2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-21 19:53:59 +08:00
linux-next/include/linux/sched.h

2174 lines
64 KiB
C
Raw Normal View History

#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H
/*
* cloning flags:
*/
#define CSIGNAL 0x000000ff /* signal mask to be sent at exit */
#define CLONE_VM 0x00000100 /* set if VM shared between processes */
#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
#define CLONE_THREAD 0x00010000 /* Same thread group? */
#define CLONE_NEWNS 0x00020000 /* New namespace group? */
#define CLONE_SYSVSEM 0x00040000 /* share system V SEM_UNDO semantics */
#define CLONE_SETTLS 0x00080000 /* create a new TLS for the child */
#define CLONE_PARENT_SETTID 0x00100000 /* set the TID in the parent */
#define CLONE_CHILD_CLEARTID 0x00200000 /* clear the TID in the child */
#define CLONE_DETACHED 0x00400000 /* Unused, ignored */
#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */
#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */
#define CLONE_STOPPED 0x02000000 /* Start in stopped state */
#define CLONE_NEWUTS 0x04000000 /* New utsname group? */
#define CLONE_NEWIPC 0x08000000 /* New ipcs */
#define CLONE_NEWUSER 0x10000000 /* New user namespace */
#define CLONE_NEWPID 0x20000000 /* New pid namespace */
#define CLONE_NEWNET 0x40000000 /* New network namespace */
#define CLONE_IO 0x80000000 /* Clone io context */
/*
* Scheduling policies
*/
#define SCHED_NORMAL 0
#define SCHED_FIFO 1
#define SCHED_RR 2
#define SCHED_BATCH 3
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE 5
#ifdef __KERNEL__
struct sched_param {
int sched_priority;
};
#include <asm/param.h> /* for HZ */
#include <linux/capability.h>
#include <linux/threads.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
#include <linux/errno.h>
#include <linux/nodemask.h>
#include <linux/mm_types.h>
#include <asm/system.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/cputime.h>
#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/signal.h>
#include <linux/fs_struct.h>
#include <linux/compiler.h>
#include <linux/completion.h>
#include <linux/pid.h>
#include <linux/percpu.h>
#include <linux/topology.h>
#include <linux/proportions.h>
#include <linux/seccomp.h>
#include <linux/rcupdate.h>
#include <linux/rtmutex.h>
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>
#include <linux/hrtimer.h>
[PATCH] io-accounting: core statistics The present per-task IO accounting isn't very useful. It simply counts the number of bytes passed into read() and write(). So if a process reads 1MB from an already-cached file, it is accused of having performed 1MB of I/O, which is wrong. (David Wright had some comments on the applicability of the present logical IO accounting: For billing purposes it is useless but for workload analysis it is very useful read_bytes/read_calls average read request size write_bytes/write_calls average write request size read_bytes/read_blocks ie logical/physical can indicate hit rate or thrashing write_bytes/write_blocks ie logical/physical guess since pdflush writes can be missed I often look for logical larger than physical to see filesystem cache problems. And the bytes/cpusec can help find applications that are dominating the cache and causing slow interactive response from page cache contention. I want to find the IO intensive applications and make sure they are doing efficient IO. Thus the acctcms(sysV) or csacms command would give the high IO commands). This patchset adds new accounting which tries to be more accurate. We account for three things: reads: attempt to count the number of bytes which this process really did cause to be fetched from the storage layer. Done at the submit_bio() level, so it is accurate for block-backed filesystems. I also attempt to wire up NFS and CIFS. writes: attempt to count the number of bytes which this process caused to be sent to the storage layer. This is done at page-dirtying time. The big inaccuracy here is truncate. If a process writes 1MB to a file and then deletes the file, it will in fact perform no writeout. But it will have been accounted as having caused 1MB of write. So... cancelled_writes: account the number of bytes which this process caused to not happen, by truncating pagecache. We _could_ just subtract this from the process's `write' accounting. But that means that some processes would be reported to have done negative amounts of write IO, which is silly. So we just report the raw number and punt this decision up to userspace. Now, we _could_ account for writes at the physical I/O level. But - This would require that we track memory-dirtying tasks at the per-page level (would require a new pointer in struct page). - It would mean that IO statistics for a process are usually only available long after that process has exitted. Which means that we probably cannot communicate this info via taskstats. This patch: Wire up the kernel-private data structures and the accessor functions to manipulate them. Cc: Jay Lan <jlan@sgi.com> Cc: Shailabh Nagar <nagar@watson.ibm.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Chris Sturtivant <csturtiv@sgi.com> Cc: Tony Ernst <tee@sgi.com> Cc: Guillaume Thouvenin <guillaume.thouvenin@bull.net> Cc: David Wright <daw@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 18:19:19 +08:00
#include <linux/task_io_accounting.h>
#include <linux/kobject.h>
#include <linux/latencytop.h>
#include <asm/processor.h>
struct mem_cgroup;
struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 15:53:42 +08:00
struct bio;
/*
* List of flags we want to share for kernel threads,
* if only because they are not used by them anyway.
*/
#define CLONE_KERNEL (CLONE_FS | CLONE_FILES | CLONE_SIGHAND)
/*
* These are the constant used to fake the fixed-point load-average
* counting. Some notes:
* - 11 bit fractions expand to 22 bits by the multiplies: this gives
* a load-average precision of 10 bits integer + 11 bits fractional
* - if you want to count load-averages more often, you need more
* precision, or rounding will get you. With 2-second counting freq,
* the EXP_n values would be 1981, 2034 and 2043 if still using only
* 11 bit fractions.
*/
extern unsigned long avenrun[]; /* Load averages */
#define FSHIFT 11 /* nr of bits of precision */
#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */
#define LOAD_FREQ (5*HZ+1) /* 5 sec intervals */
#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */
#define EXP_5 2014 /* 1/exp(5sec/5min) */
#define EXP_15 2037 /* 1/exp(5sec/15min) */
#define CALC_LOAD(load,exp,n) \
load *= exp; \
load += n*(FIXED_1-exp); \
load >>= FSHIFT;
extern unsigned long total_forks;
extern int nr_threads;
DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
extern unsigned long nr_active(void);
extern unsigned long nr_iowait(void);
[PATCH] sched: implement smpnice Problem: The introduction of separate run queues per CPU has brought with it "nice" enforcement problems that are best described by a simple example. For the sake of argument suppose that on a single CPU machine with a nice==19 hard spinner and a nice==0 hard spinner running that the nice==0 task gets 95% of the CPU and the nice==19 task gets 5% of the CPU. Now suppose that there is a system with 2 CPUs and 2 nice==19 hard spinners and 2 nice==0 hard spinners running. The user of this system would be entitled to expect that the nice==0 tasks each get 95% of a CPU and the nice==19 tasks only get 5% each. However, whether this expectation is met is pretty much down to luck as there are four equally likely distributions of the tasks to the CPUs that the load balancing code will consider to be balanced with loads of 2.0 for each CPU. Two of these distributions involve one nice==0 and one nice==19 task per CPU and in these circumstances the users expectations will be met. The other two distributions both involve both nice==0 tasks being on one CPU and both nice==19 being on the other CPU and each task will get 50% of a CPU and the user's expectations will not be met. Solution: The solution to this problem that is implemented in the attached patch is to use weighted loads when determining if the system is balanced and, when an imbalance is detected, to move an amount of weighted load between run queues (as opposed to a number of tasks) to restore the balance. Once again, the easiest way to explain why both of these measures are necessary is to use a simple example. Suppose that (in a slight variation of the above example) that we have a two CPU system with 4 nice==0 and 4 nice=19 hard spinning tasks running and that the 4 nice==0 tasks are on one CPU and the 4 nice==19 tasks are on the other CPU. The weighted loads for the two CPUs would be 4.0 and 0.2 respectively and the load balancing code would move 2 tasks resulting in one CPU with a load of 2.0 and the other with load of 2.2. If this was considered to be a big enough imbalance to justify moving a task and that task was moved using the current move_tasks() then it would move the highest priority task that it found and this would result in one CPU with a load of 3.0 and the other with a load of 1.2 which would result in the movement of a task in the opposite direction and so on -- infinite loop. If, on the other hand, an amount of load to be moved is calculated from the imbalance (in this case 0.1) and move_tasks() skips tasks until it find ones whose contributions to the weighted load are less than this amount it would move two of the nice==19 tasks resulting in a system with 2 nice==0 and 2 nice=19 on each CPU with loads of 2.1 for each CPU. One of the advantages of this mechanism is that on a system where all tasks have nice==0 the load balancing calculations would be mathematically identical to the current load balancing code. Notes: struct task_struct: has a new field load_weight which (in a trade off of space for speed) stores the contribution that this task makes to a CPU's weighted load when it is runnable. struct runqueue: has a new field raw_weighted_load which is the sum of the load_weight values for the currently runnable tasks on this run queue. This field always needs to be updated when nr_running is updated so two new inline functions inc_nr_running() and dec_nr_running() have been created to make sure that this happens. This also offers a convenient way to optimize away this part of the smpnice mechanism when CONFIG_SMP is not defined. int try_to_wake_up(): in this function the value SCHED_LOAD_BALANCE is used to represent the load contribution of a single task in various calculations in the code that decides which CPU to put the waking task on. While this would be a valid on a system where the nice values for the runnable tasks were distributed evenly around zero it will lead to anomalous load balancing if the distribution is skewed in either direction. To overcome this problem SCHED_LOAD_SCALE has been replaced by the load_weight for the relevant task or by the average load_weight per task for the queue in question (as appropriate). int move_tasks(): The modifications to this function were complicated by the fact that active_load_balance() uses it to move exactly one task without checking whether an imbalance actually exists. This precluded the simple overloading of max_nr_move with max_load_move and necessitated the addition of the latter as an extra argument to the function. The internal implementation is then modified to move up to max_nr_move tasks and max_load_move of weighted load. This slightly complicates the code where move_tasks() is called and if ever active_load_balance() is changed to not use move_tasks() the implementation of move_tasks() should be simplified accordingly. struct sched_group *find_busiest_group(): Similar to try_to_wake_up(), there are places in this function where SCHED_LOAD_SCALE is used to represent the load contribution of a single task and the same issues are created. A similar solution is adopted except that it is now the average per task contribution to a group's load (as opposed to a run queue) that is required. As this value is not directly available from the group it is calculated on the fly as the queues in the groups are visited when determining the busiest group. A key change to this function is that it is no longer to scale down *imbalance on exit as move_tasks() uses the load in its scaled form. void set_user_nice(): has been modified to update the task's load_weight field when it's nice value and also to ensure that its run queue's raw_weighted_load field is updated if it was runnable. From: "Siddha, Suresh B" <suresh.b.siddha@intel.com> With smpnice, sched groups with highest priority tasks can mask the imbalance between the other sched groups with in the same domain. This patch fixes some of the listed down scenarios by not considering the sched groups which are lightly loaded. a) on a simple 4-way MP system, if we have one high priority and 4 normal priority tasks, with smpnice we would like to see the high priority task scheduled on one cpu, two other cpus getting one normal task each and the fourth cpu getting the remaining two normal tasks. but with current smpnice extra normal priority task keeps jumping from one cpu to another cpu having the normal priority task. This is because of the busiest_has_loaded_cpus, nr_loaded_cpus logic.. We are not including the cpu with high priority task in max_load calculations but including that in total and avg_load calcuations.. leading to max_load < avg_load and load balance between cpus running normal priority tasks(2 Vs 1) will always show imbalanace as one normal priority and the extra normal priority task will keep moving from one cpu to another cpu having normal priority task.. b) 4-way system with HT (8 logical processors). Package-P0 T0 has a highest priority task, T1 is idle. Package-P1 Both T0 and T1 have 1 normal priority task each.. P2 and P3 are idle. With this patch, one of the normal priority tasks on P1 will be moved to P2 or P3.. c) With the current weighted smp nice calculations, it doesn't always make sense to look at the highest weighted runqueue in the busy group.. Consider a load balance scenario on a DP with HT system, with Package-0 containing one high priority and one low priority, Package-1 containing one low priority(with other thread being idle).. Package-1 thinks that it need to take the low priority thread from Package-0. And find_busiest_queue() returns the cpu thread with highest priority task.. And ultimately(with help of active load balance) we move high priority task to Package-1. And same continues with Package-0 now, moving high priority task from package-1 to package-0.. Even without the presence of active load balance, load balance will fail to balance the above scenario.. Fix find_busiest_queue to use "imbalance" when it is lightly loaded. [kernel@kolivas.org: sched: store weighted load on up] [kernel@kolivas.org: sched: add discrete weighted cpu load function] [suresh.b.siddha@intel.com: sched: remove dead code] Signed-off-by: Peter Williams <pwil3058@bigpond.com.au> Cc: "Siddha, Suresh B" <suresh.b.siddha@intel.com> Cc: "Chen, Kenneth W" <kenneth.w.chen@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Con Kolivas <kernel@kolivas.org> Cc: John Hawkes <hawkes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 17:54:34 +08:00
extern unsigned long weighted_cpuload(const int cpu);
struct seq_file;
struct cfs_rq;
struct task_group;
#ifdef CONFIG_SCHED_DEBUG
extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
extern void proc_sched_set_task(struct task_struct *p);
extern void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
#else
static inline void
proc_sched_show_task(struct task_struct *p, struct seq_file *m)
{
}
static inline void proc_sched_set_task(struct task_struct *p)
{
}
static inline void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
}
#endif
/*
* Task state bitmask. NOTE! These bits are also
* encoded in fs/proc/array.c: get_task_state().
*
* We have two separate sets of flags: task->state
* is about runnability, while task->exit_state are
* about the task exiting. Confusing, but this way
* modifying one set can't modify the other one by
* mistake.
*/
#define TASK_RUNNING 0
#define TASK_INTERRUPTIBLE 1
#define TASK_UNINTERRUPTIBLE 2
#define __TASK_STOPPED 4
#define __TASK_TRACED 8
/* in tsk->exit_state */
#define EXIT_ZOMBIE 16
#define EXIT_DEAD 32
/* in tsk->state again */
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
/* Convenience macros for the sake of set_task_state */
#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
#define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED)
/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
/* get_task_state() */
#define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \
TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
__TASK_TRACED)
#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0)
#define task_is_stopped_or_traced(task) \
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
((task->state & TASK_UNINTERRUPTIBLE) != 0)
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value) \
set_mb((tsk)->state, (state_value))
/*
* set_current_state() includes a barrier so that the write of current->state
* is correctly serialised wrt the caller's subsequent test of whether to
* actually sleep:
*
* set_current_state(TASK_UNINTERRUPTIBLE);
* if (do_i_need_to_sleep())
* schedule();
*
* If the caller does not need such serialisation then use __set_current_state()
*/
#define __set_current_state(state_value) \
do { current->state = (state_value); } while (0)
#define set_current_state(state_value) \
set_mb(current->state, (state_value))
/* Task command name length */
#define TASK_COMM_LEN 16
#include <linux/spinlock.h>
/*
* This serializes "schedule()" and also protects
* the run-queue from deletions/modifications (but
* _adding_ to the beginning of the run-queue has
* a separate lock).
*/
extern rwlock_t tasklist_lock;
extern spinlock_t mmlist_lock;
struct task_struct;
extern void sched_init(void);
extern void sched_init_smp(void);
extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);
extern void init_idle_bootup_task(struct task_struct *idle);
extern cpumask_t nohz_cpu_mask;
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern int select_nohz_load_balancer(int cpu);
#else
static inline int select_nohz_load_balancer(int cpu)
{
return 0;
}
#endif
extern unsigned long rt_needs_cpu(int cpu);
/*
* Only dump TASK_* tasks. (0 for all tasks)
*/
extern void show_state_filter(unsigned long state_filter);
static inline void show_state(void)
{
show_state_filter(0);
}
extern void show_regs(struct pt_regs *);
/*
* TASK is a pointer to the task whose backtrace we want to see (or NULL for current
* task), SP is the stack pointer of the first frame that should be shown in the back
* trace (or NULL if the entire call-chain of the task should be shown).
*/
extern void show_stack(struct task_struct *task, unsigned long *sp);
void io_schedule(void);
long io_schedule_timeout(long timeout);
extern void cpu_init (void);
extern void trap_init(void);
extern void account_process_tick(struct task_struct *task, int user);
extern void update_process_times(int user);
extern void scheduler_tick(void);
extern void hrtick_resched(void);
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-26 04:08:02 +08:00
extern void sched_show_task(struct task_struct *p);
#ifdef CONFIG_DETECT_SOFTLOCKUP
extern void softlockup_tick(void);
extern void spawn_softlockup_task(void);
extern void touch_softlockup_watchdog(void);
extern void touch_all_softlockup_watchdogs(void);
extern unsigned long softlockup_thresh;
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-26 04:08:02 +08:00
extern unsigned long sysctl_hung_task_check_count;
extern unsigned long sysctl_hung_task_timeout_secs;
extern unsigned long sysctl_hung_task_warnings;
#else
static inline void softlockup_tick(void)
{
}
static inline void spawn_softlockup_task(void)
{
}
static inline void touch_softlockup_watchdog(void)
{
}
static inline void touch_all_softlockup_watchdogs(void)
{
}
#endif
/* Attach to any functions which should be ignored in wchan output. */
#define __sched __attribute__((__section__(".sched.text")))
/* Linker adds these: start and end of __sched functions */
extern char __sched_text_start[], __sched_text_end[];
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);
#define MAX_SCHEDULE_TIMEOUT LONG_MAX
extern signed long schedule_timeout(signed long timeout);
extern signed long schedule_timeout_interruptible(signed long timeout);
extern signed long schedule_timeout_killable(signed long timeout);
extern signed long schedule_timeout_uninterruptible(signed long timeout);
asmlinkage void schedule(void);
struct nsproxy;
struct user_namespace;
/* Maximum number of active map areas.. This is a random (large) number */
#define DEFAULT_MAX_MAP_COUNT 65536
extern int sysctl_max_map_count;
#include <linux/aio.h>
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
unsigned long, unsigned long);
extern unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
[PATCH] Avoiding mmap fragmentation Ingo recently introduced a great speedup for allocating new mmaps using the free_area_cache pointer which boosts the specweb SSL benchmark by 4-5% and causes huge performance increases in thread creation. The downside of this patch is that it does lead to fragmentation in the mmap-ed areas (visible via /proc/self/maps), such that some applications that work fine under 2.4 kernels quickly run out of memory on any 2.6 kernel. The problem is twofold: 1) the free_area_cache is used to continue a search for memory where the last search ended. Before the change new areas were always searched from the base address on. So now new small areas are cluttering holes of all sizes throughout the whole mmap-able region whereas before small holes tended to close holes near the base leaving holes far from the base large and available for larger requests. 2) the free_area_cache also is set to the location of the last munmap-ed area so in scenarios where we allocate e.g. five regions of 1K each, then free regions 4 2 3 in this order the next request for 1K will be placed in the position of the old region 3, whereas before we appended it to the still active region 1, placing it at the location of the old region 2. Before we had 1 free region of 2K, now we only get two free regions of 1K -> fragmentation. The patch addresses thes issues by introducing yet another cache descriptor cached_hole_size that contains the largest known hole size below the current free_area_cache. If a new request comes in the size is compared against the cached_hole_size and if the request can be filled with a hole below free_area_cache the search is started from the base instead. The results look promising: Whereas 2.6.12-rc4 fragments quickly and my (earlier posted) leakme.c test program terminates after 50000+ iterations with 96 distinct and fragmented maps in /proc/self/maps it performs nicely (as expected) with thread creation, Ingo's test_str02 with 20000 threads requires 0.7s system time. Taking out Ingo's patch (un-patch available per request) by basically deleting all mentions of free_area_cache from the kernel and starting the search for new memory always at the respective bases we observe: leakme terminates successfully with 11 distinctive hardly fragmented areas in /proc/self/maps but thread creating is gringdingly slow: 30+s(!) system time for Ingo's test_str02 with 20000 threads. Now - drumroll ;-) the appended patch works fine with leakme: it ends with only 7 distinct areas in /proc/self/maps and also thread creation seems sufficiently fast with 0.71s for 20000 threads. Signed-off-by: Wolfgang Wander <wwc@rentec.com> Credit-to: "Richard Purdie" <rpurdie@rpsys.net> Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> (partly) Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22 08:14:49 +08:00
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
/*
* The mm counters are not protected by its page_table_lock,
* so must be incremented atomically.
