summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/cputime.h8
-rw-r--r--include/linux/bitops.h10
-rw-r--r--include/linux/blkdev.h3
-rw-r--r--include/linux/bootmem.h2
-rw-r--r--include/linux/clocksource.h11
-rw-r--r--include/linux/cpu.h1
-rw-r--r--include/linux/debugobjects.h6
-rw-r--r--include/linux/dma_remapping.h2
-rw-r--r--include/linux/hardirq.h21
-rw-r--r--include/linux/jump_label.h27
-rw-r--r--include/linux/kvm.h1
-rw-r--r--include/linux/lglock.h36
-rw-r--r--include/linux/lockdep.h4
-rw-r--r--include/linux/memblock.h170
-rw-r--r--include/linux/mm.h34
-rw-r--r--include/linux/mmzone.h8
-rw-r--r--include/linux/perf_event.h8
-rw-r--r--include/linux/poison.h6
-rw-r--r--include/linux/rcupdate.h115
-rw-r--r--include/linux/sched.h8
-rw-r--r--include/linux/security.h2
-rw-r--r--include/linux/srcu.h87
-rw-r--r--include/linux/tick.h11
-rw-r--r--include/linux/wait.h4
-rw-r--r--include/media/soc_camera.h7
-rw-r--r--include/net/dst.h1
-rw-r--r--include/net/flow.h1
-rw-r--r--include/net/ip_vs.h2
-rw-r--r--include/net/sctp/structs.h4
-rw-r--r--include/net/sock.h4
-rw-r--r--include/scsi/libfcoe.h3
-rw-r--r--include/trace/events/rcu.h122
-rw-r--r--include/trace/events/writeback.h15
-rw-r--r--include/xen/interface/io/xs_wire.h3
34 files changed, 547 insertions, 200 deletions
diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
index 77202e2c9fc..9a62937c56c 100644
--- a/include/asm-generic/cputime.h
+++ b/include/asm-generic/cputime.h
@@ -24,9 +24,11 @@ typedef u64 __nocast cputime64_t;
* Convert cputime to microseconds and back.
*/
#define cputime_to_usecs(__ct) \
- jiffies_to_usecs(cputime_to_jiffies(__ct));
-#define usecs_to_cputime(__msecs) \
- jiffies_to_cputime(usecs_to_jiffies(__msecs));
+ jiffies_to_usecs(cputime_to_jiffies(__ct))
+#define usecs_to_cputime(__usec) \
+ jiffies_to_cputime(usecs_to_jiffies(__usec))
+#define usecs_to_cputime64(__usec) \
+ jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
/*
* Convert cputime to seconds and back.
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3ef66a2a08..3c1063acb2a 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -22,8 +22,14 @@ extern unsigned long __sw_hweight64(__u64 w);
#include <asm/bitops.h>
#define for_each_set_bit(bit, addr, size) \
- for ((bit) = find_first_bit((addr), (size)); \
- (bit) < (size); \
+ for ((bit) = find_first_bit((addr), (size)); \
+ (bit) < (size); \
+ (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_cont(bit, addr, size) \
+ for ((bit) = find_next_bit((addr), (size), (bit)); \
+ (bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
static __inline__ int get_bitmask_order(unsigned int count)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c7a6d3b5bc7..94acd8172b5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -805,9 +805,6 @@ extern void blk_unprep_request(struct request *);
*/
extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
spinlock_t *lock, int node_id);
-extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *,
- request_fn_proc *,
- spinlock_t *, int node_id);
extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
request_fn_proc *, spinlock_t *);
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index ab344a52110..66d3e954eb6 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -44,7 +44,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat,
unsigned long endpfn);
extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
-unsigned long free_all_memory_core_early(int nodeid);
+extern unsigned long free_low_memory_core_early(int nodeid);
extern unsigned long free_all_bootmem_node(pg_data_t *pgdat);
extern unsigned long free_all_bootmem(void);
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index c86c940d1de..081147da056 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -71,7 +71,7 @@ struct timecounter {
/**
* cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds
- * @tc: Pointer to cycle counter.
+ * @cc: Pointer to cycle counter.
* @cycles: Cycles
*
* XXX - This could use some mult_lxl_ll() asm optimization. Same code
@@ -114,7 +114,7 @@ extern u64 timecounter_read(struct timecounter *tc);
* time base as values returned by
* timecounter_read()
* @tc: Pointer to time counter.
- * @cycle: a value returned by tc->cc->read()
+ * @cycle_tstamp: a value returned by tc->cc->read()
*
* Cycle counts that are converted correctly as long as they
* fall into the interval [-1/2 max cycle count, +1/2 max cycle count],
@@ -156,11 +156,12 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
* @mult: cycle to nanosecond multiplier
* @shift: cycle to nanosecond divisor (power of two)
* @max_idle_ns: max idle time permitted by the clocksource (nsecs)
- * @maxadj maximum adjustment value to mult (~11%)
+ * @maxadj: maximum adjustment value to mult (~11%)
* @flags: flags describing special properties
* @archdata: arch-specific data
* @suspend: suspend function for the clocksource, if necessary
* @resume: resume function for the clocksource, if necessary
+ * @cycle_last: most recent cycle counter value seen by ::read()
*/
struct clocksource {
/*
@@ -187,6 +188,7 @@ struct clocksource {
void (*suspend)(struct clocksource *cs);
void (*resume)(struct clocksource *cs);
+ /* private: */
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
/* Watchdog related data, used by the framework */
struct list_head wd_list;
@@ -261,6 +263,9 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant)
/**
* clocksource_cyc2ns - converts clocksource cycles to nanoseconds
+ * @cycles: cycles
+ * @mult: cycle to nanosecond multiplier
+ * @shift: cycle to nanosecond divisor (power of two)
*
* Converts cycles to nanoseconds, using the given mult and shift.
