{ 0x4b, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */
{ 0x4c, LVL_3, 12288 }, /* 12-way set assoc, 64 byte line size */
{ 0x4d, LVL_3, 16384 }, /* 16-way set assoc, 64 byte line size */
+ { 0x4e, LVL_2, 6144 }, /* 24-way set assoc, 64 byte line size */
{ 0x60, LVL_1_DATA, 16 }, /* 8-way set assoc, sectored cache, 64 byte line size */
{ 0x66, LVL_1_DATA, 8 }, /* 4-way set assoc, sectored cache, 64 byte line size */
{ 0x67, LVL_1_DATA, 16 }, /* 4-way set assoc, sectored cache, 64 byte line size */
int sibling;
this_leaf = CPUID4_INFO_IDX(cpu, index);
- for_each_cpu_mask(sibling, this_leaf->shared_cpu_map) {
+ for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) {
sibling_leaf = CPUID4_INFO_IDX(sibling, index);
cpu_clear(cpu, sibling_leaf->shared_cpu_map);
}
};
/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
- struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+ static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
[0] = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, },
[1] = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, },
[2] = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, },
static int assign_irq_vector(int irq, cpumask_t mask);
+ int first_system_vector = 0xfe;
+
+ char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+
#define __apicdebuginit __init
int sis_apic_bug; /* not actually supported, dummy for compile */
static int disable_timer_pin_1 __initdata;
- int timer_over_8254 __initdata = 1;
+ int timer_through_8259 __initdata;
/* Where if anywhere is the i8259 connect in external int mode */
static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
int nr_ioapic_registers[MAX_IO_APICS];
/* I/O APIC entries */
- struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+ struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
int nr_ioapics;
/* MP IRQ source entries */
- struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+ struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
/* # of MP IRQ source entries */
int mp_irq_entries;
+ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+
/*
* Rough estimation of how many shared IRQs there are, can
* be changed anytime.
static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
{
return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
- + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK);
+ + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
}
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
break;
reg = io_apic_read(entry->apic, 0x10 + pin*2);
/* Is the remote IRR bit set? */
- if ((reg >> 14) & 1) {
+ if (reg & IO_APIC_REDIR_REMOTE_IRR) {
spin_unlock_irqrestore(&ioapic_lock, flags);
return true;
}
break;
io_apic_write(apic, 0x11 + pin*2, dest);
reg = io_apic_read(apic, 0x10 + pin*2);
- reg &= ~0x000000ff;
+ reg &= ~IO_APIC_REDIR_VECTOR_MASK;
reg |= vector;
io_apic_modify(apic, reg);
if (!entry->next)
entry->pin = pin;
}
+ /*
+ * Reroute an IRQ to a different pin.
+ */
+ static void __init replace_pin_at_irq(unsigned int irq,
+ int oldapic, int oldpin,
+ int newapic, int newpin)
+ {
+ struct irq_pin_list *entry = irq_2_pin + irq;
+
+ while (1) {
+ if (entry->apic == oldapic && entry->pin == oldpin) {
+ entry->apic = newapic;
+ entry->pin = newpin;
+ }
+ if (!entry->next)
+ break;
+ entry = irq_2_pin + entry->next;
+ }
+ }
+
#define DO_ACTION(name,R,ACTION, FINAL) \
\
static void name##_IO_APIC_irq (unsigned int irq) \
__DO_ACTION(R, ACTION, FINAL)
- DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) )
- /* mask = 1 */
- DO_ACTION( __unmask, 0, &= 0xfffeffff, )
- /* mask = 0 */
+ /* mask = 1 */
+ DO_ACTION(__mask, 0, |= IO_APIC_REDIR_MASKED, io_apic_sync(entry->apic))
+
+ /* mask = 0 */
+ DO_ACTION(__unmask, 0, &= ~IO_APIC_REDIR_MASKED, )
static void mask_IO_APIC_irq (unsigned int irq)
{
}
__setup("disable_timer_pin_1", disable_timer_pin_setup);
- static int __init setup_disable_8254_timer(char *s)
- {
- timer_over_8254 = -1;
- return 1;
- }
- static int __init setup_enable_8254_timer(char *s)
- {
- timer_over_8254 = 2;
- return 1;
- }
-
- __setup("disable_8254_timer", setup_disable_8254_timer);
- __setup("enable_8254_timer", setup_enable_8254_timer);
-
/*
* Find the IRQ entry number of a certain pin.
int i;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_irqtype == type &&
- (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid ||
- mp_irqs[i].mpc_dstapic == MP_APIC_ALL) &&
- mp_irqs[i].mpc_dstirq == pin)
+ if (mp_irqs[i].mp_irqtype == type &&
+ (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
+ mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].mp_dstirq == pin)
return i;
return -1;
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mpc_irqtype == type) &&
- (mp_irqs[i].mpc_srcbusirq == irq))
+ (mp_irqs[i].mp_irqtype == type) &&
+ (mp_irqs[i].mp_srcbusirq == irq))
- return mp_irqs[i].mpc_dstirq;
+ return mp_irqs[i].mp_dstirq;
}
return -1;
}
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mpc_irqtype == type) &&
- (mp_irqs[i].mpc_srcbusirq == irq))
+ (mp_irqs[i].mp_irqtype == type) &&
+ (mp_irqs[i].mp_srcbusirq == irq))
break;
}
if (i < mp_irq_entries) {
int apic;
for(apic = 0; apic < nr_ioapics; apic++) {
- if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
+ if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
return apic;
}
}
apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
bus, slot, pin);
- if (mp_bus_id_to_pci_bus[bus] == -1) {
+ if (test_bit(bus, mp_bus_not_pci)) {
apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
return -1;
}
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic ||
- mp_irqs[i].mpc_dstapic == MP_APIC_ALL)
+ if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
+ mp_irqs[i].mp_dstapic == MP_APIC_ALL)
break;
if (!test_bit(lbus, mp_bus_not_pci) &&
- !mp_irqs[i].mpc_irqtype &&
+ !mp_irqs[i].mp_irqtype &&
(bus == lbus) &&
- (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+ (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
if (!(apic || IO_APIC_IRQ(irq)))
continue;
- if (pin == (mp_irqs[i].mpc_srcbusirq & 3))
+ if (pin == (mp_irqs[i].mp_srcbusirq & 3))
return irq;
/*
* Use the first all-but-pin matching entry as a
static int MPBIOS_polarity(int idx)
{
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mpc_irqflag & 3)
+ switch (mp_irqs[idx].mp_irqflag & 3)
{
case 0: /* conforms, ie. bus-type dependent polarity */
if (test_bit(bus, mp_bus_not_pci))
static int MPBIOS_trigger(int idx)
{
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
int trigger;
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
{
case 0: /* conforms, ie. bus-type dependent */
if (test_bit(bus, mp_bus_not_pci))
static int pin_2_irq(int idx, int apic, int pin)
{
int irq, i;
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
/*
* Debugging check, we are in big trouble if this message pops up!
*/
- if (mp_irqs[idx].mpc_dstirq != pin)
+ if (mp_irqs[idx].mp_dstirq != pin)
printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
if (test_bit(bus, mp_bus_not_pci)) {
- irq = mp_irqs[idx].mpc_srcbusirq;
+ irq = mp_irqs[idx].mp_srcbusirq;
} else {
/*
* PCI IRQs are mapped in order
return 0;
}
- for_each_cpu_mask(cpu, mask) {
+ for_each_cpu_mask_nr(cpu, mask) {
cpumask_t domain, new_mask;
int new_cpu;
int vector, offset;
offset = current_offset;
next:
vector += 8;
- if (vector >= FIRST_SYSTEM_VECTOR) {
+ if (vector >= first_system_vector) {
/* If we run out of vectors on large boxen, must share them. */
offset = (offset + 1) % 8;
vector = FIRST_DEVICE_VECTOR + offset;
continue;
if (vector == IA32_SYSCALL_VECTOR)
goto next;
- for_each_cpu_mask(new_cpu, new_mask)
+ for_each_cpu_mask_nr(new_cpu, new_mask)
if (per_cpu(vector_irq, new_cpu)[vector] != -1)
goto next;
/* Found one! */
cfg->move_in_progress = 1;
cfg->old_domain = cfg->domain;
}
- for_each_cpu_mask(new_cpu, new_mask)
+ for_each_cpu_mask_nr(new_cpu, new_mask)
per_cpu(vector_irq, new_cpu)[vector] = irq;
cfg->vector = vector;
cfg->domain = domain;
vector = cfg->vector;
cpus_and(mask, cfg->domain, cpu_online_map);
- for_each_cpu_mask(cpu, mask)
+ for_each_cpu_mask_nr(cpu, mask)
per_cpu(vector_irq, cpu)[vector] = -1;
cfg->vector = 0;
cpus_clear(cfg->domain);
}
- void __setup_vector_irq(int cpu)
+ static void __setup_vector_irq(int cpu)
{
/* Initialize vector_irq on a new cpu */
/* This function must be called with vector_lock held */
}
}
+ void setup_vector_irq(int cpu)
+ {
+ spin_lock(&vector_lock);
+ __setup_vector_irq(smp_processor_id());
+ spin_unlock(&vector_lock);
+ }
+
static struct irq_chip ioapic_chip;
apic_printk(APIC_VERBOSE,KERN_DEBUG
"IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
"IRQ %d Mode:%i Active:%i)\n",
- apic, mp_ioapics[apic].mpc_apicid, pin, cfg->vector,
+ apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
irq, trigger, polarity);
/*
idx = find_irq_entry(apic,pin,mp_INT);
if (idx == -1) {
if (first_notcon) {
- apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mpc_apicid, pin);
+ apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mp_apicid, pin);
first_notcon = 0;
} else
- apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin);
+ apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mp_apicid, pin);
continue;
}
if (!first_notcon) {
}
/*
- * Set up the 8259A-master output pin as broadcast to all
- * CPUs.
+ * Set up the timer pin, possibly with the 8259A-master behind.
*/
- static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+ int vector)
{
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
- disable_8259A_irq(0);
-
- /* mask LVT0 */
- apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-
/*
* We use logical delivery to get the timer IRQ
* to the first CPU.
*/
entry.dest_mode = INT_DEST_MODE;
- entry.mask = 0; /* unmask IRQ now */
+ entry.mask = 1; /* mask IRQ now */
entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
entry.delivery_mode = INT_DELIVERY_MODE;
entry.polarity = 0;
/*
* The timer IRQ doesn't have to know that behind the
- * scene we have a 8259A-master in AEOI mode ...
+ * scene we may have a 8259A-master in AEOI mode ...
*/
set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
* Add it to the IO-APIC irq-routing table:
*/
ioapic_write_entry(apic, pin, entry);
-
- enable_8259A_irq(0);
}
void __apicdebuginit print_IO_APIC(void)
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (i = 0; i < nr_ioapics; i++)
printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
- mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
+ mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
/*
* We are a bit conservative about what we expect. We have to
spin_unlock_irqrestore(&ioapic_lock, flags);
printk("\n");
- printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
v = apic_read(APIC_LVR);
printk(KERN_INFO "... APIC VERSION: %08x\n", v);
void print_all_local_APICs (void)
{
- on_each_cpu(print_local_APIC, NULL, 1, 1);
+ on_each_cpu(print_local_APIC, NULL, 1);
}
void __apicdebuginit print_PIC(void)
}
}
- static void enable_lapic_irq (unsigned int irq)
+ static void unmask_lapic_irq(unsigned int irq)
{
unsigned long v;
apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
}
- static void disable_lapic_irq (unsigned int irq)
+ static void mask_lapic_irq(unsigned int irq)
{
unsigned long v;
ack_APIC_irq();
}
- static void end_lapic_irq (unsigned int i) { /* nothing */ }
-
- static struct hw_interrupt_type lapic_irq_type __read_mostly = {
- .name = "local-APIC",
- .typename = "local-APIC-edge",
- .startup = NULL, /* startup_irq() not used for IRQ0 */
- .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */
- .enable = enable_lapic_irq,
- .disable = disable_lapic_irq,
- .ack = ack_lapic_irq,
- .end = end_lapic_irq,
+ static struct irq_chip lapic_chip __read_mostly = {
+ .name = "local-APIC",
+ .mask = mask_lapic_irq,
+ .unmask = unmask_lapic_irq,
+ .ack = ack_lapic_irq,
};
+ static void lapic_register_intr(int irq)
+ {
+ irq_desc[irq].status &= ~IRQ_LEVEL;
+ set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+ "edge");
+ }
+
static void __init setup_nmi(void)
{
/*
struct irq_cfg *cfg = irq_cfg + 0;
int apic1, pin1, apic2, pin2;
unsigned long flags;
+ int no_pin1 = 0;
local_irq_save(flags);
assign_irq_vector(0, TARGET_CPUS);
/*
- * Subtle, code in do_timer_interrupt() expects an AEOI
- * mode for the 8259A whenever interrupts are routed
- * through I/O APICs. Also IRQ0 has to be enabled in
- * the 8259A which implies the virtual wire has to be
- * disabled in the local APIC.
+ * As IRQ0 is to be enabled in the 8259A, the virtual
+ * wire has to be disabled in the local APIC.
*/
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
- if (timer_over_8254 > 0)
- enable_8259A_irq(0);
pin1 = find_isa_irq_pin(0, mp_INT);
apic1 = find_isa_irq_apic(0, mp_INT);
apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
cfg->vector, apic1, pin1, apic2, pin2);
+ /*
+ * Some BIOS writers are clueless and report the ExtINTA
+ * I/O APIC input from the cascaded 8259A as the timer
+ * interrupt input. So just in case, if only one pin
+ * was found above, try it both directly and through the
+ * 8259A.
+ */
+ if (pin1 == -1) {
+ pin1 = pin2;
+ apic1 = apic2;
+ no_pin1 = 1;
+ } else if (pin2 == -1) {
+ pin2 = pin1;
+ apic2 = apic1;
+ }
+
if (pin1 != -1) {
/*
* Ok, does IRQ0 through the IOAPIC work?
*/
+ if (no_pin1) {
+ add_pin_to_irq(0, apic1, pin1);
+ setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+ }
unmask_IO_APIC_irq(0);
if (!no_timer_check && timer_irq_works()) {
- nmi_watchdog_default();
if (nmi_watchdog == NMI_IO_APIC) {
- disable_8259A_irq(0);
setup_nmi();
enable_8259A_irq(0);
}
goto out;
}
clear_IO_APIC_pin(apic1, pin1);
- apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not "
- "connected to IO-APIC\n");
- }
+ if (!no_pin1)
+ apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: "
+ "8254 timer not connected to IO-APIC\n");
- apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) "
- "through the 8259A ... ");
- if (pin2 != -1) {
+ apic_printk(APIC_VERBOSE,KERN_INFO
+ "...trying to set up timer (IRQ0) "
+ "through the 8259A ... ");
apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...",
apic2, pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
- setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector);
+ replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+ setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+ unmask_IO_APIC_irq(0);
+ enable_8259A_irq(0);
if (timer_irq_works()) {
apic_printk(APIC_VERBOSE," works.\n");
- nmi_watchdog_default();
+ timer_through_8259 = 1;
if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
setup_nmi();
+ enable_8259A_irq(0);
}
goto out;
}
/*
* Cleanup, just in case ...
*/
+ disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
+ apic_printk(APIC_VERBOSE," failed.\n");
}
- apic_printk(APIC_VERBOSE," failed.\n");
if (nmi_watchdog == NMI_IO_APIC) {
printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
- nmi_watchdog = 0;
+ nmi_watchdog = NMI_NONE;
}
apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
- disable_8259A_irq(0);
- irq_desc[0].chip = &lapic_irq_type;
+ lapic_register_intr(0);
apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */
enable_8259A_irq(0);
apic_printk(APIC_VERBOSE," works.\n");
goto out;
}
+ disable_8259A_irq(0);
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
apic_printk(APIC_VERBOSE," failed.\n");
__setup("no_timer_check", notimercheck);
/*
- *
- * IRQs that are handled by the PIC in the MPS IOAPIC case.
- * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
- * Linux doesn't really care, as it's not actually used
- * for any interrupt handling anyway.
+ * Traditionally ISA IRQ2 is the cascade IRQ, and is not available
+ * to devices. However there may be an I/O APIC pin available for
+ * this interrupt regardless. The pin may be left unconnected, but
+ * typically it will be reused as an ExtINT cascade interrupt for
+ * the master 8259A. In the MPS case such a pin will normally be
+ * reported as an ExtINT interrupt in the MP table. With ACPI
+ * there is no provision for ExtINT interrupts, and in the absence
+ * of an override it would be treated as an ordinary ISA I/O APIC
+ * interrupt, that is edge-triggered and unmasked by default. We
+ * used to do this, but it caused problems on some systems because
+ * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using
+ * the same ExtINT cascade interrupt to drive the local APIC of the
+ * bootstrap processor. Therefore we refrain from routing IRQ2 to
+ * the I/O APIC in all cases now. No actual device should request
+ * it anyway. --macro
*/
#define PIC_IRQS (1<<2)
* calling enable_IO_APIC() is moved to setup_local_APIC for BP
*/
- if (acpi_ioapic)
- io_apic_irqs = ~0; /* all IRQs go through IOAPIC */
- else
- io_apic_irqs = ~PIC_IRQS;
+ io_apic_irqs = ~PIC_IRQS;
apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid;
+ if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
return -1;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_irqtype == mp_INT &&
- mp_irqs[i].mpc_srcbusirq == bus_irq)
+ if (mp_irqs[i].mp_irqtype == mp_INT &&
+ mp_irqs[i].mp_srcbusirq == bus_irq)
break;
if (i >= mp_irq_entries)
return -1;
ioapic_res = ioapic_setup_resources();
for (i = 0; i < nr_ioapics; i++) {
if (smp_found_config) {
- ioapic_phys = mp_ioapics[i].mpc_apicaddr;
+ ioapic_phys = mp_ioapics[i].mp_apicaddr;
} else {
ioapic_phys = (unsigned long)
alloc_bootmem_pages(PAGE_SIZE);
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mtrr.h>
- #include <asm/nmi.h>
#include <asm/vmi.h>
#include <asm/genapic.h>
#include <linux/mc146818rtc.h>
#include <mach_wakecpu.h>
#include <smpboot_hooks.h>
- /*
- * FIXME: For x86_64, those are defined in other files. But moving them here,
- * would make the setup areas dependent on smp, which is a loss. When we
- * integrate apic between arches, we can probably do a better job, but
- * right now, they'll stay here -- glommer
- */
-
- /* which logical CPU number maps to which CPU (physical APIC ID) */
- u16 x86_cpu_to_apicid_init[NR_CPUS] __initdata =
- { [0 ... NR_CPUS-1] = BAD_APICID };
- void *x86_cpu_to_apicid_early_ptr;
-
- u16 x86_bios_cpu_apicid_init[NR_CPUS] __initdata
- = { [0 ... NR_CPUS-1] = BAD_APICID };
- void *x86_bios_cpu_apicid_early_ptr;
-
#ifdef CONFIG_X86_32
u8 apicid_2_node[MAX_APICID];
static int low_mappings;
map_cpu_to_node(cpu, node);
}
- static void unmap_cpu_to_logical_apicid(int cpu)
+ void numa_remove_cpu(int cpu)
{
cpu_2_logical_apicid[cpu] = BAD_APICID;
unmap_cpu_to_node(cpu);
}
#else
- #define unmap_cpu_to_logical_apicid(cpu) do {} while (0)
#define map_cpu_to_logical_apicid() do {} while (0)
#endif
* lock helps us to not include this cpu in a currently in progress
* smp_call_function().