*/
#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
#else /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
/*
* The mm counters are protected by its page_table_lock,
* so can be incremented directly.
*/
#define set_mm_counter(mm, member, value) (mm)->_##member = (value)
#define get_mm_counter(mm, member) ((mm)->_##member)
#define add_mm_counter(mm, member, value) (mm)->_##member += (value)
#define inc_mm_counter(mm, member) (mm)->_##member++
#define dec_mm_counter(mm, member) (mm)->_##member--
#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
#define get_mm_rss(mm) \
(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
[PATCH] mm: update_hiwaters just in time update_mem_hiwater has attracted various criticisms, in particular from those concerned with mm scalability. Originally it was called whenever rss or total_vm got raised. Then many of those callsites were replaced by a timer tick call from account_system_time. Now Frank van Maarseveen reports that to be found inadequate. How about this? Works for Frank. Replace update_mem_hiwater, a poor combination of two unrelated ops, by macros update_hiwater_rss and update_hiwater_vm. Don't attempt to keep mm->hiwater_rss up to date at timer tick, nor every time we raise rss (usually by 1): those are hot paths. Do the opposite, update only when about to lower rss (usually by many), or just before final accounting in do_exit. Handle mm->hiwater_vm in the same way, though it's much less of an issue. Demand that whoever collects these hiwater statistics do the work of taking the maximum with rss or total_vm. And there has been no collector of these hiwater statistics in the tree. The new convention needs an example, so match Frank's usage by adding a VmPeak line above VmSize to /proc/<pid>/status, and also a VmHWM line above VmRSS (High-Water-Mark or High-Water-Memory). There was a particular anomaly during mremap move, that hiwater_vm might be captured too high. A fleeting such anomaly remains, but it's quickly corrected now, whereas before it would stick. What locking? None: if the app is racy then these statistics will be racy, it's not worth any overhead to make them exact. But whenever it suits, hiwater_vm is updated under exclusive mmap_sem, and hiwater_rss under page_table_lock (for now) or with preemption disabled (later on): without going to any trouble, minimize the time between reading current values and updating, to minimize those occasions when a racing thread bumps a count up and back down in between. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 09:16:18 +08:00
#define update_hiwater_rss(mm) do { \
unsigned long _rss = get_mm_rss(mm); \
if ((mm)->hiwater_rss < _rss) \
(mm)->hiwater_rss = _rss; \
} while (0)
#define update_hiwater_vm(mm) do { \
if ((mm)->hiwater_vm < (mm)->total_vm) \
(mm)->hiwater_vm = (mm)->total_vm; \
} while (0)
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
/* mm flags */
/* dumpable bits */
#define MMF_DUMPABLE 0 /* core dump is permitted */
#define MMF_DUMP_SECURELY 1 /* core file is readable only by root */
#define MMF_DUMPABLE_BITS 2
/* coredump filter bits */
#define MMF_DUMP_ANON_PRIVATE 2
#define MMF_DUMP_ANON_SHARED 3
#define MMF_DUMP_MAPPED_PRIVATE 4
#define MMF_DUMP_MAPPED_SHARED 5
#define MMF_DUMP_ELF_HEADERS 6
#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS
#define MMF_DUMP_FILTER_BITS 5
#define MMF_DUMP_FILTER_MASK \
(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED))
struct sighand_struct {
atomic_t count;
struct k_sigaction action[_NSIG];
spinlock_t siglock;
wait_queue_head_t signalfd_wqh;
};
struct pacct_struct {
int ac_flag;
long ac_exitcode;
unsigned long ac_mem;
cputime_t ac_utime, ac_stime;
unsigned long ac_minflt, ac_majflt;
};
/*
* NOTE! "signal_struct" does not have it's own
* locking, because a shared signal_struct always
* implies a shared sighand_struct, so locking
* sighand_struct is always a proper superset of
* the locking of signal_struct.
*/
struct signal_struct {
atomic_t count;
atomic_t live;
wait_queue_head_t wait_chldexit; /* for wait4() */
/* current thread group signal load-balancing target: */
struct task_struct *curr_target;
/* shared signal handling: */
struct sigpending shared_pending;
/* thread group exit support */
int group_exit_code;
/* overloaded:
* - notify group_exit_task when ->count is equal to notify_count
* - everyone except group_exit_task is stopped during signal delivery
* of fatal signals, group_exit_task processes the signal.
*/
struct task_struct *group_exit_task;
int notify_count;
/* thread group stop support, overloads group_exit_code too */
int group_stop_count;
unsigned int flags; /* see SIGNAL_* flags below */
/* POSIX.1b Interval Timers */
struct list_head posix_timers;
/* ITIMER_REAL timer for the process */
struct hrtimer real_timer;
struct pid *leader_pid;
ktime_t it_real_incr;
/* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */
cputime_t it_prof_expires, it_virt_expires;
cputime_t it_prof_incr, it_virt_incr;
/* job control IDs */
/*
* pgrp and session fields are deprecated.
* use the task_session_Xnr and task_pgrp_Xnr routines below
*/
union {
pid_t pgrp __deprecated;
pid_t __pgrp;
};
struct pid *tty_old_pgrp;
union {
pid_t session __deprecated;
pid_t __session;
};
/* boolean value for session group leader */
int leader;
struct tty_struct *tty; /* NULL if no tty */
/*
* Cumulative resource counters for dead threads in the group,
* and for reaped dead child processes forked by this group.
* Live threads maintain their own counters and add to these
* in __exit_signal, except for the group leader.
*/
cputime_t utime, stime, cutime, cstime;
cputime_t gtime;
cputime_t cgtime;
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
unsigned long inblock, oublock, cinblock, coublock;
/*
* Cumulative ns of scheduled CPU time for dead threads in the
* group, not including a zombie group leader. (This only differs
* from jiffies_to_ns(utime + stime) if sched_clock uses something
* other than jiffies.)
*/
unsigned long long sum_sched_runtime;
/*
* We don't bother to synchronize most readers of this at all,
* because there is no reader checking a limit that actually needs
* to get both rlim_cur and rlim_max atomically, and either one
* alone is a single word that can safely be read normally.
* getrlimit/setrlimit use task_lock(current->group_leader) to
* protect this instead of the siglock, because they really
* have no need to disable irqs.
*/
struct rlimit rlim[RLIM_NLIMITS];
struct list_head cpu_timers[3];
/* keep the process-shared keyrings here so that they do the right
* thing in threads created with CLONE_THREAD */
#ifdef CONFIG_KEYS
struct key *session_keyring; /* keyring inherited over fork */
struct key *process_keyring; /* keyring private to this process */
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
struct pacct_struct pacct; /* per-process accounting information */
#endif
#ifdef CONFIG_TASKSTATS
struct taskstats *stats;
#endif
Audit: add TTY input auditing Add TTY input auditing, used to audit system administrator's actions. This is required by various security standards such as DCID 6/3 and PCI to provide non-repudiation of administrator's actions and to allow a review of past actions if the administrator seems to overstep their duties or if the system becomes misconfigured for unknown reasons. These requirements do not make it necessary to audit TTY output as well. Compared to an user-space keylogger, this approach records TTY input using the audit subsystem, correlated with other audit events, and it is completely transparent to the user-space application (e.g. the console ioctls still work). TTY input auditing works on a higher level than auditing all system calls within the session, which would produce an overwhelming amount of mostly useless audit events. Add an "audit_tty" attribute, inherited across fork (). Data read from TTYs by process with the attribute is sent to the audit subsystem by the kernel. The audit netlink interface is extended to allow modifying the audit_tty attribute, and to allow sending explanatory audit events from user-space (for example, a shell might send an event containing the final command, after the interactive command-line editing and history expansion is performed, which might be difficult to decipher from the TTY input alone). Because the "audit_tty" attribute is inherited across fork (), it would be set e.g. for sshd restarted within an audited session. To prevent this, the audit_tty attribute is cleared when a process with no open TTY file descriptors (e.g. after daemon startup) opens a TTY. See https://www.redhat.com/archives/linux-audit/2007-June/msg00000.html for a more detailed rationale document for an older version of this patch. [akpm@linux-foundation.org: build fix] Signed-off-by: Miloslav Trmac <mitr@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Paul Fulghum <paulkf@microgate.com> Cc: Casey Schaufler <casey@schaufler-ca.com> Cc: Steve Grubb <sgrubb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16 14:40:56 +08:00
#ifdef CONFIG_AUDIT
unsigned audit_tty;
struct tty_audit_buf *tty_audit_buf;
#endif
};
/* Context switch must be unlocked if interrupts are to be enabled */
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
# define __ARCH_WANT_UNLOCKED_CTXSW
#endif
/*
* Bits in flags field of signal_struct.
*/
#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_DEQUEUED 0x00000002 /* stop signal dequeued */
#define SIGNAL_STOP_CONTINUED 0x00000004 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT 0x00000008 /* group exit in progress */
signals: re-assign CLD_CONTINUED notification from the sender to reciever Based on discussion with Jiri and Roland. In short: currently handle_stop_signal(SIGCONT, p) sends the notification to p->parent, with this patch p itself notifies its parent when it becomes running. handle_stop_signal(SIGCONT) has to drop ->siglock temporary in order to notify the parent with do_notify_parent_cldstop(). This leads to multiple problems: - as Jiri Kosina pointed out, the stopped task can resume without actually seeing SIGCONT which may have a handler. - we race with another sig_kernel_stop() signal which may come in that window. - we race with sig_fatal() signals which may set SIGNAL_GROUP_EXIT in that window. - we can't avoid taking tasklist_lock() while sending SIGCONT. With this patch handle_stop_signal() just sets the new SIGNAL_CLD_CONTINUED flag in p->signal->flags and returns. The notification is sent by the first task which returns from finish_stop() (there should be at least one) or any other signalled thread from get_signal_to_deliver(). This is a user-visible change. Say, currently kill(SIGCONT, stopped_child) can't return without seeing SIGCHLD, with this patch SIGCHLD can be delayed unpredictably. Another difference is that if the child is ptraced by another process, CLD_CONTINUED may be delivered to ->real_parent after ptrace_detach() while currently it always goes to the tracer which doesn't actually need this notification. Hopefully not a problem. The patch asks for the futher obvious cleanups, I'll send them separately. Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: Roland McGrath <roland@redhat.com> Cc: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-30 15:52:44 +08:00
/*
* Pending notifications to parent.
*/
#define SIGNAL_CLD_STOPPED 0x00000010
#define SIGNAL_CLD_CONTINUED 0x00000020
#define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
#define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */
/* If true, all threads except ->group_exit_task have pending SIGKILL */
static inline int signal_group_exit(const struct signal_struct *sig)
{
return (sig->flags & SIGNAL_GROUP_EXIT) ||
(sig->group_exit_task != NULL);
}
/*
* Some day this will be a full-fledged user tracking system..
*/
struct user_struct {
atomic_t __count; /* reference count */
atomic_t processes; /* How many processes does this user have? */
atomic_t files; /* How many open files does this user have? */
atomic_t sigpending; /* How many pending signals does this user have? */
#ifdef CONFIG_INOTIFY_USER
atomic_t inotify_watches; /* How many inotify watches does this user have? */
atomic_t inotify_devs; /* How many inotify devs does this user have opened? */
#endif
#ifdef CONFIG_POSIX_MQUEUE
/* protected by mq_lock */
unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
#endif
unsigned long locked_shm; /* How many pages of mlocked shm ? */
#ifdef CONFIG_KEYS
struct key *uid_keyring; /* UID specific keyring */
struct key *session_keyring; /* UID's default session keyring */
#endif
/* Hash table maintenance information */
struct hlist_node uidhash_node;
uid_t uid;
#ifdef CONFIG_USER_SCHED
struct task_group *tg;
#ifdef CONFIG_SYSFS
struct kobject kobj;
struct work_struct work;
#endif
#endif
};
extern int uids_sysfs_init(void);
extern struct user_struct *find_user(uid_t);
extern struct user_struct root_user;
#define INIT_USER (&root_user)
struct backing_dev_info;
struct reclaim_state;
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info {
/* cumulative counters */
unsigned long pcount; /* # of times run on this cpu */
unsigned long long cpu_time, /* time spent on the cpu */
run_delay; /* time spent waiting on a runqueue */
/* timestamps */
unsigned long long last_arrival,/* when we last ran on a cpu */
last_queued; /* when we were last queued to run */
#ifdef CONFIG_SCHEDSTATS
/* BKL stats */
unsigned int bkl_count;
#endif
};
#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
#ifdef CONFIG_SCHEDSTATS
extern const struct file_operations proc_schedstat_operations;
#endif /* CONFIG_SCHEDSTATS */
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
spinlock_t lock;
unsigned int flags; /* Private per-task flags */
/* For each stat XXX, add following, aligned appropriately
*
* struct timespec XXX_start, XXX_end;
* u64 XXX_delay;
* u32 XXX_count;
*
* Atomicity of updates to XXX_delay, XXX_count protected by
* single lock above (split into XXX_lock if contention is an issue).
*/
/*
* XXX_count is incremented on every XXX operation, the delay
* associated with the operation is added to XXX_delay.
* XXX_delay contains the accumulated delay time in nanoseconds.
*/
struct timespec blkio_start, blkio_end; /* Shared by blkio, swapin */
u64 blkio_delay; /* wait for sync block io completion */
u64 swapin_delay; /* wait for swapin block io completion */
u32 blkio_count; /* total count of the number of sync block */
/* io operations performed */
u32 swapin_count; /* total count of the number of swapin block */
/* io operations performed */
};
#endif /* CONFIG_TASK_DELAY_ACCT */
static inline int sched_info_on(void)
{
#ifdef CONFIG_SCHEDSTATS
return 1;
#elif defined(CONFIG_TASK_DELAY_ACCT)
extern int delayacct_on;
return delayacct_on;
#else
return 0;
#endif
}
enum cpu_idle_type {
CPU_IDLE,
CPU_NOT_IDLE,
CPU_NEWLY_IDLE,
CPU_MAX_IDLE_TYPES
};
/*
* sched-domains (multiprocessor balancing) declarations:
*/
/*
* Increase resolution of nice-level calculations:
*/
#define SCHED_LOAD_SHIFT 10
#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT)
#define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE
[PATCH] sched: implement smpnice Problem: The introduction of separate run queues per CPU has brought with it "nice" enforcement problems that are best described by a simple example. For the sake of argument suppose that on a single CPU machine with a nice==19 hard spinner and a nice==0 hard spinner running that the nice==0 task gets 95% of the CPU and the nice==19 task gets 5% of the CPU. Now suppose that there is a system with 2 CPUs and 2 nice==19 hard spinners and 2 nice==0 hard spinners running. The user of this system would be entitled to expect that the nice==0 tasks each get 95% of a CPU and the nice==19 tasks only get 5% each. However, whether this expectation is met is pretty much down to luck as there are four equally likely distributions of the tasks to the CPUs that the load balancing code will consider to be balanced with loads of 2.0 for each CPU. Two of these distributions involve one nice==0 and one nice==19 task per CPU and in these circumstances the users expectations will be met. The other two distributions both involve both nice==0 tasks being on one CPU and both nice==19 being on the other CPU and each task will get 50% of a CPU and the user's expectations will not be met. Solution: The solution to this problem that is implemented in the attached patch is to use weighted loads when determining if the system is balanced and, when an imbalance is detected, to move an amount of weighted load between run queues (as opposed to a number of tasks) to restore the balance. Once again, the easiest way to explain why both of these measures are necessary is to use a simple example. Suppose that (in a slight variation of the above example) that we have a two CPU system with 4 nice==0 and 4 nice=19 hard spinning tasks running and that the 4 nice==0 tasks are on one CPU and the 4 nice==19 tasks are on the other CPU. The weighted loads for the two CPUs would be 4.0 and 0.2 respectively and the load balancing code would move 2 tasks resulting in one CPU with a load of 2.0 and the other with load of 2.2. If this was considered to be a big enough imbalance to justify moving a task and that task was moved using the current move_tasks() then it would move the highest priority task that it found and this would result in one CPU with a load of 3.0 and the other with a load of 1.2 which would result in the movement of a task in the opposite direction and so on -- infinite loop. If, on the other hand, an amount of load to be moved is calculated from the imbalance (in this case 0.1) and move_tasks() skips tasks until it find ones whose contributions to the weighted load are less than this amount it would move two of the nice==19 tasks resulting in a system with 2 nice==0 and 2 nice=19 on each CPU with loads of 2.1 for each CPU. One of the advantages of this mechanism is that on a system where all tasks have nice==0 the load balancing calculations would be mathematically identical to the current load balancing code. Notes: struct task_struct: has a new field load_weight which (in a trade off of space for speed) stores the contribution that this task makes to a CPU's weighted load when it is runnable. struct runqueue: has a new field raw_weighted_load which is the sum of the load_weight values for the currently runnable tasks on this run queue. This field always needs to be updated when nr_running is updated so two new inline functions inc_nr_running() and dec_nr_running() have been created to make sure that this happens. This also offers a convenient way to optimize away this part of the smpnice mechanism when CONFIG_SMP is not defined. int try_to_wake_up(): in this function the value SCHED_LOAD_BALANCE is used to represent the load contribution of a single task in various calculations in the code that decides which CPU to put the waking task on. While this would be a valid on a system where the nice values for the runnable tasks were distributed evenly around zero it will lead to anomalous load balancing if the distribution is skewed in either direction. To overcome this problem SCHED_LOAD_SCALE has been replaced by the load_weight for the relevant task or by the average load_weight per task for the queue in question (as appropriate). int move_tasks(): The modifications to this function were complicated by the fact that active_load_balance() uses it to move exactly one task without checking whether an imbalance actually exists. This precluded the simple overloading of max_nr_move with max_load_move and necessitated the addition of the latter as an extra argument to the function. The internal implementation is then modified to move up to max_nr_move tasks and max_load_move of weighted load. This slightly complicates the code where move_tasks() is called and if ever active_load_balance() is changed to not use move_tasks() the implementation of move_tasks() should be simplified accordingly. struct sched_group *find_busiest_group(): Similar to try_to_wake_up(), there are places in this function where SCHED_LOAD_SCALE is used to represent the load contribution of a single task and the same issues are created. A similar solution is adopted except that it is now the average per task contribution to a group's load (as opposed to a run queue) that is required. As this value is not directly available from the group it is calculated on the fly as the queues in the groups are visited when determining the busiest group. A key change to this function is that it is no longer to scale down *imbalance on exit as move_tasks() uses the load in its scaled form. void set_user_nice(): has been modified to update the task's load_weight field when it's nice value and also to ensure that its run queue's raw_weighted_load field is updated if it was runnable. From: "Siddha, Suresh B" <suresh.b.siddha@intel.com> With smpnice, sched groups with highest priority tasks can mask the imbalance between the other sched groups with in the same domain. This patch fixes some of the listed down scenarios by not considering the sched groups which are lightly loaded. a) on a simple 4-way MP system, if we have one high priority and 4 normal priority tasks, with smpnice we would like to see the high priority task scheduled on one cpu, two other cpus getting one normal task each and the fourth cpu getting the remaining two normal tasks. but with current smpnice extra normal priority task keeps jumping from one cpu to another cpu having the normal priority task. This is because of the busiest_has_loaded_cpus, nr_loaded_cpus logic.. We are not including the cpu with high priority task in max_load calculations but including that in total and avg_load calcuations.. leading to max_load < avg_load and load balance between cpus running normal priority tasks(2 Vs 1) will always show imbalanace as one normal priority and the extra normal priority task will keep moving from one cpu to another cpu having normal priority task.. b) 4-way system with HT (8 logical processors). Package-P0 T0 has a highest priority task, T1 is idle. Package-P1 Both T0 and T1 have 1 normal priority task each.. P2 and P3 are idle. With this patch, one of the normal priority tasks on P1 will be moved to P2 or P3.. c) With the current weighted smp nice calculations, it doesn't always make sense to look at the highest weighted runqueue in the busy group.. Consider a load balance scenario on a DP with HT system, with Package-0 containing one high priority and one low priority, Package-1 containing one low priority(with other thread being idle).. Package-1 thinks that it need to take the low priority thread from Package-0. And find_busiest_queue() returns the cpu thread with highest priority task.. And ultimately(with help of active load balance) we move high priority task to Package-1. And same continues with Package-0 now, moving high priority task from package-1 to package-0.. Even without the presence of active load balance, load balance will fail to balance the above scenario.. Fix find_busiest_queue to use "imbalance" when it is lightly loaded. [kernel@kolivas.org: sched: store weighted load on up] [kernel@kolivas.org: sched: add discrete weighted cpu load function] [suresh.b.siddha@intel.com: sched: remove dead code] Signed-off-by: Peter Williams <pwil3058@bigpond.com.au> Cc: "Siddha, Suresh B" <suresh.b.siddha@intel.com> Cc: "Chen, Kenneth W" <kenneth.w.chen@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Con Kolivas <kernel@kolivas.org> Cc: John Hawkes <hawkes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 17:54:34 +08:00
#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 BALANCE_FOR_MC_POWER \
(sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0)
#define BALANCE_FOR_PKG_POWER \
((sched_mc_power_savings || sched_smt_power_savings) ? \
SD_POWERSAVINGS_BALANCE : 0)
#define test_sd_parent(sd, flag) ((sd->parent && \
(sd->parent->flags & flag)) ? 1 : 0)
struct sched_group {
struct sched_group *next; /* Must be a circular list */
cpumask_t cpumask;
/*
* CPU power of this group, SCHED_LOAD_SCALE being max power for a
* single CPU. This is read only (except for setup, hotplug CPU).
