#ifdef CONFIG_X86_32
- /* Mappings between node number and cpus on that node. */
- extern cpumask_t node_to_cpumask_map[];
-
/* Mappings between logical cpu number and node number */
extern int cpu_to_node_map[];
}
#define early_cpu_to_node(cpu) cpu_to_node(cpu)
- /* Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used. The
- * cpumask_of_node function should be used whenever possible.
- */
- static inline cpumask_t node_to_cpumask(int node)
- {
- return node_to_cpumask_map[node];
- }
-
- /* Returns a bitmask of CPUs on Node 'node'. */
- static inline const struct cpumask *cpumask_of_node(int node)
- {
- return &node_to_cpumask_map[node];
- }
-
- static inline void setup_node_to_cpumask_map(void) { }
-
#else /* CONFIG_X86_64 */
- /* Mappings between node number and cpus on that node. */
- extern cpumask_t *node_to_cpumask_map;
-
/* Mappings between logical cpu number and node number */
DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
extern int cpu_to_node(int cpu);
extern int early_cpu_to_node(int cpu);
- extern const cpumask_t *cpumask_of_node(int node);
- extern cpumask_t node_to_cpumask(int node);
#else /* !CONFIG_DEBUG_PER_CPU_MAPS */
return early_per_cpu(x86_cpu_to_node_map, cpu);
}
- /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
- static inline const cpumask_t *cpumask_of_node(int node)
- {
- return &node_to_cpumask_map[node];
- }
+ #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+ #endif /* CONFIG_X86_64 */
- /* Returns a bitmask of CPUs on Node 'node'. */
- static inline cpumask_t node_to_cpumask(int node)
+ /* Mappings between node number and cpus on that node. */
+ extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+
+ #ifdef CONFIG_DEBUG_PER_CPU_MAPS
+ extern const struct cpumask *cpumask_of_node(int node);
+ #else
+ /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+ static inline const struct cpumask *cpumask_of_node(int node)
{
return node_to_cpumask_map[node];
}
-
- #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+ #endif
extern void setup_node_to_cpumask_map(void);
- /*
- * Replace default node_to_cpumask_ptr with optimized version
- * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
- */
- #define node_to_cpumask_ptr(v, node) \
- const cpumask_t *v = cpumask_of_node(node)
-
- #define node_to_cpumask_ptr_next(v, node) \
- v = cpumask_of_node(node)
-
- #endif /* CONFIG_X86_64 */
-
/*
* Returns the number of the node containing Node 'node'. This
* architecture is flat, so it is a pretty simple function!
#define parent_node(node) (node)
#define pcibus_to_node(bus) __pcibus_to_node(bus)
- #define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
#ifdef CONFIG_X86_32
extern unsigned long node_start_pfn[];
return 0;
}
- static inline const cpumask_t *cpumask_of_node(int node)
- {
- return &cpu_online_map;
- }
- static inline cpumask_t node_to_cpumask(int node)
+ static inline const struct cpumask *cpumask_of_node(int node)
{
- return cpu_online_map;
+ return cpu_online_mask;
}
-static inline int node_to_first_cpu(int node)
-{
- return cpumask_first(cpu_online_mask);
-}
static inline void setup_node_to_cpumask_map(void) { }
- /*
- * Replace default node_to_cpumask_ptr with optimized version
- * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
- */
- #define node_to_cpumask_ptr(v, node) \
- const cpumask_t *v = cpumask_of_node(node)
-
- #define node_to_cpumask_ptr_next(v, node) \
- v = cpumask_of_node(node)
#endif
#include <asm-generic/topology.h>
- extern cpumask_t cpu_coregroup_map(int cpu);
-#ifdef CONFIG_NUMA
-/* Returns the number of the first CPU on Node 'node'. */
-static inline int node_to_first_cpu(int node)
-{
- return cpumask_first(cpumask_of_node(node));
-}
-#endif
-
extern const struct cpumask *cpu_coregroup_mask(int cpu);
#ifdef ENABLE_TOPO_DEFINES
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
- #define topology_core_siblings(cpu) (per_cpu(cpu_core_map, cpu))
- #define topology_thread_siblings(cpu) (per_cpu(cpu_sibling_map, cpu))
- #define topology_core_cpumask(cpu) (&per_cpu(cpu_core_map, cpu))
- #define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
+ #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
+ #define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
/* indicates that pointers to the topology cpumask_t maps are valid */
#define arch_provides_topology_pointers yes
void set_pci_bus_resources_arch_default(struct pci_bus *b);
#ifdef CONFIG_SMP
- #define mc_capable() (cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids)
+ #define mc_capable() (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
#define smt_capable() (smp_num_siblings > 1)
#endif
* @err: APM BIOS return code
*
* Write a meaningful log entry to the kernel log in the event of
- * an APM error.