*/
- lock_ipi_call_lock();
- #ifdef CONFIG_X86_64
- spin_lock(&vector_lock);
-
- /* Setup the per cpu irq handling data structures */
- __setup_vector_irq(smp_processor_id());
- /*
- * Allow the master to continue.
- */
- spin_unlock(&vector_lock);
+ ipi_call_lock_irq();
+ #ifdef CONFIG_X86_IO_APIC
+ setup_vector_irq(smp_processor_id());
#endif
cpu_set(smp_processor_id(), cpu_online_map);
- unlock_ipi_call_lock();
+ ipi_call_unlock_irq();
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
setup_secondary_clock();
cpu_idle();
}
- #ifdef CONFIG_X86_32
- /*
- * Everything has been set up for the secondary
- * CPUs - they just need to reload everything
- * from the task structure
- * This function must not return.
- */
- void __devinit initialize_secondary(void)
- {
- /*
- * We don't actually need to load the full TSS,
- * basically just the stack pointer and the ip.
- */
-
- asm volatile(
- "movl %0,%%esp\n\t"
- "jmp *%1"
- :
- :"m" (current->thread.sp), "m" (current->thread.ip));
- }
- #endif
-
static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c)
{
- #ifdef CONFIG_X86_32
/*
* Mask B, Pentium, but not Pentium MMX
*/
valid_k7:
;
- #endif
}
static void __cpuinit smp_checks(void)
cpu_set(cpu, cpu_sibling_setup_map);
if (smp_num_siblings > 1) {
- for_each_cpu_mask(i, cpu_sibling_setup_map) {
+ for_each_cpu_mask_nr(i, cpu_sibling_setup_map) {
if (c->phys_proc_id == cpu_data(i).phys_proc_id &&
c->cpu_core_id == cpu_data(i).cpu_core_id) {
cpu_set(i, per_cpu(cpu_sibling_map, cpu));
return;
}
- for_each_cpu_mask(i, cpu_sibling_setup_map) {
+ for_each_cpu_mask_nr(i, cpu_sibling_setup_map) {
if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
cpu_set(i, c->llc_shared_map);
return c->llc_shared_map;
}
- #ifdef CONFIG_X86_32
- /*
- * We are called very early to get the low memory for the
- * SMP bootup trampoline page.
- */
- void __init smp_alloc_memory(void)
- {
- trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE);
- /*
- * Has to be in very low memory so we can execute
- * real-mode AP code.
- */
- if (__pa(trampoline_base) >= 0x9F000)
- BUG();
- }
- #endif
-
static void impress_friends(void)
{
int cpu;
* target processor state.
*/
startup_ipi_hook(phys_apicid, (unsigned long) start_secondary,
- #ifdef CONFIG_X86_64
- (unsigned long)init_rsp);
- #else
(unsigned long)stack_start.sp);
- #endif
/*
* Run STARTUP IPI loop.
complete(&c_idle->done);
}
+ #ifdef CONFIG_X86_64
+ /*
+ * Allocate node local memory for the AP pda.
+ *
+ * Must be called after the _cpu_pda pointer table is initialized.
+ */
+ static int __cpuinit get_local_pda(int cpu)
+ {
+ struct x8664_pda *oldpda, *newpda;
+ unsigned long size = sizeof(struct x8664_pda);
+ int node = cpu_to_node(cpu);
+
+ if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem)
+ return 0;
+
+ oldpda = cpu_pda(cpu);
+ newpda = kmalloc_node(size, GFP_ATOMIC, node);
+ if (!newpda) {
+ printk(KERN_ERR "Could not allocate node local PDA "
+ "for CPU %d on node %d\n", cpu, node);
+
+ if (oldpda)
+ return 0; /* have a usable pda */
+ else
+ return -1;
+ }
+
+ if (oldpda) {
+ memcpy(newpda, oldpda, size);
+ if (!after_bootmem)
+ free_bootmem((unsigned long)oldpda, size);
+ }
+
+ newpda->in_bootmem = 0;
+ cpu_pda(cpu) = newpda;
+ return 0;
+ }
+ #endif /* CONFIG_X86_64 */
+
static int __cpuinit do_boot_cpu(int apicid, int cpu)
/*
* NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
};
INIT_WORK(&c_idle.work, do_fork_idle);
- #ifdef CONFIG_X86_64
- /* allocate memory for gdts of secondary cpus. Hotplug is considered */
- if (!cpu_gdt_descr[cpu].address &&
- !(cpu_gdt_descr[cpu].address = get_zeroed_page(GFP_KERNEL))) {
- printk(KERN_ERR "Failed to allocate GDT for CPU %d\n", cpu);
- return -1;
- }
+ #ifdef CONFIG_X86_64
/* Allocate node local memory for AP pdas */
- if (cpu_pda(cpu) == &boot_cpu_pda[cpu]) {
- struct x8664_pda *newpda, *pda;
- int node = cpu_to_node(cpu);
- pda = cpu_pda(cpu);
- newpda = kmalloc_node(sizeof(struct x8664_pda), GFP_ATOMIC,
- node);
- if (newpda) {
- memcpy(newpda, pda, sizeof(struct x8664_pda));
- cpu_pda(cpu) = newpda;
- } else
- printk(KERN_ERR
- "Could not allocate node local PDA for CPU %d on node %d\n",
- cpu, node);
+ if (cpu > 0) {
+ boot_error = get_local_pda(cpu);
+ if (boot_error)
+ goto restore_state;
+ /* if can't get pda memory, can't start cpu */
}
#endif
#ifdef CONFIG_X86_32
per_cpu(current_task, cpu) = c_idle.idle;
init_gdt(cpu);
- early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
- c_idle.idle->thread.ip = (unsigned long) start_secondary;
/* Stack for startup_32 can be just as for start_secondary onwards */
- stack_start.sp = (void *) c_idle.idle->thread.sp;
irq_ctx_init(cpu);
#else
cpu_pda(cpu)->pcurrent = c_idle.idle;
- init_rsp = c_idle.idle->thread.sp;
- load_sp0(&per_cpu(init_tss, cpu), &c_idle.idle->thread);
- initial_code = (unsigned long)start_secondary;
clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
#endif
+ early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
+ initial_code = (unsigned long)start_secondary;
+ stack_start.sp = (void *) c_idle.idle->thread.sp;
/* start_ip had better be page-aligned! */
start_ip = setup_trampoline();
inquire_remote_apic(apicid);
}
}
-
- if (boot_error) {
- /* Try to put things back the way they were before ... */
- unmap_cpu_to_logical_apicid(cpu);
#ifdef CONFIG_X86_64
- clear_node_cpumask(cpu); /* was set by numa_add_cpu */
+ restore_state:
#endif
+ if (boot_error) {
+ /* Try to put things back the way they were before ... */
+ numa_remove_cpu(cpu); /* was set by numa_add_cpu */
cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
cpu_clear(cpu, cpu_present_map);
{
cpu_present_map = cpumask_of_cpu(0);
cpu_possible_map = cpumask_of_cpu(0);
- #ifdef CONFIG_X86_32
smpboot_clear_io_apic_irqs();
- #endif
+
if (smp_found_config)
- phys_cpu_present_map =
- physid_mask_of_physid(boot_cpu_physical_apicid);
+ physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
else
- phys_cpu_present_map = physid_mask_of_physid(0);
+ physid_set_mask_of_physid(0, &phys_cpu_present_map);
map_cpu_to_logical_apicid();
cpu_set(0, per_cpu(cpu_sibling_map, 0));
cpu_set(0, per_cpu(cpu_core_map, 0));
* If SMP should be disabled, then really disable it!
*/
if (!max_cpus) {
- printk(KERN_INFO "SMP mode deactivated,"
- "forcing use of dummy APIC emulation.\n");
+ printk(KERN_INFO "SMP mode deactivated.\n");
smpboot_clear_io_apic();
- #ifdef CONFIG_X86_32
+
+ localise_nmi_watchdog();
+
connect_bsp_APIC();
- #endif
setup_local_APIC();
end_local_APIC_setup();
return -1;
void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
preempt_disable();
- nmi_watchdog_default();
smp_cpu_index_default();
current_cpu_data = boot_cpu_data;
cpu_callin_map = cpumask_of_cpu(0);
}
preempt_enable();
- #ifdef CONFIG_X86_32
connect_bsp_APIC();
- #endif
+
/*
* Switch from PIC to APIC mode.
*/
int me = smp_processor_id();
#ifdef CONFIG_X86_32
init_gdt(me);
- switch_to_new_gdt();
#endif
+ switch_to_new_gdt();
/* already set me in cpu_online_map in boot_cpu_init() */
cpu_set(me, cpu_callout_map);
per_cpu(cpu_state, me) = CPU_ONLINE;
#ifdef CONFIG_HOTPLUG_CPU
- # ifdef CONFIG_X86_32
- void cpu_exit_clear(void)
- {
- int cpu = raw_smp_processor_id();
-
- idle_task_exit();
-
- cpu_uninit();
- irq_ctx_exit(cpu);
-
- cpu_clear(cpu, cpu_callout_map);
- cpu_clear(cpu, cpu_callin_map);
-
- unmap_cpu_to_logical_apicid(cpu);
- }
- # endif /* CONFIG_X86_32 */
-
static void remove_siblinginfo(int cpu)
{
int sibling;
struct cpuinfo_x86 *c = &cpu_data(cpu);
- for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
+ for_each_cpu_mask_nr(sibling, per_cpu(cpu_core_map, cpu)) {
cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
/*/
* last thread sibling in this cpu core going down
cpu_data(sibling).booted_cores--;
}
- for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu))
+ for_each_cpu_mask_nr(sibling, per_cpu(cpu_sibling_map, cpu))
cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
cpus_clear(per_cpu(cpu_sibling_map, cpu));
cpus_clear(per_cpu(cpu_core_map, cpu));
int i;
int possible;
+ /* no processor from mptable or madt */
+ if (!num_processors)
+ num_processors = 1;
+
+ #ifdef CONFIG_HOTPLUG_CPU
if (additional_cpus == -1) {
if (disabled_cpus > 0)
additional_cpus = disabled_cpus;
else
additional_cpus = 0;
}
+ #else
+ additional_cpus = 0;
+ #endif
possible = num_processors + additional_cpus;
if (possible > NR_CPUS)
possible = NR_CPUS;
for (i = 0; i < possible; i++)
cpu_set(i, cpu_possible_map);
+
+ nr_cpu_ids = possible;
}
static void __ref remove_cpu_from_maps(int cpu)
{
cpu_clear(cpu, cpu_online_map);
- #ifdef CONFIG_X86_64
cpu_clear(cpu, cpu_callout_map);
cpu_clear(cpu, cpu_callin_map);
/* was set by cpu_init() */
clear_bit(cpu, (unsigned long *)&cpu_initialized);
- clear_node_cpumask(cpu);
- #endif
+ numa_remove_cpu(cpu);
}
int __cpu_disable(void)
#include "xen-ops.h"
#include "mmu.h"
- static cpumask_t xen_cpu_initialized_map;
- static DEFINE_PER_CPU(int, resched_irq) = -1;
- static DEFINE_PER_CPU(int, callfunc_irq) = -1;
- static DEFINE_PER_CPU(int, debug_irq) = -1;
-
- /*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- */
- static DEFINE_SPINLOCK(call_lock);
+ cpumask_t xen_cpu_initialized_map;
- struct call_data_struct {
- void (*func) (void *info);
- void *info;
- atomic_t started;
- atomic_t finished;
- int wait;
- };
+ static DEFINE_PER_CPU(int, resched_irq);
+ static DEFINE_PER_CPU(int, callfunc_irq);
+ static DEFINE_PER_CPU(int, callfuncsingle_irq);
+ static DEFINE_PER_CPU(int, debug_irq) = -1;
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
-
- static struct call_data_struct *call_data;
+ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
/*
* Reschedule call back. Nothing to do,
*/
static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
{
+ #ifdef CONFIG_X86_32
+ __get_cpu_var(irq_stat).irq_resched_count++;
+ #else
+ add_pda(irq_resched_count, 1);
+ #endif
+
return IRQ_HANDLED;
}
goto fail;
per_cpu(debug_irq, cpu) = rc;
+ callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+ rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
+ cpu,
+ xen_call_function_single_interrupt,
+ IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+ callfunc_name,
+ NULL);
+ if (rc < 0)
+ goto fail;
+ per_cpu(callfuncsingle_irq, cpu) = rc;
+
return 0;
fail:
unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
if (per_cpu(debug_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
+ if (per_cpu(callfuncsingle_irq, cpu) >= 0)
+ unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+
return rc;
}
void xen_smp_send_stop(void)
{
- smp_call_function(stop_self, NULL, 0, 0);
+ smp_call_function(stop_self, NULL, 0);
}
void xen_smp_send_reschedule(int cpu)
xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
}
-
static void xen_send_IPI_mask(cpumask_t mask, enum ipi_vector vector)
{
unsigned cpu;
cpus_and(mask, mask, cpu_online_map);
- for_each_cpu_mask(cpu, mask)
+ for_each_cpu_mask_nr(cpu, mask)
xen_send_IPI_one(cpu, vector);
}
- for_each_cpu_mask(cpu, mask) {
+ void xen_smp_send_call_function_ipi(cpumask_t mask)
+ {
+ int cpu;
+
+ xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
+
+ /* Make sure other vcpus get a chance to run if they need to. */
++ for_each_cpu_mask_nr(cpu, mask) {
+ if (xen_vcpu_stolen(cpu)) {
+ HYPERVISOR_sched_op(SCHEDOP_yield, 0);
+ break;
+ }
+ }
+ }
+
+ void xen_smp_send_call_function_single_ipi(int cpu)
+ {
+ xen_send_IPI_mask(cpumask_of_cpu(cpu), XEN_CALL_FUNCTION_SINGLE_VECTOR);
+ }
+
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
{
- void (*func) (void *info) = call_data->func;
- void *info = call_data->info;
- int wait = call_data->wait;
-
- /*
- * Notify initiating CPU that I've grabbed the data and am
- * about to execute the function
- */
- mb();
- atomic_inc(&call_data->started);
- /*
- * At this point the info structure may be out of scope unless wait==1
- */
irq_enter();
- (*func)(info);
+ generic_smp_call_function_interrupt();
__get_cpu_var(irq_stat).irq_call_count++;
irq_exit();
- if (wait) {
- mb(); /* commit everything before setting finished */
- atomic_inc(&call_data->finished);
- }
-
return IRQ_HANDLED;
}
- int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
- void *info, int wait)
+ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
{
- struct call_data_struct data;
- int cpus, cpu;
- bool yield;
-
- /* Holding any lock stops cpus from going down. */
- spin_lock(&call_lock);
-
- cpu_clear(smp_processor_id(), mask);
-
- cpus = cpus_weight(mask);
- if (!cpus) {
- spin_unlock(&call_lock);
- return 0;
- }
-
- /* Can deadlock when called with interrupts disabled */
- WARN_ON(irqs_disabled());
-
- data.func = func;
- data.info = info;
- atomic_set(&data.started, 0);
- data.wait = wait;
- if (wait)
- atomic_set(&data.finished, 0);
-
- call_data = &data;
- mb(); /* write everything before IPI */
-
- /* Send a message to other CPUs and wait for them to respond */
- xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
-
- /* Make sure other vcpus get a chance to run if they need to. */
- yield = false;
- for_each_cpu_mask_nr(cpu, mask)
- if (xen_vcpu_stolen(cpu))
- yield = true;
-
- if (yield)
- HYPERVISOR_sched_op(SCHEDOP_yield, 0);
-
- /* Wait for response */
- while (atomic_read(&data.started) != cpus ||
- (wait && atomic_read(&data.finished) != cpus))
- cpu_relax();
-
- spin_unlock(&call_lock);
+ irq_enter();
+ generic_smp_call_function_single_interrupt();
+ __get_cpu_var(irq_stat).irq_call_count++;
+ irq_exit();
- return 0;
+ return IRQ_HANDLED;
}
{
struct ehca_eq *eq = &shca->eq;
struct ehca_eqe_cache_entry *eqe_cache = eq->eqe_cache;
- u64 eqe_value;
+ u64 eqe_value, ret;
unsigned long flags;
int eqe_cnt, i;
int eq_empty = 0;
ehca_dbg(&shca->ib_device,
"No eqe found for irq event");
goto unlock_irq_spinlock;
- } else if (!is_irq)
+ } else if (!is_irq) {
+ ret = hipz_h_eoi(eq->ist);
+ if (ret != H_SUCCESS)
+ ehca_err(&shca->ib_device,
+ "bad return code EOI -rc = %ld\n", ret);
ehca_dbg(&shca->ib_device, "deadman found %x eqe", eqe_cnt);
+ }
if (unlikely(eqe_cnt == EHCA_EQE_CACHE_SIZE))
ehca_dbg(&shca->ib_device, "too many eqes for one irq event");
/* enable irq for new packets */
ehca_dmp(&cpu_online_map, sizeof(cpumask_t), "");
spin_lock_irqsave(&pool->last_cpu_lock, flags);
- cpu = next_cpu(pool->last_cpu, cpu_online_map);
- if (cpu == NR_CPUS)
+ cpu = next_cpu_nr(pool->last_cpu, cpu_online_map);
+ if (cpu >= nr_cpu_ids)
cpu = first_cpu(cpu_online_map);
pool->last_cpu = cpu;
spin_unlock_irqrestore(&pool->last_cpu_lock, flags);
#include <asm/hw_irq.h>
#include <asm/apic.h>
+ #include <asm/smp.h>
/*
* the following functions deal with sending IPIs between CPUs.