Speed up divides by cpu_power in scheduler I noticed expensive divides done in try_to_wakeup() and find_busiest_group() on a bi dual core Opteron machine (total of 4 cores), moderatly loaded (15.000 context switch per second) oprofile numbers : CPU: AMD64 processors, speed 2600.05 MHz (estimated) Counted CPU_CLK_UNHALTED events (Cycles outside of halt state) with a unit mask of 0x00 (No unit mask) count 50000 samples % symbol name ... 613914 1.0498 try_to_wake_up 834 0.0013 :ffffffff80227ae1: div %rcx 77513 0.1191 :ffffffff80227ae4: mov %rax,%r11 608893 1.0413 find_busiest_group 1841 0.0031 :ffffffff802260bf: div %rdi 140109 0.2394 :ffffffff802260c2: test %sil,%sil Some of these divides can use the reciprocal divides we introduced some time ago (currently used in slab AFAIK) We can assume a load will fit in a 32bits number, because with a SCHED_LOAD_SCALE=128 value, its still a theorical limit of 33554432 When/if we reach this limit one day, probably cpus will have a fast hardware divide and we can zap the reciprocal divide trick. Ingo suggested to rename cpu_power to __cpu_power to make clear it should not be modified without changing its reciprocal value too. I did not convert the divide in cpu_avg_load_per_task(), because tracking nr_running changes may be not worth it ? We could use a static table of 32 reciprocal values but it would add a conditional branch and table lookup. [akpm@linux-foundation.org: !SMP build fix] Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:32:57 +08:00
* Note : Never change cpu_power without recompute its reciprocal
*/
Speed up divides by cpu_power in scheduler I noticed expensive divides done in try_to_wakeup() and find_busiest_group() on a bi dual core Opteron machine (total of 4 cores), moderatly loaded (15.000 context switch per second) oprofile numbers : CPU: AMD64 processors, speed 2600.05 MHz (estimated) Counted CPU_CLK_UNHALTED events (Cycles outside of halt state) with a unit mask of 0x00 (No unit mask) count 50000 samples % symbol name ... 613914 1.0498 try_to_wake_up 834 0.0013 :ffffffff80227ae1: div %rcx 77513 0.1191 :ffffffff80227ae4: mov %rax,%r11 608893 1.0413 find_busiest_group 1841 0.0031 :ffffffff802260bf: div %rdi 140109 0.2394 :ffffffff802260c2: test %sil,%sil Some of these divides can use the reciprocal divides we introduced some time ago (currently used in slab AFAIK) We can assume a load will fit in a 32bits number, because with a SCHED_LOAD_SCALE=128 value, its still a theorical limit of 33554432 When/if we reach this limit one day, probably cpus will have a fast hardware divide and we can zap the reciprocal divide trick. Ingo suggested to rename cpu_power to __cpu_power to make clear it should not be modified without changing its reciprocal value too. I did not convert the divide in cpu_avg_load_per_task(), because tracking nr_running changes may be not worth it ? We could use a static table of 32 reciprocal values but it would add a conditional branch and table lookup. [akpm@linux-foundation.org: !SMP build fix] Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:32:57 +08:00
unsigned int __cpu_power;
/*
* reciprocal value of cpu_power to avoid expensive divides
* (see include/linux/reciprocal_div.h)
*/
u32 reciprocal_cpu_power;
};
enum sched_domain_level {
SD_LV_NONE = 0,
SD_LV_SIBLING,
SD_LV_MC,
SD_LV_CPU,
SD_LV_NODE,
SD_LV_ALLNODES,
SD_LV_MAX
};
struct sched_domain_attr {
int relax_domain_level;
};
#define SD_ATTR_INIT (struct sched_domain_attr) { \
.relax_domain_level = -1, \
}
struct sched_domain {
/* These fields must be setup */
struct sched_domain *parent; /* top domain must be null terminated */
struct sched_domain *child; /* bottom domain must be null terminated */
struct sched_group *groups; /* the balancing groups of the domain */
cpumask_t span; /* span of all CPUs in this domain */
int first_cpu; /* cache of the first cpu in this domain */
unsigned long min_interval; /* Minimum balance interval ms */
unsigned long max_interval; /* Maximum balance interval ms */
unsigned int busy_factor; /* less balancing by factor if busy */
unsigned int imbalance_pct; /* No balance until over watermark */
unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */
unsigned int busy_idx;
unsigned int idle_idx;
unsigned int newidle_idx;
unsigned int wake_idx;
unsigned int forkexec_idx;
int flags; /* See SD_* */
enum sched_domain_level level;
/* Runtime fields. */
unsigned long last_balance; /* init to jiffies. units in jiffies */
unsigned int balance_interval; /* initialise to 1. units in ms. */
unsigned int nr_balance_failed; /* initialise to 0 */
#ifdef CONFIG_SCHEDSTATS
/* load_balance() stats */
unsigned int lb_count[CPU_MAX_IDLE_TYPES];
unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
/* Active load balancing */
unsigned int alb_count;
unsigned int alb_failed;
unsigned int alb_pushed;
/* SD_BALANCE_EXEC stats */
unsigned int sbe_count;
unsigned int sbe_balanced;
unsigned int sbe_pushed;
/* SD_BALANCE_FORK stats */
unsigned int sbf_count;
unsigned int sbf_balanced;
unsigned int sbf_pushed;
/* try_to_wake_up() stats */
unsigned int ttwu_wake_remote;
unsigned int ttwu_move_affine;
unsigned int ttwu_move_balance;
#endif
};
extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
struct sched_domain_attr *dattr_new);
extern int arch_reinit_sched_domains(void);
cpuset sched_load_balance flag Add a new per-cpuset flag called 'sched_load_balance'. When enabled in a cpuset (the default value) it tells the kernel scheduler that the scheduler should provide the normal load balancing on the CPUs in that cpuset, sometimes moving tasks from one CPU to a second CPU if the second CPU is less loaded and if that task is allowed to run there. When disabled (write "0" to the file) then it tells the kernel scheduler that load balancing is not required for the CPUs in that cpuset. Now even if this flag is disabled for some cpuset, the kernel may still have to load balance some or all the CPUs in that cpuset, if some overlapping cpuset has its sched_load_balance flag enabled. If there are some CPUs that are not in any cpuset whose sched_load_balance flag is enabled, the kernel scheduler will not load balance tasks to those CPUs. Moreover the kernel will partition the 'sched domains' (non-overlapping sets of CPUs over which load balancing is attempted) into the finest granularity partition that it can find, while still keeping any two CPUs that are in the same shed_load_balance enabled cpuset in the same element of the partition. This serves two purposes: 1) It provides a mechanism for real time isolation of some CPUs, and 2) it can be used to improve performance on systems with many CPUs by supporting configurations in which load balancing is not done across all CPUs at once, but rather only done in several smaller disjoint sets of CPUs. This mechanism replaces the earlier overloading of the per-cpuset flag 'cpu_exclusive', which overloading was removed in an earlier patch: cpuset-remove-sched-domain-hooks-from-cpusets See further the Documentation and comments in the code itself. [akpm@linux-foundation.org: don't be weird] Signed-off-by: Paul Jackson <pj@sgi.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:40:20 +08:00
[PATCH] scheduler cache-hot-autodetect ) From: Ingo Molnar <mingo@elte.hu> This is the latest version of the scheduler cache-hot-auto-tune patch. The first problem was that detection time scaled with O(N^2), which is unacceptable on larger SMP and NUMA systems. To solve this: - I've added a 'domain distance' function, which is used to cache measurement results. Each distance is only measured once. This means that e.g. on NUMA distances of 0, 1 and 2 might be measured, on HT distances 0 and 1, and on SMP distance 0 is measured. The code walks the domain tree to determine the distance, so it automatically follows whatever hierarchy an architecture sets up. This cuts down on the boot time significantly and removes the O(N^2) limit. The only assumption is that migration costs can be expressed as a function of domain distance - this covers the overwhelming majority of existing systems, and is a good guess even for more assymetric systems. [ People hacking systems that have assymetries that break this assumption (e.g. different CPU speeds) should experiment a bit with the cpu_distance() function. Adding a ->migration_distance factor to the domain structure would be one possible solution - but lets first see the problem systems, if they exist at all. Lets not overdesign. ] Another problem was that only a single cache-size was used for measuring the cost of migration, and most architectures didnt set that variable up. Furthermore, a single cache-size does not fit NUMA hierarchies with L3 caches and does not fit HT setups, where different CPUs will often have different 'effective cache sizes'. To solve this problem: - Instead of relying on a single cache-size provided by the platform and sticking to it, the code now auto-detects the 'effective migration cost' between two measured CPUs, via iterating through a wide range of cachesizes. The code searches for the maximum migration cost, which occurs when the working set of the test-workload falls just below the 'effective cache size'. I.e. real-life optimized search is done for the maximum migration cost, between two real CPUs. This, amongst other things, has the positive effect hat if e.g. two CPUs share a L2/L3 cache, a different (and accurate) migration cost will be found than between two CPUs on the same system that dont share any caches. (The reliable measurement of migration costs is tricky - see the source for details.) Furthermore i've added various boot-time options to override/tune migration behavior. Firstly, there's a blanket override for autodetection: migration_cost=1000,2000,3000 will override the depth 0/1/2 values with 1msec/2msec/3msec values. Secondly, there's a global factor that can be used to increase (or decrease) the autodetected values: migration_factor=120 will increase the autodetected values by 20%. This option is useful to tune things in a workload-dependent way - e.g. if a workload is cache-insensitive then CPU utilization can be maximized by specifying migration_factor=0. I've tested the autodetection code quite extensively on x86, on 3 P3/Xeon/2MB, and the autodetected values look pretty good: Dual Celeron (128K L2 cache): --------------------- migration cost matrix (max_cache_size: 131072, cpu: 467 MHz): --------------------- [00] [01] [00]: - 1.7(1) [01]: 1.7(1) - --------------------- cacheflush times [2]: 0.0 (0) 1.7 (1784008) --------------------- Here the slow memory subsystem dominates system performance, and even though caches are small, the migration cost is 1.7 msecs. Dual HT P4 (512K L2 cache): --------------------- migration cost matrix (max_cache_size: 524288, cpu: 2379 MHz): --------------------- [00] [01] [02] [03] [00]: - 0.4(1) 0.0(0) 0.4(1) [01]: 0.4(1) - 0.4(1) 0.0(0) [02]: 0.0(0) 0.4(1) - 0.4(1) [03]: 0.4(1) 0.0(0) 0.4(1) - --------------------- cacheflush times [2]: 0.0 (33900) 0.4 (448514) --------------------- Here it can be seen that there is no migration cost between two HT siblings (CPU#0/2 and CPU#1/3 are separate physical CPUs). A fast memory system makes inter-physical-CPU migration pretty cheap: 0.4 msecs. 8-way P3/Xeon [2MB L2 cache]: --------------------- migration cost matrix (max_cache_size: 2097152, cpu: 700 MHz): --------------------- [00] [01] [02] [03] [04] [05] [06] [07] [00]: - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) [01]: 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) [02]: 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) [03]: 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) [04]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) [05]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) [06]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) [07]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - --------------------- cacheflush times [2]: 0.0 (0) 19.2 (19281756) --------------------- This one has huge caches and a relatively slow memory subsystem - so the migration cost is 19 msecs. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Cc: <wilder@us.ibm.com> Signed-off-by: John Hawkes <hawkes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-12 17:05:30 +08:00
#endif /* CONFIG_SMP */
/*
* A runqueue laden with a single nice 0 task scores a weighted_cpuload of
* SCHED_LOAD_SCALE. This function returns 1 if any cpu is laden with a
* task of nice 0 or enough lower priority tasks to bring up the
* weighted_cpuload
*/
static inline int above_background_load(void)
{
unsigned long cpu;
for_each_online_cpu(cpu) {
if (weighted_cpuload(cpu) >= SCHED_LOAD_SCALE)
return 1;
}
return 0;
}
struct io_context; /* See blkdev.h */
#define NGROUPS_SMALL 32
#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(gid_t)))
struct group_info {
int ngroups;
atomic_t usage;
gid_t small_block[NGROUPS_SMALL];
int nblocks;
gid_t *blocks[0];
};
/*
* get_group_info() must be called with the owning task locked (via task_lock())
* when task != current. The reason being that the vast majority of callers are
* looking at current->group_info, which can not be changed except by the
* current task. Changing current->group_info requires the task lock, too.