+ * an APM error. Note that this also handles (negative) kernel errors.
*/
static void apm_error(char *str, int err)
break;
if (i < ERROR_COUNT)
printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg);
+ else if (err < 0)
+ printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err);
else
printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n",
str, err);
}
- /*
- * Lock APM functionality to physical CPU 0
- */
-
- #ifdef CONFIG_SMP
-
- static cpumask_t apm_save_cpus(void)
- {
- cpumask_t x = current->cpus_allowed;
- /* Some bioses don't like being called from CPU != 0 */
- set_cpus_allowed(current, cpumask_of_cpu(0));
- BUG_ON(smp_processor_id() != 0);
- return x;
- }
-
- static inline void apm_restore_cpus(cpumask_t mask)
- {
- set_cpus_allowed(current, mask);
- }
-
- #else
-
- /*
- * No CPU lockdown needed on a uniprocessor
- */
-
- #define apm_save_cpus() (current->cpus_allowed)
- #define apm_restore_cpus(x) (void)(x)
-
- #endif
-
/*
* These are the actual BIOS calls. Depending on APM_ZERO_SEGS and
* apm_info.allow_ints, we are being really paranoid here! Not only
# define APM_DO_RESTORE_SEGS
#endif
+ struct apm_bios_call {
+ u32 func;
+ /* In and out */
+ u32 ebx;
+ u32 ecx;
+ /* Out only */
+ u32 eax;
+ u32 edx;
+ u32 esi;
+
+ /* Error: -ENOMEM, or bits 8-15 of eax */
+ int err;
+ };
+
/**
- * apm_bios_call - Make an APM BIOS 32bit call
- * @func: APM function to execute
- * @ebx_in: EBX register for call entry
- * @ecx_in: ECX register for call entry
- * @eax: EAX register return
- * @ebx: EBX register return
- * @ecx: ECX register return
- * @edx: EDX register return
- * @esi: ESI register return
+ * __apm_bios_call - Make an APM BIOS 32bit call
+ * @_call: pointer to struct apm_bios_call.
*
* Make an APM call using the 32bit protected mode interface. The
* caller is responsible for knowing if APM BIOS is configured and
* flag is loaded into AL. If there is an error, then the error
* code is returned in AH (bits 8-15 of eax) and this function
* returns non-zero.
+ *
+ * Note: this makes the call on the current CPU.
*/
-
- static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
- u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi)
+ static long __apm_bios_call(void *_call)
{
APM_DECL_SEGS
unsigned long flags;
- cpumask_t cpus;
int cpu;
struct desc_struct save_desc_40;
struct desc_struct *gdt;
-
- cpus = apm_save_cpus();
+ struct apm_bios_call *call = _call;
cpu = get_cpu();
+ BUG_ON(cpu != 0);
gdt = get_cpu_gdt_table(cpu);
save_desc_40 = gdt[0x40 / 8];
gdt[0x40 / 8] = bad_bios_desc;
apm_irq_save(flags);
APM_DO_SAVE_SEGS;
- apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi);
+ apm_bios_call_asm(call->func, call->ebx, call->ecx,
+ &call->eax, &call->ebx, &call->ecx, &call->edx,
+ &call->esi);
APM_DO_RESTORE_SEGS;
apm_irq_restore(flags);
gdt[0x40 / 8] = save_desc_40;
put_cpu();
- apm_restore_cpus(cpus);
- return *eax & 0xff;
+ return call->eax & 0xff;
+ }
+
+ /* Run __apm_bios_call or __apm_bios_call_simple on CPU 0 */
+ static int on_cpu0(long (*fn)(void *), struct apm_bios_call *call)
+ {
+ int ret;
+
+ /* Don't bother with work_on_cpu in the common case, so we don't
+ * have to worry about OOM or overhead. */
+ if (get_cpu() == 0) {
+ ret = fn(call);
+ put_cpu();
+ } else {
+ put_cpu();
+ ret = work_on_cpu(0, fn, call);
+ }
+
+ /* work_on_cpu can fail with -ENOMEM */
+ if (ret < 0)
+ call->err = ret;
+ else
+ call->err = (call->eax >> 8) & 0xff;
+
+ return ret;
}
/**
- * apm_bios_call_simple - make a simple APM BIOS 32bit call
- * @func: APM function to invoke
- * @ebx_in: EBX register value for BIOS call
- * @ecx_in: ECX register value for BIOS call
- * @eax: EAX register on return from the BIOS call
+ * apm_bios_call - Make an APM BIOS 32bit call (on CPU 0)
+ * @call: the apm_bios_call registers.
