2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-22 20:23:57 +08:00
linux-next/include/linux/init_task.h
Paul Mackerras a63eaf34ae perf_counter: Dynamically allocate tasks' perf_counter_context struct
This replaces the struct perf_counter_context in the task_struct with
a pointer to a dynamically allocated perf_counter_context struct.  The
main reason for doing is this is to allow us to transfer a
perf_counter_context from one task to another when we do lazy PMU
switching in a later patch.

This has a few side-benefits: the task_struct becomes a little smaller,
we save some memory because only tasks that have perf_counters attached
get a perf_counter_context allocated for them, and we can remove the
inclusion of <linux/perf_counter.h> in sched.h, meaning that we don't
end up recompiling nearly everything whenever perf_counter.h changes.

The perf_counter_context structures are reference-counted and freed
when the last reference is dropped.  A context can have references
from its task and the counters on its task.  Counters can outlive the
task so it is possible that a context will be freed well after its
task has exited.

Contexts are allocated on fork if the parent had a context, or
otherwise the first time that a per-task counter is created on a task.
In the latter case, we set the context pointer in the task struct
locklessly using an atomic compare-and-exchange operation in case we
raced with some other task in creating a context for the subject task.

This also removes the task pointer from the perf_counter struct.  The
task pointer was not used anywhere and would make it harder to move a
context from one task to another.  Anything that needed to know which
task a counter was attached to was already using counter->ctx->task.

The __perf_counter_init_context function moves up in perf_counter.c
so that it can be called from find_get_context, and now initializes
the refcount, but is otherwise unchanged.

We were potentially calling list_del_counter twice: once from
__perf_counter_exit_task when the task exits and once from
__perf_counter_remove_from_context when the counter's fd gets closed.
This adds a check in list_del_counter so it doesn't do anything if
the counter has already been removed from the lists.

Since perf_counter_task_sched_in doesn't do anything if the task doesn't
have a context, and leaves cpuctx->task_ctx = NULL, this adds code to
__perf_install_in_context to set cpuctx->task_ctx if necessary, i.e. in
the case where the current task adds the first counter to itself and
thus creates a context for itself.

This also adds similar code to __perf_counter_enable to handle a
similar situation which can arise when the counters have been disabled
using prctl; that also leaves cpuctx->task_ctx = NULL.

[ Impact: refactor counter context management to prepare for new feature ]

Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <18966.10075.781053.231153@cargo.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-05-22 12:18:19 +02:00

