RML pre-emptive 2.4.19-ac2 with O(1)

diff -ru linux-2.4.19-rc2/kernel/sched.c linux/kernel/sched.c
@@ -345,11 +345,13 @@
 #if CONFIG_SMP
 	int need_resched;
 
+      preempt_disable();
 	need_resched = p->need_resched;
 	wmb();
 	set_tsk_need_resched(p);
 	if (!need_resched && (p->cpu != smp_processor_id()))
 		smp_send_reschedule(p->cpu);
+ preempt_enable();
 #else
 	set_tsk_need_resched(p);
 #endif

@@ -367,6 +369,7 @@
 	runqueue_t *rq;
 
 repeat:
+	preempt_disable();
 	rq = task_rq(p);
 	if (unlikely(task_running(rq, p))) {
 		cpu_relax();

@@ -375,14 +378,17 @@
 		 * a preemption point - we are busy-waiting
 		 * anyway.
 		 */
+	        preempt_enable();
 		goto repeat;
 	}
 	rq = task_rq_lock(p, &flags);
 	if (unlikely(task_running(rq, p))) {
 		task_rq_unlock(rq, &flags);
+		preempt_enable();
 		goto repeat;
 	}
 	task_rq_unlock(rq, &flags);
+	preempt_enable();
 }
 #endif
 

@@ -519,7 +525,7 @@
 			p->sleep_avg) / (EXIT_WEIGHT + 1);
 }
 
-#if CONFIG_SMP
+#if CONFIG_SMP  || CONFIG_PREEMPT
 asmlinkage void schedule_tail(task_t *prev)
 {
 	finish_arch_switch(this_rq(), prev);

@@ -1078,6 +1084,7 @@
 		BUG();
 
 need_resched:
+	preempt_disable();
 	prev = current;
 	rq = this_rq();
 

@@ -1085,6 +1092,14 @@
 	prev->sleep_timestamp = jiffies;
 	spin_lock_irq(&rq->lock);
 
+#ifdef CONFIG_PREEMPT
+	/*
+	 * entering from preempt_schedule, off a kernel preemption,
+	 * go straight to picking the next task.
+	 */
+	if (unlikely(preempt_get_count() & PREEMPT_ACTIVE))
+		goto pick_next_task;
+#endif
 	switch (prev->state) {
 	case TASK_INTERRUPTIBLE:
 		if (unlikely(signal_pending(prev))) {

@@ -1096,9 +1111,9 @@
 	case TASK_RUNNING:
 		;
 	}
-#if CONFIG_SMP
+
 pick_next_task:
-#endif
+
 	if (unlikely(!rq->nr_running)) {
 #if CONFIG_SMP
 		load_balance(rq, 1);

@@ -1151,10 +1166,30 @@
 		spin_unlock_irq(&rq->lock);
 
 	reacquire_kernel_lock(current);
+
 	if (need_resched())
 		goto need_resched;
+     	preempt_enable_no_resched();
+
+}
+
+#ifdef CONFIG_PREEMPT
+
+ /*
+  * this is is the entry point to schedule() from in-kernel preemption.
+  */
+ asmlinkage void preempt_schedule(void)
+ {
+       do {
+               current->preempt_count += PREEMPT_ACTIVE;
+               schedule();
+               current->preempt_count -= PREEMPT_ACTIVE;
+               barrier();
+       } while (current->need_resched);
 }
 
+#endif /* CONFIG_PREEMPT */
+
 /*
  * The core wakeup function.  Non-exclusive wakeups (nr_exclusive == 0) just
  * wake everything up.  If it's an exclusive wakeup (nr_exclusive == small 

diff -ru linux-2.4.19-rc2/kernel/sched.c linux/kernel/sched.c
@@ -345,11 +345,13 @@
 #if CONFIG_SMP
 	int need_resched;
 
+      preempt_disable();
 	need_resched = p->need_resched;
 	wmb();
 	set_tsk_need_resched(p);
 	if (!need_resched && (p->cpu != smp_processor_id()))
 		smp_send_reschedule(p->cpu);
+ preempt_enable();
 #else
 	set_tsk_need_resched(p);
 #endif

@@ -367,6 +369,7 @@
 	runqueue_t *rq;
 
 repeat:
+	preempt_disable();
 	rq = task_rq(p);
 	if (unlikely(task_running(rq, p))) {
 		cpu_relax();

@@ -375,14 +378,17 @@
 		 * a preemption point - we are busy-waiting
 		 * anyway.
 		 */
+	        preempt_enable();
 		goto repeat;
 	}
 	rq = task_rq_lock(p, &flags);
 	if (unlikely(task_running(rq, p))) {
 		task_rq_unlock(rq, &flags);
+		preempt_enable();
 		goto repeat;
 	}
 	task_rq_unlock(rq, &flags);
+	preempt_enable();
 }
 #endif
 

@@ -519,7 +525,7 @@
 			p->sleep_avg) / (EXIT_WEIGHT + 1);
 }
 
-#if CONFIG_SMP
+#if CONFIG_SMP  || CONFIG_PREEMPT
 asmlinkage void schedule_tail(task_t *prev)
 {
 	finish_arch_switch(this_rq(), prev);

@@ -1078,6 +1084,7 @@
 		BUG();
 
 need_resched:
+	preempt_disable();
 	prev = current;
 	rq = this_rq();
 

@@ -1085,6 +1092,14 @@
 	prev->sleep_timestamp = jiffies;
 	spin_lock_irq(&rq->lock);
 
+#ifdef CONFIG_PREEMPT
+	/*
+	 * entering from preempt_schedule, off a kernel preemption,
+	 * go straight to picking the next task.
+	 */
+	if (unlikely(preempt_get_count() & PREEMPT_ACTIVE))
+		goto pick_next_task;
+#endif
 	switch (prev->state) {
 	case TASK_INTERRUPTIBLE:
 		if (unlikely(signal_pending(prev))) {

