aboutsummaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/dma-mapping-common.h6
-rw-r--r--include/linux/ata.h36
-rw-r--r--include/linux/cpu.h17
-rw-r--r--include/linux/dma-mapping.h5
-rw-r--r--include/linux/dmi.h13
-rw-r--r--include/linux/ftrace_event.h51
-rw-r--r--include/linux/hardirq.h10
-rw-r--r--include/linux/init_task.h11
-rw-r--r--include/linux/interrupt.h4
-rw-r--r--include/linux/irq.h18
-rw-r--r--include/linux/irqnr.h6
-rw-r--r--include/linux/kernel.h5
-rw-r--r--include/linux/libata.h3
-rw-r--r--include/linux/lockdep.h18
-rw-r--r--include/linux/module.h14
-rw-r--r--include/linux/nmi.h19
-rw-r--r--include/linux/oprofile.h5
-rw-r--r--include/linux/pagemap.h4
-rw-r--r--include/linux/pci_ids.h4
-rw-r--r--include/linux/perf_counter.h7
-rw-r--r--include/linux/rcuclassic.h178
-rw-r--r--include/linux/rcupdate.h98
-rw-r--r--include/linux/rcupreempt.h127
-rw-r--r--include/linux/rcupreempt_trace.h97
-rw-r--r--include/linux/rcutree.h262
-rw-r--r--include/linux/ring_buffer.h24
-rw-r--r--include/linux/sched.h126
-rw-r--r--include/linux/spinlock.h64
-rw-r--r--include/linux/spinlock_api_smp.h394
-rw-r--r--include/linux/swiotlb.h11
-rw-r--r--include/linux/syscalls.h131
-rw-r--r--include/linux/topology.h168
-rw-r--r--include/linux/tracepoint.h29
-rw-r--r--include/trace/define_trace.h7
-rw-r--r--include/trace/events/module.h126
-rw-r--r--include/trace/events/sched.h107
-rw-r--r--include/trace/events/syscalls.h70
-rw-r--r--include/trace/ftrace.h93
-rw-r--r--include/trace/syscall.h48
39 files changed, 1460 insertions, 956 deletions
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index 5406a601185..e694263445f 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -103,7 +103,6 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
if (ops->sync_single_for_cpu)
ops->sync_single_for_cpu(dev, addr, size, dir);
debug_dma_sync_single_for_cpu(dev, addr, size, dir);
- flush_write_buffers();
}
static inline void dma_sync_single_for_device(struct device *dev,
@@ -116,7 +115,6 @@ static inline void dma_sync_single_for_device(struct device *dev,
if (ops->sync_single_for_device)
ops->sync_single_for_device(dev, addr, size, dir);
debug_dma_sync_single_for_device(dev, addr, size, dir);
- flush_write_buffers();
}
static inline void dma_sync_single_range_for_cpu(struct device *dev,
@@ -132,7 +130,6 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
ops->sync_single_range_for_cpu(dev, addr, offset, size, dir);
debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
- flush_write_buffers();
} else
dma_sync_single_for_cpu(dev, addr, size, dir);
}
@@ -150,7 +147,6 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
ops->sync_single_range_for_device(dev, addr, offset, size, dir);
debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
- flush_write_buffers();
} else
dma_sync_single_for_device(dev, addr, size, dir);
}
@@ -165,7 +161,6 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
if (ops->sync_sg_for_cpu)
ops->sync_sg_for_cpu(dev, sg, nelems, dir);
debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
- flush_write_buffers();
}
static inline void
@@ -179,7 +174,6 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
ops->sync_sg_for_device(dev, sg, nelems, dir);
debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
- flush_write_buffers();
}
#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL)
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 9c75921f0c1..6299a259ed1 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -210,15 +210,25 @@ enum {
ATA_CMD_STANDBY = 0xE2, /* place in standby power mode */
ATA_CMD_IDLE = 0xE3, /* place in idle power mode */
ATA_CMD_EDD = 0x90, /* execute device diagnostic */
+ ATA_CMD_DOWNLOAD_MICRO = 0x92,
+ ATA_CMD_NOP = 0x00,
ATA_CMD_FLUSH = 0xE7,
ATA_CMD_FLUSH_EXT = 0xEA,
ATA_CMD_ID_ATA = 0xEC,
ATA_CMD_ID_ATAPI = 0xA1,
+ ATA_CMD_SERVICE = 0xA2,
ATA_CMD_READ = 0xC8,
ATA_CMD_READ_EXT = 0x25,
+ ATA_CMD_READ_QUEUED = 0x26,
+ ATA_CMD_READ_STREAM_EXT = 0x2B,
+ ATA_CMD_READ_STREAM_DMA_EXT = 0x2A,
ATA_CMD_WRITE = 0xCA,
ATA_CMD_WRITE_EXT = 0x35,
+ ATA_CMD_WRITE_QUEUED = 0x36,
+ ATA_CMD_WRITE_STREAM_EXT = 0x3B,
+ ATA_CMD_WRITE_STREAM_DMA_EXT = 0x3A,
ATA_CMD_WRITE_FUA_EXT = 0x3D,
+ ATA_CMD_WRITE_QUEUED_FUA_EXT = 0x3E,
ATA_CMD_FPDMA_READ = 0x60,
ATA_CMD_FPDMA_WRITE = 0x61,
ATA_CMD_PIO_READ = 0x20,
@@ -235,6 +245,7 @@ enum {
ATA_CMD_PACKET = 0xA0,
ATA_CMD_VERIFY = 0x40,
ATA_CMD_VERIFY_EXT = 0x42,
+ ATA_CMD_WRITE_UNCORR_EXT = 0x45,
ATA_CMD_STANDBYNOW1 = 0xE0,
ATA_CMD_IDLEIMMEDIATE = 0xE1,
ATA_CMD_SLEEP = 0xE6,
@@ -243,15 +254,34 @@ enum {
ATA_CMD_READ_NATIVE_MAX_EXT = 0x27,
ATA_CMD_SET_MAX = 0xF9,
ATA_CMD_SET_MAX_EXT = 0x37,
- ATA_CMD_READ_LOG_EXT = 0x2f,
+ ATA_CMD_READ_LOG_EXT = 0x2F,
+ ATA_CMD_WRITE_LOG_EXT = 0x3F,
+ ATA_CMD_READ_LOG_DMA_EXT = 0x47,
+ ATA_CMD_WRITE_LOG_DMA_EXT = 0x57,
+ ATA_CMD_TRUSTED_RCV = 0x5C,
+ ATA_CMD_TRUSTED_RCV_DMA = 0x5D,
+ ATA_CMD_TRUSTED_SND = 0x5E,
+ ATA_CMD_TRUSTED_SND_DMA = 0x5F,
ATA_CMD_PMP_READ = 0xE4,
ATA_CMD_PMP_WRITE = 0xE8,
ATA_CMD_CONF_OVERLAY = 0xB1,
+ ATA_CMD_SEC_SET_PASS = 0xF1,
+ ATA_CMD_SEC_UNLOCK = 0xF2,
+ ATA_CMD_SEC_ERASE_PREP = 0xF3,
+ ATA_CMD_SEC_ERASE_UNIT = 0xF4,
ATA_CMD_SEC_FREEZE_LOCK = 0xF5,
+ ATA_CMD_SEC_DISABLE_PASS = 0xF6,
+ ATA_CMD_CONFIG_STREAM = 0x51,
ATA_CMD_SMART = 0xB0,
ATA_CMD_MEDIA_LOCK = 0xDE,
ATA_CMD_MEDIA_UNLOCK = 0xDF,
ATA_CMD_DSM = 0x06,
+ ATA_CMD_CHK_MED_CRD_TYP = 0xD1,
+ ATA_CMD_CFA_REQ_EXT_ERR = 0x03,
+ ATA_CMD_CFA_WRITE_NE = 0x38,
+ ATA_CMD_CFA_TRANS_SECT = 0x87,
+ ATA_CMD_CFA_ERASE = 0xC0,
+ ATA_CMD_CFA_WRITE_MULT_NE = 0xCD,
/* marked obsolete in the ATA/ATAPI-7 spec */
ATA_CMD_RESTORE = 0x10,
@@ -306,6 +336,7 @@ enum {
/* SETFEATURE Sector counts for SATA features */
SATA_AN = 0x05, /* Asynchronous Notification */
SATA_DIPM = 0x03, /* Device Initiated Power Management */
+ SATA_FPDMA_AA = 0x02, /* DMA Setup FIS Auto-Activate */
/* feature values for SET_MAX */
ATA_SET_MAX_ADDR = 0x00,
@@ -525,6 +556,9 @@ static inline int ata_is_data(u8 prot)
#define ata_id_has_atapi_AN(id) \
( (((id)[76] != 0x0000) && ((id)[76] != 0xffff)) && \
((id)[78] & (1 << 5)) )
+#define ata_id_has_fpdma_aa(id) \
+ ( (((id)[76] != 0x0000) && ((id)[76] != 0xffff)) && \
+ ((id)[78] & (1 << 2)) )
#define ata_id_iordy_disable(id) ((id)[ATA_ID_CAPABILITY] & (1 << 10))
#define ata_id_has_iordy(id) ((id)[ATA_ID_CAPABILITY] & (1 << 11))
#define ata_id_u32(id,n) \
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 4d668e05d45..47536197ffd 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -48,6 +48,15 @@ struct notifier_block;
#ifdef CONFIG_SMP
/* Need to know about CPUs going up/down? */
+#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
+#define cpu_notifier(fn, pri) { \
+ static struct notifier_block fn##_nb __cpuinitdata = \
+ { .notifier_call = fn, .priority = pri }; \
+ register_cpu_notifier(&fn##_nb); \
+}
+#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
+#define cpu_notifier(fn, pri) do { (void)(fn); } while (0)
+#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
#ifdef CONFIG_HOTPLUG_CPU
extern int register_cpu_notifier(struct notifier_block *nb);
extern void unregister_cpu_notifier(struct notifier_block *nb);
@@ -74,6 +83,8 @@ extern void cpu_maps_update_done(void);
#else /* CONFIG_SMP */
+#define cpu_notifier(fn, pri) do { (void)(fn); } while (0)
+
static inline int register_cpu_notifier(struct notifier_block *nb)
{
return 0;
@@ -99,11 +110,7 @@ extern struct sysdev_class cpu_sysdev_class;
extern void get_online_cpus(void);
extern void put_online_cpus(void);
-#define hotcpu_notifier(fn, pri) { \
- static struct notifier_block fn##_nb __cpuinitdata = \
- { .notifier_call = fn, .priority = pri }; \
- register_cpu_notifier(&fn##_nb); \
-}
+#define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri)
#define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
#define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb)
int cpu_down(unsigned int cpu);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 07dfd460d28..c0f6c3cd788 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -98,11 +98,6 @@ static inline int is_device_dma_capable(struct device *dev)
return dev->dma_mask != NULL && *dev->dma_mask != DMA_MASK_NONE;
}
-static inline int is_buffer_dma_capable(u64 mask, dma_addr_t addr, size_t size)
-{
- return addr + size <= mask;
-}
-
#ifdef CONFIG_HAS_DMA
#include <asm/dma-mapping.h>
#else
diff --git a/include/linux/dmi.h b/include/linux/dmi.h
index bb5489c82c9..a8a3e1ac281 100644
--- a/include/linux/dmi.h
+++ b/include/linux/dmi.h
@@ -43,7 +43,7 @@ extern const char * dmi_get_system_info(int field);
extern const struct dmi_device * dmi_find_device(int type, const char *name,
const struct dmi_device *from);
extern void dmi_scan_machine(void);
-extern int dmi_get_year(int field);
+extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp);
extern int dmi_name_in_vendors(const char *str);
extern int dmi_name_in_serial(const char *str);
extern int dmi_available;
@@ -58,7 +58,16 @@ static inline const char * dmi_get_system_info(int field) { return NULL; }
static inline const struct dmi_device * dmi_find_device(int type, const char *name,
const struct dmi_device *from) { return NULL; }
static inline void dmi_scan_machine(void) { return; }
-static inline int dmi_get_year(int year) { return 0; }
+static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp)
+{
+ if (yearp)
+ *yearp = 0;
+ if (monthp)
+ *monthp = 0;
+ if (dayp)
+ *dayp = 0;
+ return false;
+}
static inline int dmi_name_in_vendors(const char *s) { return 0; }
static inline int dmi_name_in_serial(const char *s) { return 0; }
#define dmi_available 0
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index a81170de7f6..23f7179bf74 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -93,16 +93,22 @@ void tracing_generic_entry_update(struct trace_entry *entry,
unsigned long flags,
int pc);
struct ring_buffer_event *
-trace_current_buffer_lock_reserve(int type, unsigned long len,
+trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer,
+ int type, unsigned long len,
unsigned long flags, int pc);
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
unsigned long flags, int pc);
-void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event);
void tracing_record_cmdline(struct task_struct *tsk);
+struct event_filter;
+
struct ftrace_event_call {
struct list_head list;
char *name;
@@ -110,16 +116,18 @@ struct ftrace_event_call {
struct dentry *dir;
struct trace_event *event;
int enabled;
- int (*regfunc)(void);
- void (*unregfunc)(void);
+ int (*regfunc)(void *);
+ void (*unregfunc)(void *);
int id;
int (*raw_init)(void);
- int (*show_format)(struct trace_seq *s);
- int (*define_fields)(void);
+ int (*show_format)(struct ftrace_event_call *call,
+ struct trace_seq *s);
+ int (*define_fields)(struct ftrace_event_call *);
struct list_head fields;
int filter_active;
- void *filter;
+ struct event_filter *filter;
void *mod;
+ void *data;
atomic_t profile_count;
int (*profile_enable)(struct ftrace_event_call *);
@@ -129,15 +137,25 @@ struct ftrace_event_call {
#define MAX_FILTER_PRED 32
#define MAX_FILTER_STR_VAL 128
-extern int init_preds(struct ftrace_event_call *call);
extern void destroy_preds(struct ftrace_event_call *call);
extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
-extern int filter_current_check_discard(struct ftrace_event_call *call,
+extern int filter_current_check_discard(struct ring_buffer *buffer,
+ struct ftrace_event_call *call,
void *rec,
struct ring_buffer_event *event);
-extern int trace_define_field(struct ftrace_event_call *call, char *type,
- char *name, int offset, int size, int is_signed);
+enum {
+ FILTER_OTHER = 0,
+ FILTER_STATIC_STRING,
+ FILTER_DYN_STRING,
+ FILTER_PTR_STRING,
+};
+
+extern int trace_define_field(struct ftrace_event_call *call,
+ const char *type, const char *name,
+ int offset, int size, int is_signed,
+ int filter_type);
+extern int trace_define_common_fields(struct ftrace_event_call *call);
#define is_signed_type(type) (((type)(-1)) < 0)
@@ -162,11 +180,4 @@ do { \
__trace_printk(ip, fmt, ##args); \
} while (0)
-#define __common_field(type, item, is_signed) \
- ret = trace_define_field(event_call, #type, "common_" #item, \
- offsetof(typeof(field.ent), item), \
- sizeof(field.ent.item), is_signed); \
- if (ret) \
- return ret;
-
#endif /* _LINUX_FTRACE_EVENT_H */
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 8246c697863..6d527ee82b2 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -64,6 +64,12 @@
#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
#define NMI_OFFSET (1UL << NMI_SHIFT)
+#ifndef PREEMPT_ACTIVE
+#define PREEMPT_ACTIVE_BITS 1
+#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS)
+#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
+#endif
+
#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
#error PREEMPT_ACTIVE is too low!
