ia64 oprofile support for 2.6.0-test4

@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/efi.h>
 #include <linux/timex.h>
+#include <linux/profile.h>
 
 #include <asm/delay.h>
 #include <asm/hw_irq.h>

@@ -39,29 +40,6 @@
 #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 +177,47 @@
 	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 eip;
+	extern unsigned long prof_cpu_mask;
+ 
+	profile_hook(regs);
+ 
+	if (user_mode(regs))
+		return;
+ 
+	if (!prof_buffer)
+		return;
+
+	eip = instruction_pointer(regs);
+ 
+	/*
+	 * Only measure the CPUs specified by /proc/irq/prof_cpu_mask.
+	 * (default is all CPUs.)
+	 */
+	if (!((1<<smp_processor_id()) & prof_cpu_mask))
+		return;
+
+	eip -= (unsigned long) &_stext;
+	eip >>= prof_shift;
+	/*
+	 * Don't ignore out-of-bounds EIP values silently,
+	 * put them into the last histogram slot, so if
+	 * present, they will show up as a sharp peak.
+	 */
+	if (eip > prof_len-1)
+		eip = prof_len-1;
+	atomic_inc((atomic_t *)&prof_buffer[eip]);
+}
+
 static irqreturn_t
 timer_interrupt (int irq, void *dev_id, struct pt_regs *regs)
 {

@@ -210,14 +229,9 @@
 		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);

@@ -0,0 +1,25 @@
+/**
+ * @file init.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon <[email protected]>
+ */
+
+#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)
+{
+}

@@ -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>

@@ -223,6 +223,13 @@
 };
 
 #ifdef __KERNEL__
+/*
+ * We use the ia64_psr(regs)->ri to determine which of the three
+ * instructions in bundle took the sample. The instructions in the
+ * ia64 do not fall on nice four byte boundaries, so there is no point
+ * in multiplying ia64_psr(regs)->ri by 4.
+ */
+#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)

@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/efi.h>
 #include <linux/timex.h>
+#include <linux/profile.h>
 
 #include <asm/delay.h>
 #include <asm/hw_irq.h>

@@ -39,29 +40,6 @@
 #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 +177,47 @@
 	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;
+	extern unsigned long prof_cpu_mask;
+ 
+	profile_hook(regs);
+ 
+	if (user_mode(regs))
+		return;
+ 
+	if (!prof_buffer)
+		return;
+
+	ip = instruction_pointer(regs);
+ 
+	/*
+	 * Only measure the CPUs specified by /proc/irq/prof_cpu_mask.
+	 * (default is all CPUs.)
+	 */
+	if (!((1<<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 +229,9 @@
 		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);

@@ -0,0 +1,25 @@
+/**
+ * @file init.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon <[email protected]>
+ */
+
+#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)
+{
+}

@@ -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>

@@ -223,6 +223,14 @@
 };
 
 #ifdef __KERNEL__
+/*
+ * We use the ia64_psr(regs)->ri to determine which of the three
+ * instructions in bundle (16 bytes) took the sample. The instructions
+ * in the ia64 do not fall on nice four byte boundaries.  However, to
+ * save space in the histogram, the instructions are mapped to 4
+ * byte boundaries.
+ */
+#define instruction_pointer(regs) ((regs)->cr_iip + 4*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)

@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/efi.h>
 #include <linux/timex.h>
+#include <linux/profile.h>
 
 #include <asm/delay.h>
 #include <asm/hw_irq.h>

@@ -39,29 +40,6 @@
 #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 @@
 	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 (!((1<<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 @@
 		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);

@@ -0,0 +1,25 @@
+/**
+ * @file init.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon <[email protected]>
+ */
+
+#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)
+{
+}

@@ -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>

@@ -223,6 +223,12 @@
 };
 
 #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)