#include <linux/completion.h>
#include <linux/namespace.h>
#include <linux/personality.h>
+#include <linux/mempolicy.h>
#include <linux/sem.h>
#include <linux/file.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/fs.h>
+#include <linux/cpu.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
+#include <linux/rmap.h>
+#include <linux/vs_network.h>
+#include <linux/vs_limit.h>
+#include <linux/ckrm.h>
+#include <linux/ckrm_tsk.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
int cpu;
int total = 0;
- for_each_cpu(cpu)
+ for_each_online_cpu(cpu)
total += per_cpu(process_counts, cpu);
return total;
static void free_task(struct task_struct *tsk)
{
free_thread_info(tsk->thread_info);
+ vxdprintk("freeing up task %p\n", tsk);
+ clr_vx_info(&tsk->vx_info);
+ clr_nx_info(&tsk->nx_info);
free_task_struct(tsk);
}
EXPORT_SYMBOL(finish_wait);
-int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync)
+int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
- int ret = default_wake_function(wait, mode, sync);
+ int ret = default_wake_function(wait, mode, sync, key);
if (ret)
list_del_init(&wait->task_list);
#endif
/* create a slab on which task_structs can be allocated */
task_struct_cachep =
- kmem_cache_create("task_struct",
- sizeof(struct task_struct),ARCH_MIN_TASKALIGN,
- 0, NULL, NULL);
- if (!task_struct_cachep)
- panic("fork_init(): cannot create task_struct SLAB cache");
+ kmem_cache_create("task_struct", sizeof(struct task_struct),
+ ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL, NULL);
#endif
/*
tsk->thread_info = ti;
ti->task = tsk;
+ ckrm_cb_newtask(tsk);
/* One for us, one for whoever does the "release_task()" (usually parent) */
atomic_set(&tsk->usage,2);
return tsk;
struct vm_area_struct * mpnt, *tmp, **pprev;
struct rb_node **rb_link, *rb_parent;
int retval;
- unsigned long charge = 0;
+ unsigned long charge;
+ struct mempolicy *pol;
down_write(&oldmm->mmap_sem);
flush_cache_mm(current->mm);
if(mpnt->vm_flags & VM_DONTCOPY)
continue;
+ charge = 0;
if (mpnt->vm_flags & VM_ACCOUNT) {
unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
if (security_vm_enough_memory(len))
goto fail_nomem;
- charge += len;
+ charge = len;
}
tmp = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
+ pol = mpol_copy(vma_policy(mpnt));
+ retval = PTR_ERR(pol);
+ if (IS_ERR(pol))
+ goto fail_nomem_policy;
+ vma_set_policy(tmp, pol);
tmp->vm_flags &= ~VM_LOCKED;
tmp->vm_mm = mm;
tmp->vm_next = NULL;
+ anon_vma_link(tmp);
+ vma_prio_tree_init(tmp);
file = tmp->vm_file;
- INIT_LIST_HEAD(&tmp->shared);
if (file) {
struct inode *inode = file->f_dentry->d_inode;
get_file(file);
atomic_dec(&inode->i_writecount);
/* insert tmp into the share list, just after mpnt */
- down(&file->f_mapping->i_shared_sem);
- list_add(&tmp->shared, &mpnt->shared);
- up(&file->f_mapping->i_shared_sem);
+ spin_lock(&file->f_mapping->i_mmap_lock);
+ flush_dcache_mmap_lock(file->f_mapping);
+ vma_prio_tree_add(tmp, mpnt);
+ flush_dcache_mmap_unlock(file->f_mapping);
+ spin_unlock(&file->f_mapping->i_mmap_lock);
}
/*
tmp->vm_ops->open(tmp);
if (retval)
- goto fail;
+ goto out;
}
retval = 0;
flush_tlb_mm(current->mm);
up_write(&oldmm->mmap_sem);
return retval;
+fail_nomem_policy:
+ kmem_cache_free(vm_area_cachep, tmp);
fail_nomem:
retval = -ENOMEM;
-fail:
vm_unacct_memory(charge);
goto out;
}
+
static inline int mm_alloc_pgd(struct mm_struct * mm)
{
mm->pgd = pgd_alloc(mm);
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
+#ifdef __HAVE_ARCH_MMAP_TOP
+ mm->mmap_top = mmap_top();
+#endif
+ set_vx_info(&mm->mm_vx_info, current->vx_info);
return mm;
}
free_mm(mm);
mm = allocate_mm();
if (mm) {
memset(mm, 0, sizeof(*mm));
- return mm_init(mm);
+ mm = mm_init(mm);
}
- return NULL;
+ return mm;
}
/*
BUG_ON(mm == &init_mm);
mm_free_pgd(mm);
destroy_context(mm);
+ clr_vx_info(&mm->mm_vx_info);
free_mm(mm);
}
* not set up a proper pointer then tough luck.