#endif
@@ -132,7 +138,7 @@ static inline void account_system_vtime(struct task_struct *tsk)
}
#endif
-#if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU)
+#if defined(CONFIG_NO_HZ)
extern void rcu_irq_enter(void);
extern void rcu_irq_exit(void);
extern void rcu_nmi_enter(void);
@@ -142,7 +148,7 @@ extern void rcu_nmi_exit(void);
# 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) && !defined(CONFIG_CLASSIC_RCU) */
+#endif /* #if defined(CONFIG_NO_HZ) */
/*
* It is safe to do non-atomic ops on ->hardirq_context,
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 7fc01b13be4..9e7f2e8fc66 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -94,6 +94,16 @@ extern struct group_info init_groups;
# define CAP_INIT_BSET CAP_INIT_EFF_SET
#endif
+#ifdef CONFIG_TREE_PREEMPT_RCU
+#define INIT_TASK_RCU_PREEMPT(tsk) \
+ .rcu_read_lock_nesting = 0, \
+ .rcu_read_unlock_special = 0, \
+ .rcu_blocked_node = NULL, \
+ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),
+#else
+#define INIT_TASK_RCU_PREEMPT(tsk)
+#endif
+
extern struct cred init_cred;
#ifdef CONFIG_PERF_COUNTERS
@@ -173,6 +183,7 @@ extern struct cred init_cred;
INIT_LOCKDEP \
INIT_FTRACE_GRAPH \
INIT_TRACE_RECURSION \
+ INIT_TASK_RCU_PREEMPT(tsk) \
}
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 35e7df1e9f3..1ac57e522a1 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -50,6 +50,9 @@
* IRQF_IRQPOLL - Interrupt is used for polling (only the interrupt that is
* registered first in an shared interrupt is considered for
* performance reasons)
+ * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished.
+ * Used by threaded interrupts which need to keep the
+ * irq line disabled until the threaded handler has been run.
*/
#define IRQF_DISABLED 0x00000020
#define IRQF_SAMPLE_RANDOM 0x00000040
@@ -59,6 +62,7 @@
#define IRQF_PERCPU 0x00000400
#define IRQF_NOBALANCING 0x00000800
#define IRQF_IRQPOLL 0x00001000
+#define IRQF_ONESHOT 0x00002000
/*
* Bits used by threaded handlers:
diff --git a/include/linux/irq.h b/include/linux/irq.h
index cb2e77a3f7f..ae9653dbcd7 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -69,6 +69,8 @@ typedef void (*irq_flow_handler_t)(unsigned int irq,
#define IRQ_MOVE_PCNTXT 0x01000000 /* IRQ migration from process context */
#define IRQ_AFFINITY_SET 0x02000000 /* IRQ affinity was set from userspace*/
#define IRQ_SUSPENDED 0x04000000 /* IRQ has gone through suspend sequence */
+#define IRQ_ONESHOT 0x08000000 /* IRQ is not unmasked after hardirq */
+#define IRQ_NESTED_THREAD 0x10000000 /* IRQ is nested into another, no own handler thread */
#ifdef CONFIG_IRQ_PER_CPU
# define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
@@ -100,6 +102,9 @@ struct msi_desc;
* @set_type: set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
* @set_wake: enable/disable power-management wake-on of an IRQ
*
+ * @bus_lock: function to lock access to slow bus (i2c) chips
+ * @bus_sync_unlock: function to sync and unlock slow bus (i2c) chips
+ *
* @release: release function solely used by UML
* @typename: obsoleted by name, kept as migration helper
*/
@@ -123,6 +128,9 @@ struct irq_chip {
int (*set_type)(unsigned int irq, unsigned int flow_type);
int (*set_wake)(unsigned int irq, unsigned int on);
+ void (*bus_lock)(unsigned int irq);
+ void (*bus_sync_unlock)(unsigned int irq);
+
/* Currently used only by UML, might disappear one day.*/
#ifdef CONFIG_IRQ_RELEASE_METHOD
void (*release)(unsigned int irq, void *dev_id);
@@ -220,13 +228,6 @@ static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
/*
- * Migration helpers for obsolete names, they will go away:
- */
-#define hw_interrupt_type irq_chip
-#define no_irq_type no_irq_chip
-typedef struct irq_desc irq_desc_t;
-
-/*
* Pick up the arch-dependent methods:
*/
#include <asm/hw_irq.h>
@@ -289,6 +290,7 @@ extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc);
extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc);
extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc);
extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
+extern void handle_nested_irq(unsigned int irq);
/*
* Monolithic do_IRQ implementation.
@@ -379,6 +381,8 @@ set_irq_chained_handler(unsigned int irq,
__set_irq_handler(irq, handle, 1, NULL);
}
+extern void set_irq_nested_thread(unsigned int irq, int nest);
+
extern void set_irq_noprobe(unsigned int irq);
extern void set_irq_probe(unsigned int irq);
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index ec87b212ff7..7bf89bc8cbc 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -41,6 +41,12 @@ extern struct irq_desc *irq_to_desc(unsigned int irq);
; \
else
+#ifdef CONFIG_SMP
+#define irq_node(irq) (irq_to_desc(irq)->node)
+#else
+#define irq_node(irq) 0
+#endif
+
#endif /* CONFIG_GENERIC_HARDIRQS */
#define for_each_irq_nr(irq) \
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d6320a3e8de..2b5b1e0899a 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -125,7 +125,7 @@ extern int _cond_resched(void);
#endif
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
- void __might_sleep(char *file, int line);
+ void __might_sleep(char *file, int line, int preempt_offset);
/**
* might_sleep - annotation for functions that can sleep
*
@@ -137,8 +137,9 @@ extern int _cond_resched(void);
* supposed to.
*/
# define might_sleep() \
- do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0)
+ do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
#else
+ static inline void __might_sleep(char *file, int line, int preempt_offset) { }
# define might_sleep() do { might_resched(); } while (0)
#endif
diff --git a/include/linux/libata.h b/include/linux/libata.h
index e5b6e33c657..76319bf03e3 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -143,7 +143,6 @@ enum {
ATA_DFLAG_PIO = (1 << 12), /* device limited to PIO mode */
ATA_DFLAG_NCQ_OFF = (1 << 13), /* device limited to non-NCQ mode */
- ATA_DFLAG_SPUNDOWN = (1 << 14), /* XXX: for spindown_compat */
ATA_DFLAG_SLEEPING = (1 << 15), /* device is sleeping */
ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */
ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */
@@ -190,6 +189,7 @@ enum {
ATA_FLAG_NO_POWEROFF_SPINDOWN = (1 << 11), /* don't spindown before poweroff */
ATA_FLAG_NO_HIBERNATE_SPINDOWN = (1 << 12), /* don't spindown before hibernation */
ATA_FLAG_DEBUGMSG = (1 << 13),
+ ATA_FLAG_FPDMA_AA = (1 << 14), /* driver supports Auto-Activate */
ATA_FLAG_IGN_SIMPLEX = (1 << 15), /* ignore SIMPLEX */
ATA_FLAG_NO_IORDY = (1 << 16), /* controller lacks iordy */
ATA_FLAG_ACPI_SATA = (1 << 17), /* need native SATA ACPI layout */
@@ -386,6 +386,7 @@ enum {
ATA_HORKAGE_FIRMWARE_WARN = (1 << 12), /* firmware update warning */
ATA_HORKAGE_1_5_GBPS = (1 << 13), /* force 1.5 Gbps */
ATA_HORKAGE_NOSETXFER = (1 << 14), /* skip SETXFER, SATA only */
+ ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */
/* DMA mask for user DMA control: User visible values; DO NOT
renumber */
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b25d1b53df0..9ccf0e286b2 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -149,6 +149,12 @@ struct lock_list {
struct lock_class *class;
struct stack_trace trace;
int distance;
+
+ /*
+ * The parent field is used to implement breadth-first search, and the
+ * bit 0 is reused to indicate if the lock has been accessed in BFS.
+ */
+ struct lock_list *parent;
};
/*
@@ -208,10 +214,12 @@ struct held_lock {
* interrupt context:
*/
unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */
- unsigned int trylock:1;
+ unsigned int trylock:1; /* 16 bits */
+
unsigned int read:2; /* see lock_acquire() comment */
unsigned int check:2; /* see lock_acquire() comment */
unsigned int hardirqs_off:1;
+ unsigned int references:11; /* 32 bits */
};
/*
@@ -291,6 +299,10 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
extern void lock_release(struct lockdep_map *lock, int nested,
unsigned long ip);
+#define lockdep_is_held(lock) lock_is_held(&(lock)->dep_map)
+
+extern int lock_is_held(struct lockdep_map *lock);
+
extern void lock_set_class(struct lockdep_map *lock, const char *name,
struct lock_class_key *key, unsigned int subclass,
unsigned long ip);
@@ -309,6 +321,8 @@ extern void lockdep_trace_alloc(gfp_t mask);
#define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0)
+#define lockdep_assert_held(l) WARN_ON(debug_locks && !lockdep_is_held(l))
+
#else /* !LOCKDEP */
static inline void lockdep_off(void)
@@ -353,6 +367,8 @@ struct lock_class_key { };
#define lockdep_depth(tsk) (0)
+#define lockdep_assert_held(l) do { } while (0)
+
#endif /* !LOCKDEP */
#ifdef CONFIG_LOCK_STAT
diff --git a/include/linux/module.h b/include/linux/module.h
index 098bdb7bfac..f8f92d015ef 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -17,10 +17,12 @@
#include <linux/moduleparam.h>
#include <linux/marker.h>
#include <linux/tracepoint.h>
-#include <asm/local.h>
+#include <asm/local.h>
#include <asm/module.h>
+#include <trace/events/module.h>
+
/* Not Yet Implemented */
#define MODULE_SUPPORTED_DEVICE(name)
@@ -462,7 +464,10 @@ static inline local_t *__module_ref_addr(struct module *mod, int cpu)
static inline void __module_get(struct module *module)
{
if (module) {
- local_inc(__module_ref_addr(module, get_cpu()));
+ unsigned int cpu = get_cpu();
+ local_inc(__module_ref_addr(module, cpu));
+ trace_module_get(module, _THIS_IP_,
+ local_read(__module_ref_addr(module, cpu)));
put_cpu();
}
}
@@ -473,8 +478,11 @@ static inline int try_module_get(struct module *module)
if (module) {
unsigned int cpu = get_cpu();
- if (likely(module_is_live(module)))
+ if (likely(module_is_live(module))) {
local_inc(__module_ref_addr(module, cpu));
+ trace_module_get(module, _THIS_IP_,
+ local_read(__module_ref_addr(module, cpu)));
+ }
else
ret = 0;
put_cpu();
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 29af2d5df09..b752e807add 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -28,8 +28,23 @@ static inline void acpi_nmi_disable(void) { }
static inline void acpi_nmi_enable(void) { }
#endif
-#ifndef trigger_all_cpu_backtrace
-#define trigger_all_cpu_backtrace() do { } while (0)
+/*
+ * Create trigger_all_cpu_backtrace() out of the arch-provided
+ * base function. Return whether such support was available,
+ * to allow calling code to fall back to some other mechanism:
+ */
+#ifdef arch_trigger_all_cpu_backtrace
+static inline bool trigger_all_cpu_backtrace(void)
+{
+ arch_trigger_all_cpu_backtrace();
+
+ return true;
+}
+#else
+static inline bool trigger_all_cpu_backtrace(void)
+{
+ return false;
+}
#endif
#endif
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 1d9518bc4c5..5171639ecf0 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -67,6 +67,9 @@ struct oprofile_operations {
/* Initiate a stack backtrace. Optional. */
void (*backtrace)(struct pt_regs * const regs, unsigned int depth);
+
+ /* Multiplex between different events. Optional. */
+ int (*switch_events)(void);
/* CPU identification string. */
char * cpu_type;
};
@@ -171,7 +174,6 @@ struct op_sample;
struct op_entry {
struct ring_buffer_event *event;
struct op_sample *sample;
- unsigned long irq_flags;
unsigned long size;
unsigned long *data;
};
@@ -180,6 +182,7 @@ void oprofile_write_reserve(struct op_entry *entry,
struct pt_regs * const regs,
unsigned long pc, int code, int size);
int oprofile_add_data(struct op_entry *entry, unsigned long val);
+int oprofile_add_data64(struct op_entry *entry, u64 val);
int oprofile_write_commit(struct op_entry *entry);
#endif /* OPROFILE_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index aec3252afcf..ed5d7501e18 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -132,7 +132,7 @@ static inline int page_cache_get_speculative(struct page *page)
{
VM_BUG_ON(in_interrupt());
-#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU)
+#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
# ifdef CONFIG_PREEMPT
VM_BUG_ON(!in_atomic());
# endif
@@ -170,7 +170,7 @@ static inline int page_cache_add_speculative(struct page *page, int count)
{
VM_BUG_ON(in_interrupt());
-#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU)
+#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
# ifdef CONFIG_PREEMPT
VM_BUG_ON(!in_atomic());
# endif
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 73b46b6b904..c8fdcadce43 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -376,6 +376,9 @@
#define PCI_DEVICE_ID_ATI_IXP600_IDE 0x438c
#define PCI_DEVICE_ID_ATI_IXP700_SATA 0x4390
#define PCI_DEVICE_ID_ATI_IXP700_IDE 0x439c
+/* AMD SB Chipset */
+#define PCI_DEVICE_ID_AMD_SB900_IDE 0x780c
+#define PCI_DEVICE_ID_AMD_SB900_SATA_IDE 0x7800
#define PCI_VENDOR_ID_VLSI 0x1004
#define PCI_DEVICE_ID_VLSI_82C592 0x0005
@@ -537,6 +540,7 @@
#define PCI_DEVICE_ID_AMD_8131_BRIDGE 0x7450
#define PCI_DEVICE_ID_AMD_8131_APIC 0x7451
#define PCI_DEVICE_ID_AMD_8132_BRIDGE 0x7458
+#define PCI_DEVICE_ID_AMD_CS5535_IDE 0x208F
#define PCI_DEVICE_ID_AMD_CS5536_ISA 0x2090
#define PCI_DEVICE_ID_AMD_CS5536_FLASH 0x2091
#define PCI_DEVICE_ID_AMD_CS5536_AUDIO 0x2093
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index b53f7006cc4..972f90d7a32 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -216,6 +216,7 @@ struct perf_counter_attr {
#define PERF_COUNTER_IOC_REFRESH _IO ('$', 2)
#define PERF_COUNTER_IOC_RESET _IO ('$', 3)
#define PERF_COUNTER_IOC_PERIOD _IOW('$', 4, u64)
+#define PERF_COUNTER_IOC_SET_OUTPUT _IO ('$', 5)