+ *
+ * If there is an error, it is returned in @call.err.
+ */
+ static int apm_bios_call(struct apm_bios_call *call)
+ {
+ return on_cpu0(__apm_bios_call, call);
+ }
+
+ /**
+ * __apm_bios_call_simple - Make an APM BIOS 32bit call (on CPU 0)
+ * @_call: pointer to struct apm_bios_call.
*
* Make a BIOS call that returns one value only, or just status.
* If there is an error, then the error code is returned in AH
- * (bits 8-15 of eax) and this function returns non-zero. This is
- * used for simpler BIOS operations. This call may hold interrupts
- * off for a long time on some laptops.
+ * (bits 8-15 of eax) and this function returns non-zero (it can
+ * also return -ENOMEM). This is used for simpler BIOS operations.
+ * This call may hold interrupts off for a long time on some laptops.
+ *
+ * Note: this makes the call on the current CPU.
*/
-
- static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
+ static long __apm_bios_call_simple(void *_call)
{
u8 error;
APM_DECL_SEGS
unsigned long flags;
- cpumask_t cpus;
int cpu;
struct desc_struct save_desc_40;
struct desc_struct *gdt;
-
- cpus = apm_save_cpus();
+ struct apm_bios_call *call = _call;
cpu = get_cpu();
+ BUG_ON(cpu != 0);
gdt = get_cpu_gdt_table(cpu);
save_desc_40 = gdt[0x40 / 8];
gdt[0x40 / 8] = bad_bios_desc;
apm_irq_save(flags);
APM_DO_SAVE_SEGS;
- error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax);
+ error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
+ &call->eax);
APM_DO_RESTORE_SEGS;
apm_irq_restore(flags);
gdt[0x40 / 8] = save_desc_40;
put_cpu();
- apm_restore_cpus(cpus);
return error;
}
+ /**
+ * apm_bios_call_simple - make a simple APM BIOS 32bit call
+ * @func: APM function to invoke
+ * @ebx_in: EBX register value for BIOS call
+ * @ecx_in: ECX register value for BIOS call
+ * @eax: EAX register on return from the BIOS call
+ * @err: bits
+ *
+ * Make a BIOS call that returns one value only, or just status.
+ * If there is an error, then the error code is returned in @err
+ * and this function returns non-zero. This is used for simpler
+ * BIOS operations. This call may hold interrupts off for a long
+ * time on some laptops.
+ */
+ static int apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax,
+ int *err)
+ {
+ struct apm_bios_call call;
+ int ret;
+
+ call.func = func;
+ call.ebx = ebx_in;
+ call.ecx = ecx_in;
+
+ ret = on_cpu0(__apm_bios_call_simple, &call);
+ *eax = call.eax;
+ *err = call.err;
+ return ret;
+ }
+
/**
* apm_driver_version - APM driver version
* @val: loaded with the APM version on return
static int apm_driver_version(u_short *val)
{
u32 eax;
+ int err;
- if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax))
- return (eax >> 8) & 0xff;
+ if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax, &err))
+ return err;
*val = eax;
return APM_SUCCESS;
}
* that APM 1.2 is in use. If no messges are pending the value 0x80
* is returned (No power management events pending).