* - mbligh
*/
local_irq_save(flags);
- for_each_cpu_mask(query_cpu, mask) {
+ for_each_cpu_mask_nr(query_cpu, mask) {
__send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu),
vector, APIC_DEST_PHYSICAL);
}
#include <linux/stop_machine.h>
#include <linux/mutex.h>
+ /*
+ * Represents all cpu's present in the system
+ * In systems capable of hotplug, this map could dynamically grow
+ * as new cpu's are detected in the system via any platform specific
+ * method, such as ACPI for e.g.
+ */
+ cpumask_t cpu_present_map __read_mostly;
+ EXPORT_SYMBOL(cpu_present_map);
+
+ #ifndef CONFIG_SMP
+
+ /*
+ * Represents all cpu's that are currently online.
+ */
+ cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+ EXPORT_SYMBOL(cpu_online_map);
+
+ cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+ EXPORT_SYMBOL(cpu_possible_map);
+
+ #else /* CONFIG_SMP */
+
/* Serializes the updates to cpu_online_map, cpu_present_map */
static DEFINE_MUTEX(cpu_add_remove_lock);
goto out;
printk("Enabling non-boot CPUs ...\n");
- for_each_cpu_mask(cpu, frozen_cpus) {
+ for_each_cpu_mask_nr(cpu, frozen_cpus) {
error = _cpu_up(cpu, 1);
if (!error) {
printk("CPU%d is up\n", cpu);
cpu_maps_update_done();
}
#endif /* CONFIG_PM_SLEEP_SMP */
+
+ #endif /* CONFIG_SMP */
*/
cpus_and(cpumask, rcp->cpumask, cpu_online_map);
cpu_clear(rdp->cpu, cpumask);
- for_each_cpu_mask(cpu, cpumask)
+ for_each_cpu_mask_nr(cpu, cpumask)
smp_send_reschedule(cpu);
}
}
rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail);
rcu_move_batch(this_rdp, rdp->curlist, rdp->curtail);
rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail);
+
+ local_irq_disable();
+ this_rdp->qlen += rdp->qlen;
+ local_irq_enable();
}
static void rcu_offline_cpu(int cpu)
if (user ||
(idle_cpu(cpu) && !in_softirq() &&
hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+
+ /*
+ * Get here if this CPU took its interrupt from user
+ * mode or from the idle loop, and if this is not a
+ * nested interrupt. In this case, the CPU is in
+ * a quiescent state, so count it.
+ *
+ * Also do a memory barrier. This is needed to handle
+ * the case where writes from a preempt-disable section
+ * of code get reordered into schedule() by this CPU's
+ * write buffer. The memory barrier makes sure that
+ * the rcu_qsctr_inc() and rcu_bh_qsctr_inc() are see
+ * by other CPUs to happen after any such write.
+ */
+
+ smp_mb(); /* See above block comment. */
rcu_qsctr_inc(cpu);
rcu_bh_qsctr_inc(cpu);
- } else if (!in_softirq())
+
+ } else if (!in_softirq()) {
+
+ /*
+ * Get here if this CPU did not take its interrupt from
+ * softirq, in other words, if it is not interrupting
+ * a rcu_bh read-side critical section. This is an _bh
+ * critical section, so count it. The memory barrier
+ * is needed for the same reason as is the above one.
+ */
+
+ smp_mb(); /* See above block comment. */
rcu_bh_qsctr_inc(cpu);
+ }
raise_rcu_softirq();
}
rcu_init_percpu_data(cpu, &rcu_ctrlblk, rdp);
rcu_init_percpu_data(cpu, &rcu_bh_ctrlblk, bh_rdp);
- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks, NULL);
+ open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
}
static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/module.h>
+ #include <linux/kthread.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
- #include <linux/rcupdate.h>
#include <linux/cpu.h>
#include <linux/random.h>
#include <linux/delay.h>
spinlock_t lock; /* Protect rcu_data fields. */
long completed; /* Number of last completed batch. */
int waitlistcount;
- struct tasklet_struct rcu_tasklet;
struct rcu_head *nextlist;
struct rcu_head **nexttail;
struct rcu_head *waitlist[GP_STAGES];
struct rcu_head **waittail[GP_STAGES];
- struct rcu_head *donelist;
+ struct rcu_head *donelist; /* from waitlist & waitschedlist */
struct rcu_head **donetail;
long rcu_flipctr[2];
+ struct rcu_head *nextschedlist;
+ struct rcu_head **nextschedtail;
+ struct rcu_head *waitschedlist;
+ struct rcu_head **waitschedtail;
+ int rcu_sched_sleeping;
#ifdef CONFIG_RCU_TRACE
struct rcupreempt_trace trace;
#endif /* #ifdef CONFIG_RCU_TRACE */
rcu_try_flip_waitmb_state,
};
+ /*
+ * States for rcu_ctrlblk.rcu_sched_sleep.
+ */
+
+ enum rcu_sched_sleep_states {
+ rcu_sched_not_sleeping, /* Not sleeping, callbacks need GP. */
+ rcu_sched_sleep_prep, /* Thinking of sleeping, rechecking. */
+ rcu_sched_sleeping, /* Sleeping, awaken if GP needed. */
+ };
+
struct rcu_ctrlblk {
spinlock_t fliplock; /* Protect state-machine transitions. */
long completed; /* Number of last completed batch. */
enum rcu_try_flip_states rcu_try_flip_state; /* The current state of
the rcu state machine */
+ spinlock_t schedlock; /* Protect rcu_sched sleep state. */
+ enum rcu_sched_sleep_states sched_sleep; /* rcu_sched state. */
+ wait_queue_head_t sched_wq; /* Place for rcu_sched to sleep. */
};
static DEFINE_PER_CPU(struct rcu_data, rcu_data);
.fliplock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.fliplock),
.completed = 0,
.rcu_try_flip_state = rcu_try_flip_idle_state,
+ .schedlock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.schedlock),
+ .sched_sleep = rcu_sched_not_sleeping,
+ .sched_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rcu_ctrlblk.sched_wq),
};
+ static struct task_struct *rcu_sched_grace_period_task;
#ifdef CONFIG_RCU_TRACE
static char *rcu_try_flip_state_names[] =
*/
#define RCU_TRACE_RDP(f, rdp) RCU_TRACE(f, &((rdp)->trace));
+ #define RCU_SCHED_BATCH_TIME (HZ / 50)
+
/*
* Return the number of RCU batches processed thus far. Useful
* for debug and statistics.
}
}
- #ifdef CONFIG_NO_HZ
+ DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
+ .dynticks = 1,
+ };
- DEFINE_PER_CPU(long, dynticks_progress_counter) = 1;
- static DEFINE_PER_CPU(long, rcu_dyntick_snapshot);
+ #ifdef CONFIG_NO_HZ
static DEFINE_PER_CPU(int, rcu_update_flag);
/**
* rcu_irq_enter - Called from Hard irq handlers and NMI/SMI.
*
* If the CPU was idle with dynamic ticks active, this updates the
- * dynticks_progress_counter to let the RCU handling know that the
+ * rcu_dyntick_sched.dynticks to let the RCU handling know that the
* CPU is active.
*/
void rcu_irq_enter(void)
{
int cpu = smp_processor_id();
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
if (per_cpu(rcu_update_flag, cpu))
per_cpu(rcu_update_flag, cpu)++;
/*
* Only update if we are coming from a stopped ticks mode
- * (dynticks_progress_counter is even).
+ * (rcu_dyntick_sched.dynticks is even).
*/
if (!in_interrupt() &&
- (per_cpu(dynticks_progress_counter, cpu) & 0x1) == 0) {
+ (rdssp->dynticks & 0x1) == 0) {
/*
* The following might seem like we could have a race
* with NMI/SMIs. But this really isn't a problem.
* RCU read-side critical sections on this CPU would
* have already completed.
*/
- per_cpu(dynticks_progress_counter, cpu)++;
+ rdssp->dynticks++;
/*
* The following memory barrier ensures that any
* rcu_read_lock() primitives in the irq handler
* are seen by other CPUs to follow the above
- * increment to dynticks_progress_counter. This is
+ * increment to rcu_dyntick_sched.dynticks. This is
* required in order for other CPUs to correctly
* determine when it is safe to advance the RCU
* grace-period state machine.
smp_mb(); /* see above block comment. */
/*
* Since we can't determine the dynamic tick mode from
- * the dynticks_progress_counter after this routine,
+ * the rcu_dyntick_sched.dynticks after this routine,
* we use a second flag to acknowledge that we came
* from an idle state with ticks stopped.
*/
/*
* If we take an NMI/SMI now, they will also increment
* the rcu_update_flag, and will not update the
- * dynticks_progress_counter on exit. That is for
+ * rcu_dyntick_sched.dynticks on exit. That is for
* this IRQ to do.
*/
}
* rcu_irq_exit - Called from exiting Hard irq context.
*
* If the CPU was idle with dynamic ticks active, update the
- * dynticks_progress_counter to put let the RCU handling be
+ * rcu_dyntick_sched.dynticks to put let the RCU handling be
* aware that the CPU is going back to idle with no ticks.
*/
void rcu_irq_exit(void)
{
int cpu = smp_processor_id();
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
/*
* rcu_update_flag is set if we interrupted the CPU
* Once this occurs, we keep track of interrupt nesting
* because a NMI/SMI could also come in, and we still
* only want the IRQ that started the increment of the
- * dynticks_progress_counter to be the one that modifies
+ * rcu_dyntick_sched.dynticks to be the one that modifies
* it on exit.
*/
if (per_cpu(rcu_update_flag, cpu)) {
/*
* If an NMI/SMI happens now we are still
- * protected by the dynticks_progress_counter being odd.
+ * protected by the rcu_dyntick_sched.dynticks being odd.
*/
/*
* The following memory barrier ensures that any
* rcu_read_unlock() primitives in the irq handler
* are seen by other CPUs to preceed the following
- * increment to dynticks_progress_counter. This
+ * increment to rcu_dyntick_sched.dynticks. This
* is required in order for other CPUs to determine
* when it is safe to advance the RCU grace-period
* state machine.
*/
smp_mb(); /* see above block comment. */
- per_cpu(dynticks_progress_counter, cpu)++;
- WARN_ON(per_cpu(dynticks_progress_counter, cpu) & 0x1);
+ rdssp->dynticks++;
+ WARN_ON(rdssp->dynticks & 0x1);
}
}
static void dyntick_save_progress_counter(int cpu)
{
- per_cpu(rcu_dyntick_snapshot, cpu) =
- per_cpu(dynticks_progress_counter, cpu);
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+ rdssp->dynticks_snap = rdssp->dynticks;
}
static inline int
{
long curr;
long snap;
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
- curr = per_cpu(dynticks_progress_counter, cpu);
- snap = per_cpu(rcu_dyntick_snapshot, cpu);
+ curr = rdssp->dynticks;
+ snap = rdssp->dynticks_snap;
smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
/*
* that this CPU already acknowledged the counter.
*/
- if ((curr - snap) > 2 || (snap & 0x1) == 0)
+ if ((curr - snap) > 2 || (curr & 0x1) == 0)
return 0;
/* We need this CPU to explicitly acknowledge the counter flip. */
{
long curr;
long snap;
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
- curr = per_cpu(dynticks_progress_counter, cpu);
- snap = per_cpu(rcu_dyntick_snapshot, cpu);
+ curr = rdssp->dynticks;
+ snap = rdssp->dynticks_snap;
smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
/*
return 1;
}
+ static void dyntick_save_progress_counter_sched(int cpu)
+ {
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+ rdssp->sched_dynticks_snap = rdssp->dynticks;
+ }
+
+ static int rcu_qsctr_inc_needed_dyntick(int cpu)
+ {
+ long curr;
+ long snap;
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+ curr = rdssp->dynticks;
+ snap = rdssp->sched_dynticks_snap;
+ smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+ /*
+ * If the CPU remained in dynticks mode for the entire time
+ * and didn't take any interrupts, NMIs, SMIs, or whatever,
+ * then it cannot be in the middle of an rcu_read_lock(), so
+ * the next rcu_read_lock() it executes must use the new value
+ * of the counter. Therefore, this CPU has been in a quiescent
+ * state the entire time, and we don't need to wait for it.
+ */
+
+ if ((curr == snap) && ((curr & 0x1) == 0))
+ return 0;
+
+ /*
+ * If the CPU passed through or entered a dynticks idle phase with
+ * no active irq handlers, then, as above, this CPU has already
+ * passed through a quiescent state.
+ */
+
+ if ((curr - snap) > 2 || (snap & 0x1) == 0)
+ return 0;
+
+ /* We need this CPU to go through a quiescent state. */
+
+ return 1;
+ }
+
#else /* !CONFIG_NO_HZ */
- # define dyntick_save_progress_counter(cpu) do { } while (0)
- # define rcu_try_flip_waitack_needed(cpu) (1)
- # define rcu_try_flip_waitmb_needed(cpu) (1)
+ # define dyntick_save_progress_counter(cpu) do { } while (0)
+ # define rcu_try_flip_waitack_needed(cpu) (1)
+ # define rcu_try_flip_waitmb_needed(cpu) (1)
+
+ # define dyntick_save_progress_counter_sched(cpu) do { } while (0)
+ # define rcu_qsctr_inc_needed_dyntick(cpu) (1)
#endif /* CONFIG_NO_HZ */
+ static void save_qsctr_sched(int cpu)
+ {
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+ rdssp->sched_qs_snap = rdssp->sched_qs;
+ }
+
+ static inline int rcu_qsctr_inc_needed(int cpu)
+ {
+ struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+ /*
+ * If there has been a quiescent state, no more need to wait
+ * on this CPU.
+ */
+
+ if (rdssp->sched_qs != rdssp->sched_qs_snap) {
+ smp_mb(); /* force ordering with cpu entering schedule(). */
+ return 0;
+ }
+
+ /* We need this CPU to go through a quiescent state. */
+
+ return 1;
+ }
+
/*
* Get here when RCU is idle. Decide whether we need to
* move out of idle state, and return non-zero if so.
/* Now ask each CPU for acknowledgement of the flip. */
- for_each_cpu_mask(cpu, rcu_cpu_online_map) {
+ for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
dyntick_save_progress_counter(cpu);
}
int cpu;
RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
- for_each_cpu_mask(cpu, rcu_cpu_online_map)
+ for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
if (rcu_try_flip_waitack_needed(cpu) &&
per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
/* Check to see if the sum of the "last" counters is zero. */
RCU_TRACE_ME(rcupreempt_trace_try_flip_z1);
- for_each_cpu_mask(cpu, rcu_cpu_online_map)
+ for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
sum += RCU_DATA_CPU(cpu)->rcu_flipctr[lastidx];
if (sum != 0) {
RCU_TRACE_ME(rcupreempt_trace_try_flip_ze1);
smp_mb(); /* ^^^^^^^^^^^^ */
/* Call for a memory barrier from each CPU. */
- for_each_cpu_mask(cpu, rcu_cpu_online_map) {
+ for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
dyntick_save_progress_counter(cpu);
}
int cpu;
RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
- for_each_cpu_mask(cpu, rcu_cpu_online_map)
+ for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
if (rcu_try_flip_waitmb_needed(cpu) &&
per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
unsigned long flags;
struct rcu_data *rdp = RCU_DATA_CPU(cpu);
+ /*
+ * If this CPU took its interrupt from user mode or from the
+ * idle loop, and this is not a nested interrupt, then
+ * this CPU has to have exited all prior preept-disable
+ * sections of code. So increment the counter to note this.
+ *
+ * The memory barrier is needed to handle the case where
+ * writes from a preempt-disable section of code get reordered
+ * into schedule() by this CPU's write buffer. So the memory
+ * barrier makes sure that the rcu_qsctr_inc() is seen by other
+ * CPUs to happen after any such write.
+ */
+
+ if (user ||
+ (idle_cpu(cpu) && !in_softirq() &&
+ hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+ smp_mb(); /* Guard against aggressive schedule(). */
+ rcu_qsctr_inc(cpu);
+ }
+
rcu_check_mb(cpu);
if (rcu_ctrlblk.completed == rdp->completed)
rcu_try_flip();
struct rcu_head *list = NULL;
unsigned long flags;
struct rcu_data *rdp = RCU_DATA_CPU(cpu);
+ struct rcu_head *schedlist = NULL;
+ struct rcu_head **schedtail = &schedlist;
struct rcu_head **tail = &list;
/*
rcu_offline_cpu_enqueue(rdp->waitlist[i], rdp->waittail[i],
list, tail);
rcu_offline_cpu_enqueue(rdp->nextlist, rdp->nexttail, list, tail);
+ rcu_offline_cpu_enqueue(rdp->waitschedlist, rdp->waitschedtail,
+ schedlist, schedtail);
+ rcu_offline_cpu_enqueue(rdp->nextschedlist, rdp->nextschedtail,
+ schedlist, schedtail);
+ rdp->rcu_sched_sleeping = 0;
spin_unlock_irqrestore(&rdp->lock, flags);
rdp->waitlistcount = 0;
* fix.
