generic irq subsystem, description

@@ -0,0 +1,183 @@
+/*
+ * linux/kernel/irq/proc.c
+ *
+ * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar
+ *
+ * This file contains the /proc/irq/ handling code.
+ */
+
+#include <linux/irq.h>
+#include <linux/proc_fs.h>
+#include <linux/interrupt.h>
+
+unsigned long prof_cpu_mask = -1;
+
+static struct proc_dir_entry *root_irq_dir, *irq_dir[NR_IRQS];
+
+#ifdef CONFIG_SMP
+
+/*
+ * The /proc/irq/<irq>/smp_affinity values:
+ */
+static struct proc_dir_entry *smp_affinity_entry[NR_IRQS];
+
+cpumask_t irq_affinity[NR_IRQS] = { [0 ... NR_IRQS-1] = CPU_MASK_ALL };
+
+static int irq_affinity_read_proc(char *page, char **start, off_t off,
+				  int count, int *eof, void *data)
+{
+	int len = cpumask_scnprintf(page, count, irq_affinity[(long)data]);
+
+	if (count - len < 2)
+		return -EINVAL;
+	len += sprintf(page + len, "\n");
+	return len;
+}
+
+static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
+				   unsigned long count, void *data)
+{
+	unsigned int irq = (int)(long)data, full_count = count, err;
+	cpumask_t new_value, tmp;
+
+	if (!irq_desc[irq].handler->set_affinity)
+		return -EIO;
+
+	err = cpumask_parse(buffer, count, new_value);
+	if (err)
+		return err;
+
+	/*
+	 * Do not allow disabling IRQs completely - it's a too easy
+	 * way to make the system unusable accidentally :-) At least
+	 * one online CPU still has to be targeted.
+	 */
+	cpus_and(tmp, new_value, cpu_online_map);
+	if (cpus_empty(tmp))
+		return -EINVAL;
+
+	irq_affinity[irq] = new_value;
+	irq_desc[irq].handler->set_affinity(irq,
+					cpumask_of_cpu(first_cpu(new_value)));
+
+	return full_count;
+}
+
+#endif
+
+static int prof_cpu_mask_read_proc(char *page, char **start, off_t off,
+				   int count, int *eof, void *data)
+{
+	int len = cpumask_scnprintf(page, count, *(cpumask_t *)data);
+
+	if (count - len < 2)
+		return -EINVAL;
+	len += sprintf(page + len, "\n");
+	return len;
+}
+
+static int prof_cpu_mask_write_proc(struct file *file,
+				    const char __user *buffer,
+				    unsigned long count, void *data)
+{
+	unsigned long full_count = count, err;
+	cpumask_t *mask = (cpumask_t *)data;
+	cpumask_t new_value;
+
+	err = cpumask_parse(buffer, count, new_value);
+	if (err)
+		return err;
+
+	*mask = new_value;
+
+	return full_count;
+}
+
+#define MAX_NAMELEN 128
+
+void register_handler_proc(unsigned int irq, struct irqaction *action)
+{
+	char name [MAX_NAMELEN];
+
+	if (!irq_dir[irq] || action->dir || !action->name)
+		return;
+
+	memset(name, 0, MAX_NAMELEN);
+	snprintf(name, MAX_NAMELEN, "%s", action->name);
+
+	/* create /proc/irq/1234/handler/ */
+	action->dir = proc_mkdir(name, irq_dir[irq]);
+}
+
+#undef MAX_NAMELEN
+
+#define MAX_NAMELEN 10
+
+void register_irq_proc(unsigned int irq)
+{
+	char name [MAX_NAMELEN];
+
+	if (!root_irq_dir ||
+		(irq_desc[irq].handler == &no_irq_type) ||
+			irq_dir[irq])
+		return;
+
+	memset(name, 0, MAX_NAMELEN);
+	sprintf(name, "%d", irq);
+
+	/* create /proc/irq/1234 */
+	irq_dir[irq] = proc_mkdir(name, root_irq_dir);
+
+#ifdef CONFIG_SMP
+	{
+		struct proc_dir_entry *entry;
+
+		/* create /proc/irq/<irq>/smp_affinity */
+		entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]);
+
+		if (entry) {
+			entry->nlink = 1;
+			entry->data = (void *)(long)irq;
+			entry->read_proc = irq_affinity_read_proc;
+			entry->write_proc = irq_affinity_write_proc;
+		}
+		smp_affinity_entry[irq] = entry;
+	}
+#endif
+}
+
+#undef MAX_NAMELEN
+
+void unregister_handler_proc(unsigned int irq, struct irqaction *action)
+{
+	if (action->dir)
+		remove_proc_entry(action->dir->name, irq_dir[irq]);
+}
+
+void init_irq_proc(void)
+{
+	struct proc_dir_entry *entry;
+	int i;
+
+	/* create /proc/irq */
+	root_irq_dir = proc_mkdir("irq", NULL);
+	if (!root_irq_dir)
+		return;
+
+	/* create /proc/irq/prof_cpu_mask */
+	entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
+	if (!entry)
+		return;
+
+	entry->nlink = 1;
+	entry->data = (void *)&prof_cpu_mask;
+	entry->read_proc = prof_cpu_mask_read_proc;
+	entry->write_proc = prof_cpu_mask_write_proc;
+
+	/*
+	 * Create entries for all existing IRQs.
+	 */
+	for (i = 0; i < NR_IRQS; i++)
+		register_irq_proc(i);
+}
+

