#ifdef CONFIG_SMP
-#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
-
/* minimum unit size, also is the maximum supported allocation size */
#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(64 << 10)
#define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
extern void *__alloc_reserved_percpu(size_t size, size_t align);
-
-#else /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
-struct percpu_data {
- void *ptrs[1];
-};
-
-/* pointer disguising messes up the kmemleak objects tracking */
-#ifndef CONFIG_DEBUG_KMEMLEAK
-#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
-#else
-#define __percpu_disguise(pdata) (struct percpu_data *)(pdata)
-#endif
-
-#define per_cpu_ptr(ptr, cpu) \
-({ \
- struct percpu_data *__p = __percpu_disguise(ptr); \
- (__typeof__(ptr))__p->ptrs[(cpu)]; \
-})
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
extern void *__alloc_percpu(size_t size, size_t align);
extern void free_percpu(void *__pdata);
+ extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
extern void __init setup_per_cpu_areas(void);
kfree(p);
}
+ static inline phys_addr_t per_cpu_ptr_to_phys(void *addr)
+ {
+ return __pa(addr);
+ }
+
static inline void __init setup_per_cpu_areas(void) { }
static inline void *pcpu_lpage_remapped(void *kaddr)
#endif /* CONFIG_SMP */
-#define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type), \
- __alignof__(type))
+#define alloc_percpu(type) \
+ (typeof(type) *)__alloc_percpu(sizeof(type), __alignof__(type))
/*
* Optional methods for optimized non-lvalue per-cpu variable access.
# define percpu_xor(var, val) __percpu_generic_to_op(var, (val), ^=)
#endif
+/*
+ * Branching function to split up a function into a set of functions that
+ * are called for different scalar sizes of the objects handled.
+ */
+
+extern void __bad_size_call_parameter(void);
+
+#define __pcpu_size_call_return(stem, variable) \
+({ typeof(variable) pscr_ret__; \
+ switch(sizeof(variable)) { \
+ case 1: pscr_ret__ = stem##1(variable);break; \
+ case 2: pscr_ret__ = stem##2(variable);break; \
+ case 4: pscr_ret__ = stem##4(variable);break; \
+ case 8: pscr_ret__ = stem##8(variable);break; \
+ default: \
+ __bad_size_call_parameter();break; \
+ } \
+ pscr_ret__; \
+})
+
+#define __pcpu_size_call(stem, variable, ...) \
+do { \
+ switch(sizeof(variable)) { \
+ case 1: stem##1(variable, __VA_ARGS__);break; \
+ case 2: stem##2(variable, __VA_ARGS__);break; \
+ case 4: stem##4(variable, __VA_ARGS__);break; \
+ case 8: stem##8(variable, __VA_ARGS__);break; \
+ default: \
+ __bad_size_call_parameter();break; \
+ } \
+} while (0)
+
+/*
+ * Optimized manipulation for memory allocated through the per cpu
+ * allocator or for addresses of per cpu variables (can be determined
+ * using per_cpu_var(xx).
+ *
+ * These operation guarantee exclusivity of access for other operations
+ * on the *same* processor. The assumption is that per cpu data is only
+ * accessed by a single processor instance (the current one).
+ *
+ * The first group is used for accesses that must be done in a
+ * preemption safe way since we know that the context is not preempt
+ * safe. Interrupts may occur. If the interrupt modifies the variable
+ * too then RMW actions will not be reliable.
+ *
+ * The arch code can provide optimized functions in two ways:
+ *
+ * 1. Override the function completely. F.e. define this_cpu_add().
+ * The arch must then ensure that the various scalar format passed
+ * are handled correctly.
+ *
+ * 2. Provide functions for certain scalar sizes. F.e. provide
+ * this_cpu_add_2() to provide per cpu atomic operations for 2 byte
+ * sized RMW actions. If arch code does not provide operations for
+ * a scalar size then the fallback in the generic code will be
+ * used.