*/
- local_irq_save(flags);
+ local_irq_save(flags); /* disable preempt till we know what lock. */
rdp = RCU_DATA_ME();
spin_lock(&rdp->lock);
*rdp->nexttail = list;
if (list)
rdp->nexttail = tail;
+ *rdp->nextschedtail = schedlist;
+ if (schedlist)
+ rdp->nextschedtail = schedtail;
spin_unlock_irqrestore(&rdp->lock, flags);
}
- void __devinit rcu_online_cpu(int cpu)
+ #else /* #ifdef CONFIG_HOTPLUG_CPU */
+
+ void rcu_offline_cpu(int cpu)
+ {
+ }
+
+ #endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
+
+ void __cpuinit rcu_online_cpu(int cpu)
{
unsigned long flags;
+ struct rcu_data *rdp;
spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags);
cpu_set(cpu, rcu_cpu_online_map);
spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
- }
- #else /* #ifdef CONFIG_HOTPLUG_CPU */
-
- void rcu_offline_cpu(int cpu)
- {
- }
+ /*
+ * The rcu_sched grace-period processing might have bypassed
+ * this CPU, given that it was not in the rcu_cpu_online_map
+ * when the grace-period scan started. This means that the
+ * grace-period task might sleep. So make sure that if this
+ * should happen, the first callback posted to this CPU will
+ * wake up the grace-period task if need be.
+ */
- void __devinit rcu_online_cpu(int cpu)
- {
+ rdp = RCU_DATA_CPU(cpu);
+ spin_lock_irqsave(&rdp->lock, flags);
+ rdp->rcu_sched_sleeping = 1;
+ spin_unlock_irqrestore(&rdp->lock, flags);
}
- #endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
static void rcu_process_callbacks(struct softirq_action *unused)
{
unsigned long flags;
*rdp->nexttail = head;
rdp->nexttail = &head->next;
RCU_TRACE_RDP(rcupreempt_trace_next_add, rdp);
- spin_unlock(&rdp->lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&rdp->lock, flags);
}
EXPORT_SYMBOL_GPL(call_rcu);
+ void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+ {
+ unsigned long flags;
+ struct rcu_data *rdp;
+ int wake_gp = 0;
+
+ head->func = func;
+ head->next = NULL;
+ local_irq_save(flags);
+ rdp = RCU_DATA_ME();
+ spin_lock(&rdp->lock);
+ *rdp->nextschedtail = head;
+ rdp->nextschedtail = &head->next;
+ if (rdp->rcu_sched_sleeping) {
+
+ /* Grace-period processing might be sleeping... */
+
+ rdp->rcu_sched_sleeping = 0;
+ wake_gp = 1;
+ }
+ spin_unlock_irqrestore(&rdp->lock, flags);
+ if (wake_gp) {
+
+ /* Wake up grace-period processing, unless someone beat us. */
+
+ spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
+ if (rcu_ctrlblk.sched_sleep != rcu_sched_sleeping)
+ wake_gp = 0;
+ rcu_ctrlblk.sched_sleep = rcu_sched_not_sleeping;
+ spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
+ if (wake_gp)
+ wake_up_interruptible(&rcu_ctrlblk.sched_wq);
+ }
+ }
+ EXPORT_SYMBOL_GPL(call_rcu_sched);
+
/*
* Wait until all currently running preempt_disable() code segments
* (including hardware-irq-disable segments) complete. Note that
* in -rt this does -not- necessarily result in all currently executing
* interrupt -handlers- having completed.
*/
- void __synchronize_sched(void)
+ synchronize_rcu_xxx(__synchronize_sched, call_rcu_sched)
+ EXPORT_SYMBOL_GPL(__synchronize_sched);
+
+ /*
+ * kthread function that manages call_rcu_sched grace periods.
+ */
+ static int rcu_sched_grace_period(void *arg)
{
- cpumask_t oldmask;
+ int couldsleep; /* might sleep after current pass. */
+ int couldsleepnext = 0; /* might sleep after next pass. */
int cpu;
+ unsigned long flags;
+ struct rcu_data *rdp;
+ int ret;
- if (sched_getaffinity(0, &oldmask) < 0)
- oldmask = cpu_possible_map;
- for_each_online_cpu(cpu) {
- sched_setaffinity(0, &cpumask_of_cpu(cpu));
- schedule();
- }
- sched_setaffinity(0, &oldmask);
+ /*
+ * Each pass through the following loop handles one
+ * rcu_sched grace period cycle.
+ */
+ do {
+ /* Save each CPU's current state. */
+
+ for_each_online_cpu(cpu) {
+ dyntick_save_progress_counter_sched(cpu);
+ save_qsctr_sched(cpu);
+ }
+
+ /*
+ * Sleep for about an RCU grace-period's worth to
+ * allow better batching and to consume less CPU.
+ */
+ schedule_timeout_interruptible(RCU_SCHED_BATCH_TIME);
+
+ /*
+ * If there was nothing to do last time, prepare to
+ * sleep at the end of the current grace period cycle.
+ */
+ couldsleep = couldsleepnext;
+ couldsleepnext = 1;
+ if (couldsleep) {
+ spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
+ rcu_ctrlblk.sched_sleep = rcu_sched_sleep_prep;
+ spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
+ }
+
+ /*
+ * Wait on each CPU in turn to have either visited
+ * a quiescent state or been in dynticks-idle mode.
+ */
+ for_each_online_cpu(cpu) {
+ while (rcu_qsctr_inc_needed(cpu) &&
+ rcu_qsctr_inc_needed_dyntick(cpu)) {
+ /* resched_cpu(cpu); @@@ */
+ schedule_timeout_interruptible(1);
+ }
+ }
+
+ /* Advance callbacks for each CPU. */
+
+ for_each_online_cpu(cpu) {
+
+ rdp = RCU_DATA_CPU(cpu);
+ spin_lock_irqsave(&rdp->lock, flags);
+
+ /*
+ * We are running on this CPU irq-disabled, so no
+ * CPU can go offline until we re-enable irqs.
+ * The current CPU might have already gone
+ * offline (between the for_each_offline_cpu and
+ * the spin_lock_irqsave), but in that case all its
+ * callback lists will be empty, so no harm done.
+ *
+ * Advance the callbacks! We share normal RCU's
+ * donelist, since callbacks are invoked the
+ * same way in either case.
+ */
+ if (rdp->waitschedlist != NULL) {
+ *rdp->donetail = rdp->waitschedlist;
+ rdp->donetail = rdp->waitschedtail;
+
+ /*
+ * Next rcu_check_callbacks() will
+ * do the required raise_softirq().
+ */
+ }
+ if (rdp->nextschedlist != NULL) {
+ rdp->waitschedlist = rdp->nextschedlist;
+ rdp->waitschedtail = rdp->nextschedtail;
+ couldsleep = 0;
+ couldsleepnext = 0;
+ } else {
+ rdp->waitschedlist = NULL;
+ rdp->waitschedtail = &rdp->waitschedlist;
+ }
+ rdp->nextschedlist = NULL;
+ rdp->nextschedtail = &rdp->nextschedlist;
+
+ /* Mark sleep intention. */
+
+ rdp->rcu_sched_sleeping = couldsleep;
+
+ spin_unlock_irqrestore(&rdp->lock, flags);
+ }
+
+ /* If we saw callbacks on the last scan, go deal with them. */
+
+ if (!couldsleep)
+ continue;
+
+ /* Attempt to block... */
+
+ spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
+ if (rcu_ctrlblk.sched_sleep != rcu_sched_sleep_prep) {
+
+ /*
+ * Someone posted a callback after we scanned.
+ * Go take care of it.
+ */
+ spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
+ couldsleepnext = 0;
+ continue;
+ }
+
+ /* Block until the next person posts a callback. */
+
+ rcu_ctrlblk.sched_sleep = rcu_sched_sleeping;
+ spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
+ ret = 0;
+ __wait_event_interruptible(rcu_ctrlblk.sched_wq,
+ rcu_ctrlblk.sched_sleep != rcu_sched_sleeping,
+ ret);
+
+ /*
+ * Signals would prevent us from sleeping, and we cannot
+ * do much with them in any case. So flush them.
+ */
+ if (ret)
+ flush_signals(current);
+ couldsleepnext = 0;
+
+ } while (!kthread_should_stop());
+
+ return (0);
}
- EXPORT_SYMBOL_GPL(__synchronize_sched);
/*
* Check to see if any future RCU-related work will need to be done
return (rdp->donelist != NULL ||
!!rdp->waitlistcount ||
- rdp->nextlist != NULL);
+ rdp->nextlist != NULL ||
+ rdp->nextschedlist != NULL ||
+ rdp->waitschedlist != NULL);
}
int rcu_pending(int cpu)
if (rdp->donelist != NULL ||
!!rdp->waitlistcount ||
- rdp->nextlist != NULL)
+ rdp->nextlist != NULL ||
+ rdp->nextschedlist != NULL ||
+ rdp->waitschedlist != NULL)
return 1;
/* The RCU core needs an acknowledgement from this CPU. */
rdp->donetail = &rdp->donelist;
rdp->rcu_flipctr[0] = 0;
rdp->rcu_flipctr[1] = 0;
+ rdp->nextschedlist = NULL;
+ rdp->nextschedtail = &rdp->nextschedlist;
+ rdp->waitschedlist = NULL;
+ rdp->waitschedtail = &rdp->waitschedlist;
+ rdp->rcu_sched_sleeping = 0;
}
register_cpu_notifier(&rcu_nb);
for_each_online_cpu(cpu)
rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long) cpu);
- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks, NULL);
+ open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
}
/*
- * Deprecated, use synchronize_rcu() or synchronize_sched() instead.
+ * Late-boot-time RCU initialization that must wait until after scheduler
+ * has been initialized.
*/
- void synchronize_kernel(void)
+ void __init rcu_init_sched(void)
{
- synchronize_rcu();
+ rcu_sched_grace_period_task = kthread_run(rcu_sched_grace_period,
+ NULL,
+ "rcu_sched_grace_period");
+ WARN_ON(IS_ERR(rcu_sched_grace_period_task));
}
#ifdef CONFIG_RCU_TRACE
#include <linux/bootmem.h>
#include <linux/debugfs.h>
#include <linux/ctype.h>
+ #include <linux/ftrace.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
+ #include "sched_cpupri.h"
+
/*
* Convert user-nice values [ -20 ... 0 ... 19 ]
* to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
/* Default task group's cfs_rq on each cpu */
static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
- #endif
+ #endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
- #endif
- #else
+ #endif /* CONFIG_RT_GROUP_SCHED */
+ #else /* !CONFIG_FAIR_GROUP_SCHED */
#define root_task_group init_task_group
- #endif
+ #endif /* CONFIG_FAIR_GROUP_SCHED */
/* task_group_lock serializes add/remove of task groups and also changes to
* a task group's cpu shares.
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_USER_SCHED
# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
- #else
+ #else /* !CONFIG_USER_SCHED */
# define INIT_TASK_GROUP_LOAD NICE_0_LOAD
- #endif
+ #endif /* CONFIG_USER_SCHED */
/*
* A weight of 0 or 1 can cause arithmetics problems.
#else
static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
+ static inline struct task_group *task_group(struct task_struct *p)
+ {
+ return NULL;
+ }
#endif /* CONFIG_GROUP_SCHED */
u64 exec_clock;
u64 min_vruntime;
+ u64 pair_start;
struct rb_root tasks_timeline;
struct rb_node *rb_leftmost;
*/
struct list_head leaf_cfs_rq_list;
struct task_group *tg; /* group that "owns" this runqueue */
+
+ #ifdef CONFIG_SMP
+ /*
+ * the part of load.weight contributed by tasks
+ */
+ unsigned long task_weight;
+
+ /*
+ * h_load = weight * f(tg)
+ *
+ * Where f(tg) is the recursive weight fraction assigned to
+ * this group.
+ */
+ unsigned long h_load;
+
+ /*
+ * this cpu's part of tg->shares
+ */
+ unsigned long shares;
+
+ /*
+ * load.weight at the time we set shares
+ */
+ unsigned long rq_weight;
+ #endif
#endif
};
*/
cpumask_t rto_mask;
atomic_t rto_count;
+ #ifdef CONFIG_SMP
+ struct cpupri cpupri;
+ #endif
};
/*
int push_cpu;
/* cpu of this runqueue: */
int cpu;
+ int online;
+
+ unsigned long avg_load_per_task;
struct task_struct *migration_thread;
struct list_head migration_queue;
# define const_debug static const
#endif
+ /**
+ * runqueue_is_locked
+ *
+ * Returns true if the current cpu runqueue is locked.
+ * This interface allows printk to be called with the runqueue lock
+ * held and know whether or not it is OK to wake up the klogd.
+ */
+ int runqueue_is_locked(void)
+ {
+ int cpu = get_cpu();
+ struct rq *rq = cpu_rq(cpu);
+ int ret;
+
+ ret = spin_is_locked(&rq->lock);
+ put_cpu();
+ return ret;
+ }
+
/*
* Debugging: various feature bits
*/
*/
const_debug unsigned int sysctl_sched_nr_migrate = 32;
+ /*
+ * ratelimit for updating the group shares.
+ * default: 0.5ms
+ */
+ const_debug unsigned int sysctl_sched_shares_ratelimit = 500000;
+
/*
* period over which we measure -rt task cpu usage in us.
* default: 1s
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}
- unsigned long long time_sync_thresh = 100000;
-
- static DEFINE_PER_CPU(unsigned long long, time_offset);
- static DEFINE_PER_CPU(unsigned long long, prev_cpu_time);
-
- /*
- * Global lock which we take every now and then to synchronize
- * the CPUs time. This method is not warp-safe, but it's good
- * enough to synchronize slowly diverging time sources and thus
- * it's good enough for tracing:
- */
- static DEFINE_SPINLOCK(time_sync_lock);
- static unsigned long long prev_global_time;
-
- static unsigned long long __sync_cpu_clock(unsigned long long time, int cpu)
- {
- /*
- * We want this inlined, to not get tracer function calls
- * in this critical section:
- */
- spin_acquire(&time_sync_lock.dep_map, 0, 0, _THIS_IP_);
- __raw_spin_lock(&time_sync_lock.raw_lock);
-
- if (time < prev_global_time) {
- per_cpu(time_offset, cpu) += prev_global_time - time;
- time = prev_global_time;
- } else {
- prev_global_time = time;
- }
-
- __raw_spin_unlock(&time_sync_lock.raw_lock);
- spin_release(&time_sync_lock.dep_map, 1, _THIS_IP_);
-
- return time;
- }
-
- static unsigned long long __cpu_clock(int cpu)
- {
- unsigned long long now;
-
- /*
- * Only call sched_clock() if the scheduler has already been
- * initialized (some code might call cpu_clock() very early):
- */
- if (unlikely(!scheduler_running))
- return 0;
-
- now = sched_clock_cpu(cpu);
-
- return now;
- }
-
- /*
- * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
- * clock constructed from sched_clock():
- */
- unsigned long long cpu_clock(int cpu)
- {
- unsigned long long prev_cpu_time, time, delta_time;
- unsigned long flags;
-
- local_irq_save(flags);
- prev_cpu_time = per_cpu(prev_cpu_time, cpu);
- time = __cpu_clock(cpu) + per_cpu(time_offset, cpu);
- delta_time = time-prev_cpu_time;
-
- if (unlikely(delta_time > time_sync_thresh)) {
- time = __sync_cpu_clock(time, cpu);
- per_cpu(prev_cpu_time, cpu) = time;
- }
- local_irq_restore(flags);
-
- return time;
- }
- EXPORT_SYMBOL_GPL(cpu_clock);
-
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
if (!tsk_is_polling(rq->idle))
smp_send_reschedule(cpu);
}
- #endif
+ #endif /* CONFIG_NO_HZ */
- #else
+ #else /* !CONFIG_SMP */
static void __resched_task(struct task_struct *p, int tif_bit)
{
assert_spin_locked(&task_rq(p)->lock);
set_tsk_thread_flag(p, tif_bit);
}
- #endif
+ #endif /* CONFIG_SMP */
#if BITS_PER_LONG == 32
# define WMULT_CONST (~0UL)
*/
#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+ /*
+ * delta *= weight / lw
+ */
static unsigned long
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
struct load_weight *lw)
return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
}
- static inline unsigned long
- calc_delta_fair(unsigned long delta_exec, struct load_weight *lw)
- {
- return calc_delta_mine(delta_exec, NICE_0_LOAD, lw);
- }
-
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
#ifdef CONFIG_SMP
static unsigned long source_load(int cpu, int type);
static unsigned long target_load(int cpu, int type);
- static unsigned long cpu_avg_load_per_task(int cpu);
static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
- #else /* CONFIG_SMP */
+
+ static unsigned long cpu_avg_load_per_task(int cpu)
+ {
+ struct rq *rq = cpu_rq(cpu);
+
+ if (rq->nr_running)
+ rq->avg_load_per_task = rq->load.weight / rq->nr_running;
+
+ return rq->avg_load_per_task;
+ }
#ifdef CONFIG_FAIR_GROUP_SCHED
- static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
+
+ typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *);
+
+ /*
+ * Iterate the full tree, calling @down when first entering a node and @up when
+ * leaving it for the final time.