*/
-
static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
{
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 dummy;
+ struct apm_bios_call call;
- if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx,
- &dummy, &dummy))
- return (eax >> 8) & 0xff;
- *event = ebx;
+ call.func = APM_FUNC_GET_EVENT;
+ call.ebx = call.ecx = 0;
+
+ if (apm_bios_call(&call))
+ return call.err;
+
+ *event = call.ebx;
if (apm_info.connection_version < 0x0102)
*info = ~0; /* indicate info not valid */
else
- *info = ecx;
+ *info = call.ecx;
return APM_SUCCESS;
}
static int set_power_state(u_short what, u_short state)
{
u32 eax;
+ int err;
- if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax))
- return (eax >> 8) & 0xff;
+ if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax, &err))
+ return err;
return APM_SUCCESS;
}
u8 ret = 0;
int idled = 0;
int polling;
+ int err;
polling = !!(current_thread_info()->status & TS_POLLING);
if (polling) {
}
if (!need_resched()) {
idled = 1;
- ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax);
+ ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err);
}
if (polling)
current_thread_info()->status |= TS_POLLING;
* Only report the failure the first 5 times.
*/
if (++t < 5) {
- printk(KERN_DEBUG "apm_do_idle failed (%d)\n",
- (eax >> 8) & 0xff);
+ printk(KERN_DEBUG "apm_do_idle failed (%d)\n", err);
t = jiffies;
}
return -1;
static void apm_do_busy(void)
{
u32 dummy;
+ int err;
if (clock_slowed || ALWAYS_CALL_BUSY) {
- (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy);
+ (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy, &err);
clock_slowed = 0;
}
}
/* Some bioses don't like being called from CPU != 0 */
if (apm_info.realmode_power_off) {
- (void)apm_save_cpus();
+ set_cpus_allowed_ptr(current, cpumask_of(0));
machine_real_restart(po_bios_call, sizeof(po_bios_call));
} else {
(void)set_system_power_state(APM_STATE_OFF);
static int apm_enable_power_management(int enable)
{
u32 eax;
+ int err;
if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED))
return APM_NOT_ENGAGED;
if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL,
- enable, &eax))
- return (eax >> 8) & 0xff;
+ enable, &eax, &err))
+ return err;
if (enable)
apm_info.bios.flags &= ~APM_BIOS_DISABLED;
else
static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
{
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 edx;
- u32 dummy;
+ struct apm_bios_call call;
+
+ call.func = APM_FUNC_GET_STATUS;
+ call.ebx = APM_DEVICE_ALL;
+ call.ecx = 0;
if (apm_info.get_power_status_broken)
return APM_32_UNSUPPORTED;
- if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0,
- &eax, &ebx, &ecx, &edx, &dummy))
- return (eax >> 8) & 0xff;
- *status = ebx;
- *bat = ecx;
+ if (apm_bios_call(&call))
+ return call.err;
+ *status = call.ebx;
+ *bat = call.ecx;
if (apm_info.get_power_status_swabinminutes) {
- *life = swab16((u16)edx);
+ *life = swab16((u16)call.edx);
*life |= 0x8000;
} else
- *life = edx;
+ *life = call.edx;
return APM_SUCCESS;
}
static int apm_engage_power_management(u_short device, int enable)
{
u32 eax;
+ int err;
if ((enable == 0) && (device == APM_DEVICE_ALL)
&& (apm_info.bios.flags & APM_BIOS_DISABLED))
return APM_DISABLED;
- if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax))
- return (eax >> 8) & 0xff;
+ if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable,
+ &eax, &err))
+ return err;
if (device == APM_DEVICE_ALL) {
if (enable)
apm_info.bios.flags &= ~APM_BIOS_DISENGAGED;
struct apm_user *as;
device_suspend(PMSG_SUSPEND);
- local_irq_disable();
+
device_power_down(PMSG_SUSPEND);
+
+ local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
local_irq_enable();
if (err != APM_SUCCESS)
apm_error("suspend", err);
err = (err == APM_SUCCESS) ? 0 : -EIO;
+
sysdev_resume();
- device_power_up(PMSG_RESUME);
local_irq_enable();
+
+ device_power_up(PMSG_RESUME);
+
device_resume(PMSG_RESUME);
queue_event(APM_NORMAL_RESUME, NULL);
spin_lock(&user_list_lock);
{
int err;
- local_irq_disable();
device_power_down(PMSG_SUSPEND);
+
+ local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
local_irq_enable();
local_irq_disable();
sysdev_resume();
- device_power_up(PMSG_RESUME);
local_irq_enable();
+
+ device_power_up(PMSG_RESUME);
}
static apm_event_t get_event(void)
char *power_stat;
char *bat_stat;
- #ifdef CONFIG_SMP
/* 2002/08/01 - WT
* This is to avoid random crashes at boot time during initialization
* on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D.