enum perf_counter_ioc_flags {
PERF_IOC_FLAG_GROUP = 1U << 0,
@@ -415,6 +416,9 @@ enum perf_callchain_context {
PERF_CONTEXT_MAX = (__u64)-4095,
};
+#define PERF_FLAG_FD_NO_GROUP (1U << 0)
+#define PERF_FLAG_FD_OUTPUT (1U << 1)
+
#ifdef __KERNEL__
/*
* Kernel-internal data types and definitions:
@@ -536,6 +540,7 @@ struct perf_counter {
struct list_head sibling_list;
int nr_siblings;
struct perf_counter *group_leader;
+ struct perf_counter *output;
const struct pmu *pmu;
enum perf_counter_active_state state;
@@ -761,6 +766,8 @@ extern int sysctl_perf_counter_mlock;
extern int sysctl_perf_counter_sample_rate;
extern void perf_counter_init(void);
+extern void perf_tpcounter_event(int event_id, u64 addr, u64 count,
+ void *record, int entry_size);
#ifndef perf_misc_flags
#define perf_misc_flags(regs) (user_mode(regs) ? PERF_EVENT_MISC_USER : \
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
deleted file mode 100644
index bfd92e1e5d2..00000000000
--- a/include/linux/rcuclassic.h
+++ /dev/null
@@ -1,178 +0,0 @@
-/*
- * Read-Copy Update mechanism for mutual exclusion (classic version)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright IBM Corporation, 2001
- *
- * Author: Dipankar Sarma <dipankar@in.ibm.com>
- *
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
- * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
- * Papers:
- * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
- * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
- *
- * For detailed explanation of Read-Copy Update mechanism see -
- * Documentation/RCU
- *
- */
-
-#ifndef __LINUX_RCUCLASSIC_H
-#define __LINUX_RCUCLASSIC_H
-
-#include <linux/cache.h>
-#include <linux/spinlock.h>
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/seqlock.h>
-
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ) /* for rcp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ) /* for rcp->jiffies_stall */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-/* Global control variables for rcupdate callback mechanism. */
-struct rcu_ctrlblk {
- long cur; /* Current batch number. */
- long completed; /* Number of the last completed batch */
- long pending; /* Number of the last pending batch */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
- unsigned long gp_start; /* Time at which GP started in jiffies. */
- unsigned long jiffies_stall;
- /* Time at which to check for CPU stalls. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
- int signaled;
-
- spinlock_t lock ____cacheline_internodealigned_in_smp;
- DECLARE_BITMAP(cpumask, NR_CPUS); /* CPUs that need to switch for */
- /* current batch to proceed. */
-} ____cacheline_internodealigned_in_smp;
-
-/* Is batch a before batch b ? */
-static inline int rcu_batch_before(long a, long b)
-{
- return (a - b) < 0;
-}
-
-/* Is batch a after batch b ? */
-static inline int rcu_batch_after(long a, long b)
-{
- return (a - b) > 0;
-}
-
-/* Per-CPU data for Read-Copy UPdate. */
-struct rcu_data {
- /* 1) quiescent state handling : */
- long quiescbatch; /* Batch # for grace period */
- int passed_quiesc; /* User-mode/idle loop etc. */
- int qs_pending; /* core waits for quiesc state */
-
- /* 2) batch handling */
- /*
- * if nxtlist is not NULL, then:
- * batch:
- * The batch # for the last entry of nxtlist
- * [*nxttail[1], NULL = *nxttail[2]):
- * Entries that batch # <= batch
- * [*nxttail[0], *nxttail[1]):
- * Entries that batch # <= batch - 1
- * [nxtlist, *nxttail[0]):
- * Entries that batch # <= batch - 2
- * The grace period for these entries has completed, and
- * the other grace-period-completed entries may be moved
- * here temporarily in rcu_process_callbacks().
- */
- long batch;
- struct rcu_head *nxtlist;
- struct rcu_head **nxttail[3];
- long qlen; /* # of queued callbacks */
- struct rcu_head *donelist;
- struct rcu_head **donetail;
- long blimit; /* Upper limit on a processed batch */
- int cpu;
- struct rcu_head barrier;
-};
-
-/*
- * Increment the quiescent state counter.
- * The counter is a bit degenerated: We do not need to know
- * how many quiescent states passed, just if there was at least
- * one since the start of the grace period. Thus just a flag.
- */
-extern void rcu_qsctr_inc(int cpu);
-extern void rcu_bh_qsctr_inc(int cpu);
-
-extern int rcu_pending(int cpu);
-extern int rcu_needs_cpu(int cpu);
-
-#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_)
-#else
-# define rcu_read_acquire() do { } while (0)
-# define rcu_read_release() do { } while (0)
-#endif
-
-#define __rcu_read_lock() \
- do { \
- preempt_disable(); \
- __acquire(RCU); \
- rcu_read_acquire(); \
- } while (0)
-#define __rcu_read_unlock() \
- do { \
- rcu_read_release(); \
- __release(RCU); \
- preempt_enable(); \
- } while (0)
-#define __rcu_read_lock_bh() \
- do { \
- local_bh_disable(); \
- __acquire(RCU_BH); \
- rcu_read_acquire(); \
- } while (0)
-#define __rcu_read_unlock_bh() \
- do { \
- rcu_read_release(); \
- __release(RCU_BH); \
- local_bh_enable(); \
- } while (0)
-
-#define __synchronize_sched() synchronize_rcu()
-
-#define call_rcu_sched(head, func) call_rcu(head, func)
-
-extern void __rcu_init(void);
-#define rcu_init_sched() do { } while (0)
-extern void rcu_check_callbacks(int cpu, int user);
-extern void rcu_restart_cpu(int cpu);
-
-extern long rcu_batches_completed(void);
-extern long rcu_batches_completed_bh(void);
-
-#define rcu_enter_nohz() do { } while (0)
-#define rcu_exit_nohz() do { } while (0)
-
-/* A context switch is a grace period for rcuclassic. */
-static inline int rcu_blocking_is_gp(void)
-{
- return num_online_cpus() == 1;
-}
-
-#endif /* __LINUX_RCUCLASSIC_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 15fbb3ca634..95e0615f4d7 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -51,18 +51,26 @@ struct rcu_head {
void (*func)(struct rcu_head *head);
};
-/* Internal to kernel, but needed by rcupreempt.h. */
+/* Exported common interfaces */
+extern void synchronize_rcu(void);
+extern void synchronize_rcu_bh(void);
+extern void rcu_barrier(void);
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
+extern void synchronize_sched_expedited(void);
+extern int sched_expedited_torture_stats(char *page);
+
+/* Internal to kernel */
+extern void rcu_init(void);
+extern void rcu_scheduler_starting(void);
+extern int rcu_needs_cpu(int cpu);
extern int rcu_scheduler_active;
-#if defined(CONFIG_CLASSIC_RCU)
-#include <linux/rcuclassic.h>
-#elif defined(CONFIG_TREE_RCU)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
#include <linux/rcutree.h>
-#elif defined(CONFIG_PREEMPT_RCU)
-#include <linux/rcupreempt.h>
#else
#error "Unknown RCU implementation specified to kernel configuration"
-#endif /* #else #if defined(CONFIG_CLASSIC_RCU) */
+#endif
#define RCU_HEAD_INIT { .next = NULL, .func = NULL }
#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
@@ -70,6 +78,16 @@ extern int rcu_scheduler_active;
(ptr)->next = NULL; (ptr)->func = NULL; \
} while (0)
+#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_)
+#else
+# define rcu_read_acquire() do { } while (0)
+# define rcu_read_release() do { } while (0)
+#endif
+
/**
* rcu_read_lock - mark the beginning of an RCU read-side critical section.
*
@@ -99,7 +117,12 @@ extern int rcu_scheduler_active;
*
* It is illegal to block while in an RCU read-side critical section.
*/
-#define rcu_read_lock() __rcu_read_lock()
+static inline void rcu_read_lock(void)
+{
+ __rcu_read_lock();
+ __acquire(RCU);
+ rcu_read_acquire();
+}
/**
* rcu_read_unlock - marks the end of an RCU read-side critical section.
@@ -116,7 +139,12 @@ extern int rcu_scheduler_active;
* used as well. RCU does not care how the writers keep out of each
* others' way, as long as they do so.
*/
-#define rcu_read_unlock() __rcu_read_unlock()
+static inline void rcu_read_unlock(void)
+{
+ rcu_read_release();
+ __release(RCU);
+ __rcu_read_unlock();
+}
/**
* rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section
@@ -129,14 +157,24 @@ extern int rcu_scheduler_active;
* can use just rcu_read_lock().
*
*/
-#define rcu_read_lock_bh() __rcu_read_lock_bh()
+static inline void rcu_read_lock_bh(void)
+{
+ __rcu_read_lock_bh();
+ __acquire(RCU_BH);
+ rcu_read_acquire();
+}
/*
* rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
*
* See rcu_read_lock_bh() for more information.
*/
-#define rcu_read_unlock_bh() __rcu_read_unlock_bh()
+static inline void rcu_read_unlock_bh(void)
+{
+ rcu_read_release();
+ __release(RCU_BH);
+ __rcu_read_unlock_bh();
+}
/**
* rcu_read_lock_sched - mark the beginning of a RCU-classic critical section
@@ -147,17 +185,34 @@ extern int rcu_scheduler_active;
* - call_rcu_sched() and rcu_barrier_sched()
* on the write-side to insure proper synchronization.
*/
-#define rcu_read_lock_sched() preempt_disable()
-#define rcu_read_lock_sched_notrace() preempt_disable_notrace()
+static inline void rcu_read_lock_sched(void)
+{
+ preempt_disable();
+ __acquire(RCU_SCHED);
+ rcu_read_acquire();
+}
+static inline notrace void rcu_read_lock_sched_notrace(void)
+{
+ preempt_disable_notrace();
+ __acquire(RCU_SCHED);
+}
/*
* rcu_read_unlock_sched - marks the end of a RCU-classic critical section
*
* See rcu_read_lock_sched for more information.
*/
-#define rcu_read_unlock_sched() preempt_enable()
-#define rcu_read_unlock_sched_notrace() preempt_enable_notrace()
-
+static inline void rcu_read_unlock_sched(void)
+{
+ rcu_read_release();
+ __release(RCU_SCHED);
+ preempt_enable();
+}
+static inline notrace void rcu_read_unlock_sched_notrace(void)
+{
+ __release(RCU_SCHED);
+ preempt_enable_notrace();
+}
/**
@@ -259,15 +314,4 @@ extern void call_rcu(struct rcu_head *head,
extern void call_rcu_bh(struct rcu_head *head,
void (*func)(struct rcu_head *head));
-/* Exported common interfaces */
-extern void synchronize_rcu(void);
-extern void rcu_barrier(void);
-extern void rcu_barrier_bh(void);
-extern void rcu_barrier_sched(void);
-
-/* Internal to kernel */
-extern void rcu_init(void);
-extern void rcu_scheduler_starting(void);
-extern int rcu_needs_cpu(int cpu);
-
#endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
deleted file mode 100644
index fce522782ff..00000000000
--- a/include/linux/rcupreempt.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * Read-Copy Update mechanism for mutual exclusion (RT implementation)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2006
- *
- * Author: Paul McKenney <paulmck@us.ibm.com>
- *
- * Based on the original work by Paul McKenney <paul.mckenney@us.ibm.com>
- * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
- * Papers:
- * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
- * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
- *
- * For detailed explanation of Read-Copy Update mechanism see -
- * Documentation/RCU
- *
- */
-
-#ifndef __LINUX_RCUPREEMPT_H
-#define __LINUX_RCUPREEMPT_H
-
-#include <linux/cache.h>
-#include <linux/spinlock.h>
-#include <linux/threads.h>
-#include <linux/smp.h>
-#include <linux/cpumask.h>
-#include <linux/seqlock.h>
-
-extern void rcu_qsctr_inc(int cpu);
-static inline void rcu_bh_qsctr_inc(int cpu) { }
-
-/*
- * Someone might want to pass call_rcu_bh as a function pointer.
- * So this needs to just be a rename and not a macro function.
- * (no parentheses)
- */
-#define call_rcu_bh call_rcu
-
-/**
- * call_rcu_sched - Queue RCU callback for invocation after sched grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
- *
- * The update function will be invoked some time after a full
- * synchronize_sched()-style grace period elapses, in other words after
- * all currently executing preempt-disabled sections of code (including
- * hardirq handlers, NMI handlers, and local_irq_save() blocks) have
- * completed.
- */
-extern void call_rcu_sched(struct rcu_head *head,
- void (*func)(struct rcu_head *head));
-
-extern void __rcu_read_lock(void) __acquires(RCU);
-extern void __rcu_read_unlock(void) __releases(RCU);
-extern int rcu_pending(int cpu);
-extern int rcu_needs_cpu(int cpu);
-
-#define __rcu_read_lock_bh() { rcu_read_lock(); local_bh_disable(); }
-#define __rcu_read_unlock_bh() { local_bh_enable(); rcu_read_unlock(); }
-
-extern void __synchronize_sched(void);
-
-extern void __rcu_init(void);
-extern void rcu_init_sched(void);
-extern void rcu_check_callbacks(int cpu, int user);
-extern void rcu_restart_cpu(int cpu);
-extern long rcu_batches_completed(void);
-
-/*
- * Return the number of RCU batches processed thus far. Useful for debug
- * and statistic. The _bh variant is identifcal to straight RCU
- */
-static inline long rcu_batches_completed_bh(void)
-{
- return rcu_batches_completed();
-}
-
-#ifdef CONFIG_RCU_TRACE
-struct rcupreempt_trace;
-extern long *rcupreempt_flipctr(int cpu);
-extern long rcupreempt_data_completed(void);
-extern int rcupreempt_flip_flag(int cpu);
-extern int rcupreempt_mb_flag(int cpu);
-extern char *rcupreempt_try_flip_state_name(void);
-extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu);
-#endif
-
-struct softirq_action;
-
-#ifdef CONFIG_NO_HZ
-extern void rcu_enter_nohz(void);
-extern void rcu_exit_nohz(void);
-#else
-# define rcu_enter_nohz() do { } while (0)
-# define rcu_exit_nohz() do { } while (0)
-#endif
-
-/*
- * A context switch is a grace period for rcupreempt synchronize_rcu()
- * only during early boot, before the scheduler has been initialized.
