#include <asm/idle.h>
/*
- * Smarter SMP flushing macros.
+ * Smarter SMP flushing macros.
* c/o Linus Torvalds.
*
* These mean you can really definitely utterly forget about
*
* Optimizations Manfred Spraul <manfred@colorfullife.com>
*
- * More scalable flush, from Andi Kleen
+ * More scalable flush, from Andi Kleen
*
- * To avoid global state use 8 different call vectors.
- * Each CPU uses a specific vector to trigger flushes on other
- * CPUs. Depending on the received vector the target CPUs look into
+ * To avoid global state use 8 different call vectors.
+ * Each CPU uses a specific vector to trigger flushes on other
+ * CPUs. Depending on the received vector the target CPUs look into
* the right per cpu variable for the flush data.
*
- * With more than 8 CPUs they are hashed to the 8 available
- * vectors. The limited global vector space forces us to this right now.
+ * With more than 8 CPUs they are hashed to the 8 available
+ * vectors. The limited global vector space forces us to this right now.
* In future when interrupts are split into per CPU domains this could be
* fixed, at the cost of triggering multiple IPIs in some cases.
*/
cpumask_t flush_cpumask;
struct mm_struct *flush_mm;
unsigned long flush_va;
-#define FLUSH_ALL -1ULL
spinlock_t tlbstate_lock;
};
char pad[SMP_CACHE_BYTES];
static DEFINE_PER_CPU(union smp_flush_state, flush_state);
/*
- * We cannot call mmdrop() because we are in interrupt context,
+ * We cannot call mmdrop() because we are in interrupt context,
* instead update mm->cpu_vm_mask.
*/
-static inline void leave_mm(int cpu)
+void leave_mm(int cpu)
{
if (read_pda(mmu_state) == TLBSTATE_OK)
BUG();
cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask);
load_cr3(swapper_pg_dir);
}
+EXPORT_SYMBOL_GPL(leave_mm);
/*
*
* 1) switch_mm() either 1a) or 1b)
* 1a) thread switch to a different mm
* 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
- * Stop ipi delivery for the old mm. This is not synchronized with
- * the other cpus, but smp_invalidate_interrupt ignore flush ipis
- * for the wrong mm, and in the worst case we perform a superfluous
- * tlb flush.
+ * Stop ipi delivery for the old mm. This is not synchronized with
+ * the other cpus, but smp_invalidate_interrupt ignore flush ipis
+ * for the wrong mm, and in the worst case we perform a superfluous
+ * tlb flush.
* 1a2) set cpu mmu_state to TLBSTATE_OK
- * Now the smp_invalidate_interrupt won't call leave_mm if cpu0
+ * Now the smp_invalidate_interrupt won't call leave_mm if cpu0
* was in lazy tlb mode.
* 1a3) update cpu active_mm
- * Now cpu0 accepts tlb flushes for the new mm.
+ * Now cpu0 accepts tlb flushes for the new mm.
* 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
- * Now the other cpus will send tlb flush ipis.
+ * Now the other cpus will send tlb flush ipis.
* 1a4) change cr3.
* 1b) thread switch without mm change
* cpu active_mm is correct, cpu0 already handles
* flush ipis.
* 1b1) set cpu mmu_state to TLBSTATE_OK
* 1b2) test_and_set the cpu bit in cpu_vm_mask.
- * Atomically set the bit [other cpus will start sending flush ipis],
- * and test the bit.
+ * Atomically set the bit [other cpus will start sending flush ipis],
+ * and test the bit.
* 1b3) if the bit was 0: leave_mm was called, flush the tlb.
* 2) switch %%esp, ie current
*
* orig_rax contains the negated interrupt vector.
* Use that to determine where the sender put the data.