*
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 6cb60fd2ea8..305c263021e 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -27,6 +27,7 @@ struct cpu {
extern int register_cpu(struct cpu *cpu, int num);
extern struct sys_device *get_cpu_sysdev(unsigned cpu);
+extern bool cpu_is_hotpluggable(unsigned cpu);
extern int cpu_add_sysdev_attr(struct sysdev_attribute *attr);
extern void cpu_remove_sysdev_attr(struct sysdev_attribute *attr);
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 65970b811e2..0e5f5785d9f 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -46,6 +46,8 @@ struct debug_obj {
* fails
* @fixup_free: fixup function, which is called when the free check
* fails
+ * @fixup_assert_init: fixup function, which is called when the assert_init
+ * check fails
*/
struct debug_obj_descr {
const char *name;
@@ -54,6 +56,7 @@ struct debug_obj_descr {
int (*fixup_activate) (void *addr, enum debug_obj_state state);
int (*fixup_destroy) (void *addr, enum debug_obj_state state);
int (*fixup_free) (void *addr, enum debug_obj_state state);
+ int (*fixup_assert_init)(void *addr, enum debug_obj_state state);
};
#ifdef CONFIG_DEBUG_OBJECTS
@@ -64,6 +67,7 @@ extern void debug_object_activate (void *addr, struct debug_obj_descr *descr);
extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
extern void debug_object_destroy (void *addr, struct debug_obj_descr *descr);
extern void debug_object_free (void *addr, struct debug_obj_descr *descr);
+extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr);
/*
* Active state:
@@ -89,6 +93,8 @@ static inline void
debug_object_destroy (void *addr, struct debug_obj_descr *descr) { }
static inline void
debug_object_free (void *addr, struct debug_obj_descr *descr) { }
+static inline void
+debug_object_assert_init(void *addr, struct debug_obj_descr *descr) { }
static inline void debug_objects_early_init(void) { }
static inline void debug_objects_mem_init(void) { }
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index ef90cbd8e17..57c9a8ae4f2 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -31,6 +31,7 @@ extern void free_dmar_iommu(struct intel_iommu *iommu);
extern int iommu_calculate_agaw(struct intel_iommu *iommu);
extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
extern int dmar_disabled;
+extern int intel_iommu_enabled;
#else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
{
@@ -44,6 +45,7 @@ static inline void free_dmar_iommu(struct intel_iommu *iommu)
{
}
#define dmar_disabled (1)
+#define intel_iommu_enabled (0)
#endif
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index f743883f769..bb7f3097185 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -139,20 +139,7 @@ static inline void account_system_vtime(struct task_struct *tsk)
extern void account_system_vtime(struct task_struct *tsk);
#endif
-#if defined(CONFIG_NO_HZ)
#if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
-extern void rcu_enter_nohz(void);
-extern void rcu_exit_nohz(void);
-
-static inline void rcu_irq_enter(void)
-{
- rcu_exit_nohz();
-}
-
-static inline void rcu_irq_exit(void)
-{
- rcu_enter_nohz();
-}
static inline void rcu_nmi_enter(void)
{
@@ -163,17 +150,9 @@ static inline void rcu_nmi_exit(void)
}
#else
-extern void rcu_irq_enter(void);
-extern void rcu_irq_exit(void);
extern void rcu_nmi_enter(void);
extern void rcu_nmi_exit(void);
#endif
-#else
-# define rcu_irq_enter() do { } while (0)
-# define rcu_irq_exit() do { } while (0)
-# define rcu_nmi_enter() do { } while (0)
-# define rcu_nmi_exit() do { } while (0)
-#endif /* #if defined(CONFIG_NO_HZ) */
/*
* It is safe to do non-atomic ops on ->hardirq_context,
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 388b0d425b5..5ce8b140428 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -3,6 +3,7 @@
#include <linux/types.h>
#include <linux/compiler.h>
+#include <linux/workqueue.h>
#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
@@ -14,6 +15,12 @@ struct jump_label_key {
#endif
};
+struct jump_label_key_deferred {
+ struct jump_label_key key;
+ unsigned long timeout;
+ struct delayed_work work;
+};
+
# include <asm/jump_label.h>
# define HAVE_JUMP_LABEL
#endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */
@@ -51,8 +58,11 @@ extern void arch_jump_label_transform_static(struct jump_entry *entry,
extern int jump_label_text_reserved(void *start, void *end);
extern void jump_label_inc(struct jump_label_key *key);
extern void jump_label_dec(struct jump_label_key *key);
+extern void jump_label_dec_deferred(struct jump_label_key_deferred *key);
extern bool jump_label_enabled(struct jump_label_key *key);
extern void jump_label_apply_nops(struct module *mod);
+extern void jump_label_rate_limit(struct jump_label_key_deferred *key,
+ unsigned long rl);
#else /* !HAVE_JUMP_LABEL */
@@ -68,6 +78,10 @@ static __always_inline void jump_label_init(void)
{
}
+struct jump_label_key_deferred {
+ struct jump_label_key key;
+};
+
static __always_inline bool static_branch(struct jump_label_key *key)
{
if (unlikely(atomic_read(&key->enabled)))
@@ -85,6 +99,11 @@ static inline void jump_label_dec(struct jump_label_key *key)
atomic_dec(&key->enabled);
}
+static inline void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+{
+ jump_label_dec(&key->key);
+}
+
static inline int jump_label_text_reserved(void *start, void *end)
{
return 0;
@@ -102,6 +121,14 @@ static inline int jump_label_apply_nops(struct module *mod)
{
return 0;
}
+
+static inline void jump_label_rate_limit(struct jump_label_key_deferred *key,
+ unsigned long rl)
+{
+}
#endif /* HAVE_JUMP_LABEL */
+#define jump_label_key_enabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(1), })
+#define jump_label_key_disabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(0), })
+
#endif /* _LINUX_JUMP_LABEL_H */
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index c3892fc1d53..68e67e50d02 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -557,6 +557,7 @@ struct kvm_ppc_pvinfo {
#define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */
#define KVM_CAP_PPC_PAPR 68
#define KVM_CAP_S390_GMAP 71
+#define KVM_CAP_TSC_DEADLINE_TIMER 72
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index f549056fb20..87f402ccec5 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -22,6 +22,7 @@
#include <linux/spinlock.h>
#include <linux/lockdep.h>
#include <linux/percpu.h>
+#include <linux/cpu.h>
/* can make br locks by using local lock for read side, global lock for write */
#define br_lock_init(name) name##_lock_init()
@@ -72,9 +73,31 @@
#define DEFINE_LGLOCK(name) \
\
+ DEFINE_SPINLOCK(name##_cpu_lock); \
+ cpumask_t name##_cpus __read_mostly; \
DEFINE_PER_CPU(arch_spinlock_t, name##_lock); \
DEFINE_LGLOCK_LOCKDEP(name); \
\
+ static int \
+ name##_lg_cpu_callback(struct notifier_block *nb, \
+ unsigned long action, void *hcpu) \
+ { \
+ switch (action & ~CPU_TASKS_FROZEN) { \
+ case CPU_UP_PREPARE: \
+ spin_lock(&name##_cpu_lock); \
+ cpu_set((unsigned long)hcpu, name##_cpus); \
+ spin_unlock(&name##_cpu_lock); \
+ break; \
+ case CPU_UP_CANCELED: case CPU_DEAD: \
+ spin_lock(&name##_cpu_lock); \
+ cpu_clear((unsigned long)hcpu, name##_cpus); \
+ spin_unlock(&name##_cpu_lock); \
+ } \
+ return NOTIFY_OK; \
+ } \
+ static struct notifier_block name##_lg_cpu_notifier = { \
+ .notifier_call = name##_lg_cpu_callback, \
+ }; \
void name##_lock_init(void) { \
int i; \
LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \
@@ -83,6 +106,11 @@
lock = &per_cpu(name##_lock, i); \
*lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; \
} \
+ register_hotcpu_notifier(&name##_lg_cpu_notifier); \
+ get_online_cpus(); \
+ for_each_online_cpu(i) \
+ cpu_set(i, name##_cpus); \
+ put_online_cpus(); \
} \
EXPORT_SYMBOL(name##_lock_init); \
\
@@ -124,9 +152,9 @@
\
void name##_global_lock_online(void) { \
int i; \
- preempt_disable(); \
+ spin_lock(&name##_cpu_lock); \
rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \
- for_each_online_cpu(i) { \
+ for_each_cpu(i, &name##_cpus) { \
arch_spinlock_t *lock; \
lock = &per_cpu(name##_lock, i); \
arch_spin_lock(lock); \
@@ -137,12 +165,12 @@
void name##_global_unlock_online(void) { \
int i; \
rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \
- for_each_online_cpu(i) { \
+ for_each_cpu(i, &name##_cpus) { \
arch_spinlock_t *lock; \
lock = &per_cpu(name##_lock, i); \
arch_spin_unlock(lock); \
} \
- preempt_enable(); \
+ spin_unlock(&name##_cpu_lock); \
} \
EXPORT_SYMBOL(name##_global_unlock_online); \
\
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b6a56e37284..d36619ead3b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -343,6 +343,8 @@ extern void lockdep_trace_alloc(gfp_t mask);
#define lockdep_assert_held(l) WARN_ON(debug_locks && !lockdep_is_held(l))
+#define lockdep_recursing(tsk) ((tsk)->lockdep_recursion)
+
#else /* !LOCKDEP */
static inline void lockdep_off(void)
@@ -392,6 +394,8 @@ struct lock_class_key { };
#define lockdep_assert_held(l) do { } while (0)
+#define lockdep_recursing(tsk) (0)
+
#endif /* !LOCKDEP */
#ifdef CONFIG_LOCK_STAT
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index e6b843e16e8..a6bb1023514 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -2,8 +2,6 @@
#define _LINUX_MEMBLOCK_H
#ifdef __KERNEL__
-#define MEMBLOCK_ERROR 0
-
#ifdef CONFIG_HAVE_MEMBLOCK
/*
* Logical memory blocks.