@@ -1096,9 +1111,8 @@
 	case TASK_RUNNING:
 		;
 	}
-#if CONFIG_SMP
+
 pick_next_task:
-#endif
 	if (unlikely(!rq->nr_running)) {
 #if CONFIG_SMP
 		load_balance(rq, 1);

@@ -1151,13 +1165,33 @@
 		spin_unlock_irq(&rq->lock);
 
 	reacquire_kernel_lock(current);
+
 	if (need_resched())
 		goto need_resched;
+     	preempt_enable_no_resched();
+
+}
+
+#ifdef CONFIG_PREEMPT
+
+ /*
+  * this is is the entry point to schedule() from in-kernel preemption.
+  */
+ asmlinkage void preempt_schedule(void)
+ {
+       do {
+               current->preempt_count += PREEMPT_ACTIVE;
+               schedule();
+               current->preempt_count -= PREEMPT_ACTIVE;
+               barrier();
+       } while (current->need_resched);
 }
 
+#endif /* CONFIG_PREEMPT */
+
 /*
  * The core wakeup function.  Non-exclusive wakeups (nr_exclusive == 0) just
- * wake everything up.  If it's an exclusive wakeup (nr_exclusive == small 
+ve
+ * wake everything up.  If it's an exclusive wakeup (nr_exclusive == small
  * number) then we wake all the non-exclusive tasks and one exclusive task.
  *

diff -urN linux-2.4.18-O1-affinity/arch/arm/tools/getconstants.c linux/arch/arm/tools/getconstants.c
@@ -13,6 +13,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
+#include <asm/hardirq.h>
 
 /*
  * Make sure that the compiler and target are compatible.

@@ -39,6 +40,11 @@
 DEFN("TSS_SAVE",		OFF_TSK(thread.save));
 DEFN("TSS_FPESAVE",		OFF_TSK(thread.fpstate.soft.save));
 
+#ifdef CONFIG_PREEMPT
+DEFN("TSK_PREEMPT",		OFF_TSK(preempt_count));
+DEFN("IRQSTAT_BH_COUNT",	(unsigned long)&(((irq_cpustat_t *)0)->__local_bh_count));
+#endif
+
 #ifdef CONFIG_CPU_32
 DEFN("TSS_DOMAIN",		OFF_TSK(thread.domain));
 

diff -urN linux-2.4.18-O1-affinity/arch/i386/kernel/i387.c linux/arch/i386/kernel/i387.c
@@ -10,6 +10,7 @@
 
 #include <linux/config.h>
 #include <linux/sched.h>
+#include <linux/spinlock.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/math_emu.h>

@@ -65,6 +66,8 @@
 {
 	struct task_struct *tsk = current;
 
+	preempt_disable();
+	
 	if (tsk->flags & PF_USEDFPU) {
 		__save_init_fpu(tsk);
 		return;

diff -urN linux-2.4.18-O1-affinity/arch/i386/kernel/smp.c linux/arch/i386/kernel/smp.c
@@ -354,10 +354,14 @@
 
 asmlinkage void smp_invalidate_interrupt (void)
 {
-	unsigned long cpu = smp_processor_id();
+	unsigned long cpu;;
+
+	preempt_disable();
+
+	cpu = smp_processor_id();
 
 	if (!test_bit(cpu, &flush_cpumask))
-		return;
+		goto out;
 		/* 
 		 * This was a BUG() but until someone can quote me the
 		 * line from the intel manual that guarantees an IPI to

@@ -378,6 +382,8 @@
 	}
 	ack_APIC_irq();
 	clear_bit(cpu, &flush_cpumask);
+out:
+	preempt_enable();
 }
 
 static void flush_tlb_others (unsigned long cpumask, struct mm_struct *mm,

@@ -427,16 +433,22 @@
 void flush_tlb_current_task(void)
 {
 	struct mm_struct *mm = current->mm;
-	unsigned long cpu_mask = mm->cpu_vm_mask & ~(1 << smp_processor_id());
-
+	unsigned long cpu_mask;
+	
+	preempt_disable();
+	cpu_mask = mm->cpu_vm_mask & ~(1 << smp_processor_id());
 	local_flush_tlb();
 	if (cpu_mask)
 		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+	preempt_enable();
 }
 
 void flush_tlb_mm (struct mm_struct * mm)
 {
-	unsigned long cpu_mask = mm->cpu_vm_mask & ~(1 << smp_processor_id());
+	unsigned long cpu_mask;
+	
+	preempt_disable();
+	cpu_mask = mm->cpu_vm_mask & ~(1 << smp_processor_id());
 
 	if (current->active_mm == mm) {
 		if (current->mm)

@@ -446,12 +458,17 @@
 	}
 	if (cpu_mask)
 		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+
+	preempt_enable();
 }
 
 void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long cpu_mask = mm->cpu_vm_mask & ~(1 << smp_processor_id());
+	unsigned long cpu_mask;
+	
+	preempt_disable();
+	cpu_mask = mm->cpu_vm_mask & ~(1 << smp_processor_id());
 
 	if (current->active_mm == mm) {
 		if(current->mm)