*/
- sender = ~regs->orig_rax - INVALIDATE_TLB_VECTOR_START;
+ sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START;
f = &per_cpu(flush_state, sender);
if (!cpu_isset(cpu, f->flush_cpumask))
goto out;
- /*
+ /*
* This was a BUG() but until someone can quote me the
* line from the intel manual that guarantees an IPI to
* multiple CPUs is retried _only_ on the erroring CPUs
*
* BUG();
*/
-
+
if (f->flush_mm == read_pda(active_mm)) {
if (read_pda(mmu_state) == TLBSTATE_OK) {
- if (f->flush_va == FLUSH_ALL)
+ if (f->flush_va == TLB_FLUSH_ALL)
local_flush_tlb();
else
__flush_tlb_one(f->flush_va);
out:
ack_APIC_irq();
cpu_clear(cpu, f->flush_cpumask);
+ add_pda(irq_tlb_count, 1);
}
-static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
- unsigned long va)
+void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
+ unsigned long va)
{
int sender;
union smp_flush_state *f;
+ cpumask_t cpumask = *cpumaskp;
/* Caller has disabled preemption */
sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
f = &per_cpu(flush_state, sender);
- /* Could avoid this lock when
- num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
- probably not worth checking this for a cache-hot lock. */
+ /*
+ * Could avoid this lock when
+ * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
+ * probably not worth checking this for a cache-hot lock.
+ */
spin_lock(&f->tlbstate_lock);
f->flush_mm = mm;
int __cpuinit init_smp_flush(void)
{
int i;
+
for_each_cpu_mask(i, cpu_possible_map) {
spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock);
}
return 0;
}
-
core_initcall(init_smp_flush);
-
+
void flush_tlb_current_task(void)
{
struct mm_struct *mm = current->mm;
local_flush_tlb();
if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+ flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
preempt_enable();
}
-EXPORT_SYMBOL(flush_tlb_current_task);
void flush_tlb_mm (struct mm_struct * mm)
{
leave_mm(smp_processor_id());
}
if (!cpus_empty(cpu_mask))
- flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
+ flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
preempt_enable();
}
-EXPORT_SYMBOL(flush_tlb_mm);
void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
{
if (current->active_mm == mm) {
if(current->mm)
__flush_tlb_one(va);
- else
- leave_mm(smp_processor_id());
+ else
+ leave_mm(smp_processor_id());
}
if (!cpus_empty(cpu_mask))
preempt_enable();
}
-EXPORT_SYMBOL(flush_tlb_page);
static void do_flush_tlb_all(void* info)
{
* anything. Worst case is that we lose a reschedule ...
*/
-void smp_send_reschedule(int cpu)
+static void native_smp_send_reschedule(int cpu)
{
+ WARN_ON(cpu_is_offline(cpu));
send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
}
spin_unlock_irq(&call_lock);
}
-/*
- * this function sends a 'generic call function' IPI to one other CPU
- * in the system.
- *
- * cpu is a standard Linux logical CPU number.
- */
-static void
-__smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+static void __smp_call_function(void (*func) (void *info), void *info,
int nonatomic, int wait)
{
struct call_data_struct data;
- int cpus = 1;
+ int cpus = num_online_cpus() - 1;
+
+ if (!cpus)
+ return;
data.func = func;
data.info = info;
atomic_set(&data.finished, 0);
call_data = &data;
- wmb();
+ mb();
+
/* Send a message to all other CPUs and wait for them to respond */
- send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_VECTOR);
+ send_IPI_allbutself(CALL_FUNCTION_VECTOR);
/* Wait for response */
while (atomic_read(&data.started) != cpus)
cpu_relax();
- if (!wait)
- return;
-
- while (atomic_read(&data.finished) != cpus)
- cpu_relax();
+ if (wait)
+ while (atomic_read(&data.finished) != cpus)
+ cpu_relax();
}
-/*
- * smp_call_function_single - Run a function on a specific CPU
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @nonatomic: Currently unused.
- * @wait: If true, wait until function has completed on other CPUs.
- *
- * Retrurns 0 on success, else a negative status code.
- *
- * Does not return until the remote CPU is nearly ready to execute <func>
- * or is or has executed.