*/
#define get_group_info(group_info) do { \
atomic_inc(&(group_info)->usage); \
} while (0)
#define put_group_info(group_info) do { \
if (atomic_dec_and_test(&(group_info)->usage)) \
groups_free(group_info); \
} while (0)
[PATCH] Keys: Make request-key create an authorisation key The attached patch makes the following changes: (1) There's a new special key type called ".request_key_auth". This is an authorisation key for when one process requests a key and another process is started to construct it. This type of key cannot be created by the user; nor can it be requested by kernel services. Authorisation keys hold two references: (a) Each refers to a key being constructed. When the key being constructed is instantiated the authorisation key is revoked, rendering it of no further use. (b) The "authorising process". This is either: (i) the process that called request_key(), or: (ii) if the process that called request_key() itself had an authorisation key in its session keyring, then the authorising process referred to by that authorisation key will also be referred to by the new authorisation key. This means that the process that initiated a chain of key requests will authorise the lot of them, and will, by default, wind up with the keys obtained from them in its keyrings. (2) request_key() creates an authorisation key which is then passed to /sbin/request-key in as part of a new session keyring. (3) When request_key() is searching for a key to hand back to the caller, if it comes across an authorisation key in the session keyring of the calling process, it will also search the keyrings of the process specified therein and it will use the specified process's credentials (fsuid, fsgid, groups) to do that rather than the calling process's credentials. This allows a process started by /sbin/request-key to find keys belonging to the authorising process. (4) A key can be read, even if the process executing KEYCTL_READ doesn't have direct read or search permission if that key is contained within the keyrings of a process specified by an authorisation key found within the calling process's session keyring, and is searchable using the credentials of the authorising process. This allows a process started by /sbin/request-key to read keys belonging to the authorising process. (5) The magic KEY_SPEC_*_KEYRING key IDs when passed to KEYCTL_INSTANTIATE or KEYCTL_NEGATE will specify a keyring of the authorising process, rather than the process doing the instantiation. (6) One of the process keyrings can be nominated as the default to which request_key() should attach new keys if not otherwise specified. This is done with KEYCTL_SET_REQKEY_KEYRING and one of the KEY_REQKEY_DEFL_* constants. The current setting can also be read using this call. (7) request_key() is partially interruptible. If it is waiting for another process to finish constructing a key, it can be interrupted. This permits a request-key cycle to be broken without recourse to rebooting. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-Off-By: Benoit Boissinot <benoit.boissinot@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:56 +08:00
extern struct group_info *groups_alloc(int gidsetsize);
extern void groups_free(struct group_info *group_info);
extern int set_current_groups(struct group_info *group_info);
extern int groups_search(struct group_info *group_info, gid_t grp);
/* access the groups "array" with this macro */
#define GROUP_AT(gi, i) \
((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])
#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
extern void prefetch_stack(struct task_struct *t);
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif
struct audit_context; /* See audit.c */
struct mempolicy;
struct pipe_inode_info;
struct uts_namespace;
struct rq;
struct sched_domain;
struct sched_class {
const struct sched_class *next;
void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
void (*yield_task) (struct rq *rq);
int (*select_task_rq)(struct task_struct *p, int sync);
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);
struct task_struct * (*pick_next_task) (struct rq *rq);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
sched: simplify move_tasks() The move_tasks() function is currently multiplexed with two distinct capabilities: 1. attempt to move a specified amount of weighted load from one run queue to another; and 2. attempt to move a specified number of tasks from one run queue to another. The first of these capabilities is used in two places, load_balance() and load_balance_idle(), and in both of these cases the return value of move_tasks() is used purely to decide if tasks/load were moved and no notice of the actual number of tasks moved is taken. The second capability is used in exactly one place, active_load_balance(), to attempt to move exactly one task and, as before, the return value is only used as an indicator of success or failure. This multiplexing of sched_task() was introduced, by me, as part of the smpnice patches and was motivated by the fact that the alternative, one function to move specified load and one to move a single task, would have led to two functions of roughly the same complexity as the old move_tasks() (or the new balance_tasks()). However, the new modular design of the new CFS scheduler allows a simpler solution to be adopted and this patch addresses that solution by: 1. adding a new function, move_one_task(), to be used by active_load_balance(); and 2. making move_tasks() a single purpose function that tries to move a specified weighted load and returns 1 for success and 0 for failure. One of the consequences of these changes is that neither move_one_task() or the new move_tasks() care how many tasks sched_class.load_balance() moves and this enables its interface to be simplified by returning the amount of load moved as its result and removing the load_moved pointer from the argument list. This helps simplify the new move_tasks() and slightly reduces the amount of work done in each of sched_class.load_balance()'s implementations. Further simplification, e.g. changes to balance_tasks(), are possible but (slightly) complicated by the special needs of load_balance_fair() so I've left them to a later patch (if this one gets accepted). NB Since move_tasks() gets called with two run queue locks held even small reductions in overhead are worthwhile. [ mingo@elte.hu ] this change also reduces code size nicely: text data bss dec hex filename 39216 3618 24 42858 a76a sched.o.before 39173 3618 24 42815 a73f sched.o.after Signed-off-by: Peter Williams <pwil3058@bigpond.net.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-08-09 17:16:46 +08:00
unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
struct rq *busiest, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
sched: fix bug in balance_tasks() There are two problems with balance_tasks() and how it used: 1. The variables best_prio and best_prio_seen (inherited from the old move_tasks()) were only required to handle problems caused by the active/expired arrays, the order in which they were processed and the possibility that the task with the highest priority could be on either. These issues are no longer present and the extra overhead associated with their use is unnecessary (and possibly wrong). 2. In the absence of CONFIG_FAIR_GROUP_SCHED being set, the same this_best_prio variable needs to be used by all scheduling classes or there is a risk of moving too much load. E.g. if the highest priority task on this at the beginning is a fairly low priority task and the rt class migrates a task (during its turn) then that moved task becomes the new highest priority task on this_rq but when the sched_fair class initializes its copy of this_best_prio it will get the priority of the original highest priority task as, due to the run queue locks being held, the reschedule triggered by pull_task() will not have taken place. This could result in inappropriate overriding of skip_for_load and excessive load being moved. The attached patch addresses these problems by deleting all reference to best_prio and best_prio_seen and making this_best_prio a reference parameter to the various functions involved. load_balance_fair() has also been modified so that this_best_prio is only reset (in the loop) if CONFIG_FAIR_GROUP_SCHED is set. This should preserve the effect of helping spread groups' higher priority tasks around the available CPUs while improving system performance when CONFIG_FAIR_GROUP_SCHED isn't set. Signed-off-by: Peter Williams <pwil3058@bigpond.net.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-08-09 17:16:46 +08:00
int *all_pinned, int *this_best_prio);
int (*move_one_task) (struct rq *this_rq, int this_cpu,
struct rq *busiest, struct sched_domain *sd,
enum cpu_idle_type idle);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
void (*post_schedule) (struct rq *this_rq);
void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
#endif
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_new) (struct rq *rq, struct task_struct *p);
void (*set_cpus_allowed)(struct task_struct *p,
const cpumask_t *newmask);
void (*join_domain)(struct rq *rq);
void (*leave_domain)(struct rq *rq);
void (*switched_from) (struct rq *this_rq, struct task_struct *task,
int running);
void (*switched_to) (struct rq *this_rq, struct task_struct *task,
int running);
void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
int oldprio, int running);
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*moved_group) (struct task_struct *p);
#endif
};
struct load_weight {
unsigned long weight, inv_weight;
};
/*
* CFS stats for a schedulable entity (task, task-group etc)
*
* Current field usage histogram:
*
* 4 se->block_start
* 4 se->run_node
* 4 se->sleep_start
* 6 se->load.weight
*/
struct sched_entity {
struct load_weight load; /* for load-balancing */
struct rb_node run_node;
struct list_head group_node;
unsigned int on_rq;
u64 exec_start;
u64 sum_exec_runtime;
u64 vruntime;
sched: make the scheduler converge to the ideal latency de-HZ-ification of the granularity defaults unearthed a pre-existing property of CFS: while it correctly converges to the granularity goal, it does not prevent run-time fluctuations in the range of [-gran ... 0 ... +gran]. With the increase of the granularity due to the removal of HZ dependencies, this becomes visible in chew-max output (with 5 tasks running): out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40 out: 27 . 27. 32 | flu: 0 . 0 | ran: 17 . 13 | per: 44 . 40 out: 27 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 36 . 40 out: 29 . 27. 32 | flu: 2 . 0 | ran: 17 . 13 | per: 46 . 40 out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40 out: 29 . 27. 32 | flu: 0 . 0 | ran: 18 . 13 | per: 47 . 40 out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40 average slice is the ideal 13 msecs and the period is picture-perfect 40 msecs. But the 'ran' field fluctuates around 13.33 msecs and there's no mechanism in CFS to keep that from happening: it's a perfectly valid solution that CFS finds. to fix this we add a granularity/preemption rule that knows about the "target latency", which makes tasks that run longer than the ideal latency run a bit less. The simplest approach is to simply decrease the preemption granularity when a task overruns its ideal latency. For this we have to track how much the task executed since its last preemption. ( this adds a new field to task_struct, but we can eliminate that overhead in 2.6.24 by putting all the scheduler timestamps into an anonymous union. ) with this change in place, chew-max output is fluctuation-less all around: out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40 out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40 out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40 out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40 out: 28 . 27. 39 | flu: 0 . 1 | ran: 13 . 13 | per: 41 . 40 out: 28 . 27. 39 | flu: 0 . 1 | ran: 13 . 13 | per: 41 . 40 this patch has no impact on any fastpath or on any globally observable scheduling property. (unless you have sharp enough eyes to see millisecond-level ruckles in glxgears smoothness :-) Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Mike Galbraith <efault@gmx.de>
2007-08-28 18:53:24 +08:00
u64 prev_sum_exec_runtime;
u64 last_wakeup;
u64 avg_overlap;
#ifdef CONFIG_SCHEDSTATS
u64 wait_start;
u64 wait_max;
u64 wait_count;
u64 wait_sum;
u64 sleep_start;
u64 sleep_max;
s64 sum_sleep_runtime;
u64 block_start;
u64 block_max;
u64 exec_max;
u64 slice_max;
u64 nr_migrations;
u64 nr_migrations_cold;
u64 nr_failed_migrations_affine;
u64 nr_failed_migrations_running;
u64 nr_failed_migrations_hot;
u64 nr_forced_migrations;
u64 nr_forced2_migrations;
u64 nr_wakeups;
u64 nr_wakeups_sync;
u64 nr_wakeups_migrate;
u64 nr_wakeups_local;
u64 nr_wakeups_remote;
u64 nr_wakeups_affine;
u64 nr_wakeups_affine_attempts;
u64 nr_wakeups_passive;
u64 nr_wakeups_idle;
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
struct sched_entity *parent;
/* rq on which this entity is (to be) queued: */
struct cfs_rq *cfs_rq;
/* rq "owned" by this entity/group: */
struct cfs_rq *my_q;
#endif
};
struct sched_rt_entity {
struct list_head run_list;
unsigned int time_slice;
unsigned long timeout;
int nr_cpus_allowed;
struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
struct sched_rt_entity *parent;
/* rq on which this entity is (to be) queued: */
struct rt_rq *rt_rq;
/* rq "owned" by this entity/group: */
struct rt_rq *my_q;
#endif
};
struct task_struct {
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
rename thread_info to stack This finally renames the thread_info field in task structure to stack, so that the assumptions about this field are gone and archs have more freedom about placing the thread_info structure. Nonbroken archs which have a proper thread pointer can do the access to both current thread and task structure via a single pointer. It'll allow for a few more cleanups of the fork code, from which e.g. ia64 could benefit. Signed-off-by: Roman Zippel <zippel@linux-m68k.org> [akpm@linux-foundation.org: build fix] Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Haavard Skinnemoen <hskinnemoen@atmel.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Andi Kleen <ak@muc.de> Cc: Chris Zankel <chris@zankel.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:35:17 +08:00
void *stack;
atomic_t usage;
unsigned int flags; /* per process flags, defined below */
unsigned int ptrace;
int lock_depth; /* BKL lock depth */
[PATCH] sched: implement smpnice Problem: The introduction of separate run queues per CPU has brought with it "nice" enforcement problems that are best described by a simple example. For the sake of argument suppose that on a single CPU machine with a nice==19 hard spinner and a nice==0 hard spinner running that the nice==0 task gets 95% of the CPU and the nice==19 task gets 5% of the CPU. Now suppose that there is a system with 2 CPUs and 2 nice==19 hard spinners and 2 nice==0 hard spinners running. The user of this system would be entitled to expect that the nice==0 tasks each get 95% of a CPU and the nice==19 tasks only get 5% each. However, whether this expectation is met is pretty much down to luck as there are four equally likely distributions of the tasks to the CPUs that the load balancing code will consider to be balanced with loads of 2.0 for each CPU. Two of these distributions involve one nice==0 and one nice==19 task per CPU and in these circumstances the users expectations will be met. The other two distributions both involve both nice==0 tasks being on one CPU and both nice==19 being on the other CPU and each task will get 50% of a CPU and the user's expectations will not be met. Solution: The solution to this problem that is implemented in the attached patch is to use weighted loads when determining if the system is balanced and, when an imbalance is detected, to move an amount of weighted load between run queues (as opposed to a number of tasks) to restore the balance. Once again, the easiest way to explain why both of these measures are necessary is to use a simple example. Suppose that (in a slight variation of the above example) that we have a two CPU system with 4 nice==0 and 4 nice=19 hard spinning tasks running and that the 4 nice==0 tasks are on one CPU and the 4 nice==19 tasks are on the other CPU. The weighted loads for the two CPUs would be 4.0 and 0.2 respectively and the load balancing code would move 2 tasks resulting in one CPU with a load of 2.0 and the other with load of 2.2. If this was considered to be a big enough imbalance to justify moving a task and that task was moved using the current move_tasks() then it would move the highest priority task that it found and this would result in one CPU with a load of 3.0 and the other with a load of 1.2 which would result in the movement of a task in the opposite direction and so on -- infinite loop. If, on the other hand, an amount of load to be moved is calculated from the imbalance (in this case 0.1) and move_tasks() skips tasks until it find ones whose contributions to the weighted load are less than this amount it would move two of the nice==19 tasks resulting in a system with 2 nice==0 and 2 nice=19 on each CPU with loads of 2.1 for each CPU. One of the advantages of this mechanism is that on a system where all tasks have nice==0 the load balancing calculations would be mathematically identical to the current load balancing code. Notes: struct task_struct: has a new field load_weight which (in a trade off of space for speed) stores the contribution that this task makes to a CPU's weighted load when it is runnable. struct runqueue: has a new field raw_weighted_load which is the sum of the load_weight values for the currently runnable tasks on this run queue. This field always needs to be updated when nr_running is updated so two new inline functions inc_nr_running() and dec_nr_running() have been created to make sure that this happens. This also offers a convenient way to optimize away this part of the smpnice mechanism when CONFIG_SMP is not defined. int try_to_wake_up(): in this function the value SCHED_LOAD_BALANCE is used to represent the load contribution of a single task in various calculations in the code that decides which CPU to put the waking task on. While this would be a valid on a system where the nice values for the runnable tasks were distributed evenly around zero it will lead to anomalous load balancing if the distribution is skewed in either direction. To overcome this problem SCHED_LOAD_SCALE has been replaced by the load_weight for the relevant task or by the average load_weight per task for the queue in question (as appropriate). int move_tasks(): The modifications to this function were complicated by the fact that active_load_balance() uses it to move exactly one task without checking whether an imbalance actually exists. This precluded the simple overloading of max_nr_move with max_load_move and necessitated the addition of the latter as an extra argument to the function. The internal implementation is then modified to move up to max_nr_move tasks and max_load_move of weighted load. This slightly complicates the code where move_tasks() is called and if ever active_load_balance() is changed to not use move_tasks() the implementation of move_tasks() should be simplified accordingly. struct sched_group *find_busiest_group(): Similar to try_to_wake_up(), there are places in this function where SCHED_LOAD_SCALE is used to represent the load contribution of a single task and the same issues are created. A similar solution is adopted except that it is now the average per task contribution to a group's load (as opposed to a run queue) that is required. As this value is not directly available from the group it is calculated on the fly as the queues in the groups are visited when determining the busiest group. A key change to this function is that it is no longer to scale down *imbalance on exit as move_tasks() uses the load in its scaled form. void set_user_nice(): has been modified to update the task's load_weight field when it's nice value and also to ensure that its run queue's raw_weighted_load field is updated if it was runnable. From: "Siddha, Suresh B" <suresh.b.siddha@intel.com> With smpnice, sched groups with highest priority tasks can mask the imbalance between the other sched groups with in the same domain. This patch fixes some of the listed down scenarios by not considering the sched groups which are lightly loaded. a) on a simple 4-way MP system, if we have one high priority and 4 normal priority tasks, with smpnice we would like to see the high priority task scheduled on one cpu, two other cpus getting one normal task each and the fourth cpu getting the remaining two normal tasks. but with current smpnice extra normal priority task keeps jumping from one cpu to another cpu having the normal priority task. This is because of the busiest_has_loaded_cpus, nr_loaded_cpus logic.. We are not including the cpu with high priority task in max_load calculations but including that in total and avg_load calcuations.. leading to max_load < avg_load and load balance between cpus running normal priority tasks(2 Vs 1) will always show imbalanace as one normal priority and the extra normal priority task will keep moving from one cpu to another cpu having normal priority task.. b) 4-way system with HT (8 logical processors). Package-P0 T0 has a highest priority task, T1 is idle. Package-P1 Both T0 and T1 have 1 normal priority task each.. P2 and P3 are idle. With this patch, one of the normal priority tasks on P1 will be moved to P2 or P3.. c) With the current weighted smp nice calculations, it doesn't always make sense to look at the highest weighted runqueue in the busy group.. Consider a load balance scenario on a DP with HT system, with Package-0 containing one high priority and one low priority, Package-1 containing one low priority(with other thread being idle).. Package-1 thinks that it need to take the low priority thread from Package-0. And find_busiest_queue() returns the cpu thread with highest priority task.. And ultimately(with help of active load balance) we move high priority task to Package-1. And same continues with Package-0 now, moving high priority task from package-1 to package-0.. Even without the presence of active load balance, load balance will fail to balance the above scenario.. Fix find_busiest_queue to use "imbalance" when it is lightly loaded. [kernel@kolivas.org: sched: store weighted load on up] [kernel@kolivas.org: sched: add discrete weighted cpu load function] [suresh.b.siddha@intel.com: sched: remove dead code] Signed-off-by: Peter Williams <pwil3058@bigpond.com.au> Cc: "Siddha, Suresh B" <suresh.b.siddha@intel.com> Cc: "Chen, Kenneth W" <kenneth.w.chen@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Con Kolivas <kernel@kolivas.org> Cc: John Hawkes <hawkes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 17:54:34 +08:00
#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
int oncpu;
#endif
[PATCH] sched: implement smpnice Problem: The introduction of separate run queues per CPU has brought with it "nice" enforcement problems that are best described by a simple example. For the sake of argument suppose that on a single CPU machine with a nice==19 hard spinner and a nice==0 hard spinner running that the nice==0 task gets 95% of the CPU and the nice==19 task gets 5% of the CPU. Now suppose that there is a system with 2 CPUs and 2 nice==19 hard spinners and 2 nice==0 hard spinners running. The user of this system would be entitled to expect that the nice==0 tasks each get 95% of a CPU and the nice==19 tasks only get 5% each. However, whether this expectation is met is pretty much down to luck as there are four equally likely distributions of the tasks to the CPUs that the load balancing code will consider to be balanced with loads of 2.0 for each CPU. Two of these distributions involve one nice==0 and one nice==19 task per CPU and in these circumstances the users expectations will be met. The other two distributions both involve both nice==0 tasks being on one CPU and both nice==19 being on the other CPU and each task will get 50% of a CPU and the user's expectations will not be met. Solution: The solution to this problem that is implemented in the attached patch is to use weighted loads when determining if the system is balanced and, when an imbalance is detected, to move an amount of weighted load between run queues (as opposed to a number of tasks) to restore the balance. Once again, the easiest way to explain why both of these measures are necessary is to use a simple example. Suppose that (in a slight variation of the above example) that we have a two CPU system with 4 nice==0 and 4 nice=19 hard spinning tasks running and that the 4 nice==0 tasks are on one CPU and the 4 nice==19 tasks are on the other CPU. The weighted loads for the two CPUs would be 4.0 and 0.2 respectively and the load balancing code would move 2 tasks resulting in one CPU with a load of 2.0 and the other with load of 2.2. If this was considered to be a big enough imbalance to justify moving a task and that task was moved using the current move_tasks() then it would move the highest priority task that it found and this would result in one CPU with a load of 3.0 and the other with a load of 1.2 which would result in the movement of a task in the opposite direction and so on -- infinite loop. If, on the other hand, an amount of load to be moved is calculated from the imbalance (in this case 0.1) and move_tasks() skips tasks until it find ones whose contributions to the weighted load are less than this amount it would move two of the nice==19 tasks resulting in a system with 2 nice==0 and 2 nice=19 on each CPU with loads of 2.1 for each CPU. One of the advantages of this mechanism is that on a system where all tasks have nice==0 the load balancing calculations would be mathematically identical to the current load balancing code. Notes: struct task_struct: has a new field load_weight which (in a trade off of space for speed) stores the contribution that this task makes to a CPU's weighted load when it is runnable. struct runqueue: has a new field raw_weighted_load which is the sum of the load_weight values for the currently runnable tasks on this run queue. This field always needs to be updated when nr_running is updated so two new inline functions inc_nr_running() and dec_nr_running() have been created to make sure that this happens. This also offers a convenient way to optimize away this part of the smpnice mechanism when CONFIG_SMP is not defined. int try_to_wake_up(): in this function the value SCHED_LOAD_BALANCE is used to represent the load contribution of a single task in various calculations in the code that decides which CPU to put the waking task on. While this would be a valid on a system where the nice values for the runnable tasks were distributed evenly around zero it will lead to anomalous load balancing if the distribution is skewed in either direction. To overcome this problem SCHED_LOAD_SCALE has been replaced by the load_weight for the relevant task or by the average load_weight per task for the queue in question (as appropriate). int move_tasks(): The modifications to this function were complicated by the fact that active_load_balance() uses it to move exactly one task without checking whether an imbalance actually exists. This precluded the simple overloading of max_nr_move with max_load_move and necessitated the addition of the latter as an extra argument to the function. The internal implementation is then modified to move up to max_nr_move tasks and max_load_move of weighted load. This slightly complicates the code where move_tasks() is called and if ever active_load_balance() is changed to not use move_tasks() the implementation of move_tasks() should be simplified accordingly. struct sched_group *find_busiest_group(): Similar to try_to_wake_up(), there are places in this function where SCHED_LOAD_SCALE is used to represent the load contribution of a single task and the same issues are created. A similar solution is adopted except that it is now the average per task contribution to a group's load (as opposed to a run queue) that is required. As this value is not directly available from the group it is calculated on the fly as the queues in the groups are visited when determining the busiest group. A key change to this function is that it is no longer to scale down *imbalance on exit as move_tasks() uses the load in its scaled form. void set_user_nice(): has been modified to update the task's load_weight field when it's nice value and also to ensure that its run queue's raw_weighted_load field is updated if it was runnable. From: "Siddha, Suresh B" <suresh.b.siddha@intel.com> With smpnice, sched groups with highest priority tasks can mask the imbalance between the other sched groups with in the same domain. This patch fixes some of the listed down scenarios by not considering the sched groups which are lightly loaded. a) on a simple 4-way MP system, if we have one high priority and 4 normal priority tasks, with smpnice we would like to see the high priority task scheduled on one cpu, two other cpus getting one normal task each and the fourth cpu getting the remaining two normal tasks. but with current smpnice extra normal priority task keeps jumping from one cpu to another cpu having the normal priority task. This is because of the busiest_has_loaded_cpus, nr_loaded_cpus logic.. We are not including the cpu with high priority task in max_load calculations but including that in total and avg_load calcuations.. leading to max_load < avg_load and load balance between cpus running normal priority tasks(2 Vs 1) will always show imbalanace as one normal priority and the extra normal priority task will keep moving from one cpu to another cpu having normal priority task.. b) 4-way system with HT (8 logical processors). Package-P0 T0 has a highest priority task, T1 is idle. Package-P1 Both T0 and T1 have 1 normal priority task each.. P2 and P3 are idle. With this patch, one of the normal priority tasks on P1 will be moved to P2 or P3.. c) With the current weighted smp nice calculations, it doesn't always make sense to look at the highest weighted runqueue in the busy group.. Consider a load balance scenario on a DP with HT system, with Package-0 containing one high priority and one low priority, Package-1 containing one low priority(with other thread being idle).. Package-1 thinks that it need to take the low priority thread from Package-0. And find_busiest_queue() returns the cpu thread with highest priority task.. And ultimately(with help of active load balance) we move high priority task to Package-1. And same continues with Package-0 now, moving high priority task from package-1 to package-0.. Even without the presence of active load balance, load balance will fail to balance the above scenario.. Fix find_busiest_queue to use "imbalance" when it is lightly loaded. [kernel@kolivas.org: sched: store weighted load on up] [kernel@kolivas.org: sched: add discrete weighted cpu load function] [suresh.b.siddha@intel.com: sched: remove dead code] Signed-off-by: Peter Williams <pwil3058@bigpond.com.au> Cc: "Siddha, Suresh B" <suresh.b.siddha@intel.com> Cc: "Chen, Kenneth W" <kenneth.w.chen@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Con Kolivas <kernel@kolivas.org> Cc: John Hawkes <hawkes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 17:54:34 +08:00
#endif
int prio, static_prio, normal_prio;
const struct sched_class *sched_class;
struct sched_entity se;
struct sched_rt_entity rt;
#ifdef CONFIG_PREEMPT_NOTIFIERS
/* list of struct preempt_notifier: */
struct hlist_head preempt_notifiers;
#endif
/*
* fpu_counter contains the number of consecutive context switches
* that the FPU is used. If this is over a threshold, the lazy fpu
* saving becomes unlazy to save the trap. This is an unsigned char
* so that after 256 times the counter wraps and the behavior turns
* lazy again; this to deal with bursty apps that only use FPU for
* a short time
*/
unsigned char fpu_counter;
s8 oomkilladj; /* OOM kill score adjustment (bit shift). */
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif
unsigned int policy;
cpumask_t cpus_allowed;
#ifdef CONFIG_PREEMPT_RCU
int rcu_read_lock_nesting;
int rcu_flipctr_idx;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info sched_info;
#endif
struct list_head tasks;
/*
* ptrace_list/ptrace_children forms the list of my children
* that were stolen by a ptracer.
