* [patch 0/5] cell patches for 2.6.23
@ 2007-06-18 22:42 Arnd Bergmann
2007-06-18 22:42 ` [patch 1/5] Enable SPU switch notification to detect currently active SPU tasks Arnd Bergmann
` (5 more replies)
0 siblings, 6 replies; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-18 22:42 UTC (permalink / raw)
To: linuxppc-dev
Hi Paul,
These are some patches I'd like to get merged for 2.6.23. They
have all been reviewed on either powerpc-dev or cbe-oss-dev and
I hope that all comments have been addressed.
My patch queue also has one patch from Christian Krafft that I
think needs some more work and I'll send that when it's ready.
The remaining pending patches I have are all spufs related, so
I'll work with Jeremy to get them merged.
If no further complaints come in regarding these five patches,
please pull from
git://git.kernel.org/pub/scm/linux/kernel/git/arnd/cell-2.6 for-2.6.23
Arnd <><
^ permalink raw reply [flat|nested] 12+ messages in thread
* [patch 1/5] Enable SPU switch notification to detect currently active SPU tasks.
2007-06-18 22:42 [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
@ 2007-06-18 22:42 ` Arnd Bergmann
2007-06-18 22:42 ` [patch 2/5] Add support to OProfile for profiling Cell/B.E. SPUs Arnd Bergmann
` (4 subsequent siblings)
5 siblings, 0 replies; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-18 22:42 UTC (permalink / raw)
To: linuxppc-dev
From: Maynard Johnson <mpjohn@us.ibm.com>
This patch adds to the capability of spu_switch_event_register so that the
caller is also notified of currently active SPU tasks. It also exports
spu_switch_event_register and spu_switch_event_unregister.
Signed-off-by: Maynard Johnson <mpjohn@us.ibm.com>
Signed-off-by: Carl Love <carll@us.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Index: linux-2.6/arch/powerpc/platforms/cell/spufs/sched.c
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/cell/spufs/sched.c
+++ linux-2.6/arch/powerpc/platforms/cell/spufs/sched.c
@@ -119,21 +119,47 @@ static void spu_remove_from_active_list(
static BLOCKING_NOTIFIER_HEAD(spu_switch_notifier);
-static void spu_switch_notify(struct spu *spu, struct spu_context *ctx)
+void spu_switch_notify(struct spu *spu, struct spu_context *ctx)
{
blocking_notifier_call_chain(&spu_switch_notifier,
ctx ? ctx->object_id : 0, spu);
}
+static void notify_spus_active(void)
+{
+ int node;
+ /* Wake up the active spu_contexts. When the awakened processes
+ * see their "notify_active" flag is set, they will call
+ * spu_switch_notify();
+ */
+ for (node = 0; node < MAX_NUMNODES; node++) {
+ struct spu *spu;
+ mutex_lock(&spu_prio->active_mutex[node]);
+ list_for_each_entry(spu, &spu_prio->active_list[node], list) {
+ struct spu_context *ctx = spu->ctx;
+ set_bit(SPU_SCHED_NOTIFY_ACTIVE, &ctx->sched_flags);
+ mb();
+ wake_up_all(&ctx->stop_wq);
+ }
+ mutex_unlock(&spu_prio->active_mutex[node]);
+ }
+}
+
int spu_switch_event_register(struct notifier_block * n)
{
- return blocking_notifier_chain_register(&spu_switch_notifier, n);
+ int ret;
+ ret = blocking_notifier_chain_register(&spu_switch_notifier, n);
+ if (!ret)
+ notify_spus_active();
+ return ret;
}
+EXPORT_SYMBOL_GPL(spu_switch_event_register);
int spu_switch_event_unregister(struct notifier_block * n)
{
return blocking_notifier_chain_unregister(&spu_switch_notifier, n);
}
+EXPORT_SYMBOL_GPL(spu_switch_event_unregister);
/**
* spu_bind_context - bind spu context to physical spu
Index: linux-2.6/arch/powerpc/platforms/cell/spufs/spufs.h
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/cell/spufs/spufs.h
+++ linux-2.6/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -42,6 +42,7 @@ struct spu_gang;
/* ctx->sched_flags */
enum {
SPU_SCHED_EXITING = 0,
+ SPU_SCHED_NOTIFY_ACTIVE,
};
struct spu_context {
@@ -202,6 +203,7 @@ void spu_acquire_saved(struct spu_contex
int spu_activate(struct spu_context *ctx, unsigned long flags);
void spu_deactivate(struct spu_context *ctx);
void spu_yield(struct spu_context *ctx);
+void spu_switch_notify(struct spu *spu, struct spu_context *ctx);
void spu_start_tick(struct spu_context *ctx);
void spu_stop_tick(struct spu_context *ctx);
void spu_sched_tick(struct work_struct *work);
Index: linux-2.6/arch/powerpc/platforms/cell/spufs/run.c
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/cell/spufs/run.c
+++ linux-2.6/arch/powerpc/platforms/cell/spufs/run.c
@@ -24,9 +24,11 @@ static inline int spu_stopped(struct spu
u64 pte_fault;
*stat = ctx->ops->status_read(ctx);
- if (ctx->state != SPU_STATE_RUNNABLE)
- return 1;
+
spu = ctx->spu;
+ if (ctx->state != SPU_STATE_RUNNABLE ||
+ test_bit(SPU_SCHED_NOTIFY_ACTIVE, &ctx->sched_flags))
+ return 1;
pte_fault = spu->dsisr &
(MFC_DSISR_PTE_NOT_FOUND | MFC_DSISR_ACCESS_DENIED);
return (!(*stat & 0x1) || pte_fault || spu->class_0_pending) ? 1 : 0;
@@ -294,6 +296,7 @@ long spufs_run_spu(struct file *file, st
u32 *npc, u32 *event)
{
int ret;
+ struct spu * spu;
u32 status;
if (mutex_lock_interruptible(&ctx->run_mutex))
@@ -314,8 +317,17 @@ long spufs_run_spu(struct file *file, st
do {
ret = spufs_wait(ctx->stop_wq, spu_stopped(ctx, &status));
+ spu = ctx->spu;
if (unlikely(ret))
break;
+ if (unlikely(test_bit(SPU_SCHED_NOTIFY_ACTIVE,
+ &ctx->sched_flags))) {
+ clear_bit(SPU_SCHED_NOTIFY_ACTIVE, &ctx->sched_flags);
+ if (!(status & SPU_STATUS_STOPPED_BY_STOP)) {
+ spu_switch_notify(spu, ctx);
+ continue;
+ }
+ }
if ((status & SPU_STATUS_STOPPED_BY_STOP) &&
(status >> SPU_STOP_STATUS_SHIFT == 0x2104)) {
ret = spu_process_callback(ctx);
--
^ permalink raw reply [flat|nested] 12+ messages in thread
* [patch 2/5] Add support to OProfile for profiling Cell/B.E. SPUs
2007-06-18 22:42 [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
2007-06-18 22:42 ` [patch 1/5] Enable SPU switch notification to detect currently active SPU tasks Arnd Bergmann
@ 2007-06-18 22:42 ` Arnd Bergmann
2007-06-20 2:32 ` [Cbe-oss-dev] " mita
2007-06-18 22:42 ` [patch 3/5] cell: updated driver for DDR2 memory on AXON Arnd Bergmann
` (3 subsequent siblings)
5 siblings, 1 reply; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-18 22:42 UTC (permalink / raw)
To: linuxppc-dev
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.
Signed-off-by: Carl Love <carll@us.ibm.com>
Signed-off-by: Maynard Johnson <mpjohn@us.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Index: linux-2.6/arch/powerpc/configs/cell_defconfig
===================================================================
--- linux-2.6.orig/arch/powerpc/configs/cell_defconfig
+++ linux-2.6/arch/powerpc/configs/cell_defconfig
@@ -1492,7 +1492,8 @@ CONFIG_HAS_IOPORT=y
# Instrumentation Support
#
CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
+CONFIG_OPROFILE=m
+CONFIG_OPROFILE_CELL=y
# CONFIG_KPROBES is not set
#
Index: linux-2.6/arch/powerpc/oprofile/cell/pr_util.h
===================================================================
--- /dev/null
+++ linux-2.6/arch/powerpc/oprofile/cell/pr_util.h
@@ -0,0 +1,90 @@
+ /*
+ * 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"
+
+static inline int number_of_online_nodes(void)
+{
+ u32 cpu; u32 tmp;
+ int nodes = 0;
+ for_each_online_cpu(cpu) {
+ tmp = cbe_cpu_to_node(cpu) + 1;
+ if (tmp > nodes)
+ nodes++;
+ }
+ return nodes;
+}
+
+/* Defines used for sync_start */
+#define SKIP_GENERIC_SYNC 0
+#define SYNC_START_ERROR -1
+#define DO_GENERIC_SYNC 1
+
+struct spu_overlay_info
+{
+ unsigned int vma;
+ unsigned int size;
+ unsigned int offset;
+ unsigned int buf;
+};
+
+struct vma_to_fileoffset_map
+{
+ struct vma_to_fileoffset_map *next;
+ unsigned int vma;
+ unsigned int size;
+ unsigned int offset;
+ unsigned int guard_ptr;
+ unsigned int guard_val;
+};
+
+/* 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.
+ */
+void 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_profiling_frequency(unsigned int freq_khz, unsigned int cycles_reset);
+
+#endif // PR_UTIL_H
Index: linux-2.6/arch/powerpc/oprofile/cell/spu_profiler.c
===================================================================
--- /dev/null
+++ linux-2.6/arch/powerpc/oprofile/cell/spu_profiler.c
@@ -0,0 +1,220 @@
+/*
+ * Cell Broadband Engine OProfile Support
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Authors: Maynard Johnson <maynardj@us.ibm.com>
+ * Carl Love <carll@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.
+ */
+
+#include <linux/hrtimer.h>
+#include <linux/smp.h>
+#include <linux/slab.h>
+#include <asm/cell-pmu.h>
+#include <asm/time.h>
+#include "pr_util.h"
+
+#define TRACE_ARRAY_SIZE 1024
+#define SCALE_SHIFT 14
+
+static u32 * samples;
+
+static int spu_prof_running = 0;
+static unsigned int profiling_interval = 0;
+
+extern int spu_prof_num_nodes;
+
+
+#define NUM_SPU_BITS_TRBUF 16
+#define SPUS_PER_TB_ENTRY 4
+#define SPUS_PER_NODE 8
+
+#define SPU_PC_MASK 0xFFFF
+
+static spinlock_t sample_array_lock=SPIN_LOCK_UNLOCKED;
+unsigned long sample_array_lock_flags;
+
+void set_profiling_frequency(unsigned int freq_khz, unsigned int cycles_reset)
+{
+ unsigned long nsPerCyc;
+ if (!freq_khz)
+ freq_khz = ppc_proc_freq/1000;
+
+ /* To calculate a timeout in nanoseconds, the basic
+ * formula is ns = cycles_reset * (NSEC_PER_SEC / cpu frequency).
+ * To avoid floating point math, we use the scale math
+ * technique as described in linux/jiffies.h. We use
+ * a scale factor of SCALE_SHIFT,which provides 4 decimal places
+ * of precision, which is close enough for the purpose at hand.
+ *
+ * The value of the timeout should be small enough that the hw
+ * trace buffer will not get more then a bout 1/3 full for the
+ * maximum user specified (the LFSR value) hw sampling frequency.
+ * This is to ensure the trace buffer will never fill even if the
+ * kernel thread scheduling varies under a heavey system load.
+ */
+
+ nsPerCyc = (USEC_PER_SEC << SCALE_SHIFT)/freq_khz;
+ profiling_interval = (nsPerCyc * cycles_reset) >> SCALE_SHIFT;
+
+}
+
+/*
+ * Extract SPU PC from trace buffer entry
+ */
+static void spu_pc_extract(int cpu, int entry)
+{
+ /* the trace buffer is 128 bits */
+ u64 trace_buffer[2];
+ u64 spu_mask;
+ int spu;
+
+ spu_mask = SPU_PC_MASK;
+
+ /* Each SPU PC is 16 bits; hence, four spus in each of
+ * the two 64-bit buffer entries that make up the
+ * 128-bit trace_buffer entry. Process two 64-bit values
+ * simultaneously.
+ * trace[0] SPU PC contents are: 0 1 2 3
+ * trace[1] SPU PC contents are: 4 5 6 7
+ */
+
+ cbe_read_trace_buffer(cpu, trace_buffer);
+
+ for (spu = SPUS_PER_TB_ENTRY-1; spu >= 0; spu--) {
+ /* spu PC trace entry is upper 16 bits of the
+ * 18 bit SPU program counter
+ */
+ samples[spu * TRACE_ARRAY_SIZE + entry]
+ = (spu_mask & trace_buffer[0]) << 2;
+ samples[(spu + SPUS_PER_TB_ENTRY) * TRACE_ARRAY_SIZE + entry]
+ = (spu_mask & trace_buffer[1]) << 2;
+
+ trace_buffer[0] = trace_buffer[0] >> NUM_SPU_BITS_TRBUF;
+ trace_buffer[1] = trace_buffer[1] >> NUM_SPU_BITS_TRBUF;
+ }
+}
+
+static int cell_spu_pc_collection(int cpu)
+{
+ u32 trace_addr;
+ int entry;
+
+ /* process the collected SPU PC for the node */
+
+ entry = 0;
+
+ trace_addr = cbe_read_pm(cpu, trace_address);
+ while (!(trace_addr & CBE_PM_TRACE_BUF_EMPTY))
+ {
+ /* there is data in the trace buffer to process */
+ spu_pc_extract(cpu, entry);
+
+ entry++;
+
+ if (entry >= TRACE_ARRAY_SIZE)
+ /* spu_samples is full */
+ break;
+
+ trace_addr = cbe_read_pm(cpu, trace_address);
+ }
+
+ return(entry);
+}
+
+
+static enum hrtimer_restart profile_spus(struct hrtimer * timer)
+{
+ ktime_t kt;
+ int cpu, node, k, num_samples, spu_num;
+
+ if (!spu_prof_running)
+ goto stop;
+
+ for_each_online_cpu(cpu) {
+ if (cbe_get_hw_thread_id(cpu))
+ continue;
+
+ node = cbe_cpu_to_node(cpu);
+
+ /* There should only be on kernel thread at a time processing
+ * the samples. In the very unlikely case that the processing
+ * is taking a very long time and multiple kernel threads are
+ * started to process the samples. Make sure only one kernel
+ * thread is working on the samples array at a time. The
+ * sample array must be loaded and then processed for a given
+ * cpu. The sample array is not per cpu.
+ */
+ spin_lock_irqsave(&sample_array_lock,
+ sample_array_lock_flags);
+ num_samples = cell_spu_pc_collection(cpu);
+
+ if (num_samples == 0) {
+ spin_unlock_irqrestore(&sample_array_lock,
+ sample_array_lock_flags);
+ continue;
+ }
+
+ for (k = 0; k < SPUS_PER_NODE; k++) {
+ spu_num = k + (node * SPUS_PER_NODE);
+ spu_sync_buffer(spu_num,
+ samples + (k * TRACE_ARRAY_SIZE),
+ num_samples);
+ }
+
+ spin_unlock_irqrestore(&sample_array_lock,
+ sample_array_lock_flags);
+
+ }
+ smp_wmb();
+
+ kt = ktime_set(0, profiling_interval);
+ if (!spu_prof_running)
+ goto stop;
+ hrtimer_forward(timer, timer->base->get_time(), kt);
+ return HRTIMER_RESTART;
+
+ stop:
+ printk(KERN_INFO "SPU_PROF: spu-prof timer ending\n");
+ return HRTIMER_NORESTART;
+}
+
+static struct hrtimer timer;
+/*
+ * Entry point for SPU profiling.
+ * NOTE: SPU profiling is done system-wide, not per-CPU.
+ *
+ * cycles_reset is the count value specified by the user when
+ * setting up OProfile to count SPU_CYCLES.
+ */
+void start_spu_profiling(unsigned int cycles_reset) {
+
+ ktime_t kt;
+
+ pr_debug("timer resolution: %lu\n",
+ TICK_NSEC);
+ kt = ktime_set(0, profiling_interval);
+ hrtimer_init(&timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ timer.expires = kt;
+ timer.function = profile_spus;
+
+ /* Allocate arrays for collecting SPU PC samples */
+ samples = (u32 *) kzalloc(SPUS_PER_NODE *
+ TRACE_ARRAY_SIZE * sizeof(u32), GFP_KERNEL);
+
+ spu_prof_running = 1;
+ hrtimer_start(&timer, kt, HRTIMER_MODE_REL);
+}
+
+void stop_spu_profiling(void)
+{
+ spu_prof_running = 0;
+ hrtimer_cancel(&timer);
+ kfree(samples);
+ pr_debug("SPU_PROF: stop_spu_profiling issued\n");
+}
Index: linux-2.6/arch/powerpc/oprofile/cell/spu_task_sync.c
===================================================================
--- /dev/null
+++ linux-2.6/arch/powerpc/oprofile/cell/spu_task_sync.c
@@ -0,0 +1,464 @@
+/*
+ * 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.
+ */
+
+/* The purpose of this file is to handle SPU event task switching
+ * and to record SPU context information into the OProfile
+ * event buffer.
+ *
+ * Additionally, the spu_sync_buffer function is provided as a helper
+ * for recoding actual SPU program counter samples to the event buffer.
+ */
+#include <linux/dcookies.h>
+#include <linux/kref.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/numa.h>
+#include <linux/oprofile.h>
+#include <linux/spinlock.h>
+#include "pr_util.h"
+
+#define RELEASE_ALL 9999
+
+static spinlock_t buffer_lock = SPIN_LOCK_UNLOCKED;
+static spinlock_t cache_lock = SPIN_LOCK_UNLOCKED;
+static int num_spu_nodes;
+int spu_prof_num_nodes;
+int last_guard_val[MAX_NUMNODES * 8];
+
+/* Container for caching information about an active SPU task. */
+struct cached_info {
+ struct vma_to_fileoffset_map * map;
+ struct spu * the_spu; /* needed to access pointer to local_store */
+ struct kref cache_ref;
+};
+
+static struct cached_info * spu_info[MAX_NUMNODES * 8];
+
+static void destroy_cached_info(struct kref * kref)
+{
+ struct cached_info * info;
+ info = container_of(kref, struct cached_info, cache_ref);
+ vma_map_free(info->map);
+ kfree(info);
+ module_put(THIS_MODULE);
+}
+
+/* Return the cached_info for the passed SPU number.
+ * ATTENTION: Callers are responsible for obtaining the
+ * cache_lock if needed prior to invoking this function.
+ */
+static struct cached_info * get_cached_info(struct spu * the_spu, int spu_num)
+{
+ struct kref * ref;
+ struct cached_info * ret_info;
+ if (spu_num >= num_spu_nodes) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: Invalid index %d into spu info cache\n",
+ __FUNCTION__, __LINE__, spu_num);
+ ret_info = NULL;
+ goto out;
+ }
+ if (!spu_info[spu_num] && the_spu) {
+ ref = spu_get_profile_private_kref(the_spu->ctx);
+ if (ref) {
+ spu_info[spu_num] = container_of(ref, struct cached_info, cache_ref);
+ kref_get(&spu_info[spu_num]->cache_ref);
+ }
+ }
+
+ ret_info = spu_info[spu_num];
+ out:
+ return ret_info;
+}
+
+
+/* Looks for cached info for the passed spu. If not found, the
+ * cached info is created for the passed spu.