@@ -462,6 +479,8 @@
 
 	if (cpu_mask)
 		flush_tlb_others(cpu_mask, mm, va);
+
+	preempt_enable();
 }
 
 static inline void do_flush_tlb_all_local(void)

diff -urN linux-2.4.18-O1-affinity/arch/i386/kernel/traps.c linux/arch/i386/kernel/traps.c
@@ -694,6 +694,8 @@
  *
  * Careful.. There are problems with IBM-designed IRQ13 behaviour.
  * Don't touch unless you *really* know how it works.
+ *
+ * Must be called with kernel preemption disabled.
  */
 asmlinkage void math_state_restore(struct pt_regs regs)
 {

diff -urN linux-2.4.18-O1-affinity/arch/i386/lib/dec_and_lock.c linux/arch/i386/lib/dec_and_lock.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/spinlock.h>
+#include <linux/sched.h>
 #include <asm/atomic.h>
 
 int atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)

diff -urN linux-2.4.18-O1-affinity/arch/mips/kernel/i8259.c linux/arch/mips/kernel/i8259.c
@@ -8,6 +8,7 @@
  * Copyright (C) 1992 Linus Torvalds
  * Copyright (C) 1994 - 2000 Ralf Baechle
  */
+#include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/ioport.h>

diff -urN linux-2.4.18-O1-affinity/arch/mips/kernel/irq.c linux/arch/mips/kernel/irq.c
@@ -17,8 +17,11 @@
 #include <linux/mm.h>
 #include <linux/random.h>
 #include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/ptrace.h>
 
 #include <asm/system.h>
+#include <asm/debug.h>
 
 /*
  * Controller mappings for all interrupt sources:

@@ -244,6 +247,8 @@
 	struct irqaction * action;
 	unsigned int status;
 
+	preempt_disable();
+
 	kstat.irqs[cpu][irq]++;
 	spin_lock(&desc->lock);
 	desc->handler->ack(irq);

@@ -305,6 +310,27 @@
 
 	if (softirq_pending(cpu))
 		do_softirq();
+
+#if defined(CONFIG_PREEMPT)
+	while (--current->preempt_count == 0) {
+		db_assert(intr_off());
+		db_assert(!in_interrupt());
+
+		if (current->need_resched == 0) {
+			break;
+		}
+
+		current->preempt_count ++;
+		sti();
+		if (user_mode(regs)) {
+			schedule();
+		} else {
+			preempt_schedule();
+		}
+		cli();
+	}
+#endif
+
 	return 1;
 }
 

diff -urN linux-2.4.18-O1-affinity/arch/mips/mm/extable.c linux/arch/mips/mm/extable.c
@@ -3,6 +3,7 @@
  */
 #include <linux/config.h>
 #include <linux/module.h>
+#include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <asm/uaccess.h>
 

diff -urN linux-2.4.18-O1-affinity/arch/sh/kernel/irq.c linux/arch/sh/kernel/irq.c
@@ -229,6 +229,14 @@
 	struct irqaction * action;
 	unsigned int status;
 
+	/*
+	 * At this point we're now about to actually call handlers,
+	 * and interrupts might get reenabled during them... bump
+	 * preempt_count to prevent any preemption while the handler
+ 	 * called here is pending...
+ 	 */
+ 	preempt_disable();
+
 	/* Get IRQ number */
 	asm volatile("stc	r2_bank, %0\n\t"
 		     "shlr2	%0\n\t"

@@ -298,8 +306,17 @@
 	desc->handler->end(irq);
 	spin_unlock(&desc->lock);
 
+
 	if (softirq_pending(cpu))
 		do_softirq();
+
+	/*
+	 * We're done with the handlers, interrupts should be
+	 * currently disabled; decrement preempt_count now so
+	 * as we return preemption may be allowed...
+	 */
+	preempt_enable_no_resched();
+
 	return 1;
 }
 

diff -urN linux-2.4.18-O1-affinity/drivers/ieee1394/csr.c linux/drivers/ieee1394/csr.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/string.h>
+#include <linux/sched.h>
 
 #include "ieee1394_types.h"
 #include "hosts.h"

diff -urN linux-2.4.18-O1-affinity/drivers/sound/sound_core.c linux/drivers/sound/sound_core.c
@@ -37,6 +37,7 @@
 #include <linux/config.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/kernel.h>

diff -urN linux-2.4.18-O1-affinity/fs/adfs/map.c linux/fs/adfs/map.c
@@ -12,6 +12,7 @@
 #include <linux/fs.h>
 #include <linux/adfs_fs.h>
 #include <linux/spinlock.h>
+#include <linux/sched.h>
 
 #include "adfs.h"
 

diff -urN linux-2.4.18-O1-affinity/fs/exec.c linux/fs/exec.c
@@ -420,8 +420,8 @@
 		active_mm = current->active_mm;
 		current->mm = mm;
 		current->active_mm = mm;
-		task_unlock(current);
 		activate_mm(active_mm, mm);
+		task_unlock(current);
 		mm_release();
 		if (old_mm) {
 			if (active_mm != old_mm) BUG();

diff -urN linux-2.4.18-O1-affinity/fs/fat/cache.c linux/fs/fat/cache.c
@@ -14,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/stat.h>
 #include <linux/fat_cvf.h>
+#include <linux/sched.h>
 
 #if 0
 #  define PRINTK(x) printk x

diff -urN linux-2.4.18-O1-affinity/fs/nls/nls_base.c linux/fs/nls/nls_base.c
@@ -18,6 +18,7 @@
 #ifdef CONFIG_KMOD
 #include <linux/kmod.h>
 #endif
+#include <linux/sched.h>
 #include <linux/spinlock.h>
 
 static struct nls_table *tables;

diff -urN linux-2.4.18-O1-affinity/include/asm-arm/dma.h linux/include/asm-arm/dma.h
@@ -5,6 +5,7 @@
 
 #include <linux/config.h>
 #include <linux/spinlock.h>
+#include <linux/sched.h>
 #include <asm/system.h>
 #include <asm/memory.h>
 #include <asm/scatterlist.h>

diff -urN linux-2.4.18-O1-affinity/include/asm-arm/hardirq.h linux/include/asm-arm/hardirq.h
@@ -34,6 +34,7 @@
 #define irq_exit(cpu,irq)	(local_irq_count(cpu)--)
 
 #define synchronize_irq()	do { } while (0)
+#define release_irqlock(cpu)	do { } while (0)
 
 #else
 #error SMP not supported

diff -urN linux-2.4.18-O1-affinity/include/asm-arm/pgalloc.h linux/include/asm-arm/pgalloc.h
@@ -57,40 +57,48 @@
 {
 	unsigned long *ret;
 
