* 'perfcounters-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (574 commits)
perf_counter: Turn off by default
perf_counter: Add counter->id to the throttle event
perf_counter: Better align code
perf_counter: Rename L2 to LL cache
perf_counter: Standardize event names
perf_counter: Rename enums
perf_counter tools: Clean up u64 usage
perf_counter: Rename perf_counter_limit sysctl
perf_counter: More paranoia settings
perf_counter: powerpc: Implement generalized cache events for POWER processors
perf_counters: powerpc: Add support for POWER7 processors
perf_counter: Accurate period data
perf_counter: Introduce struct for sample data
perf_counter tools: Normalize data using per sample period data
perf_counter: Annotate exit ctx recursion
perf_counter tools: Propagate signals properly
perf_counter tools: Small frequency related fixes
perf_counter: More aggressive frequency adjustment
perf_counter/x86: Fix the model number of Intel Core2 processors
perf_counter, x86: Correct some event and umask values for Intel processors
...
M: Mail patches to
L: Mailing list that is relevant to this area
W: Web-page with status/info
-T: SCM tree type and location. Type is one of: git, hg, quilt.
+T: SCM tree type and location. Type is one of: git, hg, quilt, stgit.
S: Status, one of the following:
Supported: Someone is actually paid to look after this.
8250/16?50 (AND CLONE UARTS) SERIAL DRIVER
L: linux-serial@vger.kernel.org
W: http://serial.sourceforge.net
-S: Orphan
+M: alan@lxorguk.ukuu.org.uk
+S: Odd Fixes
F: drivers/serial/8250*
F: include/linux/serial_8250.h
F: drivers/edac/edac_*
F: include/linux/edac.h
+EDAC-AMD64
+P: Doug Thompson
+M: dougthompson@xmission.com
+P: Borislav Petkov
+M: borislav.petkov@amd.com
+L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers)
+W: bluesmoke.sourceforge.net
+S: Supported
+F: drivers/edac/amd64_edac*
+
EDAC-E752X
P: Mark Gross
M: mark.gross@intel.com
F: include/linux/delayacct.h
F: kernel/delayacct.c
+ PERFORMANCE COUNTER SUBSYSTEM
+ P: Peter Zijlstra
+ M: a.p.zijlstra@chello.nl
+ P: Paul Mackerras
+ M: paulus@samba.org
+ P: Ingo Molnar
+ M: mingo@elte.hu
+ L: linux-kernel@vger.kernel.org
+ S: Supported
+
PERSONALITY HANDLING
P: Christoph Hellwig
M: hch@infradead.org
M: alan@lxorguk.ukuu.org.uk
L: linux-kernel@vger.kernel.org
S: Maintained
+T: stgit http://zeniv.linux.org.uk/~alan/ttydev/
TULIP NETWORK DRIVERS
P: Grant Grundler
#include <linux/string.h>
#include <linux/init.h>
#include <linux/pagemap.h>
+ #include <linux/perf_counter.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
task_lock(tsk);
strlcpy(tsk->comm, buf, sizeof(tsk->comm));
task_unlock(tsk);
+ perf_counter_comm(tsk);
}
int flush_old_exec(struct linux_binprm * bprm)
current->personality &= ~bprm->per_clear;
+ /*
+ * Flush performance counters when crossing a
+ * security domain:
+ */
+ if (!get_dumpable(current->mm))
+ perf_counter_exit_task(current);
+
/* An exec changes our domain. We are no longer part of the thread
group */
commit_creds(bprm->cred);
bprm->cred = NULL;
- /* cred_exec_mutex must be held at least to this point to prevent
+ /* cred_guard_mutex must be held at least to this point to prevent
* ptrace_attach() from altering our determination of the task's
* credentials; any time after this it may be unlocked */
/*
* determine how safe it is to execute the proposed program
- * - the caller must hold current->cred_exec_mutex to protect against
+ * - the caller must hold current->cred_guard_mutex to protect against
* PTRACE_ATTACH
*/
int check_unsafe_exec(struct linux_binprm *bprm)
if (!bprm)
goto out_files;
- retval = mutex_lock_interruptible(¤t->cred_exec_mutex);
+ retval = mutex_lock_interruptible(¤t->cred_guard_mutex);
if (retval < 0)
goto out_free;
current->in_execve = 1;
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