- * So, how the heck do we get a context switch? Well, if the caller
- * invokes synchronize_rcu(), they are willing to accept a context
- * switch, so we simply pretend that one happened.
- *
- * After boot, there might be a blocked or preempted task in an RCU
- * read-side critical section, so we cannot then take the fastpath.
- */
-static inline int rcu_blocking_is_gp(void)
-{
- return num_online_cpus() == 1 && !rcu_scheduler_active;
-}
-
-#endif /* __LINUX_RCUPREEMPT_H */
diff --git a/include/linux/rcupreempt_trace.h b/include/linux/rcupreempt_trace.h
deleted file mode 100644
index b99ae073192..00000000000
--- a/include/linux/rcupreempt_trace.h
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * Read-Copy Update mechanism for mutual exclusion (RT implementation)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2006
- *
- * Author: Paul McKenney <paulmck@us.ibm.com>
- *
- * Based on the original work by Paul McKenney <paul.mckenney@us.ibm.com>
- * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
- * Papers:
- * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
- * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
- *
- * For detailed explanation of the Preemptible Read-Copy Update mechanism see -
- * http://lwn.net/Articles/253651/
- */
-
-#ifndef __LINUX_RCUPREEMPT_TRACE_H
-#define __LINUX_RCUPREEMPT_TRACE_H
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-
-#include <asm/atomic.h>
-
-/*
- * PREEMPT_RCU data structures.
- */
-
-struct rcupreempt_trace {
- long next_length;
- long next_add;
- long wait_length;
- long wait_add;
- long done_length;
- long done_add;
- long done_remove;
- atomic_t done_invoked;
- long rcu_check_callbacks;
- atomic_t rcu_try_flip_1;
- atomic_t rcu_try_flip_e1;
- long rcu_try_flip_i1;
- long rcu_try_flip_ie1;
- long rcu_try_flip_g1;
- long rcu_try_flip_a1;
- long rcu_try_flip_ae1;
- long rcu_try_flip_a2;
- long rcu_try_flip_z1;
- long rcu_try_flip_ze1;
- long rcu_try_flip_z2;
- long rcu_try_flip_m1;
- long rcu_try_flip_me1;
- long rcu_try_flip_m2;
-};
-
-#ifdef CONFIG_RCU_TRACE
-#define RCU_TRACE(fn, arg) fn(arg);
-#else
-#define RCU_TRACE(fn, arg)
-#endif
-
-extern void rcupreempt_trace_move2done(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_move2wait(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_e1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_i1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_ie1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_g1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_a1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_ae1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_a2(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_z1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_ze1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_z2(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_m1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_me1(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_try_flip_m2(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_check_callbacks(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_done_remove(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_invoke(struct rcupreempt_trace *trace);
-extern void rcupreempt_trace_next_add(struct rcupreempt_trace *trace);
-
-#endif /* __LINUX_RCUPREEMPT_TRACE_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 5a5153806c4..a8930771782 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,264 +30,57 @@
#ifndef __LINUX_RCUTREE_H
#define __LINUX_RCUTREE_H
-#include <linux/cache.h>
-#include <linux/spinlock.h>
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/seqlock.h>
+extern void rcu_sched_qs(int cpu);
+extern void rcu_bh_qs(int cpu);
-/*
- * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
- * In theory, it should be possible to add more levels straightforwardly.
- * In practice, this has not been tested, so there is probably some
- * bug somewhere.
- */
-#define MAX_RCU_LVLS 3
-#define RCU_FANOUT (CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT)
-#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT)
-
-#if NR_CPUS <= RCU_FANOUT
-# define NUM_RCU_LVLS 1
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 (NR_CPUS)
-# define NUM_RCU_LVL_2 0
-# define NUM_RCU_LVL_3 0
-#elif NR_CPUS <= RCU_FANOUT_SQ
-# define NUM_RCU_LVLS 2
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT - 1) / RCU_FANOUT)
-# define NUM_RCU_LVL_2 (NR_CPUS)
-# define NUM_RCU_LVL_3 0
-#elif NR_CPUS <= RCU_FANOUT_CUBE
-# define NUM_RCU_LVLS 3
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT_SQ - 1) / RCU_FANOUT_SQ)
-# define NUM_RCU_LVL_2 (((NR_CPUS) + (RCU_FANOUT) - 1) / (RCU_FANOUT))
-# define NUM_RCU_LVL_3 NR_CPUS
-#else
-# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT */
-
-#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
-#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
-
-/*
- * Dynticks per-CPU state.
- */
-struct rcu_dynticks {
- int dynticks_nesting; /* Track nesting level, sort of. */
- int dynticks; /* Even value for dynticks-idle, else odd. */
- int dynticks_nmi; /* Even value for either dynticks-idle or */
- /* not in nmi handler, else odd. So this */
- /* remains even for nmi from irq handler. */
-};
-
-/*
- * Definition for node within the RCU grace-period-detection hierarchy.
- */
-struct rcu_node {
- spinlock_t lock;
- unsigned long qsmask; /* CPUs or groups that need to switch in */
- /* order for current grace period to proceed.*/
- unsigned long qsmaskinit;
- /* Per-GP initialization for qsmask. */
- unsigned long grpmask; /* Mask to apply to parent qsmask. */
- int grplo; /* lowest-numbered CPU or group here. */
- int grphi; /* highest-numbered CPU or group here. */
- u8 grpnum; /* CPU/group number for next level up. */
- u8 level; /* root is at level 0. */
- struct rcu_node *parent;
-} ____cacheline_internodealigned_in_smp;
-
-/* Index values for nxttail array in struct rcu_data. */
-#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */
-#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */
-#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */
-#define RCU_NEXT_TAIL 3
-#define RCU_NEXT_SIZE 4
-
-/* Per-CPU data for read-copy update. */
-struct rcu_data {
- /* 1) quiescent-state and grace-period handling : */
- long completed; /* Track rsp->completed gp number */
- /* in order to detect GP end. */
- long gpnum; /* Highest gp number that this CPU */
- /* is aware of having started. */
- long passed_quiesc_completed;
- /* Value of completed at time of qs. */
- bool passed_quiesc; /* User-mode/idle loop etc. */
- bool qs_pending; /* Core waits for quiesc state. */
- bool beenonline; /* CPU online at least once. */
- struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
- unsigned long grpmask; /* Mask to apply to leaf qsmask. */
-
- /* 2) batch handling */
- /*
- * If nxtlist is not NULL, it is partitioned as follows.
- * Any of the partitions might be empty, in which case the
- * pointer to that partition will be equal to the pointer for
- * the following partition. When the list is empty, all of
- * the nxttail elements point to nxtlist, which is NULL.
- *
- * [*nxttail[RCU_NEXT_READY_TAIL], NULL = *nxttail[RCU_NEXT_TAIL]):
- * Entries that might have arrived after current GP ended
- * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
- * Entries known to have arrived before current GP ended
- * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
- * Entries that batch # <= ->completed - 1: waiting for current GP
- * [nxtlist, *nxttail[RCU_DONE_TAIL]):
- * Entries that batch # <= ->completed
- * The grace period for these entries has completed, and
- * the other grace-period-completed entries may be moved
- * here temporarily in rcu_process_callbacks().
- */
- struct rcu_head *nxtlist;
- struct rcu_head **nxttail[RCU_NEXT_SIZE];
- long qlen; /* # of queued callbacks */
- long blimit; /* Upper limit on a processed batch */
-
-#ifdef CONFIG_NO_HZ
- /* 3) dynticks interface. */
- struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */
- int dynticks_snap; /* Per-GP tracking for dynticks. */
- int dynticks_nmi_snap; /* Per-GP tracking for dynticks_nmi. */
-#endif /* #ifdef CONFIG_NO_HZ */
-
- /* 4) reasons this CPU needed to be kicked by force_quiescent_state */
-#ifdef CONFIG_NO_HZ
- unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
-#endif /* #ifdef CONFIG_NO_HZ */
- unsigned long offline_fqs; /* Kicked due to being offline. */
- unsigned long resched_ipi; /* Sent a resched IPI. */
-
- /* 5) __rcu_pending() statistics. */
- long n_rcu_pending; /* rcu_pending() calls since boot. */
- long n_rp_qs_pending;
- long n_rp_cb_ready;
- long n_rp_cpu_needs_gp;
- long n_rp_gp_completed;
- long n_rp_gp_started;
- long n_rp_need_fqs;
- long n_rp_need_nothing;
-
- int cpu;
-};
-
-/* Values for signaled field in struct rcu_state. */
-#define RCU_GP_INIT 0 /* Grace period being initialized. */
-#define RCU_SAVE_DYNTICK 1 /* Need to scan dyntick state. */
-#define RCU_FORCE_QS 2 /* Need to force quiescent state. */
-#ifdef CONFIG_NO_HZ
-#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
-#else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT RCU_FORCE_QS
-#endif /* #else #ifdef CONFIG_NO_HZ */
-
-#define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ) /* for rsp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ) /* for rsp->jiffies_stall */
-#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */
- /* to take at least one */
- /* scheduling clock irq */
- /* before ratting on them. */
-
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-/*
- * RCU global state, including node hierarchy. This hierarchy is
- * represented in "heap" form in a dense array. The root (first level)
- * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
- * level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
- * and the third level in ->node[m+1] and following (->node[m+1] referenced
- * by ->level[2]). The number of levels is determined by the number of
- * CPUs and by CONFIG_RCU_FANOUT. Small systems will have a "hierarchy"
- * consisting of a single rcu_node.
- */
-struct rcu_state {
- struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */
- struct rcu_node *level[NUM_RCU_LVLS]; /* Hierarchy levels. */
- u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */
- u8 levelspread[NUM_RCU_LVLS]; /* kids/node in each level. */
- struct rcu_data *rda[NR_CPUS]; /* array of rdp pointers. */
-
- /* The following fields are guarded by the root rcu_node's lock. */
-
- u8 signaled ____cacheline_internodealigned_in_smp;
- /* Force QS state. */
- long gpnum; /* Current gp number. */
- long completed; /* # of last completed gp. */
- spinlock_t onofflock; /* exclude on/offline and */
- /* starting new GP. */
- spinlock_t fqslock; /* Only one task forcing */
- /* quiescent states. */
- unsigned long jiffies_force_qs; /* Time at which to invoke */
- /* force_quiescent_state(). */
- unsigned long n_force_qs; /* Number of calls to */
- /* force_quiescent_state(). */
- unsigned long n_force_qs_lh; /* ~Number of calls leaving */
- /* due to lock unavailable. */
- unsigned long n_force_qs_ngp; /* Number of calls leaving */
- /* due to no GP active. */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
- unsigned long gp_start; /* Time at which GP started, */
- /* but in jiffies. */
- unsigned long jiffies_stall; /* Time at which to check */
- /* for CPU stalls. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#ifdef CONFIG_NO_HZ
- long dynticks_completed; /* Value of completed @ snap. */
-#endif /* #ifdef CONFIG_NO_HZ */
-};
+extern int rcu_needs_cpu(int cpu);
-extern void rcu_qsctr_inc(int cpu);
-extern void rcu_bh_qsctr_inc(int cpu);
+#ifdef CONFIG_TREE_PREEMPT_RCU
-extern int rcu_pending(int cpu);
-extern int rcu_needs_cpu(int cpu);
+extern void __rcu_read_lock(void);
+extern void __rcu_read_unlock(void);
+extern void exit_rcu(void);
-#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_)
-#else
-# define rcu_read_acquire() do { } while (0)
-# define rcu_read_release() do { } while (0)
-#endif
+#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
static inline void __rcu_read_lock(void)
{
preempt_disable();
- __acquire(RCU);
- rcu_read_acquire();
}
+
static inline void __rcu_read_unlock(void)
{
- rcu_read_release();
- __release(RCU);
preempt_enable();
}
+
+static inline void exit_rcu(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+
static inline void __rcu_read_lock_bh(void)
{
local_bh_disable();
- __acquire(RCU_BH);
- rcu_read_acquire();
}
static inline void __rcu_read_unlock_bh(void)
{
- rcu_read_release();
- __release(RCU_BH);
local_bh_enable();
}
#define __synchronize_sched() synchronize_rcu()
-#define call_rcu_sched(head, func) call_rcu(head, func)
+extern void call_rcu_sched(struct rcu_head *head,
+ void (*func)(struct rcu_head *rcu));
-static inline void rcu_init_sched(void)
+static inline void synchronize_rcu_expedited(void)
{
+ synchronize_sched_expedited();
+}
+
+static inline void synchronize_rcu_bh_expedited(void)
+{
+ synchronize_sched_expedited();
}
extern void __rcu_init(void);
@@ -296,6 +89,11 @@ extern void rcu_restart_cpu(int cpu);
extern long rcu_batches_completed(void);
extern long rcu_batches_completed_bh(void);
+extern long rcu_batches_completed_sched(void);
+
+static inline void rcu_init_sched(void)
+{
+}
#ifdef CONFIG_NO_HZ
void rcu_enter_nohz(void);
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 29f8599e6be..5fcc31ed577 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -75,20 +75,6 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
}
/*
- * ring_buffer_event_discard can discard any event in the ring buffer.
- * it is up to the caller to protect against a reader from
- * consuming it or a writer from wrapping and replacing it.
- *
- * No external protection is needed if this is called before
- * the event is commited. But in that case it would be better to
- * use ring_buffer_discard_commit.
- *
- * Note, if an event that has not been committed is discarded
- * with ring_buffer_event_discard, it must still be committed.