*/
struct list_head ptrace_children;
struct list_head ptrace_list;
struct mm_struct *mm, *active_mm;
/* task state */
struct linux_binfmt *binfmt;
int exit_state;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
/* ??? */
unsigned int personality;
unsigned did_exec: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,
* older sibling, respectively. (p->father can be replaced with
* p->parent->pid)
*/
struct task_struct *real_parent; /* real parent process (when being debugged) */
struct task_struct *parent; /* parent process */
/*
* children/sibling forms the list of my children plus the
* tasks I'm ptracing.
*/
struct list_head children; /* list of my children */
struct list_head sibling; /* linkage in my parent's children list */
struct task_struct *group_leader; /* threadgroup leader */
/* PID/PID hash table linkage. */
[PATCH] pidhash: Refactor the pid hash table Simplifies the code, reduces the need for 4 pid hash tables, and makes the code more capable. In the discussions I had with Oleg it was felt that to a large extent the cleanup itself justified the work. With struct pid being dynamically allocated meant we could create the hash table entry when the pid was allocated and free the hash table entry when the pid was freed. Instead of playing with the hash lists when ever a process would attach or detach to a process. For myself the fact that it gave what my previous task_ref patch gave for free with simpler code was a big win. The problem is that if you hold a reference to struct task_struct you lock in 10K of low memory. If you do that in a user controllable way like /proc does, with an unprivileged but hostile user space application with typical resource limits of 1000 fds and 100 processes I can trigger the OOM killer by consuming all of low memory with task structs, on a machine wight 1GB of low memory. If I instead hold a reference to struct pid which holds a pointer to my task_struct, I don't suffer from that problem because struct pid is 2 orders of magnitude smaller. In fact struct pid is small enough that most other kernel data structures dwarf it, so simply limiting the number of referring data structures is enough to prevent exhaustion of low memory. This splits the current struct pid into two structures, struct pid and struct pid_link, and reduces our number of hash tables from PIDTYPE_MAX to just one. struct pid_link is the per process linkage into the hash tables and lives in struct task_struct. struct pid is given an indepedent lifetime, and holds pointers to each of the pid types. The independent life of struct pid simplifies attach_pid, and detach_pid, because we are always manipulating the list of pids and not the hash table. In addition in giving struct pid an indpendent life it makes the concept much more powerful. Kernel data structures can now embed a struct pid * instead of a pid_t and not suffer from pid wrap around problems or from keeping unnecessarily large amounts of memory allocated. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-31 18:31:42 +08:00
struct pid_link pids[PIDTYPE_MAX];
struct list_head thread_group;
struct completion *vfork_done; /* for vfork() */
int __user *set_child_tid; /* CLONE_CHILD_SETTID */
int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
unsigned int rt_priority;
cputime_t utime, stime, utimescaled, stimescaled;
cputime_t gtime;
cputime_t prev_utime, prev_stime;
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time; /* monotonic time */
struct timespec real_start_time; /* boot based time */
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
unsigned long min_flt, maj_flt;
cputime_t it_prof_expires, it_virt_expires;
unsigned long long it_sched_expires;
struct list_head cpu_timers[3];
/* process credentials */
uid_t uid,euid,suid,fsuid;
gid_t gid,egid,sgid,fsgid;
struct group_info *group_info;
capabilities: introduce per-process capability bounding set The capability bounding set is a set beyond which capabilities cannot grow. Currently cap_bset is per-system. It can be manipulated through sysctl, but only init can add capabilities. Root can remove capabilities. By default it includes all caps except CAP_SETPCAP. This patch makes the bounding set per-process when file capabilities are enabled. It is inherited at fork from parent. Noone can add elements, CAP_SETPCAP is required to remove them. One example use of this is to start a safer container. For instance, until device namespaces or per-container device whitelists are introduced, it is best to take CAP_MKNOD away from a container. The bounding set will not affect pP and pE immediately. It will only affect pP' and pE' after subsequent exec()s. It also does not affect pI, and exec() does not constrain pI'. So to really start a shell with no way of regain CAP_MKNOD, you would do prctl(PR_CAPBSET_DROP, CAP_MKNOD); cap_t cap = cap_get_proc(); cap_value_t caparray[1]; caparray[0] = CAP_MKNOD; cap_set_flag(cap, CAP_INHERITABLE, 1, caparray, CAP_DROP); cap_set_proc(cap); cap_free(cap); The following test program will get and set the bounding set (but not pI). For instance ./bset get (lists capabilities in bset) ./bset drop cap_net_raw (starts shell with new bset) (use capset, setuid binary, or binary with file capabilities to try to increase caps) ************************************************************ cap_bound.c ************************************************************ #include <sys/prctl.h> #include <linux/capability.h> #include <sys/types.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #ifndef PR_CAPBSET_READ #define PR_CAPBSET_READ 23 #endif #ifndef PR_CAPBSET_DROP #define PR_CAPBSET_DROP 24 #endif int usage(char *me) { printf("Usage: %s get\n", me); printf(" %s drop <capability>\n", me); return 1; } #define numcaps 32 char *captable[numcaps] = { "cap_chown", "cap_dac_override", "cap_dac_read_search", "cap_fowner", "cap_fsetid", "cap_kill", "cap_setgid", "cap_setuid", "cap_setpcap", "cap_linux_immutable", "cap_net_bind_service", "cap_net_broadcast", "cap_net_admin", "cap_net_raw", "cap_ipc_lock", "cap_ipc_owner", "cap_sys_module", "cap_sys_rawio", "cap_sys_chroot", "cap_sys_ptrace", "cap_sys_pacct", "cap_sys_admin", "cap_sys_boot", "cap_sys_nice", "cap_sys_resource", "cap_sys_time", "cap_sys_tty_config", "cap_mknod", "cap_lease", "cap_audit_write", "cap_audit_control", "cap_setfcap" }; int getbcap(void) { int comma=0; unsigned long i; int ret; printf("i know of %d capabilities\n", numcaps); printf("capability bounding set:"); for (i=0; i<numcaps; i++) { ret = prctl(PR_CAPBSET_READ, i); if (ret < 0) perror("prctl"); else if (ret==1) printf("%s%s", (comma++) ? ", " : " ", captable[i]); } printf("\n"); return 0; } int capdrop(char *str) { unsigned long i; int found=0; for (i=0; i<numcaps; i++) { if (strcmp(captable[i], str) == 0) { found=1; break; } } if (!found) return 1; if (prctl(PR_CAPBSET_DROP, i)) { perror("prctl"); return 1; } return 0; } int main(int argc, char *argv[]) { if (argc<2) return usage(argv[0]); if (strcmp(argv[1], "get")==0) return getbcap(); if (strcmp(argv[1], "drop")!=0 || argc<3) return usage(argv[0]); if (capdrop(argv[2])) { printf("unknown capability\n"); return 1; } return execl("/bin/bash", "/bin/bash", NULL); } ************************************************************ [serue@us.ibm.com: fix typo] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andrew G. Morgan <morgan@kernel.org> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Casey Schaufler <casey@schaufler-ca.com>a Signed-off-by: "Serge E. Hallyn" <serue@us.ibm.com> Tested-by: Jiri Slaby <jirislaby@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:29:45 +08:00
kernel_cap_t cap_effective, cap_inheritable, cap_permitted, cap_bset;
capabilities: implement per-process securebits Filesystem capability support makes it possible to do away with (set)uid-0 based privilege and use capabilities instead. That is, with filesystem support for capabilities but without this present patch, it is (conceptually) possible to manage a system with capabilities alone and never need to obtain privilege via (set)uid-0. Of course, conceptually isn't quite the same as currently possible since few user applications, certainly not enough to run a viable system, are currently prepared to leverage capabilities to exercise privilege. Further, many applications exist that may never get upgraded in this way, and the kernel will continue to want to support their setuid-0 base privilege needs. Where pure-capability applications evolve and replace setuid-0 binaries, it is desirable that there be a mechanisms by which they can contain their privilege. In addition to leveraging the per-process bounding and inheritable sets, this should include suppressing the privilege of the uid-0 superuser from the process' tree of children. The feature added by this patch can be leveraged to suppress the privilege associated with (set)uid-0. This suppression requires CAP_SETPCAP to initiate, and only immediately affects the 'current' process (it is inherited through fork()/exec()). This reimplementation differs significantly from the historical support for securebits which was system-wide, unwieldy and which has ultimately withered to a dead relic in the source of the modern kernel. With this patch applied a process, that is capable(CAP_SETPCAP), can now drop all legacy privilege (through uid=0) for itself and all subsequently fork()'d/exec()'d children with: prctl(PR_SET_SECUREBITS, 0x2f); This patch represents a no-op unless CONFIG_SECURITY_FILE_CAPABILITIES is enabled at configure time. [akpm@linux-foundation.org: fix uninitialised var warning] [serue@us.ibm.com: capabilities: use cap_task_prctl when !CONFIG_SECURITY] Signed-off-by: Andrew G. Morgan <morgan@kernel.org> Acked-by: Serge Hallyn <serue@us.ibm.com> Reviewed-by: James Morris <jmorris@namei.org> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Paul Moore <paul.moore@hp.com> Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:13:40 +08:00
unsigned securebits;
struct user_struct *user;
#ifdef CONFIG_KEYS
[PATCH] keys: Permit running process to instantiate keys Make it possible for a running process (such as gssapid) to be able to instantiate a key, as was requested by Trond Myklebust for NFS4. The patch makes the following changes: (1) A new, optional key type method has been added. This permits a key type to intercept requests at the point /sbin/request-key is about to be spawned and do something else with them - passing them over the rpc_pipefs files or netlink sockets for instance. The uninstantiated key, the authorisation key and the intended operation name are passed to the method. (2) The callout_info is no longer passed as an argument to /sbin/request-key to prevent unauthorised viewing of this data using ps or by looking in /proc/pid/cmdline. This means that the old /sbin/request-key program will not work with the patched kernel as it will expect to see an extra argument that is no longer there. A revised keyutils package will be made available tomorrow. (3) The callout_info is now attached to the authorisation key. Reading this key will retrieve the information. (4) A new field has been added to the task_struct. This holds the authorisation key currently active for a thread. Searches now look here for the caller's set of keys rather than looking for an auth key in the lowest level of the session keyring. This permits a thread to be servicing multiple requests at once and to switch between them. Note that this is per-thread, not per-process, and so is usable in multithreaded programs. The setting of this field is inherited across fork and exec. (5) A new keyctl function (KEYCTL_ASSUME_AUTHORITY) has been added that permits a thread to assume the authority to deal with an uninstantiated key. Assumption is only permitted if the authorisation key associated with the uninstantiated key is somewhere in the thread's keyrings. This function can also clear the assumption. (6) A new magic key specifier has been added to refer to the currently assumed authorisation key (KEY_SPEC_REQKEY_AUTH_KEY). (7) Instantiation will only proceed if the appropriate authorisation key is assumed first. The assumed authorisation key is discarded if instantiation is successful. (8) key_validate() is moved from the file of request_key functions to the file of permissions functions. (9) The documentation is updated. From: <Valdis.Kletnieks@vt.edu> Build fix. Signed-off-by: David Howells <dhowells@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Alexander Zangerl <az@bond.edu.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:02:47 +08:00
struct key *request_key_auth; /* assumed request_key authority */
struct key *thread_keyring; /* keyring private to this thread */
[PATCH] Keys: Make request-key create an authorisation key The attached patch makes the following changes: (1) There's a new special key type called ".request_key_auth". This is an authorisation key for when one process requests a key and another process is started to construct it. This type of key cannot be created by the user; nor can it be requested by kernel services. Authorisation keys hold two references: (a) Each refers to a key being constructed. When the key being constructed is instantiated the authorisation key is revoked, rendering it of no further use. (b) The "authorising process". This is either: (i) the process that called request_key(), or: (ii) if the process that called request_key() itself had an authorisation key in its session keyring, then the authorising process referred to by that authorisation key will also be referred to by the new authorisation key. This means that the process that initiated a chain of key requests will authorise the lot of them, and will, by default, wind up with the keys obtained from them in its keyrings. (2) request_key() creates an authorisation key which is then passed to /sbin/request-key in as part of a new session keyring. (3) When request_key() is searching for a key to hand back to the caller, if it comes across an authorisation key in the session keyring of the calling process, it will also search the keyrings of the process specified therein and it will use the specified process's credentials (fsuid, fsgid, groups) to do that rather than the calling process's credentials. This allows a process started by /sbin/request-key to find keys belonging to the authorising process. (4) A key can be read, even if the process executing KEYCTL_READ doesn't have direct read or search permission if that key is contained within the keyrings of a process specified by an authorisation key found within the calling process's session keyring, and is searchable using the credentials of the authorising process. This allows a process started by /sbin/request-key to read keys belonging to the authorising process. (5) The magic KEY_SPEC_*_KEYRING key IDs when passed to KEYCTL_INSTANTIATE or KEYCTL_NEGATE will specify a keyring of the authorising process, rather than the process doing the instantiation. (6) One of the process keyrings can be nominated as the default to which request_key() should attach new keys if not otherwise specified. This is done with KEYCTL_SET_REQKEY_KEYRING and one of the KEY_REQKEY_DEFL_* constants. The current setting can also be read using this call. (7) request_key() is partially interruptible. If it is waiting for another process to finish constructing a key, it can be interrupted. This permits a request-key cycle to be broken without recourse to rebooting. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-Off-By: Benoit Boissinot <benoit.boissinot@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:00:56 +08:00
unsigned char jit_keyring; /* default keyring to attach requested keys to */
#endif
char comm[TASK_COMM_LEN]; /* executable name excluding path
- access with [gs]et_task_comm (which lock
it with task_lock())
- initialized normally by flush_old_exec */
/* file system info */
int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
struct sysv_sem sysvsem;
#endif
softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [<c04883a5>] schedule_timeout+0x6d/0x8b [<c04883d8>] schedule_timeout_uninterruptible+0x15/0x17 [<c0133a76>] msleep+0x10/0x16 [<c0138974>] sys_prctl+0x30/0x1e2 [<c0104c52>] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [<c0197d11>] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [<c01ca3d2>] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy <ego@in.ibm.com>: CPU hotplug fixes. ] [ Andrew Morton <akpm@linux-foundation.org>: build warning fix. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2008-01-26 04:08:02 +08:00
#ifdef CONFIG_DETECT_SOFTLOCKUP
/* hung task detection */
unsigned long last_switch_timestamp;
unsigned long last_switch_count;
#endif
/* CPU-specific state of this task */
struct thread_struct thread;
/* filesystem information */
struct fs_struct *fs;
/* open file information */
struct files_struct *files;
/* namespaces */
struct nsproxy *nsproxy;
/* signal handlers */
struct signal_struct *signal;
struct sighand_struct *sighand;
sigset_t blocked, real_blocked;
sigset_t saved_sigmask; /* To be restored with TIF_RESTORE_SIGMASK */
struct sigpending pending;
unsigned long sas_ss_sp;
size_t sas_ss_size;
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
#ifdef CONFIG_SECURITY
void *security;
#endif
struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
uid_t loginuid;
unsigned int sessionid;
#endif
seccomp_t seccomp;
/* Thread group tracking */
u32 parent_exec_id;
u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
spinlock_t alloc_lock;
/* Protection of the PI data structures: */
spinlock_t pi_lock;
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task */
struct plist_head pi_waiters;
/* Deadlock detection and priority inheritance handling */
struct rt_mutex_waiter *pi_blocked_on;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
/* mutex deadlock detection */
struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned int irq_events;
int hardirqs_enabled;
unsigned long hardirq_enable_ip;
unsigned int hardirq_enable_event;
unsigned long hardirq_disable_ip;
unsigned int hardirq_disable_event;
int softirqs_enabled;
unsigned long softirq_disable_ip;
unsigned int softirq_disable_event;
unsigned long softirq_enable_ip;
unsigned int softirq_enable_event;
int hardirq_context;
int softirq_context;
#endif