@@ -19,81 +17,161 @@
#include <linux/init.h>
#include <linux/mm.h>
-#include <asm/memblock.h>
-
#define INIT_MEMBLOCK_REGIONS 128
struct memblock_region {
phys_addr_t base;
phys_addr_t size;
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+ int nid;
+#endif
};
struct memblock_type {
unsigned long cnt; /* number of regions */
unsigned long max; /* size of the allocated array */
+ phys_addr_t total_size; /* size of all regions */
struct memblock_region *regions;
};
struct memblock {
phys_addr_t current_limit;
- phys_addr_t memory_size; /* Updated by memblock_analyze() */
struct memblock_type memory;
struct memblock_type reserved;
};
extern struct memblock memblock;
extern int memblock_debug;
-extern int memblock_can_resize;
#define memblock_dbg(fmt, ...) \
if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
-u64 memblock_find_in_range(u64 start, u64 end, u64 size, u64 align);
+phys_addr_t memblock_find_in_range_node(phys_addr_t start, phys_addr_t end,
+ phys_addr_t size, phys_addr_t align, int nid);
+phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
+ phys_addr_t size, phys_addr_t align);
int memblock_free_reserved_regions(void);
int memblock_reserve_reserved_regions(void);
-extern void memblock_init(void);
-extern void memblock_analyze(void);
-extern long memblock_add(phys_addr_t base, phys_addr_t size);
-extern long memblock_remove(phys_addr_t base, phys_addr_t size);
-extern long memblock_free(phys_addr_t base, phys_addr_t size);
-extern long memblock_reserve(phys_addr_t base, phys_addr_t size);
+void memblock_allow_resize(void);
+int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid);
+int memblock_add(phys_addr_t base, phys_addr_t size);
+int memblock_remove(phys_addr_t base, phys_addr_t size);
+int memblock_free(phys_addr_t base, phys_addr_t size);
+int memblock_reserve(phys_addr_t base, phys_addr_t size);
+
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
+ unsigned long *out_end_pfn, int *out_nid);
+
+/**
+ * for_each_mem_pfn_range - early memory pfn range iterator
+ * @i: an integer used as loop variable
+ * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @p_start: ptr to ulong for start pfn of the range, can be %NULL
+ * @p_end: ptr to ulong for end pfn of the range, can be %NULL
+ * @p_nid: ptr to int for nid of the range, can be %NULL
+ *
+ * Walks over configured memory ranges. Available after early_node_map is
+ * populated.
+ */
+#define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid) \
+ for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \
+ i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
+void __next_free_mem_range(u64 *idx, int nid, phys_addr_t *out_start,
+ phys_addr_t *out_end, int *out_nid);
+
+/**
+ * for_each_free_mem_range - iterate through free memblock areas
+ * @i: u64 used as loop variable
+ * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ * @p_nid: ptr to int for nid of the range, can be %NULL
+ *
+ * Walks over free (memory && !reserved) areas of memblock. Available as
+ * soon as memblock is initialized.
+ */
+#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid) \
+ for (i = 0, \
+ __next_free_mem_range(&i, nid, p_start, p_end, p_nid); \
+ i != (u64)ULLONG_MAX; \
+ __next_free_mem_range(&i, nid, p_start, p_end, p_nid))
+
+void __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start,
+ phys_addr_t *out_end, int *out_nid);
-/* The numa aware allocator is only available if
- * CONFIG_ARCH_POPULATES_NODE_MAP is set
+/**
+ * for_each_free_mem_range_reverse - rev-iterate through free memblock areas
+ * @i: u64 used as loop variable
+ * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ * @p_nid: ptr to int for nid of the range, can be %NULL
+ *
+ * Walks over free (memory && !reserved) areas of memblock in reverse
+ * order. Available as soon as memblock is initialized.
