From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757213AbYLKQxV (ORCPT ); Thu, 11 Dec 2008 11:53:21 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755988AbYLKQtQ (ORCPT ); Thu, 11 Dec 2008 11:49:16 -0500 Received: from outbound-dub.frontbridge.com ([213.199.154.16]:24095 "EHLO IE1EHSOBE005.bigfish.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757206AbYLKQtN (ORCPT ); Thu, 11 Dec 2008 11:49:13 -0500 X-BigFish: VPS3(zzzzzzz32i43j65h) X-Spam-TCS-SCL: 4:0 X-WSS-ID: 0KBQ1DJ-02-VNH-01 From: Robert Richter To: LKML CC: oprofile-list , Ingo Molnar , Steven Rostedt , Robert Richter Subject: [PATCH 3/9] oprofile: adding cpu_buffer_entries() Date: Thu, 11 Dec 2008 17:41:57 +0100 Message-ID: <1229013723-8191-4-git-send-email-robert.richter@amd.com> X-Mailer: git-send-email 1.6.0.1 In-Reply-To: <1229013723-8191-1-git-send-email-robert.richter@amd.com> References: <1229013723-8191-1-git-send-email-robert.richter@amd.com> X-OriginalArrivalTime: 11 Dec 2008 16:48:57.0009 (UTC) FILETIME=[5BD90210:01C95BB0] MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This is in preparation for changes in the cpu buffer implementation. Signed-off-by: Robert Richter --- drivers/oprofile/buffer_sync.c | 31 ++----------------------------- drivers/oprofile/cpu_buffer.h | 27 +++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 29 deletions(-) diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c index 44f676c..aed286c 100644 --- a/drivers/oprofile/buffer_sync.c +++ b/drivers/oprofile/buffer_sync.c @@ -464,33 +464,6 @@ static inline int is_code(unsigned long val) } -/* "acquire" as many cpu buffer slots as we can */ -static unsigned long get_slots(struct oprofile_cpu_buffer *b) -{ - unsigned long head = b->head_pos; - unsigned long tail = b->tail_pos; - - /* - * Subtle. This resets the persistent last_task - * and in_kernel values used for switching notes. - * BUT, there is a small window between reading - * head_pos, and this call, that means samples - * can appear at the new head position, but not - * be prefixed with the notes for switching - * kernel mode or a task switch. This small hole - * can lead to mis-attribution or samples where - * we don't know if it's in the kernel or not, - * at the start of an event buffer. - */ - cpu_buffer_reset(b); - - if (head >= tail) - return head - tail; - - return head + (b->buffer_size - tail); -} - - /* Move tasks along towards death. Any tasks on dead_tasks * will definitely have no remaining references in any * CPU buffers at this point, because we use two lists, @@ -576,11 +549,11 @@ void sync_buffer(int cpu) /* Remember, only we can modify tail_pos */ #ifndef CONFIG_OPROFILE_IBS - available = get_slots(cpu_buf); + available = cpu_buffer_entries(cpu_buf); for (i = 0; i < available; ++i) { #else - while (get_slots(cpu_buf)) { + while (cpu_buffer_entries(cpu_buf)) { #endif struct op_sample *s = cpu_buffer_read_entry(cpu_buf); diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h index e608976..6055b56 100644 --- a/drivers/oprofile/cpu_buffer.h +++ b/drivers/oprofile/cpu_buffer.h @@ -81,6 +81,33 @@ struct op_sample *cpu_buffer_read_entry(struct oprofile_cpu_buffer *cpu_buf) return &cpu_buf->buffer[cpu_buf->tail_pos]; } +/* "acquire" as many cpu buffer slots as we can */ +static inline +unsigned long cpu_buffer_entries(struct oprofile_cpu_buffer *b) +{ + unsigned long head = b->head_pos; + unsigned long tail = b->tail_pos; + + /* + * Subtle. This resets the persistent last_task + * and in_kernel values used for switching notes. + * BUT, there is a small window between reading + * head_pos, and this call, that means samples + * can appear at the new head position, but not + * be prefixed with the notes for switching + * kernel mode or a task switch. This small hole + * can lead to mis-attribution or samples where + * we don't know if it's in the kernel or not, + * at the start of an event buffer. + */ + cpu_buffer_reset(b); + + if (head >= tail) + return head - tail; + + return head + (b->buffer_size - tail); +} + /* transient events for the CPU buffer -> event buffer */ #define CPU_IS_KERNEL 1 #define CPU_TRACE_BEGIN 2 -- 1.6.0.1