aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/platforms/cell
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/platforms/cell
parent0443bbd3d8496f9c2bc3e8c9d1833c6638722743 (diff)
[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/platforms/cell')
-rw-r--r--arch/powerpc/platforms/cell/cbe_regs.c12
-rw-r--r--arch/powerpc/platforms/cell/pmu.c23
2 files changed, 33 insertions, 2 deletions
diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c
index 5a91b75c2f0..9a0ee62691d 100644
--- a/arch/powerpc/platforms/cell/cbe_regs.c
+++ b/arch/powerpc/platforms/cell/cbe_regs.c
@@ -130,6 +130,18 @@ struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu)
}
EXPORT_SYMBOL_GPL(cbe_get_cpu_mic_tm_regs);
+/* FIXME
+ * This is little more than a stub at the moment. It should be
+ * fleshed out so that it works for both SMT and non-SMT, no
+ * matter if the passed cpu is odd or even.
+ * For SMT enabled, returns 0 for even-numbered cpu; otherwise 1.
+ * For SMT disabled, returns 0 for all cpus.
+ */
+u32 cbe_get_hw_thread_id(int cpu)
+{
+ return (cpu & 1);
+}
+EXPORT_SYMBOL_GPL(cbe_get_hw_thread_id);
void __init cbe_regs_init(void)
{
diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c
index f28abf2fc27..99c612025e8 100644
--- a/arch/powerpc/platforms/cell/pmu.c
+++ b/arch/powerpc/platforms/cell/pmu.c
@@ -25,6 +25,7 @@
#include <linux/interrupt.h>
#include <linux/types.h>
#include <asm/io.h>
+#include <asm/irq_regs.h>
#include <asm/machdep.h>
#include <asm/pmc.h>
#include <asm/reg.h>
@@ -375,9 +376,9 @@ void cbe_disable_pm_interrupts(u32 cpu)
}
EXPORT_SYMBOL_GPL(cbe_disable_pm_interrupts);
-static irqreturn_t cbe_pm_irq(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t cbe_pm_irq(int irq, void *dev_id)
{
- perf_irq(regs);
+ perf_irq(get_irq_regs());
return IRQ_HANDLED;
}
@@ -408,3 +409,21 @@ int __init cbe_init_pm_irq(void)
}
arch_initcall(cbe_init_pm_irq);
+void cbe_sync_irq(int node)
+{
+ unsigned int irq;
+
+ irq = irq_find_mapping(NULL,
+ IIC_IRQ_IOEX_PMI
+ | (node << IIC_IRQ_NODE_SHIFT));
+
+ if (irq == NO_IRQ) {
+ printk(KERN_WARNING "ERROR, unable to get existing irq %d " \
+ "for node %d\n", irq, node);
+ return;
+ }
+
+ synchronize_irq(irq);
+}
+EXPORT_SYMBOL_GPL(cbe_sync_irq);
+