*/
-extern phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align,
- int nid);
-extern phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
- int nid);
+#define for_each_free_mem_range_reverse(i, nid, p_start, p_end, p_nid) \
+ for (i = (u64)ULLONG_MAX, \
+ __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid); \
+ i != (u64)ULLONG_MAX; \
+ __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid))
-extern phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+int memblock_set_node(phys_addr_t base, phys_addr_t size, int nid);
+
+static inline void memblock_set_region_node(struct memblock_region *r, int nid)
+{
+ r->nid = nid;
+}
+
+static inline int memblock_get_region_node(const struct memblock_region *r)
+{
+ return r->nid;
+}
+#else
+static inline void memblock_set_region_node(struct memblock_region *r, int nid)
+{
+}
+
+static inline int memblock_get_region_node(const struct memblock_region *r)
+{
+ return 0;
+}
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
+phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid);
+phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid);
+
+phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0)
#define MEMBLOCK_ALLOC_ACCESSIBLE 0
-extern phys_addr_t memblock_alloc_base(phys_addr_t size,
- phys_addr_t align,
- phys_addr_t max_addr);
-extern phys_addr_t __memblock_alloc_base(phys_addr_t size,
- phys_addr_t align,
- phys_addr_t max_addr);
-extern phys_addr_t memblock_phys_mem_size(void);
-extern phys_addr_t memblock_start_of_DRAM(void);
-extern phys_addr_t memblock_end_of_DRAM(void);
-extern void memblock_enforce_memory_limit(phys_addr_t memory_limit);
-extern int memblock_is_memory(phys_addr_t addr);
-extern int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
-extern int memblock_is_reserved(phys_addr_t addr);
-extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
-
-extern void memblock_dump_all(void);
-
-/* Provided by the architecture */
-extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid);
-extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
- phys_addr_t addr2, phys_addr_t size2);
+phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
+ phys_addr_t max_addr);
+phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,
+ phys_addr_t max_addr);
+phys_addr_t memblock_phys_mem_size(void);
+phys_addr_t memblock_start_of_DRAM(void);
+phys_addr_t memblock_end_of_DRAM(void);
+void memblock_enforce_memory_limit(phys_addr_t memory_limit);
+int memblock_is_memory(phys_addr_t addr);
+int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
+int memblock_is_reserved(phys_addr_t addr);
+int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
+
+extern void __memblock_dump_all(void);
+
+static inline void memblock_dump_all(void)
+{
+ if (memblock_debug)
+ __memblock_dump_all();
+}
/**
* memblock_set_current_limit - Set the current allocation limit to allow
@@ -101,7 +179,7 @@ extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
* accessible during boot
* @limit: New limit value (physical address)
*/
-extern void memblock_set_current_limit(phys_addr_t limit);
+void memblock_set_current_limit(phys_addr_t limit);
/*
@@ -154,9 +232,9 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
region++)
-#ifdef ARCH_DISCARD_MEMBLOCK
-#define __init_memblock __init
-#define __initdata_memblock __initdata
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+#define __init_memblock __meminit
+#define __initdata_memblock __meminitdata
#else
#define __init_memblock
#define __initdata_memblock
@@ -165,7 +243,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
#else
static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
{
- return MEMBLOCK_ERROR;
+ return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4baadd18f4a..5d9b4c9813b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1253,41 +1253,34 @@ static inline void pgtable_page_dtor(struct page *page)
extern void free_area_init(unsigned long * zones_size);
extern void free_area_init_node(int nid, unsigned long * zones_size,
unsigned long zone_start_pfn, unsigned long *zholes_size);
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
/*
- * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its
+ * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its
* zones, allocate the backing mem_map and account for memory holes in a more
* architecture independent manner. This is a substitute for creating the
* zone_sizes[] and zholes_size[] arrays and passing them to
* free_area_init_node()
*
* An architecture is expected to register range of page frames backed by
- * physical memory with add_active_range() before calling
+ * physical memory with memblock_add[_node]() before calling
* free_area_init_nodes() passing in the PFN each zone ends at. At a basic
* usage, an architecture is expected to do something like
*
* unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn,
* max_highmem_pfn};
* for_each_valid_physical_page_range()
- * add_active_range(node_id, start_pfn, end_pfn)
+ * memblock_add_node(base, size, nid)
* free_area_init_nodes(max_zone_pfns);
*
- * If the architecture guarantees that there are no holes in the ranges
- * registered with add_active_range(), free_bootmem_active_regions()
- * will call free_bootmem_node() for each registered physical page range.
- * Similarly sparse_memory_present_with_active_regions() calls
- * memory_present() for each range when SPARSEMEM is enabled.
+ * free_bootmem_with_active_regions() calls free_bootmem_node() for each
+ * registered physical page range. Similarly
+ * sparse_memory_present_with_active_regions() calls memory_present() for
+ * each range when SPARSEMEM is enabled.
*
* See mm/page_alloc.c for more information on each function exposed by
- * CONFIG_ARCH_POPULATES_NODE_MAP
+ * CONFIG_HAVE_MEMBLOCK_NODE_MAP.
*/
extern void free_area_init_nodes(unsigned long *max_zone_pfn);
-extern void add_active_range(unsigned int nid, unsigned long start_pfn,
- unsigned long end_pfn);
-extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
- unsigned long end_pfn);
-extern void remove_all_active_ranges(void);
-void sort_node_map(void);
unsigned long node_map_pfn_alignment(void);
unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
unsigned long end_pfn);
@@ -1300,14 +1293,11 @@ extern void free_bootmem_with_active_regions(int nid,
unsigned long max_low_pfn);
int add_from_early_node_map(struct range *range, int az,
int nr_range, int nid);
-u64 __init find_memory_core_early(int nid, u64 size, u64 align,
- u64 goal, u64 limit);
-typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
-extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
extern void sparse_memory_present_with_active_regions(int nid);
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
-#if !defined(CONFIG_ARCH_POPULATES_NODE_MAP) && \
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
+#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
!defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)
static inline int __early_pfn_to_nid(unsigned long pfn)
{
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 188cb2ffe8d..3ac040f1936 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -598,13 +598,13 @@ struct zonelist {
#endif
};
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
struct node_active_region {
unsigned long start_pfn;
unsigned long end_pfn;
int nid;
};
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
#ifndef CONFIG_DISCONTIGMEM
/* The array of struct pages - for discontigmem use pgdat->lmem_map */
@@ -720,7 +720,7 @@ extern int movable_zone;
static inline int zone_movable_is_highmem(void)
{
-#if defined(CONFIG_HIGHMEM) && defined(CONFIG_ARCH_POPULATES_NODE_MAP)
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE)
return movable_zone == ZONE_HIGHMEM;
#else
return 0;
@@ -938,7 +938,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
#endif
#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
- !defined(CONFIG_ARCH_POPULATES_NODE_MAP)
+ !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
static inline unsigned long early_pfn_to_nid(unsigned long pfn)
{
return 0;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b1f89122bf6..08855613ceb 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -54,6 +54,7 @@ enum perf_hw_id {
PERF_COUNT_HW_BUS_CYCLES = 6,
PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7,
PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8,
+ PERF_COUNT_HW_REF_CPU_CYCLES = 9,
PERF_COUNT_HW_MAX, /* non-ABI */
};
@@ -890,6 +891,7 @@ struct perf_event_context {
int nr_active;
int is_active;
int nr_stat;
+ int nr_freq;
int rotate_disable;
atomic_t refcount;
struct task_struct *task;
@@ -1063,12 +1065,12 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
}
}
-extern struct jump_label_key perf_sched_events;
+extern struct jump_label_key_deferred perf_sched_events;
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
- if (static_branch(&perf_sched_events))
+ if (static_branch(&perf_sched_events.key))
__perf_event_task_sched_in(prev, task);
}
@@ -1077,7 +1079,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
{
perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
- if (static_branch(&perf_sched_events))
+ if (static_branch(&perf_sched_events.key))
__perf_event_task_sched_out(prev, next);
}
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 79159de0e34..2110a81c5e2 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -40,12 +40,6 @@
#define RED_INACTIVE 0x09F911029D74E35BULL /* when obj is inactive */
#define RED_ACTIVE 0xD84156C5635688C0ULL /* when obj is active */
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
-#define MEMBLOCK_INACTIVE 0x3a84fb0144c9e71bULL
-#else
-#define MEMBLOCK_INACTIVE 0x44c9e71bUL
-#endif
-
#define SLUB_RED_INACTIVE 0xbb
#define SLUB_RED_ACTIVE 0xcc
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 2cf4226ade7..81c04f4348e 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -51,6 +51,8 @@ extern int rcutorture_runnable; /* for sysctl */
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
extern void rcutorture_record_test_transition(void);
extern void rcutorture_record_progress(unsigned long vernum);
+extern void do_trace_rcu_torture_read(char *rcutorturename,
+ struct rcu_head *rhp);
#else
static inline void rcutorture_record_test_transition(void)
{
@@ -58,6 +60,12 @@ static inline void rcutorture_record_test_transition(void)
static inline void rcutorture_record_progress(unsigned long vernum)
{
}
+#ifdef CONFIG_RCU_TRACE
+extern void do_trace_rcu_torture_read(char *rcutorturename,
+ struct rcu_head *rhp);
+#else
+#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#endif
#endif
#define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b))
@@ -177,23 +185,10 @@ extern void rcu_sched_qs(int cpu);
extern void rcu_bh_qs(int cpu);
extern void rcu_check_callbacks(int cpu, int user);
struct notifier_block;
-
-#ifdef CONFIG_NO_HZ
-
-extern void rcu_enter_nohz(void);
-extern void rcu_exit_nohz(void);
-
-#else /* #ifdef CONFIG_NO_HZ */
-
-static inline void rcu_enter_nohz(void)
-{
-}
-
-static inline void rcu_exit_nohz(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_NO_HZ */
+extern void rcu_idle_enter(void);
+extern void rcu_idle_exit(void);
+extern void rcu_irq_enter(void);
+extern void rcu_irq_exit(void);
/*
* Infrastructure to implement the synchronize_() primitives in
@@ -233,22 +228,30 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-extern struct lockdep_map rcu_lock_map;
-# define rcu_read_acquire() \
- lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
-# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_)
+#ifdef CONFIG_PROVE_RCU
+extern int rcu_is_cpu_idle(void);
+#else /* !CONFIG_PROVE_RCU */
+static inline int rcu_is_cpu_idle(void)
+{
+ return 0;
+}
+#endif /* else !CONFIG_PROVE_RCU */
-extern struct lockdep_map rcu_bh_lock_map;
-# define rcu_read_acquire_bh() \
- lock_acquire(&rcu_bh_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
-# define rcu_read_release_bh() lock_release(&rcu_bh_lock_map, 1, _THIS_IP_)
+static inline void rcu_lock_acquire(struct lockdep_map *map)
+{
+ WARN_ON_ONCE(rcu_is_cpu_idle());
+ lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_);
+}
-extern struct lockdep_map rcu_sched_lock_map;
-# define rcu_read_acquire_sched() \
- lock_acquire(&rcu_sched_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
-# define rcu_read_release_sched() \
- lock_release(&rcu_sched_lock_map, 1, _THIS_IP_)
+static inline void rcu_lock_release(struct lockdep_map *map)
+{
+ WARN_ON_ONCE(rcu_is_cpu_idle());
+ lock_release(map, 1, _THIS_IP_);
+}
+extern struct lockdep_map rcu_lock_map;
+extern struct lockdep_map rcu_bh_lock_map;
+extern struct lockdep_map rcu_sched_lock_map;
extern int debug_lockdep_rcu_enabled(void);
/**
@@ -262,11 +265,18 @@ extern int debug_lockdep_rcu_enabled(void);
*
* Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
* and while lockdep is disabled.
+ *
+ * Note that rcu_read_lock() and the matching rcu_read_unlock() must
+ * occur in the same context, for example, it is illegal to invoke
+ * rcu_read_unlock() in process context if the matching rcu_read_lock()
+ * was invoked from within an irq handler.
*/
static inline int rcu_read_lock_held(void)
{
if (!debug_lockdep_rcu_enabled())
return 1;
+ if (rcu_is_cpu_idle())
+ return 0;
return lock_is_held(&rcu_lock_map);
}
@@ -290,6 +300,19 @@ extern int rcu_read_lock_bh_held(void);
*
* Check debug_lockdep_rcu_enabled() to prevent false positives during boot
* and while lockdep is disabled.
+ *
+ * Note that if the CPU is in the idle loop from an RCU point of
+ * view (ie: that we are in the section between rcu_idle_enter() and
+ * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
+ * did an rcu_read_lock(). The reason for this is that RCU ignores CPUs
+ * that are in such a section, considering these as in extended quiescent
+ * state, so such a CPU is effectively never in an RCU read-side critical
+ * section regardless of what RCU primitives it invokes. This state of
+ * affairs is required --- we need to keep an RCU-free window in idle
+ * where the CPU may possibly enter into low power mode. This way we can
+ * notice an extended quiescent state to other CPUs that started a grace
+ * period. Otherwise we would delay any grace period as long as we run in
+ * the idle task.
*/
#ifdef CONFIG_PREEMPT_COUNT
static inline int rcu_read_lock_sched_held(void)
@@ -298,6 +321,8 @@ static inline int rcu_read_lock_sched_held(void)
if (!debug_lockdep_rcu_enabled())
return 1;
+ if (rcu_is_cpu_idle())
+ return 0;
if (debug_locks)
lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
@@ -311,12 +336,8 @@ static inline int rcu_read_lock_sched_held(void)
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-# define rcu_read_acquire() do { } while (0)
-# define rcu_read_release() do { } while (0)
-# define rcu_read_acquire_bh() do { } while (0)
-# define rcu_read_release_bh() do { } while (0)
-# define rcu_read_acquire_sched() do { } while (0)
-# define rcu_read_release_sched() do { } while (0)
+# define rcu_lock_acquire(a) do { } while (0)
+# define rcu_lock_release(a) do { } while (0)
static inline int rcu_read_lock_held(void)
{
@@ -637,7 +658,7 @@ static inline void rcu_read_lock(void)
{
__rcu_read_lock();
__acquire(RCU);
- rcu_read_acquire();
+ rcu_lock_acquire(&rcu_lock_map);
}
/*
@@ -657,7 +678,7 @@ static inline void rcu_read_lock(void)
*/
static inline void rcu_read_unlock(void)
{
- rcu_read_release();
+ rcu_lock_release(&rcu_lock_map);
__release(RCU);
__rcu_read_unlock();
}
@@ -673,12 +694,17 @@ static inline void rcu_read_unlock(void)
* critical sections in interrupt context can use just rcu_read_lock(),
* though this should at least be commented to avoid confusing people
* reading the code.
+ *
+ * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh()
+ * must occur in the same context, for example, it is illegal to invoke
+ * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh()
+ * was invoked from some other task.
*/
static inline void rcu_read_lock_bh(void)
{
local_bh_disable();
__acquire(RCU_BH);
- rcu_read_acquire_bh();
+ rcu_lock_acquire(&rcu_bh_lock_map);
}
/*
@@ -688,7 +714,7 @@ static inline void rcu_read_lock_bh(void)
*/
static inline void rcu_read_unlock_bh(void)
{
- rcu_read_release_bh();
+ rcu_lock_release(&rcu_bh_lock_map);
__release(RCU_BH);
local_bh_enable();
}
@@ -700,12 +726,17 @@ static inline void rcu_read_unlock_bh(void)
* are being done using call_rcu_sched() or synchronize_rcu_sched().
* Read-side critical sections can also be introduced by anything that
* disables preemption, including local_irq_disable() and friends.