+ */
+ static void
+ walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd)
{
+ struct task_group *parent, *child;
+
+ rcu_read_lock();
+ parent = &root_task_group;
+ down:
+ (*down)(parent, cpu, sd);
+ list_for_each_entry_rcu(child, &parent->children, siblings) {
+ parent = child;
+ goto down;
+
+ up:
+ continue;
+ }
+ (*up)(parent, cpu, sd);
+
+ child = parent;
+ parent = parent->parent;
+ if (parent)
+ goto up;
+ rcu_read_unlock();
}
+
+ static void __set_se_shares(struct sched_entity *se, unsigned long shares);
+
+ /*
+ * Calculate and set the cpu's group shares.
+ */
+ static void
+ __update_group_shares_cpu(struct task_group *tg, int cpu,
+ unsigned long sd_shares, unsigned long sd_rq_weight)
+ {
+ int boost = 0;
+ unsigned long shares;
+ unsigned long rq_weight;
+
+ if (!tg->se[cpu])
+ return;
+
+ rq_weight = tg->cfs_rq[cpu]->load.weight;
+
+ /*
+ * If there are currently no tasks on the cpu pretend there is one of
+ * average load so that when a new task gets to run here it will not
+ * get delayed by group starvation.
+ */
+ if (!rq_weight) {
+ boost = 1;
+ rq_weight = NICE_0_LOAD;
+ }
+
+ if (unlikely(rq_weight > sd_rq_weight))
+ rq_weight = sd_rq_weight;
+
+ /*
+ * \Sum shares * rq_weight
+ * shares = -----------------------
+ * \Sum rq_weight
+ *
+ */
+ shares = (sd_shares * rq_weight) / (sd_rq_weight + 1);
+
+ /*
+ * record the actual number of shares, not the boosted amount.
+ */
+ tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
+ tg->cfs_rq[cpu]->rq_weight = rq_weight;
+
+ if (shares < MIN_SHARES)
+ shares = MIN_SHARES;
+ else if (shares > MAX_SHARES)
+ shares = MAX_SHARES;
+
+ __set_se_shares(tg->se[cpu], shares);
+ }
+
+ /*
+ * Re-compute the task group their per cpu shares over the given domain.
+ * This needs to be done in a bottom-up fashion because the rq weight of a
+ * parent group depends on the shares of its child groups.
+ */
+ static void
+ tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
+ {
+ unsigned long rq_weight = 0;
+ unsigned long shares = 0;
+ int i;
+
+ for_each_cpu_mask(i, sd->span) {
+ rq_weight += tg->cfs_rq[i]->load.weight;
+ shares += tg->cfs_rq[i]->shares;
+ }
+
+ if ((!shares && rq_weight) || shares > tg->shares)
+ shares = tg->shares;
+
+ if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
+ shares = tg->shares;
+
+ if (!rq_weight)
+ rq_weight = cpus_weight(sd->span) * NICE_0_LOAD;
+
+ for_each_cpu_mask(i, sd->span) {
+ struct rq *rq = cpu_rq(i);
+ unsigned long flags;
+
+ spin_lock_irqsave(&rq->lock, flags);
+ __update_group_shares_cpu(tg, i, shares, rq_weight);
+ spin_unlock_irqrestore(&rq->lock, flags);
+ }
+ }
+
+ /*
+ * Compute the cpu's hierarchical load factor for each task group.
+ * This needs to be done in a top-down fashion because the load of a child
+ * group is a fraction of its parents load.
+ */
+ static void
+ tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd)
+ {
+ unsigned long load;
+
+ if (!tg->parent) {
+ load = cpu_rq(cpu)->load.weight;
+ } else {
+ load = tg->parent->cfs_rq[cpu]->h_load;
+ load *= tg->cfs_rq[cpu]->shares;
+ load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
+ }
+
+ tg->cfs_rq[cpu]->h_load = load;
+ }
+
+ static void
+ tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd)
+ {
+ }
+
+ static void update_shares(struct sched_domain *sd)
+ {
+ u64 now = cpu_clock(raw_smp_processor_id());
+ s64 elapsed = now - sd->last_update;
+
+ if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
+ sd->last_update = now;
+ walk_tg_tree(tg_nop, tg_shares_up, 0, sd);
+ }
+ }
+
+ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
+ {
+ spin_unlock(&rq->lock);
+ update_shares(sd);
+ spin_lock(&rq->lock);
+ }
+
+ static void update_h_load(int cpu)
+ {
+ walk_tg_tree(tg_load_down, tg_nop, cpu, NULL);
+ }
+
+ #else
+
+ static inline void update_shares(struct sched_domain *sd)
+ {
+ }
+
+ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
+ {
+ }
+
#endif
- #endif /* CONFIG_SMP */
+ #endif
+
+ #ifdef CONFIG_FAIR_GROUP_SCHED
+ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
+ {
+ #ifdef CONFIG_SMP
+ cfs_rq->shares = shares;
+ #endif
+ }
+ #endif
#include "sched_stats.h"
#include "sched_idletask.c"
#endif
#define sched_class_highest (&rt_sched_class)
+ #define for_each_class(class) \
+ for (class = sched_class_highest; class; class = class->next)
- static inline void inc_load(struct rq *rq, const struct task_struct *p)
- {
- update_load_add(&rq->load, p->se.load.weight);
- }
-
- static inline void dec_load(struct rq *rq, const struct task_struct *p)
- {
- update_load_sub(&rq->load, p->se.load.weight);
- }
-
- static void inc_nr_running(struct task_struct *p, struct rq *rq)
+ static void inc_nr_running(struct rq *rq)
{
rq->nr_running++;
- inc_load(rq, p);
}
- static void dec_nr_running(struct task_struct *p, struct rq *rq)
+ static void dec_nr_running(struct rq *rq)
{
rq->nr_running--;
- dec_load(rq, p);
}
static void set_load_weight(struct task_struct *p)
p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
}
+ static void update_avg(u64 *avg, u64 sample)
+ {
+ s64 diff = sample - *avg;
+ *avg += diff >> 3;
+ }
+
static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
{
sched_info_queued(p);
static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
{
+ if (sleep && p->se.last_wakeup) {
+ update_avg(&p->se.avg_overlap,
+ p->se.sum_exec_runtime - p->se.last_wakeup);
+ p->se.last_wakeup = 0;
+ }
+
+ sched_info_dequeued(p);
p->sched_class->dequeue_task(rq, p, sleep);
p->se.on_rq = 0;
}
rq->nr_uninterruptible--;
enqueue_task(rq, p, wakeup);
- inc_nr_running(p, rq);
+ inc_nr_running(rq);
}
/*
rq->nr_uninterruptible++;
dequeue_task(rq, p, sleep);
- dec_nr_running(p, rq);
+ dec_nr_running(rq);
}
/**
return cpu_curr(task_cpu(p)) == p;
}
- /* Used instead of source_load when we know the type == 0 */
- unsigned long weighted_cpuload(const int cpu)
- {
- return cpu_rq(cpu)->load.weight;
- }
-
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
set_task_rq(p, cpu);
#ifdef CONFIG_SMP
+ /* Used instead of source_load when we know the type == 0 */
+ static unsigned long weighted_cpuload(const int cpu)
+ {
+ return cpu_rq(cpu)->load.weight;
+ }
+
/*
* Is this task likely cache-hot:
*/
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
- if (type == 0)
+ if (type == 0 || !sched_feat(LB_BIAS))
return total;
return min(rq->cpu_load[type-1], total);
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
- if (type == 0)
+ if (type == 0 || !sched_feat(LB_BIAS))
return total;
return max(rq->cpu_load[type-1], total);
}
- /*
- * Return the average load per task on the cpu's run queue
- */
- static unsigned long cpu_avg_load_per_task(int cpu)
- {
- struct rq *rq = cpu_rq(cpu);
- unsigned long total = weighted_cpuload(cpu);
- unsigned long n = rq->nr_running;
-
- return n ? total / n : SCHED_LOAD_SCALE;
- }
-
/*
* find_idlest_group finds and returns the least busy CPU group within the
* domain.
/* Tally up the load of all CPUs in the group */
avg_load = 0;
- for_each_cpu_mask(i, group->cpumask) {
+ for_each_cpu_mask_nr(i, group->cpumask) {
/* Bias balancing toward cpus of our domain */
if (local_group)
load = source_load(i, load_idx);
/* Traverse only the allowed CPUs */
cpus_and(*tmp, group->cpumask, p->cpus_allowed);
- for_each_cpu_mask(i, *tmp) {
+ for_each_cpu_mask_nr(i, *tmp) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == this_cpu)) {
sd = tmp;
}
+ if (sd)
+ update_shares(sd);
+
while (sd) {
cpumask_t span, tmpmask;
struct sched_group *group;
if (!sched_feat(SYNC_WAKEUPS))
sync = 0;
+ #ifdef CONFIG_SMP
+ if (sched_feat(LB_WAKEUP_UPDATE)) {
+ struct sched_domain *sd;
+
+ this_cpu = raw_smp_processor_id();
+ cpu = task_cpu(p);
+
+ for_each_domain(this_cpu, sd) {
+ if (cpu_isset(cpu, sd->span)) {
+ update_shares(sd);
+ break;
+ }
+ }
+ }
+ #endif
+
smp_wmb();
rq = task_rq_lock(p, &flags);
old_state = p->state;
}
}
}
- #endif
+ #endif /* CONFIG_SCHEDSTATS */
out_activate:
#endif /* CONFIG_SMP */
success = 1;
out_running:
+ trace_mark(kernel_sched_wakeup,
+ "pid %d state %ld ## rq %p task %p rq->curr %p",
+ p->pid, p->state, rq, p, rq->curr);
check_preempt_curr(rq, p);
p->state = TASK_RUNNING;
p->sched_class->task_wake_up(rq, p);
#endif
out:
+ current->se.last_wakeup = current->se.sum_exec_runtime;
+
task_rq_unlock(rq, &flags);
return success;
* management (if any):
*/
p->sched_class->task_new(rq, p);
- inc_nr_running(p, rq);
+ inc_nr_running(rq);
}
+ trace_mark(kernel_sched_wakeup_new,
+ "pid %d state %ld ## rq %p task %p rq->curr %p",
+ p->pid, p->state, rq, p, rq->curr);
check_preempt_curr(rq, p);
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
notifier->ops->sched_out(notifier, next);
}
- #else
+ #else /* !CONFIG_PREEMPT_NOTIFIERS */
static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
{
}
- #endif
+ #endif /* CONFIG_PREEMPT_NOTIFIERS */
/**
* prepare_task_switch - prepare to switch tasks
struct mm_struct *mm, *oldmm;
prepare_task_switch(rq, prev, next);
+ trace_mark(kernel_sched_schedule,
+ "prev_pid %d next_pid %d prev_state %ld "
+ "## rq %p prev %p next %p",
+ prev->pid, next->pid, prev->state,
+ rq, prev, next);
mm = next->mm;
oldmm = prev->active_mm;
/*
enum cpu_idle_type idle, int *all_pinned,
int *this_best_prio, struct rq_iterator *iterator)
{
- int loops = 0, pulled = 0, pinned = 0, skip_for_load;
+ int loops = 0, pulled = 0, pinned = 0;
struct task_struct *p;
long rem_load_move = max_load_move;
next:
if (!p || loops++ > sysctl_sched_nr_migrate)
goto out;
- /*
- * To help distribute high priority tasks across CPUs we don't
- * skip a task if it will be the highest priority task (i.e. smallest
- * prio value) on its new queue regardless of its load weight
- */
- skip_for_load = (p->se.load.weight >> 1) > rem_load_move +
- SCHED_LOAD_SCALE_FUZZ;
- if ((skip_for_load && p->prio >= *this_best_prio) ||
+
+ if ((p->se.load.weight >> 1) > rem_load_move ||
!can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
p = iterator->next(iterator->arg);
goto next;
max_load_move - total_load_moved,
sd, idle, all_pinned, &this_best_prio);
class = class->next;
+
+ if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
+ break;
+
} while (class && max_load_move > total_load_moved);
return total_load_moved > 0;
max_load = this_load = total_load = total_pwr = 0;
busiest_load_per_task = busiest_nr_running = 0;
this_load_per_task = this_nr_running = 0;
+
if (idle == CPU_NOT_IDLE)
load_idx = sd->busy_idx;
else if (idle == CPU_NEWLY_IDLE)
int __group_imb = 0;
unsigned int balance_cpu = -1, first_idle_cpu = 0;
unsigned long sum_nr_running, sum_weighted_load;
+ unsigned long sum_avg_load_per_task;
+ unsigned long avg_load_per_task;
local_group = cpu_isset(this_cpu, group->cpumask);
/* Tally up the load of all CPUs in the group */
sum_weighted_load = sum_nr_running = avg_load = 0;
+ sum_avg_load_per_task = avg_load_per_task = 0;
+
max_cpu_load = 0;
min_cpu_load = ~0UL;
- for_each_cpu_mask(i, group->cpumask) {
+ for_each_cpu_mask_nr(i, group->cpumask) {
struct rq *rq;
if (!cpu_isset(i, *cpus))
avg_load += load;
sum_nr_running += rq->nr_running;
sum_weighted_load += weighted_cpuload(i);
+
+ sum_avg_load_per_task += cpu_avg_load_per_task(i);
}
/*
avg_load = sg_div_cpu_power(group,
avg_load * SCHED_LOAD_SCALE);
- if ((max_cpu_load - min_cpu_load) > SCHED_LOAD_SCALE)
+
+ /*
+ * Consider the group unbalanced when the imbalance is larger
+ * than the average weight of two tasks.
+ *
+ * APZ: with cgroup the avg task weight can vary wildly and
+ * might not be a suitable number - should we keep a
+ * normalized nr_running number somewhere that negates
+ * the hierarchy?
+ */
+ avg_load_per_task = sg_div_cpu_power(group,
+ sum_avg_load_per_task * SCHED_LOAD_SCALE);
+
+ if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
__group_imb = 1;
group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
if (busiest_load_per_task > this_load_per_task)
imbn = 1;
} else
- this_load_per_task = SCHED_LOAD_SCALE;
+ this_load_per_task = cpu_avg_load_per_task(this_cpu);
- if (max_load - this_load + SCHED_LOAD_SCALE_FUZZ >=
+ if (max_load - this_load + 2*busiest_load_per_task >=
busiest_load_per_task * imbn) {
*imbalance = busiest_load_per_task;
return busiest;
unsigned long max_load = 0;
int i;
- for_each_cpu_mask(i, group->cpumask) {
+ for_each_cpu_mask_nr(i, group->cpumask) {
unsigned long wl;
if (!cpu_isset(i, *cpus))
schedstat_inc(sd, lb_count[idle]);
redo:
+ update_shares(sd);
group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
cpus, balance);
if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- return -1;
- return ld_moved;
+ ld_moved = -1;
+
+ goto out;
out_balanced:
schedstat_inc(sd, lb_balanced[idle]);
if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- return -1;
- return 0;
+ ld_moved = -1;
+ else
+ ld_moved = 0;
+ out:
+ if (ld_moved)
+ update_shares(sd);
+ return ld_moved;
}
/*
schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
redo:
+ update_shares_locked(this_rq, sd);
group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
&sd_idle, cpus, NULL);
if (!group) {
} else
sd->nr_balance_failed = 0;
+ update_shares_locked(this_rq, sd);
return ld_moved;
out_balanced:
/* Earliest time when we have to do rebalance again */
unsigned long next_balance = jiffies + 60*HZ;
int update_next_balance = 0;
+ int need_serialize;
cpumask_t tmp;
for_each_domain(cpu, sd) {
if (interval > HZ*NR_CPUS/10)
interval = HZ*NR_CPUS/10;
+ need_serialize = sd->flags & SD_SERIALIZE;
- if (sd->flags & SD_SERIALIZE) {
+ if (need_serialize) {
if (!spin_trylock(&balancing))
goto out;
}
}
sd->last_balance = jiffies;
}
- if (sd->flags & SD_SERIALIZE)
+ if (need_serialize)
spin_unlock(&balancing);
out:
if (time_after(next_balance, sd->last_balance + interval)) {
int balance_cpu;
cpu_clear(this_cpu, cpus);
- for_each_cpu_mask(balance_cpu, cpus) {
+ for_each_cpu_mask_nr(balance_cpu, cpus) {
/*
* If this cpu gets work to do, stop the load balancing
* work being done for other cpus. Next load
#endif
}
- #if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
+ #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+ defined(CONFIG_PREEMPT_TRACER))
+
+ static inline unsigned long get_parent_ip(unsigned long addr)
+ {
+ if (in_lock_functions(addr)) {
+ addr = CALLER_ADDR2;
+ if (in_lock_functions(addr))
+ addr = CALLER_ADDR3;
+ }
+ return addr;
+ }
void __kprobes add_preempt_count(int val)
{
+ #ifdef CONFIG_DEBUG_PREEMPT
/*
* Underflow?
*/
if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
return;
+ #endif
preempt_count() += val;
+ #ifdef CONFIG_DEBUG_PREEMPT
/*
* Spinlock count overflowing soon?
*/
DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
PREEMPT_MASK - 10);
+ #endif
+ if (preempt_count() == val)
+ trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
EXPORT_SYMBOL(add_preempt_count);
void __kprobes sub_preempt_count(int val)
{
+ #ifdef CONFIG_DEBUG_PREEMPT
/*
* Underflow?
*/
if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
!(preempt_count() & PREEMPT_MASK)))
return;
+ #endif
+ if (preempt_count() == val)
+ trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
preempt_count() -= val;
}
EXPORT_SYMBOL(sub_preempt_count);
prev->comm, prev->pid, preempt_count());
debug_show_held_locks(prev);
+ print_modules();
if (irqs_disabled())
print_irqtrace_events(prev);
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
- int cpu;
+ int cpu, hrtick = sched_feat(HRTICK);
need_resched:
preempt_disable();
schedule_debug(prev);
- hrtick_clear(rq);
+ if (hrtick)
+ hrtick_clear(rq);
/*
* Do the rq-clock update outside the rq lock:
} else
spin_unlock_irq(&rq->lock);
- hrtick_set(rq);
+ if (hrtick)
+ hrtick_set(rq);
if (unlikely(reacquire_kernel_lock(current) < 0))
goto need_resched_nonpreemptible;
goto out_unlock;
}
on_rq = p->se.on_rq;
- if (on_rq) {
+ if (on_rq)
dequeue_task(rq, p, 0);
- dec_load(rq, p);
- }
p->static_prio = NICE_TO_PRIO(nice);
set_load_weight(p);
if (on_rq) {
enqueue_task(rq, p, 0);
- inc_load(rq, p);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
set_load_weight(p);
}
- /**
- * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
- * @p: the task in question.