[PATCH] lockdep: core Do 'make oldconfig' and accept all the defaults for new config options - reboot into the kernel and if everything goes well it should boot up fine and you should have /proc/lockdep and /proc/lockdep_stats files. Typically if the lock validator finds some problem it will print out voluminous debug output that begins with "BUG: ..." and which syslog output can be used by kernel developers to figure out the precise locking scenario. What does the lock validator do? It "observes" and maps all locking rules as they occur dynamically (as triggered by the kernel's natural use of spinlocks, rwlocks, mutexes and rwsems). Whenever the lock validator subsystem detects a new locking scenario, it validates this new rule against the existing set of rules. If this new rule is consistent with the existing set of rules then the new rule is added transparently and the kernel continues as normal. If the new rule could create a deadlock scenario then this condition is printed out. When determining validity of locking, all possible "deadlock scenarios" are considered: assuming arbitrary number of CPUs, arbitrary irq context and task context constellations, running arbitrary combinations of all the existing locking scenarios. In a typical system this means millions of separate scenarios. This is why we call it a "locking correctness" validator - for all rules that are observed the lock validator proves it with mathematical certainty that a deadlock could not occur (assuming that the lock validator implementation itself is correct and its internal data structures are not corrupted by some other kernel subsystem). [see more details and conditionals of this statement in include/linux/lockdep.h and Documentation/lockdep-design.txt] Furthermore, this "all possible scenarios" property of the validator also enables the finding of complex, highly unlikely multi-CPU multi-context races via single single-context rules, increasing the likelyhood of finding bugs drastically. In practical terms: the lock validator already found a bug in the upstream kernel that could only occur on systems with 3 or more CPUs, and which needed 3 very unlikely code sequences to occur at once on the 3 CPUs. That bug was found and reported on a single-CPU system (!). So in essence a race will be found "piecemail-wise", triggering all the necessary components for the race, without having to reproduce the race scenario itself! In its short existence the lock validator found and reported many bugs before they actually caused a real deadlock. To further increase the efficiency of the validator, the mapping is not per "lock instance", but per "lock-class". For example, all struct inode objects in the kernel have inode->inotify_mutex. If there are 10,000 inodes cached, then there are 10,000 lock objects. But ->inotify_mutex is a single "lock type", and all locking activities that occur against ->inotify_mutex are "unified" into this single lock-class. The advantage of the lock-class approach is that all historical ->inotify_mutex uses are mapped into a single (and as narrow as possible) set of locking rules - regardless of how many different tasks or inode structures it took to build this set of rules. The set of rules persist during the lifetime of the kernel. To see the rough magnitude of checking that the lock validator does, here's a portion of /proc/lockdep_stats, fresh after bootup: lock-classes: 694 [max: 2048] direct dependencies: 1598 [max: 8192] indirect dependencies: 17896 all direct dependencies: 16206 dependency chains: 1910 [max: 8192] in-hardirq chains: 17 in-softirq chains: 105 in-process chains: 1065 stack-trace entries: 38761 [max: 131072] combined max dependencies: 2033928 hardirq-safe locks: 24 hardirq-unsafe locks: 176 softirq-safe locks: 53 softirq-unsafe locks: 137 irq-safe locks: 59 irq-unsafe locks: 176 The lock validator has observed 1598 actual single-thread locking patterns, and has validated all possible 2033928 distinct locking scenarios. More details about the design of the lock validator can be found in Documentation/lockdep-design.txt, which can also found at: http://redhat.com/~mingo/lockdep-patches/lockdep-design.txt [bunk@stusta.de: cleanups] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-03 15:24:50 +08:00
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
[PATCH] lockdep: core Do 'make oldconfig' and accept all the defaults for new config options - reboot into the kernel and if everything goes well it should boot up fine and you should have /proc/lockdep and /proc/lockdep_stats files. Typically if the lock validator finds some problem it will print out voluminous debug output that begins with "BUG: ..." and which syslog output can be used by kernel developers to figure out the precise locking scenario. What does the lock validator do? It "observes" and maps all locking rules as they occur dynamically (as triggered by the kernel's natural use of spinlocks, rwlocks, mutexes and rwsems). Whenever the lock validator subsystem detects a new locking scenario, it validates this new rule against the existing set of rules. If this new rule is consistent with the existing set of rules then the new rule is added transparently and the kernel continues as normal. If the new rule could create a deadlock scenario then this condition is printed out. When determining validity of locking, all possible "deadlock scenarios" are considered: assuming arbitrary number of CPUs, arbitrary irq context and task context constellations, running arbitrary combinations of all the existing locking scenarios. In a typical system this means millions of separate scenarios. This is why we call it a "locking correctness" validator - for all rules that are observed the lock validator proves it with mathematical certainty that a deadlock could not occur (assuming that the lock validator implementation itself is correct and its internal data structures are not corrupted by some other kernel subsystem). [see more details and conditionals of this statement in include/linux/lockdep.h and Documentation/lockdep-design.txt] Furthermore, this "all possible scenarios" property of the validator also enables the finding of complex, highly unlikely multi-CPU multi-context races via single single-context rules, increasing the likelyhood of finding bugs drastically. In practical terms: the lock validator already found a bug in the upstream kernel that could only occur on systems with 3 or more CPUs, and which needed 3 very unlikely code sequences to occur at once on the 3 CPUs. That bug was found and reported on a single-CPU system (!). So in essence a race will be found "piecemail-wise", triggering all the necessary components for the race, without having to reproduce the race scenario itself! In its short existence the lock validator found and reported many bugs before they actually caused a real deadlock. To further increase the efficiency of the validator, the mapping is not per "lock instance", but per "lock-class". For example, all struct inode objects in the kernel have inode->inotify_mutex. If there are 10,000 inodes cached, then there are 10,000 lock objects. But ->inotify_mutex is a single "lock type", and all locking activities that occur against ->inotify_mutex are "unified" into this single lock-class. The advantage of the lock-class approach is that all historical ->inotify_mutex uses are mapped into a single (and as narrow as possible) set of locking rules - regardless of how many different tasks or inode structures it took to build this set of rules. The set of rules persist during the lifetime of the kernel. To see the rough magnitude of checking that the lock validator does, here's a portion of /proc/lockdep_stats, fresh after bootup: lock-classes: 694 [max: 2048] direct dependencies: 1598 [max: 8192] indirect dependencies: 17896 all direct dependencies: 16206 dependency chains: 1910 [max: 8192] in-hardirq chains: 17 in-softirq chains: 105 in-process chains: 1065 stack-trace entries: 38761 [max: 131072] combined max dependencies: 2033928 hardirq-safe locks: 24 hardirq-unsafe locks: 176 softirq-safe locks: 53 softirq-unsafe locks: 137 irq-safe locks: 59 irq-unsafe locks: 176 The lock validator has observed 1598 actual single-thread locking patterns, and has validated all possible 2033928 distinct locking scenarios. More details about the design of the lock validator can be found in Documentation/lockdep-design.txt, which can also found at: http://redhat.com/~mingo/lockdep-patches/lockdep-design.txt [bunk@stusta.de: cleanups] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-03 15:24:50 +08:00
u64 curr_chain_key;
int lockdep_depth;
struct held_lock held_locks[MAX_LOCK_DEPTH];
unsigned int lockdep_recursion;
#endif
/* journalling filesystem info */
void *journal_info;
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 15:53:42 +08:00
/* stacked block device info */
struct bio *bio_list, **bio_tail;
/* VM state */
struct reclaim_state *reclaim_state;
struct backing_dev_info *backing_dev_info;
struct io_context *io_context;
unsigned long ptrace_message;
siginfo_t *last_siginfo; /* For ptrace use. */
#ifdef CONFIG_TASK_XACCT
/* i/o counters(bytes read/written, #syscalls */
u64 rchar, wchar, syscr, syscw;
#endif
[PATCH] io-accounting: core statistics The present per-task IO accounting isn't very useful. It simply counts the number of bytes passed into read() and write(). So if a process reads 1MB from an already-cached file, it is accused of having performed 1MB of I/O, which is wrong. (David Wright had some comments on the applicability of the present logical IO accounting: For billing purposes it is useless but for workload analysis it is very useful read_bytes/read_calls average read request size write_bytes/write_calls average write request size read_bytes/read_blocks ie logical/physical can indicate hit rate or thrashing write_bytes/write_blocks ie logical/physical guess since pdflush writes can be missed I often look for logical larger than physical to see filesystem cache problems. And the bytes/cpusec can help find applications that are dominating the cache and causing slow interactive response from page cache contention. I want to find the IO intensive applications and make sure they are doing efficient IO. Thus the acctcms(sysV) or csacms command would give the high IO commands). This patchset adds new accounting which tries to be more accurate. We account for three things: reads: attempt to count the number of bytes which this process really did cause to be fetched from the storage layer. Done at the submit_bio() level, so it is accurate for block-backed filesystems. I also attempt to wire up NFS and CIFS. writes: attempt to count the number of bytes which this process caused to be sent to the storage layer. This is done at page-dirtying time. The big inaccuracy here is truncate. If a process writes 1MB to a file and then deletes the file, it will in fact perform no writeout. But it will have been accounted as having caused 1MB of write. So... cancelled_writes: account the number of bytes which this process caused to not happen, by truncating pagecache. We _could_ just subtract this from the process's `write' accounting. But that means that some processes would be reported to have done negative amounts of write IO, which is silly. So we just report the raw number and punt this decision up to userspace. Now, we _could_ account for writes at the physical I/O level. But - This would require that we track memory-dirtying tasks at the per-page level (would require a new pointer in struct page). - It would mean that IO statistics for a process are usually only available long after that process has exitted. Which means that we probably cannot communicate this info via taskstats. This patch: Wire up the kernel-private data structures and the accessor functions to manipulate them. Cc: Jay Lan <jlan@sgi.com> Cc: Shailabh Nagar <nagar@watson.ibm.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Chris Sturtivant <csturtiv@sgi.com> Cc: Tony Ernst <tee@sgi.com> Cc: Guillaume Thouvenin <guillaume.thouvenin@bull.net> Cc: David Wright <daw@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 18:19:19 +08:00
struct task_io_accounting ioac;
#if defined(CONFIG_TASK_XACCT)
u64 acct_rss_mem1; /* accumulated rss usage */
u64 acct_vm_mem1; /* accumulated virtual memory usage */
cputime_t acct_stimexpd;/* stime since last update */
#endif
#ifdef CONFIG_NUMA
struct mempolicy *mempolicy;
short il_next;
#endif
#ifdef CONFIG_CPUSETS
nodemask_t mems_allowed;
int cpuset_mems_generation;
[PATCH] cpuset memory spread basic implementation This patch provides the implementation and cpuset interface for an alternative memory allocation policy that can be applied to certain kinds of memory allocations, such as the page cache (file system buffers) and some slab caches (such as inode caches). The policy is called "memory spreading." If enabled, it spreads out these kinds of memory allocations over all the nodes allowed to a task, instead of preferring to place them on the node where the task is executing. All other kinds of allocations, including anonymous pages for a tasks stack and data regions, are not affected by this policy choice, and continue to be allocated preferring the node local to execution, as modified by the NUMA mempolicy. There are two boolean flag files per cpuset that control where the kernel allocates pages for the file system buffers and related in kernel data structures. They are called 'memory_spread_page' and 'memory_spread_slab'. If the per-cpuset boolean flag file 'memory_spread_page' is set, then the kernel will spread the file system buffers (page cache) evenly over all the nodes that the faulting task is allowed to use, instead of preferring to put those pages on the node where the task is running. If the per-cpuset boolean flag file 'memory_spread_slab' is set, then the kernel will spread some file system related slab caches, such as for inodes and dentries evenly over all the nodes that the faulting task is allowed to use, instead of preferring to put those pages on the node where the task is running. The implementation is simple. Setting the cpuset flags 'memory_spread_page' or 'memory_spread_cache' turns on the per-process flags PF_SPREAD_PAGE or PF_SPREAD_SLAB, respectively, for each task that is in the cpuset or subsequently joins that cpuset. In subsequent patches, the page allocation calls for the affected page cache and slab caches are modified to perform an inline check for these flags, and if set, a call to a new routine cpuset_mem_spread_node() returns the node to prefer for the allocation. The cpuset_mem_spread_node() routine is also simple. It uses the value of a per-task rotor cpuset_mem_spread_rotor to select the next node in the current tasks mems_allowed to prefer for the allocation. This policy can provide substantial improvements for jobs that need to place thread local data on the corresponding node, but that need to access large file system data sets that need to be spread across the several nodes in the jobs cpuset in order to fit. Without this patch, especially for jobs that might have one thread reading in the data set, the memory allocation across the nodes in the jobs cpuset can become very uneven. A couple of Copyright year ranges are updated as well. And a couple of email addresses that can be found in the MAINTAINERS file are removed. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:16:03 +08:00
int cpuset_mem_spread_rotor;
#endif
Task Control Groups: basic task cgroup framework Generic Process Control Groups -------------------------- There have recently been various proposals floating around for resource management/accounting and other task grouping subsystems in the kernel, including ResGroups, User BeanCounters, NSProxy cgroups, and others. These all need the basic abstraction of being able to group together multiple processes in an aggregate, in order to track/limit the resources permitted to those processes, or control other behaviour of the processes, and all implement this grouping in different ways. This patchset provides a framework for tracking and grouping processes into arbitrary "cgroups" and assigning arbitrary state to those groupings, in order to control the behaviour of the cgroup as an aggregate. The intention is that the various resource management and virtualization/cgroup efforts can also become task cgroup clients, with the result that: - the userspace APIs are (somewhat) normalised - it's easier to test e.g. the ResGroups CPU controller in conjunction with the BeanCounters memory controller, or use either of them as the resource-control portion of a virtual server system. - the additional kernel footprint of any of the competing resource management systems is substantially reduced, since it doesn't need to provide process grouping/containment, hence improving their chances of getting into the kernel This patch: Add the main task cgroups framework - the cgroup filesystem, and the basic structures for tracking membership and associating subsystem state objects to tasks. Signed-off-by: Paul Menage <menage@google.com> Cc: Serge E. Hallyn <serue@us.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Jackson <pj@sgi.com> Cc: Kirill Korotaev <dev@openvz.org> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:30 +08:00
#ifdef CONFIG_CGROUPS
Task Control Groups: shared cgroup subsystem group arrays Replace the struct css_set embedded in task_struct with a pointer; all tasks that have the same set of memberships across all hierarchies will share a css_set object, and will be linked via their css_sets field to the "tasks" list_head in the css_set. Assuming that many tasks share the same cgroup assignments, this reduces overall space usage and keeps the size of the task_struct down (three pointers added to task_struct compared to a non-cgroups kernel, no matter how many subsystems are registered). [akpm@linux-foundation.org: fix a printk] [akpm@linux-foundation.org: build fix] Signed-off-by: Paul Menage <menage@google.com> Cc: Serge E. Hallyn <serue@us.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Jackson <pj@sgi.com> Cc: Kirill Korotaev <dev@openvz.org> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Serge E. Hallyn <serue@us.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Jackson <pj@sgi.com> Cc: Kirill Korotaev <dev@openvz.org> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:36 +08:00
/* Control Group info protected by css_set_lock */
struct css_set *cgroups;
/* cg_list protected by css_set_lock and tsk->alloc_lock */
struct list_head cg_list;
Task Control Groups: basic task cgroup framework Generic Process Control Groups -------------------------- There have recently been various proposals floating around for resource management/accounting and other task grouping subsystems in the kernel, including ResGroups, User BeanCounters, NSProxy cgroups, and others. These all need the basic abstraction of being able to group together multiple processes in an aggregate, in order to track/limit the resources permitted to those processes, or control other behaviour of the processes, and all implement this grouping in different ways. This patchset provides a framework for tracking and grouping processes into arbitrary "cgroups" and assigning arbitrary state to those groupings, in order to control the behaviour of the cgroup as an aggregate. The intention is that the various resource management and virtualization/cgroup efforts can also become task cgroup clients, with the result that: - the userspace APIs are (somewhat) normalised - it's easier to test e.g. the ResGroups CPU controller in conjunction with the BeanCounters memory controller, or use either of them as the resource-control portion of a virtual server system. - the additional kernel footprint of any of the competing resource management systems is substantially reduced, since it doesn't need to provide process grouping/containment, hence improving their chances of getting into the kernel This patch: Add the main task cgroups framework - the cgroup filesystem, and the basic structures for tracking membership and associating subsystem state objects to tasks. Signed-off-by: Paul Menage <menage@google.com> Cc: Serge E. Hallyn <serue@us.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Jackson <pj@sgi.com> Cc: Kirill Korotaev <dev@openvz.org> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:30 +08:00
#endif
#ifdef CONFIG_FUTEX
struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
struct compat_robust_list_head __user *compat_robust_list;
#endif
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
#endif
atomic_t fs_excl; /* holding fs exclusive resources */
struct rcu_head rcu;
/*
* cache last used pipe for splice
*/
struct pipe_inode_info *splice_pipe;
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
#endif
struct prop_local_single dirties;
#ifdef CONFIG_LATENCYTOP
int latency_record_count;
struct latency_record latency_record[LT_SAVECOUNT];
#endif
};
/*
* Priority of a process goes from 0..MAX_PRIO-1, valid RT
* priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
* tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
* values are inverted: lower p->prio value means higher priority.