+ * Returns 0 for success; otherwise, -1 for error.
+ */
+static int
+prepare_cached_spu_info(struct spu * spu, unsigned long objectId)
+{
+ unsigned long flags;
+ struct vma_to_fileoffset_map * new_map;
+ int retval = 0;
+ struct cached_info * info;
+
+ /* We won't bother getting cache_lock here since
+ * don't do anything with the cached_info that's returned.
+ */
+ info = get_cached_info(spu, spu->number);
+
+ if (info) {
+ pr_debug("Found cached SPU info.\n");
+ goto out;
+ }
+
+ /* Create cached_info and set spu_info[spu->number] to point to it.
+ * spu->number is a system-wide value, not a per-node value.
+ */
+ info = kzalloc(sizeof(struct cached_info), GFP_KERNEL);
+ if (!info) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: create vma_map failed\n",
+ __FUNCTION__, __LINE__);
+ retval = -ENOMEM;
+ goto err_alloc;
+ }
+ new_map = create_vma_map(spu, objectId);
+ if (!new_map) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: create vma_map failed\n",
+ __FUNCTION__, __LINE__);
+ retval = -ENOMEM;
+ goto err_alloc;
+ }
+
+ pr_debug("Created vma_map\n");
+ info->map = new_map;
+ info->the_spu = spu;
+ kref_init(&info->cache_ref);
+ spin_lock_irqsave(&cache_lock, flags);
+ spu_info[spu->number] = info;
+ /* Increment count before passing off ref to SPUFS. */
+ kref_get(&info->cache_ref);
+
+ /* We increment the module refcount here since SPUFS is
+ * responsible for the final destruction of the cached_info,
+ * and it must be able to access the destroy_cached_info()
+ * function defined in the OProfile module. We decrement
+ * the module refcount in destroy_cached_info.
+ */
+ try_module_get(THIS_MODULE);
+ spu_set_profile_private_kref(spu->ctx, &info->cache_ref,
+ destroy_cached_info);
+ spin_unlock_irqrestore(&cache_lock, flags);
+ goto out;
+
+err_alloc:
+ kfree(info);
+out:
+ return retval;
+}
+
+/*
+ * NOTE: The caller is responsible for locking the
+ * cache_lock prior to calling this function.
+ */
+static int release_cached_info(int spu_index)
+{
+ int index, end;
+ if (spu_index == RELEASE_ALL) {
+ end = num_spu_nodes;
+ index = 0;
+ } else {
+ if (spu_index >= num_spu_nodes) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: "
+ "Invalid index %d into spu info cache\n",
+ __FUNCTION__, __LINE__, spu_index);
+ goto out;
+ }
+ end = spu_index +1;
+ index = spu_index;
+ }
+ for (; index < end; index++) {
+ if (spu_info[index]) {
+ kref_put(&spu_info[index]->cache_ref,
+ destroy_cached_info);
+ spu_info[index] = NULL;
+ }
+ }
+
+out:
+ return 0;
+}
+
+/* The source code for fast_get_dcookie was "borrowed"
+ * from drivers/oprofile/buffer_sync.c.
+ */
+
+/* Optimisation. We can manage without taking the dcookie sem
+ * because we cannot reach this code without at least one
+ * dcookie user still being registered (namely, the reader
+ * of the event buffer).
+ */
+static inline unsigned long fast_get_dcookie(struct dentry * dentry,
+ struct vfsmount * vfsmnt)
+{
+ unsigned long cookie;
+
+ if (dentry->d_cookie)
+ return (unsigned long)dentry;
+ get_dcookie(dentry, vfsmnt, &cookie);
+ return cookie;
+}
+
+/* Look up the dcookie for the task's first VM_EXECUTABLE mapping,
+ * which corresponds loosely to "application name". Also, determine
+ * the offset for the SPU ELF object. If computed offset is
+ * non-zero, it implies an embedded SPU object; otherwise, it's a
+ * separate SPU binary, in which case we retrieve it's dcookie.
+ * For the embedded case, we must determine if SPU ELF is embedded
+ * in the executable application or another file (i.e., shared lib).
+ * If embedded in a shared lib, we must get the dcookie and return
+ * that to the caller.
+ */
+static unsigned long
+get_exec_dcookie_and_offset(struct spu * spu, unsigned int * offsetp,
+ unsigned long * spu_bin_dcookie,
+ unsigned long spu_ref)
+{
+ unsigned long app_cookie = 0;
+ unsigned int my_offset = 0;
+ struct file * app = NULL;
+ struct vm_area_struct * vma;
+ struct mm_struct * mm = spu->mm;
+
+ if (!mm)
+ goto out;
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (!vma->vm_file)
+ continue;
+ if (!(vma->vm_flags & VM_EXECUTABLE))
+ continue;
+ app_cookie = fast_get_dcookie(vma->vm_file->f_dentry,
+ vma->vm_file->f_vfsmnt);
+ pr_debug("got dcookie for %s\n",
+ vma->vm_file->f_dentry->d_name.name);
+ app = vma->vm_file;
+ break;
+ }
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (vma->vm_start > spu_ref || vma->vm_end <= spu_ref)
+ continue;
+ my_offset = spu_ref - vma->vm_start;
+ if (!vma->vm_file)
+ goto fail_no_image_cookie;
+
+ pr_debug("Found spu ELF at %X(object-id:%lx) for file %s\n",
+ my_offset, spu_ref,
+ vma->vm_file->f_dentry->d_name.name);
+ *offsetp = my_offset;
+ break;
+ }
+
+ *spu_bin_dcookie = fast_get_dcookie(vma->vm_file->f_dentry,
+ vma->vm_file->f_vfsmnt);
+ pr_debug("got dcookie for %s\n", vma->vm_file->f_dentry->d_name.name);
+
+out:
+ return app_cookie;
+
+fail_no_image_cookie:
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: Cannot find dcookie for SPU binary\n",
+ __FUNCTION__, __LINE__);
+ goto out;
+}
+
+
+
+/* This function finds or creates cached context information for the
+ * passed SPU and records SPU context information into the OProfile
+ * event buffer.
+ */
+static int process_context_switch(struct spu * spu, unsigned long objectId)
+{
+ unsigned long flags;
+ int retval;
+ unsigned int offset = 0;
+ unsigned long spu_cookie = 0, app_dcookie;
+
+ retval = prepare_cached_spu_info(spu, objectId);
+ if (retval)
+ goto out;
+
+ /* Get dcookie first because a mutex_lock is taken in that
+ * code path, so interrupts must not be disabled.
+ */
+ app_dcookie = get_exec_dcookie_and_offset(spu, &offset, &spu_cookie, objectId);
+ if (!app_dcookie || !spu_cookie) {
+ retval = -ENOENT;
+ goto out;
+ }
+
+ /* Record context info in event buffer */
+ spin_lock_irqsave(&buffer_lock, flags);
+ add_event_entry(ESCAPE_CODE);
+ add_event_entry(SPU_CTX_SWITCH_CODE);
+ add_event_entry(spu->number);
+ add_event_entry(spu->pid);
+ add_event_entry(spu->tgid);
+ add_event_entry(app_dcookie);
+ add_event_entry(spu_cookie);
+ add_event_entry(offset);
+ spin_unlock_irqrestore(&buffer_lock, flags);
+ smp_wmb();
+out:
+ return retval;
+}
+
+/*
+ * This function is invoked on either a bind_context or unbind_context.
+ * If called for an unbind_context, the val arg is 0; otherwise,
+ * it is the object-id value for the spu context.
+ * The data arg is of type 'struct spu *'.
+ */
+static int spu_active_notify(struct notifier_block * self, unsigned long val,
+ void * data)
+{
+ int retval;
+ unsigned long flags;
+ struct spu *the_spu = data;
+ pr_debug("SPU event notification arrived\n");
+ if (!val){
+ spin_lock_irqsave(&cache_lock, flags);
+ retval = release_cached_info(the_spu->number);
+ spin_unlock_irqrestore(&cache_lock, flags);
+ } else {
+ retval = process_context_switch(the_spu, val);
+ }
+ return retval;
+}
+
+static struct notifier_block spu_active = {
+ .notifier_call = spu_active_notify,
+};
+
+/* The main purpose of this function is to synchronize
+ * OProfile with SPUFS by registering to be notified of
+ * SPU task switches.
+ *
+ * NOTE: When profiling SPUs, we must ensure that only
+ * spu_sync_start is invoked and not the generic sync_start
+ * in drivers/oprofile/oprof.c. A return value of
+ * SKIP_GENERIC_SYNC or SYNC_START_ERROR will
+ * accomplish this.
+ */
+int spu_sync_start(void) {
+ int k;
+ int ret = SKIP_GENERIC_SYNC;
+ int register_ret;
+ unsigned long flags = 0;
+ spu_prof_num_nodes = number_of_online_nodes();
+ num_spu_nodes = spu_prof_num_nodes * 8;
+
+ spin_lock_irqsave(&buffer_lock, flags);
+ add_event_entry(ESCAPE_CODE);
+ add_event_entry(SPU_PROFILING_CODE);
+ add_event_entry(num_spu_nodes);
+ spin_unlock_irqrestore(&buffer_lock, flags);
+
+ /* Register for SPU events */
+ register_ret = spu_switch_event_register(&spu_active);
+ if (register_ret) {
+ ret = SYNC_START_ERROR;
+ goto out;
+ }
+
+ for (k = 0; k < (MAX_NUMNODES * 8); k++)
+ last_guard_val[k] = 0;
+ pr_debug("spu_sync_start -- running.\n");
+out:
+ return ret;
+}
+
+/* Record SPU program counter samples to the oprofile event buffer. */
+void spu_sync_buffer(int spu_num, unsigned int * samples,
+ int num_samples)
+{
+ unsigned long long file_offset;
+ unsigned long flags;
+ int i;
+ struct vma_to_fileoffset_map * map;
+ struct spu * the_spu;
+ unsigned long long spu_num_ll = spu_num;
+ unsigned long long spu_num_shifted = spu_num_ll << 32;
+ struct cached_info * c_info;
+
+ /* We need to obtain the cache_lock here because it's
+ * possible that after getting the cached_info, the SPU job
+ * corresponding to this cached_info may end, thus resulting
+ * in the destruction of the cached_info.
+ */
+ spin_lock_irqsave(&cache_lock, flags);
+ c_info = get_cached_info(NULL, spu_num);
+ if (!c_info) {
+ /* This legitimately happens when the SPU task ends before all
+ * samples are recorded. No big deal -- so we just drop a few samples.
+ */
+ pr_debug("SPU_PROF: No cached SPU contex "
+ "for SPU #%d. Dropping samples.\n", spu_num);
+ goto out;
+ }
+
+ map = c_info->map;
+ the_spu = c_info->the_spu;
+ spin_lock(&buffer_lock);
+ for (i = 0; i < num_samples; i++) {
+ unsigned int sample = *(samples+i);
+ int grd_val = 0;
+ file_offset = 0;
+ if (sample == 0)
+ continue;
+ file_offset = vma_map_lookup( map, sample, the_spu, &grd_val);
+
+ /* If overlays are used by this SPU application, the guard
+ * value is non-zero, indicating which overlay section is in
+ * use. We need to discard samples taken during the time
+ * period which an overlay occurs (i.e., guard value changes).
+ */
+ if (grd_val && grd_val != last_guard_val[spu_num]) {
+ last_guard_val[spu_num] = grd_val;
+ /* Drop the rest of the samples. */
+ break;
+ }
+
+ /* For now, we'll drop samples that can't be mapped.
+ * This can happen for generated stubs executed from
+ * the SPU stack. Do we need to record these somehow?
+ */
+ if (unlikely(file_offset == 0xffffffff))
+ continue;
+ add_event_entry(file_offset | spu_num_shifted);
+ }
+ spin_unlock(&buffer_lock);
+out:
+ spin_unlock_irqrestore(&cache_lock, flags);
+}
+
+
+int spu_sync_stop(void)
+{
+ unsigned long flags = 0;
+ int ret = spu_switch_event_unregister(&spu_active);
+ if (ret) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: spu_switch_event_unregister returned %d\n",
+ __FUNCTION__, __LINE__, ret);
+ goto out;
+ }
+
+ spin_lock_irqsave(&cache_lock, flags);
+ ret = release_cached_info(RELEASE_ALL);
+ spin_unlock_irqrestore(&cache_lock, flags);
+out:
+ pr_debug("spu_sync_stop -- done.\n");
+ return ret;
+}
+
+
Index: linux-2.6/arch/powerpc/oprofile/cell/vma_map.c
===================================================================
--- /dev/null
+++ linux-2.6/arch/powerpc/oprofile/cell/vma_map.c
@@ -0,0 +1,279 @@
+ /*
+ * 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.
+ */
+
+/* The code in this source file is responsible for generating
+ * vma-to-fileOffset maps for both overlay and non-overlay SPU
+ * applications.
+ */
+
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/elf.h>
+#include "pr_util.h"
+
+
+void vma_map_free(struct vma_to_fileoffset_map *map)
+{
+ while (map) {
+ struct vma_to_fileoffset_map *next = map->next;
+ kfree(map);
+ map = next;
+ }
+}
+
+unsigned int
+vma_map_lookup(struct vma_to_fileoffset_map *map, unsigned int vma,
+ const struct spu * aSpu, int * grd_val)
+{
+ u32 offset = 0xffffffff;
+ u32 ovly_grd;
+ for (; map; map = map->next) {
+ if (vma < map->vma || vma >= map->vma + map->size)
+ continue;
+
+ if (map->guard_ptr) {
+ ovly_grd = *(u32 *)(aSpu->local_store + map->guard_ptr);
+ if (ovly_grd != map->guard_val)
+ continue;
+ *grd_val = ovly_grd;
+ }
+ offset = vma - map->vma + map->offset;
+ break;
+ }
+
+ return offset;
+}
+
+static struct vma_to_fileoffset_map *
+vma_map_add(struct vma_to_fileoffset_map * map, unsigned int vma,
+ unsigned int size, unsigned int offset, unsigned int guard_ptr,
+ unsigned int guard_val)
+{
+ struct vma_to_fileoffset_map * new =
+ kzalloc(sizeof(struct vma_to_fileoffset_map), GFP_KERNEL);
+ if (!new) {
+ printk(KERN_ERR "SPU_PROF: %s, line %d: malloc failed\n",
+ __FUNCTION__, __LINE__);
+ vma_map_free(map);
+ return NULL;
+ }
+
+ new->next = map;
+ new->vma = vma;
+ new->size = size;
+ new->offset = offset;
+ new->guard_ptr = guard_ptr;
+ new->guard_val = guard_val;
+
+ return new;
+}
+
+
+/* Parse SPE ELF header and generate a list of vma_maps.
+ * A pointer to the first vma_map in the generated list
+ * of vma_maps is returned. */
+struct vma_to_fileoffset_map * create_vma_map(const struct spu * aSpu,
+ unsigned long spu_elf_start)
+{
+ static const unsigned char expected[EI_PAD] = {
+ [EI_MAG0] = ELFMAG0,
+ [EI_MAG1] = ELFMAG1,
+ [EI_MAG2] = ELFMAG2,
+ [EI_MAG3] = ELFMAG3,
+ [EI_CLASS] = ELFCLASS32,
+ [EI_DATA] = ELFDATA2MSB,
+ [EI_VERSION] = EV_CURRENT,
+ [EI_OSABI] = ELFOSABI_NONE
+ };
+
+ int grd_val;
+ struct vma_to_fileoffset_map * map = NULL;
+ struct spu_overlay_info ovly;
+ unsigned int overlay_tbl_offset = -1;
+ unsigned long phdr_start, shdr_start;
+ Elf32_Ehdr ehdr;
+ Elf32_Phdr phdr;
+ Elf32_Shdr shdr, shdr_str;
+ Elf32_Sym sym;
+ int i, j;
+ char name[32];
+
+ unsigned int ovly_table_sym = 0;
+ unsigned int ovly_buf_table_sym = 0;
+ unsigned int ovly_table_end_sym = 0;
+ unsigned int ovly_buf_table_end_sym = 0;
+ unsigned long ovly_table;
+ unsigned int n_ovlys;
+
+ /* Get and validate ELF header. */
+
+ if (copy_from_user(&ehdr, (void *) spu_elf_start, sizeof (ehdr)))
+ goto fail;
+
+ if (memcmp(ehdr.e_ident, expected, EI_PAD) != 0) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: Unexpected e_ident parsing SPU ELF\n",
+ __FUNCTION__, __LINE__);
+ goto fail;
+ }
+ if (ehdr.e_machine != EM_SPU) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: Unexpected e_machine parsing SPU ELF\n",
+ __FUNCTION__, __LINE__);
+ goto fail;
+ }
+ if (ehdr.e_type != ET_EXEC) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: Unexpected e_type parsing SPU ELF\n",
+ __FUNCTION__, __LINE__);
+ goto fail;
+ }
+ phdr_start = spu_elf_start + ehdr.e_phoff;
+ shdr_start = spu_elf_start + ehdr.e_shoff;
+
+ /* Traverse program headers. */
+ for (i = 0; i < ehdr.e_phnum; i++) {
+ if (copy_from_user(&phdr,
+ (void *) (phdr_start + i * sizeof(phdr)),
+ sizeof(phdr)))
+ goto fail;
+
+ if (phdr.p_type != PT_LOAD)
+ continue;
+ if (phdr.p_flags & (1 << 27))
+ continue;
+
+ map = vma_map_add(map, phdr.p_vaddr, phdr.p_memsz,
+ phdr.p_offset, 0, 0);
+ if (!map)
+ goto fail;
+ }
+
+ pr_debug("SPU_PROF: Created non-overlay maps\n");
+ /* Traverse section table and search for overlay-related symbols. */
+ for (i = 0; i < ehdr.e_shnum; i++) {
+ if (copy_from_user(&shdr,
+ (void *) (shdr_start + i * sizeof(shdr)),
+ sizeof(shdr)))
+ goto fail;
+
+ if (shdr.sh_type != SHT_SYMTAB)
+ continue;
+ if (shdr.sh_entsize != sizeof (sym))
+ continue;
+
+ if (copy_from_user(&shdr_str,
+ (void *) (shdr_start + shdr.sh_link *
+ sizeof(shdr)),
+ sizeof(shdr)))
+ goto fail;
+
+ if (shdr_str.sh_type != SHT_STRTAB)
+ goto fail;;
+
+ for (j = 0; j < shdr.sh_size / sizeof (sym); j++) {
+ if (copy_from_user(&sym, (void *) (spu_elf_start +
+ shdr.sh_offset + j *
+ sizeof (sym)),
+ sizeof (sym)))
+ goto fail;
+
+ if (copy_from_user(name, (void *)
+ (spu_elf_start + shdr_str.sh_offset +
+ sym.st_name),
+ 20))
+ goto fail;
+
+ if (memcmp(name, "_ovly_table", 12) == 0)
+ ovly_table_sym = sym.st_value;
+ if (memcmp(name, "_ovly_buf_table", 16) == 0)
+ ovly_buf_table_sym = sym.st_value;
+ if (memcmp(name, "_ovly_table_end", 16) == 0)
+ ovly_table_end_sym = sym.st_value;
+ if (memcmp(name, "_ovly_buf_table_end", 20) == 0)
+ ovly_buf_table_end_sym = sym.st_value;
+ }
+ }
+
+ /* If we don't have overlays, we're done. */
+ if (ovly_table_sym == 0 || ovly_buf_table_sym == 0
+ || ovly_table_end_sym == 0 || ovly_buf_table_end_sym == 0) {
+ pr_debug("SPU_PROF: No overlay table found\n");
+ goto out;
+ }
+ else {
+ pr_debug("SPU_PROF: Overlay table found\n");
+ }
+
+ /* The _ovly_table symbol represents a table with one entry
+ * per overlay section. The _ovly_buf_table symbol represents
+ * a table with one entry per overlay region.