+	preempt_disable();
 	if ((ret = pgd_quicklist) != NULL) {
 		pgd_quicklist = (unsigned long *)__pgd_next(ret);
 		ret[1] = ret[2];
 		clean_dcache_entry(ret + 1);
 		pgtable_cache_size--;
 	}
+	preempt_enable();
 	return (pgd_t *)ret;
 }
 
 static inline void free_pgd_fast(pgd_t *pgd)
 {
+	preempt_disable();
 	__pgd_next(pgd) = (unsigned long) pgd_quicklist;
 	pgd_quicklist = (unsigned long *) pgd;
 	pgtable_cache_size++;
+	preempt_enable();
 }
 
 static inline pte_t *pte_alloc_one_fast(struct mm_struct *mm, unsigned long address)
 {
 	unsigned long *ret;
 
+	preempt_disable();
 	if((ret = pte_quicklist) != NULL) {
 		pte_quicklist = (unsigned long *)__pte_next(ret);
 		ret[0] = 0;
 		clean_dcache_entry(ret);
 		pgtable_cache_size--;
 	}
+	preempt_enable();
 	return (pte_t *)ret;
 }
 
 static inline void free_pte_fast(pte_t *pte)
 {
+	preempt_disable();
 	__pte_next(pte) = (unsigned long) pte_quicklist;
 	pte_quicklist = (unsigned long *) pte;
 	pgtable_cache_size++;
+	preempt_enable();
 }
 
 #else	/* CONFIG_NO_PGT_CACHE */

diff -urN linux-2.4.18-O1-affinity/include/asm-arm/smplock.h linux/include/asm-arm/smplock.h
@@ -3,12 +3,17 @@
  *
  * Default SMP lock implementation
  */
+#include <linux/config.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 
 extern spinlock_t kernel_flag;
 
+#ifdef CONFIG_PREEMPT
+#define kernel_locked()		preempt_get_count()
+#else
 #define kernel_locked()		spin_is_locked(&kernel_flag)
+#endif
 
 /*
  * Release global kernel lock and global interrupt lock

@@ -40,8 +45,14 @@
  */
 static inline void lock_kernel(void)
 {
+#ifdef CONFIG_PREEMPT
+	if (current->lock_depth == -1)
+		spin_lock(&kernel_flag);
+	++current->lock_depth;
+#else
 	if (!++current->lock_depth)
 		spin_lock(&kernel_flag);
+#endif
 }
 
 static inline void unlock_kernel(void)

diff -urN linux-2.4.18-O1-affinity/include/asm-arm/softirq.h linux/include/asm-arm/softirq.h
@@ -5,20 +5,22 @@
 #include <asm/hardirq.h>
 
 #define __cpu_bh_enable(cpu) \
-		do { barrier(); local_bh_count(cpu)--; } while (0)
+		do { barrier(); local_bh_count(cpu)--; preempt_enable(); } while (0)
 #define cpu_bh_disable(cpu) \
-		do { local_bh_count(cpu)++; barrier(); } while (0)
+		do { preempt_disable(); local_bh_count(cpu)++; barrier(); } while (0)
 
 #define local_bh_disable()	cpu_bh_disable(smp_processor_id())
 #define __local_bh_enable()	__cpu_bh_enable(smp_processor_id())
 
 #define in_softirq()		(local_bh_count(smp_processor_id()) != 0)
 
-#define local_bh_enable()						\
+#define _local_bh_enable()						\
 do {									\
 	unsigned int *ptr = &local_bh_count(smp_processor_id());	\
 	if (!--*ptr && ptr[-2])						\
 		__asm__("bl%? __do_softirq": : : "lr");/* out of line */\
 } while (0)
 
+#define local_bh_enable() do { _local_bh_enable(); preempt_enable(); } while (0)
+
 #endif	/* __ASM_SOFTIRQ_H */

diff -urN linux-2.4.18-O1-affinity/include/asm-i386/hardirq.h linux/include/asm-i386/hardirq.h
@@ -36,6 +36,8 @@
 
 #define synchronize_irq()	barrier()
 
+#define release_irqlock(cpu)	do { } while (0)
+
 #else
 
 #include <asm/atomic.h>

diff -urN linux-2.4.18-O1-affinity/include/asm-i386/highmem.h linux/include/asm-i386/highmem.h
@@ -88,6 +88,7 @@
 	enum fixed_addresses idx;
 	unsigned long vaddr;
 
+	preempt_disable();
 	if (page < highmem_start_page)
 		return page_address(page);
 

@@ -109,8 +110,10 @@
 	unsigned long vaddr = (unsigned long) kvaddr;
 	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
 
-	if (vaddr < FIXADDR_START) // FIXME
+	if (vaddr < FIXADDR_START) { // FIXME
+		preempt_enable();
 		return;
+	}
 
 	if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx))
 		BUG();

@@ -122,6 +125,8 @@
 	pte_clear(kmap_pte-idx);
 	__flush_tlb_one(vaddr);
 #endif
+
+	preempt_enable();
 }
 
 #endif /* __KERNEL__ */

diff -urN linux-2.4.18-O1-affinity/include/asm-i386/hw_irq.h linux/include/asm-i386/hw_irq.h
@@ -95,6 +95,18 @@
 #define __STR(x) #x
 #define STR(x) __STR(x)
 
+#define GET_CURRENT \
+	"movl %esp, %ebx\n\t" \
+	"andl $-8192, %ebx\n\t"
+
+#ifdef CONFIG_PREEMPT
+#define BUMP_LOCK_COUNT \
+	GET_CURRENT \
+	"incl 4(%ebx)\n\t"
+#else
+#define BUMP_LOCK_COUNT
+#endif
+
 #define SAVE_ALL \
 	"cld\n\t" \
 	"pushl %es\n\t" \