347 lines not on this page · raw message

96 lines not on this page · raw message

204 lines not on this page · raw message

188 lines not on this page · raw message

@@ -0,0 +1,18 @@
+/*
+ * IRQ subsystem internal functions and variables:
+ */
+
+extern int noirqdebug;
+
+#ifdef CONFIG_PROC_FS
+extern void register_irq_proc(unsigned int irq);
+extern void register_handler_proc(unsigned int irq, struct irqaction *action);
+extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
+#else
+static inline void register_irq_proc(unsigned int irq) { }
+static inline void register_handler_proc(unsigned int irq,
+					 struct irqaction *action) { }
+static inline void unregister_handler_proc(unsigned int irq,
+					   struct irqaction *action) { }
+#endif
+

@@ -13,6 +13,7 @@
 
 #if !defined(CONFIG_ARCH_S390)
 
+#include <linux/linkage.h>
 #include <linux/cache.h>
 #include <linux/spinlock.h>
 #include <linux/cpumask.h>

@@ -71,7 +72,19 @@ extern irq_desc_t irq_desc [NR_IRQS];
 
 #include <asm/hw_irq.h> /* the arch dependent stuff */
 
-extern int setup_irq(unsigned int , struct irqaction * );
+#ifdef CONFIG_GENERIC_HARDIRQS
+extern cpumask_t irq_affinity[NR_IRQS];
+
+extern asmlinkage int handle_IRQ_event(unsigned int irq, struct pt_regs *regs,
+				       struct irqaction *action);
+extern asmlinkage unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs);
+extern void note_interrupt(unsigned int irq, irq_desc_t *desc, int action_ret);
+extern void report_bad_irq(unsigned int irq, irq_desc_t *desc, int action_ret);
+extern int can_request_irq(unsigned int irq, unsigned long irqflags);
+extern int setup_irq(unsigned int irq, struct irqaction * new);
+
+extern void init_irq_proc(void);
+#endif
 
 extern hw_irq_controller no_irq_type;  /* needed in every arch ? */
 

@@ -40,6 +40,8 @@ struct irqaction {
 	const char *name;
 	void *dev_id;
 	struct irqaction *next;
+	int irq;
+	struct proc_dir_entry *dir;
 };
 
 extern irqreturn_t no_action(int cpl, void *dev_id, struct pt_regs *regs);

@@ -48,6 +50,13 @@ extern int request_irq(unsigned int,
 		       unsigned long, const char *, void *);
 extern void free_irq(unsigned int, void *);
 
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+extern void disable_irq_nosync(unsigned int irq);
+extern void disable_irq(unsigned int irq);
+extern void enable_irq(unsigned int irq);
+#endif
+
 /*
  * Temporary defines for UP kernels, until all code gets fixed.
  */

52 lines not on this page · raw message

@@ -741,7 +741,7 @@ static inline void free_vm86_irq(int irq
 	spin_unlock_irqrestore(&irqbits_lock, flags);	
 }
 