+ * The struct spu_overlay_info gives the structure of the _ovly_table
+ * entries. The structure of _ovly_table_buf is simply one
+ * u32 word per entry.
+ */
+ overlay_tbl_offset = vma_map_lookup(map, ovly_table_sym, aSpu, &grd_val);
+ if (overlay_tbl_offset < 0) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: Error finding SPU overlay table\n",
+ __FUNCTION__, __LINE__);
+ goto fail;
+ }
+ ovly_table = spu_elf_start + overlay_tbl_offset;
+
+ n_ovlys = (ovly_table_end_sym -
+ ovly_table_sym) / sizeof (ovly);
+
+ /* Traverse overlay table. */
+ for (i = 0; i < n_ovlys; i++) {
+ if (copy_from_user(&ovly, (void *)
+ (ovly_table + i * sizeof (ovly)),
+ sizeof (ovly)))
+ goto fail;
+
+ /* The ovly.vma/size/offset arguments are analogous to the same
+ * arguments used above for non-overlay maps. The final two
+ * args are referred to as the guard pointer and the guard
+ * value.
+ * 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.
+ */
+ map = vma_map_add(map, ovly.vma, ovly.size, ovly.offset,
+ ovly_buf_table_sym + (ovly.buf - 1) * 4, i + 1);
+ if (!map)
+ goto fail;
+ }
+ goto out;
+
+ fail:
+ map = NULL;
+ out:
+ return map;
+}
Index: linux-2.6/arch/powerpc/oprofile/common.c
===================================================================
--- linux-2.6.orig/arch/powerpc/oprofile/common.c
+++ linux-2.6/arch/powerpc/oprofile/common.c
@@ -29,6 +29,8 @@ static struct op_powerpc_model *model;
static struct op_counter_config ctr[OP_MAX_COUNTER];
static struct op_system_config sys;
+static int op_powerpc_flag;
+
static void op_handle_interrupt(struct pt_regs *regs)
{
model->handle_interrupt(regs, ctr);
@@ -36,25 +38,41 @@ static void op_handle_interrupt(struct p
static void op_powerpc_cpu_setup(void *dummy)
{
- model->cpu_setup(ctr);
+ int ret;
+
+ ret = model->cpu_setup(ctr);
+
+ if (ret != 0)
+ op_powerpc_flag = ret;
}
static int op_powerpc_setup(void)
{
int err;
+ op_powerpc_flag = 0;
+
/* Grab the hardware */
err = reserve_pmc_hardware(op_handle_interrupt);
if (err)
return err;
/* Pre-compute the values to stuff in the hardware registers. */
- model->reg_setup(ctr, &sys, model->num_counters);
+ op_powerpc_flag = model->reg_setup(ctr, &sys, model->num_counters);
- /* Configure the registers on all cpus. */
+ if (op_powerpc_flag)
+ goto out;
+
+ /* Configure the registers on all cpus. If an error occurs on one
+ * of the cpus, op_powerpc_flag will be set to the error */
on_each_cpu(op_powerpc_cpu_setup, NULL, 0, 1);
- return 0;
+out: if (op_powerpc_flag) {
+ /* error on setup release the performance counter hardware */
+ release_pmc_hardware();
+ }
+
+ return op_powerpc_flag;
}
static void op_powerpc_shutdown(void)
@@ -64,16 +82,29 @@ static void op_powerpc_shutdown(void)
static void op_powerpc_cpu_start(void *dummy)
{
- model->start(ctr);
+ /* If any of the cpus have return an error, set the
+ * global flag to the error so it can be returned
+ * to the generic OProfile caller.
+ */
+ int ret;
+
+ ret = model->start(ctr);
+ if (ret != 0)
+ op_powerpc_flag = ret;
}
static int op_powerpc_start(void)
{
+ op_powerpc_flag = 0;
+
if (model->global_start)
- model->global_start(ctr);
- if (model->start)
+ return model->global_start(ctr);
+ if (model->start) {
on_each_cpu(op_powerpc_cpu_start, NULL, 0, 1);
- return 0;
+ return op_powerpc_flag;
+ }
+ return -EIO; /* No start function is defined for this
+ power architecture */
}
static inline void op_powerpc_cpu_stop(void *dummy)
@@ -147,11 +178,13 @@ int __init oprofile_arch_init(struct opr
switch (cur_cpu_spec->oprofile_type) {
#ifdef CONFIG_PPC64
-#ifdef CONFIG_PPC_CELL_NATIVE
+#ifdef CONFIG_OPROFILE_CELL
case PPC_OPROFILE_CELL:
if (firmware_has_feature(FW_FEATURE_LPAR))
return -ENODEV;
model = &op_model_cell;
+ ops->sync_start = model->sync_start;
+ ops->sync_stop = model->sync_stop;
break;
#endif
case PPC_OPROFILE_RS64:
Index: linux-2.6/arch/powerpc/oprofile/Kconfig
===================================================================
--- linux-2.6.orig/arch/powerpc/oprofile/Kconfig
+++ linux-2.6/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.
Index: linux-2.6/arch/powerpc/oprofile/Makefile
===================================================================
--- linux-2.6.orig/arch/powerpc/oprofile/Makefile
+++ linux-2.6/arch/powerpc/oprofile/Makefile
@@ -11,7 +11,9 @@ DRIVER_OBJS := $(addprefix ../../../driv
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
Index: linux-2.6/arch/powerpc/oprofile/op_model_cell.c
===================================================================
--- linux-2.6.orig/arch/powerpc/oprofile/op_model_cell.c
+++ linux-2.6/arch/powerpc/oprofile/op_model_cell.c
@@ -5,8 +5,8 @@
*
* Author: David Erb (djerb@us.ibm.com)
* Modifications:
- * Carl Love <carll@us.ibm.com>
- * Maynard Johnson <maynardj@us.ibm.com>
+ * Carl Love <carll@us.ibm.com>
+ * 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
@@ -38,12 +38,23 @@
#include "../platforms/cell/interrupt.h"
#include "../platforms/cell/cbe_regs.h"
+#include "cell/pr_util.h"
+
+/*
+ * spu_cycle_reset is the number of cycles between samples.
+ * This variable is used for SPU profiling and should ONLY be set
+ * at the beginning of cell_reg_setup; otherwise, it's read-only.
+ */
+static unsigned int spu_cycle_reset = 0;
+
+#define NUM_SPUS_PER_NODE 8
+#define SPU_CYCLES_EVENT_NUM 2 /* event number for SPU_CYCLES */
#define PPU_CYCLES_EVENT_NUM 1 /* event number for CYCLES */
-#define PPU_CYCLES_GRP_NUM 1 /* special group number for identifying
- * PPU_CYCLES event
- */
-#define CBE_COUNT_ALL_CYCLES 0x42800000 /* PPU cycle event specifier */
+#define PPU_CYCLES_GRP_NUM 1 /* special group number for identifying
+ * PPU_CYCLES event
+ */
+#define CBE_COUNT_ALL_CYCLES 0x42800000 /* PPU cycle event specifier */
#define NUM_THREADS 2 /* number of physical threads in
* physical processor
@@ -51,6 +62,7 @@
#define NUM_TRACE_BUS_WORDS 4
#define NUM_INPUT_BUS_WORDS 2
+#define MAX_SPU_COUNT 0xFFFFFF /* maximum 24 bit LFSR value */
struct pmc_cntrl_data {
unsigned long vcntr;
@@ -62,11 +74,10 @@ struct pmc_cntrl_data {
/*
* ibm,cbe-perftools rtas parameters
*/
-
struct pm_signal {
u16 cpu; /* Processor to modify */
- u16 sub_unit; /* hw subunit this applies to (if applicable) */
- short int signal_group; /* Signal Group to Enable/Disable */
+ u16 sub_unit; /* hw subunit this applies to (if applicable)*/
+ short int signal_group; /* Signal Group to Enable/Disable */
u8 bus_word; /* Enable/Disable on this Trace/Trigger/Event
* Bus Word(s) (bitmask)
*/
@@ -112,21 +123,42 @@ static DEFINE_PER_CPU(unsigned long[NR_P
static struct pmc_cntrl_data pmc_cntrl[NUM_THREADS][NR_PHYS_CTRS];
-/* Interpetation of hdw_thread:
+/*
+ * The CELL profiling code makes rtas calls to setup the debug bus to
+ * route the performance signals. Additionally, SPU profiling requires
+ * a second rtas call to setup the hardware to capture the SPU PCs.
+ * The EIO error value is returned if the token lookups or the rtas
+ * call fail. The EIO error number is the best choice of the existing
+ * error numbers. The probability of rtas related error is very low. But
+ * by returning EIO and printing additional information to dmsg the user
+ * will know that OProfile did not start and dmesg will tell them why.
+ * OProfile does not support returning errors on Stop. Not a huge issue
+ * since failure to reset the debug bus or stop the SPU PC collection is
+ * not a fatel issue. Chances are if the Stop failed, Start doesn't work
+ * either.
+ */
+
+/*
+ * Interpetation of hdw_thread:
* 0 - even virtual cpus 0, 2, 4,...
* 1 - odd virtual cpus 1, 3, 5, ...
+ *
+ * FIXME: this is strictly wrong, we need to clean this up in a number
+ * of places. It works for now. -arnd
*/
static u32 hdw_thread;
static u32 virt_cntr_inter_mask;
static struct timer_list timer_virt_cntr;
-/* pm_signal needs to be global since it is initialized in
+/*
+ * pm_signal needs to be global since it is initialized in
* cell_reg_setup at the time when the necessary information
* is available.
*/
static struct pm_signal pm_signal[NR_PHYS_CTRS];
-static int pm_rtas_token;
+static int pm_rtas_token; /* token for debug bus setup call */
+static int spu_rtas_token; /* token for SPU cycle profiling */
static u32 reset_value[NR_PHYS_CTRS];
static int num_counters;
@@ -147,8 +179,8 @@ rtas_ibm_cbe_perftools(int subfunc, int
{
u64 paddr = __pa(address);
- return rtas_call(pm_rtas_token, 5, 1, NULL, subfunc, passthru,
- paddr >> 32, paddr & 0xffffffff, length);
+ return rtas_call(pm_rtas_token, 5, 1, NULL, subfunc,
+ passthru, paddr >> 32, paddr & 0xffffffff, length);
}
static void pm_rtas_reset_signals(u32 node)
@@ -156,12 +188,13 @@ static void pm_rtas_reset_signals(u32 no
int ret;
struct pm_signal pm_signal_local;
- /* The debug bus is being set to the passthru disable state.
- * However, the FW still expects atleast one legal signal routing
- * entry or it will return an error on the arguments. If we don't
- * supply a valid entry, we must ignore all return values. Ignoring
- * all return values means we might miss an error we should be
- * concerned about.
+ /*
+ * The debug bus is being set to the passthru disable state.
+ * However, the FW still expects atleast one legal signal routing
+ * entry or it will return an error on the arguments. If we don't
+ * supply a valid entry, we must ignore all return values. Ignoring
+ * all return values means we might miss an error we should be
+ * concerned about.
*/
/* fw expects physical cpu #. */
@@ -175,18 +208,24 @@ static void pm_rtas_reset_signals(u32 no
&pm_signal_local,
sizeof(struct pm_signal));
- if (ret)
+ if (unlikely(ret))
+ /*
+ * Not a fatal error. For Oprofile stop, the oprofile
+ * functions do not support returning an error for
+ * failure to stop OProfile.
+ */
printk(KERN_WARNING "%s: rtas returned: %d\n",
__FUNCTION__, ret);
}
-static void pm_rtas_activate_signals(u32 node, u32 count)
+static int pm_rtas_activate_signals(u32 node, u32 count)
{
int ret;
int i, j;
struct pm_signal pm_signal_local[NR_PHYS_CTRS];
- /* There is no debug setup required for the cycles event.
+ /*
+ * There is no debug setup required for the cycles event.
* Note that only events in the same group can be used.
* Otherwise, there will be conflicts in correctly routing
* the signals on the debug bus. It is the responsiblity
@@ -213,10 +252,14 @@ static void pm_rtas_activate_signals(u32
pm_signal_local,
i * sizeof(struct pm_signal));
- if (ret)
+ if (unlikely(ret)) {
printk(KERN_WARNING "%s: rtas returned: %d\n",
__FUNCTION__, ret);
+ return -EIO;
+ }
}
+
+ return 0;
}
/*
@@ -260,11 +303,12 @@ static void set_pm_event(u32 ctr, int ev
pm_regs.pm07_cntrl[ctr] |= PM07_CTR_POLARITY(polarity);
pm_regs.pm07_cntrl[ctr] |= PM07_CTR_INPUT_CONTROL(input_control);
- /* Some of the islands signal selection is based on 64 bit words.
+ /*
+ * Some of the islands signal selection is based on 64 bit words.
* The debug bus words are 32 bits, the input words to the performance
* counters are defined as 32 bits. Need to convert the 64 bit island
* specification to the appropriate 32 input bit and bus word for the
- * performance counter event selection. See the CELL Performance
+ * performance counter event selection. See the CELL Performance
* monitoring signals manual and the Perf cntr hardware descriptions
* for the details.
*/
@@ -298,6 +342,7 @@ static void set_pm_event(u32 ctr, int ev
input_bus[j] = i;
pm_regs.group_control |=
(i << (31 - i));
+
break;
}
}
@@ -309,7 +354,8 @@ out:
static void write_pm_cntrl(int cpu)
{
- /* Oprofile will use 32 bit counters, set bits 7:10 to 0
+ /*
+ * Oprofile will use 32 bit counters, set bits 7:10 to 0
* pmregs.pm_cntrl is a global
*/
@@ -326,7 +372,8 @@ static void write_pm_cntrl(int cpu)
if (pm_regs.pm_cntrl.freeze == 1)
val |= CBE_PM_FREEZE_ALL_CTRS;
- /* Routine set_count_mode must be called previously to set
+ /*
+ * Routine set_count_mode must be called previously to set
* the count mode based on the user selection of user and kernel.
*/
val |= CBE_PM_COUNT_MODE_SET(pm_regs.pm_cntrl.count_mode);
@@ -336,7 +383,8 @@ static void write_pm_cntrl(int cpu)
static inline void
set_count_mode(u32 kernel, u32 user)
{
- /* The user must specify user and kernel if they want them. If
+ /*
+ * The user must specify user and kernel if they want them. If
* neither is specified, OProfile will count in hypervisor mode.
* pm_regs.pm_cntrl is a global
*/
@@ -364,7 +412,7 @@ static inline void enable_ctr(u32 cpu, u
/*
* Oprofile is expected to collect data on all CPUs simultaneously.
- * However, there is one set of performance counters per node. There are
+ * However, there is one set of performance counters per node. There are
* two hardware threads or virtual CPUs on each node. Hence, OProfile must
* multiplex in time the performance counter collection on the two virtual
* CPUs. The multiplexing of the performance counters is done by this
@@ -377,19 +425,19 @@ static inline void enable_ctr(u32 cpu, u
* pair of per-cpu arrays is used for storing the previous and next
* pmc values for a given node.
* NOTE: We use the per-cpu variable to improve cache performance.
+ *
+ * This routine will alternate loading the virtual counters for
+ * virtual CPUs
*/
static void cell_virtual_cntr(unsigned long data)
{
- /* This routine will alternate loading the virtual counters for
- * virtual CPUs
- */
int i, prev_hdw_thread, next_hdw_thread;
u32 cpu;
unsigned long flags;
- /* Make sure that the interrupt_hander and
- * the virt counter are not both playing with
- * the counters on the same node.
+ /*
+ * Make sure that the interrupt_hander and the virt counter are
+ * not both playing with the counters on the same node.
*/
spin_lock_irqsave(&virt_cntr_lock, flags);
@@ -400,22 +448,25 @@ static void cell_virtual_cntr(unsigned l
hdw_thread = 1 ^ hdw_thread;
next_hdw_thread = hdw_thread;
- for (i = 0; i < num_counters; i++)
- /* There are some per thread events. Must do the
+ /*
+ * There are some per thread events. Must do the
* set event, for the thread that is being started
*/
+ for (i = 0; i < num_counters; i++)
set_pm_event(i,
pmc_cntrl[next_hdw_thread][i].evnts,
pmc_cntrl[next_hdw_thread][i].masks);
- /* The following is done only once per each node, but
+ /*
+ * The following is done only once per each node, but
* we need cpu #, not node #, to pass to the cbe_xxx functions.
*/
for_each_online_cpu(cpu) {
if (cbe_get_hw_thread_id(cpu))
continue;
- /* stop counters, save counter values, restore counts
+ /*
+ * stop counters, save counter values, restore counts
* for previous thread
*/
cbe_disable_pm(cpu);
@@ -428,7 +479,7 @@ static void cell_virtual_cntr(unsigned l
== 0xFFFFFFFF)
/* If the cntr value is 0xffffffff, we must
* reset that to 0xfffffff0 when the current
- * thread is restarted. This will generate a
+ * thread is restarted. This will generate a
* new interrupt and make sure that we never
* restore the counters to the max value. If
* the counters were restored to the max value,
@@ -444,13 +495,15 @@ static void cell_virtual_cntr(unsigned l
next_hdw_thread)[i]);
}
- /* Switch to the other thread. Change the interrupt
+ /*
+ * Switch to the other thread. Change the interrupt
* and control regs to be scheduled on the CPU
* corresponding to the thread to execute.
*/
for (i = 0; i < num_counters; i++) {
if (pmc_cntrl[next_hdw_thread][i].enabled) {
- /* There are some per thread events.
+ /*
+ * There are some per thread events.
* Must do the set event, enable_cntr
* for each cpu.
*/
@@ -482,17 +535,42 @@ static void start_virt_cntrs(void)
}
/* This function is called once for all cpus combined */
-static void
-cell_reg_setup(struct op_counter_config *ctr,
- struct op_system_config *sys, int num_ctrs)
+static int cell_reg_setup(struct op_counter_config *ctr,
+ struct op_system_config *sys, int num_ctrs)
{
int i, j, cpu;
+ spu_cycle_reset = 0;
+
+ if (ctr[0].event == SPU_CYCLES_EVENT_NUM) {
+ spu_cycle_reset = ctr[0].count;
+
+ /*
+ * Each node will need to make the rtas call to start
+ * and stop SPU profiling. Get the token once and store it.
+ */
+ spu_rtas_token = rtas_token("ibm,cbe-spu-perftools");
+
+ if (unlikely(spu_rtas_token == RTAS_UNKNOWN_SERVICE)) {
+ printk(KERN_ERR
+ "%s: rtas token ibm,cbe-spu-perftools unknown\n",
+ __FUNCTION__);
+ return -EIO;
+ }
+ }
pm_rtas_token = rtas_token("ibm,cbe-perftools");
- if (pm_rtas_token == RTAS_UNKNOWN_SERVICE) {
- printk(KERN_WARNING "%s: RTAS_UNKNOWN_SERVICE\n",
+
+ /*
+ * For all events excetp PPU CYCLEs, each node will need to make
+ * the rtas cbe-perftools call to setup and reset the debug bus.