@@ -108,15 +120,12 @@
 	"pushl %ebx\n\t" \
 	"movl $" STR(__KERNEL_DS) ",%edx\n\t" \
 	"movl %edx,%ds\n\t" \
-	"movl %edx,%es\n\t"
+	"movl %edx,%es\n\t" \
+	BUMP_LOCK_COUNT
 
 #define IRQ_NAME2(nr) nr##_interrupt(void)
 #define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
 
-#define GET_CURRENT \
-	"movl %esp, %ebx\n\t" \
-	"andl $-8192, %ebx\n\t"
-
 /*
  *	SMP has a few special interrupts for IPI messages
  */

diff -urN linux-2.4.18-O1-affinity/include/asm-i386/i387.h linux/include/asm-i386/i387.h
@@ -12,6 +12,7 @@
 #define __ASM_I386_I387_H
 
 #include <linux/sched.h>
+#include <linux/spinlock.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
 #include <asm/user.h>

@@ -24,7 +25,7 @@
 extern void restore_fpu( struct task_struct *tsk );
 
 extern void kernel_fpu_begin(void);
-#define kernel_fpu_end() stts()
+#define kernel_fpu_end() do { stts(); preempt_enable(); } while(0)
 
 
 #define unlazy_fpu( tsk ) do { \

diff -urN linux-2.4.18-O1-affinity/include/asm-i386/pgalloc.h linux/include/asm-i386/pgalloc.h
@@ -75,20 +75,26 @@
 {
 	unsigned long *ret;
 
+	preempt_disable();
 	if ((ret = pgd_quicklist) != NULL) {
 		pgd_quicklist = (unsigned long *)(*ret);
 		ret[0] = 0;
 		pgtable_cache_size--;
-	} else
+		preempt_enable();
+	} else {
+		preempt_enable();
 		ret = (unsigned long *)get_pgd_slow();
+	}
 	return (pgd_t *)ret;
 }
 
 static inline void free_pgd_fast(pgd_t *pgd)
 {
+	preempt_disable();
 	*(unsigned long *)pgd = (unsigned long) pgd_quicklist;
 	pgd_quicklist = (unsigned long *) pgd;
 	pgtable_cache_size++;
+	preempt_enable();
 }
 
 static inline void free_pgd_slow(pgd_t *pgd)

@@ -119,19 +125,23 @@
 {
 	unsigned long *ret;
 
+	preempt_disable();
 	if ((ret = (unsigned long *)pte_quicklist) != NULL) {
 		pte_quicklist = (unsigned long *)(*ret);
 		ret[0] = ret[1];
 		pgtable_cache_size--;
 	}
+	preempt_enable();
 	return (pte_t *)ret;
 }
 
 static inline void pte_free_fast(pte_t *pte)
 {
+	preempt_disable();
 	*(unsigned long *)pte = (unsigned long) pte_quicklist;
 	pte_quicklist = (unsigned long *) pte;
 	pgtable_cache_size++;
+	preempt_enable();
 }
 
 static __inline__ void pte_free_slow(pte_t *pte)

diff -urN linux-2.4.18-O1-affinity/include/asm-i386/smplock.h linux/include/asm-i386/smplock.h
@@ -10,7 +10,15 @@
 
 extern spinlock_t kernel_flag;
 
+#ifdef CONFIG_SMP
 #define kernel_locked()		spin_is_locked(&kernel_flag)
+#else
+#ifdef CONFIG_PREEMPT
+#define kernel_locked()		preempt_get_count()
+#else
+#define kernel_locked()		1
+#endif
+#endif
 
 /*
  * Release global kernel lock and global interrupt lock

@@ -42,6 +50,11 @@
  */
 static __inline__ void lock_kernel(void)
 {
+#ifdef CONFIG_PREEMPT
+	if (current->lock_depth == -1)
+		spin_lock(&kernel_flag);
+	++current->lock_depth;
+#else
 #if 1
 	if (!++current->lock_depth)
 		spin_lock(&kernel_flag);

@@ -54,6 +67,7 @@
 		:"=m" (__dummy_lock(&kernel_flag)),
 		 "=m" (current->lock_depth));
 #endif
+#endif
 }
 
 static __inline__ void unlock_kernel(void)

diff -urN linux-2.4.18-O1-affinity/include/asm-i386/softirq.h linux/include/asm-i386/softirq.h
@@ -6,9 +6,9 @@
 #include <linux/stringify.h>
 
 #define __cpu_bh_enable(cpu) \
-		do { barrier(); local_bh_count(cpu)--; } while (0)
+		do { barrier(); local_bh_count(cpu)--; preempt_enable(); } while (0)
 #define cpu_bh_disable(cpu) \
-		do { local_bh_count(cpu)++; barrier(); } while (0)
+		do { preempt_disable(); local_bh_count(cpu)++; barrier(); } while (0)
 
 #define local_bh_disable()	cpu_bh_disable(smp_processor_id())
 #define __local_bh_enable()	__cpu_bh_enable(smp_processor_id())

@@ -23,7 +23,7 @@
  * If you change the offsets in irq_stat then you have to
  * update this code as well.
  */
-#define local_bh_enable()						\
+#define _local_bh_enable()						\
 do {									\
 	unsigned int *ptr = &local_bh_count(smp_processor_id());	\
 									\

@@ -49,4 +49,6 @@
 		/* no registers clobbered */ );				\
 } while (0)
 
+#define local_bh_enable() do { _local_bh_enable(); preempt_enable(); } while (0)
+
 #endif	/* __ASM_SOFTIRQ_H */

diff -urN linux-2.4.18-O1-affinity/include/asm-i386/spinlock.h linux/include/asm-i386/spinlock.h
@@ -81,7 +81,7 @@
 		:"=m" (lock->lock) : : "memory"
 