- * @policy: new policy.
- * @param: structure containing the new RT priority.
- *
- * NOTE that the task may be already dead.
- */
- int sched_setscheduler(struct task_struct *p, int policy,
- struct sched_param *param)
+ static int __sched_setscheduler(struct task_struct *p, int policy,
+ struct sched_param *param, bool user)
{
int retval, oldprio, oldpolicy = -1, on_rq, running;
unsigned long flags;
/*
* Allow unprivileged RT tasks to decrease priority:
*/
- if (!capable(CAP_SYS_NICE)) {
+ if (user && !capable(CAP_SYS_NICE)) {
if (rt_policy(policy)) {
unsigned long rlim_rtprio;
* Do not allow realtime tasks into groups that have no runtime
* assigned.
*/
- if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
+ if (user
+ && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
return -EPERM;
#endif
return 0;
}
+
+ /**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * NOTE that the task may be already dead.
+ */
+ int sched_setscheduler(struct task_struct *p, int policy,
+ struct sched_param *param)
+ {
+ return __sched_setscheduler(p, policy, param, true);
+ }
EXPORT_SYMBOL_GPL(sched_setscheduler);
+ /**
+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * Just like sched_setscheduler, only don't bother checking if the
+ * current context has permission. For example, this is needed in
+ * stop_machine(): we create temporary high priority worker threads,
+ * but our caller might not have that capability.
+ */
+ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
+ struct sched_param *param)
+ {
+ return __sched_setscheduler(p, policy, param, false);
+ }
+
static int
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
return sched_setaffinity(pid, &new_mask);
}
- /*
- * Represents all cpu's present in the system
- * In systems capable of hotplug, this map could dynamically grow
- * as new cpu's are detected in the system via any platform specific
- * method, such as ACPI for e.g.
- */
-
- cpumask_t cpu_present_map __read_mostly;
- EXPORT_SYMBOL(cpu_present_map);
-
- #ifndef CONFIG_SMP
- cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
- EXPORT_SYMBOL(cpu_online_map);
-
- cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
- EXPORT_SYMBOL(cpu_possible_map);
- #endif
-
long sched_getaffinity(pid_t pid, cpumask_t *mask)
{
struct task_struct *p;
return retval;
}
- static const char stat_nam[] = "RSDTtZX";
+ static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
void sched_show_task(struct task_struct *p)
{
goto out;
}
+ if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
+ !cpus_equal(p->cpus_allowed, *new_mask))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
if (p->sched_class->set_cpus_allowed)
p->sched_class->set_cpus_allowed(p, new_mask);
else {
double_rq_lock(rq_src, rq_dest);
/* Already moved. */
if (task_cpu(p) != src_cpu)
- goto out;
+ goto done;
/* Affinity changed (again). */
if (!cpu_isset(dest_cpu, p->cpus_allowed))
- goto out;
+ goto fail;
on_rq = p->se.on_rq;
if (on_rq)
activate_task(rq_dest, p, 0);
check_preempt_curr(rq_dest, p);
}
+ done:
ret = 1;
- out:
+ fail:
double_rq_unlock(rq_src, rq_dest);
return ret;
}
}
#endif
+ static void set_rq_online(struct rq *rq)
+ {
+ if (!rq->online) {
+ const struct sched_class *class;
+
+ cpu_set(rq->cpu, rq->rd->online);
+ rq->online = 1;
+
+ for_each_class(class) {
+ if (class->rq_online)
+ class->rq_online(rq);
+ }
+ }
+ }
+
+ static void set_rq_offline(struct rq *rq)
+ {
+ if (rq->online) {
+ const struct sched_class *class;
+
+ for_each_class(class) {
+ if (class->rq_offline)
+ class->rq_offline(rq);
+ }
+
+ cpu_clear(rq->cpu, rq->rd->online);
+ rq->online = 0;
+ }
+ }
+
/*
* migration_call - callback that gets triggered when a CPU is added.
* Here we can start up the necessary migration thread for the new CPU.
spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpu_isset(cpu, rq->rd->span));
- cpu_set(cpu, rq->rd->online);
+
+ set_rq_online(rq);
}
spin_unlock_irqrestore(&rq->lock, flags);
break;
spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpu_isset(cpu, rq->rd->span));
- cpu_clear(cpu, rq->rd->online);
+ set_rq_offline(rq);
}
spin_unlock_irqrestore(&rq->lock, flags);
break;
#ifdef CONFIG_SCHED_DEBUG
+ static inline const char *sd_level_to_string(enum sched_domain_level lvl)
+ {
+ switch (lvl) {
+ case SD_LV_NONE:
+ return "NONE";
+ case SD_LV_SIBLING:
+ return "SIBLING";
+ case SD_LV_MC:
+ return "MC";
+ case SD_LV_CPU:
+ return "CPU";
+ case SD_LV_NODE:
+ return "NODE";
+ case SD_LV_ALLNODES:
+ return "ALLNODES";
+ case SD_LV_MAX:
+ return "MAX";
+
+ }
+ return "MAX";
+ }
+
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
cpumask_t *groupmask)
{
return -1;
}
- printk(KERN_CONT "span %s\n", str);
+ printk(KERN_CONT "span %s level %s\n",
+ str, sd_level_to_string(sd->level));
if (!cpu_isset(cpu, sd->span)) {
printk(KERN_ERR "ERROR: domain->span does not contain "
}
kfree(groupmask);
}
- #else
+ #else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0)
- #endif
+ #endif /* CONFIG_SCHED_DEBUG */
static int sd_degenerate(struct sched_domain *sd)
{
static void rq_attach_root(struct rq *rq, struct root_domain *rd)
{
unsigned long flags;
- const struct sched_class *class;
spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
struct root_domain *old_rd = rq->rd;
- for (class = sched_class_highest; class; class = class->next) {
- if (class->leave_domain)
- class->leave_domain(rq);
- }
+ if (cpu_isset(rq->cpu, old_rd->online))
+ set_rq_offline(rq);
cpu_clear(rq->cpu, old_rd->span);
- cpu_clear(rq->cpu, old_rd->online);
if (atomic_dec_and_test(&old_rd->refcount))
kfree(old_rd);
cpu_set(rq->cpu, rd->span);
if (cpu_isset(rq->cpu, cpu_online_map))
- cpu_set(rq->cpu, rd->online);
-
- for (class = sched_class_highest; class; class = class->next) {
- if (class->join_domain)
- class->join_domain(rq);
- }
+ set_rq_online(rq);
spin_unlock_irqrestore(&rq->lock, flags);
}
cpus_clear(rd->span);
cpus_clear(rd->online);
+
+ cpupri_init(&rd->cpupri);
}
static void init_defrootdomain(void)
cpus_clear(*covered);
- for_each_cpu_mask(i, *span) {
+ for_each_cpu_mask_nr(i, *span) {
struct sched_group *sg;
int group = group_fn(i, cpu_map, &sg, tmpmask);
int j;
cpus_clear(sg->cpumask);
sg->__cpu_power = 0;
- for_each_cpu_mask(j, *span) {
+ for_each_cpu_mask_nr(j, *span) {
if (group_fn(j, cpu_map, NULL, tmpmask) != group)
continue;
cpus_or(*span, *span, *nodemask);
}
}
- #endif
+ #endif /* CONFIG_NUMA */
int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
*sg = &per_cpu(sched_group_cpus, cpu);
return cpu;
}
- #endif
+ #endif /* CONFIG_SCHED_SMT */
/*
* multi-core sched-domains:
#ifdef CONFIG_SCHED_MC
static DEFINE_PER_CPU(struct sched_domain, core_domains);
static DEFINE_PER_CPU(struct sched_group, sched_group_core);
- #endif
+ #endif /* CONFIG_SCHED_MC */
#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
static int
if (!sg)
return;
do {
- for_each_cpu_mask(j, sg->cpumask) {
+ for_each_cpu_mask_nr(j, sg->cpumask) {
struct sched_domain *sd;
sd = &per_cpu(phys_domains, j);
sg = sg->next;
} while (sg != group_head);
}
- #endif
+ #endif /* CONFIG_NUMA */
#ifdef CONFIG_NUMA
/* Free memory allocated for various sched_group structures */
{
int cpu, i;
- for_each_cpu_mask(cpu, *cpu_map) {
+ for_each_cpu_mask_nr(cpu, *cpu_map) {
struct sched_group **sched_group_nodes
= sched_group_nodes_bycpu[cpu];
sched_group_nodes_bycpu[cpu] = NULL;
}
}
- #else
+ #else /* !CONFIG_NUMA */
static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
{
}
- #endif
+ #endif /* CONFIG_NUMA */
/*
* Initialize sched groups cpu_power.
/*
* Set up domains for cpus specified by the cpu_map.
*/
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd = NULL, *p;
SCHED_CPUMASK_VAR(nodemask, allmasks);
#ifdef CONFIG_SCHED_SMT
/* Set up CPU (sibling) groups */
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
SCHED_CPUMASK_VAR(this_sibling_map, allmasks);
SCHED_CPUMASK_VAR(send_covered, allmasks);
#ifdef CONFIG_SCHED_MC
/* Set up multi-core groups */
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
SCHED_CPUMASK_VAR(this_core_map, allmasks);
SCHED_CPUMASK_VAR(send_covered, allmasks);
goto error;
}
sched_group_nodes[i] = sg;
- for_each_cpu_mask(j, *nodemask) {
+ for_each_cpu_mask_nr(j, *nodemask) {
struct sched_domain *sd;
sd = &per_cpu(node_domains, j);
/* Calculate CPU power for physical packages and nodes */
#ifdef CONFIG_SCHED_SMT
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd = &per_cpu(cpu_domains, i);
init_sched_groups_power(i, sd);
}
#endif
#ifdef CONFIG_SCHED_MC
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd = &per_cpu(core_domains, i);
init_sched_groups_power(i, sd);
}
#endif
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd = &per_cpu(phys_domains, i);
init_sched_groups_power(i, sd);
#endif
/* Attach the domains */
- for_each_cpu_mask(i, *cpu_map) {
+ for_each_cpu_mask_nr(i, *cpu_map) {
struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
sd = &per_cpu(cpu_domains, i);
unregister_sched_domain_sysctl();
- for_each_cpu_mask(i, *cpu_map)
+ for_each_cpu_mask_nr(i, *cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
synchronize_sched();
arch_destroy_sched_domains(cpu_map, &tmpmask);
#endif
return err;
}
- #endif
+ #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
/*
* Force a reinitialization of the sched domains hierarchy. The domains
static int update_sched_domains(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
+ int cpu = (int)(long)hcpu;
+
switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
+ disable_runtime(cpu_rq(cpu));
+ /* fall-through */
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
detach_destroy_domains(&cpu_online_map);
free_sched_domains();
return NOTIFY_OK;
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
+
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
+ enable_runtime(cpu_rq(cpu));
+ /* fall-through */
+ case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
/*
root_task_group.cfs_rq = (struct cfs_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
- #endif
- #endif
+ #endif /* CONFIG_USER_SCHED */
+ #endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
init_task_group.rt_se = (struct sched_rt_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.rt_rq = (struct rt_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
- #endif
- #endif
+ #endif /* CONFIG_USER_SCHED */
+ #endif /* CONFIG_RT_GROUP_SCHED */
}
#ifdef CONFIG_SMP
#ifdef CONFIG_USER_SCHED
init_rt_bandwidth(&root_task_group.rt_bandwidth,
global_rt_period(), RUNTIME_INF);
- #endif
- #endif
+ #endif /* CONFIG_USER_SCHED */
+ #endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_GROUP_SCHED
list_add(&init_task_group.list, &task_groups);
INIT_LIST_HEAD(&root_task_group.children);
init_task_group.parent = &root_task_group;
list_add(&init_task_group.siblings, &root_task_group.children);
- #endif
- #endif
+ #endif /* CONFIG_USER_SCHED */
+ #endif /* CONFIG_GROUP_SCHED */
for_each_possible_cpu(i) {
struct rq *rq;
rq->next_balance = jiffies;
rq->push_cpu = 0;
rq->cpu = i;
+ rq->online = 0;
rq->migration_thread = NULL;
INIT_LIST_HEAD(&rq->migration_queue);
rq_attach_root(rq, &def_root_domain);
#endif
#ifdef CONFIG_SMP
- open_softirq(SCHED_SOFTIRQ, run_rebalance_domains, NULL);
+ open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
#endif
#ifdef CONFIG_RT_MUTEXES
{
list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list);
}
- #else
+ #else /* !CONFG_FAIR_GROUP_SCHED */
static inline void free_fair_sched_group(struct task_group *tg)
{
}
static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
{
}
- #endif
+ #endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
static void free_rt_sched_group(struct task_group *tg)
{
list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list);
}
- #else
+ #else /* !CONFIG_RT_GROUP_SCHED */
static inline void free_rt_sched_group(struct task_group *tg)
{
}
static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
{
}
- #endif
+ #endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_GROUP_SCHED
static void free_sched_group(struct task_group *tg)
task_rq_unlock(rq, &flags);
}
- #endif
+ #endif /* CONFIG_GROUP_SCHED */
#ifdef CONFIG_FAIR_GROUP_SCHED
- static void set_se_shares(struct sched_entity *se, unsigned long shares)
+ static void __set_se_shares(struct sched_entity *se, unsigned long shares)
{
struct cfs_rq *cfs_rq = se->cfs_rq;
- struct rq *rq = cfs_rq->rq;
int on_rq;
- spin_lock_irq(&rq->lock);
-
on_rq = se->on_rq;
if (on_rq)
dequeue_entity(cfs_rq, se, 0);
if (on_rq)
enqueue_entity(cfs_rq, se, 0);
+ }
- spin_unlock_irq(&rq->lock);
+ static void set_se_shares(struct sched_entity *se, unsigned long shares)
+ {
+ struct cfs_rq *cfs_rq = se->cfs_rq;
+ struct rq *rq = cfs_rq->rq;
+ unsigned long flags;
+
+ spin_lock_irqsave(&rq->lock, flags);
+ __set_se_shares(se, shares);
+ spin_unlock_irqrestore(&rq->lock, flags);
}
static DEFINE_MUTEX(shares_mutex);
* w/o tripping rebalance_share or load_balance_fair.
*/
tg->shares = shares;
- for_each_possible_cpu(i)
+ for_each_possible_cpu(i) {
+ /*
+ * force a rebalance
+ */
+ cfs_rq_set_shares(tg->cfs_rq[i], 0);
set_se_shares(tg->se[i], shares);
+ }
/*
* Enable load balance activity on this group, by inserting it back on
#ifdef CONFIG_CGROUP_SCHED
static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
{
- struct task_group *tgi, *parent = tg ? tg->parent : NULL;
+ struct task_group *tgi, *parent = tg->parent;
unsigned long total = 0;
if (!parent) {
}
rcu_read_unlock();
- return total + to_ratio(period, runtime) <
+ return total + to_ratio(period, runtime) <=
to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period),
parent->rt_bandwidth.rt_runtime);
}
static int sched_rt_global_constraints(void)
{
+ struct task_group *tg = &root_task_group;
+ u64 rt_runtime, rt_period;
int ret = 0;
+ rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+ rt_runtime = tg->rt_bandwidth.rt_runtime;
+
mutex_lock(&rt_constraints_mutex);
- if (!__rt_schedulable(NULL, 1, 0))
+ if (!__rt_schedulable(tg, rt_period, rt_runtime))
ret = -EINVAL;
mutex_unlock(&rt_constraints_mutex);
return ret;
}
- #else
+ #else /* !CONFIG_RT_GROUP_SCHED */
static int sched_rt_global_constraints(void)
{
unsigned long flags;
return 0;
}
- #endif
+ #endif /* CONFIG_RT_GROUP_SCHED */
int sched_rt_handler(struct ctl_table *table, int write,
struct file *filp, void __user *buffer, size_t *lenp,
return (u64) tg->shares;
}
- #endif
+ #endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
{
return sched_group_rt_period(cgroup_tg(cgrp));
}
- #endif
+ #endif /* CONFIG_RT_GROUP_SCHED */
static struct cftype cpu_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* SCHED_OTHER wake-up granularity.
- * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
* This option delays the preemption effects of decoupled workloads
* and reduces their over-scheduling. Synchronous workloads will still
* have immediate wakeup/sleep latencies.
*/
- unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
+ unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
}
#endif
+ /*
+ * delta *= w / rw
+ */
+ static inline unsigned long
+ calc_delta_weight(unsigned long delta, struct sched_entity *se)
+ {
+ for_each_sched_entity(se) {
+ delta = calc_delta_mine(delta,
+ se->load.weight, &cfs_rq_of(se)->load);
+ }
+
+ return delta;
+ }
+
+ /*
+ * delta *= rw / w
+ */
+ static inline unsigned long
+ calc_delta_fair(unsigned long delta, struct sched_entity *se)
+ {
+ for_each_sched_entity(se) {
+ delta = calc_delta_mine(delta,
+ cfs_rq_of(se)->load.weight, &se->load);
+ }
+
+ return delta;
+ }
+
/*
* The idea is to set a period in which each task runs once.
*
*/
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- u64 slice = __sched_period(cfs_rq->nr_running);
-
- for_each_sched_entity(se) {
- cfs_rq = cfs_rq_of(se);
-
- slice *= se->load.weight;
- do_div(slice, cfs_rq->load.weight);
- }
-
-
- return slice;
+ return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
}
/*
* We calculate the vruntime slice of a to be inserted task
*
- * vs = s/w = p/rw
+ * vs = s*rw/w = p
*/
static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
unsigned long nr_running = cfs_rq->nr_running;
- unsigned long weight;
- u64 vslice;
if (!se->on_rq)
nr_running++;
- vslice = __sched_period(nr_running);
+ return __sched_period(nr_running);
+ }
+
+ /*
+ * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
+ * that it favours >=0 over <0.