189 lines
5.2 KiB
C

#ifndef _LINUX__INIT_TASK_H
#define _LINUX__INIT_TASK_H
#include <linux/rcupdate.h>
#include <linux/irqflags.h>
#include <linux/utsname.h>
#include <linux/lockdep.h>
#include <linux/ftrace.h>
#include <linux/ipc.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/securebits.h>
#include <net/net_namespace.h>
extern struct files_struct init_files;
extern struct fs_struct init_fs;
#define INIT_MM(name) \
{ \
.mm_rb = RB_ROOT, \
.pgd = swapper_pg_dir, \
.mm_users = ATOMIC_INIT(2), \
.mm_count = ATOMIC_INIT(1), \
.mmap_sem = __RWSEM_INITIALIZER(name.mmap_sem), \
.page_table_lock = __SPIN_LOCK_UNLOCKED(name.page_table_lock), \
.mmlist = LIST_HEAD_INIT(name.mmlist), \
.cpu_vm_mask = CPU_MASK_ALL, \
}
#define INIT_SIGNALS(sig) { \
.count = ATOMIC_INIT(1), \
.wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
.shared_pending = { \
.list = LIST_HEAD_INIT(sig.shared_pending.list), \
.signal = {{0}}}, \
.posix_timers = LIST_HEAD_INIT(sig.posix_timers), \
.cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \
.rlim = INIT_RLIMITS, \
.cputimer = { \
.cputime = INIT_CPUTIME, \
.running = 0, \
.lock = __SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \
}, \
}
extern struct nsproxy init_nsproxy;
#define INIT_NSPROXY(nsproxy) { \
.pid_ns = &init_pid_ns, \
.count = ATOMIC_INIT(1), \
.uts_ns = &init_uts_ns, \
.mnt_ns = NULL, \
INIT_NET_NS(net_ns) \
INIT_IPC_NS(ipc_ns) \
}
#define INIT_SIGHAND(sighand) { \
.count = ATOMIC_INIT(1), \
.action = { { { .sa_handler = NULL, } }, }, \
.siglock = __SPIN_LOCK_UNLOCKED(sighand.siglock), \
.signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(sighand.signalfd_wqh), \
}
extern struct group_info init_groups;
#define INIT_STRUCT_PID { \
.count = ATOMIC_INIT(1), \
.tasks = { \
{ .first = &init_task.pids[PIDTYPE_PID].node }, \
{ .first = &init_task.pids[PIDTYPE_PGID].node }, \
{ .first = &init_task.pids[PIDTYPE_SID].node }, \
}, \
.rcu = RCU_HEAD_INIT, \
.level = 0, \
.numbers = { { \
.nr = 0, \
.ns = &init_pid_ns, \
.pid_chain = { .next = NULL, .pprev = NULL }, \
}, } \
}
#define INIT_PID_LINK(type) \
{ \
.node = { \
.next = NULL, \
.pprev = &init_struct_pid.tasks[type].first, \
}, \
.pid = &init_struct_pid, \
}
#ifdef CONFIG_AUDITSYSCALL
#define INIT_IDS \
.loginuid = -1, \
.sessionid = -1,
#else
#define INIT_IDS
#endif
#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
/*
* Because of the reduced scope of CAP_SETPCAP when filesystem
* capabilities are in effect, it is safe to allow CAP_SETPCAP to
* be available in the default configuration.
*/
# define CAP_INIT_BSET CAP_FULL_SET
#else
# define CAP_INIT_BSET CAP_INIT_EFF_SET
#endif
extern struct cred init_cred;
/*
* INIT_TASK is used to set up the first task table, touch at
* your own risk!. Base=0, limit=0x1fffff (=2MB)
*/
#define INIT_TASK(tsk) \
{ \
.state = 0, \
.stack = &init_thread_info, \
.usage = ATOMIC_INIT(2), \
.flags = PF_KTHREAD, \
.lock_depth = -1, \
.prio = MAX_PRIO-20, \
.static_prio = MAX_PRIO-20, \
.normal_prio = MAX_PRIO-20, \
.policy = SCHED_NORMAL, \
.cpus_allowed = CPU_MASK_ALL, \
.mm = NULL, \
.active_mm = &init_mm, \
.se = { \
.group_node = LIST_HEAD_INIT(tsk.se.group_node), \
}, \
.rt = { \
.run_list = LIST_HEAD_INIT(tsk.rt.run_list), \
.time_slice = HZ, \
.nr_cpus_allowed = NR_CPUS, \
}, \
.tasks = LIST_HEAD_INIT(tsk.tasks), \
.pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \
.ptraced = LIST_HEAD_INIT(tsk.ptraced), \
.ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \
.real_parent = &tsk, \
.parent = &tsk, \
.children = LIST_HEAD_INIT(tsk.children), \
.sibling = LIST_HEAD_INIT(tsk.sibling), \
.group_leader = &tsk, \
.real_cred = &init_cred, \
.cred = &init_cred, \
.cred_exec_mutex = \
__MUTEX_INITIALIZER(tsk.cred_exec_mutex), \
.comm = "swapper", \
.thread = INIT_THREAD, \
.fs = &init_fs, \
.files = &init_files, \
.signal = &init_signals, \
.sighand = &init_sighand, \
.nsproxy = &init_nsproxy, \
.pending = { \
.list = LIST_HEAD_INIT(tsk.pending.list), \
.signal = {{0}}}, \
.blocked = {{0}}, \
.alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \
.journal_info = NULL, \
.cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
.fs_excl = ATOMIC_INIT(0), \
.pi_lock = __SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
.timer_slack_ns = 50000, /* 50 usec default slack */ \
.pids = { \
[PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \
[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \
[PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \
}, \
.dirties = INIT_PROP_LOCAL_SINGLE(dirties), \
INIT_IDS \
INIT_TRACE_IRQFLAGS \
INIT_LOCKDEP \
INIT_FTRACE_GRAPH \
}
#define INIT_CPU_TIMERS(cpu_timers) \
{ \
LIST_HEAD_INIT(cpu_timers[0]), \
LIST_HEAD_INIT(cpu_timers[1]), \
LIST_HEAD_INIT(cpu_timers[2]), \
}
#endif