Commit 1474855d authored by Bob Nelson's avatar Bob Nelson Committed by Arnd Bergmann
Browse files

[CELL] oprofile: add support to OProfile for profiling CELL BE SPUs 



From: Maynard Johnson <mpjohn@us.ibm.com>

This patch updates the existing arch/powerpc/oprofile/op_model_cell.c
to add in the SPU profiling capabilities.  In addition, a 'cell' subdirectory
was added to arch/powerpc/oprofile to hold Cell-specific SPU profiling code.
Exports spu_set_profile_private_kref and spu_get_profile_private_kref which
are used by OProfile to store private profile information in spufs data
structures.

Also incorporated several fixes from other patches (rrn).  Check pointer
returned from kzalloc.  Eliminated unnecessary cast.  Better error
handling and cleanup in the related area.  64-bit unsigned long parameter
was being demoted to 32-bit unsigned int and eventually promoted back to
unsigned long.

Signed-off-by: default avatarCarl Love <carll@us.ibm.com>
Signed-off-by: default avatarMaynard Johnson <mpjohn@us.ibm.com>
Signed-off-by: default avatarBob Nelson <rrnelson@us.ibm.com>
Signed-off-by: default avatarArnd Bergmann <arnd.bergmann@de.ibm.com>
Acked-by: default avatarPaul Mackerras <paulus@samba.org>
parent 36aaccc1

arch/powerpc/configs/cell_defconfig

+2 −1
Original line number Diff line number Diff line
@@ -1455,7 +1455,8 @@ CONFIG_HAS_DMA=y 
# Instrumentation Support

#

CONFIG_PROFILING=y

CONFIG_OPROFILE=y

CONFIG_OPROFILE=m

CONFIG_OPROFILE_CELL=y

# CONFIG_KPROBES is not set



#

arch/powerpc/kernel/time.c

+1 −0
Original line number Diff line number Diff line
@@ -122,6 +122,7 @@ extern struct timezone sys_tz; 
static long timezone_offset;



unsigned long ppc_proc_freq;

EXPORT_SYMBOL(ppc_proc_freq);

unsigned long ppc_tb_freq;



static u64 tb_last_jiffy __cacheline_aligned_in_smp;

arch/powerpc/oprofile/Kconfig

+7 −0
Original line number Diff line number Diff line
@@ -15,3 +15,10 @@ config OPROFILE 


	  If unsure, say N.



config OPROFILE_CELL

	bool "OProfile for Cell Broadband Engine"

	depends on (SPU_FS = y && OPROFILE = m) || (SPU_FS = y && OPROFILE = y) || (SPU_FS = m && OPROFILE = m)

	default y

	help

	  Profiling of Cell BE SPUs requires special support enabled

	  by this option.

arch/powerpc/oprofile/Makefile

+3 −1
Original line number Diff line number Diff line
@@ -11,7 +11,9 @@ DRIVER_OBJS := $(addprefix ../../../drivers/oprofile/, \ 
		timer_int.o )



oprofile-y := $(DRIVER_OBJS) common.o backtrace.o

oprofile-$(CONFIG_PPC_CELL_NATIVE) += op_model_cell.o

oprofile-$(CONFIG_OPROFILE_CELL) += op_model_cell.o \

		cell/spu_profiler.o cell/vma_map.o \

		cell/spu_task_sync.o

oprofile-$(CONFIG_PPC64) += op_model_rs64.o op_model_power4.o op_model_pa6t.o

oprofile-$(CONFIG_FSL_BOOKE) += op_model_fsl_booke.o

oprofile-$(CONFIG_6xx) += op_model_7450.o

arch/powerpc/oprofile/cell/pr_util.h

0 → 100644
+97 −0
Original line number Diff line number Diff line 
 /*

 * Cell Broadband Engine OProfile Support

 *

 * (C) Copyright IBM Corporation 2006

 *

 * Author: Maynard Johnson <maynardj@us.ibm.com>

 *

 * This program is free software; you can redistribute it and/or

 * modify it under the terms of the GNU General Public License

 * as published by the Free Software Foundation; either version

 * 2 of the License, or (at your option) any later version.

 */



#ifndef PR_UTIL_H

#define PR_UTIL_H



#include <linux/cpumask.h>

#include <linux/oprofile.h>

#include <asm/cell-pmu.h>

#include <asm/spu.h>



#include "../../platforms/cell/cbe_regs.h"



/* Defines used for sync_start */

#define SKIP_GENERIC_SYNC 0

#define SYNC_START_ERROR -1

#define DO_GENERIC_SYNC 1



struct spu_overlay_info {	/* map of sections within an SPU overlay */

	unsigned int vma;	/* SPU virtual memory address from elf */

	unsigned int size;	/* size of section from elf */

	unsigned int offset;	/* offset of section into elf file */

	unsigned int buf;

};



struct vma_to_fileoffset_map {	/* map of sections within an SPU program */

	struct vma_to_fileoffset_map *next;	/* list pointer */

	unsigned int vma;	/* SPU virtual memory address from elf */

	unsigned int size;	/* size of section from elf */

	unsigned int offset;	/* offset of section into elf file */

	unsigned int guard_ptr;

	unsigned int guard_val;

        /*

	 * The guard pointer is an entry in the _ovly_buf_table,

	 * computed using ovly.buf as the index into the table.  Since

	 * ovly.buf values begin at '1' to reference the first (or 0th)

	 * entry in the _ovly_buf_table, the computation subtracts 1

	 * from ovly.buf.

	 * The guard value is stored in the _ovly_buf_table entry and

	 * is an index (starting at 1) back to the _ovly_table entry

	 * that is pointing at this _ovly_buf_table entry.  So, for

	 * example, for an overlay scenario with one overlay segment

	 * and two overlay sections:

	 *      - Section 1 points to the first entry of the

	 *        _ovly_buf_table, which contains a guard value

	 *        of '1', referencing the first (index=0) entry of

	 *        _ovly_table.

	 *      - Section 2 points to the second entry of the

	 *        _ovly_buf_table, which contains a guard value

	 *        of '2', referencing the second (index=1) entry of

	 *        _ovly_table.

	 */



};



/* The three functions below are for maintaining and accessing

 * the vma-to-fileoffset map.

 */

struct vma_to_fileoffset_map *create_vma_map(const struct spu *spu,

					     u64 objectid);

unsigned int vma_map_lookup(struct vma_to_fileoffset_map *map,

			    unsigned int vma, const struct spu *aSpu,

			    int *grd_val);

void vma_map_free(struct vma_to_fileoffset_map *map);



/*

 * Entry point for SPU profiling.

 * cycles_reset is the SPU_CYCLES count value specified by the user.

 */

int start_spu_profiling(unsigned int cycles_reset);



void stop_spu_profiling(void);





/* add the necessary profiling hooks */

int spu_sync_start(void);



/* remove the hooks */

int spu_sync_stop(void);



/* Record SPU program counter samples to the oprofile event buffer. */

void spu_sync_buffer(int spu_num, unsigned int *samples,

		     int num_samples);



void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_reset);



#endif	  /* PR_UTIL_H */

CRA Git | Maintained and supported by SUSTech CRA and CCSE