this_cpu_ptr(printk_sched_buf); va_start(args, fmt); r = vsnprintf(buf, PRINTK_BUF_SIZE, fmt, args); va_end(args); __this_cpu_or(printk_pending, PRINTK_PENDING_SCHED); - irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); local_irq_restore(flags); return r; Index: linux/kernel/smp.c =================================================================== --- linux.orig/kernel/smp.c 2013-09-19 15:16:05.428149660 -0500 +++ linux/kernel/smp.c 2013-09-19 15:16:05.424149701 -0500 @@ -175,7 +175,7 @@ void generic_exec_single(int cpu, struct */ void generic_smp_call_function_single_interrupt(void) { - struct call_single_queue *q = &__get_cpu_var(call_single_queue); + struct call_single_queue *q = this_cpu_ptr(&call_single_queue); LIST_HEAD(list); /* @@ -243,7 +243,7 @@ int smp_call_function_single(int cpu, sm struct call_single_data *csd = &d; if (!wait) - csd = &__get_cpu_var(csd_data); + csd = this_cpu_ptr(&csd_data); csd_lock(csd); @@ -390,7 +390,7 @@ void smp_call_function_many(const struct return; } - cfd = &__get_cpu_var(cfd_data); + cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); cpumask_clear_cpu(this_cpu, cfd->cpumask); From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from qmta09.emeryville.ca.mail.comcast.net ([76.96.30.96]:60106 "EHLO qmta09.emeryville.ca.mail.comcast.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933440Ab3JOSID (ORCPT ); Tue, 15 Oct 2013 14:08:03 -0400 Message-ID: <20131015180054.785696220@linux.com> Date: Tue, 15 Oct 2013 12:59:02 -0500 From: Christoph Lameter Subject: [PATCH 10/10] kernel misc: Replace __get_cpu_var uses References: <20131015175852.122827685@linux.com> Content-Disposition: inline; filename=this_misc Sender: linux-arch-owner@vger.kernel.org List-ID: To: Tejun Heo Cc: akpm@linuxfoundation.org, linux-arch@vger.kernel.org, Steven Rostedt , linux-kernel@vger.kernel.org, Ingo Molnar , Peter Zijlstra Message-ID: <20131015175902.j1nXtyw904eFP6EEBaMez9BEtgGYcyVHMn_kTBM0p_M@z> __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) Signed-off-by: Christoph Lameter Index: linux/kernel/printk/printk.c =================================================================== --- linux.orig/kernel/printk/printk.c 2013-09-19 15:16:05.428149660 -0500 +++ linux/kernel/printk/printk.c 2013-09-19 15:16:05.404149909 -0500 @@ -2448,7 +2448,7 @@ static void wake_up_klogd_work_func(stru int pending = __this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_SCHED) { - char *buf = __get_cpu_var(printk_sched_buf); + char *buf = this_cpu_ptr(printk_sched_buf); printk(KERN_WARNING "[sched_delayed] %s", buf); } @@ -2466,7 +2466,7 @@ void wake_up_klogd(void) preempt_disable(); if (waitqueue_active(&log_wait)) { this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); - irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } @@ -2479,14 +2479,14 @@ int printk_sched(const char *fmt, ...) int r; local_irq_save(flags); - buf = __get_cpu_var(printk_sched_buf); + buf = this_cpu_ptr(printk_sched_buf); va_start(args, fmt); r = vsnprintf(buf, PRINTK_BUF_SIZE, fmt, args); va_end(args); __this_cpu_or(printk_pending, PRINTK_PENDING_SCHED); - irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); local_irq_restore(flags); return r; Index: linux/kernel/smp.c =================================================================== --- linux.orig/kernel/smp.c 2013-09-19 15:16:05.428149660 -0500 +++ linux/kernel/smp.c 2013-09-19 15:16:05.424149701 -0500 @@ -175,7 +175,7 @@ void generic_exec_single(int cpu, struct */ void generic_smp_call_function_single_interrupt(void) { - struct call_single_queue *q = &__get_cpu_var(call_single_queue); + struct call_single_queue *q = this_cpu_ptr(&call_single_queue); LIST_HEAD(list); /* @@ -243,7 +243,7 @@ int smp_call_function_single(int cpu, sm struct call_single_data *csd = &d; if (!wait) - csd = &__get_cpu_var(csd_data); + csd = this_cpu_ptr(&csd_data); csd_lock(csd); @@ -390,7 +390,7 @@ void smp_call_function_many(const struct return; } - cfd = &__get_cpu_var(cfd_data); + cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); cpumask_clear_cpu(this_cpu, cfd->cpumask);