+ *
+ * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched()
+ * must occur in the same context, for example, it is illegal to invoke
+ * rcu_read_unlock_sched() from process context if the matching
+ * rcu_read_lock_sched() was invoked from an NMI handler.
*/
static inline void rcu_read_lock_sched(void)
{
preempt_disable();
__acquire(RCU_SCHED);
- rcu_read_acquire_sched();
+ rcu_lock_acquire(&rcu_sched_lock_map);
}
/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
@@ -722,7 +753,7 @@ static inline notrace void rcu_read_lock_sched_notrace(void)
*/
static inline void rcu_read_unlock_sched(void)
{
- rcu_read_release_sched();
+ rcu_lock_release(&rcu_sched_lock_map);
__release(RCU_SCHED);
preempt_enable();
}
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5a2ab3c2757..cf0eb342bcb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2085,6 +2085,14 @@ extern int sched_setscheduler(struct task_struct *, int,
extern int sched_setscheduler_nocheck(struct task_struct *, int,
const struct sched_param *);
extern struct task_struct *idle_task(int cpu);
+/**
+ * is_idle_task - is the specified task an idle task?
+ * @tsk: the task in question.
+ */
+static inline bool is_idle_task(struct task_struct *p)
+{
+ return p->pid == 0;
+}
extern struct task_struct *curr_task(int cpu);
extern void set_curr_task(int cpu, struct task_struct *p);
diff --git a/include/linux/security.h b/include/linux/security.h
index 19d8e04e168..e8c619d3929 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2056,7 +2056,7 @@ static inline int security_old_inode_init_security(struct inode *inode,
char **name, void **value,
size_t *len)
{
- return 0;
+ return -EOPNOTSUPP;
}
static inline int security_inode_create(struct inode *dir,
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 58971e891f4..e1b005918bb 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -28,6 +28,7 @@
#define _LINUX_SRCU_H
#include <linux/mutex.h>
+#include <linux/rcupdate.h>
struct srcu_struct_array {
int c[2];
@@ -60,18 +61,10 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name,
__init_srcu_struct((sp), #sp, &__srcu_key); \
})
-# define srcu_read_acquire(sp) \
- lock_acquire(&(sp)->dep_map, 0, 0, 2, 1, NULL, _THIS_IP_)
-# define srcu_read_release(sp) \
- lock_release(&(sp)->dep_map, 1, _THIS_IP_)
-
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
int init_srcu_struct(struct srcu_struct *sp);
-# define srcu_read_acquire(sp) do { } while (0)
-# define srcu_read_release(sp) do { } while (0)
-
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
void cleanup_srcu_struct(struct srcu_struct *sp);
@@ -90,12 +83,32 @@ long srcu_batches_completed(struct srcu_struct *sp);
* read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC,
* this assumes we are in an SRCU read-side critical section unless it can
* prove otherwise.
+ *
+ * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
+ *
+ * Note that if the CPU is in the idle loop from an RCU point of view
+ * (ie: that we are in the section between rcu_idle_enter() and
+ * rcu_idle_exit()) then srcu_read_lock_held() returns false even if
+ * the CPU did an srcu_read_lock(). The reason for this is that RCU
+ * ignores CPUs that are in such a section, considering these as in
+ * extended quiescent state, so such a CPU is effectively never in an
+ * RCU read-side critical section regardless of what RCU primitives it
+ * invokes. This state of affairs is required --- we need to keep an
+ * RCU-free window in idle where the CPU may possibly enter into low
+ * power mode. This way we can notice an extended quiescent state to
+ * other CPUs that started a grace period. Otherwise we would delay any
+ * grace period as long as we run in the idle task.
*/
static inline int srcu_read_lock_held(struct srcu_struct *sp)
{
- if (debug_locks)
- return lock_is_held(&sp->dep_map);
- return 1;
+ if (rcu_is_cpu_idle())
+ return 0;
+
+ if (!debug_lockdep_rcu_enabled())
+ return 1;
+
+ return lock_is_held(&sp->dep_map);
}
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
@@ -145,12 +158,17 @@ static inline int srcu_read_lock_held(struct srcu_struct *sp)
* one way to indirectly wait on an SRCU grace period is to acquire
* a mutex that is held elsewhere while calling synchronize_srcu() or
* synchronize_srcu_expedited().
+ *
+ * Note that srcu_read_lock() and the matching srcu_read_unlock() must
+ * occur in the same context, for example, it is illegal to invoke
+ * srcu_read_unlock() in an irq handler if the matching srcu_read_lock()
+ * was invoked in process context.
*/
static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
{
int retval = __srcu_read_lock(sp);
- srcu_read_acquire(sp);
+ rcu_lock_acquire(&(sp)->dep_map);
return retval;
}
@@ -164,8 +182,51 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
__releases(sp)
{
- srcu_read_release(sp);
+ rcu_lock_release(&(sp)->dep_map);
+ __srcu_read_unlock(sp, idx);
+}
+
+/**
+ * srcu_read_lock_raw - register a new reader for an SRCU-protected structure.
+ * @sp: srcu_struct in which to register the new reader.
+ *
+ * Enter an SRCU read-side critical section. Similar to srcu_read_lock(),
+ * but avoids the RCU-lockdep checking. This means that it is legal to
+ * use srcu_read_lock_raw() in one context, for example, in an exception
+ * handler, and then have the matching srcu_read_unlock_raw() in another
+ * context, for example in the task that took the exception.
+ *
+ * However, the entire SRCU read-side critical section must reside within a
+ * single task. For example, beware of using srcu_read_lock_raw() in
+ * a device interrupt handler and srcu_read_unlock() in the interrupted
+ * task: This will not work if interrupts are threaded.
+ */
+static inline int srcu_read_lock_raw(struct srcu_struct *sp)
+{
+ unsigned long flags;
+ int ret;
+
+ local_irq_save(flags);
+ ret = __srcu_read_lock(sp);
+ local_irq_restore(flags);
+ return ret;
+}
+
+/**
+ * srcu_read_unlock_raw - unregister reader from an SRCU-protected structure.
+ * @sp: srcu_struct in which to unregister the old reader.
+ * @idx: return value from corresponding srcu_read_lock_raw().
+ *
+ * Exit an SRCU read-side critical section without lockdep-RCU checking.
+ * See srcu_read_lock_raw() for more details.
