summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/oprofile/common.c
diff options
context:
space:
mode:
authorMaynard Johnson <maynardj@us.ibm.com>2006-11-20 18:45:16 +0100
committerPaul Mackerras <paulus@samba.org>2006-12-04 20:40:14 +1100
commit18f2190d796198fbb5d4bc4c87511acf3ced7d47 (patch)
tree621afac81fc83728a41fa5ff9ee3381a1b0f5921 /arch/powerpc/oprofile/common.c
parent0443bbd3d8496f9c2bc3e8c9d1833c6638722743 (diff)
downloadblackbird-op-linux-18f2190d796198fbb5d4bc4c87511acf3ced7d47.tar.gz
blackbird-op-linux-18f2190d796198fbb5d4bc4c87511acf3ced7d47.zip
[POWERPC] cell: Add oprofile support
Add PPU event-based and cycle-based profiling support to Oprofile for Cell. Oprofile is expected to collect data on all CPUs simultaneously. 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 a virtual counter routine. Initially, the counters are configured to collect data on the even CPUs in the system, one CPU per node. In order to capture the PC for the virtual CPU when the performance counter interrupt occurs (the specified number of events between samples has occurred), the even processors are configured to handle the performance counter interrupts for their node. The virtual counter routine is called via a kernel timer after the virtual sample time. The routine stops the counters, saves the current counts, loads the last counts for the other virtual CPU on the node, sets interrupts to be handled by the other virtual CPU and restarts the counters, the virtual timer routine is scheduled to run again. The virtual sample time is kept relatively small to make sure sampling occurs on both CPUs on the node with a relatively small granularity. Whenever the counters overflow, the performance counter interrupt is called to collect the PC for the CPU where data is being collected. The oprofile driver relies on a firmware RTAS call to setup the debug bus to route the desired signals to the performance counter hardware to be counted. The RTAS call must set the routing registers appropriately in each of the islands to pass the signals down the debug bus as well as routing the signals from a particular island onto the bus. There is a second firmware RTAS call to reset the debug bus to the non pass thru state when the counters are not in use. 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> Signed-off-by: Paul Mackerras <paulus@samba.org>
Diffstat (limited to 'arch/powerpc/oprofile/common.c')
-rw-r--r--arch/powerpc/oprofile/common.c15
1 files changed, 13 insertions, 2 deletions
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
index 63bbef3b63f1..7a423437977c 100644
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -69,7 +69,10 @@ static void op_powerpc_cpu_start(void *dummy)
static int op_powerpc_start(void)
{
- on_each_cpu(op_powerpc_cpu_start, NULL, 0, 1);
+ if (model->global_start)
+ model->global_start(ctr);
+ if (model->start)
+ on_each_cpu(op_powerpc_cpu_start, NULL, 0, 1);
return 0;
}
@@ -80,7 +83,10 @@ static inline void op_powerpc_cpu_stop(void *dummy)
static void op_powerpc_stop(void)
{
- on_each_cpu(op_powerpc_cpu_stop, NULL, 0, 1);
+ if (model->stop)
+ on_each_cpu(op_powerpc_cpu_stop, NULL, 0, 1);
+ if (model->global_stop)
+ model->global_stop();
}
static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
@@ -141,6 +147,11 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
switch (cur_cpu_spec->oprofile_type) {
#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_CELL
+ case PPC_OPROFILE_CELL:
+ model = &op_model_cell;
+ break;
+#endif
case PPC_OPROFILE_RS64:
model = &op_model_rs64;
break;
OpenPOWER on IntegriCloud