- */
-
-int smp_call_function_single (int cpu, void (*func) (void *info), void *info,
- int nonatomic, int wait)
-{
- /* prevent preemption and reschedule on another processor */
- int me = get_cpu();
-
- /* Can deadlock when called with interrupts disabled */
- WARN_ON(irqs_disabled());
-
- if (cpu == me) {
- local_irq_disable();
- func(info);
- local_irq_enable();
- put_cpu();
- return 0;
- }
-
- spin_lock(&call_lock);
- __smp_call_function_single(cpu, func, info, nonatomic, wait);
- spin_unlock(&call_lock);
- put_cpu();
- return 0;
-}
-EXPORT_SYMBOL(smp_call_function_single);
/*
- * this function sends a 'generic call function' IPI to all other CPUs
- * in the system.
+ * this function sends a 'generic call function' IPI to all other CPU
+ * of the system defined in the mask.
*/
-static void __smp_call_function (void (*func) (void *info), void *info,
- int nonatomic, int wait)
+static int __smp_call_function_mask(cpumask_t mask,
+ void (*func)(void *), void *info,
+ int wait)
{
struct call_data_struct data;
- int cpus = num_online_cpus()-1;
+ cpumask_t allbutself;
+ int cpus;
+
+ allbutself = cpu_online_map;
+ cpu_clear(smp_processor_id(), allbutself);
+
+ cpus_and(mask, mask, allbutself);
+ cpus = cpus_weight(mask);
if (!cpus)
- return;
+ return 0;
data.func = func;
data.info = info;
call_data = &data;
wmb();
- /* Send a message to all other CPUs and wait for them to respond */
- send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+
+ /* Send a message to other CPUs */
+ if (cpus_equal(mask, allbutself))
+ send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+ else
+ send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
/* Wait for response */
while (atomic_read(&data.started) != cpus)
cpu_relax();
if (!wait)
- return;
+ return 0;
while (atomic_read(&data.finished) != cpus)
cpu_relax();
-}
-/*
- * smp_call_function - run a function on all other CPUs.
+ return 0;
+}
+/**
+ * smp_call_function_mask(): Run a function on a set of other CPUs.
+ * @mask: The set of cpus to run on. Must not include the current cpu.
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
- * @nonatomic: currently unused.
- * @wait: If true, wait (atomically) until function has completed on other
- * CPUs.
+ * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ *
+ * Returns 0 on success, else a negative status code.
*
- * Returns 0 on success, else a negative status code. Does not return until
- * remote CPUs are nearly ready to execute func or are or have executed.
+ * If @wait is true, then returns once @func has returned; otherwise
+ * it returns just before the target cpu calls @func.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
- * Actually there are a few legal cases, like panic.
*/
-int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
- int wait)
+int native_smp_call_function_mask(cpumask_t mask,
+ void (*func)(void *), void *info,
+ int wait)
{
+ int ret;
+
+ /* Can deadlock when called with interrupts disabled */
+ WARN_ON(irqs_disabled());
+
spin_lock(&call_lock);
- __smp_call_function(func,info,nonatomic,wait);
+ ret = __smp_call_function_mask(mask, func, info, wait);
spin_unlock(&call_lock);
- return 0;
+ return ret;
}
-EXPORT_SYMBOL(smp_call_function);
static void stop_this_cpu(void *dummy)
{
*/
cpu_clear(smp_processor_id(), cpu_online_map);
disable_local_APIC();
- for (;;)
+ for (;;)
halt();
-}
+}
void smp_send_stop(void)
{
asmlinkage void smp_reschedule_interrupt(void)
{
ack_APIC_irq();
+ add_pda(irq_resched_count, 1);
}
asmlinkage void smp_call_function_interrupt(void)
exit_idle();
irq_enter();
(*func)(info);
+ add_pda(irq_call_count, 1);
irq_exit();
if (wait) {
mb();
}
}
+struct smp_ops smp_ops = {
+ .smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
+ .smp_prepare_cpus = native_smp_prepare_cpus,
+ .smp_cpus_done = native_smp_cpus_done,
+
+ .smp_send_reschedule = native_smp_send_reschedule,
+ .smp_call_function_mask = native_smp_call_function_mask,
+ .cpu_up = native_cpu_up,
+};
+EXPORT_SYMBOL_GPL(smp_ops);