+ */
+
+#define _this_cpu_generic_read(pcp) \
+({ typeof(pcp) ret__; \
+ preempt_disable(); \
+ ret__ = *this_cpu_ptr(&(pcp)); \
+ preempt_enable(); \
+ ret__; \
+})
+
+#ifndef this_cpu_read
+# ifndef this_cpu_read_1
+# define this_cpu_read_1(pcp) _this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_2
+# define this_cpu_read_2(pcp) _this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_4
+# define this_cpu_read_4(pcp) _this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_8
+# define this_cpu_read_8(pcp) _this_cpu_generic_read(pcp)
+# endif
+# define this_cpu_read(pcp) __pcpu_size_call_return(this_cpu_read_, (pcp))
+#endif
+
+#define _this_cpu_generic_to_op(pcp, val, op) \
+do { \
+ preempt_disable(); \
+ *__this_cpu_ptr(&pcp) op val; \
+ preempt_enable(); \
+} while (0)
+
+#ifndef this_cpu_write
+# ifndef this_cpu_write_1
+# define this_cpu_write_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_2
+# define this_cpu_write_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_4
+# define this_cpu_write_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_8
+# define this_cpu_write_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# define this_cpu_write(pcp, val) __pcpu_size_call(this_cpu_write_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_add
+# ifndef this_cpu_add_1
+# define this_cpu_add_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_2
+# define this_cpu_add_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_4
+# define this_cpu_add_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_8
+# define this_cpu_add_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define this_cpu_add(pcp, val) __pcpu_size_call(this_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_sub
+# define this_cpu_sub(pcp, val) this_cpu_add((pcp), -(val))
+#endif
+
+#ifndef this_cpu_inc
+# define this_cpu_inc(pcp) this_cpu_add((pcp), 1)
+#endif
+
+#ifndef this_cpu_dec
+# define this_cpu_dec(pcp) this_cpu_sub((pcp), 1)
+#endif
+
+#ifndef this_cpu_and
+# ifndef this_cpu_and_1
+# define this_cpu_and_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_2
+# define this_cpu_and_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_4
+# define this_cpu_and_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_8
+# define this_cpu_and_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define this_cpu_and(pcp, val) __pcpu_size_call(this_cpu_and_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_or
+# ifndef this_cpu_or_1
+# define this_cpu_or_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_2
+# define this_cpu_or_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_4
+# define this_cpu_or_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_8
+# define this_cpu_or_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define this_cpu_or(pcp, val) __pcpu_size_call(this_cpu_or_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_xor
+# ifndef this_cpu_xor_1
+# define this_cpu_xor_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_2
+# define this_cpu_xor_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_4
+# define this_cpu_xor_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_8
+# define this_cpu_xor_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define this_cpu_xor(pcp, val) __pcpu_size_call(this_cpu_or_, (pcp), (val))
+#endif
+
+/*
+ * Generic percpu operations that do not require preemption handling.
+ * Either we do not care about races or the caller has the
+ * responsibility of handling preemptions issues. Arch code can still
+ * override these instructions since the arch per cpu code may be more
+ * efficient and may actually get race freeness for free (that is the
+ * case for x86 for example).
+ *
+ * If there is no other protection through preempt disable and/or
+ * disabling interupts then one of these RMW operations can show unexpected
+ * behavior because the execution thread was rescheduled on another processor
+ * or an interrupt occurred and the same percpu variable was modified from
+ * the interrupt context.