+ * Make the token lookup call once and store it in the global
+ * variable pm_rtas_token.
+ */
+ if (unlikely(pm_rtas_token == RTAS_UNKNOWN_SERVICE)) {
+ printk(KERN_ERR
+ "%s: rtas token ibm,cbe-perftools unknown\n",
__FUNCTION__);
- goto out;
+ return -EIO;
}
num_counters = num_ctrs;
@@ -520,7 +598,8 @@ cell_reg_setup(struct op_counter_config
per_cpu(pmc_values, j)[i] = 0;
}
- /* Setup the thread 1 events, map the thread 0 event to the
+ /*
+ * Setup the thread 1 events, map the thread 0 event to the
* equivalent thread 1 event.
*/
for (i = 0; i < num_ctrs; ++i) {
@@ -544,9 +623,10 @@ cell_reg_setup(struct op_counter_config
for (i = 0; i < NUM_INPUT_BUS_WORDS; i++)
input_bus[i] = 0xff;
- /* Our counters count up, and "count" refers to
+ /*
+ * Our counters count up, and "count" refers to
* how much before the next interrupt, and we interrupt
- * on overflow. So we calculate the starting value
+ * on overflow. So we calculate the starting value
* which will give us "count" until overflow.
* Then we set the events on the enabled counters.
*/
@@ -569,28 +649,27 @@ cell_reg_setup(struct op_counter_config
for (i = 0; i < num_counters; ++i) {
per_cpu(pmc_values, cpu)[i] = reset_value[i];
}
-out:
- ;
+
+ return 0;
}
+
+
/* This function is called once for each cpu */
-static void cell_cpu_setup(struct op_counter_config *cntr)
+static int cell_cpu_setup(struct op_counter_config *cntr)
{
u32 cpu = smp_processor_id();
u32 num_enabled = 0;
int i;
+ if (spu_cycle_reset)
+ return 0;
+
/* There is one performance monitor per processor chip (i.e. node),
* so we only need to perform this function once per node.
*/
if (cbe_get_hw_thread_id(cpu))
- goto out;
-
- if (pm_rtas_token == RTAS_UNKNOWN_SERVICE) {
- printk(KERN_WARNING "%s: RTAS_UNKNOWN_SERVICE\n",
- __FUNCTION__);
- goto out;
- }
+ return 0;
/* Stop all counters */
cbe_disable_pm(cpu);
@@ -609,16 +688,282 @@ static void cell_cpu_setup(struct op_cou
}
}
- pm_rtas_activate_signals(cbe_cpu_to_node(cpu), num_enabled);
+ /*
+ * The pm_rtas_activate_signals will return -EIO if the FW
+ * call failed.
+ */
+ return pm_rtas_activate_signals(cbe_cpu_to_node(cpu), num_enabled);
+}
+
+#define ENTRIES 303
+#define MAXLFSR 0xFFFFFF
+
+/* precomputed table of 24 bit LFSR values */
+static int initial_lfsr[] = {
+ 8221349, 12579195, 5379618, 10097839, 7512963, 7519310, 3955098, 10753424,
+ 15507573, 7458917, 285419, 2641121, 9780088, 3915503, 6668768, 1548716,
+ 4885000, 8774424, 9650099, 2044357, 2304411, 9326253, 10332526, 4421547,
+ 3440748, 10179459, 13332843, 10375561, 1313462, 8375100, 5198480, 6071392,
+ 9341783, 1526887, 3985002, 1439429, 13923762, 7010104, 11969769, 4547026,
+ 2040072, 4025602, 3437678, 7939992, 11444177, 4496094, 9803157, 10745556,
+ 3671780, 4257846, 5662259, 13196905, 3237343, 12077182, 16222879, 7587769,
+ 14706824, 2184640, 12591135, 10420257, 7406075, 3648978, 11042541, 15906893,
+ 11914928, 4732944, 10695697, 12928164, 11980531, 4430912, 11939291, 2917017,
+ 6119256, 4172004, 9373765, 8410071, 14788383, 5047459, 5474428, 1737756,
+ 15967514, 13351758, 6691285, 8034329, 2856544, 14394753, 11310160, 12149558,
+ 7487528, 7542781, 15668898, 12525138, 12790975, 3707933, 9106617, 1965401,
+ 16219109, 12801644, 2443203, 4909502, 8762329, 3120803, 6360315, 9309720,
+ 15164599, 10844842, 4456529, 6667610, 14924259, 884312, 6234963, 3326042,
+ 15973422, 13919464, 5272099, 6414643, 3909029, 2764324, 5237926, 4774955,
+ 10445906, 4955302, 5203726, 10798229, 11443419, 2303395, 333836, 9646934,
+ 3464726, 4159182, 568492, 995747, 10318756, 13299332, 4836017, 8237783,
+ 3878992, 2581665, 11394667, 5672745, 14412947, 3159169, 9094251, 16467278,
+ 8671392, 15230076, 4843545, 7009238, 15504095, 1494895, 9627886, 14485051,
+ 8304291, 252817, 12421642, 16085736, 4774072, 2456177, 4160695, 15409741,
+ 4902868, 5793091, 13162925, 16039714, 782255, 11347835, 14884586, 366972,
+ 16308990, 11913488, 13390465, 2958444, 10340278, 1177858, 1319431, 10426302,
+ 2868597, 126119, 5784857, 5245324, 10903900, 16436004, 3389013, 1742384,
+ 14674502, 10279218, 8536112, 10364279, 6877778, 14051163, 1025130, 6072469,
+ 1988305, 8354440, 8216060, 16342977, 13112639, 3976679, 5913576, 8816697,
+ 6879995, 14043764, 3339515, 9364420, 15808858, 12261651, 2141560, 5636398,
+ 10345425, 10414756, 781725, 6155650, 4746914, 5078683, 7469001, 6799140,
+ 10156444, 9667150, 10116470, 4133858, 2121972, 1124204, 1003577, 1611214,
+ 14304602, 16221850, 13878465, 13577744, 3629235, 8772583, 10881308, 2410386,
+ 7300044, 5378855, 9301235, 12755149, 4977682, 8083074, 10327581, 6395087,
+ 9155434, 15501696, 7514362, 14520507, 15808945, 3244584, 4741962, 9658130,
+ 14336147, 8654727, 7969093, 15759799, 14029445, 5038459, 9894848, 8659300,
+ 13699287, 8834306, 10712885, 14753895, 10410465, 3373251, 309501, 9561475,
+ 5526688, 14647426, 14209836, 5339224, 207299, 14069911, 8722990, 2290950,
+ 3258216, 12505185, 6007317, 9218111, 14661019, 10537428, 11731949, 9027003,
+ 6641507, 9490160, 200241, 9720425, 16277895, 10816638, 1554761, 10431375,
+ 7467528, 6790302, 3429078, 14633753, 14428997, 11463204, 3576212, 2003426,
+ 6123687, 820520, 9992513, 15784513, 5778891, 6428165, 8388607
+};
+
+/*
+ * The hardware uses an LFSR counting sequence to determine when to capture
+ * the SPU PCs. An LFSR sequence is like a puesdo random number sequence
+ * where each number occurs once in the sequence but the sequence is not in
+ * numerical order. The SPU PC capture is done when the LFSR sequence reaches
+ * the last value in the sequence. Hence the user specified value N
+ * corresponds to the LFSR number that is N from the end of the sequence.
+ *
+ * To avoid the time to compute the LFSR, a lookup table is used. The 24 bit
+ * LFSR sequence is broken into four ranges. The spacing of the precomputed
+ * values is adjusted in each range so the error between the user specifed
+ * number (N) of events between samples and the actual number of events based
+ * on the precomputed value will be les then about 6.2%. Note, if the user
+ * specifies N < 2^16, the LFSR value that is 2^16 from the end will be used.
+ * This is to prevent the loss of samples because the trace buffer is full.
+ *
+ * User specified N Step between Index in
+ * precomputed values precomputed
+ * table
+ * 0 to 2^16-1 ---- 0
+ * 2^16 to 2^16+2^19-1 2^12 1 to 128
+ * 2^16+2^19 to 2^16+2^19+2^22-1 2^15 129 to 256
+ * 2^16+2^19+2^22 to 2^24-1 2^18 257 to 302
+ *
+ *
+ * For example, the LFSR values in the second range are computed for 2^16,
+ * 2^16+2^12, ... , 2^19-2^16, 2^19 and stored in the table at indicies
+ * 1, 2,..., 127, 128.
+ *
+ * The 24 bit LFSR value for the nth number in the sequence can be
+ * calculated using the following code:
+ *
+ * #define size 24
+ * int calculate_lfsr(int n)
+ * {
+ * int i;
+ * unsigned int newlfsr0;
+ * unsigned int lfsr = 0xFFFFFF;
+ * unsigned int howmany = n;
+ *
+ * for (i = 2; i < howmany + 2; i++) {
+ * newlfsr0 = (((lfsr >> (size - 1 - 0)) & 1) ^
+ * ((lfsr >> (size - 1 - 1)) & 1) ^
+ * (((lfsr >> (size - 1 - 6)) & 1) ^
+ * ((lfsr >> (size - 1 - 23)) & 1)));
+ *
+ * lfsr >>= 1;
+ * lfsr = lfsr | (newlfsr0 << (size - 1));
+ * }
+ * return lfsr;
+ * }
+ */
+
+#define V2_16 (0x1 <<16)
+#define V2_19 (0x1 <<19)
+#define V2_22 (0x1 <<22)
+
+static int calculate_lfsr(int n)
+{
+ /*
+ * The ranges and steps are in powers of 2 so the calculations
+ * can be done using shifts rather then divide.
+ */
+ int index;
+
+ if ((n >> 16) == 0)
+ index = 0;
+ else if (((n - V2_16) >> 19) == 0)
+ index = ((n - V2_16) >> 12) + 1;
+ else if (((n - V2_16 - V2_19) >> 22) == 0)
+ index = ((n - V2_16 - V2_19) >> 15 ) + 1 + 128;
+ else if (((n - V2_16 - V2_19 - V2_22) >> 24) == 0)
+ index = ((n - V2_16 - V2_19 - V2_22) >> 18 ) + 1 + 256;
+ else
+ index = ENTRIES-1;
+
+ /* make sure index is valid */
+ if ((index > ENTRIES) || (index < 0))
+ index = ENTRIES-1;
+
+ return initial_lfsr[index];
+}
+
+static int pm_rtas_activate_spu_profiling(u32 node)
+{
+ int ret, i;
+ struct pm_signal pm_signal_local[NR_PHYS_CTRS];
+
+ /*
+ * Set up the rtas call to configure the debug bus to
+ * route the SPU PCs. Setup the pm_signal for each SPU
+ */
+ for (i = 0; i < NUM_SPUS_PER_NODE; i++) {
+ pm_signal_local[i].cpu = node;
+ pm_signal_local[i].signal_group = 41;
+ /* spu i on word (i/2) */
+ pm_signal_local[i].bus_word = 1 << i / 2;
+ /* spu i */
+ pm_signal_local[i].sub_unit = i;
+ pm_signal_local[i].bit = 63;
+ }
+
+ ret = rtas_ibm_cbe_perftools(SUBFUNC_ACTIVATE,
+ PASSTHRU_ENABLE, pm_signal_local,
+ (NUM_SPUS_PER_NODE
+ * sizeof(struct pm_signal)));
+
+ if (unlikely(ret)) {
+ printk(KERN_WARNING "%s: rtas returned: %d\n",
+ __FUNCTION__, ret);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_CPU_FREQ
+static int
+oprof_cpufreq_notify(struct notifier_block *nb, unsigned long val, void *data)
+{
+ int ret = 0;
+ struct cpufreq_freqs * frq = data;
+ if ((val == CPUFREQ_PRECHANGE && frq->old < frq->new) ||
+ (val == CPUFREQ_POSTCHANGE && frq->old > frq->new) ||
+ (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE))
+ set_profiling_frequency(frq->new, spu_cycle_reset);
+ return ret;
+}
+
+static struct notifier_block cpu_freq_notifier_block = {
+ .notifier_call = oprof_cpufreq_notify
+};
+#endif
+
+static int cell_global_start_spu(struct op_counter_config *ctr)
+{
+ int subfunc, rtn_value;
+ unsigned int lfsr_value;
+ int cpu;
+ int ret;
+ int rtas_error;
+ unsigned int cpu_khzfreq = 0;
+
+ /* The SPU profiling uses time-based profiling based on
+ * cpu frequency, so if configured with the CPU_FREQ
+ * option, we should detect frequency changes and react
+ * accordingly.
+ */
+#ifdef CONFIG_CPU_FREQ
+ ret = cpufreq_register_notifier(&cpu_freq_notifier_block,
+ CPUFREQ_TRANSITION_NOTIFIER);
+ if (ret < 0)
+ /* this is not a fatal error */
+ printk(KERN_ERR "CPU freq change registration failed: %d\n",
+ ret);
+
+ else
+ cpu_khzfreq = cpufreq_quick_get(smp_processor_id());
+#endif
+
+ set_profiling_frequency(cpu_khzfreq, spu_cycle_reset);
+
+ for_each_online_cpu(cpu) {
+ if (cbe_get_hw_thread_id(cpu))
+ continue;
+
+ /*
+ * Setup SPU cycle-based profiling.
+ * Set perf_mon_control bit 0 to a zero before
+ * enabling spu collection hardware.
+ */
+ cbe_write_pm(cpu, pm_control, 0);
+
+ if (spu_cycle_reset > MAX_SPU_COUNT)
+ /* use largest possible value */
+ lfsr_value = calculate_lfsr(MAX_SPU_COUNT-1);
+ else
+ lfsr_value = calculate_lfsr(spu_cycle_reset);
+
+ /* must use a non zero value. Zero disables data collection. */
+ if (lfsr_value == 0)
+ lfsr_value = calculate_lfsr(1);
+
+ lfsr_value = lfsr_value << 8; /* shift lfsr to correct
+ * register location
+ */
+
+ /* debug bus setup */
+ ret = pm_rtas_activate_spu_profiling(cbe_cpu_to_node(cpu));
+
+ if (unlikely(ret)) {
+ rtas_error = ret;
+ goto out;
+ }
+
+
+ subfunc = 2; /* 2 - activate SPU tracing, 3 - deactivate */
+
+ /* start profiling */
+ rtn_value = rtas_call(spu_rtas_token, 3, 1, NULL, subfunc,
+ cbe_cpu_to_node(cpu), lfsr_value);
+
+ if (unlikely(rtn_value != 0)) {
+ printk(KERN_ERR
+ "%s: rtas call ibm,cbe-spu-perftools failed, return = %d\n",
+ __FUNCTION__, rtn_value);
+ rtas_error = -EIO;
+ goto out;
+ }
+ }
+
+ start_spu_profiling(spu_cycle_reset);
+
+ oprofile_running = 1;
+ return 0;
+
out:
- ;
+ return rtas_error;
}
-static void cell_global_start(struct op_counter_config *ctr)
+static int cell_global_start_ppu(struct op_counter_config *ctr)
{
- u32 cpu;
+ u32 cpu, i;
u32 interrupt_mask = 0;
- u32 i;
/* This routine gets called once for the system.
* There is one performance monitor per node, so we
@@ -651,19 +996,80 @@ static void cell_global_start(struct op_
oprofile_running = 1;
smp_wmb();
- /* NOTE: start_virt_cntrs will result in cell_virtual_cntr() being
- * executed which manipulates the PMU. We start the "virtual counter"
+ /*
+ * NOTE: start_virt_cntrs will result in cell_virtual_cntr() being
+ * executed which manipulates the PMU. We start the "virtual counter"
* here so that we do not need to synchronize access to the PMU in
* the above for-loop.
*/
start_virt_cntrs();
+
+ return 0;
}
-static void cell_global_stop(void)
+static int cell_global_start(struct op_counter_config *ctr)
+{
+ if (spu_cycle_reset) {
+ return cell_global_start_spu(ctr);
+ } else {
+ return cell_global_start_ppu(ctr);
+ }
+}
+
+/*
+ * Note the generic OProfile stop calls do not support returning
+ * an error on stop. Hence, will not return an error if the FW
+ * calls fail on stop. Failure to reset the debug bus is not an issue.
+ * Failure to disable the SPU profiling is not an issue. The FW calls
+ * to enable the performance counters and debug bus will work even if
+ * the hardware was not cleanly reset.
+ */
+static void cell_global_stop_spu(void)
+{
+ int subfunc, rtn_value;
+ unsigned int lfsr_value;
+ int cpu;
+
+ oprofile_running = 0;
+
+#ifdef CONFIG_CPU_FREQ
+ cpufreq_unregister_notifier(&cpu_freq_notifier_block,
+ CPUFREQ_TRANSITION_NOTIFIER);
+#endif
+
+ for_each_online_cpu(cpu) {
+ if (cbe_get_hw_thread_id(cpu))
+ continue;
+
+ subfunc = 3; /*
+ * 2 - activate SPU tracing,
+ * 3 - deactivate
+ */
+ lfsr_value = 0x8f100000;
+
+ rtn_value = rtas_call(spu_rtas_token, 3, 1, NULL,
+ subfunc, cbe_cpu_to_node(cpu),
+ lfsr_value);
+
+ if (unlikely(rtn_value != 0)) {
+ printk(KERN_ERR
+ "%s: rtas call ibm,cbe-spu-perftools failed, return = %d\n",
+ __FUNCTION__, rtn_value);
+ }
+
+ /* Deactivate the signals */
+ pm_rtas_reset_signals(cbe_cpu_to_node(cpu));
+ }
+
+ stop_spu_profiling();
+}
+
+static void cell_global_stop_ppu(void)
{
int cpu;
- /* This routine will be called once for the system.
+ /*
+ * This routine will be called once for the system.
* There is one performance monitor per node, so we
* only need to perform this function once per node.
*/
@@ -687,8 +1093,17 @@ static void cell_global_stop(void)
}
}
-static void
-cell_handle_interrupt(struct pt_regs *regs, struct op_counter_config *ctr)
+static void cell_global_stop(void)
+{
+ if (spu_cycle_reset) {
+ cell_global_stop_spu();
+ } else {
+ cell_global_stop_ppu();
+ }
+}
+
+static void cell_handle_interrupt(struct pt_regs *regs,
+ struct op_counter_config *ctr)
{
u32 cpu;
u64 pc;
@@ -699,13 +1114,15 @@ cell_handle_interrupt(struct pt_regs *re
cpu = smp_processor_id();
- /* Need to make sure the interrupt handler and the virt counter
+ /*
+ * Need to make sure the interrupt handler and the virt counter
* routine are not running at the same time. See the
* cell_virtual_cntr() routine for additional comments.
*/
spin_lock_irqsave(&virt_cntr_lock, flags);
- /* Need to disable and reenable the performance counters
+ /*
+ * Need to disable and reenable the performance counters
* to get the desired behavior from the hardware. This
* is hardware specific.
*/
@@ -714,7 +1131,8 @@ cell_handle_interrupt(struct pt_regs *re
interrupt_mask = cbe_get_and_clear_pm_interrupts(cpu);
- /* If the interrupt mask has been cleared, then the virt cntr
+ /*
+ * If the interrupt mask has been cleared, then the virt cntr
* has cleared the interrupt. When the thread that generated
* the interrupt is restored, the data count will be restored to
* 0xffffff0 to cause the interrupt to be regenerated.