*/
put_user(0, tidptr);
- sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL);
+ sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0);
}
}
/* Copy the current MM stuff.. */
memcpy(mm, oldmm, sizeof(*mm));
+ mm->mm_vx_info = NULL;
if (!mm_init(mm))
goto fail_nomem;
{
int retval;
struct task_struct *p = NULL;
+ struct vx_info *vxi;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
goto fork_out;
retval = -ENOMEM;
+
p = dup_task_struct(current);
if (!p)
goto fork_out;
+ p->vx_info = NULL;
+ set_vx_info(&p->vx_info, current->vx_info);
+ p->nx_info = NULL;
+ set_nx_info(&p->nx_info, current->nx_info);
+
+ /* check vserver memory */
+ if (p->mm && !(clone_flags & CLONE_VM)) {
+ if (vx_vmpages_avail(p->mm, p->mm->total_vm))
+ vx_pages_add(p->mm->mm_vx_info, RLIMIT_AS, p->mm->total_vm);
+ else
+ goto bad_fork_free;
+ }
+ if (p->mm && vx_flags(VXF_FORK_RSS, 0)) {
+ if (!vx_rsspages_avail(p->mm, p->mm->rss))
+ goto bad_fork_free;
+ }
+
retval = -EAGAIN;
+ if (!vx_nproc_avail(1))
+ goto bad_fork_free;
+
if (atomic_read(&p->user->processes) >=
p->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
if (p->binfmt && !try_module_get(p->binfmt->module))
goto bad_fork_cleanup_put_domain;
+ init_delays(p);
p->did_exec = 0;
copy_flags(clone_flags, p);
if (clone_flags & CLONE_IDLETASK)
p->security = NULL;
p->io_context = NULL;
p->audit_context = NULL;
+#ifdef CONFIG_NUMA
+ p->mempolicy = mpol_copy(p->mempolicy);
+ if (IS_ERR(p->mempolicy)) {
+ retval = PTR_ERR(p->mempolicy);
+ p->mempolicy = NULL;
+ goto bad_fork_cleanup;
+ }
+#endif
retval = -ENOMEM;
if ((retval = security_task_alloc(p)))
- goto bad_fork_cleanup;
+ goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
goto bad_fork_cleanup_security;
/* copy all the process information */
link_pid(p, p->pids + PIDTYPE_TGID, &p->group_leader->pids[PIDTYPE_TGID].pid);
nr_threads++;
+ vxi = current->vx_info;
+ if (vxi) {
+ atomic_inc(&vxi->cacct.nr_threads);
+ // atomic_inc(&vxi->limit.rcur[RLIMIT_NPROC]);
+ }
+ vx_nproc_inc();
write_unlock_irq(&tasklist_lock);
retval = 0;
audit_free(p);
bad_fork_cleanup_security:
security_task_free(p);
+bad_fork_cleanup_policy:
+#ifdef CONFIG_NUMA
+ mpol_free(p->mempolicy);
+#endif
bad_fork_cleanup:
if (p->pid > 0)
free_pidmap(p->pid);
clone_flags |= CLONE_PTRACE;
}
+#ifdef CONFIG_CKRM_TYPE_TASKCLASS
+ if (numtasks_get_ref(current->taskclass, 0) == 0) {
+ return -ENOMEM;
+ }
+#endif
+
p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr);
/*
* Do this prior waking up the new thread - the thread pointer
if (!IS_ERR(p)) {
struct completion vfork;
+ ckrm_cb_fork(p);
+
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
set_tsk_thread_flag(p, TIF_SIGPENDING);
}
- if (!(clone_flags & CLONE_STOPPED))
- wake_up_forked_process(p); /* do this last */
- else
+ if (!(clone_flags & CLONE_STOPPED)) {
+ /*
+ * Do the wakeup last. On SMP we treat fork() and
+ * CLONE_VM separately, because fork() has already
+ * created cache footprint on this CPU (due to
+ * copying the pagetables), hence migration would
+ * probably be costy. Threads on the other hand
+ * have less traction to the current CPU, and if
+ * there's an imbalance then the scheduler can
+ * migrate this fresh thread now, before it
+ * accumulates a larger cache footprint:
+ */
+ if (clone_flags & CLONE_VM)
+ wake_up_forked_thread(p);
+ else
+ wake_up_forked_process(p);
+ } else {
+ int cpu = get_cpu();
+
p->state = TASK_STOPPED;
+ if (cpu_is_offline(task_cpu(p)))
+ set_task_cpu(p, cpu);
+
+ put_cpu();
+ }
++total_forks;
if (unlikely (trace)) {
* COW overhead when the child exec()s afterwards.
*/
set_need_resched();
+ } else {
+#ifdef CONFIG_CKRM_TYPE_TASKCLASS
+ numtasks_put_ref(current->taskclass);
+#endif
}
return pid;
}
{
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- if (!sighand_cachep)
- panic("Cannot create sighand SLAB cache");
-
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
signal_cachep = kmem_cache_create("signal_cache",
sizeof(struct signal_struct), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- if (!signal_cachep)
- panic("Cannot create signal SLAB cache");
-
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
files_cachep = kmem_cache_create("files_cache",
- sizeof(struct files_struct), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- if (!files_cachep)
- panic("Cannot create files SLAB cache");
-
+ sizeof(struct files_struct), 0,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
fs_cachep = kmem_cache_create("fs_cache",
- sizeof(struct fs_struct), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- if (!fs_cachep)
- panic("Cannot create fs_struct SLAB cache");
-
+ sizeof(struct fs_struct), 0,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
vm_area_cachep = kmem_cache_create("vm_area_struct",
sizeof(struct vm_area_struct), 0,
- 0, NULL, NULL);
- if(!vm_area_cachep)
- panic("vma_init: Cannot alloc vm_area_struct SLAB cache");
-
+ SLAB_PANIC, NULL, NULL);
mm_cachep = kmem_cache_create("mm_struct",
sizeof(struct mm_struct), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- if(!mm_cachep)
- panic("vma_init: Cannot alloc mm_struct SLAB cache");
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
}
git://git.onelab.eu / linux-2.6.git / blobdiff