+ */
+static inline void srcu_read_unlock_raw(struct srcu_struct *sp, int idx)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
__srcu_read_unlock(sp, idx);
+ local_irq_restore(flags);
}
#endif
diff --git a/include/linux/tick.h b/include/linux/tick.h
index b232ccc0ee2..ab8be90b5cc 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -7,6 +7,7 @@
#define _LINUX_TICK_H
#include <linux/clockchips.h>
+#include <linux/irqflags.h>
#ifdef CONFIG_GENERIC_CLOCKEVENTS
@@ -121,14 +122,16 @@ static inline int tick_oneshot_mode_active(void) { return 0; }
#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
# ifdef CONFIG_NO_HZ
-extern void tick_nohz_stop_sched_tick(int inidle);
-extern void tick_nohz_restart_sched_tick(void);
+extern void tick_nohz_idle_enter(void);
+extern void tick_nohz_idle_exit(void);
+extern void tick_nohz_irq_exit(void);
extern ktime_t tick_nohz_get_sleep_length(void);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
# else
-static inline void tick_nohz_stop_sched_tick(int inidle) { }
-static inline void tick_nohz_restart_sched_tick(void) { }
+static inline void tick_nohz_idle_enter(void) { }
+static inline void tick_nohz_idle_exit(void) { }
+
static inline ktime_t tick_nohz_get_sleep_length(void)
{
ktime_t len = { .tv64 = NSEC_PER_SEC/HZ };
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 3efc9f3f43a..a9ce45e8501 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -77,13 +77,13 @@ struct task_struct;
#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \
{ .flags = word, .bit_nr = bit, }
-extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *);
+extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *);
#define init_waitqueue_head(q) \
do { \
static struct lock_class_key __key; \
\
- __init_waitqueue_head((q), &__key); \
+ __init_waitqueue_head((q), #q, &__key); \
} while (0)
#ifdef CONFIG_LOCKDEP
diff --git a/include/media/soc_camera.h b/include/media/soc_camera.h
index b1377b931eb..5fb2c3d10c0 100644
--- a/include/media/soc_camera.h
+++ b/include/media/soc_camera.h
@@ -254,7 +254,7 @@ unsigned long soc_camera_apply_board_flags(struct soc_camera_link *icl,
static inline struct video_device *soc_camera_i2c_to_vdev(const struct i2c_client *client)
{
struct v4l2_subdev *sd = i2c_get_clientdata(client);
- struct soc_camera_device *icd = (struct soc_camera_device *)sd->grp_id;
+ struct soc_camera_device *icd = v4l2_get_subdev_hostdata(sd);
return icd ? icd->vdev : NULL;
}
@@ -279,6 +279,11 @@ static inline struct soc_camera_device *soc_camera_from_vbq(const struct videobu
return container_of(vq, struct soc_camera_device, vb_vidq);
}
+static inline u32 soc_camera_grp_id(const struct soc_camera_device *icd)
+{
+ return (icd->iface << 8) | (icd->devnum + 1);
+}
+
void soc_camera_lock(struct vb2_queue *vq);
void soc_camera_unlock(struct vb2_queue *vq);
diff --git a/include/net/dst.h b/include/net/dst.h
index 6faec1a6021..75766b42660 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -53,6 +53,7 @@ struct dst_entry {
#define DST_NOHASH 0x0008
#define DST_NOCACHE 0x0010
#define DST_NOCOUNT 0x0020
+#define DST_NOPEER 0x0040
short error;
short obsolete;
diff --git a/include/net/flow.h b/include/net/flow.h
index a09447749e2..57f15a7f1cd 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -207,6 +207,7 @@ extern struct flow_cache_object *flow_cache_lookup(
u8 dir, flow_resolve_t resolver, void *ctx);
extern void flow_cache_flush(void);
+extern void flow_cache_flush_deferred(void);
extern atomic_t flow_cache_genid;
#endif
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 873d5be7926..e5a7b9aaf55 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1207,7 +1207,7 @@ extern void ip_vs_control_cleanup(void);
extern struct ip_vs_dest *
ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
- __u16 protocol, __u32 fwmark);
+ __u16 protocol, __u32 fwmark, __u32 flags);
extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index e90e7a9935d..a15432da27c 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -241,6 +241,9 @@ extern struct sctp_globals {
* bits is an indicator of when to send and window update SACK.
*/
int rwnd_update_shift;
+
+ /* Threshold for autoclose timeout, in seconds. */
+ unsigned long max_autoclose;
} sctp_globals;
#define sctp_rto_initial (sctp_globals.rto_initial)
@@ -281,6 +284,7 @@ extern struct sctp_globals {
#define sctp_auth_enable (sctp_globals.auth_enable)
#define sctp_checksum_disable (sctp_globals.checksum_disable)
#define sctp_rwnd_upd_shift (sctp_globals.rwnd_update_shift)
+#define sctp_max_autoclose (sctp_globals.max_autoclose)
/* SCTP Socket type: UDP or TCP style. */
typedef enum {
diff --git a/include/net/sock.h b/include/net/sock.h
index abb6e0f0c3c..32e39371fba 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -637,12 +637,14 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
/*
* Take into account size of receive queue and backlog queue
+ * Do not take into account this skb truesize,
+ * to allow even a single big packet to come.
*/
static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb)
{
unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);
- return qsize + skb->truesize > sk->sk_rcvbuf;
+ return qsize > sk->sk_rcvbuf;
}
/* The per-socket spinlock must be held here. */
diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h
index d1e95c6ac77..5a35a2a2d3c 100644
--- a/include/scsi/libfcoe.h
+++ b/include/scsi/libfcoe.h
@@ -147,6 +147,7 @@ struct fcoe_ctlr {
u8 map_dest;
u8 spma;
u8 probe_tries;
+ u8 priority;
u8 dest_addr[ETH_ALEN];
u8 ctl_src_addr[ETH_ALEN];
@@ -301,6 +302,7 @@ struct fcoe_percpu_s {
* @lport: The associated local port
* @fcoe_pending_queue: The pending Rx queue of skbs
* @fcoe_pending_queue_active: Indicates if the pending queue is active
+ * @priority: Packet priority (DCB)
* @max_queue_depth: Max queue depth of pending queue
* @min_queue_depth: Min queue depth of pending queue
* @timer: The queue timer
@@ -316,6 +318,7 @@ struct fcoe_port {
struct fc_lport *lport;
struct sk_buff_head fcoe_pending_queue;
u8 fcoe_pending_queue_active;
+ u8 priority;
u32 max_queue_depth;
u32 min_queue_depth;
struct timer_list timer;
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 669fbd62ec2..d2d88bed891 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -241,24 +241,73 @@ TRACE_EVENT(rcu_fqs,
/*
* Tracepoint for dyntick-idle entry/exit events. These take a string
- * as argument: "Start" for entering dyntick-idle mode and "End" for
- * leaving it.
+ * as argument: "Start" for entering dyntick-idle mode, "End" for
+ * leaving it, "--=" for events moving towards idle, and "++=" for events
+ * moving away from idle. "Error on entry: not idle task" and "Error on
+ * exit: not idle task" indicate that a non-idle task is erroneously
+ * toying with the idle loop.
+ *
+ * These events also take a pair of numbers, which indicate the nesting
+ * depth before and after the event of interest. Note that task-related
+ * events use the upper bits of each number, while interrupt-related
+ * events use the lower bits.
*/
TRACE_EVENT(rcu_dyntick,
- TP_PROTO(char *polarity),
+ TP_PROTO(char *polarity, long long oldnesting, long long newnesting),
- TP_ARGS(polarity),
+ TP_ARGS(polarity, oldnesting, newnesting),
TP_STRUCT__entry(
__field(char *, polarity)
+ __field(long long, oldnesting)
+ __field(long long, newnesting)
),
TP_fast_assign(
__entry->polarity = polarity;
+ __entry->oldnesting = oldnesting;
+ __entry->newnesting = newnesting;
+ ),
+
+ TP_printk("%s %llx %llx", __entry->polarity,
+ __entry->oldnesting, __entry->newnesting)
+);
+
+/*
+ * Tracepoint for RCU preparation for idle, the goal being to get RCU
+ * processing done so that the current CPU can shut off its scheduling
+ * clock and enter dyntick-idle mode. One way to accomplish this is
+ * to drain all RCU callbacks from this CPU, and the other is to have
+ * done everything RCU requires for the current grace period. In this
+ * latter case, the CPU will be awakened at the end of the current grace
+ * period in order to process the remainder of its callbacks.