@@ -732,18 +1150,20 @@ cell_handle_interrupt(struct pt_regs *re
}
}
- /* The counters were frozen by the interrupt.
+ /*
+ * The counters were frozen by the interrupt.
* Reenable the interrupt and restart the counters.
* If there was a race between the interrupt handler and
- * the virtual counter routine. The virutal counter
+ * the virtual counter routine. The virutal counter
* routine may have cleared the interrupts. Hence must
* use the virt_cntr_inter_mask to re-enable the interrupts.
*/
cbe_enable_pm_interrupts(cpu, hdw_thread,
virt_cntr_inter_mask);
- /* The writes to the various performance counters only writes
- * to a latch. The new values (interrupt setting bits, reset
+ /*
+ * The writes to the various performance counters only writes
+ * to a latch. The new values (interrupt setting bits, reset
* counter value etc.) are not copied to the actual registers
* until the performance monitor is enabled. In order to get
* this to work as desired, the permormance monitor needs to
@@ -755,10 +1175,33 @@ cell_handle_interrupt(struct pt_regs *re
spin_unlock_irqrestore(&virt_cntr_lock, flags);
}
+/*
+ * This function is called from the generic OProfile
+ * driver. When profiling PPUs, we need to do the
+ * generic sync start; otherwise, do spu_sync_start.
+ */
+static int cell_sync_start(void)
+{
+ if (spu_cycle_reset)
+ return spu_sync_start();
+ else
+ return DO_GENERIC_SYNC;
+}
+
+static int cell_sync_stop(void)
+{
+ if (spu_cycle_reset)
+ return spu_sync_stop();
+ else
+ return 1;
+}
+
struct op_powerpc_model op_model_cell = {
.reg_setup = cell_reg_setup,
.cpu_setup = cell_cpu_setup,
.global_start = cell_global_start,
.global_stop = cell_global_stop,
+ .sync_start = cell_sync_start,
+ .sync_stop = cell_sync_stop,
.handle_interrupt = cell_handle_interrupt,
};
Index: linux-2.6/arch/powerpc/platforms/cell/spufs/sched.c
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/cell/spufs/sched.c
+++ linux-2.6/arch/powerpc/platforms/cell/spufs/sched.c
@@ -149,6 +149,7 @@ static void spu_bind_context(struct spu
ctx->spu = spu;
ctx->ops = &spu_hw_ops;
spu->pid = current->pid;
+ spu->tgid = current->tgid;
spu_associate_mm(spu, ctx->owner);
spu->ibox_callback = spufs_ibox_callback;
spu->wbox_callback = spufs_wbox_callback;
@@ -188,6 +189,7 @@ static void spu_unbind_context(struct sp
spu->dma_callback = NULL;
spu_associate_mm(spu, NULL);
spu->pid = 0;
+ spu->tgid = 0;
ctx->ops = &spu_backing_ops;
ctx->spu = NULL;
spu->flags = 0;
@@ -421,7 +423,7 @@ void spu_deactivate(struct spu_context *
}
/**
- * spu_yield - yield a physical spu if others are waiting
+ * spu_yield - yield a physical spu if others are waiting
* @ctx: spu context to yield
*
* Check if there is a higher priority context waiting and if yes
Index: linux-2.6/drivers/oprofile/buffer_sync.c
===================================================================
--- linux-2.6.orig/drivers/oprofile/buffer_sync.c
+++ linux-2.6/drivers/oprofile/buffer_sync.c
@@ -26,8 +26,9 @@
#include <linux/profile.h>
#include <linux/module.h>
#include <linux/fs.h>
+#include <linux/oprofile.h>
#include <linux/sched.h>
-
+
#include "oprofile_stats.h"
#include "event_buffer.h"
#include "cpu_buffer.h"
Index: linux-2.6/drivers/oprofile/event_buffer.h
===================================================================
--- linux-2.6.orig/drivers/oprofile/event_buffer.h
+++ linux-2.6/drivers/oprofile/event_buffer.h
@@ -19,28 +19,10 @@ void free_event_buffer(void);
/* wake up the process sleeping on the event file */
void wake_up_buffer_waiter(void);
-
-/* Each escaped entry is prefixed by ESCAPE_CODE
- * then one of the following codes, then the
- * relevant data.
- */
-#define ESCAPE_CODE ~0UL
-#define CTX_SWITCH_CODE 1
-#define CPU_SWITCH_CODE 2
-#define COOKIE_SWITCH_CODE 3
-#define KERNEL_ENTER_SWITCH_CODE 4
-#define KERNEL_EXIT_SWITCH_CODE 5
-#define MODULE_LOADED_CODE 6
-#define CTX_TGID_CODE 7
-#define TRACE_BEGIN_CODE 8
-#define TRACE_END_CODE 9
-
+
#define INVALID_COOKIE ~0UL
#define NO_COOKIE 0UL
-/* add data to the event buffer */
-void add_event_entry(unsigned long data);
-
extern const struct file_operations event_buffer_fops;
/* mutex between sync_cpu_buffers() and the
Index: linux-2.6/drivers/oprofile/oprof.c
===================================================================
--- linux-2.6.orig/drivers/oprofile/oprof.c
+++ linux-2.6/drivers/oprofile/oprof.c
@@ -53,9 +53,23 @@ int oprofile_setup(void)
* us missing task deaths and eventually oopsing
* when trying to process the event buffer.
*/
+ if (oprofile_ops.sync_start) {
+ int sync_ret = oprofile_ops.sync_start();
+ switch (sync_ret) {
+ case 0: goto post_sync;
+ break;
+ case 1: goto do_generic;
+ break;
+ case -1: goto out3;
+ break;
+ default: goto out3;
+ }
+ }
+do_generic:
if ((err = sync_start()))
goto out3;
+post_sync:
is_setup = 1;
mutex_unlock(&start_mutex);
return 0;
@@ -118,7 +132,19 @@ out:
void oprofile_shutdown(void)
{
mutex_lock(&start_mutex);
+ if (oprofile_ops.sync_stop) {
+ int sync_ret = oprofile_ops.sync_stop();
+ switch (sync_ret) {
+ case 0: goto post_sync;
+ break;
+ case 1: goto do_generic;
+ break;
+ default: goto post_sync;
+ }
+ }
+do_generic:
sync_stop();
+post_sync:
if (oprofile_ops.shutdown)
oprofile_ops.shutdown();
is_setup = 0;
Index: linux-2.6/include/asm-powerpc/oprofile_impl.h
===================================================================
--- linux-2.6.orig/include/asm-powerpc/oprofile_impl.h
+++ linux-2.6/include/asm-powerpc/oprofile_impl.h
@@ -39,14 +39,16 @@ struct op_system_config {
/* Per-arch configuration */
struct op_powerpc_model {
- void (*reg_setup) (struct op_counter_config *,
+ int (*reg_setup) (struct op_counter_config *,
struct op_system_config *,
int num_counters);
- void (*cpu_setup) (struct op_counter_config *);
- void (*start) (struct op_counter_config *);
- void (*global_start) (struct op_counter_config *);
+ int (*cpu_setup) (struct op_counter_config *);
+ int (*start) (struct op_counter_config *);
+ int (*global_start) (struct op_counter_config *);
void (*stop) (void);
void (*global_stop) (void);
+ int (*sync_start)(void);
+ int (*sync_stop)(void);
void (*handle_interrupt) (struct pt_regs *,
struct op_counter_config *);
int num_counters;
Index: linux-2.6/include/asm-powerpc/spu.h
===================================================================
--- linux-2.6.orig/include/asm-powerpc/spu.h
+++ linux-2.6/include/asm-powerpc/spu.h
@@ -129,6 +129,7 @@ struct spu {
struct spu_runqueue *rq;
unsigned long long timestamp;
pid_t pid;
+ pid_t tgid;
int class_0_pending;
spinlock_t register_lock;
@@ -172,6 +173,20 @@ extern void spu_associate_mm(struct spu
struct mm_struct;
extern void spu_flush_all_slbs(struct mm_struct *mm);
+/* This interface allows a profiler (e.g., OProfile) to store a ref
+ * to spu context information that it creates. This caching technique
+ * avoids the need to recreate this information after a save/restore operation.
+ *
+ * Assumes the caller has already incremented the ref count to
+ * profile_info; then spu_context_destroy must call kref_put
+ * on prof_info_kref.
+ */
+void spu_set_profile_private_kref(struct spu_context * ctx,
+ struct kref * prof_info_kref,
+ void (* prof_info_release) (struct kref * kref));
+
+void * spu_get_profile_private_kref(struct spu_context * ctx);
+
/* system callbacks from the SPU */
struct spu_syscall_block {
u64 nr_ret;
Index: linux-2.6/include/linux/oprofile.h
===================================================================
--- linux-2.6.orig/include/linux/oprofile.h
+++ linux-2.6/include/linux/oprofile.h
@@ -17,6 +17,26 @@
#include <linux/spinlock.h>
#include <asm/atomic.h>
+/* Each escaped entry is prefixed by ESCAPE_CODE
+ * then one of the following codes, then the
+ * relevant data.
+ * These #defines live in this file so that arch-specific
+ * buffer sync'ing code can access them.
+ */
+#define ESCAPE_CODE ~0UL
+#define CTX_SWITCH_CODE 1
+#define CPU_SWITCH_CODE 2
+#define COOKIE_SWITCH_CODE 3
+#define KERNEL_ENTER_SWITCH_CODE 4
+#define KERNEL_EXIT_SWITCH_CODE 5
+#define MODULE_LOADED_CODE 6
+#define CTX_TGID_CODE 7
+#define TRACE_BEGIN_CODE 8
+#define TRACE_END_CODE 9
+#define XEN_ENTER_SWITCH_CODE 10
+#define SPU_PROFILING_CODE 11
+#define SPU_CTX_SWITCH_CODE 12
+
struct super_block;
struct dentry;
struct file_operations;
@@ -35,6 +55,14 @@ struct oprofile_operations {
int (*start)(void);
/* Stop delivering interrupts. */
void (*stop)(void);
+ /* Arch-specific buffer sync functions.
+ * Return value = 0: Success
+ * Return value = -1: Failure
+ * Return value = 1: Run generic sync function
+ */
+ int (*sync_start)(void);
+ int (*sync_stop)(void);
+
/* Initiate a stack backtrace. Optional. */
void (*backtrace)(struct pt_regs * const regs, unsigned int depth);
/* CPU identification string. */
@@ -56,6 +84,13 @@ int oprofile_arch_init(struct oprofile_o
void oprofile_arch_exit(void);
/**
+ * Add data to the event buffer.
+ * The data passed is free-form, but typically consists of
+ * file offsets, dcookies, context information, and ESCAPE codes.
+ */
+void add_event_entry(unsigned long data);
+
+/**
* Add a sample. This may be called from any context. Pass
* smp_processor_id() as cpu.
*/
Index: linux-2.6/arch/powerpc/kernel/time.c
===================================================================
--- linux-2.6.orig/arch/powerpc/kernel/time.c
+++ linux-2.6/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;
Index: linux-2.6/arch/powerpc/platforms/cell/spufs/spufs.h
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/cell/spufs/spufs.h
+++ linux-2.6/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -80,9 +80,11 @@ struct spu_context {
struct list_head gang_list;
struct spu_gang *gang;
+ struct kref *prof_priv_kref;
+ void (* prof_priv_release) (struct kref *kref);
/* scheduler fields */
- struct list_head rq;
+ struct list_head rq;
struct delayed_work sched_work;
unsigned long sched_flags;
unsigned long rt_priority;
Index: linux-2.6/arch/powerpc/platforms/cell/spufs/context.c
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/cell/spufs/context.c
+++ linux-2.6/arch/powerpc/platforms/cell/spufs/context.c
@@ -22,6 +22,7 @@
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/module.h>
#include <linux/slab.h>
#include <asm/spu.h>
#include <asm/spu_csa.h>
@@ -75,6 +76,8 @@ void destroy_spu_context(struct kref *kr
spu_fini_csa(&ctx->csa);
if (ctx->gang)
spu_gang_remove_ctx(ctx->gang, ctx);
+ if (ctx->prof_priv_kref)
+ kref_put(ctx->prof_priv_kref, ctx->prof_priv_release);
BUG_ON(!list_empty(&ctx->rq));
kfree(ctx);
}
@@ -162,3 +165,20 @@ void spu_acquire_saved(struct spu_contex
if (ctx->state != SPU_STATE_SAVED)
spu_deactivate(ctx);
}
+
+void spu_set_profile_private_kref(struct spu_context * ctx,
+ struct kref * prof_info_kref,
+ void (* prof_info_release) (struct kref * kref))
+{
+ ctx->prof_priv_kref = prof_info_kref;
+ ctx->prof_priv_release = prof_info_release;
+}
+EXPORT_SYMBOL_GPL(spu_set_profile_private_kref);
+
+void * spu_get_profile_private_kref(struct spu_context * ctx)
+{
+ return ctx->prof_priv_kref;
+}
+EXPORT_SYMBOL_GPL(spu_get_profile_private_kref);
+
+
Index: linux-2.6/include/linux/dcookies.h
===================================================================
--- linux-2.6.orig/include/linux/dcookies.h
+++ linux-2.6/include/linux/dcookies.h
@@ -12,6 +12,7 @@
#ifdef CONFIG_PROFILING
+#include <linux/dcache.h>
#include <linux/types.h>
struct dcookie_user;
Index: linux-2.6/include/linux/elf-em.h
===================================================================
--- linux-2.6.orig/include/linux/elf-em.h
+++ linux-2.6/include/linux/elf-em.h
@@ -20,7 +20,8 @@
#define EM_PARISC 15 /* HPPA */
#define EM_SPARC32PLUS 18 /* Sun's "v8plus" */
#define EM_PPC 20 /* PowerPC */
-#define EM_PPC64 21 /* PowerPC64 */
+#define EM_PPC64 21 /* PowerPC64 */
+#define EM_SPU 23 /* Cell BE SPU */
#define EM_SH 42 /* SuperH */
#define EM_SPARCV9 43 /* SPARC v9 64-bit */
#define EM_IA_64 50 /* HP/Intel IA-64 */
Index: linux-2.6/arch/powerpc/oprofile/op_model_rs64.c
===================================================================
--- linux-2.6.orig/arch/powerpc/oprofile/op_model_rs64.c
+++ linux-2.6/arch/powerpc/oprofile/op_model_rs64.c
@@ -88,7 +88,7 @@ static unsigned long reset_value[OP_MAX_
static int num_counters;
-static void rs64_reg_setup(struct op_counter_config *ctr,
+static int rs64_reg_setup(struct op_counter_config *ctr,
struct op_system_config *sys,
int num_ctrs)
{
@@ -100,9 +100,10 @@ static void rs64_reg_setup(struct op_cou
reset_value[i] = 0x80000000UL - ctr[i].count;
/* XXX setup user and kernel profiling */
+ return 0;
}
-static void rs64_cpu_setup(struct op_counter_config *ctr)
+static int rs64_cpu_setup(struct op_counter_config *ctr)
{
unsigned int mmcr0;
@@ -125,9 +126,11 @@ static void rs64_cpu_setup(struct op_cou
mfspr(SPRN_MMCR0));
dbg("setup on cpu %d, mmcr1 %lx\n", smp_processor_id(),
mfspr(SPRN_MMCR1));
+
+ return 0;
}
-static void rs64_start(struct op_counter_config *ctr)
+static int rs64_start(struct op_counter_config *ctr)
{
int i;
unsigned int mmcr0;
@@ -155,6 +158,7 @@ static void rs64_start(struct op_counter
mtspr(SPRN_MMCR0, mmcr0);
dbg("start on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
+ return 0;
}
static void rs64_stop(void)
Index: linux-2.6/arch/powerpc/oprofile/op_model_power4.c
===================================================================
--- linux-2.6.orig/arch/powerpc/oprofile/op_model_power4.c
+++ linux-2.6/arch/powerpc/oprofile/op_model_power4.c
@@ -30,7 +30,7 @@ static u32 mmcr0_val;
static u64 mmcr1_val;
static u64 mmcra_val;
-static void power4_reg_setup(struct op_counter_config *ctr,
+static int power4_reg_setup(struct op_counter_config *ctr,
struct op_system_config *sys,
int num_ctrs)
{
@@ -58,6 +58,8 @@ static void power4_reg_setup(struct op_c
mmcr0_val &= ~MMCR0_PROBLEM_DISABLE;
else
mmcr0_val |= MMCR0_PROBLEM_DISABLE;
+
+ return 0;
}
extern void ppc64_enable_pmcs(void);
@@ -82,7 +84,7 @@ static inline int mmcra_must_set_sample(
return 0;
}
-static void power4_cpu_setup(struct op_counter_config *ctr)
+static int power4_cpu_setup(struct op_counter_config *ctr)
{
unsigned int mmcr0 = mmcr0_val;
unsigned long mmcra = mmcra_val;
@@ -109,9 +111,11 @@ static void power4_cpu_setup(struct op_c
mfspr(SPRN_MMCR1));
dbg("setup on cpu %d, mmcra %lx\n", smp_processor_id(),
mfspr(SPRN_MMCRA));
+
+ return 0;
}
-static void power4_start(struct op_counter_config *ctr)
+static int power4_start(struct op_counter_config *ctr)
{
int i;
unsigned int mmcr0;
@@ -146,6 +150,7 @@ static void power4_start(struct op_count
oprofile_running = 1;
dbg("start on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
+ return 0;
}
static void power4_stop(void)
--
^ permalink raw reply [flat|nested] 12+ messages in thread
* [patch 3/5] cell: updated driver for DDR2 memory on AXON
2007-06-18 22:42 [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
2007-06-18 22:42 ` [patch 1/5] Enable SPU switch notification to detect currently active SPU tasks Arnd Bergmann
2007-06-18 22:42 ` [patch 2/5] Add support to OProfile for profiling Cell/B.E. SPUs Arnd Bergmann
@ 2007-06-18 22:42 ` Arnd Bergmann
[not found] ` <20070619154812.GA20347@ps3linux.grid.fixstars.com>
2007-06-18 22:42 ` [patch 4/5] cell: saving spus information for kexec crash Arnd Bergmann
` (2 subsequent siblings)
5 siblings, 1 reply; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-18 22:42 UTC (permalink / raw)
To: linuxppc-dev
From: Maxim Shchetynin <maxim@de.ibm.com>
The Axon bridge chip used on new Cell/B.E. based blade servers
comes with a DDR2 memory controller that can be used to
attach cheap memory modules, as opposed to the high-speed
XDR memory that is used by the CPU itself.
Since the memory controller does not participate in the
cache coherency protocol, we can not use the memory direcly
for Linux applications, but by providing a block device
it can be used for swap space, temporary file storage and
through the use of the direct_access block device operation
for mapping into user addresses, when it is mounted with
an appropriate file system
Signed-off-by: Maxim Shchetynin <maxim@de.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Index: linux-2.6/arch/powerpc/platforms/Kconfig
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/Kconfig
+++ linux-2.6/arch/powerpc/platforms/Kconfig
@@ -250,4 +250,14 @@ config CPM2
you wish to build a kernel for a machine with a CPM2 coprocessor
on it (826x, 827x, 8560).
+config AXON_RAM
+ tristate "Axon DDR2 memory device driver"
+ depends on PPC_IBM_CELL_BLADE
+ default m
+ help
+ It registers one block device per Axon's DDR2 memory bank found
+ on a system. Block devices are called axonram?, their major and
+ minor numbers are available in /proc/devices, /proc/partitions or
+ in /sys/block/axonram?/dev.