- mutex_unlock(¤t->cred_exec_mutex);
+ mutex_unlock(¤t->cred_guard_mutex);
acct_update_integrals(current);
free_bprm(bprm);
if (displaced)
out_unlock:
current->in_execve = 0;
- mutex_unlock(¤t->cred_exec_mutex);
+ mutex_unlock(¤t->cred_guard_mutex);
out_free:
free_bprm(bprm);
extern struct cred init_cred;
+ #ifdef CONFIG_PERF_COUNTERS
+ # define INIT_PERF_COUNTERS(tsk) \
+ .perf_counter_mutex = \
+ __MUTEX_INITIALIZER(tsk.perf_counter_mutex), \
+ .perf_counter_list = LIST_HEAD_INIT(tsk.perf_counter_list),
+ #else
+ # define INIT_PERF_COUNTERS(tsk)
+ #endif
+
/*
* INIT_TASK is used to set up the first task table, touch at
* your own risk!. Base=0, limit=0x1fffff (=2MB)
.group_leader = &tsk, \
.real_cred = &init_cred, \
.cred = &init_cred, \
- .cred_exec_mutex = \
- __MUTEX_INITIALIZER(tsk.cred_exec_mutex), \
+ .cred_guard_mutex = \
+ __MUTEX_INITIALIZER(tsk.cred_guard_mutex), \
.comm = "swapper", \
.thread = INIT_THREAD, \
.fs = &init_fs, \
}, \
.dirties = INIT_PROP_LOCAL_SINGLE(dirties), \
INIT_IDS \
+ INIT_PERF_COUNTERS(tsk) \
INIT_TRACE_IRQFLAGS \
INIT_LOCKDEP \
INIT_FTRACE_GRAPH \
struct bio;
struct fs_struct;
struct bts_context;
+ struct perf_counter_context;
/*
* List of flags we want to share for kernel threads,
extern unsigned long nr_uninterruptible(void);
extern unsigned long nr_iowait(void);
extern void calc_global_load(void);
+ extern u64 cpu_nr_migrations(int cpu);
extern unsigned long get_parent_ip(unsigned long addr);
struct work_struct work;
#endif
#endif
+
+ #ifdef CONFIG_PERF_COUNTERS
+ atomic_long_t locked_vm;
+ #endif
};
extern int uids_sysfs_init(void);
u64 last_wakeup;
u64 avg_overlap;
+ u64 nr_migrations;
+
u64 start_runtime;
u64 avg_wakeup;
- u64 nr_migrations;
#ifdef CONFIG_SCHEDSTATS
u64 wait_start;
* credentials (COW) */
const struct cred *cred; /* effective (overridable) subjective task
* credentials (COW) */
- struct mutex cred_exec_mutex; /* execve vs ptrace cred calculation mutex */
+ struct mutex cred_guard_mutex; /* guard against foreign influences on
+ * credential calculations
+ * (notably. ptrace) */
char comm[TASK_COMM_LEN]; /* executable name excluding path
- access with [gs]et_task_comm (which lock
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
#endif
+ #ifdef CONFIG_PERF_COUNTERS
+ struct perf_counter_context *perf_counter_ctxp;
+ struct mutex perf_counter_mutex;
+ struct list_head perf_counter_list;
+ #endif
#ifdef CONFIG_NUMA
struct mempolicy *mempolicy;
short il_next;
extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
+extern void __flush_signals(struct task_struct *);
extern void ignore_signals(struct task_struct *);
extern void flush_signal_handlers(struct task_struct *, int force_default);
extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
#define TASK_SIZE_OF(tsk) TASK_SIZE
#endif
+ /*
+ * Call the function if the target task is executing on a CPU right now:
+ */
+ extern void task_oncpu_function_call(struct task_struct *p,
+ void (*func) (void *info), void *info);
+
+
#ifdef CONFIG_MM_OWNER
extern void mm_update_next_owner(struct mm_struct *mm);
extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
#include <linux/tracehook.h>
#include <linux/fs_struct.h>
#include <linux/init_task.h>
+ #include <linux/perf_counter.h>
#include <trace/events/sched.h>
#include <asm/uaccess.h>
{
struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+ #ifdef CONFIG_PERF_COUNTERS
+ WARN_ON_ONCE(tsk->perf_counter_ctxp);
+ #endif
trace_sched_process_free(tsk);
put_task_struct(tsk);
}
atomic_dec(&__task_cred(p)->user->processes);
proc_flush_task(p);
+
write_lock_irq(&tasklist_lock);
tracehook_finish_release_task(p);
__exit_signal(p);
module_put(tsk->binfmt->module);
proc_exit_connector(tsk);
+
+ /*
+ * Flush inherited counters to the parent - before the parent
+ * gets woken up by child-exit notifications.