+ *
+ * These tracepoints take a string as argument:
+ *
+ * "No callbacks": Nothing to do, no callbacks on this CPU.
+ * "In holdoff": Nothing to do, holding off after unsuccessful attempt.
+ * "Begin holdoff": Attempt failed, don't retry until next jiffy.
+ * "Dyntick with callbacks": Entering dyntick-idle despite callbacks.
+ * "More callbacks": Still more callbacks, try again to clear them out.
+ * "Callbacks drained": All callbacks processed, off to dyntick idle!
+ * "Timer": Timer fired to cause CPU to continue processing callbacks.
+ */
+TRACE_EVENT(rcu_prep_idle,
+
+ TP_PROTO(char *reason),
+
+ TP_ARGS(reason),
+
+ TP_STRUCT__entry(
+ __field(char *, reason)
+ ),
+
+ TP_fast_assign(
+ __entry->reason = reason;
),
- TP_printk("%s", __entry->polarity)
+ TP_printk("%s", __entry->reason)
);
/*
@@ -412,27 +461,71 @@ TRACE_EVENT(rcu_invoke_kfree_callback,
/*
* Tracepoint for exiting rcu_do_batch after RCU callbacks have been
- * invoked. The first argument is the name of the RCU flavor and
- * the second argument is number of callbacks actually invoked.
+ * invoked. The first argument is the name of the RCU flavor,
+ * the second argument is number of callbacks actually invoked,
+ * the third argument (cb) is whether or not any of the callbacks that
+ * were ready to invoke at the beginning of this batch are still
+ * queued, the fourth argument (nr) is the return value of need_resched(),
+ * the fifth argument (iit) is 1 if the current task is the idle task,
+ * and the sixth argument (risk) is the return value from
+ * rcu_is_callbacks_kthread().
*/
TRACE_EVENT(rcu_batch_end,
- TP_PROTO(char *rcuname, int callbacks_invoked),
+ TP_PROTO(char *rcuname, int callbacks_invoked,
+ bool cb, bool nr, bool iit, bool risk),
- TP_ARGS(rcuname, callbacks_invoked),
+ TP_ARGS(rcuname, callbacks_invoked, cb, nr, iit, risk),
TP_STRUCT__entry(
__field(char *, rcuname)
__field(int, callbacks_invoked)
+ __field(bool, cb)
+ __field(bool, nr)
+ __field(bool, iit)
+ __field(bool, risk)
),
TP_fast_assign(
__entry->rcuname = rcuname;
__entry->callbacks_invoked = callbacks_invoked;
+ __entry->cb = cb;
+ __entry->nr = nr;
+ __entry->iit = iit;
+ __entry->risk = risk;
+ ),
+
+ TP_printk("%s CBs-invoked=%d idle=%c%c%c%c",
+ __entry->rcuname, __entry->callbacks_invoked,
+ __entry->cb ? 'C' : '.',
+ __entry->nr ? 'S' : '.',
+ __entry->iit ? 'I' : '.',
+ __entry->risk ? 'R' : '.')
+);
+
+/*
+ * Tracepoint for rcutorture readers. The first argument is the name
+ * of the RCU flavor from rcutorture's viewpoint and the second argument
+ * is the callback address.
+ */
+TRACE_EVENT(rcu_torture_read,
+
+ TP_PROTO(char *rcutorturename, struct rcu_head *rhp),
+
+ TP_ARGS(rcutorturename, rhp),
+
+ TP_STRUCT__entry(
+ __field(char *, rcutorturename)
+ __field(struct rcu_head *, rhp)
+ ),
+
+ TP_fast_assign(
+ __entry->rcutorturename = rcutorturename;
+ __entry->rhp = rhp;
),
- TP_printk("%s CBs-invoked=%d",
- __entry->rcuname, __entry->callbacks_invoked)
+ TP_printk("%s torture read %p",
+ __entry->rcutorturename, __entry->rhp)
);
#else /* #ifdef CONFIG_RCU_TRACE */
@@ -443,13 +536,16 @@ TRACE_EVENT(rcu_batch_end,
#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0)
#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
-#define trace_rcu_dyntick(polarity) do { } while (0)
+#define trace_rcu_dyntick(polarity, oldnesting, newnesting) do { } while (0)
+#define trace_rcu_prep_idle(reason) do { } while (0)
#define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0)
#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0)
#define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0)
#define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0)
#define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0)
-#define trace_rcu_batch_end(rcuname, callbacks_invoked) do { } while (0)
+#define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \
+ do { } while (0)
+#define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
#endif /* #else #ifdef CONFIG_RCU_TRACE */
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index b99caa8b780..99d1d0decf8 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -21,6 +21,16 @@
{I_REFERENCED, "I_REFERENCED"} \
)
+#define WB_WORK_REASON \
+ {WB_REASON_BACKGROUND, "background"}, \
+ {WB_REASON_TRY_TO_FREE_PAGES, "try_to_free_pages"}, \
+ {WB_REASON_SYNC, "sync"}, \
+ {WB_REASON_PERIODIC, "periodic"}, \
+ {WB_REASON_LAPTOP_TIMER, "laptop_timer"}, \
+ {WB_REASON_FREE_MORE_MEM, "free_more_memory"}, \
+ {WB_REASON_FS_FREE_SPACE, "fs_free_space"}, \
+ {WB_REASON_FORKER_THREAD, "forker_thread"}
+
struct wb_writeback_work;
DECLARE_EVENT_CLASS(writeback_work_class,
@@ -55,7 +65,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
__entry->for_kupdate,
__entry->range_cyclic,
__entry->for_background,
- wb_reason_name[__entry->reason]
+ __print_symbolic(__entry->reason, WB_WORK_REASON)
)
);
#define DEFINE_WRITEBACK_WORK_EVENT(name) \
@@ -184,7 +194,8 @@ TRACE_EVENT(writeback_queue_io,
__entry->older, /* older_than_this in jiffies */
__entry->age, /* older_than_this in relative milliseconds */
__entry->moved,
- wb_reason_name[__entry->reason])
+ __print_symbolic(__entry->reason, WB_WORK_REASON)
+ )
);
TRACE_EVENT(global_dirty_state,
diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h
index f0b6890370b..f6f07aa35af 100644
--- a/include/xen/interface/io/xs_wire.h
+++ b/include/xen/interface/io/xs_wire.h
@@ -29,8 +29,7 @@ enum xsd_sockmsg_type
XS_IS_DOMAIN_INTRODUCED,
XS_RESUME,
XS_SET_TARGET,
- XS_RESTRICT,
- XS_RESET_WATCHES
+ XS_RESTRICT
};
#define XS_WRITE_NONE "NONE"