+ */
+#ifndef __this_cpu_read
+# ifndef __this_cpu_read_1
+# define __this_cpu_read_1(pcp) (*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_2
+# define __this_cpu_read_2(pcp) (*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_4
+# define __this_cpu_read_4(pcp) (*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_8
+# define __this_cpu_read_8(pcp) (*__this_cpu_ptr(&(pcp)))
+# endif
+# define __this_cpu_read(pcp) __pcpu_size_call_return(__this_cpu_read_, (pcp))
+#endif
+
+#define __this_cpu_generic_to_op(pcp, val, op) \
+do { \
+ *__this_cpu_ptr(&(pcp)) op val; \
+} while (0)
+
+#ifndef __this_cpu_write
+# ifndef __this_cpu_write_1
+# define __this_cpu_write_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_2
+# define __this_cpu_write_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_4
+# define __this_cpu_write_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_8
+# define __this_cpu_write_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# define __this_cpu_write(pcp, val) __pcpu_size_call(__this_cpu_write_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_add
+# ifndef __this_cpu_add_1
+# define __this_cpu_add_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_2
+# define __this_cpu_add_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_4
+# define __this_cpu_add_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_8
+# define __this_cpu_add_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define __this_cpu_add(pcp, val) __pcpu_size_call(__this_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_sub
+# define __this_cpu_sub(pcp, val) __this_cpu_add((pcp), -(val))
+#endif
+
+#ifndef __this_cpu_inc
+# define __this_cpu_inc(pcp) __this_cpu_add((pcp), 1)
+#endif
+
+#ifndef __this_cpu_dec
+# define __this_cpu_dec(pcp) __this_cpu_sub((pcp), 1)
+#endif
+
+#ifndef __this_cpu_and
+# ifndef __this_cpu_and_1
+# define __this_cpu_and_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_2
+# define __this_cpu_and_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_4
+# define __this_cpu_and_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_8
+# define __this_cpu_and_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define __this_cpu_and(pcp, val) __pcpu_size_call(__this_cpu_and_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_or
+# ifndef __this_cpu_or_1
+# define __this_cpu_or_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_2
+# define __this_cpu_or_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_4
+# define __this_cpu_or_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_8
+# define __this_cpu_or_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define __this_cpu_or(pcp, val) __pcpu_size_call(__this_cpu_or_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_xor
+# ifndef __this_cpu_xor_1
+# define __this_cpu_xor_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_2
+# define __this_cpu_xor_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_4
+# define __this_cpu_xor_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_8
+# define __this_cpu_xor_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define __this_cpu_xor(pcp, val) __pcpu_size_call(__this_cpu_xor_, (pcp), (val))
+#endif
+
+/*
+ * IRQ safe versions of the per cpu RMW operations. Note that these operations
+ * are *not* safe against modification of the same variable from another
+ * processors (which one gets when using regular atomic operations)
+ . They are guaranteed to be atomic vs. local interrupts and
+ * preemption only.
+ */
+#define irqsafe_cpu_generic_to_op(pcp, val, op) \
+do { \
+ unsigned long flags; \
+ local_irq_save(flags); \
+ *__this_cpu_ptr(&(pcp)) op val; \
+ local_irq_restore(flags); \
+} while (0)
+
+#ifndef irqsafe_cpu_add
+# ifndef irqsafe_cpu_add_1
+# define irqsafe_cpu_add_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_2
+# define irqsafe_cpu_add_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_4
+# define irqsafe_cpu_add_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_8
+# define irqsafe_cpu_add_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define irqsafe_cpu_add(pcp, val) __pcpu_size_call(irqsafe_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef irqsafe_cpu_sub
+# define irqsafe_cpu_sub(pcp, val) irqsafe_cpu_add((pcp), -(val))
+#endif
+
+#ifndef irqsafe_cpu_inc
+# define irqsafe_cpu_inc(pcp) irqsafe_cpu_add((pcp), 1)
+#endif
+
+#ifndef irqsafe_cpu_dec
+# define irqsafe_cpu_dec(pcp) irqsafe_cpu_sub((pcp), 1)
+#endif
+
+#ifndef irqsafe_cpu_and
+# ifndef irqsafe_cpu_and_1
+# define irqsafe_cpu_and_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_2
+# define irqsafe_cpu_and_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_4