+ */
+ perf_counter_exit_task(tsk);
+
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
mpol_put(tsk->mempolicy);
tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX
- /*
- * This must happen late, after the PID is not
- * hashed anymore:
- */
if (unlikely(!list_empty(&tsk->pi_state_list)))
exit_pi_state_list(tsk);
if (unlikely(current->pi_state_cache))
*/
if (*notask_error)
*notask_error = ret;
+ return 0;
}
if (likely(!ptrace) && unlikely(p->ptrace)) {
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/debug_locks.h>
+ #include <linux/perf_counter.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
#include <linux/pagemap.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
-#include <linux/bootmem.h>
#include <linux/debugfs.h>
#include <linux/ctype.h>
#include <linux/ftrace.h>
struct load_weight load;
unsigned long nr_load_updates;
u64 nr_switches;
+ u64 nr_migrations_in;
struct cfs_rq cfs;
struct rt_rq rt;
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
- static inline void update_rq_clock(struct rq *rq)
+ inline void update_rq_clock(struct rq *rq)
{
rq->clock = sched_clock_cpu(cpu_of(rq));
}
p->se.sleep_start -= clock_offset;
if (p->se.block_start)
p->se.block_start -= clock_offset;
+ #endif
if (old_cpu != new_cpu) {
- schedstat_inc(p, se.nr_migrations);
+ p->se.nr_migrations++;
+ new_rq->nr_migrations_in++;
+ #ifdef CONFIG_SCHEDSTATS
if (task_hot(p, old_rq->clock, NULL))
schedstat_inc(p, se.nr_forced2_migrations);
- }
#endif
+ perf_counter_task_migration(p, new_cpu);
+ }
p->se.vruntime -= old_cfsrq->min_vruntime -
new_cfsrq->min_vruntime;
#endif /* CONFIG_SMP */
+ /**
+ * task_oncpu_function_call - call a function on the cpu on which a task runs
+ * @p: the task to evaluate
+ * @func: the function to be called
+ * @info: the function call argument
+ *
+ * Calls the function @func when the task is currently running. This might
+ * be on the current CPU, which just calls the function directly
+ */
+ void task_oncpu_function_call(struct task_struct *p,
+ void (*func) (void *info), void *info)
+ {
+ int cpu;
+
+ preempt_disable();
+ cpu = task_cpu(p);
+ if (task_curr(p))
+ smp_call_function_single(cpu, func, info, 1);
+ preempt_enable();
+ }
+
/***
* try_to_wake_up - wake up a thread
* @p: the to-be-woken-up thread
p->se.exec_start = 0;
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
+ p->se.nr_migrations = 0;
p->se.last_wakeup = 0;
p->se.avg_overlap = 0;
p->se.start_runtime = 0;
*/
prev_state = prev->state;
finish_arch_switch(prev);
+ perf_counter_task_sched_in(current, cpu_of(rq));
finish_lock_switch(rq, prev);
#ifdef CONFIG_SMP
if (post_schedule)
}
}
+ /*
+ * Externally visible per-cpu scheduler statistics:
+ * cpu_nr_migrations(cpu) - number of migrations into that cpu
+ */
+ u64 cpu_nr_migrations(int cpu)
+ {
+ return cpu_rq(cpu)->nr_migrations_in;
+ }
+
/*
* Update rq->cpu_load[] statistics. This function is usually called every
* scheduler tick (TICK_NSEC).
curr->sched_class->task_tick(rq, curr, 0);
spin_unlock(&rq->lock);
+ perf_counter_task_tick(curr, cpu);
+
#ifdef CONFIG_SMP
rq->idle_at_tick = idle_cpu(cpu);
trigger_load_balance(rq, cpu);
if (likely(prev != next)) {
sched_info_switch(prev, next);
+ perf_counter_task_sched_out(prev, next, cpu);
rq->nr_switches++;
rq->curr = next;
return NOTIFY_OK;
}
- /* Register at highest priority so that task migration (migrate_all_tasks)
- * happens before everything else.