* Some bioses don't like being called from CPU != 0.
* Method suggested by Ingo Molnar.
*/
- set_cpus_allowed(current, cpumask_of_cpu(0));
+ set_cpus_allowed_ptr(current, cpumask_of(0));
BUG_ON(smp_processor_id() != 0);
- #endif
if (apm_info.connection_version == 0) {
apm_info.connection_version = apm_info.bios.version;
node = dev_to_node(&dev->dev);
if (node >= 0) {
int cpu;
- node_to_cpumask_ptr(nodecpumask, node);
get_online_cpus();
- cpu = cpumask_any_and(nodecpumask, cpu_online_mask);
+ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
if (cpu < nr_cpu_ids)
error = work_on_cpu(cpu, local_pci_probe, &ddi);
else
{
struct pci_dev * pci_dev = to_pci_dev(dev);
struct pci_driver * drv = pci_dev->driver;
- int i = 0;
+
+ pci_dev->state_saved = false;
if (drv && drv->suspend) {
pci_power_t prev = pci_dev->current_state;
+ int error;
- pci_dev->state_saved = false;
-
- i = drv->suspend(pci_dev, state);
- suspend_report_result(drv->suspend, i);
- if (i)
- return i;
-
- if (pci_dev->state_saved)
- goto Fixup;
+ error = drv->suspend(pci_dev, state);
+ suspend_report_result(drv->suspend, error);
+ if (error)
+ return error;
- if (pci_dev->current_state != PCI_D0
+ if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
&& pci_dev->current_state != PCI_UNKNOWN) {
WARN_ONCE(pci_dev->current_state != prev,
"PCI PM: Device state not saved by %pF\n",
drv->suspend);
- goto Fixup;
}
}
- pci_save_state(pci_dev);
- /*
- * This is for compatibility with existing code with legacy PM support.
- */
- pci_pm_set_unknown_state(pci_dev);
-
- Fixup:
pci_fixup_device(pci_fixup_suspend, pci_dev);
- return i;
+ return 0;
}
static int pci_legacy_suspend_late(struct device *dev, pm_message_t state)
{
struct pci_dev * pci_dev = to_pci_dev(dev);
struct pci_driver * drv = pci_dev->driver;
- int i = 0;
if (drv && drv->suspend_late) {
- i = drv->suspend_late(pci_dev, state);
- suspend_report_result(drv->suspend_late, i);
+ pci_power_t prev = pci_dev->current_state;
+ int error;
+
+ error = drv->suspend_late(pci_dev, state);
+ suspend_report_result(drv->suspend_late, error);
+ if (error)
+ return error;
+
+ if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+ && pci_dev->current_state != PCI_UNKNOWN) {
+ WARN_ONCE(pci_dev->current_state != prev,
+ "PCI PM: Device state not saved by %pF\n",
+ drv->suspend_late);
+ return 0;
+ }
}
- return i;
+
+ if (!pci_dev->state_saved)
+ pci_save_state(pci_dev);
+
+ pci_pm_set_unknown_state(pci_dev);
+
+ return 0;
}
static int pci_legacy_resume_early(struct device *dev)
/* Auxiliary functions used by the new power management framework */
+/**
+ * pci_restore_standard_config - restore standard config registers of PCI device
+ * @pci_dev: PCI device to handle
+ */
+static int pci_restore_standard_config(struct pci_dev *pci_dev)
+{
+ pci_update_current_state(pci_dev, PCI_UNKNOWN);
+
+ if (pci_dev->current_state != PCI_D0) {
+ int error = pci_set_power_state(pci_dev, PCI_D0);
+ if (error)
+ return error;
+ }
+
+ return pci_dev->state_saved ? pci_restore_state(pci_dev) : 0;
+}
+
static void pci_pm_default_resume_noirq(struct pci_dev *pci_dev)
{
pci_restore_standard_config(pci_dev);
/* Disable non-bridge devices without PM support */
if (!pci_is_bridge(pci_dev))
pci_disable_enabled_device(pci_dev);
- pci_save_state(pci_dev);
}
static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev)
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_SUSPEND);
+ pci_dev->state_saved = false;
+
if (!pm) {
pci_pm_default_suspend(pci_dev);
goto Fixup;
}
- pci_dev->state_saved = false;
-
if (pm->suspend) {
pci_power_t prev = pci_dev->current_state;
int error;
if (error)
return error;
- if (pci_dev->state_saved)
- goto Fixup;
-
- if (pci_dev->current_state != PCI_D0
+ if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
&& pci_dev->current_state != PCI_UNKNOWN) {
WARN_ONCE(pci_dev->current_state != prev,
"PCI PM: State of device not saved by %pF\n",
pm->suspend);
- goto Fixup;
}
}
- if (!pci_dev->state_saved) {