 
-static inline void spin_unlock(spinlock_t *lock)
+static inline void _raw_spin_unlock(spinlock_t *lock)
 {
 #if SPINLOCK_DEBUG
 	if (lock->magic != SPINLOCK_MAGIC)

@@ -101,7 +101,7 @@
 		:"=q" (oldval), "=m" (lock->lock) \
 		:"0" (oldval) : "memory"
 
-static inline void spin_unlock(spinlock_t *lock)
+static inline void _raw_spin_unlock(spinlock_t *lock)
 {
 	char oldval = 1;
 #if SPINLOCK_DEBUG

@@ -117,7 +117,7 @@
 
 #endif
 
-static inline int spin_trylock(spinlock_t *lock)
+static inline int _raw_spin_trylock(spinlock_t *lock)
 {
 	char oldval;
 	__asm__ __volatile__(

@@ -127,7 +127,7 @@
 	return oldval > 0;
 }
 
-static inline void spin_lock(spinlock_t *lock)
+static inline void _raw_spin_lock(spinlock_t *lock)
 {
 #if SPINLOCK_DEBUG
 	__label__ here;

@@ -183,7 +183,7 @@
  */
 /* the spinlock helpers are in arch/i386/kernel/semaphore.c */
 
-static inline void read_lock(rwlock_t *rw)
+static inline void _raw_read_lock(rwlock_t *rw)
 {
 #if SPINLOCK_DEBUG
 	if (rw->magic != RWLOCK_MAGIC)

@@ -192,7 +192,7 @@
 	__build_read_lock(rw, "__read_lock_failed");
 }
 
-static inline void write_lock(rwlock_t *rw)
+static inline void _raw_write_lock(rwlock_t *rw)
 {
 #if SPINLOCK_DEBUG
 	if (rw->magic != RWLOCK_MAGIC)

@@ -201,10 +201,10 @@
 	__build_write_lock(rw, "__write_lock_failed");
 }
 
-#define read_unlock(rw)		asm volatile("lock ; incl %0" :"=m" ((rw)->lock) : : "memory")
-#define write_unlock(rw)	asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory")
+#define _raw_read_unlock(rw)		asm volatile("lock ; incl %0" :"=m" ((rw)->lock) : : "memory")
+#define _raw_write_unlock(rw)	asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory")
 
-static inline int write_trylock(rwlock_t *lock)
+static inline int _raw_write_trylock(rwlock_t *lock)
 {
 	atomic_t *count = (atomic_t *)lock;
 	if (atomic_sub_and_test(RW_LOCK_BIAS, count))

diff -urN linux-2.4.18-O1-affinity/include/asm-mips/smplock.h linux/include/asm-mips/smplock.h
@@ -6,12 +6,21 @@
  *
  * Default SMP lock implementation
  */
+#include <linux/config.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 
 extern spinlock_t kernel_flag;
 
+#ifdef CONFIG_SMP
 #define kernel_locked()		spin_is_locked(&kernel_flag)
+#else
+#ifdef CONFIG_PREEMPT
+#define kernel_locked()         preempt_get_count()
+#else
+#define kernel_locked()         1
+#endif
+#endif
 
 /*
  * Release global kernel lock and global interrupt lock

@@ -43,8 +52,14 @@
  */
 extern __inline__ void lock_kernel(void)
 {
+#ifdef CONFIG_PREEMPT
+	if (current->lock_depth == -1)
+		spin_lock(&kernel_flag);
+	++current->lock_depth;
+#else
 	if (!++current->lock_depth)
 		spin_lock(&kernel_flag);
+#endif
 }
 
 extern __inline__ void unlock_kernel(void)

diff -urN linux-2.4.18-O1-affinity/include/asm-mips/softirq.h linux/include/asm-mips/softirq.h
@@ -15,6 +15,7 @@
 
 extern inline void cpu_bh_disable(int cpu)
 {
+	preempt_disable();
 	local_bh_count(cpu)++;
 	barrier();
 }

@@ -23,6 +24,7 @@
 {
 	barrier();
 	local_bh_count(cpu)--;
+	preempt_enable();
 }
 
 

@@ -36,6 +38,7 @@
 	cpu = smp_processor_id();				\
 	if (!--local_bh_count(cpu) && softirq_pending(cpu))	\
 		do_softirq();					\
+	preempt_enable();                                       \
 } while (0)
 
 #define in_softirq() (local_bh_count(smp_processor_id()) != 0)

diff -urN linux-2.4.18-O1-affinity/include/asm-mips/system.h linux/include/asm-mips/system.h
@@ -261,4 +261,16 @@
 #define die_if_kernel(msg, regs)					\
 	__die_if_kernel(msg, regs, __FILE__ ":"__FUNCTION__, __LINE__)
 
+extern __inline__ int intr_on(void)
+{
+	unsigned long flags;
+	save_flags(flags);
+	return flags & 1;
+}
+
+extern __inline__ int intr_off(void)
+{
+	return ! intr_on();
+}
+
 #endif /* _ASM_SYSTEM_H */

diff -urN linux-2.4.18-O1-affinity/include/asm-sh/hardirq.h linux/include/asm-sh/hardirq.h
@@ -34,6 +34,8 @@
 
 #define synchronize_irq()	barrier()
 
+#define release_irqlock(cpu)	do { } while (0)
+
 #else
 
 #error Super-H SMP is not available

94 lines not on this page · raw message

diff -urN linux-2.4.18-O1-affinity/include/asm-sh/softirq.h linux/include/asm-sh/softirq.h
@@ -6,6 +6,7 @@
 
 #define local_bh_disable()			\
 do {						\
+	preempt_disable();			\
 	local_bh_count(smp_processor_id())++;	\
 	barrier();				\
 } while (0)

@@ -14,6 +15,7 @@
 do {						\
 	barrier();				\
 	local_bh_count(smp_processor_id())--;	\
+	preempt_enable();			\
 } while (0)
 