+
endmenu
Index: linux-2.6/arch/powerpc/sysdev/Makefile
===================================================================
--- linux-2.6.orig/arch/powerpc/sysdev/Makefile
+++ linux-2.6/arch/powerpc/sysdev/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_TSI108_BRIDGE) += tsi108_pc
obj-$(CONFIG_QUICC_ENGINE) += qe_lib/
mv64x60-$(CONFIG_PCI) += mv64x60_pci.o
obj-$(CONFIG_MV64X60) += $(mv64x60-y) mv64x60_pic.o mv64x60_dev.o
+obj-$(CONFIG_AXON_RAM) += axonram.o
# contains only the suspend handler for time
obj-$(CONFIG_PM) += timer.o
Index: linux-2.6/arch/powerpc/sysdev/axonram.c
===================================================================
--- /dev/null
+++ linux-2.6/arch/powerpc/sysdev/axonram.c
@@ -0,0 +1,394 @@
+/*
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2006
+ *
+ * Author: Maxim Shchetynin <maxim@de.ibm.com>
+ *
+ * Axon DDR2 device driver.
+ * It registers one block device per Axon's DDR2 memory bank found on a system.
+ * Block devices are called axonram?, their major and minor numbers are
+ * available in /proc/devices, /proc/partitions or in /sys/block/axonram?/dev.
+ *
+ * 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, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/irqreturn.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/of_device.h>
+#include <asm/of_platform.h>
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/string.h>
+
+#define AXON_RAM_MODULE_NAME "axonram"
+#define AXON_RAM_DEVICE_NAME "axonram"
+#define AXON_RAM_MINORS_PER_DISK 16
+#define AXON_RAM_BLOCK_SHIFT PAGE_SHIFT
+#define AXON_RAM_BLOCK_SIZE 1 << AXON_RAM_BLOCK_SHIFT
+#define AXON_RAM_SECTOR_SHIFT 9
+#define AXON_RAM_SECTOR_SIZE 1 << AXON_RAM_SECTOR_SHIFT
+#define AXON_RAM_IRQ_FLAGS IRQF_SHARED | IRQF_TRIGGER_RISING
+
+struct axon_ram_bank {
+ struct of_device *device;
+ struct gendisk *disk;
+ unsigned int irq_correctable;
+ unsigned int irq_uncorrectable;
+ unsigned long ph_addr;
+ unsigned long io_addr;
+ unsigned long size;
+ unsigned long ecc_counter;
+};
+
+static ssize_t
+axon_ram_sysfs_ecc(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct of_device *device = to_of_device(dev);
+ struct axon_ram_bank *bank = device->dev.platform_data;
+
+ BUG_ON(!bank);
+
+ return sprintf(buf, "%ld\n", bank->ecc_counter);
+}
+
+static DEVICE_ATTR(ecc, S_IRUGO, axon_ram_sysfs_ecc, NULL);
+
+/**
+ * axon_ram_irq_handler - interrupt handler for Axon RAM ECC
+ * @irq: interrupt ID
+ * @dev: pointer to of_device
+ */
+static irqreturn_t
+axon_ram_irq_handler(int irq, void *dev)
+{
+ struct of_device *device = dev;
+ struct axon_ram_bank *bank = device->dev.platform_data;
+
+ BUG_ON(!bank);
+
+ if (irq == bank->irq_correctable) {
+ dev_err(&device->dev, "Correctable memory error occured\n");
+ bank->ecc_counter++;
+ return IRQ_HANDLED;
+ } else if (irq == bank->irq_uncorrectable) {
+ dev_err(&device->dev, "Uncorrectable memory error occured\n");
+ panic("Critical ECC error on %s", device->node->full_name);
+ }
+
+ return IRQ_NONE;
+}
+
+/**
+ * axon_ram_make_request - make_request() method for block device
+ * @queue, @bio: see blk_queue_make_request()
+ */
+static int
+axon_ram_make_request(struct request_queue *queue, struct bio *bio)
+{
+ struct axon_ram_bank *bank = bio->bi_bdev->bd_disk->private_data;
+ unsigned long phys_mem, phys_end;
+ void *user_mem;
+ struct bio_vec *vec;
+ unsigned int transfered;
+ unsigned short idx;
+ int rc = 0;
+
+ phys_mem = bank->io_addr + (bio->bi_sector << AXON_RAM_SECTOR_SHIFT);
+ phys_end = bank->io_addr + bank->size;
+ transfered = 0;
+ bio_for_each_segment(vec, bio, idx) {
+ if (unlikely(phys_mem + vec->bv_len > phys_end)) {
+ bio_io_error(bio, bio->bi_size);
+ rc = -ERANGE;
+ break;
+ }
+
+ user_mem = page_address(vec->bv_page) + vec->bv_offset;
+ if (bio_data_dir(bio) == READ)
+ memcpy(user_mem, (void*) phys_mem, vec->bv_len);
+ else
+ memcpy((void*) phys_mem, user_mem, vec->bv_len);
+
+ phys_mem += vec->bv_len;
+ transfered += vec->bv_len;
+ }
+ bio_endio(bio, transfered, 0);
+
+ return rc;
+}
+
+/**
+ * axon_ram_open - open() method for device
+ * @inode, @file: see file_operations method
+ */
+static int
+axon_ram_open(struct inode *inode, struct file *file)
+{
+ inode->i_bdev->bd_block_size = AXON_RAM_BLOCK_SIZE;
+
+ return 0;
+}
+
+/**
+ * axon_ram_direct_access - direct_access() method for block device
+ * @device, @sector, @data: see block_device_operations method
+ */
+static int
+axon_ram_direct_access(struct block_device *device, sector_t sector,
+ unsigned long *data)
+{
+ struct axon_ram_bank *bank = device->bd_disk->private_data;
+ loff_t offset;
+
+ offset = sector << AXON_RAM_SECTOR_SHIFT;
+ if (offset >= bank->size) {
+ dev_err(&bank->device->dev, "Access outside of address space\n");
+ return -ERANGE;
+ }
+
+ *data = bank->ph_addr + offset;
+
+ return 0;
+}
+
+static struct block_device_operations axon_ram_devops = {
+ .owner = THIS_MODULE,
+ .open = axon_ram_open,
+ .direct_access = axon_ram_direct_access
+};
+
+/**
+ * axon_ram_probe - probe() method for platform driver
+ * @device, @device_id: see of_platform_driver method
+ */
+static int
+axon_ram_probe(struct of_device *device, const struct of_device_id *device_id)
+{
+ static int axon_ram_bank_id = -1;
+ struct axon_ram_bank *bank;
+ struct resource resource;
+ int rc = 0;
+
+ axon_ram_bank_id++;
+
+ dev_info(&device->dev, "Found memory controller on %s\n",
+ device->node->full_name);
+
+ bank = kzalloc(sizeof(struct axon_ram_bank), GFP_KERNEL);
+ if (bank == NULL) {
+ dev_err(&device->dev, "Out of memory\n");
+ rc = -ENOMEM;
+ goto failed;
+ }
+
+ device->dev.platform_data = bank;
+
+ bank->device = device;
+
+ if (of_address_to_resource(device->node, 0, &resource) != 0) {
+ dev_err(&device->dev, "Cannot access device tree\n");
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ bank->size = resource.end - resource.start + 1;
+
+ if (bank->size == 0) {
+ dev_err(&device->dev, "No DDR2 memory found for %s%d\n",
+ AXON_RAM_DEVICE_NAME, axon_ram_bank_id);
+ rc = -ENODEV;
+ goto failed;
+ }
+
+ dev_info(&device->dev, "Register DDR2 memory device %s%d with %luMB\n",
+ AXON_RAM_DEVICE_NAME, axon_ram_bank_id, bank->size >> 20);
+
+ bank->ph_addr = resource.start;
+ bank->io_addr = (unsigned long) ioremap_flags(
+ bank->ph_addr, bank->size, _PAGE_NO_CACHE);
+ if (bank->io_addr == 0) {
+ dev_err(&device->dev, "ioremap() failed\n");
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ bank->disk = alloc_disk(AXON_RAM_MINORS_PER_DISK);
+ if (bank->disk == NULL) {
+ dev_err(&device->dev, "Cannot register disk\n");
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ bank->disk->first_minor = 0;
+ bank->disk->fops = &axon_ram_devops;
+ bank->disk->private_data = bank;
+ bank->disk->driverfs_dev = &device->dev;
+
+ sprintf(bank->disk->disk_name, "%s%d",
+ AXON_RAM_DEVICE_NAME, axon_ram_bank_id);
+ bank->disk->major = register_blkdev(0, bank->disk->disk_name);
+ if (bank->disk->major < 0) {
+ dev_err(&device->dev, "Cannot register block device\n");
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ bank->disk->queue = blk_alloc_queue(GFP_KERNEL);
+ if (bank->disk->queue == NULL) {
+ dev_err(&device->dev, "Cannot register disk queue\n");
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT);
+ blk_queue_make_request(bank->disk->queue, axon_ram_make_request);
+ blk_queue_hardsect_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE);
+ add_disk(bank->disk);
+
+ bank->irq_correctable = irq_of_parse_and_map(device->node, 0);
+ bank->irq_uncorrectable = irq_of_parse_and_map(device->node, 1);
+ if ((bank->irq_correctable <= 0) || (bank->irq_uncorrectable <= 0)) {
+ dev_err(&device->dev, "Cannot access ECC interrupt ID\n");
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ rc = request_irq(bank->irq_correctable, axon_ram_irq_handler,
+ AXON_RAM_IRQ_FLAGS, bank->disk->disk_name, device);
+ if (rc != 0) {
+ dev_err(&device->dev, "Cannot register ECC interrupt handler\n");
+ bank->irq_correctable = bank->irq_uncorrectable = 0;
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ rc = request_irq(bank->irq_uncorrectable, axon_ram_irq_handler,
+ AXON_RAM_IRQ_FLAGS, bank->disk->disk_name, device);
+ if (rc != 0) {
+ dev_err(&device->dev, "Cannot register ECC interrupt handler\n");
+ bank->irq_uncorrectable = 0;
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ rc = device_create_file(&device->dev, &dev_attr_ecc);
+ if (rc != 0) {
+ dev_err(&device->dev, "Cannot create sysfs file\n");
+ rc = -EFAULT;
+ goto failed;
+ }
+
+ return 0;
+
+failed:
+ if (bank != NULL) {
+ if (bank->irq_uncorrectable > 0)
+ free_irq(bank->irq_uncorrectable, device);
+ if (bank->irq_correctable > 0)
+ free_irq(bank->irq_correctable, device);
+ if (bank->disk != NULL) {
+ if (bank->disk->queue != NULL)
+ blk_cleanup_queue(bank->disk->queue);
+ if (bank->disk->major > 0)
+ unregister_blkdev(bank->disk->major,
+ bank->disk->disk_name);
+ del_gendisk(bank->disk);
+ }
+ device->dev.platform_data = NULL;
+ if (bank->io_addr != 0)
+ iounmap((void __iomem*) bank->io_addr);
+ kfree(bank);
+ }
+
+ return rc;
+}
+
+/**
+ * axon_ram_remove - remove() method for platform driver
+ * @device: see of_platform_driver method
+ */
+static int
+axon_ram_remove(struct of_device *device)
+{
+ struct axon_ram_bank *bank = device->dev.platform_data;
+
+ BUG_ON(!bank || !bank->disk);
+
+ device_remove_file(&device->dev, &dev_attr_ecc);
+ free_irq(bank->irq_uncorrectable, device);
+ free_irq(bank->irq_correctable, device);
+ blk_cleanup_queue(bank->disk->queue);
+ unregister_blkdev(bank->disk->major, bank->disk->disk_name);
+ del_gendisk(bank->disk);
+ iounmap((void __iomem*) bank->io_addr);
+ kfree(bank);
+
+ return 0;
+}
+
+static struct of_device_id axon_ram_device_id[] = {
+ {
+ .type = "dma-memory"
+ },
+ {}
+};
+
+static struct of_platform_driver axon_ram_driver = {
+ .owner = THIS_MODULE,
+ .name = AXON_RAM_MODULE_NAME,
+ .match_table = axon_ram_device_id,
+ .probe = axon_ram_probe,
+ .remove = axon_ram_remove
+};
+
+/**
+ * axon_ram_init
+ */
+static int __init
+axon_ram_init(void)
+{
+ return of_register_platform_driver(&axon_ram_driver);
+}
+
+/**
+ * axon_ram_exit
+ */
+static void __exit
+axon_ram_exit(void)
+{
+ of_unregister_platform_driver(&axon_ram_driver);
+}
+
+module_init(axon_ram_init);
+module_exit(axon_ram_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Maxim Shchetynin <maxim@de.ibm.com>");
+MODULE_DESCRIPTION("Axon DDR2 RAM device driver for IBM Cell BE");
--
^ permalink raw reply [flat|nested] 12+ messages in thread
* [patch 4/5] cell: saving spus information for kexec crash
2007-06-18 22:42 [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
` (2 preceding siblings ...)
2007-06-18 22:42 ` [patch 3/5] cell: updated driver for DDR2 memory on AXON Arnd Bergmann
@ 2007-06-18 22:42 ` Arnd Bergmann
2007-06-18 23:58 ` [Cbe-oss-dev] " Michael Ellerman
2007-06-18 22:42 ` [patch 5/5] Update cell_defconfig Arnd Bergmann
2007-06-18 23:01 ` [Cbe-oss-dev] [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
5 siblings, 1 reply; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-18 22:42 UTC (permalink / raw)
To: linuxppc-dev
From: Andre Detsch <adetsch@br.ibm.com>
This patch adds support for investigating spus information after a
kernel crash event, through kdump vmcore file.
Implementation is based on xmon code, but the new functionality was
kept independent from xmon.
Signed-off-by: Lucio Jose Herculano Correia <luciojhc@br.ibm.com>
Signed-off-by: Andre Detsch <adetsch@br.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Index: linux-2.6/arch/powerpc/kernel/crash.c
===================================================================
--- linux-2.6.orig/arch/powerpc/kernel/crash.c
+++ linux-2.6/arch/powerpc/kernel/crash.c
@@ -219,6 +219,70 @@ void crash_kexec_secondary(struct pt_reg
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 (spu->number >= CRASH_NUM_SPUS) {
+ WARN_ON(1);
+ continue;
+ }
+
+ crash_spu_info[spu->number].spu = spu;
+ }
+}
+
+#endif /* CONFIG_SPU_BASE */
void default_machine_crash_shutdown(struct pt_regs *regs)
{
@@ -254,6 +318,9 @@ void default_machine_crash_shutdown(stru
crash_save_cpu(regs, crashing_cpu);
crash_kexec_prepare_cpus(crashing_cpu);
cpu_set(crashing_cpu, cpus_in_crash);
+#ifdef CONFIG_SPU_BASE
+ crash_kexec_stop_spus();
+#endif
if (ppc_md.kexec_cpu_down)
ppc_md.kexec_cpu_down(1, 0);
}
Index: linux-2.6/include/asm-powerpc/spu.h
===================================================================
--- linux-2.6.orig/include/asm-powerpc/spu.h
+++ linux-2.6/include/asm-powerpc/spu.h
@@ -166,6 +166,10 @@ int spu_irq_class_0_bottom(struct spu *s
int spu_irq_class_1_bottom(struct spu *spu);
void spu_irq_setaffinity(struct spu *spu, int cpu);
+#ifdef CONFIG_KEXEC
+void crash_register_spus(struct list_head *list);
+#endif
+
extern void spu_invalidate_slbs(struct spu *spu);
extern void spu_associate_mm(struct spu *spu, struct mm_struct *mm);
Index: linux-2.6/arch/powerpc/platforms/cell/spu_base.c
===================================================================
--- linux-2.6.orig/arch/powerpc/platforms/cell/spu_base.c
+++ linux-2.6/arch/powerpc/platforms/cell/spu_base.c
@@ -610,6 +610,9 @@ static int __init init_spu_base(void)
}
xmon_register_spus(&spu_full_list);
+#ifdef CONFIG_KEXEC
+ crash_register_spus(&spu_full_list);
+#endif
return 0;
--
^ permalink raw reply [flat|nested] 12+ messages in thread
* [patch 5/5] Update cell_defconfig
2007-06-18 22:42 [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
` (3 preceding siblings ...)