+ *
+ * -20 |
+ * |
+ * 0 --------+-------
+ * .'
+ * 19 .'
+ *
+ */
+ static unsigned long
+ calc_delta_asym(unsigned long delta, struct sched_entity *se)
+ {
+ struct load_weight lw = {
+ .weight = NICE_0_LOAD,
+ .inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
+ };
for_each_sched_entity(se) {
- cfs_rq = cfs_rq_of(se);
+ struct load_weight *se_lw = &se->load;
+ unsigned long rw = cfs_rq_of(se)->load.weight;
+
+ #ifdef CONFIG_FAIR_SCHED_GROUP
+ struct cfs_rq *cfs_rq = se->my_q;
+ struct task_group *tg = NULL
+
+ if (cfs_rq)
+ tg = cfs_rq->tg;
+
+ if (tg && tg->shares < NICE_0_LOAD) {
+ /*
+ * scale shares to what it would have been had
+ * tg->weight been NICE_0_LOAD:
+ *
+ * weight = 1024 * shares / tg->weight
+ */
+ lw.weight *= se->load.weight;
+ lw.weight /= tg->shares;
+
+ lw.inv_weight = 0;
+
+ se_lw = &lw;
+ rw += lw.weight - se->load.weight;
+ } else
+ #endif
- weight = cfs_rq->load.weight;
- if (!se->on_rq)
- weight += se->load.weight;
+ if (se->load.weight < NICE_0_LOAD) {
+ se_lw = &lw;
+ rw += NICE_0_LOAD - se->load.weight;
+ }
- vslice *= NICE_0_LOAD;
- do_div(vslice, weight);
+ delta = calc_delta_mine(delta, rw, se_lw);
}
- return vslice;
+ return delta;
}
/*
curr->sum_exec_runtime += delta_exec;
schedstat_add(cfs_rq, exec_clock, delta_exec);
- delta_exec_weighted = delta_exec;
- if (unlikely(curr->load.weight != NICE_0_LOAD)) {
- delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
- &curr->load);
- }
+ delta_exec_weighted = calc_delta_fair(delta_exec, curr);
curr->vruntime += delta_exec_weighted;
}
* Scheduling class queueing methods:
*/
+ #if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+ static void
+ add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
+ {
+ cfs_rq->task_weight += weight;
+ }
+ #else
+ static inline void
+ add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
+ {
+ }
+ #endif
+
static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_add(&cfs_rq->load, se->load.weight);
+ if (!parent_entity(se))
+ inc_cpu_load(rq_of(cfs_rq), se->load.weight);
+ if (entity_is_task(se))
+ add_cfs_task_weight(cfs_rq, se->load.weight);
cfs_rq->nr_running++;
se->on_rq = 1;
list_add(&se->group_node, &cfs_rq->tasks);
account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_sub(&cfs_rq->load, se->load.weight);
+ if (!parent_entity(se))
+ dec_cpu_load(rq_of(cfs_rq), se->load.weight);
+ if (entity_is_task(se))
+ add_cfs_task_weight(cfs_rq, -se->load.weight);
cfs_rq->nr_running--;
se->on_rq = 0;
list_del_init(&se->group_node);
if (!initial) {
/* sleeps upto a single latency don't count. */
- if (sched_feat(NEW_FAIR_SLEEPERS))
- vruntime -= sysctl_sched_latency;
+ if (sched_feat(NEW_FAIR_SLEEPERS)) {
+ unsigned long thresh = sysctl_sched_latency;
+
+ /*
+ * convert the sleeper threshold into virtual time
+ */
+ if (sched_feat(NORMALIZED_SLEEPER))
+ thresh = calc_delta_fair(thresh, se);
+
+ vruntime -= thresh;
+ }
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
__enqueue_entity(cfs_rq, se);
}
- static void update_avg(u64 *avg, u64 sample)
- {
- s64 diff = sample - *avg;
- *avg += diff >> 3;
- }
-
- static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
- {
- if (!se->last_wakeup)
- return;
-
- update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
- se->last_wakeup = 0;
- }
-
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
update_stats_dequeue(cfs_rq, se);
if (sleep) {
- update_avg_stats(cfs_rq, se);
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
- static int
- wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
-
static struct sched_entity *
pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (!cfs_rq->next)
- return se;
+ struct rq *rq = rq_of(cfs_rq);
+ u64 pair_slice = rq->clock - cfs_rq->pair_start;
- if (wakeup_preempt_entity(cfs_rq->next, se) != 0)
+ if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
+ cfs_rq->pair_start = rq->clock;
return se;
+ }
return cfs_rq->next;
}
hrtick_start(rq, delta, requeue);
}
}
- #else
+ #else /* !CONFIG_SCHED_HRTICK */
static inline void
hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
|| ((sd->flags & SD_WAKE_IDLE_FAR)
&& !task_hot(p, task_rq(p)->clock, sd))) {
cpus_and(tmp, sd->span, p->cpus_allowed);
- for_each_cpu_mask(i, tmp) {
+ for_each_cpu_mask_nr(i, tmp) {
if (idle_cpu(i)) {
if (i != task_cpu(p)) {
schedstat_inc(p,
}
return cpu;
}
- #else
+ #else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
static inline int wake_idle(int cpu, struct task_struct *p)
{
return cpu;
static const struct sched_class fair_sched_class;
+ #ifdef CONFIG_FAIR_GROUP_SCHED
+ /*
+ * effective_load() calculates the load change as seen from the root_task_group
+ *
+ * Adding load to a group doesn't make a group heavier, but can cause movement
+ * of group shares between cpus. Assuming the shares were perfectly aligned one
+ * can calculate the shift in shares.
+ *
+ * The problem is that perfectly aligning the shares is rather expensive, hence
+ * we try to avoid doing that too often - see update_shares(), which ratelimits
+ * this change.
+ *
+ * We compensate this by not only taking the current delta into account, but
+ * also considering the delta between when the shares were last adjusted and
+ * now.
+ *
+ * We still saw a performance dip, some tracing learned us that between
+ * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
+ * significantly. Therefore try to bias the error in direction of failing
+ * the affine wakeup.
+ *
+ */
+ static long effective_load(struct task_group *tg, int cpu,
+ long wl, long wg)
+ {
+ struct sched_entity *se = tg->se[cpu];
+ long more_w;
+
+ if (!tg->parent)
+ return wl;
+
+ /*
+ * By not taking the decrease of shares on the other cpu into
+ * account our error leans towards reducing the affine wakeups.
+ */
+ if (!wl && sched_feat(ASYM_EFF_LOAD))
+ return wl;
+
+ /*
+ * Instead of using this increment, also add the difference
+ * between when the shares were last updated and now.
+ */
+ more_w = se->my_q->load.weight - se->my_q->rq_weight;
+ wl += more_w;
+ wg += more_w;
+
+ for_each_sched_entity(se) {
+ #define D(n) (likely(n) ? (n) : 1)
+
+ long S, rw, s, a, b;
+
+ S = se->my_q->tg->shares;
+ s = se->my_q->shares;
+ rw = se->my_q->rq_weight;
+
+ a = S*(rw + wl);
+ b = S*rw + s*wg;
+
+ wl = s*(a-b)/D(b);
+ /*
+ * Assume the group is already running and will
+ * thus already be accounted for in the weight.
+ *
+ * That is, moving shares between CPUs, does not
+ * alter the group weight.
+ */
+ wg = 0;
+ #undef D
+ }
+
+ return wl;
+ }
+
+ #else
+
+ static inline unsigned long effective_load(struct task_group *tg, int cpu,
+ unsigned long wl, unsigned long wg)
+ {
+ return wl;
+ }
+
+ #endif
+
static int
wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
struct task_struct *p, int prev_cpu, int this_cpu, int sync,
unsigned int imbalance)
{
struct task_struct *curr = this_rq->curr;
+ struct task_group *tg;
unsigned long tl = this_load;
unsigned long tl_per_task;
+ unsigned long weight;
int balanced;
if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
* effect of the currently running task from the load
* of the current CPU:
*/
- if (sync)
- tl -= current->se.load.weight;
+ if (sync) {
+ tg = task_group(current);
+ weight = current->se.load.weight;
+
+ tl += effective_load(tg, this_cpu, -weight, -weight);
+ load += effective_load(tg, prev_cpu, 0, -weight);
+ }
- balanced = 100*(tl + p->se.load.weight) <= imbalance*load;
+ tg = task_group(p);
+ weight = p->se.load.weight;
+
+ balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+ imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
/*
* If the currently running task will sleep within
* a reasonable amount of time then attract this newly
* woken task:
*/
- if (sync && balanced && curr->sched_class == &fair_sched_class) {
+ if (sync && balanced) {
if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
- p->se.avg_overlap < sysctl_sched_migration_cost)
+ p->se.avg_overlap < sysctl_sched_migration_cost)
return 1;
}
unsigned long gran = sysctl_sched_wakeup_granularity;
/*
- * More easily preempt - nice tasks, while not making
- * it harder for + nice tasks.
+ * More easily preempt - nice tasks, while not making it harder for
+ * + nice tasks.
*/
- if (unlikely(se->load.weight > NICE_0_LOAD))
- gran = calc_delta_fair(gran, &se->load);
+ if (sched_feat(ASYM_GRAN))
+ gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
+ else
+ gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
return gran;
}
return;
}
- se->last_wakeup = se->sum_exec_runtime;
if (unlikely(se == pse))
return;
struct task_struct *p = NULL;
struct sched_entity *se;
- if (next == &cfs_rq->tasks)
- return NULL;
-
- /* Skip over entities that are not tasks */
- do {
+ while (next != &cfs_rq->tasks) {
se = list_entry(next, struct sched_entity, group_node);
next = next->next;
- } while (next != &cfs_rq->tasks && !entity_is_task(se));
- if (next == &cfs_rq->tasks)
- return NULL;
+ /* Skip over entities that are not tasks */
+ if (entity_is_task(se)) {
+ p = task_of(se);
+ break;
+ }
+ }
cfs_rq->balance_iterator = next;
-
- if (entity_is_task(se))
- p = task_of(se);
-
return p;
}
return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
}
- #ifdef CONFIG_FAIR_GROUP_SCHED
- static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
+ static unsigned long
+ __load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ unsigned long max_load_move, struct sched_domain *sd,
+ enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
+ struct cfs_rq *cfs_rq)
{
- struct sched_entity *curr;
- struct task_struct *p;
-
- if (!cfs_rq->nr_running || !first_fair(cfs_rq))
- return MAX_PRIO;
-
- curr = cfs_rq->curr;
- if (!curr)
- curr = __pick_next_entity(cfs_rq);
+ struct rq_iterator cfs_rq_iterator;
- p = task_of(curr);
+ cfs_rq_iterator.start = load_balance_start_fair;
+ cfs_rq_iterator.next = load_balance_next_fair;
+ cfs_rq_iterator.arg = cfs_rq;
- return p->prio;
+ return balance_tasks(this_rq, this_cpu, busiest,
+ max_load_move, sd, idle, all_pinned,
+ this_best_prio, &cfs_rq_iterator);
}
- #endif
+ #ifdef CONFIG_FAIR_GROUP_SCHED
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio)
{
- struct cfs_rq *busy_cfs_rq;
long rem_load_move = max_load_move;
- struct rq_iterator cfs_rq_iterator;
+ int busiest_cpu = cpu_of(busiest);
+ struct task_group *tg;
- cfs_rq_iterator.start = load_balance_start_fair;
- cfs_rq_iterator.next = load_balance_next_fair;
-
- for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
- #ifdef CONFIG_FAIR_GROUP_SCHED
- struct cfs_rq *this_cfs_rq;
- long imbalance;
- unsigned long maxload;
+ rcu_read_lock();
+ update_h_load(busiest_cpu);
- this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
+ list_for_each_entry(tg, &task_groups, list) {
+ struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
+ unsigned long busiest_h_load = busiest_cfs_rq->h_load;
+ unsigned long busiest_weight = busiest_cfs_rq->load.weight;
+ u64 rem_load, moved_load;
- imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
- /* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
- if (imbalance <= 0)
+ /*
+ * empty group
+ */
+ if (!busiest_cfs_rq->task_weight)
continue;
- /* Don't pull more than imbalance/2 */
- imbalance /= 2;
- maxload = min(rem_load_move, imbalance);
+ rem_load = (u64)rem_load_move * busiest_weight;
+ rem_load = div_u64(rem_load, busiest_h_load + 1);
- *this_best_prio = cfs_rq_best_prio(this_cfs_rq);
- #else
- # define maxload rem_load_move
- #endif
- /*
- * pass busy_cfs_rq argument into
- * load_balance_[start|next]_fair iterators
- */
- cfs_rq_iterator.arg = busy_cfs_rq;
- rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
- maxload, sd, idle, all_pinned,
- this_best_prio,
- &cfs_rq_iterator);
+ moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
+ rem_load, sd, idle, all_pinned, this_best_prio,
+ tg->cfs_rq[busiest_cpu]);
- if (rem_load_move <= 0)
+ if (!moved_load)
+ continue;
+
+ moved_load *= busiest_h_load;
+ moved_load = div_u64(moved_load, busiest_weight + 1);
+
+ rem_load_move -= moved_load;
+ if (rem_load_move < 0)
break;
}
+ rcu_read_unlock();
return max_load_move - rem_load_move;
}
+ #else
+ static unsigned long
+ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ unsigned long max_load_move,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ int *all_pinned, int *this_best_prio)
+ {
+ return __load_balance_fair(this_rq, this_cpu, busiest,
+ max_load_move, sd, idle, all_pinned,
+ this_best_prio, &busiest->cfs);
+ }
+ #endif
static int
move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
return 0;
}
- #endif
+ #endif /* CONFIG_SMP */
/*
* scheduler tick hitting a task of our scheduling class:
static inline void rt_set_overload(struct rq *rq)
{
+ if (!rq->online)
+ return;
+
cpu_set(rq->cpu, rq->rd->rto_mask);
/*
* Make sure the mask is visible before we set
static inline void rt_clear_overload(struct rq *rq)
{
+ if (!rq->online)
+ return;
+
/* the order here really doesn't matter */
atomic_dec(&rq->rd->rto_count);
cpu_clear(rq->cpu, rq->rd->rto_mask);
return &rt_rq->tg->rt_bandwidth;
}
- #else
+ #else /* !CONFIG_RT_GROUP_SCHED */
static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
{
return &def_rt_bandwidth;
}
- #endif
-
- static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
- {
- int i, idle = 1;
- cpumask_t span;
-
- if (rt_b->rt_runtime == RUNTIME_INF)
- return 1;
-
- span = sched_rt_period_mask();
- for_each_cpu_mask_nr(i, span) {
- int enqueue = 0;
- struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
- struct rq *rq = rq_of_rt_rq(rt_rq);
-
- spin_lock(&rq->lock);
- if (rt_rq->rt_time) {
- u64 runtime;
-
- spin_lock(&rt_rq->rt_runtime_lock);
- runtime = rt_rq->rt_runtime;
- rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
- if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
- rt_rq->rt_throttled = 0;
- enqueue = 1;
- }
- if (rt_rq->rt_time || rt_rq->rt_nr_running)
- idle = 0;
- spin_unlock(&rt_rq->rt_runtime_lock);
- } else if (rt_rq->rt_nr_running)
- idle = 0;
-
- if (enqueue)
- sched_rt_rq_enqueue(rt_rq);
- spin_unlock(&rq->lock);
- }
-
- return idle;
- }
+ #endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_SMP
- static int balance_runtime(struct rt_rq *rt_rq)
+ static int do_balance_runtime(struct rt_rq *rt_rq)
{
struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
spin_lock(&rt_b->rt_runtime_lock);
rt_period = ktime_to_ns(rt_b->rt_period);
- for_each_cpu_mask(i, rd->span) {
+ for_each_cpu_mask_nr(i, rd->span) {
struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
s64 diff;
continue;
spin_lock(&iter->rt_runtime_lock);
+ if (iter->rt_runtime == RUNTIME_INF)
+ goto next;
+
diff = iter->rt_runtime - iter->rt_time;
if (diff > 0) {
do_div(diff, weight);
break;
}
}
+ next:
spin_unlock(&iter->rt_runtime_lock);
}
spin_unlock(&rt_b->rt_runtime_lock);
return more;
}
- #endif
+
+ static void __disable_runtime(struct rq *rq)
+ {
+ struct root_domain *rd = rq->rd;
+ struct rt_rq *rt_rq;
+
+ if (unlikely(!scheduler_running))
+ return;
+
+ for_each_leaf_rt_rq(rt_rq, rq) {
+ struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+ s64 want;
+ int i;