-void release_x86_irqs(struct task_struct *task)
+void release_vm86_irqs(struct task_struct *task)
 {
 	int i;
 	for (i = FIRST_VM86_IRQ ; i <= LAST_VM86_IRQ; i++)

@@ -255,8 +255,6 @@ static void set_ioapic_affinity_irq(unsi
 #  define Dprintk(x...) 
 # endif
 
-extern cpumask_t irq_affinity[NR_IRQS];
-
 cpumask_t __cacheline_aligned pending_irq_balance_cpumask[NR_IRQS];
 
 #define IRQBALANCE_CHECK_ARCH -999

@@ -76,9 +76,6 @@ EXPORT_SYMBOL_GPL(kernel_fpu_begin);
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(ioremap_nocache);
 EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(enable_irq);
-EXPORT_SYMBOL(disable_irq);
-EXPORT_SYMBOL(disable_irq_nosync);
 EXPORT_SYMBOL(probe_irq_mask);
 EXPORT_SYMBOL(kernel_thread);
 EXPORT_SYMBOL(pm_idle);

@@ -146,7 +143,6 @@ EXPORT_SYMBOL(__write_lock_failed);
 EXPORT_SYMBOL(__read_lock_failed);
 
 /* Global SMP stuff */
-EXPORT_SYMBOL(synchronize_irq);
 EXPORT_SYMBOL(smp_call_function);
 
 /* TLB flushing */

@@ -344,7 +344,7 @@ void release_thread(struct task_struct *
 		}
 	}
 
-	release_x86_irqs(dead_task);
+	release_vm86_irqs(dead_task);
 }
 
 /*

1,208 lines not on this page · raw message

@@ -21,38 +21,17 @@ static __inline__ int irq_canonicalize(i
 	return ((irq == 2) ? 9 : irq);
 }
 
-extern void disable_irq(unsigned int);
-extern void disable_irq_nosync(unsigned int);
-extern void enable_irq(unsigned int);
-extern void release_x86_irqs(struct task_struct *);
-extern int can_request_irq(unsigned int, unsigned long flags);
+extern void release_vm86_irqs(struct task_struct *);
 
 #ifdef CONFIG_X86_LOCAL_APIC
-#define ARCH_HAS_NMI_WATCHDOG		/* See include/linux/nmi.h */
+# define ARCH_HAS_NMI_WATCHDOG		/* See include/linux/nmi.h */
 #endif
 
 #ifdef CONFIG_4KSTACKS
-/*
- * per-CPU IRQ handling contexts (thread information and stack)
- */
-union irq_ctx {
-	struct thread_info      tinfo;
-	u32                     stack[THREAD_SIZE/sizeof(u32)];
-};
-
-extern union irq_ctx *hardirq_ctx[NR_CPUS];
-extern union irq_ctx *softirq_ctx[NR_CPUS];
-
-extern void irq_ctx_init(int cpu);
-
-#define __ARCH_HAS_DO_SOFTIRQ
+  extern void irq_ctx_init(int cpu);
+# define __ARCH_HAS_DO_SOFTIRQ
 #else
-#define irq_ctx_init(cpu) do { ; } while (0)
+# define irq_ctx_init(cpu) do { } while (0)
 #endif
 
-struct irqaction;
-struct pt_regs;
-asmlinkage int handle_IRQ_event(unsigned int, struct pt_regs *,
-				struct irqaction *);
-
 #endif /* _ASM_IRQ_H */

65 lines not on this page · raw message

@@ -45,8 +45,6 @@ asmlinkage void thermal_interrupt(struct
 #define platform_legacy_irq(irq)	((irq) < 16)
 #endif
 
-void mask_irq(unsigned int irq);
-void unmask_irq(unsigned int irq);
 void disable_8259A_irq(unsigned int irq);
 void enable_8259A_irq(unsigned int irq);
 int i8259A_irq_pending(unsigned int irq);

863 lines not on this page · raw message

@@ -44,11 +44,6 @@ static __inline__ int irq_canonicalize(i
 	return ((irq == 2) ? 9 : irq);
 }
 
-extern void disable_irq(unsigned int);
-extern void disable_irq_nosync(unsigned int);
-extern void enable_irq(unsigned int);
-extern int can_request_irq(unsigned int, unsigned long flags);
-
 #ifdef CONFIG_X86_LOCAL_APIC
 #define ARCH_HAS_NMI_WATCHDOG		/* See include/linux/nmi.h */
 #endif