2007-06-18 22:42 ` [patch 4/5] cell: saving spus information for kexec crash Arnd Bergmann
@ 2007-06-18 22:42 ` Arnd Bergmann
2007-06-18 23:01 ` [Cbe-oss-dev] [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
5 siblings, 0 replies; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-18 22:42 UTC (permalink / raw)
To: linuxppc-dev
From: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
---
Index: linux-2.6/arch/powerpc/configs/cell_defconfig
===================================================================
--- linux-2.6.orig/arch/powerpc/configs/cell_defconfig
+++ linux-2.6/arch/powerpc/configs/cell_defconfig
@@ -1,9 +1,23 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.21-rc6
-# Mon Apr 23 20:46:48 2007
+# Linux kernel version: 2.6.22-rc4
+# Sat Jun 16 20:45:34 2007
#
CONFIG_PPC64=y
+
+#
+# Processor support
+#
+# CONFIG_POWER4_ONLY is not set
+CONFIG_POWER3=y
+CONFIG_POWER4=y
+CONFIG_PPC_FPU=y
+CONFIG_ALTIVEC=y
+CONFIG_PPC_STD_MMU=y
+CONFIG_PPC_MM_SLICES=y
+CONFIG_VIRT_CPU_ACCOUNTING=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
CONFIG_64BIT=y
CONFIG_PPC_MERGE=y
CONFIG_MMU=y
@@ -27,23 +41,10 @@ CONFIG_PPC_UDBG_16550=y
CONFIG_AUDIT_ARCH=y
CONFIG_GENERIC_BUG=y
# CONFIG_DEFAULT_UIMAGE is not set
-
-#
-# Processor support
-#
-# CONFIG_POWER4_ONLY is not set
-CONFIG_POWER3=y
-CONFIG_POWER4=y
-CONFIG_PPC_FPU=y
# CONFIG_PPC_DCR_NATIVE is not set
CONFIG_PPC_DCR_MMIO=y
CONFIG_PPC_DCR=y
CONFIG_PPC_OF_PLATFORM_PCI=y
-CONFIG_ALTIVEC=y
-CONFIG_PPC_STD_MMU=y
-CONFIG_VIRT_CPU_ACCOUNTING=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=4
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
#
@@ -69,6 +70,7 @@ CONFIG_SYSVIPC_SYSCTL=y
# CONFIG_AUDIT is not set
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=15
CONFIG_CPUSETS=y
CONFIG_SYSFS_DEPRECATED=y
# CONFIG_RELAY is not set
@@ -87,14 +89,19 @@ CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
CONFIG_SHMEM=y
-CONFIG_SLAB=y
CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+# CONFIG_SLOB is not set
CONFIG_RT_MUTEXES=y
# CONFIG_TINY_SHMEM is not set
CONFIG_BASE_SMALL=0
-# CONFIG_SLOB is not set
#
# Loadable module support
@@ -131,7 +138,6 @@ CONFIG_DEFAULT_IOSCHED="anticipatory"
#
CONFIG_PPC_MULTIPLATFORM=y
# CONFIG_EMBEDDED6xx is not set
-# CONFIG_APUS is not set
# CONFIG_PPC_PSERIES is not set
# CONFIG_PPC_ISERIES is not set
# CONFIG_PPC_MPC52xx is not set
@@ -151,7 +157,11 @@ CONFIG_PS3_HTAB_SIZE=20
CONFIG_PS3_USE_LPAR_ADDR=y
CONFIG_PS3_VUART=y
CONFIG_PS3_PS3AV=y
-CONFIG_PS3_SYS_MANAGER=y
+CONFIG_PS3_SYS_MANAGER=m
+CONFIG_PS3_STORAGE=y
+CONFIG_PS3_DISK=y
+CONFIG_PS3_ROM=m
+CONFIG_PS3_FLASH=m
CONFIG_PPC_CELL=y
CONFIG_PPC_CELL_NATIVE=y
CONFIG_PPC_IBM_CELL_BLADE=y
@@ -163,9 +173,17 @@ CONFIG_SPU_FS=m
CONFIG_SPU_BASE=y
CONFIG_CBE_RAS=y
CONFIG_CBE_THERM=m
+CONFIG_CBE_CPUFREQ=m
+# CONFIG_PQ2ADS is not set
CONFIG_PPC_NATIVE=y
CONFIG_UDBG_RTAS_CONSOLE=y
CONFIG_PPC_UDBG_BEAT=y
+CONFIG_PPC_SYSTEMSIM=y
+# CONFIG_SYSTEMSIM_IDLE is not set
+# CONFIG_SYSTEMSIM_BOOT is not set
+CONFIG_MPIC=y
+# CONFIG_MPIC_WEIRD is not set
+# CONFIG_PPC_I8259 is not set
# CONFIG_U3_DART is not set
CONFIG_PPC_RTAS=y
# CONFIG_RTAS_ERROR_LOGGING is not set
@@ -177,9 +195,24 @@ CONFIG_MMIO_NVRAM=y
# CONFIG_PPC_970_NAP is not set
CONFIG_PPC_INDIRECT_IO=y
CONFIG_GENERIC_IOMAP=y
-# CONFIG_CPU_FREQ_PMAC64 is not set
-# CONFIG_WANT_EARLY_SERIAL is not set
-CONFIG_MPIC=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_TABLE=m
+CONFIG_CPU_FREQ_DEBUG=y
+CONFIG_CPU_FREQ_STAT=m
+CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_POWERSAVE=m
+CONFIG_CPU_FREQ_GOV_USERSPACE=m
+CONFIG_CPU_FREQ_GOV_ONDEMAND=m
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
+
+#
+# CPU Frequency drivers
+#
+# CONFIG_CPM2 is not set
+CONFIG_AXON_RAM=m
#
# Kernel options
@@ -224,12 +257,14 @@ CONFIG_RESOURCES_64BIT=y
CONFIG_ZONE_DMA_FLAG=1
CONFIG_ARCH_MEMORY_PROBE=y
CONFIG_NODES_SPAN_OTHER_NODES=y
+CONFIG_PPC_HAS_HASH_64K=y
CONFIG_PPC_64K_PAGES=y
CONFIG_SCHED_SMT=y
CONFIG_PROC_DEVICETREE=y
# CONFIG_CMDLINE_BOOL is not set
# CONFIG_PM is not set
CONFIG_SECCOMP=y
+# CONFIG_WANT_DEVICE_TREE is not set
CONFIG_ISA_DMA_API=y
#
@@ -237,22 +272,18 @@ CONFIG_ISA_DMA_API=y
#
CONFIG_ZONE_DMA=y
CONFIG_GENERIC_ISA_DMA=y
-# CONFIG_MPIC_WEIRD is not set
-# CONFIG_PPC_I8259 is not set
# CONFIG_PPC_INDIRECT_PCI is not set
CONFIG_PCI=y
CONFIG_PCI_DOMAINS=y
CONFIG_PCIEPORTBUS=y
+CONFIG_ARCH_SUPPORTS_MSI=y
+CONFIG_PCI_MSI=y
# CONFIG_PCI_DEBUG is not set
#
# PCCARD (PCMCIA/CardBus) support
#
# CONFIG_PCCARD is not set
-
-#
-# PCI Hotplug Support
-#
# CONFIG_HOTPLUG_PCI is not set
CONFIG_KERNEL_START=0xc000000000000000
@@ -264,7 +295,6 @@ CONFIG_NET=y
#
# Networking options
#
-# CONFIG_NETDEBUG is not set
CONFIG_PACKET=y
# CONFIG_PACKET_MMAP is not set
CONFIG_UNIX=y
@@ -300,14 +330,11 @@ CONFIG_INET_TCP_DIAG=y
CONFIG_TCP_CONG_CUBIC=y
CONFIG_DEFAULT_TCP_CONG="cubic"
# CONFIG_TCP_MD5SIG is not set
-
-#
-# IP: Virtual Server Configuration
-#
# CONFIG_IP_VS is not set
CONFIG_IPV6=y
# CONFIG_IPV6_PRIVACY is not set
# CONFIG_IPV6_ROUTER_PREF is not set
+# CONFIG_IPV6_OPTIMISTIC_DAD is not set
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
@@ -332,6 +359,7 @@ CONFIG_NETFILTER_NETLINK=m
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NETFILTER_NETLINK_LOG=m
# CONFIG_NF_CONNTRACK_ENABLED is not set
+# CONFIG_NF_CONNTRACK is not set
CONFIG_NETFILTER_XTABLES=m
CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
CONFIG_NETFILTER_XT_TARGET_DSCP=m
@@ -389,20 +417,8 @@ CONFIG_IP_NF_ARP_MANGLE=m
#
# CONFIG_IP6_NF_QUEUE is not set
# CONFIG_IP6_NF_IPTABLES is not set
-
-#
-# DCCP Configuration (EXPERIMENTAL)
-#
# CONFIG_IP_DCCP is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
# CONFIG_IP_SCTP is not set
-
-#
-# TIPC Configuration (EXPERIMENTAL)
-#
# CONFIG_TIPC is not set
# CONFIG_ATM is not set
# CONFIG_BRIDGE is not set
@@ -420,6 +436,7 @@ CONFIG_IP_NF_ARP_MANGLE=m
# QoS and/or fair queueing
#
# CONFIG_NET_SCHED is not set
+CONFIG_NET_SCH_FIFO=y
CONFIG_NET_CLS_ROUTE=y
#
@@ -429,7 +446,18 @@ CONFIG_NET_CLS_ROUTE=y
# CONFIG_HAMRADIO is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+
+#
+# Wireless
+#
+CONFIG_CFG80211=m
+CONFIG_WIRELESS_EXT=y
+CONFIG_MAC80211=m
+# CONFIG_MAC80211_DEBUGFS is not set
+# CONFIG_MAC80211_DEBUG is not set
# CONFIG_IEEE80211 is not set
+# CONFIG_RFKILL is not set
#
# Device Drivers
@@ -449,10 +477,6 @@ CONFIG_FW_LOADER=y
# Connector - unified userspace <-> kernelspace linker
#
# CONFIG_CONNECTOR is not set
-
-#
-# Memory Technology Devices (MTD)
-#
# CONFIG_MTD is not set
#
@@ -483,18 +507,18 @@ CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=131072
CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
+CONFIG_BLK_DEV_SYSTEMSIM=m
# CONFIG_CDROM_PKTCDVD is not set
# CONFIG_ATA_OVER_ETH is not set
#
# Misc devices
#
+# CONFIG_PHANTOM is not set
# CONFIG_SGI_IOC4 is not set
# CONFIG_TIFM_CORE is not set
-
-#
-# ATA/ATAPI/MFM/RLL support
-#
+# CONFIG_BLINK is not set
+# CONFIG_EEPROM_93CX6 is not set
CONFIG_IDE=y
CONFIG_BLK_DEV_IDE=y
@@ -509,6 +533,7 @@ CONFIG_IDEDISK_MULTI_MODE=y
# CONFIG_BLK_DEV_IDEFLOPPY is not set
# CONFIG_BLK_DEV_IDESCSI is not set
# CONFIG_IDE_TASK_IOCTL is not set
+# CONFIG_IDE_PROC_FS is not set
#
# IDE chipset support/bugfixes
@@ -516,6 +541,7 @@ CONFIG_IDEDISK_MULTI_MODE=y
CONFIG_IDE_GENERIC=y
CONFIG_BLK_DEV_IDEPCI=y
CONFIG_IDEPCI_SHARE_IRQ=y
+CONFIG_IDEPCI_PCIBUS_ORDER=y
# CONFIG_BLK_DEV_OFFBOARD is not set
CONFIG_BLK_DEV_GENERIC=y
# CONFIG_BLK_DEV_OPTI621 is not set
@@ -580,6 +606,7 @@ CONFIG_CHR_DEV_SG=y
# CONFIG_SCSI_CONSTANTS is not set
# CONFIG_SCSI_LOGGING is not set
# CONFIG_SCSI_SCAN_ASYNC is not set
+CONFIG_SCSI_WAIT_SCAN=m
#
# SCSI Transports
@@ -626,10 +653,6 @@ CONFIG_SCSI_SAS_ATTRS=y
# CONFIG_SCSI_DC390T is not set
# CONFIG_SCSI_DEBUG is not set
# CONFIG_SCSI_SRP is not set
-
-#
-# Serial ATA (prod) and Parallel ATA (experimental) drivers
-#
CONFIG_ATA=y
# CONFIG_ATA_NONSTANDARD is not set
# CONFIG_SATA_AHCI is not set
@@ -652,6 +675,7 @@ CONFIG_SATA_PROMISE=y
# CONFIG_PATA_AMD is not set
# CONFIG_PATA_ARTOP is not set
# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_CMD640_PCI is not set
# CONFIG_PATA_CMD64X is not set
# CONFIG_PATA_CS5520 is not set
# CONFIG_PATA_CS5530 is not set
@@ -705,6 +729,7 @@ CONFIG_DM_MIRROR=m
CONFIG_DM_ZERO=m
CONFIG_DM_MULTIPATH=m
# CONFIG_DM_MULTIPATH_EMC is not set
+# CONFIG_DM_DELAY is not set
#
# Fusion MPT device support
@@ -719,58 +744,32 @@ CONFIG_FUSION_MAX_SGE=128
#
# IEEE 1394 (FireWire) support
#
+# CONFIG_FIREWIRE is not set
# CONFIG_IEEE1394 is not set
#
# I2O device support
#
# CONFIG_I2O is not set
-
-#
-# Macintosh device drivers
-#
-# CONFIG_MAC_EMUMOUSEBTN is not set
-# CONFIG_WINDFARM is not set
-
-#
-# Network device support
-#
+# CONFIG_MACINTOSH_DRIVERS is not set
CONFIG_NETDEVICES=y
# CONFIG_DUMMY is not set
CONFIG_BONDING=m
# CONFIG_EQUALIZER is not set
CONFIG_TUN=y
-
-#
-# ARCnet devices
-#
# CONFIG_ARCNET is not set
-
-#
-# PHY device support
-#
# CONFIG_PHYLIB is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
CONFIG_NET_ETHERNET=y
CONFIG_MII=y
# CONFIG_HAPPYMEAL is not set
# CONFIG_SUNGEM is not set
# CONFIG_CASSINI is not set
# CONFIG_NET_VENDOR_3COM is not set
-
-#
-# Tulip family network device support
-#
# CONFIG_NET_TULIP is not set
# CONFIG_HP100 is not set
+CONFIG_SYSTEMSIM_NET=m
# CONFIG_NET_PCI is not set
-
-#
-# Ethernet (1000 Mbit)
-#
+CONFIG_NETDEV_1000=y
# CONFIG_ACENIC is not set
# CONFIG_DL2K is not set
CONFIG_E1000=m
@@ -784,36 +783,43 @@ CONFIG_E1000_NAPI=y
CONFIG_SKGE=m
CONFIG_SKY2=m
# CONFIG_SK98LIN is not set
+# CONFIG_VIA_VELOCITY is not set
CONFIG_TIGON3=y
# CONFIG_BNX2 is not set
CONFIG_SPIDER_NET=y
+CONFIG_GELIC_NET=m
+CONFIG_GELIC_WIRELESS=y
# CONFIG_QLA3XXX is not set
# CONFIG_ATL1 is not set
-
-#
-# Ethernet (10000 Mbit)
-#
-# CONFIG_CHELSIO_T1 is not set
-# CONFIG_CHELSIO_T3 is not set
-# CONFIG_IXGB is not set
-# CONFIG_S2IO is not set
-# CONFIG_MYRI10GE is not set
-# CONFIG_NETXEN_NIC is not set
-# CONFIG_PASEMI_MAC is not set
-
-#
-# Token Ring devices
-#
+# CONFIG_NETDEV_10000 is not set
+CONFIG_MLX4_CORE=m
# CONFIG_TR is not set
#
-# Wireless LAN (non-hamradio)
+# Wireless LAN
#
-# CONFIG_NET_RADIO is not set
+# CONFIG_WLAN_PRE80211 is not set
+CONFIG_WLAN_80211=y
+# CONFIG_IPW2100 is not set
+# CONFIG_IPW2200 is not set
+# CONFIG_LIBERTAS is not set
+# CONFIG_AIRO is not set
+# CONFIG_HERMES is not set
+# CONFIG_ATMEL is not set
+# CONFIG_PRISM54 is not set
+# CONFIG_USB_ZD1201 is not set
+# CONFIG_RTL8187 is not set
+# CONFIG_HOSTAP is not set
#
-# Wan interfaces
+# USB Network Adapters
#
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET_MII is not set
+# CONFIG_USB_USBNET is not set
# CONFIG_WAN is not set
# CONFIG_FDDI is not set
# CONFIG_HIPPI is not set
@@ -840,6 +846,7 @@ CONFIG_SPIDER_NET=y
#
CONFIG_INPUT=y
# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
#
# Userland interfaces
@@ -859,6 +866,7 @@ CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
# CONFIG_INPUT_TOUCHSCREEN is not set
# CONFIG_INPUT_MISC is not set
@@ -921,6 +929,8 @@ CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_UNIX98_PTYS=y
# CONFIG_LEGACY_PTYS is not set
CONFIG_HVC_DRIVER=y
+# CONFIG_HVC_FSS is not set
+# CONFIG_PPC_EARLY_DEBUG_FSS is not set
CONFIG_HVC_RTAS=y
CONFIG_HVC_BEAT=y
@@ -933,10 +943,6 @@ CONFIG_IPMI_DEVICE_INTERFACE=m
CONFIG_IPMI_SI=m
CONFIG_IPMI_WATCHDOG=m
CONFIG_IPMI_POWEROFF=m
-
-#
-# Watchdog Cards
-#
CONFIG_WATCHDOG=y
# CONFIG_WATCHDOG_NOWAYOUT is not set
@@ -959,7 +965,6 @@ CONFIG_WATCHDOG=y
# CONFIG_HW_RANDOM is not set
CONFIG_GEN_RTC=y
# CONFIG_GEN_RTC_X is not set
-# CONFIG_DTLK is not set
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set
# CONFIG_AGP is not set
@@ -971,11 +976,9 @@ CONFIG_GEN_RTC=y
# TPM devices
#
# CONFIG_TCG_TPM is not set
-
-#
-# I2C support
-#
+CONFIG_DEVPORT=y
CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
# CONFIG_I2C_CHARDEV is not set
#
@@ -999,17 +1002,17 @@ CONFIG_I2C_ALGOBIT=y
# CONFIG_I2C_NFORCE2 is not set
# CONFIG_I2C_OCORES is not set
# CONFIG_I2C_PARPORT_LIGHT is not set
-# CONFIG_I2C_PASEMI is not set
# CONFIG_I2C_PROSAVAGE is not set
# CONFIG_I2C_SAVAGE4 is not set
+# CONFIG_I2C_SIMTEC is not set
# CONFIG_I2C_SIS5595 is not set
# CONFIG_I2C_SIS630 is not set
# CONFIG_I2C_SIS96X is not set
# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_TINY_USB is not set
# CONFIG_I2C_VIA is not set
# CONFIG_I2C_VIAPRO is not set
# CONFIG_I2C_VOODOO3 is not set
-# CONFIG_I2C_PCA_ISA is not set
#
# Miscellaneous I2C Chip support
@@ -1036,12 +1039,7 @@ CONFIG_I2C_ALGOBIT=y
# Dallas's 1-wire bus
#
# CONFIG_W1 is not set
-
-#
-# Hardware Monitoring support
-#
# CONFIG_HWMON is not set
-# CONFIG_HWMON_VID is not set
#
# Multifunction device drivers
@@ -1052,17 +1050,19 @@ CONFIG_I2C_ALGOBIT=y
# Multimedia devices
#
# CONFIG_VIDEO_DEV is not set
+# CONFIG_DVB_CORE is not set
+# CONFIG_DAB is not set
#
-# Digital Video Broadcasting Devices
+# Graphics support
#
-# CONFIG_DVB is not set
-# CONFIG_USB_DABUSB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
#
-# Graphics support
+# Display device support
#
-# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_VGASTATE is not set
# CONFIG_FB is not set
# CONFIG_FB_IBM_GXT4500 is not set
@@ -1084,6 +1084,17 @@ CONFIG_HID=m
# CONFIG_HID_DEBUG is not set
#
+# USB Input Devices
+#
+# CONFIG_USB_HID is not set
+
+#
+# USB HID Boot Protocol drivers
+#
+# CONFIG_USB_KBD is not set
+# CONFIG_USB_MOUSE is not set
+
+#
# USB support
#
CONFIG_USB_ARCH_HAS_HCD=y
@@ -1096,6 +1107,7 @@ CONFIG_USB=m
# Miscellaneous USB options
#
CONFIG_USB_DEVICEFS=y
+# CONFIG_USB_DEVICE_CLASS is not set
# CONFIG_USB_DYNAMIC_MINORS is not set
# CONFIG_USB_OTG is not set
@@ -1147,44 +1159,10 @@ CONFIG_USB_STORAGE=m
# CONFIG_USB_LIBUSUAL is not set
#
-# USB Input Devices
-#
-# CONFIG_USB_HID is not set
-
-#
-# USB HID Boot Protocol drivers
-#
-# CONFIG_USB_KBD is not set
-# CONFIG_USB_MOUSE is not set
-# CONFIG_USB_AIPTEK is not set
-# CONFIG_USB_WACOM is not set
-# CONFIG_USB_ACECAD is not set
-# CONFIG_USB_KBTAB is not set
-# CONFIG_USB_POWERMATE is not set
-# CONFIG_USB_TOUCHSCREEN is not set
-# CONFIG_USB_YEALINK is not set
-# CONFIG_USB_XPAD is not set
-# CONFIG_USB_ATI_REMOTE is not set
-# CONFIG_USB_ATI_REMOTE2 is not set
-# CONFIG_USB_KEYSPAN_REMOTE is not set
-# CONFIG_USB_APPLETOUCH is not set
-# CONFIG_USB_GTCO is not set
-
-#
# USB Imaging devices
#
# CONFIG_USB_MDC800 is not set
# CONFIG_USB_MICROTEK is not set
-
-#
-# USB Network Adapters
-#
-# CONFIG_USB_CATC is not set
-# CONFIG_USB_KAWETH is not set
-# CONFIG_USB_PEGASUS is not set
-# CONFIG_USB_RTL8150 is not set
-# CONFIG_USB_USBNET_MII is not set
-# CONFIG_USB_USBNET is not set
CONFIG_USB_MON=y
#
@@ -1228,10 +1206,6 @@ CONFIG_USB_MON=y
# USB Gadget Support
#
# CONFIG_USB_GADGET is not set
-
-#
-# MMC/SD Card support
-#
# CONFIG_MMC is not set
#
@@ -1253,10 +1227,13 @@ CONFIG_USB_MON=y
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_MAD=m
CONFIG_INFINIBAND_USER_ACCESS=m
+CONFIG_INFINIBAND_USER_MEM=y
CONFIG_INFINIBAND_ADDR_TRANS=y
CONFIG_INFINIBAND_MTHCA=m
CONFIG_INFINIBAND_MTHCA_DEBUG=y
+# CONFIG_INFINIBAND_IPATH is not set
# CONFIG_INFINIBAND_AMSO1100 is not set
+CONFIG_MLX4_INFINIBAND=m
CONFIG_INFINIBAND_IPOIB=m
# CONFIG_INFINIBAND_IPOIB_CM is not set
CONFIG_INFINIBAND_IPOIB_DEBUG=y
@@ -1287,14 +1264,6 @@ CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
#
#
-# Auxiliary Display support
-#
-
-#
-# Virtualization
-#
-
-#
# File systems
#
CONFIG_EXT2_FS=y
@@ -1389,6 +1358,7 @@ CONFIG_LOCKD_V4=y
CONFIG_NFS_ACL_SUPPORT=y
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=y
+# CONFIG_SUNRPC_BIND34 is not set
# CONFIG_RPCSEC_GSS_KRB5 is not set
# CONFIG_RPCSEC_GSS_SPKM3 is not set
# CONFIG_SMB_FS is not set
@@ -1418,6 +1388,7 @@ CONFIG_MSDOS_PARTITION=y
# CONFIG_SUN_PARTITION is not set
# CONFIG_KARMA_PARTITION is not set
CONFIG_EFI_PARTITION=y
+# CONFIG_SYSV68_PARTITION is not set
#
# Native Language Support
@@ -1468,7 +1439,6 @@ CONFIG_NLS_ISO8859_15=m
#
# CONFIG_DLM is not set
# CONFIG_UCC_SLOW is not set
-# CONFIG_UCC_FAST is not set
#
# Library routines
@@ -1476,6 +1446,7 @@ CONFIG_NLS_ISO8859_15=m
CONFIG_BITREVERSE=y
# CONFIG_CRC_CCITT is not set
# CONFIG_CRC16 is not set
+# CONFIG_CRC_ITU_T is not set
CONFIG_CRC32=y
# CONFIG_LIBCRC32C is not set
CONFIG_ZLIB_INFLATE=m
@@ -1487,6 +1458,7 @@ CONFIG_TEXTSEARCH_FSM=m
CONFIG_PLIST=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
#
# Instrumentation Support
@@ -1507,7 +1479,6 @@ CONFIG_DEBUG_FS=y
# CONFIG_HEADERS_CHECK is not set
CONFIG_DEBUG_KERNEL=y
# CONFIG_DEBUG_SHIRQ is not set
-CONFIG_LOG_BUF_SHIFT=15
# CONFIG_DETECT_SOFTLOCKUP is not set
# CONFIG_SCHEDSTATS is not set
# CONFIG_TIMER_STATS is not set
@@ -1548,6 +1519,7 @@ CONFIG_IRQSTACKS=y
#
CONFIG_CRYPTO=y
CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_ABLKCIPHER=m
CONFIG_CRYPTO_BLKCIPHER=m
CONFIG_CRYPTO_HASH=y
CONFIG_CRYPTO_MANAGER=y
@@ -1566,16 +1538,17 @@ CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_CBC=m
CONFIG_CRYPTO_PCBC=m
# CONFIG_CRYPTO_LRW is not set
+CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_DES=m
# CONFIG_CRYPTO_FCRYPT is not set
# CONFIG_CRYPTO_BLOWFISH is not set
# CONFIG_CRYPTO_TWOFISH is not set
# CONFIG_CRYPTO_SERPENT is not set
-# CONFIG_CRYPTO_AES is not set
+CONFIG_CRYPTO_AES=m
# CONFIG_CRYPTO_CAST5 is not set
# CONFIG_CRYPTO_CAST6 is not set
# CONFIG_CRYPTO_TEA is not set
-# CONFIG_CRYPTO_ARC4 is not set
+CONFIG_CRYPTO_ARC4=m
# CONFIG_CRYPTO_KHAZAD is not set
# CONFIG_CRYPTO_ANUBIS is not set
CONFIG_CRYPTO_DEFLATE=m
--
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [Cbe-oss-dev] [patch 0/5] cell patches for 2.6.23
2007-06-18 22:42 [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
` (4 preceding siblings ...)