+
+ spin_lock(&rt_b->rt_runtime_lock);
+ spin_lock(&rt_rq->rt_runtime_lock);
+ if (rt_rq->rt_runtime == RUNTIME_INF ||
+ rt_rq->rt_runtime == rt_b->rt_runtime)
+ goto balanced;
+ spin_unlock(&rt_rq->rt_runtime_lock);
+
+ want = rt_b->rt_runtime - rt_rq->rt_runtime;
+
+ for_each_cpu_mask(i, rd->span) {
+ struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
+ s64 diff;
+
+ if (iter == rt_rq)
+ continue;
+
+ spin_lock(&iter->rt_runtime_lock);
+ if (want > 0) {
+ diff = min_t(s64, iter->rt_runtime, want);
+ iter->rt_runtime -= diff;
+ want -= diff;
+ } else {
+ iter->rt_runtime -= want;
+ want -= want;
+ }
+ spin_unlock(&iter->rt_runtime_lock);
+
+ if (!want)
+ break;
+ }
+
+ spin_lock(&rt_rq->rt_runtime_lock);
+ BUG_ON(want);
+ balanced:
+ rt_rq->rt_runtime = RUNTIME_INF;
+ spin_unlock(&rt_rq->rt_runtime_lock);
+ spin_unlock(&rt_b->rt_runtime_lock);
+ }
+ }
+
+ static void disable_runtime(struct rq *rq)
+ {
+ unsigned long flags;
+
+ spin_lock_irqsave(&rq->lock, flags);
+ __disable_runtime(rq);
+ spin_unlock_irqrestore(&rq->lock, flags);
+ }
+
+ static void __enable_runtime(struct rq *rq)
+ {
+ struct rt_rq *rt_rq;
+
+ if (unlikely(!scheduler_running))
+ return;
+
+ for_each_leaf_rt_rq(rt_rq, rq) {
+ struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+ spin_lock(&rt_b->rt_runtime_lock);
+ spin_lock(&rt_rq->rt_runtime_lock);
+ rt_rq->rt_runtime = rt_b->rt_runtime;
+ rt_rq->rt_time = 0;
+ spin_unlock(&rt_rq->rt_runtime_lock);
+ spin_unlock(&rt_b->rt_runtime_lock);
+ }
+ }
+
+ static void enable_runtime(struct rq *rq)
+ {
+ unsigned long flags;
+
+ spin_lock_irqsave(&rq->lock, flags);
+ __enable_runtime(rq);
+ spin_unlock_irqrestore(&rq->lock, flags);
+ }
+
+ static int balance_runtime(struct rt_rq *rt_rq)
+ {
+ int more = 0;
+
+ if (rt_rq->rt_time > rt_rq->rt_runtime) {
+ spin_unlock(&rt_rq->rt_runtime_lock);
+ more = do_balance_runtime(rt_rq);
+ spin_lock(&rt_rq->rt_runtime_lock);
+ }
+
+ return more;
+ }
+ #else /* !CONFIG_SMP */
+ static inline int balance_runtime(struct rt_rq *rt_rq)
+ {
+ return 0;
+ }
+ #endif /* CONFIG_SMP */
+
+ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
+ {
+ int i, idle = 1;
+ cpumask_t span;
+
+ if (rt_b->rt_runtime == RUNTIME_INF)
+ return 1;
+
+ span = sched_rt_period_mask();
+ for_each_cpu_mask(i, span) {
+ int enqueue = 0;
+ struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
+ struct rq *rq = rq_of_rt_rq(rt_rq);
+
+ spin_lock(&rq->lock);
+ if (rt_rq->rt_time) {
+ u64 runtime;
+
+ spin_lock(&rt_rq->rt_runtime_lock);
+ if (rt_rq->rt_throttled)
+ balance_runtime(rt_rq);
+ runtime = rt_rq->rt_runtime;
+ rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
+ if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
+ rt_rq->rt_throttled = 0;
+ enqueue = 1;
+ }
+ if (rt_rq->rt_time || rt_rq->rt_nr_running)
+ idle = 0;
+ spin_unlock(&rt_rq->rt_runtime_lock);
+ } else if (rt_rq->rt_nr_running)
+ idle = 0;
+
+ if (enqueue)
+ sched_rt_rq_enqueue(rt_rq);
+ spin_unlock(&rq->lock);
+ }
+
+ return idle;
+ }
static inline int rt_se_prio(struct sched_rt_entity *rt_se)
{
if (sched_rt_runtime(rt_rq) >= sched_rt_period(rt_rq))
return 0;
- #ifdef CONFIG_SMP
- if (rt_rq->rt_time > runtime) {
- int more;
-
- spin_unlock(&rt_rq->rt_runtime_lock);
- more = balance_runtime(rt_rq);
- spin_lock(&rt_rq->rt_runtime_lock);
-
- if (more)
- runtime = sched_rt_runtime(rt_rq);
- }
- #endif
+ balance_runtime(rt_rq);
+ runtime = sched_rt_runtime(rt_rq);
+ if (runtime == RUNTIME_INF)
+ return 0;
if (rt_rq->rt_time > runtime) {
rt_rq->rt_throttled = 1;
WARN_ON(!rt_prio(rt_se_prio(rt_se)));
rt_rq->rt_nr_running++;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
- if (rt_se_prio(rt_se) < rt_rq->highest_prio)
+ if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
+ struct rq *rq = rq_of_rt_rq(rt_rq);
+
rt_rq->highest_prio = rt_se_prio(rt_se);
+ #ifdef CONFIG_SMP
+ if (rq->online)
+ cpupri_set(&rq->rd->cpupri, rq->cpu,
+ rt_se_prio(rt_se));
+ #endif
+ }
#endif
#ifdef CONFIG_SMP
if (rt_se->nr_cpus_allowed > 1) {
struct rq *rq = rq_of_rt_rq(rt_rq);
+
rq->rt.rt_nr_migratory++;
}
static inline
void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ #ifdef CONFIG_SMP
+ int highest_prio = rt_rq->highest_prio;
+ #endif
+
WARN_ON(!rt_prio(rt_se_prio(rt_se)));
WARN_ON(!rt_rq->rt_nr_running);
rt_rq->rt_nr_running--;
rq->rt.rt_nr_migratory--;
}
+ if (rt_rq->highest_prio != highest_prio) {
+ struct rq *rq = rq_of_rt_rq(rt_rq);
+
+ if (rq->online)
+ cpupri_set(&rq->rd->cpupri, rq->cpu,
+ rt_rq->highest_prio);
+ }
+
update_rt_migration(rq_of_rt_rq(rt_rq));
#endif /* CONFIG_SMP */
#ifdef CONFIG_RT_GROUP_SCHED
struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
struct rt_prio_array *array = &rt_rq->active;
struct rt_rq *group_rq = group_rt_rq(rt_se);
+ struct list_head *queue = array->queue + rt_se_prio(rt_se);
/*
* Don't enqueue the group if its throttled, or when empty.
if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
return;
- list_add_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se));
+ if (rt_se->nr_cpus_allowed == 1)
+ list_add(&rt_se->run_list, queue);
+ else
+ list_add_tail(&rt_se->run_list, queue);
+
__set_bit(rt_se_prio(rt_se), array->bitmap);
inc_rt_tasks(rt_se, rt_rq);
rt_se->timeout = 0;
enqueue_rt_entity(rt_se);
+
+ inc_cpu_load(rq, p->se.load.weight);
}
static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
update_curr_rt(rq);
dequeue_rt_entity(rt_se);
+
+ dec_cpu_load(rq, p->se.load.weight);
}
/*
void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
{
struct rt_prio_array *array = &rt_rq->active;
- struct list_head *queue = array->queue + rt_se_prio(rt_se);
- if (on_rt_rq(rt_se))
- list_move_tail(&rt_se->run_list, queue);
+ if (on_rt_rq(rt_se)) {
+ list_del_init(&rt_se->run_list);
+ list_add_tail(&rt_se->run_list,
+ array->queue + rt_se_prio(rt_se));
+ }
}
static void requeue_task_rt(struct rq *rq, struct task_struct *p)
*/
static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
{
- if (p->prio < rq->curr->prio)
+ if (p->prio < rq->curr->prio) {
resched_task(rq->curr);
+ return;
+ }
+
+ #ifdef CONFIG_SMP
+ /*
+ * If:
+ *
+ * - the newly woken task is of equal priority to the current task
+ * - the newly woken task is non-migratable while current is migratable
+ * - current will be preempted on the next reschedule
+ *
+ * we should check to see if current can readily move to a different
+ * cpu. If so, we will reschedule to allow the push logic to try
+ * to move current somewhere else, making room for our non-migratable
+ * task.
+ */
+ if((p->prio == rq->curr->prio)
+ && p->rt.nr_cpus_allowed == 1
+ && rq->curr->rt.nr_cpus_allowed != 1) {
+ cpumask_t mask;
+
+ if (cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
+ /*
+ * There appears to be other cpus that can accept
+ * current, so lets reschedule to try and push it away
+ */
+ resched_task(rq->curr);
+ }
+ #endif
}
static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
static DEFINE_PER_CPU(cpumask_t, local_cpu_mask);
- static int find_lowest_cpus(struct task_struct *task, cpumask_t *lowest_mask)
- {
- int lowest_prio = -1;
- int lowest_cpu = -1;
- int count = 0;
- int cpu;
-
- cpus_and(*lowest_mask, task_rq(task)->rd->online, task->cpus_allowed);
-
- /*
- * Scan each rq for the lowest prio.
- */
- for_each_cpu_mask(cpu, *lowest_mask) {
- struct rq *rq = cpu_rq(cpu);
-
- /* We look for lowest RT prio or non-rt CPU */
- if (rq->rt.highest_prio >= MAX_RT_PRIO) {
- /*
- * if we already found a low RT queue
- * and now we found this non-rt queue
- * clear the mask and set our bit.
- * Otherwise just return the queue as is
- * and the count==1 will cause the algorithm
- * to use the first bit found.
- */
- if (lowest_cpu != -1) {
- cpus_clear(*lowest_mask);
- cpu_set(rq->cpu, *lowest_mask);
- }
- return 1;
- }
-
- /* no locking for now */
- if ((rq->rt.highest_prio > task->prio)
- && (rq->rt.highest_prio >= lowest_prio)) {
- if (rq->rt.highest_prio > lowest_prio) {
- /* new low - clear old data */
- lowest_prio = rq->rt.highest_prio;
- lowest_cpu = cpu;
- count = 0;
- }
- count++;
- } else
- cpu_clear(cpu, *lowest_mask);
- }
-
- /*
- * Clear out all the set bits that represent
- * runqueues that were of higher prio than
- * the lowest_prio.
- */
- if (lowest_cpu > 0) {
- /*
- * Perhaps we could add another cpumask op to
- * zero out bits. Like cpu_zero_bits(cpumask, nrbits);
- * Then that could be optimized to use memset and such.
- */
- for_each_cpu_mask(cpu, *lowest_mask) {
- if (cpu >= lowest_cpu)
- break;
- cpu_clear(cpu, *lowest_mask);
- }
- }
-
- return count;
- }
-
static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
{
int first;
cpumask_t *lowest_mask = &__get_cpu_var(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
- int count = find_lowest_cpus(task, lowest_mask);
- if (!count)
- return -1; /* No targets found */
+ if (task->rt.nr_cpus_allowed == 1)
+ return -1; /* No other targets possible */
- /*
- * There is no sense in performing an optimal search if only one
- * target is found.
- */
- if (count == 1)
- return first_cpu(*lowest_mask);
+ if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
+ return -1; /* No targets found */
/*
* At this point we have built a mask of cpus representing the
next = pick_next_task_rt(this_rq);
- for_each_cpu_mask(cpu, this_rq->rd->rto_mask) {
+ for_each_cpu_mask_nr(cpu, this_rq->rd->rto_mask) {
if (this_cpu == cpu)
continue;
}
/* Assumes rq->lock is held */
- static void join_domain_rt(struct rq *rq)
+ static void rq_online_rt(struct rq *rq)
{
if (rq->rt.overloaded)
rt_set_overload(rq);
+
+ __enable_runtime(rq);
+
+ cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio);
}
/* Assumes rq->lock is held */
- static void leave_domain_rt(struct rq *rq)
+ static void rq_offline_rt(struct rq *rq)
{
if (rq->rt.overloaded)
rt_clear_overload(rq);
+
+ __disable_runtime(rq);
+
+ cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID);
}
/*
.load_balance = load_balance_rt,
.move_one_task = move_one_task_rt,
.set_cpus_allowed = set_cpus_allowed_rt,
- .join_domain = join_domain_rt,
- .leave_domain = leave_domain_rt,
+ .rq_online = rq_online_rt,
+ .rq_offline = rq_offline_rt,
.pre_schedule = pre_schedule_rt,
.post_schedule = post_schedule_rt,
.task_wake_up = task_wake_up_rt,
.prio_changed = prio_changed_rt,
.switched_to = switched_to_rt,
};
+
+ #ifdef CONFIG_SCHED_DEBUG
+ extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+
+ static void print_rt_stats(struct seq_file *m, int cpu)
+ {
+ struct rt_rq *rt_rq;
+
+ rcu_read_lock();
+ for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu))
+ print_rt_rq(m, cpu, rt_rq);
+ rcu_read_unlock();
+ }
+ #endif /* CONFIG_SCHED_DEBUG */
struct tick_device tick_broadcast_device;
static cpumask_t tick_broadcast_mask;
static DEFINE_SPINLOCK(tick_broadcast_lock);
+ static int tick_broadcast_force;
#ifdef CONFIG_TICK_ONESHOT
static void tick_broadcast_clear_oneshot(int cpu);
CLOCK_EVT_MODE_SHUTDOWN);
}
if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
- dev->features |= CLOCK_EVT_FEAT_DUMMY;
+ tick_broadcast_force = 1;
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
- if (cpu_isset(cpu, tick_broadcast_mask)) {
+ if (!tick_broadcast_force &&
+ cpu_isset(cpu, tick_broadcast_mask)) {
cpu_clear(cpu, tick_broadcast_mask);
if (td->mode == TICKDEV_MODE_PERIODIC)
tick_setup_periodic(dev, 0);
"offline CPU #%d\n", *oncpu);
else
smp_call_function_single(*oncpu, tick_do_broadcast_on_off,
- &reason, 1, 1);
+ &reason, 1);
}
/*
mask = CPU_MASK_NONE;
now = ktime_get();
/* Find all expired events */
- for (cpu = first_cpu(tick_broadcast_oneshot_mask); cpu != NR_CPUS;
- cpu = next_cpu(cpu, tick_broadcast_oneshot_mask)) {
+ for_each_cpu_mask_nr(cpu, tick_broadcast_oneshot_mask) {
td = &per_cpu(tick_cpu_device, cpu);
if (td->evtdev->next_event.tv64 <= now.tv64)
cpu_set(cpu, mask);
*/
if (!cpus_empty(net_dma.channel_mask)) {
int chan_idx;
- for_each_cpu_mask(chan_idx, net_dma.channel_mask) {
+ for_each_cpu_mask_nr(chan_idx, net_dma.channel_mask) {
struct dma_chan *chan = net_dma.channels[chan_idx];
if (chan)
dma_async_memcpy_issue_pending(chan);
i = 0;
cpu = first_cpu(cpu_online_map);
- for_each_cpu_mask(chan_idx, net_dma->channel_mask) {
+ for_each_cpu_mask_nr(chan_idx, net_dma->channel_mask) {
chan = net_dma->channels[chan_idx];
n = ((num_online_cpus() / cpus_weight(net_dma->channel_mask))
dev_boot_phase = 0;
- open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
- open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);
+ open_softirq(NET_TX_SOFTIRQ, net_tx_action);
+ open_softirq(NET_RX_SOFTIRQ, net_rx_action);
hotcpu_notifier(dev_cpu_callback, 0);
dst_init();
if (cpu_isset(cpu, iucv_buffer_cpumask) &&
!cpu_isset(cpu, iucv_irq_cpumask))
smp_call_function_single(cpu, iucv_allow_cpu,
- NULL, 0, 1);
+ NULL, 1);
preempt_enable();
}
/* Disable all cpu but the first in cpu_irq_cpumask. */
cpumask = iucv_irq_cpumask;
cpu_clear(first_cpu(iucv_irq_cpumask), cpumask);
- for_each_cpu_mask(cpu, cpumask)
+ for_each_cpu_mask_nr(cpu, cpumask)
- smp_call_function_single(cpu, iucv_block_cpu, NULL, 0, 1);
+ smp_call_function_single(cpu, iucv_block_cpu, NULL, 1);
}
/**
rc = -EIO;
preempt_disable();
for_each_online_cpu(cpu)
- smp_call_function_single(cpu, iucv_declare_cpu, NULL, 0, 1);
+ smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1);
preempt_enable();
if (cpus_empty(iucv_buffer_cpumask))
/* No cpu could declare an iucv buffer. */
*/
static void iucv_disable(void)
{
- on_each_cpu(iucv_retrieve_cpu, NULL, 0, 1);
+ on_each_cpu(iucv_retrieve_cpu, NULL, 1);
kfree(iucv_path_table);
}
case CPU_ONLINE_FROZEN:
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- smp_call_function_single(cpu, iucv_declare_cpu, NULL, 0, 1);
+ smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
if (cpus_empty(cpumask))
/* Can't offline last IUCV enabled cpu. */
return NOTIFY_BAD;
- smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 0, 1);
+ smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 1);
if (cpus_empty(iucv_irq_cpumask))
smp_call_function_single(first_cpu(iucv_buffer_cpumask),
- iucv_allow_cpu, NULL, 0, 1);
+ iucv_allow_cpu, NULL, 1);
break;
}
return NOTIFY_OK;
* pending interrupts force them to the work queue by calling
* an empty function on all cpus.
*/
- smp_call_function(__iucv_cleanup_queue, NULL, 0, 1);
+ smp_call_function(__iucv_cleanup_queue, NULL, 1);
spin_lock_irq(&iucv_queue_lock);
list_for_each_entry_safe(p, n, &iucv_task_queue, list) {
/* Remove stale work items from the task queue. */
p = iucv_irq_data[smp_processor_id()];
if (p->ippathid >= iucv_max_pathid) {
- printk(KERN_WARNING "iucv_do_int: Got interrupt with "
- "pathid %d > max_connections (%ld)\n",
- p->ippathid, iucv_max_pathid - 1);
+ WARN_ON(p->ippathid >= iucv_max_pathid);
iucv_sever_pathid(p->ippathid, iucv_error_no_listener);
return;
}
- if (p->iptype < 0x01 || p->iptype > 0x09) {
- printk(KERN_ERR "iucv_do_int: unknown iucv interrupt\n");
- return;
- }
+ BUG_ON(p->iptype < 0x01 || p->iptype > 0x09);
work = kmalloc(sizeof(struct iucv_irq_list), GFP_ATOMIC);
if (!work) {
printk(KERN_WARNING "iucv_external_interrupt: out of memory\n");