72 lines not on this page · raw message

@@ -105,7 +105,7 @@ m8xx_do_IRQ(struct pt_regs *regs,
 		ppc_spurious_interrupts++;
 	}
 	else {
-                ppc_irq_dispatch_handler( regs, irq );
+                __do_IRQ(irq, regs);
 	}
 
 }

@@ -161,7 +161,7 @@ void mbx_i8259_action(int cpl, void *dev
 	}
 	bits = 1UL << irq;
 	irq += i8259_pic.irq_offset;
-	ppc_irq_dispatch_handler( regs, irq );
+	__do_IRQ(irq, regs);
 }
 #endif
 

@@ -84,10 +84,6 @@ EXPORT_SYMBOL(SingleStepException);
 EXPORT_SYMBOL(sys_sigreturn);
 EXPORT_SYMBOL(ppc_n_lost_interrupts);
 EXPORT_SYMBOL(ppc_lost_interrupts);
-EXPORT_SYMBOL(enable_irq);
-EXPORT_SYMBOL(disable_irq);
-EXPORT_SYMBOL(disable_irq_nosync);
-EXPORT_SYMBOL(probe_irq_mask);
 
 EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
 EXPORT_SYMBOL(DMA_MODE_READ);

@@ -205,7 +201,6 @@ EXPORT_SYMBOL(giveup_spe);
 #ifdef CONFIG_SMP
 EXPORT_SYMBOL(smp_call_function);
 EXPORT_SYMBOL(smp_hw_index);
-EXPORT_SYMBOL(synchronize_irq);
 #endif
 
 EXPORT_SYMBOL(ppc_md);

@@ -292,8 +287,6 @@ EXPORT_SYMBOL(local_irq_restore_end);
 #endif
 EXPORT_SYMBOL(timer_interrupt);
 EXPORT_SYMBOL(irq_desc);
-void ppc_irq_dispatch_handler(struct pt_regs *, int);
-EXPORT_SYMBOL(ppc_irq_dispatch_handler);
 EXPORT_SYMBOL(tb_ticks_per_jiffy);
 EXPORT_SYMBOL(get_wchan);
 EXPORT_SYMBOL(console_drivers);

562 lines not on this page · raw message

@@ -214,7 +214,7 @@ static irqreturn_t gatwick_action(int cp
 		if (bits == 0)
 			continue;
 		irq += __ilog2(bits);
-		ppc_irq_dispatch_handler(regs, irq);
+		__do_IRQ(irq, regs);
 		return IRQ_HANDLED;
 	}
 	printk("gatwick irq not from gatwick pic\n");

@@ -383,11 +383,34 @@ static irqreturn_t k2u3_action(int cpl, 
 
 	irq = openpic2_get_irq(regs);
 	if (irq != -1)
-		ppc_irq_dispatch_handler(regs, irq);
+		__do_IRQ(irq, regs);
 	return IRQ_HANDLED;
 }
+
+static struct irqaction k2u3_cascade_action = {
+	.handler	= k2u3_action,
+	.flags		= 0,
+	.mask		= CPU_MASK_NONE,
+	.name		= "U3->K2 Cascade",
+};
 #endif /* CONFIG_POWER4 */
 
+#ifdef CONFIG_XMON
+static struct irqaction xmon_action = {
+	.handler	= xmon_irq,
+	.flags		= 0,
+	.mask		= CPU_MASK_NONE,
+	.name		= "NMI - XMON"
+};
+#endif
+
+static struct irqaction gatwick_cascade_action = {
+	.handler	= gatwick_action,
+	.flags		= SA_INTERRUPT,
+	.mask		= CPU_MASK_NONE,
+	.name		= "cascade",
+};
+
 void __init pmac_pic_init(void)
 {
         int i;

@@ -440,8 +463,9 @@ void __init pmac_pic_init(void)
 				OpenPIC_InitSenses = senses;
 				OpenPIC_NumInitSenses = 128;
 				openpic2_init(PMAC_OPENPIC2_OFFSET);
-				if (request_irq(irqctrler2->intrs[0].line, k2u3_action, 0,
-						"U3->K2 Cascade", NULL))
+
+				if (setup_irq(irqctrler2->intrs[0].line,
+					      &k2u3_cascade_action))
 					printk("Unable to get OpenPIC IRQ for cascade\n");
 			}
 #endif /* CONFIG_POWER4 */