2007-06-18 22:42 ` [patch 5/5] Update cell_defconfig Arnd Bergmann
@ 2007-06-18 23:01 ` Arnd Bergmann
5 siblings, 0 replies; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-18 23:01 UTC (permalink / raw)
To: cbe-oss-dev; +Cc: linuxppc-dev, paulus
On Tuesday 19 June 2007, Arnd Bergmann wrote:
> From:
> Arnd Bergmann <arnd@arndb.de>
> To:
> paulus@samba.org
> CC:
> powerpc-dev@ozlabs.org, cbe-oss-dev@ozlabs.org
It's getting late here, that should have been linuxppc-dev
instead of powerpc-dev, obviously. I hope at least the patches
are ok, when I can't handle the mail system any more...
Arnd <><
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [Cbe-oss-dev] [patch 4/5] cell: saving spus information for kexec crash
2007-06-18 22:42 ` [patch 4/5] cell: saving spus information for kexec crash Arnd Bergmann
@ 2007-06-18 23:58 ` Michael Ellerman
2007-06-20 18:52 ` André Detsch
0 siblings, 1 reply; 12+ messages in thread
From: Michael Ellerman @ 2007-06-18 23:58 UTC (permalink / raw)
To: Arnd Bergmann
Cc: Arnd Bergmann, linuxppc-dev list, paulus,
Lucio Jose Herculano Correia, Andre Detsch, cbe-oss-dev
[-- Attachment #1: Type: text/plain, Size: 4595 bytes --]
On Tue, 2007-06-19 at 00:42 +0200, Arnd Bergmann wrote:
> plain text document attachment (cell-spus-info-kexec-crash-1.diff)
> From: Andre Detsch <adetsch@br.ibm.com>
> This patch adds support for investigating spus information after a
> kernel crash event, through kdump vmcore file.
> Implementation is based on xmon code, but the new functionality was
> kept independent from xmon.
>
> Signed-off-by: Lucio Jose Herculano Correia <luciojhc@br.ibm.com>
> Signed-off-by: Andre Detsch <adetsch@br.ibm.com>
> Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
I'd like to have this patch share the emergency stopping logic with the
xmon code, I'll try and get a patch done in the next few days.
cheers
> Index: linux-2.6/arch/powerpc/kernel/crash.c
> ===================================================================
> --- linux-2.6.orig/arch/powerpc/kernel/crash.c
> +++ linux-2.6/arch/powerpc/kernel/crash.c
> @@ -219,6 +219,70 @@ void crash_kexec_secondary(struct pt_reg
> 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 (spu->number >= CRASH_NUM_SPUS) {
> + WARN_ON(1);
> + continue;
> + }
> +
> + crash_spu_info[spu->number].spu = spu;
> + }
> +}
> +
> +#endif /* CONFIG_SPU_BASE */
>
> void default_machine_crash_shutdown(struct pt_regs *regs)
> {
> @@ -254,6 +318,9 @@ void default_machine_crash_shutdown(stru
> crash_save_cpu(regs, crashing_cpu);
> crash_kexec_prepare_cpus(crashing_cpu);
> cpu_set(crashing_cpu, cpus_in_crash);
> +#ifdef CONFIG_SPU_BASE
> + crash_kexec_stop_spus();
> +#endif
> if (ppc_md.kexec_cpu_down)
> ppc_md.kexec_cpu_down(1, 0);
> }
> Index: linux-2.6/include/asm-powerpc/spu.h
> ===================================================================
> --- linux-2.6.orig/include/asm-powerpc/spu.h
> +++ linux-2.6/include/asm-powerpc/spu.h
> @@ -166,6 +166,10 @@ int spu_irq_class_0_bottom(struct spu *s
> int spu_irq_class_1_bottom(struct spu *spu);
> void spu_irq_setaffinity(struct spu *spu, int cpu);
>
> +#ifdef CONFIG_KEXEC
> +void crash_register_spus(struct list_head *list);
> +#endif
> +
> extern void spu_invalidate_slbs(struct spu *spu);
> extern void spu_associate_mm(struct spu *spu, struct mm_struct *mm);
>
> Index: linux-2.6/arch/powerpc/platforms/cell/spu_base.c
> ===================================================================
> --- linux-2.6.orig/arch/powerpc/platforms/cell/spu_base.c
> +++ linux-2.6/arch/powerpc/platforms/cell/spu_base.c
> @@ -610,6 +610,9 @@ static int __init init_spu_base(void)
> }
>
> xmon_register_spus(&spu_full_list);
> +#ifdef CONFIG_KEXEC
> + crash_register_spus(&spu_full_list);
> +#endif
>
> return 0;
>
>
> --
>
> _______________________________________________
> cbe-oss-dev mailing list
> cbe-oss-dev@ozlabs.org
> https://ozlabs.org/mailman/listinfo/cbe-oss-dev
--
Michael Ellerman
OzLabs, IBM Australia Development Lab
wwweb: http://michael.ellerman.id.au
phone: +61 2 6212 1183 (tie line 70 21183)
We do not inherit the earth from our ancestors,
we borrow it from our children. - S.M.A.R.T Person
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [Cbe-oss-dev] [patch 3/5] cell: updated driver for DDR2 memory on AXON
[not found] ` <20070619154812.GA20347@ps3linux.grid.fixstars.com>
@ 2007-06-19 23:03 ` Arnd Bergmann
0 siblings, 0 replies; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-19 23:03 UTC (permalink / raw)
To: cbe-oss-dev; +Cc: Akinobu Mita, linuxppc-dev
On Tuesday 19 June 2007, Akinobu Mita wrote:
> > + if (of_address_to_resource(device->node, 0, &resource) != 0) {
> > + dev_err(&device->dev, "Cannot access device tree\n");
> > + rc = -EFAULT;
> > + goto failed;
> > + }
>
> of_address_to_resource() returns error code on failure:
>
> rc = of_address_to_resource(device->node, 0, &resource);
> if (rc) {
> dev_err(&device->dev, "Cannot access device tree\n");
> goto failed;
> }
>
> is better.
Right.
> > + bank->ph_addr = resource.start;
> > + bank->io_addr = (unsigned long) ioremap_flags(
> > + bank->ph_addr, bank->size, _PAGE_NO_CACHE);
> > + if (bank->io_addr == 0) {
> > + dev_err(&device->dev, "ioremap() failed\n");
> > + rc = -EFAULT;
> > + goto failed;
> > + }
> > +
> > + bank->disk = alloc_disk(AXON_RAM_MINORS_PER_DISK);
> > + if (bank->disk == NULL) {
> > + dev_err(&device->dev, "Cannot register disk\n");
> > + rc = -EFAULT;
> > + goto failed;
> > + }
>
> -ENOMEM is better than -EFAULT. Because alloc_disk() failure happens
> only when it runs out of memory.
yes. EFAULT should only be used when an access to user memory has failed,
so it's wrong practically everywhere in here, your other comments are
obviously correct as well.
Arnd <><
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [Cbe-oss-dev] [patch 2/5] Add support to OProfile for profiling Cell/B.E. SPUs
2007-06-18 22:42 ` [patch 2/5] Add support to OProfile for profiling Cell/B.E. SPUs Arnd Bergmann
@ 2007-06-20 2:32 ` mita
2007-06-20 9:35 ` Arnd Bergmann
0 siblings, 1 reply; 12+ messages in thread
From: mita @ 2007-06-20 2:32 UTC (permalink / raw)
To: Arnd Bergmann
Cc: Arnd Bergmann, linuxppc-dev, paulus, Maynard Johnson, cbe-oss-dev,
Carl Love
> +static enum hrtimer_restart profile_spus(struct hrtimer * timer)
> +{
> + ktime_t kt;
> + int cpu, node, k, num_samples, spu_num;
> +
> + if (!spu_prof_running)
> + goto stop;
> +
> + for_each_online_cpu(cpu) {
> + if (cbe_get_hw_thread_id(cpu))
> + continue;
> +
> + node = cbe_cpu_to_node(cpu);
> +
> + /* There should only be on kernel thread at a time processing
> + * the samples. In the very unlikely case that the processing
> + * is taking a very long time and multiple kernel threads are
> + * started to process the samples. Make sure only one kernel
> + * thread is working on the samples array at a time. The
> + * sample array must be loaded and then processed for a given
> + * cpu. The sample array is not per cpu.
> + */
> + spin_lock_irqsave(&sample_array_lock,
> + sample_array_lock_flags);
> + num_samples = cell_spu_pc_collection(cpu);
> +
> + if (num_samples == 0) {
> + spin_unlock_irqrestore(&sample_array_lock,
> + sample_array_lock_flags);
> + continue;
> + }
> +
> + for (k = 0; k < SPUS_PER_NODE; k++) {
> + spu_num = k + (node * SPUS_PER_NODE);
> + spu_sync_buffer(spu_num,
> + samples + (k * TRACE_ARRAY_SIZE),
> + num_samples);
> + }
> +
> + spin_unlock_irqrestore(&sample_array_lock,
> + sample_array_lock_flags);
> +
> + }
> + smp_wmb();
> +
> + kt = ktime_set(0, profiling_interval);
> + if (!spu_prof_running)
> + goto stop;
> + hrtimer_forward(timer, timer->base->get_time(), kt);
> + return HRTIMER_RESTART;
> +
> + stop:
> + printk(KERN_INFO "SPU_PROF: spu-prof timer ending\n");
> + return HRTIMER_NORESTART;
> +}
> +
> +static struct hrtimer timer;
> +/*
> + * Entry point for SPU profiling.
> + * NOTE: SPU profiling is done system-wide, not per-CPU.
> + *
> + * cycles_reset is the count value specified by the user when
> + * setting up OProfile to count SPU_CYCLES.
> + */
> +void start_spu_profiling(unsigned int cycles_reset) {
> +
> + ktime_t kt;
> +
> + pr_debug("timer resolution: %lu\n",
> + TICK_NSEC);
> + kt = ktime_set(0, profiling_interval);
> + hrtimer_init(&timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
> + timer.expires = kt;
> + timer.function = profile_spus;
> +
> + /* Allocate arrays for collecting SPU PC samples */
> + samples = (u32 *) kzalloc(SPUS_PER_NODE *
> + TRACE_ARRAY_SIZE * sizeof(u32), GFP_KERNEL);
> +
- Unnecessary cast for kzalloc().
- Allocation failure is ignored here. But there is no error handling
in timer fuction (profile_spus), too.
> + spu_prof_running = 1;
> + hrtimer_start(&timer, kt, HRTIMER_MODE_REL);
> +}
> +
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [Cbe-oss-dev] [patch 2/5] Add support to OProfile for profiling Cell/B.E. SPUs
2007-06-20 2:32 ` [Cbe-oss-dev] " mita
@ 2007-06-20 9:35 ` Arnd Bergmann
0 siblings, 0 replies; 12+ messages in thread
From: Arnd Bergmann @ 2007-06-20 9:35 UTC (permalink / raw)
To: mita
Cc: Bob Nelson, linuxppc-dev, paulus, Maynard Johnson, cbe-oss-dev,
Carl Love
On Wednesday 20 June 2007, mita@fixstars.com wrote:
> > +
> > +=A0=A0=A0=A0=A0/* Allocate arrays for collecting SPU PC samples */
> > +=A0=A0=A0=A0=A0samples =3D (u32 *) kzalloc(SPUS_PER_NODE *
> > +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=
=A0=A0=A0=A0=A0=A0 =A0TRACE_ARRAY_SIZE * sizeof(u32), GFP_KERNEL);
> > +
>=20
> =A0- Unnecessary cast for kzalloc().
>=20
> =A0- Allocation failure is ignored here. But there is no error handling
> =A0 =A0in timer fuction (profile_spus), too.
Right. Bob, can you make a patch to remove the case and make sure that
we never access the sample array when the allocation has failed?
Arnd <><
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [Cbe-oss-dev] [patch 4/5] cell: saving spus information for kexec crash
2007-06-18 23:58 ` [Cbe-oss-dev] " Michael Ellerman
@ 2007-06-20 18:52 ` André Detsch
0 siblings, 0 replies; 12+ messages in thread
From: André Detsch @ 2007-06-20 18:52 UTC (permalink / raw)
To: michael
Cc: Arnd Bergmann, Arnd Bergmann, Luke Browning, linuxppc-dev list,
Lucio Jose Herculano Correia, cbe-oss-dev
Michael Ellerman wrote:
> On Tue, 2007-06-19 at 00:42 +0200, Arnd Bergmann wrote:
>> plain text document attachment (cell-spus-info-kexec-crash-1.diff)
>> From: Andre Detsch <adetsch@br.ibm.com>
>> This patch adds support for investigating spus information after a
>> kernel crash event, through kdump vmcore file.
>> Implementation is based on xmon code, but the new functionality was
>> kept independent from xmon.
>>
>> Signed-off-by: Lucio Jose Herculano Correia <luciojhc@br.ibm.com>
>> Signed-off-by: Andre Detsch <adetsch@br.ibm.com>
>> Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
>
>
> I'd like to have this patch share the emergency stopping logic with the
> xmon code, I'll try and get a patch done in the next few days.
>
Hi Michael,
What aspect of the patch do you think would benefit from sharing logic
with xmon? The structures (struct crash_spu + crash_register_spus
function) or the stop spus logic itself (crash_kexec_stop_spus)? Or both?
My first approach was actually to use the same structure and code as
xmon (as you might remember from an private email I've sent before
posting the patch). However, talking with Luke, we decided to keep xmon
and crash data independent from each other, since he was interested on
eventually allowing xmon to be run before the second kernel gets loaded.
So, having a separate structure for crash info would allow us to save
the exact state when the crash occurred, no matter of what the user did
while running xmon.
Best regards,
--
Andre Detsch
^ permalink raw reply [flat|nested] 12+ messages in thread
end of thread, other threads:[~2007-06-20 18:52 UTC | newest]
Thread overview: 12+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-06-18 22:42 [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
2007-06-18 22:42 ` [patch 1/5] Enable SPU switch notification to detect currently active SPU tasks Arnd Bergmann
2007-06-18 22:42 ` [patch 2/5] Add support to OProfile for profiling Cell/B.E. SPUs Arnd Bergmann
2007-06-20 2:32 ` [Cbe-oss-dev] " mita
2007-06-20 9:35 ` Arnd Bergmann
2007-06-18 22:42 ` [patch 3/5] cell: updated driver for DDR2 memory on AXON Arnd Bergmann
[not found] ` <20070619154812.GA20347@ps3linux.grid.fixstars.com>
2007-06-19 23:03 ` [Cbe-oss-dev] " Arnd Bergmann
2007-06-18 22:42 ` [patch 4/5] cell: saving spus information for kexec crash Arnd Bergmann
2007-06-18 23:58 ` [Cbe-oss-dev] " Michael Ellerman
2007-06-20 18:52 ` André Detsch
2007-06-18 22:42 ` [patch 5/5] Update cell_defconfig Arnd Bergmann
2007-06-18 23:01 ` [Cbe-oss-dev] [patch 0/5] cell patches for 2.6.23 Arnd Bergmann
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).