 #define local_bh_enable()				\

@@ -23,6 +25,7 @@
 	    && softirq_pending(smp_processor_id())) {	\
 		do_softirq();				\
 	}						\
+	preempt_enable();				\
 } while (0)
 
 #define in_softirq() (local_bh_count(smp_processor_id()) != 0)

diff -urN linux-2.4.18-O1-affinity/include/linux/brlock.h linux/include/linux/brlock.h
@@ -171,11 +171,11 @@
 }
 
 #else
-# define br_read_lock(idx)	((void)(idx))
-# define br_read_unlock(idx)	((void)(idx))
-# define br_write_lock(idx)	((void)(idx))
-# define br_write_unlock(idx)	((void)(idx))
-#endif
+# define br_read_lock(idx)	({ (void)(idx); preempt_disable(); })
+# define br_read_unlock(idx)	({ (void)(idx); preempt_enable(); })
+# define br_write_lock(idx)	({ (void)(idx); preempt_disable(); })
+# define br_write_unlock(idx)	({ (void)(idx); preempt_enable(); })
+#endif	/* CONFIG_SMP */
 
 /*
  * Now enumerate all of the possible sw/hw IRQ protected

65 lines not on this page · raw message

diff -urN linux-2.4.18-O1-affinity/include/linux/fs_struct.h linux/include/linux/fs_struct.h
@@ -20,6 +20,15 @@
 extern void exit_fs(struct task_struct *);
 extern void set_fs_altroot(void);
 
+struct fs_struct *copy_fs_struct(struct fs_struct *old);
+void put_fs_struct(struct fs_struct *fs);
+
+#endif
+#endif
+
+#if !defined(_LINUX_FS_STRUCT_H_INLINES) && defined(_TASK_STRUCT_DEFINED)
+#define _LINUX_FS_STRUCT_H_INLINES
+#ifdef __KERNEL__
 /*
  * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
  * It can block. Requires the big lock held.

@@ -65,9 +74,5 @@
 		mntput(old_pwdmnt);
 	}
 }
-
-struct fs_struct *copy_fs_struct(struct fs_struct *old);
-void put_fs_struct(struct fs_struct *fs);
-
 #endif
 #endif

diff -urN linux-2.4.18-O1-affinity/include/linux/sched.h linux/include/linux/sched.h
@@ -91,6 +91,7 @@
 #define TASK_UNINTERRUPTIBLE	2
 #define TASK_ZOMBIE		4
 #define TASK_STOPPED		8
+#define PREEMPT_ACTIVE		0x4000000
 
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)

@@ -155,6 +156,9 @@
 #define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
 extern signed long FASTCALL(schedule_timeout(signed long timeout));
 asmlinkage void schedule(void);
+#ifdef CONFIG_PREEMPT
+asmlinkage void preempt_schedule(void);
+#endif
 
 extern int schedule_task(struct tq_struct *task);
 extern void flush_scheduled_tasks(void);

@@ -332,7 +336,7 @@
 	 * offsets of these are hardcoded elsewhere - touch with care
 	 */
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
-	unsigned long flags;	/* per process flags, defined below */
+	int preempt_count;	/* 0 => preemptable, <0 => BUG */
 	int sigpending;
 	mm_segment_t addr_limit;	/* thread address space:
 					 	0-0xBFFFFFFF for user-thead

@@ -358,6 +362,7 @@
 	unsigned long policy;
 	unsigned long cpus_allowed;
 	unsigned int time_slice;
+	unsigned long flags;
 
 	task_t *next_task, *prev_task;
 

@@ -976,6 +981,11 @@
 	return unlikely(current->need_resched);
 }
 
+#define _TASK_STRUCT_DEFINED
+#include <linux/dcache.h>
+#include <linux/tqueue.h>
+#include <linux/fs_struct.h>
+
 #endif /* __KERNEL__ */
 
 #endif

diff -urN linux-2.4.18-O1-affinity/include/linux/smp.h linux/include/linux/smp.h
@@ -81,7 +81,9 @@
 #define smp_processor_id()			0
 #define hard_smp_processor_id()			0
 #define smp_threads_ready			1
+#ifndef CONFIG_PREEMPT
 #define kernel_lock()
+#endif
 #define cpu_logical_map(cpu)			0
 #define cpu_number_map(cpu)			0
 #define smp_call_function(func,info,retry,wait)	({ 0; })

diff -urN linux-2.4.18-O1-affinity/include/linux/smp_lock.h linux/include/linux/smp_lock.h
@@ -3,7 +3,7 @@
 
 #include <linux/config.h>
 
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT)
 
 #define lock_kernel()				do { } while(0)
 #define unlock_kernel()				do { } while(0)

119 lines not on this page · raw message

diff -urN linux-2.4.18-O1-affinity/include/linux/tqueue.h linux/include/linux/tqueue.h
@@ -94,6 +94,22 @@
 extern spinlock_t tqueue_lock;
 
 /*
+ * Call all "bottom halfs" on a given list.
+ */
+
+extern void __run_task_queue(task_queue *list);
+
+static inline void run_task_queue(task_queue *list)
+{
+	if (TQ_ACTIVE(*list))
+		__run_task_queue(list);
+}
+
+#endif /* _LINUX_TQUEUE_H */
+
+#if !defined(_LINUX_TQUEUE_H_INLINES) && defined(_TASK_STRUCT_DEFINED)
+#define _LINUX_TQUEUE_H_INLINES
+/*
  * Queue a task on a tq.  Return non-zero if it was successfully
  * added.
  */

