Re: [PATCH] ia64 oprofile support for 2.6.0-test4

[Will Cohen <wcohen@redhat.com>]

[-- Attachment #1: Type: text/plain, Size: 1101 bytes --]

Revised the instruction_pointer to return the canonical ip and 
ia64_do_profile() to adjust the resulting ip value for the histogram.

-Will

David Mosberger wrote:
>>>>>>On Tue, 26 Aug 2003 17:51:15 -0400, Will Cohen <wcohen@redhat.com> said:
>>>>>
> 
>   Will> I have revised the patch based on the comments below: 1) use
>   Will> ip instead of eip 2) multiply ri by 4, to get more compact
>   Will> histograms
> 
> Hmmh, I'm not sure I like this patch better.  Like I mentioned in the
> earlier mail, it does make sense to encode the slot number in bits 0
> and 1 for instruction_pointer().  That is the canonical representation
> used by IA-64 Linux (and ELF, gdb, etc.).  The traditional histogram
> is a special case, because there it is more useful to get the slot
> number bits close to the bundle-address bits, so I think we should
> special-case this in ia64_do_profile() instead.  Perhaps something
> along the lines of:
> 
> 	ip = instruction_pointer(regs);
> 	/* for histogram, encode slot bits in address bits 2 and 3: */
> 	slot = ip & 3;
> 	ip = (ip & ~3UL) + 4*slot;
> 
>   --david


[-- Attachment #2: oprof20030825f.patch --]
[-- Type: text/plain, Size: 6326 bytes --]

--- linux-2.6.0-test4-bk2oprof/arch/ia64/kernel/time.c.orig	2003-08-22 19:53:07.000000000 -0400
+++ linux-2.6.0-test4-bk2oprof/arch/ia64/kernel/time.c	2003-08-27 09:42:42.731374187 -0400
@@ -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);
--- linux-2.6.0-test4-bk2oprof/arch/ia64/Makefile.orig	2003-08-22 19:51:04.000000000 -0400
+++ linux-2.6.0-test4-bk2oprof/arch/ia64/Makefile	2003-08-25 14:35:58.000000000 -0400
@@ -65,6 +65,7 @@
 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
 
--- /dev/null	2003-08-22 16:30:19.000000000 -0400
+++ linux-2.6.0-test4-bk2oprof/arch/ia64/oprofile/init.c	2003-08-25 15:58:25.000000000 -0400
@@ -0,0 +1,25 @@
+/**
+ * @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)
+{
+}
--- /dev/null	2003-08-22 16:30:19.000000000 -0400
+++ linux-2.6.0-test4-bk2oprof/arch/ia64/oprofile/Kconfig	2003-08-25 14:35:58.000000000 -0400
@@ -0,0 +1,23 @@
+
+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
+
--- /dev/null	2003-08-22 16:30:19.000000000 -0400
+++ linux-2.6.0-test4-bk2oprof/arch/ia64/oprofile/Makefile	2003-08-25 14:35:58.000000000 -0400
@@ -0,0 +1,9 @@
+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
--- linux-2.6.0-test4-bk2oprof/arch/ia64/Kconfig.orig	2003-08-25 11:29:46.000000000 -0400
+++ linux-2.6.0-test4-bk2oprof/arch/ia64/Kconfig	2003-08-25 14:35:58.000000000 -0400
@@ -589,6 +589,8 @@
 
 source "arch/ia64/hp/sim/Kconfig"
 
+source "arch/ia64/oprofile/Kconfig"
+
 
 menu "Kernel hacking"
 
--- linux-2.6.0-test4-bk2oprof/include/asm-ia64/hw_irq.h.orig	2003-08-22 19:55:39.000000000 -0400
+++ linux-2.6.0-test4-bk2oprof/include/asm-ia64/hw_irq.h	2003-08-26 15:13:40.000000000 -0400
@@ -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>
--- linux-2.6.0-test4-bk2oprof/include/asm-ia64/ptrace.h.orig	2003-08-22 19:57:23.000000000 -0400
+++ linux-2.6.0-test4-bk2oprof/include/asm-ia64/ptrace.h	2003-08-27 09:44:09.313087486 -0400
@@ -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)