- replaced by linux-2.4-sfq.patch

[packages/kernel.git] / irqbalance-2.4.20-MRC.patch

diff -ruN linux-2.4.20.orig/arch/i386/kernel/io_apic.c linux-2.4.20/arch/i386/kernel/io_apic.c
--- linux-2.4.20.orig/arch/i386/kernel/io_apic.c	Thu Nov 28 16:53:09 2002
+++ linux-2.4.20/arch/i386/kernel/io_apic.c	Tue Dec 17 10:37:58 2002
@@ -28,6 +28,7 @@
 #include <linux/config.h>
 #include <linux/smp_lock.h>
 #include <linux/mc146818rtc.h>
+#include <linux/compiler.h>
 
 #include <asm/io.h>
 #include <asm/smp.h>
@@ -188,6 +189,86 @@
 			clear_IO_APIC_pin(apic, pin);
 }
 
+static void set_ioapic_affinity (unsigned int irq, unsigned long mask)
+{
+	unsigned long flags;
+
+	/*
+	 * Only the first 8 bits are valid.
+	 */
+	mask = mask << 24;
+	spin_lock_irqsave(&ioapic_lock, flags);
+	__DO_ACTION(1, = mask, )
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+#if CONFIG_SMP
+
+typedef struct {
+	unsigned int cpu;
+	unsigned long timestamp;
+} ____cacheline_aligned irq_balance_t;
+
+static irq_balance_t irq_balance[NR_IRQS] __cacheline_aligned
+			= { [ 0 ... NR_IRQS-1 ] = { 1, 0 } };
+
+extern unsigned long irq_affinity [NR_IRQS];
+
+#endif
+
+#define IDLE_ENOUGH(cpu,now) \
+		(idle_cpu(cpu) && ((now) - irq_stat[(cpu)].idle_timestamp > 1))
+
+#define IRQ_ALLOWED(cpu,allowed_mask) \
+		((1 << cpu) & (allowed_mask))
+
+static unsigned long move(int curr_cpu, unsigned long allowed_mask, unsigned long now, int direction)
+{
+	int search_idle = 1;
+	int cpu = curr_cpu;
+
+	goto inside;
+
+	do {
+		if (unlikely(cpu == curr_cpu))
+			search_idle = 0;
+inside:
+		if (direction == 1) {
+			cpu++;
+			if (cpu >= smp_num_cpus)
+				cpu = 0;
+		} else {
+			cpu--;
+			if (cpu == -1)
+				cpu = smp_num_cpus-1;
+		}
+	} while (!IRQ_ALLOWED(cpu,allowed_mask) ||
+			(search_idle && !IDLE_ENOUGH(cpu,now)));
+
+	return cpu;
+}
+
+static inline void balance_irq(int irq)
+{
+#if CONFIG_SMP
+	irq_balance_t *entry = irq_balance + irq;
+	unsigned long now = jiffies;
+
+	if (unlikely(entry->timestamp != now)) {
+		unsigned long allowed_mask;
+		int random_number;
+
+		rdtscl(random_number);
+		random_number &= 1;
+
+		allowed_mask = cpu_online_map & irq_affinity[irq];
+		entry->timestamp = now;
+		entry->cpu = move(entry->cpu, allowed_mask, now, random_number);
+		set_ioapic_affinity(irq, 1 << entry->cpu);
+	}
+#endif
+}
+
 /*
  * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to
  * specific CPU-side IRQs.
@@ -693,8 +774,7 @@
 }
 
 /*
- * Set up the 8259A-master output pin as broadcast to all
- * CPUs.
+ * Set up the 8259A-master output pin:
  */
 void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector)
 {
@@ -1214,6 +1294,7 @@
  */
 static void ack_edge_ioapic_irq(unsigned int irq)
 {
+	balance_irq(irq);
 	if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED))
 					== (IRQ_PENDING | IRQ_DISABLED))
 		mask_IO_APIC_irq(irq);
@@ -1253,6 +1334,7 @@
 	unsigned long v;
 	int i;
 
+	balance_irq(irq);
 /*
  * It appears there is an erratum which affects at least version 0x11
  * of I/O APIC (that's the 82093AA and cores integrated into various
@@ -1309,19 +1391,6 @@
 
 static void mask_and_ack_level_ioapic_irq (unsigned int irq) { /* nothing */ }
 
-static void set_ioapic_affinity (unsigned int irq, unsigned long mask)
-{
-	unsigned long flags;
-	/*
-	 * Only the first 8 bits are valid.
-	 */
-	mask = mask << 24;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	__DO_ACTION(1, = mask, )
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
 /*
  * Level and edge triggered IO-APIC interrupts need different handling,
  * so we use two separate IRQ descriptors. Edge triggered IRQs can be
diff -ruN linux-2.4.20.orig/arch/i386/kernel/irq.c linux-2.4.20/arch/i386/kernel/irq.c
--- linux-2.4.20.orig/arch/i386/kernel/irq.c	Thu Nov 28 16:53:09 2002
+++ linux-2.4.20/arch/i386/kernel/irq.c	Tue Dec 17 10:37:58 2002
@@ -1090,7 +1090,7 @@
 
 static struct proc_dir_entry * smp_affinity_entry [NR_IRQS];
 
-static unsigned long irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = ~0UL };
+unsigned long irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = ~0UL };
 static int irq_affinity_read_proc (char *page, char **start, off_t off,
 			int count, int *eof, void *data)
 {
diff -ruN linux-2.4.20.orig/include/asm-i386/hardirq.h linux-2.4.20/include/asm-i386/hardirq.h
--- linux-2.4.20.orig/include/asm-i386/hardirq.h	Thu Nov 22 12:46:19 2001
+++ linux-2.4.20/include/asm-i386/hardirq.h	Tue Dec 17 10:37:58 2002
@@ -12,6 +12,7 @@
 	unsigned int __local_bh_count;
 	unsigned int __syscall_count;
 	struct task_struct * __ksoftirqd_task; /* waitqueue is too large */
+	unsigned long idle_timestamp;
 	unsigned int __nmi_count;	/* arch dependent */
 } ____cacheline_aligned irq_cpustat_t;
 
diff -ruN linux-2.4.20.orig/include/linux/sched.h linux-2.4.20/include/linux/sched.h
--- linux-2.4.20.orig/include/linux/sched.h	Thu Nov 28 16:53:15 2002
+++ linux-2.4.20/include/linux/sched.h	Tue Dec 17 10:37:58 2002
@@ -147,6 +147,7 @@
 
 extern void sched_init(void);
 extern void init_idle(void);
+extern int idle_cpu(int cpu);
 extern void show_state(void);
 extern void cpu_init (void);
 extern void trap_init(void);
diff -ruN linux-2.4.20.orig/kernel/sched.c linux-2.4.20/kernel/sched.c
--- linux-2.4.20.orig/kernel/sched.c	Thu Nov 28 16:53:15 2002
+++ linux-2.4.20/kernel/sched.c	Tue Dec 17 10:37:58 2002
@@ -118,6 +118,11 @@
 #define can_schedule(p,cpu) \
 	((p)->cpus_runnable & (p)->cpus_allowed & (1 << cpu))
 
+int idle_cpu(int cpu)
+{
+	return cpu_curr(cpu) == idle_task(cpu);
+}
+
 #else
 
 #define idle_task(cpu) (&init_task)