- pci_save_state(pci_dev);
- if (!pci_is_bridge(pci_dev))
- pci_prepare_to_sleep(pci_dev);
- }
-
Fixup:
pci_fixup_device(pci_fixup_suspend, pci_dev);
static int pci_pm_suspend_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- struct device_driver *drv = dev->driver;
- int error = 0;
+ struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend_late(dev, PMSG_SUSPEND);
- if (drv && drv->pm && drv->pm->suspend_noirq) {
- error = drv->pm->suspend_noirq(dev);
- suspend_report_result(drv->pm->suspend_noirq, error);
+ if (!pm) {
+ pci_save_state(pci_dev);
+ return 0;
}
- if (!error)
- pci_pm_set_unknown_state(pci_dev);
+ if (pm->suspend_noirq) {
+ pci_power_t prev = pci_dev->current_state;
+ int error;
- return error;
+ error = pm->suspend_noirq(dev);
+ suspend_report_result(pm->suspend_noirq, error);
+ if (error)
+ return error;
+
+ if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+ && pci_dev->current_state != PCI_UNKNOWN) {
+ WARN_ONCE(pci_dev->current_state != prev,
+ "PCI PM: State of device not saved by %pF\n",
+ pm->suspend_noirq);
+ return 0;
+ }
+ }
+
+ if (!pci_dev->state_saved) {
+ pci_save_state(pci_dev);
+ if (!pci_is_bridge(pci_dev))
+ pci_prepare_to_sleep(pci_dev);
+ }
+
+ pci_pm_set_unknown_state(pci_dev);
+
+ return 0;
}
static int pci_pm_resume_noirq(struct device *dev)
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_FREEZE);
+ pci_dev->state_saved = false;
+
if (!pm) {
pci_pm_default_suspend(pci_dev);
return 0;
}
- pci_dev->state_saved = false;
-
if (pm->freeze) {
int error;
return error;
}
- if (!pci_dev->state_saved)
- pci_save_state(pci_dev);
-
return 0;
}
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct device_driver *drv = dev->driver;
- int error = 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend_late(dev, PMSG_FREEZE);
if (drv && drv->pm && drv->pm->freeze_noirq) {
+ int error;
+
error = drv->pm->freeze_noirq(dev);
suspend_report_result(drv->pm->freeze_noirq, error);
+ if (error)
+ return error;
}
- if (!error)
- pci_pm_set_unknown_state(pci_dev);
+ if (!pci_dev->state_saved)
+ pci_save_state(pci_dev);
- return error;
+ pci_pm_set_unknown_state(pci_dev);
+
+ return 0;
}
static int pci_pm_thaw_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
- int error = 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_HIBERNATE);
+ pci_dev->state_saved = false;
+
if (!pm) {
pci_pm_default_suspend(pci_dev);
goto Fixup;
}
- pci_dev->state_saved = false;
-
if (pm->poweroff) {
+ int error;
+
error = pm->poweroff(dev);
suspend_report_result(pm->poweroff, error);
+ if (error)
+ return error;
}
- if (!pci_dev->state_saved && !pci_is_bridge(pci_dev))
- pci_prepare_to_sleep(pci_dev);
-
Fixup:
pci_fixup_device(pci_fixup_suspend, pci_dev);
- return error;
+ return 0;
}
static int pci_pm_poweroff_noirq(struct device *dev)
{
+ struct pci_dev *pci_dev = to_pci_dev(dev);
struct device_driver *drv = dev->driver;
- int error = 0;
if (pci_has_legacy_pm_support(to_pci_dev(dev)))
return pci_legacy_suspend_late(dev, PMSG_HIBERNATE);
- if (drv && drv->pm && drv->pm->poweroff_noirq) {
+ if (!drv || !drv->pm)
+ return 0;
+
+ if (drv->pm->poweroff_noirq) {
+ int error;
+
error = drv->pm->poweroff_noirq(dev);
suspend_report_result(drv->pm->poweroff_noirq, error);
+ if (error)
+ return error;
}
- return error;
+ if (!pci_dev->state_saved && !pci_is_bridge(pci_dev))
+ pci_prepare_to_sleep(pci_dev);
+
+ return 0;
}
static int pci_pm_restore_noirq(struct device *dev)
*/
#define MAX_PINNED_INTERVAL 512
+ /* Working cpumask for load_balance and load_balance_newidle. */
+ static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+
/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
*/
static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
- int *balance, struct cpumask *cpus)
+ int *balance)
{
int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
unsigned long flags;
+ struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
cpumask_setall(cpus);
* this_rq is locked.