*
* The MAX_USER_RT_PRIO value allows the actual maximum
* RT priority to be separate from the value exported to
* user-space. This allows kernel threads to set their
* priority to a value higher than any user task. Note:
* MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
*/
#define MAX_USER_RT_PRIO 100
#define MAX_RT_PRIO MAX_USER_RT_PRIO
#define MAX_PRIO (MAX_RT_PRIO + 40)
#define DEFAULT_PRIO (MAX_RT_PRIO + 20)
static inline int rt_prio(int prio)
{
if (unlikely(prio < MAX_RT_PRIO))
return 1;
return 0;
}
static inline int rt_task(struct task_struct *p)
{
return rt_prio(p->prio);
}
static inline void set_task_session(struct task_struct *tsk, pid_t session)
{
tsk->signal->__session = session;
}
static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp)
{
tsk->signal->__pgrp = pgrp;
}
static inline struct pid *task_pid(struct task_struct *task)
[PATCH] pid: implement access helpers for a tacks various process groups In the last round of cleaning up the pid hash table a more general struct pid was introduced, that can be referenced counted. With the more general struct pid most if not all places where we store a pid_t we can now store a struct pid * and remove the need for a hash table lookup, and avoid any possible problems with pid roll over. Looking forward to the pid namespaces struct pid * gives us an absolute form a pid so we can compare and use them without caring which pid namespace we are in. This patchset introduces the infrastructure needed to use struct pid instead of pid_t, and then it goes on to convert two different kernel users that currently store a pid_t value. There are a lot more places to go but this is enough to get the basic idea. Before we can merge a pid namespace patch all of the kernel pid_t users need to be examined. Those that deal with user space processes need to be converted to using a struct pid *. Those that deal with kernel processes need to converted to using the kthread api. A rare few that only use their current processes pid values get to be left alone. This patch: task_session returns the struct pid of a tasks session. task_pgrp returns the struct pid of a tasks process group. task_tgid returns the struct pid of a tasks thread group. task_pid returns the struct pid of a tasks process id. These can be used to avoid unnecessary hash table lookups, and to implement safe pid comparisions in the face of a pid namespace. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:17:09 +08:00
{
return task->pids[PIDTYPE_PID].pid;
}
static inline struct pid *task_tgid(struct task_struct *task)
[PATCH] pid: implement access helpers for a tacks various process groups In the last round of cleaning up the pid hash table a more general struct pid was introduced, that can be referenced counted. With the more general struct pid most if not all places where we store a pid_t we can now store a struct pid * and remove the need for a hash table lookup, and avoid any possible problems with pid roll over. Looking forward to the pid namespaces struct pid * gives us an absolute form a pid so we can compare and use them without caring which pid namespace we are in. This patchset introduces the infrastructure needed to use struct pid instead of pid_t, and then it goes on to convert two different kernel users that currently store a pid_t value. There are a lot more places to go but this is enough to get the basic idea. Before we can merge a pid namespace patch all of the kernel pid_t users need to be examined. Those that deal with user space processes need to be converted to using a struct pid *. Those that deal with kernel processes need to converted to using the kthread api. A rare few that only use their current processes pid values get to be left alone. This patch: task_session returns the struct pid of a tasks session. task_pgrp returns the struct pid of a tasks process group. task_tgid returns the struct pid of a tasks thread group. task_pid returns the struct pid of a tasks process id. These can be used to avoid unnecessary hash table lookups, and to implement safe pid comparisions in the face of a pid namespace. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:17:09 +08:00
{
return task->group_leader->pids[PIDTYPE_PID].pid;
}
static inline struct pid *task_pgrp(struct task_struct *task)
[PATCH] pid: implement access helpers for a tacks various process groups In the last round of cleaning up the pid hash table a more general struct pid was introduced, that can be referenced counted. With the more general struct pid most if not all places where we store a pid_t we can now store a struct pid * and remove the need for a hash table lookup, and avoid any possible problems with pid roll over. Looking forward to the pid namespaces struct pid * gives us an absolute form a pid so we can compare and use them without caring which pid namespace we are in. This patchset introduces the infrastructure needed to use struct pid instead of pid_t, and then it goes on to convert two different kernel users that currently store a pid_t value. There are a lot more places to go but this is enough to get the basic idea. Before we can merge a pid namespace patch all of the kernel pid_t users need to be examined. Those that deal with user space processes need to be converted to using a struct pid *. Those that deal with kernel processes need to converted to using the kthread api. A rare few that only use their current processes pid values get to be left alone. This patch: task_session returns the struct pid of a tasks session. task_pgrp returns the struct pid of a tasks process group. task_tgid returns the struct pid of a tasks thread group. task_pid returns the struct pid of a tasks process id. These can be used to avoid unnecessary hash table lookups, and to implement safe pid comparisions in the face of a pid namespace. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:17:09 +08:00
{
return task->group_leader->pids[PIDTYPE_PGID].pid;
}
static inline struct pid *task_session(struct task_struct *task)
[PATCH] pid: implement access helpers for a tacks various process groups In the last round of cleaning up the pid hash table a more general struct pid was introduced, that can be referenced counted. With the more general struct pid most if not all places where we store a pid_t we can now store a struct pid * and remove the need for a hash table lookup, and avoid any possible problems with pid roll over. Looking forward to the pid namespaces struct pid * gives us an absolute form a pid so we can compare and use them without caring which pid namespace we are in. This patchset introduces the infrastructure needed to use struct pid instead of pid_t, and then it goes on to convert two different kernel users that currently store a pid_t value. There are a lot more places to go but this is enough to get the basic idea. Before we can merge a pid namespace patch all of the kernel pid_t users need to be examined. Those that deal with user space processes need to be converted to using a struct pid *. Those that deal with kernel processes need to converted to using the kthread api. A rare few that only use their current processes pid values get to be left alone. This patch: task_session returns the struct pid of a tasks session. task_pgrp returns the struct pid of a tasks process group. task_tgid returns the struct pid of a tasks thread group. task_pid returns the struct pid of a tasks process id. These can be used to avoid unnecessary hash table lookups, and to implement safe pid comparisions in the face of a pid namespace. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:17:09 +08:00
{
return task->group_leader->pids[PIDTYPE_SID].pid;
}
struct pid_namespace;
/*
* the helpers to get the task's different pids as they are seen
* from various namespaces
*
* task_xid_nr() : global id, i.e. the id seen from the init namespace;
* task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of
* current.
* task_xid_nr_ns() : id seen from the ns specified;
*
* set_task_vxid() : assigns a virtual id to a task;
*
* see also pid_nr() etc in include/linux/pid.h
*/
static inline pid_t task_pid_nr(struct task_struct *tsk)
{
return tsk->pid;
}
pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
return pid_vnr(task_pid(tsk));
}
static inline pid_t task_tgid_nr(struct task_struct *tsk)
{
return tsk->tgid;
}
pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
static inline pid_t task_tgid_vnr(struct task_struct *tsk)
{
return pid_vnr(task_tgid(tsk));
}
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
return tsk->signal->__pgrp;
}
pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
return pid_vnr(task_pgrp(tsk));
}
static inline pid_t task_session_nr(struct task_struct *tsk)
{
return tsk->signal->__session;
}
pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
static inline pid_t task_session_vnr(struct task_struct *tsk)
{
return pid_vnr(task_session(tsk));
}
/**
* pid_alive - check that a task structure is not stale
* @p: Task structure to be checked.
*
* Test if a process is not yet dead (at most zombie state)
* If pid_alive fails, then pointers within the task structure
* can be stale and must not be dereferenced.
*/
static inline int pid_alive(struct task_struct *p)
{
[PATCH] pidhash: Refactor the pid hash table Simplifies the code, reduces the need for 4 pid hash tables, and makes the code more capable. In the discussions I had with Oleg it was felt that to a large extent the cleanup itself justified the work. With struct pid being dynamically allocated meant we could create the hash table entry when the pid was allocated and free the hash table entry when the pid was freed. Instead of playing with the hash lists when ever a process would attach or detach to a process. For myself the fact that it gave what my previous task_ref patch gave for free with simpler code was a big win. The problem is that if you hold a reference to struct task_struct you lock in 10K of low memory. If you do that in a user controllable way like /proc does, with an unprivileged but hostile user space application with typical resource limits of 1000 fds and 100 processes I can trigger the OOM killer by consuming all of low memory with task structs, on a machine wight 1GB of low memory. If I instead hold a reference to struct pid which holds a pointer to my task_struct, I don't suffer from that problem because struct pid is 2 orders of magnitude smaller. In fact struct pid is small enough that most other kernel data structures dwarf it, so simply limiting the number of referring data structures is enough to prevent exhaustion of low memory. This splits the current struct pid into two structures, struct pid and struct pid_link, and reduces our number of hash tables from PIDTYPE_MAX to just one. struct pid_link is the per process linkage into the hash tables and lives in struct task_struct. struct pid is given an indepedent lifetime, and holds pointers to each of the pid types. The independent life of struct pid simplifies attach_pid, and detach_pid, because we are always manipulating the list of pids and not the hash table. In addition in giving struct pid an indpendent life it makes the concept much more powerful. Kernel data structures can now embed a struct pid * instead of a pid_t and not suffer from pid wrap around problems or from keeping unnecessarily large amounts of memory allocated. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-31 18:31:42 +08:00
return p->pids[PIDTYPE_PID].pid != NULL;
}
/**
pid namespaces: define is_global_init() and is_container_init() is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:52 +08:00
* is_global_init - check if a task structure is init
* @tsk: Task structure to be checked.
*
* Check if a task structure is the first user space task the kernel created.
pid namespaces: define is_global_init() and is_container_init() is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:52 +08:00
*/
static inline int is_global_init(struct task_struct *tsk)
{
return tsk->pid == 1;
}
pid namespaces: define is_global_init() and is_container_init() is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:52 +08:00
/*
* is_container_init:
* check whether in the task is init in its own pid namespace.
*/
extern int is_container_init(struct task_struct *tsk);
extern struct pid *cad_pid;
extern void free_task(struct task_struct *tsk);
#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
extern void __put_task_struct(struct task_struct *t);
static inline void put_task_struct(struct task_struct *t)
{
if (atomic_dec_and_test(&t->usage))
[PATCH] task: RCU protect task->usage A big problem with rcu protected data structures that are also reference counted is that you must jump through several hoops to increase the reference count. I think someone finally implemented atomic_inc_not_zero(&count) to automate the common case. Unfortunately this means you must special case the rcu access case. When data structures are only visible via rcu in a manner that is not determined by the reference count on the object (i.e. tasks are visible until their zombies are reaped) there is a much simpler technique we can employ. Simply delaying the decrement of the reference count until the rcu interval is over. What that means is that the proc code that looks up a task and later wants to sleep can now do: rcu_read_lock(); task = find_task_by_pid(some_pid); if (task) { get_task_struct(task); } rcu_read_unlock(); The effect on the rest of the kernel is that put_task_struct becomes cheaper and immediate, and in the case where the task has been reaped it frees the task immediate instead of unnecessarily waiting an until the rcu interval is over. Cleanup of task_struct does not happen when its reference count drops to zero, instead cleanup happens when release_task is called. Tasks can only be looked up via rcu before release_task is called. All rcu protected members of task_struct are freed by release_task. Therefore we can move call_rcu from put_task_struct into release_task. And we can modify release_task to not immediately release the reference count but instead have it call put_task_struct from the function it gives to call_rcu. The end result: - get_task_struct is safe in an rcu context where we have just looked up the task. - put_task_struct() simplifies into its old pre rcu self. This reorganization also makes put_task_struct uncallable from modules as it is not exported but it does not appear to be called from any modules so this should not be an issue, and is trivially fixed. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-31 18:31:37 +08:00
__put_task_struct(t);
}
/*
* Per process flags
*/
#define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */
/* Not implemented yet, only for 486*/
#define PF_STARTING 0x00000002 /* being created */
#define PF_EXITING 0x00000004 /* getting shut down */
pi-futex: fix exit races and locking problems 1. New entries can be added to tsk->pi_state_list after task completed exit_pi_state_list(). The result is memory leakage and deadlocks. 2. handle_mm_fault() is called under spinlock. The result is obvious. 3. results in self-inflicted deadlock inside glibc. Sometimes futex_lock_pi returns -ESRCH, when it is not expected and glibc enters to for(;;) sleep() to simulate deadlock. This problem is quite obvious and I think the patch is right. Though it looks like each "if" in futex_lock_pi() got some stupid special case "else if". :-) 4. sometimes futex_lock_pi() returns -EDEADLK, when nobody has the lock. The reason is also obvious (see comment in the patch), but correct fix is far beyond my comprehension. I guess someone already saw this, the chunk: if (rt_mutex_trylock(&q.pi_state->pi_mutex)) ret = 0; is obviously from the same opera. But it does not work, because the rtmutex is really taken at this point: wake_futex_pi() of previous owner reassigned it to us. My fix works. But it looks very stupid. I would think about removal of shift of ownership in wake_futex_pi() and making all the work in context of process taking lock. From: Thomas Gleixner <tglx@linutronix.de> Fix 1) Avoid the tasklist lock variant of the exit race fix by adding an additional state transition to the exit code. This fixes also the issue, when a task with recursive segfaults is not able to release the futexes. Fix 2) Cleanup the lookup_pi_state() failure path and solve the -ESRCH problem finally. Fix 3) Solve the fixup_pi_state_owner() problem which needs to do the fixup in the lock protected section by using the in_atomic userspace access functions. This removes also the ugly lock drop / unqueue inside of fixup_pi_state() Fix 4) Fix a stale lock in the error path of futex_wake_pi() Added some error checks for verification. The -EDEADLK problem is solved by the rtmutex fixups. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Ulrich Drepper <drepper@redhat.com> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-06-09 04:47:00 +08:00
#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */
#define PF_VCPU 0x00000010 /* I'm a virtual CPU */
#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */
#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */
#define PF_DUMPCORE 0x00000200 /* dumped core */
#define PF_SIGNALED 0x00000400 /* killed by a signal */
#define PF_MEMALLOC 0x00000800 /* Allocating memory */
#define PF_FLUSHER 0x00001000 /* responsible for disk writeback */
#define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */
#define PF_NOFREEZE 0x00008000 /* this thread should not be frozen */
#define PF_FROZEN 0x00010000 /* frozen for system suspend */
#define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */
#define PF_KSWAPD 0x00040000 /* I am kswapd */
#define PF_SWAPOFF 0x00080000 /* I am in swapoff */
#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */
#define PF_BORROWED_MM 0x00200000 /* I am a kthread doing use_mm */
#define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
#define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */
#define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */
#define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezeable */
/*
* Only the _current_ task can read/write to tsk->flags, but other
* tasks can access tsk->flags in readonly mode for example
* with tsk_used_math (like during threaded core dumping).
* There is however an exception to this rule during ptrace
* or during fork: the ptracer task is allowed to write to the
* child->flags of its traced child (same goes for fork, the parent
* can write to the child->flags), because we're guaranteed the
* child is not running and in turn not changing child->flags
* at the same time the parent does it.
*/
#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0)
#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0)
#define clear_used_math() clear_stopped_child_used_math(current)
#define set_used_math() set_stopped_child_used_math(current)
#define conditional_stopped_child_used_math(condition, child) \
do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)
#define conditional_used_math(condition) \
conditional_stopped_child_used_math(condition, current)
#define copy_to_stopped_child_used_math(child) \
do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)
/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)
#ifdef CONFIG_SMP
extern int set_cpus_allowed_ptr(struct task_struct *p,
const cpumask_t *new_mask);
#else
static inline int set_cpus_allowed_ptr(struct task_struct *p,
const cpumask_t *new_mask)
{
if (!cpu_isset(0, *new_mask))
return -EINVAL;
return 0;
}
#endif
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
return set_cpus_allowed_ptr(p, &new_mask);
}
extern unsigned long long sched_clock(void);
/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
* clock constructed from sched_clock():
*/
extern unsigned long long cpu_clock(int cpu);
extern unsigned long long
task_sched_runtime(struct task_struct *task);
/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
extern void sched_exec(void);
#else
#define sched_exec() {}
#endif
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#ifdef CONFIG_HOTPLUG_CPU
extern void idle_task_exit(void);
#else
static inline void idle_task_exit(void) {}
#endif
extern void sched_idle_next(void);
#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
extern void wake_up_idle_cpu(int cpu);
#else
static inline void wake_up_idle_cpu(int cpu) { }
#endif
#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_latency;
extern unsigned int sysctl_sched_min_granularity;
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_child_runs_first;
extern unsigned int sysctl_sched_features;
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;
int sched_nr_latency_handler(struct ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length,
loff_t *ppos);
#endif
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
int sched_rt_handler(struct ctl_table *table, int write,
struct file *filp, void __user *buffer, size_t *lenp,
loff_t *ppos);
extern unsigned int sysctl_sched_compat_yield;
#ifdef CONFIG_RT_MUTEXES
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
extern void rt_mutex_adjust_pi(struct task_struct *p);
#else
static inline int rt_mutex_getprio(struct task_struct *p)
{
return p->normal_prio;
}
# define rt_mutex_adjust_pi(p) do { } while (0)
#endif
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
extern int task_nice(const struct task_struct *p);
extern int can_nice(const struct task_struct *p, const int nice);
extern int task_curr(const struct task_struct *p);
extern int idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
extern struct task_struct *idle_task(int cpu);
extern struct task_struct *curr_task(int cpu);
extern void set_curr_task(int cpu, struct task_struct *p);
void yield(void);
/*
* The default (Linux) execution domain.