@@ -455,8 +479,7 @@ void __init pmac_pic_init(void)
 				if (pswitch && pswitch->n_intrs) {
 					nmi_irq = pswitch->intrs[0].line;
 					openpic_init_nmi_irq(nmi_irq);
-					request_irq(nmi_irq, xmon_irq, 0,
-						    "NMI - XMON", NULL);
+					setup_irq(nmi_irq, &xmon_action);
 				}
 			}
 #endif	/* CONFIG_XMON */

@@ -553,8 +576,7 @@ void __init pmac_pic_init(void)
 			(int)irq_cascade);
 		for ( i = max_real_irqs ; i < max_irqs ; i++ )
 			irq_desc[i].handler = &gatwick_pic;
-		request_irq( irq_cascade, gatwick_action, SA_INTERRUPT,
-			     "cascade", NULL );
+		setup_irq(irq_cascade, &gatwick_cascade_action);
 	}
 	printk("System has %d possible interrupts\n", max_irqs);
 	if (max_irqs != max_real_irqs)

@@ -562,7 +584,7 @@ void __init pmac_pic_init(void)
 			max_real_irqs);
 
 #ifdef CONFIG_XMON
-	request_irq(20, xmon_irq, 0, "NMI - XMON", NULL);
+	setup_irq(20, &xmon_action);
 #endif	/* CONFIG_XMON */
 }
 

@@ -191,9 +191,7 @@ mpc85xx_cds_show_cpuinfo(struct seq_file
 static void cpm2_cascade(int irq, void *dev_id, struct pt_regs *regs)
 {
 	while((irq = cpm2_get_irq(regs)) >= 0)
-	{
-		ppc_irq_dispatch_handler(regs,irq);
-	}
+		__do_IRQ(irq, regs);
 }
 #endif /* CONFIG_CPM2 */
 

@@ -145,9 +145,8 @@ mpc8560ads_setup_arch(void)
 
 static irqreturn_t cpm2_cascade(int irq, void *dev_id, struct pt_regs *regs)
 {
-	while ((irq = cpm2_get_irq(regs)) >= 0) {
-		ppc_irq_dispatch_handler(regs, irq);
-	}
+	while ((irq = cpm2_get_irq(regs)) >= 0)
+		__do_IRQ(irq, regs);
 	return IRQ_HANDLED;
 }
 

@@ -11,7 +11,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/pci.h>
-#include <linux/irq.h>
+#include <linux/interrupt.h>
 
 #include <asm/io.h>
 #include <asm/i8259.h>

@@ -20,11 +20,6 @@
 static void adir_onboard_pic_enable(unsigned int irq);
 static void adir_onboard_pic_disable(unsigned int irq);
 
-static void
-no_action(int cpl, void *dev_id, struct pt_regs *regs)
-{
-}
-
 __init static void
 adir_onboard_pic_init(void)
 {

@@ -88,6 +83,13 @@ static struct hw_interrupt_type adir_onb
 	NULL
 };
 
+static struct irqaction noop_action = {
+	.handler	= no_action,
+	.flags          = SA_INTERRUPT,
+	.mask           = CPU_MASK_NONE,
+	.name           = "82c59 primary cascade",
+};
+
 /*
  * Linux interrupt values are assigned as follows:
  *

@@ -110,11 +112,7 @@ adir_init_IRQ(void)
 	adir_onboard_pic_init();
 
 	/* Enable 8259 interrupt cascade */
-	request_irq(ADIR_IRQ_VT82C686_INTR,
-			no_action,
-			SA_INTERRUPT,
-			"82c59 primary cascade",
-			NULL);
+	setup_irq(ADIR_IRQ_VT82C686_INTR, &noop_action);
 }
 
 int

@@ -142,7 +142,7 @@ static irqreturn_t sbc82xx_i8259_demux(i
 			return IRQ_HANDLED;
 		}
 	}
-	ppc_irq_dispatch_handler(regs, NR_SIU_INTS + irq);
+	__do_IRQ(NR_SIU_INTS + irq, regs);
 	return IRQ_HANDLED;
 }
 