*/
static int
- load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
- struct cpumask *cpus)
+ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
{
struct sched_group *group;
struct rq *busiest = NULL;
int ld_moved = 0;
int sd_idle = 0;
int all_pinned = 0;
+ struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
cpumask_setall(cpus);
struct sched_domain *sd;
int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
- cpumask_var_t tmpmask;
-
- if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
- return;
for_each_domain(this_cpu, sd) {
unsigned long interval;
if (sd->flags & SD_BALANCE_NEWIDLE)
/* If we've pulled tasks over stop searching: */
pulled_task = load_balance_newidle(this_cpu, this_rq,
- sd, tmpmask);
+ sd);
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
*/
this_rq->next_balance = next_balance;
}
- free_cpumask_var(tmpmask);
}
/*
unsigned long next_balance = jiffies + 60*HZ;
int update_next_balance = 0;
int need_serialize;
- cpumask_var_t tmp;
-
- /* Fails alloc? Rebalancing probably not a priority right now. */
- if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
- return;
for_each_domain(cpu, sd) {
if (!(sd->flags & SD_LOAD_BALANCE))
}
if (time_after_eq(jiffies, sd->last_balance + interval)) {
- if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
+ if (load_balance(cpu, rq, sd, idle, &balance)) {
/*
* We've pulled tasks over so either we're no
* longer idle, or one of our SMT siblings is
*/
if (likely(update_next_balance))
rq->next_balance = next_balance;
-
- free_cpumask_var(tmp);
}
/*
/*
* schedule() is the main scheduler function.
*/
-asmlinkage void __sched schedule(void)
+asmlinkage void __sched __schedule(void)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
-need_resched:
- preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
rcu_qsctr_inc(cpu);
if (unlikely(reacquire_kernel_lock(current) < 0))
goto need_resched_nonpreemptible;
+}
+asmlinkage void __sched schedule(void)
+{
+need_resched:
+ preempt_disable();
+ __schedule();
preempt_enable_no_resched();
if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
goto need_resched;
}
EXPORT_SYMBOL(schedule);
+#ifdef CONFIG_SMP
+/*
+ * Look out! "owner" is an entirely speculative pointer
+ * access and not reliable.
+ */
+int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
+{
+ unsigned int cpu;
+ struct rq *rq;
+
+ if (!sched_feat(OWNER_SPIN))
+ return 0;
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ /*
+ * Need to access the cpu field knowing that
+ * DEBUG_PAGEALLOC could have unmapped it if
+ * the mutex owner just released it and exited.
+ */
+ if (probe_kernel_address(&owner->cpu, cpu))
+ goto out;
+#else
+ cpu = owner->cpu;
+#endif
+
+ /*
+ * Even if the access succeeded (likely case),
+ * the cpu field may no longer be valid.
+ */
+ if (cpu >= nr_cpumask_bits)
+ goto out;
+
+ /*
+ * We need to validate that we can do a
+ * get_cpu() and that we have the percpu area.
+ */
+ if (!cpu_online(cpu))
+ goto out;
+
+ rq = cpu_rq(cpu);
+
+ for (;;) {
+ /*
+ * Owner changed, break to re-assess state.
+ */
+ if (lock->owner != owner)
+ break;
+
+ /*
+ * Is that owner really running on that cpu?