- */
-void ring_buffer_event_discard(struct ring_buffer_event *event);
-
-/*
* ring_buffer_discard_commit will remove an event that has not
* ben committed yet. If this is used, then ring_buffer_unlock_commit
* must not be called on the discarded event. This function
@@ -154,8 +140,17 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer);
void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
void ring_buffer_reset(struct ring_buffer *buffer);
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
struct ring_buffer *buffer_b, int cpu);
+#else
+static inline int
+ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+ struct ring_buffer *buffer_b, int cpu)
+{
+ return -ENODEV;
+}
+#endif
int ring_buffer_empty(struct ring_buffer *buffer);
int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
@@ -170,7 +165,6 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
-unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9304027673b..f3d74bd04d1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -38,6 +38,8 @@
#define SCHED_BATCH 3
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE 5
+/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+#define SCHED_RESET_ON_FORK 0x40000000
#ifdef __KERNEL__
@@ -796,18 +798,19 @@ enum cpu_idle_type {
#define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE
#ifdef CONFIG_SMP
-#define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */
-#define SD_BALANCE_NEWIDLE 2 /* Balance when about to become idle */
-#define SD_BALANCE_EXEC 4 /* Balance on exec */
-#define SD_BALANCE_FORK 8 /* Balance on fork, clone */
-#define SD_WAKE_IDLE 16 /* Wake to idle CPU on task wakeup */
-#define SD_WAKE_AFFINE 32 /* Wake task to waking CPU */
-#define SD_WAKE_BALANCE 64 /* Perform balancing at task wakeup */
-#define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */
-#define SD_POWERSAVINGS_BALANCE 256 /* Balance for power savings */
-#define SD_SHARE_PKG_RESOURCES 512 /* Domain members share cpu pkg resources */
-#define SD_SERIALIZE 1024 /* Only a single load balancing instance */
-#define SD_WAKE_IDLE_FAR 2048 /* Gain latency sacrificing cache hit */
+#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */
+#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */
+#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */
+#define SD_WAKE_IDLE 0x0010 /* Wake to idle CPU on task wakeup */
+#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
+#define SD_WAKE_BALANCE 0x0040 /* Perform balancing at task wakeup */
+#define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */
+#define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */
+#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
+#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
+#define SD_WAKE_IDLE_FAR 0x0800 /* Gain latency sacrificing cache hit */
+#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
enum powersavings_balance_level {
POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */
@@ -827,7 +830,7 @@ static inline int sd_balance_for_mc_power(void)
if (sched_smt_power_savings)
return SD_POWERSAVINGS_BALANCE;
- return 0;
+ return SD_PREFER_SIBLING;
}
static inline int sd_balance_for_package_power(void)
@@ -835,7 +838,7 @@ static inline int sd_balance_for_package_power(void)
if (sched_mc_power_savings | sched_smt_power_savings)
return SD_POWERSAVINGS_BALANCE;
- return 0;
+ return SD_PREFER_SIBLING;
}
/*
@@ -857,15 +860,9 @@ struct sched_group {
/*
* CPU power of this group, SCHED_LOAD_SCALE being max power for a
- * single CPU. This is read only (except for setup, hotplug CPU).
- * Note : Never change cpu_power without recompute its reciprocal
+ * single CPU.
*/
- unsigned int __cpu_power;
- /*
- * reciprocal value of cpu_power to avoid expensive divides
- * (see include/linux/reciprocal_div.h)
- */
- u32 reciprocal_cpu_power;
+ unsigned int cpu_power;
/*
* The CPUs this group covers.
@@ -918,6 +915,7 @@ struct sched_domain {
unsigned int newidle_idx;
unsigned int wake_idx;
unsigned int forkexec_idx;
+ unsigned int smt_gain;
int flags; /* See SD_* */
enum sched_domain_level level;
@@ -1045,7 +1043,6 @@ struct sched_class {
struct rq *busiest, struct sched_domain *sd,
enum cpu_idle_type idle);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
- int (*needs_post_schedule) (struct rq *this_rq);
void (*post_schedule) (struct rq *this_rq);
void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
@@ -1110,6 +1107,8 @@ struct sched_entity {
u64 wait_max;
u64 wait_count;
u64 wait_sum;
+ u64 iowait_count;
+ u64 iowait_sum;
u64 sleep_start;
u64 sleep_max;
@@ -1163,6 +1162,8 @@ struct sched_rt_entity {
#endif
};
+struct rcu_node;
+
struct task_struct {
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
void *stack;
@@ -1206,10 +1207,12 @@ struct task_struct {
unsigned int policy;
cpumask_t cpus_allowed;
-#ifdef CONFIG_PREEMPT_RCU
+#ifdef CONFIG_TREE_PREEMPT_RCU
int rcu_read_lock_nesting;
- int rcu_flipctr_idx;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
+ char rcu_read_unlock_special;
+ struct rcu_node *rcu_blocked_node;
+ struct list_head rcu_node_entry;
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info sched_info;
@@ -1230,11 +1233,19 @@ struct task_struct {
unsigned did_exec:1;
unsigned in_execve:1; /* Tell the LSMs that the process is doing an
* execve */
+ unsigned in_iowait:1;
+
+
+ /* Revert to default priority/policy when forking */
+ unsigned sched_reset_on_fork:1;
+
pid_t pid;
pid_t tgid;
+#ifdef CONFIG_CC_STACKPROTECTOR
/* Canary value for the -fstack-protector gcc feature */
unsigned long stack_canary;
+#endif
/*
* pointers to (original) parent process, youngest child, younger sibling,
@@ -1725,6 +1736,28 @@ extern cputime_t task_gtime(struct task_struct *p);
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
+#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
+#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
+#define RCU_READ_UNLOCK_GOT_QS (1 << 2) /* CPU has responded to RCU core. */
+
+static inline void rcu_copy_process(struct task_struct *p)
+{
+ p->rcu_read_lock_nesting = 0;
+ p->rcu_read_unlock_special = 0;
+ p->rcu_blocked_node = NULL;
+ INIT_LIST_HEAD(&p->rcu_node_entry);
+}
+
+#else
+
+static inline void rcu_copy_process(struct task_struct *p)
+{
+}
+
+#endif
+
#ifdef CONFIG_SMP
extern int set_cpus_allowed_ptr(struct task_struct *p,
const struct cpumask *new_mask);
@@ -1814,11 +1847,12 @@ extern unsigned int sysctl_sched_min_granularity;
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_shares_ratelimit;
extern unsigned int sysctl_sched_shares_thresh;
-#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_child_runs_first;
+#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_features;
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;
+extern unsigned int sysctl_sched_time_avg;
extern unsigned int sysctl_timer_migration;
int sched_nr_latency_handler(struct ctl_table *table, int write,
@@ -2282,23 +2316,31 @@ static inline int need_resched(void)
* cond_resched_softirq() will enable bhs before scheduling.
*/
extern int _cond_resched(void);
-#ifdef CONFIG_PREEMPT_BKL
-static inline int cond_resched(void)
-{
- return 0;
-}
+
+#define cond_resched() ({ \
+ __might_sleep(__FILE__, __LINE__, 0); \
+ _cond_resched(); \
+})
+
+extern int __cond_resched_lock(spinlock_t *lock);
+
+#ifdef CONFIG_PREEMPT
+#define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET
#else
-static inline int cond_resched(void)
-{
- return _cond_resched();
-}
+#define PREEMPT_LOCK_OFFSET 0
#endif
-extern int cond_resched_lock(spinlock_t * lock);
-extern int cond_resched_softirq(void);
-static inline int cond_resched_bkl(void)
-{
- return _cond_resched();
-}
+
+#define cond_resched_lock(lock) ({ \
+ __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \
+ __cond_resched_lock(lock); \
+})
+
+extern int __cond_resched_softirq(void);
+
+#define cond_resched_softirq() ({ \
+ __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET); \
+ __cond_resched_softirq(); \
+})
/*
* Does a critical section need to be broken due to another
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 4be57ab0347..f0ca7a7a175 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -143,15 +143,6 @@ static inline void smp_mb__after_lock(void) { smp_mb(); }
*/
#define spin_unlock_wait(lock) __raw_spin_unlock_wait(&(lock)->raw_lock)
-/*
- * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
- */
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-# include <linux/spinlock_api_smp.h>
-#else
-# include <linux/spinlock_api_up.h>
-#endif
-
#ifdef CONFIG_DEBUG_SPINLOCK
extern void _raw_spin_lock(spinlock_t *lock);
#define _raw_spin_lock_flags(lock, flags) _raw_spin_lock(lock)
@@ -268,50 +259,16 @@ static inline void smp_mb__after_lock(void) { smp_mb(); }
#define spin_lock_irq(lock) _spin_lock_irq(lock)
#define spin_lock_bh(lock) _spin_lock_bh(lock)
-
#define read_lock_irq(lock) _read_lock_irq(lock)
#define read_lock_bh(lock) _read_lock_bh(lock)
-
#define write_lock_irq(lock) _write_lock_irq(lock)
#define write_lock_bh(lock) _write_lock_bh(lock)
-
-/*
- * We inline the unlock functions in the nondebug case:
- */
-#if defined(CONFIG_DEBUG_SPINLOCK) || defined(CONFIG_PREEMPT) || \
- !defined(CONFIG_SMP)
-# define spin_unlock(lock) _spin_unlock(lock)
-# define read_unlock(lock) _read_unlock(lock)
-# define write_unlock(lock) _write_unlock(lock)
-# define spin_unlock_irq(lock) _spin_unlock_irq(lock)
-# define read_unlock_irq(lock) _read_unlock_irq(lock)
-# define write_unlock_irq(lock) _write_unlock_irq(lock)
-#else
-# define spin_unlock(lock) \
- do {__raw_spin_unlock(&(lock)->raw_lock); __release(lock); } while (0)
-# define read_unlock(lock) \
- do {__raw_read_unlock(&(lock)->raw_lock); __release(lock); } while (0)
-# define write_unlock(lock) \
- do {__raw_write_unlock(&(lock)->raw_lock); __release(lock); } while (0)
-# define spin_unlock_irq(lock) \
-do { \
- __raw_spin_unlock(&(lock)->raw_lock); \
- __release(lock); \
- local_irq_enable(); \
-} while (0)
-# define read_unlock_irq(lock) \
-do { \
- __raw_read_unlock(&(lock)->raw_lock); \
- __release(lock); \
- local_irq_enable(); \
-} while (0)
-# define write_unlock_irq(lock) \
-do { \
- __raw_write_unlock(&(lock)->raw_lock); \
- __release(lock); \
- local_irq_enable(); \
-} while (0)
-#endif
+#define spin_unlock(lock) _spin_unlock(lock)
+#define read_unlock(lock) _read_unlock(lock)
+#define write_unlock(lock) _write_unlock(lock)
+#define spin_unlock_irq(lock) _spin_unlock_irq(lock)
+#define read_unlock_irq(lock) _read_unlock_irq(lock)
+#define write_unlock_irq(lock) _write_unlock_irq(lock)
#define spin_unlock_irqrestore(lock, flags) \
do { \
@@ -380,4 +337,13 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
*/
#define spin_can_lock(lock) (!spin_is_locked(lock))
+/*
+ * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+# include <linux/spinlock_api_smp.h>
+#else
+# include <linux/spinlock_api_up.h>
+#endif
+
#endif /* __LINUX_SPINLOCK_H */
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index d79845d034b..7a7e18fc241 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -60,4 +60,398 @@ void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
__releases(lock);
+/*
+ * We inline the unlock functions in the nondebug case:
+ */
+#if !defined(CONFIG_DEBUG_SPINLOCK) && !defined(CONFIG_PREEMPT)
+#define __always_inline__spin_unlock
+#define __always_inline__read_unlock
+#define __always_inline__write_unlock
+#define __always_inline__spin_unlock_irq
+#define __always_inline__read_unlock_irq
+#define __always_inline__write_unlock_irq
+#endif
+
+#ifndef CONFIG_DEBUG_SPINLOCK
+#ifndef CONFIG_GENERIC_LOCKBREAK
+
+#ifdef __always_inline__spin_lock
+#define _spin_lock(lock) __spin_lock(lock)
+#endif
+
+#ifdef __always_inline__read_lock
+#define _read_lock(lock) __read_lock(lock)
+#endif
+
+#ifdef __always_inline__write_lock
+#define _write_lock(lock) __write_lock(lock)
+#endif
+
+#ifdef __always_inline__spin_lock_bh
+#define _spin_lock_bh(lock) __spin_lock_bh(lock)
+#endif
+
+#ifdef __always_inline__read_lock_bh
+#define _read_lock_bh(lock) __read_lock_bh(lock)
+#endif
+
+#ifdef __always_inline__write_lock_bh
+#define _write_lock_bh(lock) __write_lock_bh(lock)
+#endif
+
+#ifdef __always_inline__spin_lock_irq
+#define _spin_lock_irq(lock) __spin_lock_irq(lock)
+#endif
+
+#ifdef __always_inline__read_lock_irq
+#define _read_lock_irq(lock) __read_lock_irq(lock)
+#endif
+
+#ifdef __always_inline__write_lock_irq
+#define _write_lock_irq(lock) __write_lock_irq(lock)
+#endif
+
+#ifdef __always_inline__spin_lock_irqsave
+#define _spin_lock_irqsave(lock) __spin_lock_irqsave(lock)
+#endif
+
+#ifdef __always_inline__read_lock_irqsave
+#define _read_lock_irqsave(lock) __read_lock_irqsave(lock)
+#endif
+
+#ifdef __always_inline__write_lock_irqsave
+#define _write_lock_irqsave(lock) __write_lock_irqsave(lock)
+#endif
+
+#endif /* !CONFIG_GENERIC_LOCKBREAK */
+
+#ifdef __always_inline__spin_trylock
+#define _spin_trylock(lock) __spin_trylock(lock)
+#endif
+
+#ifdef __always_inline__read_trylock
+#define _read_trylock(lock) __read_trylock(lock)