+# define irqsafe_cpu_and_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_8
+# define irqsafe_cpu_and_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define irqsafe_cpu_and(pcp, val) __pcpu_size_call(irqsafe_cpu_and_, (val))
+#endif
+
+#ifndef irqsafe_cpu_or
+# ifndef irqsafe_cpu_or_1
+# define irqsafe_cpu_or_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_2
+# define irqsafe_cpu_or_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_4
+# define irqsafe_cpu_or_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_8
+# define irqsafe_cpu_or_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define irqsafe_cpu_or(pcp, val) __pcpu_size_call(irqsafe_cpu_or_, (val))
+#endif
+
+#ifndef irqsafe_cpu_xor
+# ifndef irqsafe_cpu_xor_1
+# define irqsafe_cpu_xor_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_2
+# define irqsafe_cpu_xor_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_4
+# define irqsafe_cpu_xor_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_8
+# define irqsafe_cpu_xor_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define irqsafe_cpu_xor(pcp, val) __pcpu_size_call(irqsafe_cpu_xor_, (val))
+#endif
+
#endif /* __LINUX_PERCPU_H */
#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
#endif /* CONFIG_RT_GROUP_SCHED */
#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
return single_open(filp, sched_feat_show, NULL);
}
-static struct file_operations sched_feat_fops = {
+static const struct file_operations sched_feat_fops = {
.open = sched_feat_open,
.write = sched_feat_write,
.read = seq_read,
#ifdef CONFIG_FAIR_GROUP_SCHED
- struct update_shares_data {
- unsigned long rq_weight[NR_CPUS];
- };
-
- static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+ static __read_mostly unsigned long *update_shares_data;
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
static void update_group_shares_cpu(struct task_group *tg, int cpu,
unsigned long sd_shares,
unsigned long sd_rq_weight,
- struct update_shares_data *usd)
+ unsigned long *usd_rq_weight)
{
unsigned long shares, rq_weight;
int boost = 0;
- rq_weight = usd->rq_weight[cpu];
+ rq_weight = usd_rq_weight[cpu];
if (!rq_weight) {
boost = 1;
rq_weight = NICE_0_LOAD;
static int tg_shares_up(struct task_group *tg, void *data)
{
unsigned long weight, rq_weight = 0, shares = 0;
- struct update_shares_data *usd;
+ unsigned long *usd_rq_weight;
struct sched_domain *sd = data;
unsigned long flags;
int i;
return 0;
local_irq_save(flags);
- usd = &__get_cpu_var(update_shares_data);
+ usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
for_each_cpu(i, sched_domain_span(sd)) {
weight = tg->cfs_rq[i]->load.weight;
- usd->rq_weight[i] = weight;
+ usd_rq_weight[i] = weight;
/*
* If there are currently no tasks on the cpu pretend there
shares = tg->shares;
for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+ update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
local_irq_restore(flags);
*/
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
static int
cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
struct sched_group **sg, struct cpumask *unused)
{
if (sg)
- *sg = &per_cpu(sched_group_cpus, cpu).sg;
+ *sg = &per_cpu(sched_groups, cpu).sg;
return cpu;
}
#endif /* CONFIG_SCHED_SMT */
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_GROUP_SCHED */
+ #if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
+ update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+ __alignof__(unsigned long));
+ #endif
for_each_possible_cpu(i) {
struct rq *rq;
#elif defined CONFIG_USER_SCHED
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
init_tg_rt_entry(&init_task_group,
- &per_cpu(init_rt_rq, i),
+ &per_cpu(init_rt_rq_var, i),
&per_cpu(init_sched_rt_entity, i), i, 1,
root_task_group.rt_se[i]);
#endif
*
* To use this allocator, arch code should do the followings.
*
- * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA
- *
* - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
* regular address to percpu pointer and back if they need to be
* different from the default
#include <asm/cacheflush.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
+ #include <asm/io.h>
#define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */
#define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */
*
* During allocation, pcpu_alloc_mutex is kept locked all the time and
* pcpu_lock is grabbed and released as necessary. All actual memory
- * allocations are done using GFP_KERNEL with pcpu_lock released.
+ * allocations are done using GFP_KERNEL with pcpu_lock released. In
+ * general, percpu memory can't be allocated with irq off but
+ * irqsave/restore are still used in alloc path so that it can be used
+ * from early init path - sched_init() specifically.