+ */
+ if (task_thread_info(rq->curr) != owner || need_resched())
+ return 0;
+
+ cpu_relax();
+ }
+out:
+ return 1;
+}
+#endif
+
#ifdef CONFIG_PREEMPT
/*
* this is the entry point to schedule() from in-kernel preemption
{
int group;
- cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+ cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
group = cpumask_first(mask);
if (sg)
*sg = &per_cpu(sched_group_core, group).sg;
cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
group = cpumask_first(mask);
#elif defined(CONFIG_SCHED_SMT)
- cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+ cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
group = cpumask_first(mask);
#else
group = cpu;
SD_INIT(sd, SIBLING);
set_domain_attribute(sd, attr);
cpumask_and(sched_domain_span(sd),
- &per_cpu(cpu_sibling_map, i), cpu_map);
+ topology_thread_cpumask(i), cpu_map);
sd->parent = p;
p->child = sd;
cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
/* Set up CPU (sibling) groups */
for_each_cpu(i, cpu_map) {
cpumask_and(this_sibling_map,
- &per_cpu(cpu_sibling_map, i), cpu_map);
+ topology_thread_cpumask(i), cpu_map);
if (i != cpumask_first(this_sibling_map))
continue;
#endif
#ifdef CONFIG_USER_SCHED
alloc_size *= 2;
+ #endif
+ #ifdef CONFIG_CPUMASK_OFFSTACK
+ alloc_size += num_possible_cpus() * cpumask_size();
#endif
/*
* As sched_init() is called before page_alloc is setup,
ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_RT_GROUP_SCHED */
+ #ifdef CONFIG_CPUMASK_OFFSTACK
+ for_each_possible_cpu(i) {
+ per_cpu(load_balance_tmpmask, i) = (void *)ptr;
+ ptr += cpumask_size();
+ }
+ #endif /* CONFIG_CPUMASK_OFFSTACK */
}
#ifdef CONFIG_SMP
unsigned long did_some_progress;
unsigned long pages_reclaimed = 0;
+ lockdep_trace_alloc(gfp_mask);
+
might_sleep_if(wait);
if (should_fail_alloc_page(gfp_mask, order))
*/
cpuset_update_task_memory_state();
p->flags |= PF_MEMALLOC;
+
+ lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
p->reclaim_state = NULL;
+ lockdep_clear_current_reclaim_state();
p->flags &= ~PF_MEMALLOC;
cond_resched();
int n, val;
int min_val = INT_MAX;
int best_node = -1;
- node_to_cpumask_ptr(tmp, 0);
+ const struct cpumask *tmp = cpumask_of_node(0);
/* Use the local node if we haven't already */
if (!node_isset(node, *used_node_mask)) {
val += (n < node);
/* Give preference to headless and unused nodes */
- node_to_cpumask_ptr_next(tmp, n);
- if (!cpus_empty(*tmp))
+ tmp = cpumask_of_node(n);
+ if (!cpumask_empty(tmp))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
struct kmem_cache *cachep;
struct kmem_list3 *l3 = NULL;
int node = cpu_to_node(cpu);
- node_to_cpumask_ptr(mask, node);
+ const struct cpumask *mask = cpumask_of_node(node);
list_for_each_entry(cachep, &cache_chain, next) {
struct array_cache *nc;
unsigned long save_flags;
void *ptr;
+ lockdep_trace_alloc(flags);
+
if (slab_should_failslab(cachep, flags))
return NULL;
unsigned long save_flags;
void *objp;
+ lockdep_trace_alloc(flags);
+
if (slab_should_failslab(cachep, flags))
return NULL;
struct reclaim_state reclaim_state = {
.reclaimed_slab = 0,
};
- node_to_cpumask_ptr(cpumask, pgdat->node_id);
+ const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+ lockdep_set_current_reclaim_state(GFP_KERNEL);
+
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(tsk, cpumask);
current->reclaim_state = &reclaim_state;
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
for_each_node_state(nid, N_HIGH_MEMORY) {
pg_data_t *pgdat = NODE_DATA(nid);
- node_to_cpumask_ptr(mask, pgdat->node_id);
+ const struct cpumask *mask;
+
+ mask = cpumask_of_node(pgdat->node_id);
if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
/* One of our CPUs online: restore mask */
switch (m->mode) {
case SVC_POOL_PERCPU:
{
- set_cpus_allowed_ptr(task, &cpumask_of_cpu(node));
+ set_cpus_allowed_ptr(task, cpumask_of(node));
break;
}
case SVC_POOL_PERNODE:
{
- node_to_cpumask_ptr(nodecpumask, node);
- set_cpus_allowed_ptr(task, nodecpumask);
+ set_cpus_allowed_ptr(task, cpumask_of_node(node));
break;
}
}