Merge branch 'for-2.6.23' of master.kernel.org:/pub/scm/linux/kernel/…

…git/arnd/cell-2.6

* 'for-2.6.23' of master.kernel.org:/pub/scm/linux/kernel/git/arnd/cell-2.6: (37 commits)
  [CELL] spufs: rework list management and associated locking
  [CELL] oprofile: add support to OProfile for profiling CELL BE SPUs
  [CELL] oprofile: enable SPU switch notification to detect currently active SPU tasks
  [CELL] spu_base: locking cleanup
  [CELL] cell: indexing of SPUs based on firmware vicinity properties
  [CELL] spufs: integration of SPE affinity with the scheduller
  [CELL] cell: add placement computation for scheduling of affinity contexts
  [CELL] spufs: extension of spu_create to support affinity definition
  [CELL] cell: add hardcoded spu vicinity information for QS20
  [CELL] cell: add vicinity information on spus
  [CELL] cell: add per BE structure with info about its SPUs
  [CELL] spufs: use find_first_bit() instead of sched_find_first_bit()
  [CELL] spufs: remove unused file argument from spufs_run_spu()
  [CELL] spufs: change decrementer restore timing
  [CELL] spufs: dont halt decrementer at restore step 47
  [CELL] spufs: limit saving MFC_CNTL bits
  [CELL] spufs: fix read and write for decr_status file
  [CELL] spufs: fix decr_status meanings
  [CELL] spufs: remove needless context save/restore code
  [CELL] spufs: fix array size of channel index
  ...

arch/powerpc/configs/cell_defconfig

@@ -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/crash.c

@@ -219,6 +219,72 @@ void crash_kexec_secondary(struct pt_regs *regs)
 	cpus_in_sr = CPU_MASK_NONE;
 }
 #endif
+#ifdef CONFIG_SPU_BASE
+
+#include <asm/spu.h>
+#include <asm/spu_priv1.h>
+
+struct crash_spu_info {
+	struct spu *spu;
+	u32 saved_spu_runcntl_RW;
+	u32 saved_spu_status_R;
+	u32 saved_spu_npc_RW;
+	u64 saved_mfc_sr1_RW;
+	u64 saved_mfc_dar;
+	u64 saved_mfc_dsisr;
+};
+
+#define CRASH_NUM_SPUS	16	/* Enough for current hardware */
+static struct crash_spu_info crash_spu_info[CRASH_NUM_SPUS];
+
+static void crash_kexec_stop_spus(void)
+{
+	struct spu *spu;
+	int i;
+	u64 tmp;
+
+	for (i = 0; i < CRASH_NUM_SPUS; i++) {
+		if (!crash_spu_info[i].spu)
+			continue;
+
+		spu = crash_spu_info[i].spu;
+
+		crash_spu_info[i].saved_spu_runcntl_RW =
+			in_be32(&spu->problem->spu_runcntl_RW);
+		crash_spu_info[i].saved_spu_status_R =
+			in_be32(&spu->problem->spu_status_R);
+		crash_spu_info[i].saved_spu_npc_RW =
+			in_be32(&spu->problem->spu_npc_RW);
+
+		crash_spu_info[i].saved_mfc_dar    = spu_mfc_dar_get(spu);
+		crash_spu_info[i].saved_mfc_dsisr  = spu_mfc_dsisr_get(spu);
+		tmp = spu_mfc_sr1_get(spu);
+		crash_spu_info[i].saved_mfc_sr1_RW = tmp;
+
+		tmp &= ~MFC_STATE1_MASTER_RUN_CONTROL_MASK;
+		spu_mfc_sr1_set(spu, tmp);
+
+		__delay(200);
+	}
+}
+
+void crash_register_spus(struct list_head *list)
+{
+	struct spu *spu;
+
+	list_for_each_entry(spu, list, full_list) {
+		if (WARN_ON(spu->number >= CRASH_NUM_SPUS))
+			continue;
+
+		crash_spu_info[spu->number].spu = spu;
+	}
+}
+
+#else
+static inline void crash_kexec_stop_spus(void)
+{
+}
+#endif /* CONFIG_SPU_BASE */
 
 void default_machine_crash_shutdown(struct pt_regs *regs)
 {
@@ -254,6 +320,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	crash_save_cpu(regs, crashing_cpu);
 	crash_kexec_prepare_cpus(crashing_cpu);
 	cpu_set(crashing_cpu, cpus_in_crash);
+	crash_kexec_stop_spus();
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(1, 0);
 }

arch/powerpc/kernel/time.c

@@ -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

@@ -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

@@ -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

@@ -0,0 +1,97 @@
+ /*
+ * Cell Broadband Engine OProfile Support
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Author: Maynard Johnson <[email protected]>
+ *
+ * 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 */