+#endif
+
+#ifdef __always_inline__write_trylock
+#define _write_trylock(lock) __write_trylock(lock)
+#endif
+
+#ifdef __always_inline__spin_trylock_bh
+#define _spin_trylock_bh(lock) __spin_trylock_bh(lock)
+#endif
+
+#ifdef __always_inline__spin_unlock
+#define _spin_unlock(lock) __spin_unlock(lock)
+#endif
+
+#ifdef __always_inline__read_unlock
+#define _read_unlock(lock) __read_unlock(lock)
+#endif
+
+#ifdef __always_inline__write_unlock
+#define _write_unlock(lock) __write_unlock(lock)
+#endif
+
+#ifdef __always_inline__spin_unlock_bh
+#define _spin_unlock_bh(lock) __spin_unlock_bh(lock)
+#endif
+
+#ifdef __always_inline__read_unlock_bh
+#define _read_unlock_bh(lock) __read_unlock_bh(lock)
+#endif
+
+#ifdef __always_inline__write_unlock_bh
+#define _write_unlock_bh(lock) __write_unlock_bh(lock)
+#endif
+
+#ifdef __always_inline__spin_unlock_irq
+#define _spin_unlock_irq(lock) __spin_unlock_irq(lock)
+#endif
+
+#ifdef __always_inline__read_unlock_irq
+#define _read_unlock_irq(lock) __read_unlock_irq(lock)
+#endif
+
+#ifdef __always_inline__write_unlock_irq
+#define _write_unlock_irq(lock) __write_unlock_irq(lock)
+#endif
+
+#ifdef __always_inline__spin_unlock_irqrestore
+#define _spin_unlock_irqrestore(lock, flags) __spin_unlock_irqrestore(lock, flags)
+#endif
+
+#ifdef __always_inline__read_unlock_irqrestore
+#define _read_unlock_irqrestore(lock, flags) __read_unlock_irqrestore(lock, flags)
+#endif
+
+#ifdef __always_inline__write_unlock_irqrestore
+#define _write_unlock_irqrestore(lock, flags) __write_unlock_irqrestore(lock, flags)
+#endif
+
+#endif /* CONFIG_DEBUG_SPINLOCK */
+
+static inline int __spin_trylock(spinlock_t *lock)
+{
+ preempt_disable();
+ if (_raw_spin_trylock(lock)) {
+ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+ return 1;
+ }
+ preempt_enable();
+ return 0;
+}
+
+static inline int __read_trylock(rwlock_t *lock)
+{
+ preempt_disable();
+ if (_raw_read_trylock(lock)) {
+ rwlock_acquire_read(&lock->dep_map, 0, 1, _RET_IP_);
+ return 1;
+ }
+ preempt_enable();
+ return 0;
+}
+
+static inline int __write_trylock(rwlock_t *lock)
+{
+ preempt_disable();
+ if (_raw_write_trylock(lock)) {
+ rwlock_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+ return 1;
+ }
+ preempt_enable();
+ return 0;
+}
+
+/*
+ * If lockdep is enabled then we use the non-preemption spin-ops
+ * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
+ * not re-enabled during lock-acquire (which the preempt-spin-ops do):
+ */
+#if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
+
+static inline void __read_lock(rwlock_t *lock)
+{
+ preempt_disable();
+ rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+}
+
+static inline unsigned long __spin_lock_irqsave(spinlock_t *lock)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ preempt_disable();
+ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+ /*
+ * On lockdep we dont want the hand-coded irq-enable of
+ * _raw_spin_lock_flags() code, because lockdep assumes
+ * that interrupts are not re-enabled during lock-acquire:
+ */
+#ifdef CONFIG_LOCKDEP
+ LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+#else
+ _raw_spin_lock_flags(lock, &flags);
+#endif
+ return flags;
+}
+
+static inline void __spin_lock_irq(spinlock_t *lock)
+{
+ local_irq_disable();
+ preempt_disable();
+ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+}
+
+static inline void __spin_lock_bh(spinlock_t *lock)
+{
+ local_bh_disable();
+ preempt_disable();
+ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+}
+
+static inline unsigned long __read_lock_irqsave(rwlock_t *lock)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ preempt_disable();
+ rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED_FLAGS(lock, _raw_read_trylock, _raw_read_lock,
+ _raw_read_lock_flags, &flags);
+ return flags;
+}
+
+static inline void __read_lock_irq(rwlock_t *lock)
+{
+ local_irq_disable();
+ preempt_disable();
+ rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+}
+
+static inline void __read_lock_bh(rwlock_t *lock)
+{
+ local_bh_disable();
+ preempt_disable();
+ rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+}
+
+static inline unsigned long __write_lock_irqsave(rwlock_t *lock)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ preempt_disable();
+ rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED_FLAGS(lock, _raw_write_trylock, _raw_write_lock,
+ _raw_write_lock_flags, &flags);
+ return flags;
+}
+
+static inline void __write_lock_irq(rwlock_t *lock)
+{
+ local_irq_disable();
+ preempt_disable();
+ rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+}
+
+static inline void __write_lock_bh(rwlock_t *lock)
+{
+ local_bh_disable();
+ preempt_disable();
+ rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+}
+
+static inline void __spin_lock(spinlock_t *lock)
+{
+ preempt_disable();
+ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+}
+
+static inline void __write_lock(rwlock_t *lock)
+{
+ preempt_disable();
+ rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+}
+
+#endif /* CONFIG_PREEMPT */
+
+static inline void __spin_unlock(spinlock_t *lock)
+{
+ spin_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_spin_unlock(lock);
+ preempt_enable();
+}
+
+static inline void __write_unlock(rwlock_t *lock)
+{
+ rwlock_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_write_unlock(lock);
+ preempt_enable();
+}
+
+static inline void __read_unlock(rwlock_t *lock)
+{
+ rwlock_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_read_unlock(lock);
+ preempt_enable();
+}
+
+static inline void __spin_unlock_irqrestore(spinlock_t *lock,
+ unsigned long flags)
+{
+ spin_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_spin_unlock(lock);
+ local_irq_restore(flags);
+ preempt_enable();
+}
+
+static inline void __spin_unlock_irq(spinlock_t *lock)
+{
+ spin_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_spin_unlock(lock);
+ local_irq_enable();
+ preempt_enable();
+}
+
+static inline void __spin_unlock_bh(spinlock_t *lock)
+{
+ spin_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_spin_unlock(lock);
+ preempt_enable_no_resched();
+ local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+}
+
+static inline void __read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+{
+ rwlock_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_read_unlock(lock);
+ local_irq_restore(flags);
+ preempt_enable();
+}
+
+static inline void __read_unlock_irq(rwlock_t *lock)
+{
+ rwlock_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_read_unlock(lock);
+ local_irq_enable();
+ preempt_enable();
+}
+
+static inline void __read_unlock_bh(rwlock_t *lock)
+{
+ rwlock_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_read_unlock(lock);
+ preempt_enable_no_resched();
+ local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+}
+
+static inline void __write_unlock_irqrestore(rwlock_t *lock,
+ unsigned long flags)
+{
+ rwlock_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_write_unlock(lock);
+ local_irq_restore(flags);
+ preempt_enable();
+}
+
+static inline void __write_unlock_irq(rwlock_t *lock)
+{
+ rwlock_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_write_unlock(lock);
+ local_irq_enable();
+ preempt_enable();
+}
+
+static inline void __write_unlock_bh(rwlock_t *lock)
+{
+ rwlock_release(&lock->dep_map, 1, _RET_IP_);
+ _raw_write_unlock(lock);
+ preempt_enable_no_resched();
+ local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+}
+
+static inline int __spin_trylock_bh(spinlock_t *lock)
+{
+ local_bh_disable();
+ preempt_disable();
+ if (_raw_spin_trylock(lock)) {
+ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+ return 1;
+ }
+ preempt_enable_no_resched();
+ local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+ return 0;
+}
+
#endif /* __LINUX_SPINLOCK_API_SMP_H */
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index cb1a6631b8f..73b1f1cec42 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -14,7 +14,6 @@ struct scatterlist;
*/
#define IO_TLB_SEGSIZE 128
-
/*
* log of the size of each IO TLB slab. The number of slabs is command line
* controllable.
@@ -24,16 +23,6 @@ struct scatterlist;
extern void
swiotlb_init(void);
-extern void *swiotlb_alloc_boot(size_t bytes, unsigned long nslabs);
-extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
-
-extern dma_addr_t swiotlb_phys_to_bus(struct device *hwdev,
- phys_addr_t address);
-extern phys_addr_t swiotlb_bus_to_phys(struct device *hwdev,
- dma_addr_t address);
-
-extern int swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size);
-
extern void
*swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 80de7003d8c..a8e37821cc6 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -64,6 +64,7 @@ struct perf_counter_attr;
#include <linux/sem.h>
#include <asm/siginfo.h>
#include <asm/signal.h>
+#include <linux/unistd.h>
#include <linux/quota.h>
#include <linux/key.h>
#include <trace/syscall.h>
@@ -97,6 +98,53 @@ struct perf_counter_attr;
#define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
#define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
+#ifdef CONFIG_EVENT_PROFILE
+#define TRACE_SYS_ENTER_PROFILE(sname) \
+static int prof_sysenter_enable_##sname(struct ftrace_event_call *event_call) \
+{ \
+ int ret = 0; \
+ if (!atomic_inc_return(&event_enter_##sname.profile_count)) \
+ ret = reg_prof_syscall_enter("sys"#sname); \
+ return ret; \
+} \
+ \
+static void prof_sysenter_disable_##sname(struct ftrace_event_call *event_call)\
+{ \
+ if (atomic_add_negative(-1, &event_enter_##sname.profile_count)) \
+ unreg_prof_syscall_enter("sys"#sname); \
+}
+
+#define TRACE_SYS_EXIT_PROFILE(sname) \
+static int prof_sysexit_enable_##sname(struct ftrace_event_call *event_call) \
+{ \
+ int ret = 0; \
+ if (!atomic_inc_return(&event_exit_##sname.profile_count)) \
+ ret = reg_prof_syscall_exit("sys"#sname); \
+ return ret; \
+} \
+ \
+static void prof_sysexit_disable_##sname(struct ftrace_event_call *event_call) \
+{ \
+ if (atomic_add_negative(-1, &event_exit_##sname.profile_count)) \
+ unreg_prof_syscall_exit("sys"#sname); \
+}
+
+#define TRACE_SYS_ENTER_PROFILE_INIT(sname) \
+ .profile_count = ATOMIC_INIT(-1), \
+ .profile_enable = prof_sysenter_enable_##sname, \
+ .profile_disable = prof_sysenter_disable_##sname,
+
+#define TRACE_SYS_EXIT_PROFILE_INIT(sname) \
+ .profile_count = ATOMIC_INIT(-1), \
+ .profile_enable = prof_sysexit_enable_##sname, \
+ .profile_disable = prof_sysexit_disable_##sname,
+#else
+#define TRACE_SYS_ENTER_PROFILE(sname)
+#define TRACE_SYS_ENTER_PROFILE_INIT(sname)
+#define TRACE_SYS_EXIT_PROFILE(sname)
+#define TRACE_SYS_EXIT_PROFILE_INIT(sname)
+#endif
+
#ifdef CONFIG_FTRACE_SYSCALLS
#define __SC_STR_ADECL1(t, a) #a
#define __SC_STR_ADECL2(t, a, ...) #a, __SC_STR_ADECL1(__VA_ARGS__)
@@ -112,7 +160,81 @@ struct perf_counter_attr;
#define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__)
#define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__)
+#define SYSCALL_TRACE_ENTER_EVENT(sname) \
+ static struct ftrace_event_call event_enter_##sname; \
+ struct trace_event enter_syscall_print_##sname = { \
+ .trace = print_syscall_enter, \
+ }; \
+ static int init_enter_##sname(void) \
+ { \
+ int num, id; \
+ num = syscall_name_to_nr("sys"#sname); \
+ if (num < 0) \
+ return -ENOSYS; \
+ id = register_ftrace_event(&enter_syscall_print_##sname);\
+ if (!id) \
+ return -ENODEV; \
+ event_enter_##sname.id = id; \
+ set_syscall_enter_id(num, id); \
+ INIT_LIST_HEAD(&event_enter_##sname.fields); \
+ return 0; \
+ } \
+ TRACE_SYS_ENTER_PROFILE(sname); \
+ static struct ftrace_event_call __used \
+ __attribute__((__aligned__(4))) \
+ __attribute__((section("_ftrace_events"))) \
+ event_enter_##sname = { \
+ .name = "sys_enter"#sname, \
+ .system = "syscalls", \
+ .event = &event_syscall_enter, \
+ .raw_init = init_enter_##sname, \
+ .show_format = syscall_enter_format, \
+ .define_fields = syscall_enter_define_fields, \
+ .regfunc = reg_event_syscall_enter, \
+ .unregfunc = unreg_event_syscall_enter, \
+ .data = "sys"#sname, \
+ TRACE_SYS_ENTER_PROFILE_INIT(sname) \
+ }
+
+#define SYSCALL_TRACE_EXIT_EVENT(sname) \
+ static struct ftrace_event_call event_exit_##sname; \
+ struct trace_event exit_syscall_print_##sname = { \
+ .trace = print_syscall_exit, \
+ }; \
+ static int init_exit_##sname(void) \
+ { \
+ int num, id; \
+ num = syscall_name_to_nr("sys"#sname); \
+ if (num < 0) \
+ return -ENOSYS; \
+ id = register_ftrace_event(&exit_syscall_print_##sname);\
+ if (!id) \
+ return -ENODEV; \
+ event_exit_##sname.id = id; \
+ set_syscall_exit_id(num, id); \
+ INIT_LIST_HEAD(&event_exit_##sname.fields); \
+ return 0; \
+ } \
+ TRACE_SYS_EXIT_PROFILE(sname); \
+ static struct ftrace_event_call __used \
+ __attribute__((__aligned__(4))) \
+ __attribute__((section("_ftrace_events"))) \
+ event_exit_##sname = { \
+ .name = "sys_exit"#sname, \
+ .system = "syscalls", \
+ .event = &event_syscall_exit, \
+ .raw_init = init_exit_##sname, \
+ .show_format = syscall_exit_format, \
+ .define_fields = syscall_exit_define_fields, \