@@ -109,17 +125,4 @@
 	}
 	return ret;
 }
-
-/*
- * Call all "bottom halfs" on a given list.
- */
-
-extern void __run_task_queue(task_queue *list);
-
-static inline void run_task_queue(task_queue *list)
-{
-	if (TQ_ACTIVE(*list))
-		__run_task_queue(list);
-}
-
-#endif /* _LINUX_TQUEUE_H */
+#endif

diff -urN linux-2.4.18-O1-affinity/kernel/exit.c linux/kernel/exit.c
@@ -366,8 +366,8 @@
 		/* more a memory barrier than a real lock */
 		task_lock(tsk);
 		tsk->mm = NULL;
-		task_unlock(tsk);
 		enter_lazy_tlb(mm, current, smp_processor_id());
+		task_unlock(tsk);
 		mmput(mm);
 	}
 }

@@ -488,6 +488,11 @@
 	tsk->flags |= PF_EXITING;
 	del_timer_sync(&tsk->real_timer);
 
+	if (unlikely(preempt_get_count()))
+		printk(KERN_WARNING "%s[%d] exited with preempt_count %d\n",
+				current->comm, current->pid,
+				preempt_get_count());
+
 fake_volatile:
 #ifdef CONFIG_BSD_PROCESS_ACCT
 	acct_process(code);

diff -urN linux-2.4.18-O1-affinity/kernel/fork.c linux/kernel/fork.c
@@ -616,6 +616,13 @@
 	if (p->binfmt && p->binfmt->module)
 		__MOD_INC_USE_COUNT(p->binfmt->module);
 
+#ifdef CONFIG_PREEMPT
+	/*
+	 * schedule_tail drops this_rq()->lock so compensate with a count
+	 * of 1.  Also, we want to start with kernel preemption disabled.
+	 */
+	p->preempt_count = 1;
+#endif
 	p->did_exec = 0;
 	p->swappable = 0;
 	p->state = TASK_UNINTERRUPTIBLE;

diff -urN linux-2.4.18-O1-affinity/kernel/ksyms.c linux/kernel/ksyms.c
@@ -436,6 +436,9 @@
 EXPORT_SYMBOL(interruptible_sleep_on);
 EXPORT_SYMBOL(interruptible_sleep_on_timeout);
 EXPORT_SYMBOL(schedule);
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(preempt_schedule);
+#endif
 EXPORT_SYMBOL(schedule_timeout);
 EXPORT_SYMBOL(sys_sched_yield);
 EXPORT_SYMBOL(set_user_nice);

186 lines not on this page · raw message

diff -urN linux-2.4.18-O1-affinity/lib/dec_and_lock.c linux/lib/dec_and_lock.c
@@ -1,5 +1,6 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
+#include <linux/sched.h>
 #include <asm/atomic.h>
 
 /*

diff -urN linux-2.4.18-O1-affinity/mm/slab.c linux/mm/slab.c
@@ -49,7 +49,8 @@
  *  constructors and destructors are called without any locking.
  *  Several members in kmem_cache_t and slab_t never change, they
  *	are accessed without any locking.
- *  The per-cpu arrays are never accessed from the wrong cpu, no locking.
+ *  The per-cpu arrays are never accessed from the wrong cpu, no locking,
+ *  	and local interrupts are disabled so slab code is preempt-safe.
  *  The non-constant members are protected with a per-cache irq spinlock.
  *
  * Further notes from the original documentation:

diff -urN linux-2.4.18-O1-affinity/net/core/dev.c linux/net/core/dev.c
@@ -1033,9 +1033,11 @@
 		int cpu = smp_processor_id();
 
 		if (dev->xmit_lock_owner != cpu) {
+			preempt_disable();
 			spin_unlock(&dev->queue_lock);
 			spin_lock(&dev->xmit_lock);
 			dev->xmit_lock_owner = cpu;
+			preempt_enable();
 
 			if (!netif_queue_stopped(dev)) {
 				if (netdev_nit)

diff -urN linux-2.4.18-O1-affinity/net/core/skbuff.c linux/net/core/skbuff.c
@@ -111,33 +111,37 @@
 
 static __inline__ struct sk_buff *skb_head_from_pool(void)
 {
-	struct sk_buff_head *list = &skb_head_pool[smp_processor_id()].list;
+	struct sk_buff_head *list;
+	struct sk_buff *skb = NULL;
+	unsigned long flags;
 
-	if (skb_queue_len(list)) {
-		struct sk_buff *skb;
-		unsigned long flags;
+	local_irq_save(flags);
 
-		local_irq_save(flags);
+	list = &skb_head_pool[smp_processor_id()].list;
+
+	if (skb_queue_len(list))
 		skb = __skb_dequeue(list);
-		local_irq_restore(flags);
-		return skb;
-	}
-	return NULL;
+
+	local_irq_restore(flags);
+	return skb;
 }
 
 static __inline__ void skb_head_to_pool(struct sk_buff *skb)
 {
-	struct sk_buff_head *list = &skb_head_pool[smp_processor_id()].list;
+	struct sk_buff_head *list;
+	unsigned long flags;
 
-	if (skb_queue_len(list) < sysctl_hot_list_len) {
-		unsigned long flags;
+	local_irq_save(flags);
+
+	list = &skb_head_pool[smp_processor_id()].list;
 
-		local_irq_save(flags);
+	if (skb_queue_len(list) < sysctl_hot_list_len) {
 		__skb_queue_head(list, skb);
 		local_irq_restore(flags);
 
 		return;
 	}
+	local_irq_restore(flags);
 	kmem_cache_free(skbuff_head_cache, skb);
 }
 

diff -urN linux-2.4.18-O1-affinity/net/socket.c linux/net/socket.c
@@ -133,7 +133,7 @@
 
 static struct net_proto_family *net_families[NPROTO];
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
 static atomic_t net_family_lockct = ATOMIC_INIT(0);
 static spinlock_t net_family_lock = SPIN_LOCK_UNLOCKED;
 

diff -urN linux-2.4.18-O1-affinity/net/sunrpc/pmap_clnt.c linux/net/sunrpc/pmap_clnt.c
@@ -12,6 +12,7 @@
 #include <linux/config.h>
 #include <linux/types.h>
 #include <linux/socket.h>
+#include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/uio.h>