*
* Free path accesses and alters only the index data structures, so it
* can be safely called from atomic context. When memory needs to be
}
/**
- * pcpu_extend_area_map - extend area map for allocation
- * @chunk: target chunk
+ * pcpu_need_to_extend - determine whether chunk area map needs to be extended
+ * @chunk: chunk of interest
*
- * Extend area map of @chunk so that it can accomodate an allocation.
- * A single allocation can split an area into three areas, so this
- * function makes sure that @chunk->map has at least two extra slots.
+ * Determine whether area map of @chunk needs to be extended to
+ * accomodate a new allocation.
*
* CONTEXT:
- * pcpu_alloc_mutex, pcpu_lock. pcpu_lock is released and reacquired
- * if area map is extended.
+ * pcpu_lock.
*
* RETURNS:
- * 0 if noop, 1 if successfully extended, -errno on failure.
+ * New target map allocation length if extension is necessary, 0
+ * otherwise.
*/
- static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
- __releases(lock) __acquires(lock)
+ static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
{
int new_alloc;
- int *new;
- size_t size;
- /* has enough? */
if (chunk->map_alloc >= chunk->map_used + 2)
return 0;
- spin_unlock_irq(&pcpu_lock);
-
new_alloc = PCPU_DFL_MAP_ALLOC;
while (new_alloc < chunk->map_used + 2)
new_alloc *= 2;
- new = pcpu_mem_alloc(new_alloc * sizeof(new[0]));
- if (!new) {
- spin_lock_irq(&pcpu_lock);
+ return new_alloc;
+ }
+
+ /**
+ * pcpu_extend_area_map - extend area map of a chunk
+ * @chunk: chunk of interest
+ * @new_alloc: new target allocation length of the area map
+ *
+ * Extend area map of @chunk to have @new_alloc entries.
+ *
+ * CONTEXT:
+ * Does GFP_KERNEL allocation. Grabs and releases pcpu_lock.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
+ {
+ int *old = NULL, *new = NULL;
+ size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
+ unsigned long flags;
+
+ new = pcpu_mem_alloc(new_size);
+ if (!new)
return -ENOMEM;
- }
- /*
- * Acquire pcpu_lock and switch to new area map. Only free
- * could have happened inbetween, so map_used couldn't have
- * grown.
- */
- spin_lock_irq(&pcpu_lock);
- BUG_ON(new_alloc < chunk->map_used + 2);
+ /* acquire pcpu_lock and switch to new area map */
+ spin_lock_irqsave(&pcpu_lock, flags);
+
+ if (new_alloc <= chunk->map_alloc)
+ goto out_unlock;
- size = chunk->map_alloc * sizeof(chunk->map[0]);
- memcpy(new, chunk->map, size);
+ old_size = chunk->map_alloc * sizeof(chunk->map[0]);
+ memcpy(new, chunk->map, old_size);
/*
* map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is
* one of the first chunks and still using static map.
*/
if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC)
- pcpu_mem_free(chunk->map, size);
+ old = chunk->map;
chunk->map_alloc = new_alloc;
chunk->map = new;
+ new = NULL;
+
+ out_unlock:
+ spin_unlock_irqrestore(&pcpu_lock, flags);
+
+ /*
+ * pcpu_mem_free() might end up calling vfree() which uses
+ * IRQ-unsafe lock and thus can't be called under pcpu_lock.