+ .regfunc = reg_event_syscall_exit, \
+ .unregfunc = unreg_event_syscall_exit, \
+ .data = "sys"#sname, \
+ TRACE_SYS_EXIT_PROFILE_INIT(sname) \
+ }
+
#define SYSCALL_METADATA(sname, nb) \
+ SYSCALL_TRACE_ENTER_EVENT(sname); \
+ SYSCALL_TRACE_EXIT_EVENT(sname); \
static const struct syscall_metadata __used \
__attribute__((__aligned__(4))) \
__attribute__((section("__syscalls_metadata"))) \
@@ -121,18 +243,23 @@ struct perf_counter_attr;
.nb_args = nb, \
.types = types_##sname, \
.args = args_##sname, \
- }
+ .enter_event = &event_enter_##sname, \
+ .exit_event = &event_exit_##sname, \
+ };
#define SYSCALL_DEFINE0(sname) \
+ SYSCALL_TRACE_ENTER_EVENT(_##sname); \
+ SYSCALL_TRACE_EXIT_EVENT(_##sname); \
static const struct syscall_metadata __used \
__attribute__((__aligned__(4))) \
__attribute__((section("__syscalls_metadata"))) \
__syscall_meta_##sname = { \
.name = "sys_"#sname, \
.nb_args = 0, \
+ .enter_event = &event_enter__##sname, \
+ .exit_event = &event_exit__##sname, \
}; \
asmlinkage long sys_##sname(void)
-
#else
#define SYSCALL_DEFINE0(name) asmlinkage long sys_##name(void)
#endif
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 7402c1a27c4..85e8cf7d393 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -85,20 +85,29 @@ int arch_update_cpu_topology(void);
#define ARCH_HAS_SCHED_WAKE_IDLE
/* Common values for SMT siblings */
#ifndef SD_SIBLING_INIT
-#define SD_SIBLING_INIT (struct sched_domain) { \
- .min_interval = 1, \
- .max_interval = 2, \
- .busy_factor = 64, \
- .imbalance_pct = 110, \
- .flags = SD_LOAD_BALANCE \
- | SD_BALANCE_NEWIDLE \
- | SD_BALANCE_FORK \
- | SD_BALANCE_EXEC \
- | SD_WAKE_AFFINE \
- | SD_WAKE_BALANCE \
- | SD_SHARE_CPUPOWER, \
- .last_balance = jiffies, \
- .balance_interval = 1, \
+#define SD_SIBLING_INIT (struct sched_domain) { \
+ .min_interval = 1, \
+ .max_interval = 2, \
+ .busy_factor = 64, \
+ .imbalance_pct = 110, \
+ \
+ .flags = 1*SD_LOAD_BALANCE \
+ | 1*SD_BALANCE_NEWIDLE \
+ | 1*SD_BALANCE_EXEC \
+ | 1*SD_BALANCE_FORK \
+ | 0*SD_WAKE_IDLE \
+ | 1*SD_WAKE_AFFINE \
+ | 1*SD_WAKE_BALANCE \
+ | 1*SD_SHARE_CPUPOWER \
+ | 0*SD_POWERSAVINGS_BALANCE \
+ | 0*SD_SHARE_PKG_RESOURCES \
+ | 0*SD_SERIALIZE \
+ | 0*SD_WAKE_IDLE_FAR \
+ | 0*SD_PREFER_SIBLING \
+ , \
+ .last_balance = jiffies, \
+ .balance_interval = 1, \
+ .smt_gain = 1178, /* 15% */ \
}
#endif
#endif /* CONFIG_SCHED_SMT */
@@ -106,69 +115,94 @@ int arch_update_cpu_topology(void);
#ifdef CONFIG_SCHED_MC
/* Common values for MC siblings. for now mostly derived from SD_CPU_INIT */
#ifndef SD_MC_INIT
-#define SD_MC_INIT (struct sched_domain) { \
- .min_interval = 1, \
- .max_interval = 4, \
- .busy_factor = 64, \
- .imbalance_pct = 125, \
- .cache_nice_tries = 1, \
- .busy_idx = 2, \
- .wake_idx = 1, \
- .forkexec_idx = 1, \
- .flags = SD_LOAD_BALANCE \
- | SD_BALANCE_FORK \
- | SD_BALANCE_EXEC \
- | SD_WAKE_AFFINE \
- | SD_WAKE_BALANCE \
- | SD_SHARE_PKG_RESOURCES\
- | sd_balance_for_mc_power()\
- | sd_power_saving_flags(),\
- .last_balance = jiffies, \
- .balance_interval = 1, \
+#define SD_MC_INIT (struct sched_domain) { \
+ .min_interval = 1, \
+ .max_interval = 4, \
+ .busy_factor = 64, \
+ .imbalance_pct = 125, \
+ .cache_nice_tries = 1, \
+ .busy_idx = 2, \
+ .wake_idx = 1, \
+ .forkexec_idx = 1, \
+ \
+ .flags = 1*SD_LOAD_BALANCE \
+ | 1*SD_BALANCE_NEWIDLE \
+ | 1*SD_BALANCE_EXEC \
+ | 1*SD_BALANCE_FORK \
+ | 1*SD_WAKE_IDLE \
+ | 1*SD_WAKE_AFFINE \
+ | 1*SD_WAKE_BALANCE \
+ | 0*SD_SHARE_CPUPOWER \
+ | 1*SD_SHARE_PKG_RESOURCES \
+ | 0*SD_SERIALIZE \
+ | 0*SD_WAKE_IDLE_FAR \
+ | sd_balance_for_mc_power() \
+ | sd_power_saving_flags() \
+ , \
+ .last_balance = jiffies, \
+ .balance_interval = 1, \
}
#endif
#endif /* CONFIG_SCHED_MC */
/* Common values for CPUs */
#ifndef SD_CPU_INIT
-#define SD_CPU_INIT (struct sched_domain) { \
- .min_interval = 1, \
- .max_interval = 4, \
- .busy_factor = 64, \
- .imbalance_pct = 125, \
- .cache_nice_tries = 1, \
- .busy_idx = 2, \
- .idle_idx = 1, \
- .newidle_idx = 2, \
- .wake_idx = 1, \
- .forkexec_idx = 1, \
- .flags = SD_LOAD_BALANCE \
- | SD_BALANCE_EXEC \
- | SD_BALANCE_FORK \
- | SD_WAKE_AFFINE \
- | SD_WAKE_BALANCE \
- | sd_balance_for_package_power()\
- | sd_power_saving_flags(),\
- .last_balance = jiffies, \
- .balance_interval = 1, \
+#define SD_CPU_INIT (struct sched_domain) { \
+ .min_interval = 1, \
+ .max_interval = 4, \
+ .busy_factor = 64, \
+ .imbalance_pct = 125, \
+ .cache_nice_tries = 1, \
+ .busy_idx = 2, \
+ .idle_idx = 1, \
+ .newidle_idx = 2, \
+ .wake_idx = 1, \
+ .forkexec_idx = 1, \
+ \
+ .flags = 1*SD_LOAD_BALANCE \
+ | 1*SD_BALANCE_NEWIDLE \
+ | 1*SD_BALANCE_EXEC \
+ | 1*SD_BALANCE_FORK \
+ | 1*SD_WAKE_IDLE \
+ | 0*SD_WAKE_AFFINE \
+ | 1*SD_WAKE_BALANCE \
+ | 0*SD_SHARE_CPUPOWER \
+ | 0*SD_SHARE_PKG_RESOURCES \
+ | 0*SD_SERIALIZE \
+ | 0*SD_WAKE_IDLE_FAR \
+ | sd_balance_for_package_power() \
+ | sd_power_saving_flags() \
+ , \
+ .last_balance = jiffies, \
+ .balance_interval = 1, \
}
#endif
/* sched_domains SD_ALLNODES_INIT for NUMA machines */
-#define SD_ALLNODES_INIT (struct sched_domain) { \
- .min_interval = 64, \
- .max_interval = 64*num_online_cpus(), \
- .busy_factor = 128, \
- .imbalance_pct = 133, \
- .cache_nice_tries = 1, \
- .busy_idx = 3, \
- .idle_idx = 3, \
- .flags = SD_LOAD_BALANCE \
- | SD_BALANCE_NEWIDLE \
- | SD_WAKE_AFFINE \
- | SD_SERIALIZE, \
- .last_balance = jiffies, \
- .balance_interval = 64, \
+#define SD_ALLNODES_INIT (struct sched_domain) { \
+ .min_interval = 64, \
+ .max_interval = 64*num_online_cpus(), \
+ .busy_factor = 128, \
+ .imbalance_pct = 133, \
+ .cache_nice_tries = 1, \
+ .busy_idx = 3, \
+ .idle_idx = 3, \
+ .flags = 1*SD_LOAD_BALANCE \
+ | 1*SD_BALANCE_NEWIDLE \
+ | 0*SD_BALANCE_EXEC \
+ | 0*SD_BALANCE_FORK \
+ | 0*SD_WAKE_IDLE \
+ | 1*SD_WAKE_AFFINE \
+ | 0*SD_WAKE_BALANCE \
+ | 0*SD_SHARE_CPUPOWER \
+ | 0*SD_POWERSAVINGS_BALANCE \
+ | 0*SD_SHARE_PKG_RESOURCES \
+ | 1*SD_SERIALIZE \
+ | 1*SD_WAKE_IDLE_FAR \
+ | 0*SD_PREFER_SIBLING \
+ , \
+ .last_balance = jiffies, \
+ .balance_interval = 64, \
}
#ifdef CONFIG_NUMA
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index b9dc4ca0246..63a3f7a8058 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -23,6 +23,8 @@ struct tracepoint;
struct tracepoint {
const char *name; /* Tracepoint name */
int state; /* State. */
+ void (*regfunc)(void);
+ void (*unregfunc)(void);
void **funcs;
} __attribute__((aligned(32))); /*
* Aligned on 32 bytes because it is
@@ -78,12 +80,16 @@ struct tracepoint {
return tracepoint_probe_unregister(#name, (void *)probe);\
}
-#define DEFINE_TRACE(name) \
+
+#define DEFINE_TRACE_FN(name, reg, unreg) \
static const char __tpstrtab_##name[] \
__attribute__((section("__tracepoints_strings"))) = #name; \
struct tracepoint __tracepoint_##name \
__attribute__((section("__tracepoints"), aligned(32))) = \
- { __tpstrtab_##name, 0, NULL }
+ { __tpstrtab_##name, 0, reg, unreg, NULL }
+
+#define DEFINE_TRACE(name) \
+ DEFINE_TRACE_FN(name, NULL, NULL);
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \
EXPORT_SYMBOL_GPL(__tracepoint_##name)
@@ -108,6 +114,7 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin,
return -ENOSYS; \
}
+#define DEFINE_TRACE_FN(name, reg, unreg)
#define DEFINE_TRACE(name)
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
#define EXPORT_TRACEPOINT_SYMBOL(name)
@@ -158,6 +165,15 @@ static inline void tracepoint_synchronize_unregister(void)
#define PARAMS(args...) args
+#endif /* _LINUX_TRACEPOINT_H */
+
+/*
+ * Note: we keep the TRACE_EVENT outside the include file ifdef protection.
+ * This is due to the way trace events work. If a file includes two
+ * trace event headers under one "CREATE_TRACE_POINTS" the first include
+ * will override the TRACE_EVENT and break the second include.
+ */
+
#ifndef TRACE_EVENT
/*
* For use with the TRACE_EVENT macro:
@@ -259,10 +275,15 @@ static inline void tracepoint_synchronize_unregister(void)
* can also by used by generic instrumentation like SystemTap), and
* it is also used to expose a structured trace record in
* /sys/kernel/debug/tracing/events/.
+ *
+ * A set of (un)registration functions can be passed to the variant
+ * TRACE_EVENT_FN to perform any (un)registration work.
*/
#define TRACE_EVENT(name, proto, args, struct, assign, print) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-#endif
+#define TRACE_EVENT_FN(name, proto, args, struct, \
+ assign, print, reg, unreg) \
+ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-#endif
+#endif /* ifdef TRACE_EVENT (see note above) */
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index f7a7ae1e8f9..2a4b3bf7403 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -26,6 +26,11 @@
#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
DEFINE_TRACE(name)
+#undef TRACE_EVENT_FN
+#define TRACE_EVENT_FN(name, proto, args, tstruct, \
+ assign, print, reg, unreg) \
+ DEFINE_TRACE_FN(name, reg, unreg)
+
#undef DECLARE_TRACE
#define DECLARE_TRACE(name, proto, args) \
DEFINE_TRACE(name)
@@ -56,6 +61,8 @@
#include <trace/ftrace.h>
#endif
+#undef TRACE_EVENT
+#undef TRACE_EVENT_FN
#undef TRACE_HEADER_MULTI_READ
/* Only undef what we defined in this file */
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
new file mode 100644
index 00000000000..84160fb1847
--- /dev/null
+++ b/include/trace/events/module.h
@@ -0,0 +1,126 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM module
+
+#if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MODULE_H
+
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_MODULES
+
+struct module;
+
+#define show_module_flags(flags) __print_flags(flags, "", \
+ { (1UL << TAINT_PROPRIETARY_MODULE), "P" }, \
+ { (1UL << TAINT_FORCED_MODULE), "F" }, \
+ { (1UL << TAINT_CRAP), "C" })
+
+TRACE_EVENT(module_load,
+
+ TP_PROTO(struct module *mod),
+
+ TP_ARGS(mod),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, taints )
+ __string( name, mod->name )
+ ),
+
+ TP_fast_assign(
+ __entry->taints = mod->taints;
+ __assign_str(name, mod->name);
+ ),
+
+ TP_printk("%s %s", __get_str(name), show_module_flags(__entry->taints))
+);
+
+TRACE_EVENT(module_free,
+
+ TP_PROTO(struct module *mod),
+
+ TP_ARGS(mod),
+
+ TP_STRUCT__entry(
+ __string( name, mod->name )
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, mod->name);
+ ),
+
+ TP_printk("%s", __get_str(name))
+);
+
+TRACE_EVENT(module_get,
+
+ TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+
+ TP_ARGS(mod, ip, refcnt),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, ip )
+ __field( int, refcnt )
+ __string( name, mod->name )
+ ),
+
+ TP_fast_assign(
+ __entry->ip = ip;
+ __entry->refcnt = refcnt;
+ __assign_str(name, mod->name);
+ ),
+
+ TP_printk("%s call_site=%pf refcnt=%d",
+ __get_str(name), (void *)__entry->ip, __entry->refcnt)
+);
+
+TRACE_EVENT(module_put,
+
+ TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+
+ TP_ARGS(mod, ip, refcnt),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, ip )
+ __field( int, refcnt )
+ __string( name, mod->name )
+ ),
+
+ TP_fast_assign(
+ __entry->ip = ip;
+ __entry->refcnt = refcnt;
+ __assign_str(name, mod->name);
+ ),
+
+ TP_printk("%s call_site=%pf refcnt=%d",
+ __get_str(name), (void *)__entry->ip, __entry->refcnt)
+);
+
+TRACE_EVENT(module_request,
+
+ TP_PROTO(char *name, bool wait, unsigned long ip),
+
+ TP_ARGS(name, wait, ip),
+
+ TP_STRUCT__entry(
+ __field( bool, wait )
+ __field( unsigned long, ip )
+ __string( name, name )
+ ),
+
+ TP_fast_assign(
+ __entry->wait = wait;
+ __entry->ip = ip;
+ __assign_str(name, name);
+ ),
+
+ TP_printk("%s wait=%d call_site=%pf",
+ __get_str(name), (int)__entry->wait, (void *)__entry->ip)
+);
+
+#endif /* CONFIG_MODULES */
+
+#endif /* _TRACE_MODULE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 8949bb7eb08..b48f1ad7c94 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -94,6 +94,7 @@ TRACE_EVENT(sched_wakeup,
__field( pid_t, pid )
__field( int, prio )
__field( int, success )
+ __field( int, cpu )
),
TP_fast_assign(
@@ -101,11 +102,12 @@ TRACE_EVENT(sched_wakeup,
__entry->pid = p->pid;
__entry->prio = p->prio;
__entry->success = success;
+ __entry->cpu = task_cpu(p);
),
- TP_printk("task %s:%d [%d] success=%d",
+ TP_printk("task %s:%d [%d] success=%d [%03d]",
__entry->comm, __entry->pid, __entry->prio,
- __entry->success)
+ __entry->success, __entry->cpu)
);
/*
@@ -125,6 +127,7 @@ TRACE_EVENT(sched_wakeup_new,
__field( pid_t, pid )
__field( int, prio )
__field( int, success )
+ __field( int, cpu )
),
TP_fast_assign(
@@ -132,11 +135,12 @@ TRACE_EVENT(sched_wakeup_new,
__entry->pid = p->pid;
__entry->prio = p->prio;
__entry->success = success;
+ __entry->cpu = task_cpu(p);
),
- TP_printk("task %s:%d [%d] success=%d",
+ TP_printk("task %s:%d [%d] success=%d [%03d]",
__entry->comm, __entry->pid, __entry->prio,
- __entry->success)
+ __entry->success, __entry->cpu)
);
/*
@@ -340,6 +344,101 @@ TRACE_EVENT(sched_signal_send,
__entry->sig, __entry->comm, __entry->pid)
);
+/*
+ * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
+ * adding sched_stat support to SCHED_FIFO/RR would be welcome.