@@ -6,10 +6,6 @@
 #include <asm/machdep.h>		/* ppc_md */
 #include <asm/atomic.h>
 
-extern void disable_irq(unsigned int);
-extern void disable_irq_nosync(unsigned int);
-extern void enable_irq(unsigned int);
-
 /*
  * These constants are used for passing information about interrupt
  * signal polarity and level/edge sensing to the low-level PIC chip

51 lines not on this page · raw message

@@ -9,7 +9,6 @@
 #include <asm/reg.h>
 
 extern void timer_interrupt(struct pt_regs *);
-extern void ppc_irq_dispatch_handler(struct pt_regs *regs, int irq);
 
 #define INLINE_IRQS
 

548 lines not on this page · raw message

@@ -17,10 +17,6 @@
  */
 #define NR_IRQS		512
 
-extern void disable_irq(unsigned int);
-extern void disable_irq_nosync(unsigned int);
-extern void enable_irq(unsigned int);
-
 /* this number is used when no interrupt has been assigned */
 #define NO_IRQ			(-1)
 

@@ -80,7 +76,6 @@ static __inline__ int irq_canonicalize(i
 
 struct irqaction;
 struct pt_regs;
-int handle_irq_event(int, struct pt_regs *, struct irqaction *);
 
 #ifdef CONFIG_IRQSTACKS
 /*

@@ -91,7 +86,7 @@ extern struct thread_info *softirq_ctx[N
 
 extern void irq_ctx_init(void);
 extern void call_do_softirq(struct thread_info *tp);
-extern int call_handle_irq_event(int irq, struct pt_regs *regs,
+extern int call_handle_IRQ_event(int irq, struct pt_regs *regs,
 			struct irqaction *action, struct thread_info *tp);
 
 #define __ARCH_HAS_DO_SOFTIRQ

50 lines not on this page · raw message

@@ -52,8 +52,6 @@ extern cpumask_t cpu_sibling_map[NR_CPUS
 #endif
 #define PPC_MSG_DEBUGGER_BREAK  3
 
-extern cpumask_t irq_affinity[];
-
 void smp_init_iSeries(void);
 void smp_init_pSeries(void);
 

diff -u -p -B -r1.1.1.1 apic.c
@@ -26,6 +26,7 @@
 #include <linux/mc146818rtc.h>
 #include <linux/kernel_stat.h>
 #include <linux/sysdev.h>
+#include <linux/cpu.h>
 
 #include <asm/atomic.h>
 #include <asm/smp.h>

@@ -1055,7 +1056,7 @@ void __init setup_secondary_APIC_clock(v
 	local_irq_enable();
 }
 
-void __init disable_APIC_timer(void)
+void __devinit disable_APIC_timer(void)
 {
 	if (using_apic_timer) {
 		unsigned long v;

diff -u -p -B -r1.1.1.1 io_apic.c
@@ -574,9 +574,11 @@ static int balanced_irq(void *unused)
 		time_remaining = schedule_timeout(time_remaining);
 		if (time_after(jiffies,
 				prev_balance_time+balanced_irq_interval)) {
+			preempt_disable();
 			do_irq_balance();
 			prev_balance_time = jiffies;
 			time_remaining = balanced_irq_interval;
+			preempt_enable();
 		}
 	}
 	return 0;

96 lines not on this page · raw message

diff -u -p -B -r1.1.1.1 msr.c
@@ -260,7 +260,7 @@ static struct file_operations msr_fops =
 	.open = msr_open,
 };
 
-static int msr_class_simple_device_add(int i)
+static int __devinit msr_class_simple_device_add(int i)
 {
 	int err = 0;
 	struct class_device *class_err;

diff -u -p -B -r1.1.1.1 process.c
@@ -13,6 +13,7 @@
 
 #include <stdarg.h>
 
+#include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/fs.h>

@@ -54,6 +55,9 @@
 #include <linux/irq.h>
 #include <linux/err.h>
 
+#include <asm/tlbflush.h>
+#include <asm/cpu.h>
+
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
 int hlt_counter;

