[PATCH] ia64: oprofile support

I have revised the oprofile patch for ia64 to provide just the basic
timer interrupt mechanism to avoid interferring with the perfmon 2.0
support. I have verified the oprofile ia64 patch applies cleanly and
build a working kernel with the 2.6.0-test4 kernel and the
linux-2.6.0-test4-ia64-030826.diff.bz2 patch.

More work is required to get oprofile to work with the perfmon 2.0.
However, the patch as it is currently implements should not cause
problems for the perfom 2.0 support.

arch/ia64/Kconfig

@@ -589,6 +589,7 @@ source "lib/Kconfig"
 
 source "arch/ia64/hp/sim/Kconfig"
 
+source "arch/ia64/oprofile/Kconfig"
 
 menu "Kernel hacking"
 

arch/ia64/Makefile

@@ -65,6 +65,7 @@ drivers-$(CONFIG_PCI)		+= arch/ia64/pci/
 drivers-$(CONFIG_IA64_HP_SIM)	+= arch/ia64/hp/sim/
 drivers-$(CONFIG_IA64_HP_ZX1)	+= arch/ia64/hp/common/ arch/ia64/hp/zx1/
 drivers-$(CONFIG_IA64_GENERIC)	+= arch/ia64/hp/common/ arch/ia64/hp/zx1/ arch/ia64/hp/sim/
+drivers-$(CONFIG_OPROFILE)	+= arch/ia64/oprofile/
 
 boot := arch/ia64/hp/sim/boot
 

arch/ia64/kernel/time.c

@@ -17,6 +17,7 @@
 #include <linux/time.h>
 #include <linux/interrupt.h>
 #include <linux/efi.h>
+#include <linux/profile.h>
 #include <linux/timex.h>
 
 #include <asm/delay.h>
@@ -38,29 +39,6 @@ unsigned long last_cli_ip;
 
 #endif
 
-static void
-do_profile (unsigned long ip)
-{
-	extern cpumask_t prof_cpu_mask;
-
-	if (!prof_buffer)
-		return;
-
-	if (!cpu_isset(smp_processor_id(), prof_cpu_mask))
-		return;
-
-	ip -= (unsigned long) _stext;
-	ip >>= prof_shift;
-	/*
-	 * Don't ignore out-of-bounds IP values silently, put them into the last
-	 * histogram slot, so if present, they will show up as a sharp peak.
-	 */
-	if (ip > prof_len - 1)
-		ip = prof_len - 1;
-
-	atomic_inc((atomic_t *) &prof_buffer[ip]);
-}
-
 static void
 itc_reset (void)
 {
@@ -199,6 +177,52 @@ do_gettimeofday (struct timeval *tv)
 	tv->tv_usec = usec;
 }
 
+/*
+ * The profiling function is SMP safe. (nothing can mess
+ * around with "current", and the profiling counters are
+ * updated with atomic operations). This is especially
+ * useful with a profiling multiplier != 1
+ */
+static inline void
+ia64_do_profile (struct pt_regs * regs)
+{
+	unsigned long ip, slot;
+	extern unsigned long prof_cpu_mask;
+
+	profile_hook(regs);
+
+	if (user_mode(regs))
+		return;
+
+	if (!prof_buffer)
+		return;
+
+	ip = instruction_pointer(regs);
+	/* Conserve space in histogram by encoding slot bits in address
+	 * bits 2 and 3 rather than bits 0 and 1.
+	 */
+	slot = ip & 3;
+	ip = (ip & ~3UL) + 4*slot;
+
+	/*
+	 * Only measure the CPUs specified by /proc/irq/prof_cpu_mask.
+	 * (default is all CPUs.)
+	 */
+	if (!cpu_isset(smp_processor_id(), prof_cpu_mask))
+		return;
+
+	ip -= (unsigned long) &_stext;
+	ip >>= prof_shift;
+	/*
+	 * Don't ignore out-of-bounds IP values silently,
+	 * put them into the last histogram slot, so if
+	 * present, they will show up as a sharp peak.
+	 */
+	if (ip > prof_len-1)
+		ip = prof_len-1;
+	atomic_inc((atomic_t *)&prof_buffer[ip]);
+}
+
 static irqreturn_t
 timer_interrupt (int irq, void *dev_id, struct pt_regs *regs)
 {
@@ -210,14 +234,9 @@ timer_interrupt (int irq, void *dev_id, struct pt_regs *regs)
 		printk(KERN_ERR "Oops: timer tick before it's due (itc=%lx,itm=%lx)\n",
 		       ia64_get_itc(), new_itm);
 
+	ia64_do_profile(regs);
+
 	while (1) {
-		/*
-		 * Do kernel PC profiling here.  We multiply the instruction number by
-		 * four so that we can use a prof_shift of 2 to get instruction-level
-		 * instead of just bundle-level accuracy.
-		 */
-		if (!user_mode(regs))
-			do_profile(regs->cr_iip + 4*ia64_psr(regs)->ri);
 
 #ifdef CONFIG_SMP
 		smp_do_timer(regs);

arch/ia64/oprofile/Kconfig

+
+menu "Profiling support"
+	depends on EXPERIMENTAL
+
+config PROFILING
+	bool "Profiling support (EXPERIMENTAL)"
+	help
+	  Say Y here to enable the extended profiling support mechanisms used
+	  by profilers such as OProfile.
+
+config OPROFILE
+	tristate "OProfile system profiling (EXPERIMENTAL)"
+	depends on PROFILING
+	help
+	  OProfile is a profiling system capable of profiling the
+	  whole system, include the kernel, kernel modules, libraries,
+	  and applications.
+
+	  If unsure, say N.
+
+endmenu
+

arch/ia64/oprofile/Makefile

+obj-$(CONFIG_OPROFILE) += oprofile.o
+
+DRIVER_OBJS := $(addprefix ../../../drivers/oprofile/, \
+		oprof.o cpu_buffer.o buffer_sync.o \
+		event_buffer.o oprofile_files.o \
+		oprofilefs.o oprofile_stats.o \
+		timer_int.o )
+
+oprofile-y := $(DRIVER_OBJS) init.o

arch/ia64/oprofile/init.c

+/**
+ * @file init.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon <levon@movementarian.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/oprofile.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+ 
+extern void timer_init(struct oprofile_operations ** ops);
+
+int __init oprofile_arch_init(struct oprofile_operations ** ops)
+{
+	return -ENODEV;
+}
+
+
+void oprofile_arch_exit(void)
+{
+}

include/asm-ia64/hw_irq.h

@@ -9,6 +9,7 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/types.h>
+#include <linux/profile.h>
 
 #include <asm/machvec.h>
 #include <asm/ptrace.h>

include/asm-ia64/ptrace.h

@@ -223,6 +223,12 @@ struct switch_stack {
 };
 
 #ifdef __KERNEL__
+/*
+ * We use the ia64_psr(regs)->ri to determine which of the three
+ * instructions in bundle (16 bytes) took the sample. Generate
+ * the canonical representation by adding to instruction pointer.
+ */
+# define instruction_pointer(regs) ((regs)->cr_iip + ia64_psr(regs)->ri)
   /* given a pointer to a task_struct, return the user's pt_regs */
 # define ia64_task_regs(t)		(((struct pt_regs *) ((char *) (t) + IA64_STK_OFFSET)) - 1)
 # define ia64_psr(regs)			((struct ia64_psr *) &(regs)->cr_ipsr)