+ */
+
+/*
+ * Tracepoint for accounting wait time (time the task is runnable
+ * but not actually running due to scheduler contention).
+ */
+TRACE_EVENT(sched_stat_wait,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d wait: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting sleep time (time the task is not runnable,
+ * including iowait, see below).
+ */
+TRACE_EVENT(sched_stat_sleep,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d sleep: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting iowait time (time the task is not runnable
+ * due to waiting on IO to complete).
+ */
+TRACE_EVENT(sched_stat_iowait,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d iowait: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
new file mode 100644
index 00000000000..397dff2dbd5
--- /dev/null
+++ b/include/trace/events/syscalls.h
@@ -0,0 +1,70 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM syscalls
+
+#if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EVENTS_SYSCALLS_H
+
+#include <linux/tracepoint.h>
+
+#include <asm/ptrace.h>
+#include <asm/syscall.h>
+
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+
+extern void syscall_regfunc(void);
+extern void syscall_unregfunc(void);
+
+TRACE_EVENT_FN(sys_enter,
+
+ TP_PROTO(struct pt_regs *regs, long id),
+
+ TP_ARGS(regs, id),
+
+ TP_STRUCT__entry(
+ __field( long, id )
+ __array( unsigned long, args, 6 )
+ ),
+
+ TP_fast_assign(
+ __entry->id = id;
+ syscall_get_arguments(current, regs, 0, 6, __entry->args);
+ ),
+
+ TP_printk("NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)",
+ __entry->id,
+ __entry->args[0], __entry->args[1], __entry->args[2],
+ __entry->args[3], __entry->args[4], __entry->args[5]),
+
+ syscall_regfunc, syscall_unregfunc
+);
+
+TRACE_EVENT_FN(sys_exit,
+
+ TP_PROTO(struct pt_regs *regs, long ret),
+
+ TP_ARGS(regs, ret),
+
+ TP_STRUCT__entry(
+ __field( long, id )
+ __field( long, ret )
+ ),
+
+ TP_fast_assign(
+ __entry->id = syscall_get_nr(current, regs);
+ __entry->ret = ret;
+ ),
+
+ TP_printk("NR %ld = %ld",
+ __entry->id, __entry->ret),
+
+ syscall_regfunc, syscall_unregfunc
+);
+
+#endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
+
+#endif /* _TRACE_EVENTS_SYSCALLS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index f64fbaae781..308bafd9332 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -21,11 +21,14 @@
#undef __field
#define __field(type, item) type item;
+#undef __field_ext
+#define __field_ext(type, item, filter_type) type item;
+
#undef __array
#define __array(type, item, len) type item[len];
#undef __dynamic_array
-#define __dynamic_array(type, item, len) unsigned short __data_loc_##item;
+#define __dynamic_array(type, item, len) u32 __data_loc_##item;
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
@@ -42,6 +45,16 @@
}; \
static struct ftrace_event_call event_##name
+#undef __cpparg
+#define __cpparg(arg...) arg
+
+/* Callbacks are meaningless to ftrace. */
+#undef TRACE_EVENT_FN
+#define TRACE_EVENT_FN(name, proto, args, tstruct, \
+ assign, print, reg, unreg) \
+ TRACE_EVENT(name, __cpparg(proto), __cpparg(args), \
+ __cpparg(tstruct), __cpparg(assign), __cpparg(print)) \
+
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
@@ -51,23 +64,27 @@
* Include the following:
*
* struct ftrace_data_offsets_<call> {
- * int <item1>;
- * int <item2>;
+ * u32 <item1>;
+ * u32 <item2>;
* [...]
* };
*
- * The __dynamic_array() macro will create each int <item>, this is
+ * The __dynamic_array() macro will create each u32 <item>, this is
* to keep the offset of each array from the beginning of the event.
+ * The size of an array is also encoded, in the higher 16 bits of <item>.
*/
#undef __field
-#define __field(type, item);
+#define __field(type, item)
+
+#undef __field_ext
+#define __field_ext(type, item, filter_type)
#undef __array
#define __array(type, item, len)
#undef __dynamic_array
-#define __dynamic_array(type, item, len) int item;
+#define __dynamic_array(type, item, len) u32 item;
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
@@ -109,6 +126,9 @@
if (!ret) \
return 0;
+#undef __field_ext
+#define __field_ext(type, item, filter_type) __field(type, item)
+
#undef __array
#define __array(type, item, len) \
ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
@@ -120,7 +140,7 @@
#undef __dynamic_array
#define __dynamic_array(type, item, len) \
- ret = trace_seq_printf(s, "\tfield:__data_loc " #item ";\t" \
+ ret = trace_seq_printf(s, "\tfield:__data_loc " #type "[] " #item ";\t"\
"offset:%u;\tsize:%u;\n", \
(unsigned int)offsetof(typeof(field), \
__data_loc_##item), \
@@ -150,7 +170,8 @@
#undef TRACE_EVENT
#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
static int \
-ftrace_format_##call(struct trace_seq *s) \
+ftrace_format_##call(struct ftrace_event_call *unused, \
+ struct trace_seq *s) \
{ \
struct ftrace_raw_##call field __attribute__((unused)); \
int ret = 0; \
@@ -210,7 +231,7 @@ ftrace_format_##call(struct trace_seq *s) \
#undef __get_dynamic_array
#define __get_dynamic_array(field) \
- ((void *)__entry + __entry->__data_loc_##field)
+ ((void *)__entry + (__entry->__data_loc_##field & 0xffff))
#undef __get_str
#define __get_str(field) (char *)__get_dynamic_array(field)
@@ -263,28 +284,33 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-#undef __field
-#define __field(type, item) \
+#undef __field_ext
+#define __field_ext(type, item, filter_type) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
- sizeof(field.item), is_signed_type(type)); \
+ sizeof(field.item), \
+ is_signed_type(type), filter_type); \
if (ret) \
return ret;
+#undef __field
+#define __field(type, item) __field_ext(type, item, FILTER_OTHER)
+
#undef __array
#define __array(type, item, len) \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
ret = trace_define_field(event_call, #type "[" #len "]", #item, \
offsetof(typeof(field), item), \
- sizeof(field.item), 0); \
+ sizeof(field.item), 0, FILTER_OTHER); \
if (ret) \
return ret;
#undef __dynamic_array
#define __dynamic_array(type, item, len) \
- ret = trace_define_field(event_call, "__data_loc" "[" #type "]", #item,\
- offsetof(typeof(field), __data_loc_##item), \
- sizeof(field.__data_loc_##item), 0);
+ ret = trace_define_field(event_call, "__data_loc " #type "[]", #item, \
+ offsetof(typeof(field), __data_loc_##item), \
+ sizeof(field.__data_loc_##item), 0, \
+ FILTER_OTHER);
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
@@ -292,17 +318,14 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
#undef TRACE_EVENT
#define TRACE_EVENT(call, proto, args, tstruct, func, print) \
int \
-ftrace_define_fields_##call(void) \
+ftrace_define_fields_##call(struct ftrace_event_call *event_call) \
{ \
struct ftrace_raw_##call field; \
- struct ftrace_event_call *event_call = &event_##call; \
int ret; \
\
- __common_field(int, type, 1); \
- __common_field(unsigned char, flags, 0); \
- __common_field(unsigned char, preempt_count, 0); \
- __common_field(int, pid, 1); \
- __common_field(int, tgid, 1); \
+ ret = trace_define_common_fields(event_call); \
+ if (ret) \
+ return ret; \
\
tstruct; \
\
@@ -321,6 +344,9 @@ ftrace_define_fields_##call(void) \
#undef __field
#define __field(type, item)
+#undef __field_ext
+#define __field_ext(type, item, filter_type)
+
#undef __array
#define __array(type, item, len)
@@ -328,6 +354,7 @@ ftrace_define_fields_##call(void) \
#define __dynamic_array(type, item, len) \
__data_offsets->item = __data_size + \
offsetof(typeof(*entry), __data); \
+ __data_offsets->item |= (len * sizeof(type)) << 16; \
__data_size += (len) * sizeof(type);
#undef __string
@@ -433,13 +460,15 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
* {
* struct ring_buffer_event *event;
* struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ * struct ring_buffer *buffer;
* unsigned long irq_flags;
* int pc;
*
* local_save_flags(irq_flags);
* pc = preempt_count();
*
- * event = trace_current_buffer_lock_reserve(event_<call>.id,
+ * event = trace_current_buffer_lock_reserve(&buffer,
+ * event_<call>.id,
* sizeof(struct ftrace_raw_<call>),
* irq_flags, pc);
* if (!event)
@@ -449,7 +478,7 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
* <assign>; <-- Here we assign the entries by the __field and
* __array macros.
*
- * trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ * trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
* }
*
* static int ftrace_raw_reg_event_<call>(void)
@@ -541,6 +570,7 @@ static void ftrace_raw_event_##call(proto) \
struct ftrace_event_call *event_call = &event_##call; \
struct ring_buffer_event *event; \
struct ftrace_raw_##call *entry; \
+ struct ring_buffer *buffer; \
unsigned long irq_flags; \
int __data_size; \
int pc; \
@@ -550,7 +580,8 @@ static void ftrace_raw_event_##call(proto) \
\
__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
\
- event = trace_current_buffer_lock_reserve(event_##call.id, \
+ event = trace_current_buffer_lock_reserve(&buffer, \
+ event_##call.id, \
sizeof(*entry) + __data_size, \
irq_flags, pc); \
if (!event) \
@@ -562,11 +593,12 @@ static void ftrace_raw_event_##call(proto) \
\
{ assign; } \
\
- if (!filter_current_check_discard(event_call, entry, event)) \
- trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+ if (!filter_current_check_discard(buffer, event_call, entry, event)) \
+ trace_nowake_buffer_unlock_commit(buffer, \
+ event, irq_flags, pc); \
} \
\
-static int ftrace_raw_reg_event_##call(void) \
+static int ftrace_raw_reg_event_##call(void *ptr) \
{ \
int ret; \
\
@@ -577,7 +609,7 @@ static int ftrace_raw_reg_event_##call(void) \
return ret; \
} \
\
-static void ftrace_raw_unreg_event_##call(void) \
+static void ftrace_raw_unreg_event_##call(void *ptr) \
{ \
unregister_trace_##call(ftrace_raw_event_##call); \
} \
@@ -595,7 +627,6 @@ static int ftrace_raw_init_event_##call(void) \
return -ENODEV; \
event_##call.id = id; \
INIT_LIST_HEAD(&event_##call.fields); \
- init_preds(&event_##call); \
return 0; \
} \
\
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 8cfe515cbc4..5dc283ba5ae 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -1,8 +1,13 @@
#ifndef _TRACE_SYSCALL_H
#define _TRACE_SYSCALL_H
+#include <linux/tracepoint.h>
+#include <linux/unistd.h>
+#include <linux/ftrace_event.h>
+
#include <asm/ptrace.h>
+
/*
* A syscall entry in the ftrace syscalls array.
*
@@ -10,26 +15,49 @@
* @nb_args: number of parameters it takes
* @types: list of types as strings
* @args: list of args as strings (args[i] matches types[i])
+ * @enter_id: associated ftrace enter event id
+ * @exit_id: associated ftrace exit event id
+ * @enter_event: associated syscall_enter trace event
+ * @exit_event: associated syscall_exit trace event
*/
struct syscall_metadata {
const char *name;
int nb_args;
const char **types;
const char **args;
+ int enter_id;
+ int exit_id;
+
+ struct ftrace_event_call *enter_event;
+ struct ftrace_event_call *exit_event;
};
#ifdef CONFIG_FTRACE_SYSCALLS
-extern void arch_init_ftrace_syscalls(void);
extern struct syscall_metadata *syscall_nr_to_meta(int nr);
-extern void start_ftrace_syscalls(void);
-extern void stop_ftrace_syscalls(void);
-extern void ftrace_syscall_enter(struct pt_regs *regs);
-extern void ftrace_syscall_exit(struct pt_regs *regs);
-#else
-static inline void start_ftrace_syscalls(void) { }
-static inline void stop_ftrace_syscalls(void) { }
-static inline void ftrace_syscall_enter(struct pt_regs *regs) { }
-static inline void ftrace_syscall_exit(struct pt_regs *regs) { }
+extern int syscall_name_to_nr(char *name);
+void set_syscall_enter_id(int num, int id);
+void set_syscall_exit_id(int num, int id);
+extern struct trace_event event_syscall_enter;
+extern struct trace_event event_syscall_exit;
+extern int reg_event_syscall_enter(void *ptr);
+extern void unreg_event_syscall_enter(void *ptr);
+extern int reg_event_syscall_exit(void *ptr);
+extern void unreg_event_syscall_exit(void *ptr);
+extern int syscall_enter_format(struct ftrace_event_call *call,
+ struct trace_seq *s);
+extern int syscall_exit_format(struct ftrace_event_call *call,
+ struct trace_seq *s);
+extern int syscall_enter_define_fields(struct ftrace_event_call *call);
+extern int syscall_exit_define_fields(struct ftrace_event_call *call);
+enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags);
+enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
+#endif
+#ifdef CONFIG_EVENT_PROFILE
+int reg_prof_syscall_enter(char *name);
+void unreg_prof_syscall_enter(char *name);
+int reg_prof_syscall_exit(char *name);
+void unreg_prof_syscall_exit(char *name);
+
#endif
#endif /* _TRACE_SYSCALL_H */