@@ -132,6 +136,34 @@ static void poll_idle (void)
 	}
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+#include <asm/nmi.h>
+/* We don't actually take CPU down, just spin without interrupts. */
+static inline void play_dead(void)
+{
+	/* Ack it */
+	__get_cpu_var(cpu_state) = CPU_DEAD;
+
+	/* We shouldn't have to disable interrupts while dead, but
+	 * some interrupts just don't seem to go away, and this makes
+	 * it "work" for testing purposes. */
+	/* Death loop */
+	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
+		cpu_relax();
+
+	local_irq_disable();
+	__flush_tlb_all();
+	cpu_set(smp_processor_id(), cpu_online_map);
+	enable_APIC_timer();
+	local_irq_enable();
+}
+#else
+static inline void play_dead(void)
+{
+	BUG();
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
 /*
  * The idle thread. There's no useful work to be
  * done, so just try to conserve power and have a

@@ -155,6 +187,8 @@ void cpu_idle (void)
 			if (!idle)
 				idle = default_idle;
 
+			if (cpu_is_offline(smp_processor_id()))
+				play_dead();
 			irq_stat[smp_processor_id()].idle_timestamp = jiffies;
 			idle();
 			rcu_read_unlock();

diff -u -p -B -r1.1.1.1 smp.c
@@ -19,6 +19,7 @@
 #include <linux/mc146818rtc.h>
 #include <linux/cache.h>
 #include <linux/interrupt.h>
+#include <linux/cpu.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>

@@ -166,7 +167,7 @@ void send_IPI_mask_bitmask(cpumask_t cpu
 	unsigned long flags;
 
 	local_irq_save(flags);
-		
+	WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]);
 	/*
 	 * Wait for idle.
 	 */

@@ -351,21 +352,21 @@ out:
 static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 						unsigned long va)
 {
-	cpumask_t tmp;
 	/*
 	 * A couple of (to be removed) sanity checks:
 	 *
-	 * - we do not send IPIs to not-yet booted CPUs.
 	 * - current CPU must not be in mask
 	 * - mask must exist :)
 	 */
 	BUG_ON(cpus_empty(cpumask));
-
-	cpus_and(tmp, cpumask, cpu_online_map);
-	BUG_ON(!cpus_equal(cpumask, tmp));
 	BUG_ON(cpu_isset(smp_processor_id(), cpumask));
 	BUG_ON(!mm);
 
+	/* If a CPU which we ran on has gone down, OK. */
+	cpus_and(cpumask, cpumask, cpu_online_map);
+	if (cpus_empty(cpumask))
+		return;
+
 	/*
 	 * i'm not happy about this global shared spinlock in the
 	 * MM hot path, but we'll see how contended it is.

@@ -490,6 +491,7 @@ void smp_send_nmi_allbutself(void)
  */
 void smp_send_reschedule(int cpu)
 {
+	WARN_ON(cpu_is_offline(cpu));
 	send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
 }
 

@@ -535,10 +537,16 @@ int smp_call_function (void (*func) (voi
  */
 {
 	struct call_data_struct data;
-	int cpus = num_online_cpus()-1;
+	int cpus;
 
-	if (!cpus)
+	/* Holding any lock stops cpus from going down. */
+	spin_lock(&call_lock);
+	cpus = num_online_cpus()-1;
+
+	if (!cpus) {
+		spin_unlock(&call_lock);
 		return 0;
+	}
 
 	/* Can deadlock when called with interrupts disabled */
 	WARN_ON(irqs_disabled());

@@ -550,7 +558,6 @@ int smp_call_function (void (*func) (voi
 	if (wait)
 		atomic_set(&data.finished, 0);
 
-	spin_lock(&call_lock);
 	call_data = &data;
 	mb();
 	

131 lines not on this page · raw message

diff -u -p -B -r1.1.1.1 traps.c
@@ -692,6 +692,14 @@ asmlinkage void do_nmi(struct pt_regs * 
 	nmi_enter();
 
 	cpu = smp_processor_id();
+
+#ifdef CONFIG_HOTPLUG_CPU
+	if (!cpu_online(cpu)) {
+		nmi_exit();
+		return;
+	}
+#endif
+
 	++nmi_count(cpu);
 
 	if (!nmi_callback(regs, cpu))

diff -u -p -B -r1.1.1.1 smpboot.c
@@ -591,9 +591,10 @@ int __cpu_disable(void)
 	if (cpu == 0)
 		return -EBUSY;
 