*/
extern struct exec_domain default_exec_domain;
union thread_union {
struct thread_info thread_info;
unsigned long stack[THREAD_SIZE/sizeof(long)];
};
#ifndef __HAVE_ARCH_KSTACK_END
static inline int kstack_end(void *addr)
{
/* Reliable end of stack detection:
* Some APM bios versions misalign the stack
*/
return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
}
#endif
extern union thread_union init_thread_union;
extern struct task_struct init_task;
extern struct mm_struct init_mm;
extern struct pid_namespace init_pid_ns;
/*
* find a task by one of its numerical ids
*
* find_task_by_pid_type_ns():
* it is the most generic call - it finds a task by all id,
* type and namespace specified
* find_task_by_pid_ns():
* finds a task by its pid in the specified namespace
* find_task_by_vpid():
* finds a task by its virtual pid
* find_task_by_pid():
* finds a task by its global pid
*
* see also find_pid() etc in include/linux/pid.h
*/
extern struct task_struct *find_task_by_pid_type_ns(int type, int pid,
struct pid_namespace *ns);
extern struct task_struct *find_task_by_pid(pid_t nr);
extern struct task_struct *find_task_by_vpid(pid_t nr);
extern struct task_struct *find_task_by_pid_ns(pid_t nr,
struct pid_namespace *ns);
extern void __set_special_pids(struct pid *pid);
/* per-UID process charging. */
extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
static inline struct user_struct *get_uid(struct user_struct *u)
{
atomic_inc(&u->__count);
return u;
}
extern void free_uid(struct user_struct *);
extern void switch_uid(struct user_struct *);
extern void release_uids(struct user_namespace *ns);
#include <asm/current.h>
[PATCH] simplify update_times (avoid jiffies/jiffies_64 aliasing problem) Pass ticks to do_timer() and update_times(), and adjust x86_64 and s390 timer interrupt handler with this change. Currently update_times() calculates ticks by "jiffies - wall_jiffies", but callers of do_timer() should know how many ticks to update. Passing ticks get rid of this redundant calculation. Also there are another redundancy pointed out by Martin Schwidefsky. This cleanup make a barrier added by 5aee405c662ca644980c184774277fc6d0769a84 needless. So this patch removes it. As a bonus, this cleanup make wall_jiffies can be removed easily, since now wall_jiffies is always synced with jiffies. (This patch does not really remove wall_jiffies. It would be another cleanup patch) Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: john stultz <johnstul@us.ibm.com> Cc: Andi Kleen <ak@muc.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Acked-by: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Acked-by: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Hirokazu Takata <takata.hirokazu@renesas.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 17:00:32 +08:00
extern void do_timer(unsigned long ticks);
extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
extern void wake_up_new_task(struct task_struct *tsk,
unsigned long clone_flags);
#ifdef CONFIG_SMP
extern void kick_process(struct task_struct *tsk);
#else
static inline void kick_process(struct task_struct *tsk) { }
#endif
extern void sched_fork(struct task_struct *p, int clone_flags);
extern void sched_dead(struct task_struct *p);
extern int in_group_p(gid_t);
extern int in_egroup_p(gid_t);
extern void proc_caches_init(void);
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);
static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&tsk->sighand->siglock, flags);
ret = dequeue_signal(tsk, mask, info);
spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
return ret;
}
extern void block_all_signals(int (*notifier)(void *priv), void *priv,
sigset_t *mask);
extern void unblock_all_signals(void);
extern void release_task(struct task_struct * p);
extern int send_sig_info(int, struct siginfo *, struct task_struct *);
extern int force_sigsegv(int, struct task_struct *);
extern int force_sig_info(int, struct siginfo *, struct task_struct *);
extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32);
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
extern int kill_proc_info(int, struct siginfo *, pid_t);
extern void do_notify_parent(struct task_struct *, int);
extern void force_sig(int, struct task_struct *);
extern void force_sig_specific(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
extern void zap_other_threads(struct task_struct *p);
extern int kill_proc(pid_t, int, int);
extern struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group);
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);
static inline int kill_cad_pid(int sig, int priv)
{
return kill_pid(cad_pid, sig, priv);
}
/* These can be the second arg to send_sig_info/send_group_sig_info. */
#define SEND_SIG_NOINFO ((struct siginfo *) 0)
#define SEND_SIG_PRIV ((struct siginfo *) 1)
#define SEND_SIG_FORCED ((struct siginfo *) 2)
static inline int is_si_special(const struct siginfo *info)
{
return info <= SEND_SIG_FORCED;
}
/* True if we are on the alternate signal stack. */
static inline int on_sig_stack(unsigned long sp)
{
return (sp - current->sas_ss_sp < current->sas_ss_size);
}
static inline int sas_ss_flags(unsigned long sp)
{
return (current->sas_ss_size == 0 ? SS_DISABLE
: on_sig_stack(sp) ? SS_ONSTACK : 0);
}
/*
* Routines for handling mm_structs
*/
extern struct mm_struct * mm_alloc(void);
/* mmdrop drops the mm and the page tables */
extern void __mmdrop(struct mm_struct *);
static inline void mmdrop(struct mm_struct * mm)
{
if (unlikely(atomic_dec_and_test(&mm->mm_count)))
__mmdrop(mm);
}
/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);
/* Allocate a new mm structure and copy contents from tsk->mm */
extern struct mm_struct *dup_mm(struct task_struct *tsk);
extern int copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
extern void flush_thread(void);
extern void exit_thread(void);
extern void exit_files(struct task_struct *);
extern void __cleanup_signal(struct signal_struct *);
extern void __cleanup_sighand(struct sighand_struct *);
extern void exit_itimers(struct signal_struct *);
extern NORET_TYPE void do_group_exit(int);
extern void daemonize(const char *, ...);
extern int allow_signal(int);
extern int disallow_signal(int);
extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *);
extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
struct task_struct *fork_idle(int);
extern void set_task_comm(struct task_struct *tsk, char *from);
extern char *get_task_comm(char *to, struct task_struct *tsk);
#ifdef CONFIG_SMP
extern void wait_task_inactive(struct task_struct * p);
#else
#define wait_task_inactive(p) do { } while (0)
#endif
#define remove_parent(p) list_del_init(&(p)->sibling)
#define add_parent(p) list_add_tail(&(p)->sibling,&(p)->parent->children)
#define next_task(p) list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
/*
* Careful: do_each_thread/while_each_thread is a double loop so
* 'break' will not work as expected - use goto instead.
*/
#define do_each_thread(g, t) \
for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
#define while_each_thread(g, t) \
while ((t = next_thread(t)) != g)
[PATCH] de_thread: Don't confuse users do_each_thread. Oleg Nesterov spotted two interesting bugs with the current de_thread code. The simplest is a long standing double decrement of __get_cpu_var(process_counts) in __unhash_process. Caused by two processes exiting when only one was created. The other is that since we no longer detach from the thread_group list it is possible for do_each_thread when run under the tasklist_lock to see the same task_struct twice. Once on the task list as a thread_group_leader, and once on the thread list of another thread. The double appearance in do_each_thread can cause a double increment of mm_core_waiters in zap_threads resulting in problems later on in coredump_wait. To remedy those two problems this patch takes the simple approach of changing the old thread group leader into a child thread. The only routine in release_task that cares is __unhash_process, and it can be trivially seen that we handle cleaning up a thread group leader properly. Since de_thread doesn't change the pid of the exiting leader process and instead shares it with the new leader process. I change thread_group_leader to recognize group leadership based on the group_leader field and not based on pids. This should also be slightly cheaper then the existing thread_group_leader macro. I performed a quick audit and I couldn't see any user of thread_group_leader that cared about the difference. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-11 07:16:49 +08:00
/* de_thread depends on thread_group_leader not being a pid based check */
#define thread_group_leader(p) (p == p->group_leader)
[PATCH] proc: readdir race fix (take 3) The problem: An opendir, readdir, closedir sequence can fail to report process ids that are continually in use throughout the sequence of system calls. For this race to trigger the process that proc_pid_readdir stops at must exit before readdir is called again. This can cause ps to fail to report processes, and it is in violation of posix guarantees and normal application expectations with respect to readdir. Currently there is no way to work around this problem in user space short of providing a gargantuan buffer to user space so the directory read all happens in on system call. This patch implements the normal directory semantics for proc, that guarantee that a directory entry that is neither created nor destroyed while reading the directory entry will be returned. For directory that are either created or destroyed during the readdir you may or may not see them. Furthermore you may seek to a directory offset you have previously seen. These are the guarantee that ext[23] provides and that posix requires, and more importantly that user space expects. Plus it is a simple semantic to implement reliable service. It is just a matter of calling readdir a second time if you are wondering if something new has show up. These better semantics are implemented by scanning through the pids in numerical order and by making the file offset a pid plus a fixed offset. The pid scan happens on the pid bitmap, which when you look at it is remarkably efficient for a brute force algorithm. Given that a typical cache line is 64 bytes and thus covers space for 64*8 == 200 pids. There are only 40 cache lines for the entire 32K pid space. A typical system will have 100 pids or more so this is actually fewer cache lines we have to look at to scan a linked list, and the worst case of having to scan the entire pid bitmap is pretty reasonable. If we need something more efficient we can go to a more efficient data structure for indexing the pids, but for now what we have should be sufficient. In addition this takes no additional locks and is actually less code than what we are doing now. Also another very subtle bug in this area has been fixed. It is possible to catch a task in the middle of de_thread where a thread is assuming the thread of it's thread group leader. This patch carefully handles that case so if we hit it we don't fail to return the pid, that is undergoing the de_thread dance. Thanks to KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> for providing the first fix, pointing this out and working on it. [oleg@tv-sign.ru: fix it] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: Jean Delvare <jdelvare@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:17:04 +08:00
/* Do to the insanities of de_thread it is possible for a process
* to have the pid of the thread group leader without actually being
* the thread group leader. For iteration through the pids in proc
* all we care about is that we have a task with the appropriate
* pid, we don't actually care if we have the right task.
*/
static inline int has_group_leader_pid(struct task_struct *p)
[PATCH] proc: readdir race fix (take 3) The problem: An opendir, readdir, closedir sequence can fail to report process ids that are continually in use throughout the sequence of system calls. For this race to trigger the process that proc_pid_readdir stops at must exit before readdir is called again. This can cause ps to fail to report processes, and it is in violation of posix guarantees and normal application expectations with respect to readdir. Currently there is no way to work around this problem in user space short of providing a gargantuan buffer to user space so the directory read all happens in on system call. This patch implements the normal directory semantics for proc, that guarantee that a directory entry that is neither created nor destroyed while reading the directory entry will be returned. For directory that are either created or destroyed during the readdir you may or may not see them. Furthermore you may seek to a directory offset you have previously seen. These are the guarantee that ext[23] provides and that posix requires, and more importantly that user space expects. Plus it is a simple semantic to implement reliable service. It is just a matter of calling readdir a second time if you are wondering if something new has show up. These better semantics are implemented by scanning through the pids in numerical order and by making the file offset a pid plus a fixed offset. The pid scan happens on the pid bitmap, which when you look at it is remarkably efficient for a brute force algorithm. Given that a typical cache line is 64 bytes and thus covers space for 64*8 == 200 pids. There are only 40 cache lines for the entire 32K pid space. A typical system will have 100 pids or more so this is actually fewer cache lines we have to look at to scan a linked list, and the worst case of having to scan the entire pid bitmap is pretty reasonable. If we need something more efficient we can go to a more efficient data structure for indexing the pids, but for now what we have should be sufficient. In addition this takes no additional locks and is actually less code than what we are doing now. Also another very subtle bug in this area has been fixed. It is possible to catch a task in the middle of de_thread where a thread is assuming the thread of it's thread group leader. This patch carefully handles that case so if we hit it we don't fail to return the pid, that is undergoing the de_thread dance. Thanks to KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> for providing the first fix, pointing this out and working on it. [oleg@tv-sign.ru: fix it] Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: Jean Delvare <jdelvare@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 17:17:04 +08:00
{
return p->pid == p->tgid;
}
static inline
int same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
return p1->tgid == p2->tgid;
}
static inline struct task_struct *next_thread(const struct task_struct *p)
{
return list_entry(rcu_dereference(p->thread_group.next),
struct task_struct, thread_group);
}
static inline int thread_group_empty(struct task_struct *p)
{
return list_empty(&p->thread_group);
}
#define delay_group_leader(p) \
(thread_group_leader(p) && !thread_group_empty(p))
/*
* Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
* subscriptions and synchronises with wait4(). Also used in procfs. Also
Task Control Groups: basic task cgroup framework Generic Process Control Groups -------------------------- There have recently been various proposals floating around for resource management/accounting and other task grouping subsystems in the kernel, including ResGroups, User BeanCounters, NSProxy cgroups, and others. These all need the basic abstraction of being able to group together multiple processes in an aggregate, in order to track/limit the resources permitted to those processes, or control other behaviour of the processes, and all implement this grouping in different ways. This patchset provides a framework for tracking and grouping processes into arbitrary "cgroups" and assigning arbitrary state to those groupings, in order to control the behaviour of the cgroup as an aggregate. The intention is that the various resource management and virtualization/cgroup efforts can also become task cgroup clients, with the result that: - the userspace APIs are (somewhat) normalised - it's easier to test e.g. the ResGroups CPU controller in conjunction with the BeanCounters memory controller, or use either of them as the resource-control portion of a virtual server system. - the additional kernel footprint of any of the competing resource management systems is substantially reduced, since it doesn't need to provide process grouping/containment, hence improving their chances of getting into the kernel This patch: Add the main task cgroups framework - the cgroup filesystem, and the basic structures for tracking membership and associating subsystem state objects to tasks. Signed-off-by: Paul Menage <menage@google.com> Cc: Serge E. Hallyn <serue@us.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Jackson <pj@sgi.com> Cc: Kirill Korotaev <dev@openvz.org> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:30 +08:00
* pins the final release of task.io_context. Also protects ->cpuset and
* ->cgroup.subsys[].
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
* neither inside nor outside.
*/
static inline void task_lock(struct task_struct *p)
{
spin_lock(&p->alloc_lock);
}
static inline void task_unlock(struct task_struct *p)
{
spin_unlock(&p->alloc_lock);
}
extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
unsigned long *flags);
static inline void unlock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
{
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}
#ifndef __HAVE_THREAD_FUNCTIONS
rename thread_info to stack This finally renames the thread_info field in task structure to stack, so that the assumptions about this field are gone and archs have more freedom about placing the thread_info structure. Nonbroken archs which have a proper thread pointer can do the access to both current thread and task structure via a single pointer. It'll allow for a few more cleanups of the fork code, from which e.g. ia64 could benefit. Signed-off-by: Roman Zippel <zippel@linux-m68k.org> [akpm@linux-foundation.org: build fix] Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Haavard Skinnemoen <hskinnemoen@atmel.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Andi Kleen <ak@muc.de> Cc: Chris Zankel <chris@zankel.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:35:17 +08:00
#define task_thread_info(task) ((struct thread_info *)(task)->stack)
#define task_stack_page(task) ((task)->stack)
static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
{
*task_thread_info(p) = *task_thread_info(org);
task_thread_info(p)->task = p;
}
static inline unsigned long *end_of_stack(struct task_struct *p)
{
rename thread_info to stack This finally renames the thread_info field in task structure to stack, so that the assumptions about this field are gone and archs have more freedom about placing the thread_info structure. Nonbroken archs which have a proper thread pointer can do the access to both current thread and task structure via a single pointer. It'll allow for a few more cleanups of the fork code, from which e.g. ia64 could benefit. Signed-off-by: Roman Zippel <zippel@linux-m68k.org> [akpm@linux-foundation.org: build fix] Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Haavard Skinnemoen <hskinnemoen@atmel.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Andi Kleen <ak@muc.de> Cc: Chris Zankel <chris@zankel.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:35:17 +08:00
return (unsigned long *)(task_thread_info(p) + 1);
}
#endif
extern void thread_info_cache_init(void);
/* set thread flags in other task's structures
* - see asm/thread_info.h for TIF_xxxx flags available
*/
static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
set_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
clear_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
return test_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline void set_tsk_need_resched(struct task_struct *tsk)
{
set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}
static inline void clear_tsk_need_resched(struct task_struct *tsk)
{
clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}
static inline int signal_pending(struct task_struct *p)
{
return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
extern int __fatal_signal_pending(struct task_struct *p);
static inline int fatal_signal_pending(struct task_struct *p)
{
return signal_pending(p) && __fatal_signal_pending(p);
}
static inline int need_resched(void)
{
return unlikely(test_thread_flag(TIF_NEED_RESCHED));
}
/*
* cond_resched() and cond_resched_lock(): latency reduction via
* explicit rescheduling in places that are safe. The return
* value indicates whether a reschedule was done in fact.
* cond_resched_lock() will drop the spinlock before scheduling,
* cond_resched_softirq() will enable bhs before scheduling.
*/
#ifdef CONFIG_PREEMPT
static inline int cond_resched(void)
{
return 0;
}
#else
extern int _cond_resched(void);
static inline int cond_resched(void)
{
return _cond_resched();
}
#endif
extern int cond_resched_lock(spinlock_t * lock);
extern int cond_resched_softirq(void);
/*
* Does a critical section need to be broken due to another
* task waiting?: (technically does not depend on CONFIG_PREEMPT,
* but a general need for low latency)
*/
static inline int spin_needbreak(spinlock_t *lock)
{
#ifdef CONFIG_PREEMPT
return spin_is_contended(lock);
#else
return 0;
#endif
}
/*
* Reevaluate whether the task has signals pending delivery.
* Wake the task if so.
* This is required every time the blocked sigset_t changes.
* callers must hold sighand->siglock.
*/
extern void recalc_sigpending_and_wake(struct task_struct *t);
extern void recalc_sigpending(void);
extern void signal_wake_up(struct task_struct *t, int resume_stopped);
/*
* Wrappers for p->thread_info->cpu access. No-op on UP.
*/
#ifdef CONFIG_SMP
static inline unsigned int task_cpu(const struct task_struct *p)
{
return task_thread_info(p)->cpu;
}
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
#else
static inline unsigned int task_cpu(const struct task_struct *p)
{
return 0;
}
static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
{
}
#endif /* CONFIG_SMP */
#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
extern void arch_pick_mmap_layout(struct mm_struct *mm);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm)
{
mm->mmap_base = TASK_UNMAPPED_BASE;
mm->get_unmapped_area = arch_get_unmapped_area;
mm->unmap_area = arch_unmap_area;
}
#endif
extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask);
extern long sched_getaffinity(pid_t pid, cpumask_t *mask);
extern int sched_mc_power_savings, sched_smt_power_savings;
extern void normalize_rt_tasks(void);
#ifdef CONFIG_GROUP_SCHED
extern struct task_group init_task_group;
#ifdef CONFIG_USER_SCHED
extern struct task_group root_task_group;
#endif
extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
extern void sched_move_task(struct task_struct *tsk);
#ifdef CONFIG_FAIR_GROUP_SCHED
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
extern unsigned long sched_group_shares(struct task_group *tg);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
extern int sched_group_set_rt_runtime(struct task_group *tg,
long rt_runtime_us);
extern long sched_group_rt_runtime(struct task_group *tg);
extern int sched_group_set_rt_period(struct task_group *tg,
long rt_period_us);
extern long sched_group_rt_period(struct task_group *tg);
#endif
#endif
#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
tsk->rchar += amt;
}
static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
tsk->wchar += amt;
}
static inline void inc_syscr(struct task_struct *tsk)
{
tsk->syscr++;
}
static inline void inc_syscw(struct task_struct *tsk)
{
tsk->syscw++;
}
#else
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
}
static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
}
static inline void inc_syscr(struct task_struct *tsk)
{
}
static inline void inc_syscw(struct task_struct *tsk)
{
}
#endif
#ifdef CONFIG_SMP
void migration_init(void);
#else
static inline void migration_init(void)
{
}
#endif
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk) TASK_SIZE
#endif
cgroups: add an owner to the mm_struct Remove the mem_cgroup member from mm_struct and instead adds an owner. This approach was suggested by Paul Menage. The advantage of this approach is that, once the mm->owner is known, using the subsystem id, the cgroup can be determined. It also allows several control groups that are virtually grouped by mm_struct, to exist independent of the memory controller i.e., without adding mem_cgroup's for each controller, to mm_struct. A new config option CONFIG_MM_OWNER is added and the memory resource controller selects this config option. This patch also adds cgroup callbacks to notify subsystems when mm->owner changes. The mm_cgroup_changed callback is called with the task_lock() of the new task held and is called just prior to changing the mm->owner. I am indebted to Paul Menage for the several reviews of this patchset and helping me make it lighter and simpler. This patch was tested on a powerpc box, it was compiled with both the MM_OWNER config turned on and off. After the thread group leader exits, it's moved to init_css_state by cgroup_exit(), thus all future charges from runnings threads would be redirected to the init_css_set's subsystem. Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Cc: Hirokazu Takahashi <taka@valinux.co.jp> Cc: David Rientjes <rientjes@google.com>, Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Reviewed-by: Paul Menage <menage@google.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 16:00:16 +08:00
#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);
#else
static inline void mm_update_next_owner(struct mm_struct *mm)
{
}
static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
}
#endif /* CONFIG_MM_OWNER */
#endif /* __KERNEL__ */
#endif