+ */
+ pcpu_mem_free(old, old_size);
+ pcpu_mem_free(new, new_size);
+
return 0;
}
static int warn_limit = 10;
struct pcpu_chunk *chunk;
const char *err;
- int slot, off;
+ int slot, off, new_alloc;
+ unsigned long flags;
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
WARN(true, "illegal size (%zu) or align (%zu) for "
}
mutex_lock(&pcpu_alloc_mutex);
- spin_lock_irq(&pcpu_lock);
+ spin_lock_irqsave(&pcpu_lock, flags);
/* serve reserved allocations from the reserved chunk if available */
if (reserved && pcpu_reserved_chunk) {
chunk = pcpu_reserved_chunk;
- if (size > chunk->contig_hint ||
- pcpu_extend_area_map(chunk) < 0) {
- err = "failed to extend area map of reserved chunk";
+
+ if (size > chunk->contig_hint) {
+ err = "alloc from reserved chunk failed";
goto fail_unlock;
}
+
+ while ((new_alloc = pcpu_need_to_extend(chunk))) {
+ spin_unlock_irqrestore(&pcpu_lock, flags);
+ if (pcpu_extend_area_map(chunk, new_alloc) < 0) {
+ err = "failed to extend area map of reserved chunk";
+ goto fail_unlock_mutex;
+ }
+ spin_lock_irqsave(&pcpu_lock, flags);
+ }
+
off = pcpu_alloc_area(chunk, size, align);
if (off >= 0)
goto area_found;
+
err = "alloc from reserved chunk failed";
goto fail_unlock;
}
if (size > chunk->contig_hint)
continue;
- switch (pcpu_extend_area_map(chunk)) {
- case 0:
- break;
- case 1:
- goto restart; /* pcpu_lock dropped, restart */
- default:
- err = "failed to extend area map";
- goto fail_unlock;
+ new_alloc = pcpu_need_to_extend(chunk);
+ if (new_alloc) {
+ spin_unlock_irqrestore(&pcpu_lock, flags);
+ if (pcpu_extend_area_map(chunk,
+ new_alloc) < 0) {
+ err = "failed to extend area map";
+ goto fail_unlock_mutex;
+ }
+ spin_lock_irqsave(&pcpu_lock, flags);
+ /*
+ * pcpu_lock has been dropped, need to
+ * restart cpu_slot list walking.
+ */
+ goto restart;
}
off = pcpu_alloc_area(chunk, size, align);
}
/* hmmm... no space left, create a new chunk */
- spin_unlock_irq(&pcpu_lock);
+ spin_unlock_irqrestore(&pcpu_lock, flags);
chunk = alloc_pcpu_chunk();
if (!chunk) {
goto fail_unlock_mutex;
}
- spin_lock_irq(&pcpu_lock);
+ spin_lock_irqsave(&pcpu_lock, flags);
pcpu_chunk_relocate(chunk, -1);
goto restart;
area_found:
- spin_unlock_irq(&pcpu_lock);
+ spin_unlock_irqrestore(&pcpu_lock, flags);
/* populate, map and clear the area */
if (pcpu_populate_chunk(chunk, off, size)) {
- spin_lock_irq(&pcpu_lock);
+ spin_lock_irqsave(&pcpu_lock, flags);
pcpu_free_area(chunk, off);
err = "failed to populate";
goto fail_unlock;
return __addr_to_pcpu_ptr(chunk->base_addr + off);
fail_unlock:
- spin_unlock_irq(&pcpu_lock);
+ spin_unlock_irqrestore(&pcpu_lock, flags);
fail_unlock_mutex:
mutex_unlock(&pcpu_alloc_mutex);
if (warn_limit) {
}
EXPORT_SYMBOL_GPL(free_percpu);
+ /**
+ * per_cpu_ptr_to_phys - convert translated percpu address to physical address
+ * @addr: the address to be converted to physical address
+ *
+ * Given @addr which is dereferenceable address obtained via one of
+ * percpu access macros, this function translates it into its physical
+ * address. The caller is responsible for ensuring @addr stays valid
+ * until this function finishes.
+ *
+ * RETURNS:
+ * The physical address for @addr.
+ */
+ phys_addr_t per_cpu_ptr_to_phys(void *addr)
+ {
+ if ((unsigned long)addr < VMALLOC_START ||
+ (unsigned long)addr >= VMALLOC_END)
+ return __pa(addr);
+ else
+ return page_to_phys(vmalloc_to_page(addr));
+ }
+
static inline size_t pcpu_calc_fc_sizes(size_t static_size,
size_t reserved_size,
ssize_t *dyn_sizep)
projects / linux.git / commitdiff