+	cpu_clear(cpu, cpu_online_map);
 	fixup_irqs();
 	local_flush_tlb_all();
-	printk ("Disabled cpu %u\n", smp_processor_id());
+	printk("Disabled cpu %u\n", cpu);
 	return 0;
 }
 

diff -u -p -B -r1.1.1.1 smp.c
@@ -273,11 +273,13 @@ int __cpu_disable(void)
 {
 	/* FIXME: go put this in a header somewhere */
 	extern void xics_migrate_irqs_away(void);
+	int cpu = smp_processor_id();
 
+	cpu_clear(cpu, cpu_online_map);
 	systemcfg->processorCount--;
 
 	/*fix boot_cpuid here*/
-	if (smp_processor_id() == boot_cpuid)
+	if (cpu == boot_cpuid)
 		boot_cpuid = any_online_cpu(cpu_online_map);
 
 	/* FIXME: abstract this to not be platform specific later on */

diff -u -p -B -r1.1.1.1 smp.c
@@ -688,13 +688,15 @@ __cpu_disable(void)
 {
 	unsigned long flags;
 	ec_creg_mask_parms cr_parms;
+	int cpu = smp_processor_id();
 
 	spin_lock_irqsave(&smp_reserve_lock, flags);
-	if (smp_cpu_reserved[smp_processor_id()] != 0) {
+	if (smp_cpu_reserved[cpu] != 0) {
 		spin_unlock_irqrestore(&smp_reserve_lock, flags);
 		return -EBUSY;
 	}
 
+	cpu_clear(cpu, cpu_online_map);
 	/* disable all external interrupts */
 
 	cr_parms.start_ctl = 0;

diff -u -p -B -r1.1.1.1 cpu.h
@@ -5,6 +5,7 @@
 #include <linux/cpu.h>
 #include <linux/topology.h>
 #include <linux/nodemask.h>
+#include <linux/percpu.h>
 
 #include <asm/node.h>
 

@@ -26,4 +27,5 @@ static inline int arch_register_cpu(int 
 	return register_cpu(&cpu_devices[num].cpu, num, parent);
 }
 
+DECLARE_PER_CPU(int, cpu_state);
 #endif /* _ASM_I386_CPU_H_ */

diff -u -p -B -r1.1.1.1 irq.h
@@ -34,4 +34,8 @@ extern void release_vm86_irqs(struct tas
 # define irq_ctx_init(cpu) do { } while (0)
 #endif
 
+#ifdef CONFIG_HOTPLUG_CPU
+extern void fixup_irqs(cpumask_t map);
+#endif
+
 #endif /* _ASM_IRQ_H */

diff -u -p -B -r1.1.1.1 smp.h
@@ -85,6 +85,9 @@ static __inline int logical_smp_processo
 }
 
 #endif
+
+extern int __cpu_disable(void);
+extern void __cpu_die(unsigned int cpu);
 #endif /* !__ASSEMBLY__ */
 
 #define NO_PROC_ID		0xFF		/* No processor magic marker */

diff -u -p -B -r1.1.1.1 cpu.c
@@ -62,19 +62,15 @@ static int take_cpu_down(void *unused)
 {
 	int err;
 
-	/* Take offline: makes arch_cpu_down somewhat easier. */
-	cpu_clear(smp_processor_id(), cpu_online_map);
-
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
 	if (err < 0)
-		cpu_set(smp_processor_id(), cpu_online_map);
-	else
-		/* Force idle task to run as soon as we yield: it should
-		   immediately notice cpu is offline and die quickly. */
-		sched_idle_next();
+		return err;
 
-	return err;
+	/* Force idle task to run as soon as we yield: it should
+	   immediately notice cpu is offline and die quickly. */
+	sched_idle_next();
+	return 0;
 }
 
 int cpu_down(unsigned int cpu)

diff -puN kernel/cpu.c~cpu_down-fix-smp_processor_id-warning kernel/cpu.c
@@ -129,7 +129,8 @@ int cpu_down(unsigned int cpu)
 	__cpu_die(cpu);
 
 	/* Move it here so it can run. */
-	kthread_bind(p, smp_processor_id());
+	kthread_bind(p, get_cpu());
+	put_cpu();
 
 	/* CPU is completely dead: tell everyone.  Too late to complain. */
 	if (notifier_call_chain(&cpu_chain, CPU_DEAD, (void *)(long)cpu)