+ /*
+ * Register at high priority so that task migration (migrate_all_tasks)
+ * happens before everything else. This has to be lower priority than
+ * the notifier in the perf_counter subsystem, though.
*/
static struct notifier_block __cpuinitdata migration_notifier = {
.notifier_call = migration_call,
static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
{
+ gfp_t gfp = GFP_KERNEL;
+
memset(rd, 0, sizeof(*rd));
- if (bootmem) {
- alloc_bootmem_cpumask_var(&def_root_domain.span);
- alloc_bootmem_cpumask_var(&def_root_domain.online);
- alloc_bootmem_cpumask_var(&def_root_domain.rto_mask);
- cpupri_init(&rd->cpupri, true);
- return 0;
- }
+ if (bootmem)
+ gfp = GFP_NOWAIT;
- if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->span, gfp))
goto out;
- if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->online, gfp))
goto free_span;
- if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->rto_mask, gfp))
goto free_online;
- if (cpupri_init(&rd->cpupri, false) != 0)
+ if (cpupri_init(&rd->cpupri, bootmem) != 0)
goto free_rto_mask;
return 0;
* we use alloc_bootmem().
*/
if (alloc_size) {
- ptr = (unsigned long)alloc_bootmem(alloc_size);
+ ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
#ifdef CONFIG_FAIR_GROUP_SCHED
init_task_group.se = (struct sched_entity **)ptr;
* 1024) and two child groups A0 and A1 (of weight 1024 each),
* then A0's share of the cpu resource is:
*
- * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
+ * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
*
* We achieve this by letting init_task_group's tasks sit
* directly in rq->cfs (i.e init_task_group->se[] = NULL).
current->sched_class = &fair_sched_class;
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
- alloc_bootmem_cpumask_var(&nohz_cpu_mask);
+ alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ
- alloc_bootmem_cpumask_var(&nohz.cpu_mask);
- alloc_bootmem_cpumask_var(&nohz.ilb_grp_nohz_mask);
+ alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+ alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
#endif
- alloc_bootmem_cpumask_var(&cpu_isolated_map);
+ alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */
+ perf_counter_init();
+
scheduler_running = 1;
}
#include <linux/reboot.h>
#include <linux/ftrace.h>
#include <linux/slow-work.h>
+ #include <linux/perf_counter.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
#ifdef CONFIG_MODULES
extern char modprobe_path[];
+extern int modules_disabled;
#endif
#ifdef CONFIG_CHR_DEV_SG
extern int sg_big_buff;
.proc_handler = &proc_dostring,
.strategy = &sysctl_string,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "modules_disabled",
+ .data = &modules_disabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ /* only handle a transition from default "0" to "1" */
+ .proc_handler = &proc_dointvec_minmax,
+ .extra1 = &one,
+ .extra2 = &one,
+ },
#endif
#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
{
.child = slow_work_sysctls,
},
#endif
+ #ifdef CONFIG_PERF_COUNTERS
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "perf_counter_paranoid",
+ .data = &sysctl_perf_counter_paranoid,
+ .maxlen = sizeof(sysctl_perf_counter_paranoid),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "perf_counter_mlock_kb",
+ .data = &sysctl_perf_counter_mlock,
+ .maxlen = sizeof(sysctl_perf_counter_mlock),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "perf_counter_max_sample_rate",
+ .data = &sysctl_perf_counter_sample_rate,
+ .maxlen = sizeof(sysctl_perf_counter_sample_rate),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ #endif
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
.strategy = &sysctl_jiffies,
},
#endif
-#ifdef CONFIG_SECURITY
{
.ctl_name = CTL_UNNUMBERED,
.procname = "mmap_min_addr",
.mode = 0644,
.proc_handler = &proc_doulongvec_minmax,
},
-#endif
#ifdef CONFIG_NUMA
{
.ctl_name = CTL_UNNUMBERED,
#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
+ #include <linux/perf_counter.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
struct percpu_counter vm_committed_as;
+/* amount of vm to protect from userspace access */
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+
/*
* Check that a process has enough memory to allocate a new virtual
* mapping. 0 means there is enough memory for the allocation to
if (correct_wcount)
atomic_inc(&inode->i_writecount);
out:
+ perf_counter_mmap(vma);
+
mm->total_vm += len >> PAGE_SHIFT;
vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
if (vm_flags & VM_LOCKED) {
mm->total_vm += len >> PAGE_SHIFT;
+ perf_counter_mmap(vma);
+
return 0;
}