#include <linux/syscalls.h>
#include <linux/jiffies.h>
#include <linux/futex.h>
+#include <linux/rcupdate.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/acct.h>
+#include <linux/cn_proc.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
/* One for us, one for whoever does the "release_task()" (usually parent) */
atomic_set(&tsk->usage,2);
+ atomic_set(&tsk->fs_excl, 0);
return tsk;
}
#ifdef CONFIG_MMU
-static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
+static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
- struct vm_area_struct * mpnt, *tmp, **pprev;
+ struct vm_area_struct *mpnt, *tmp, **pprev;
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
struct mempolicy *pol;
down_write(&oldmm->mmap_sem);
- flush_cache_mm(current->mm);
+ flush_cache_mm(oldmm);
+ down_write(&mm->mmap_sem);
+
mm->locked_vm = 0;
mm->mmap = NULL;
mm->mmap_cache = NULL;
mm->free_area_cache = oldmm->mmap_base;
mm->cached_hole_size = ~0UL;
mm->map_count = 0;
- set_mm_counter(mm, rss, 0);
- set_mm_counter(mm, anon_rss, 0);
cpus_clear(mm->cpu_vm_mask);
mm->mm_rb = RB_ROOT;
rb_link = &mm->mm_rb.rb_node;
rb_parent = NULL;
pprev = &mm->mmap;
- for (mpnt = current->mm->mmap ; mpnt ; mpnt = mpnt->vm_next) {
+ for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
- __vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
- -vma_pages(mpnt));
+ long pages = vma_pages(mpnt);
+ mm->total_vm -= pages;
+ vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
+ -pages);
continue;
}
charge = 0;
}
/*
- * Link in the new vma and copy the page table entries:
- * link in first so that swapoff can see swap entries.
- * Note that, exceptionally, here the vma is inserted
- * without holding mm->mmap_sem.
+ * Link in the new vma and copy the page table entries.
*/
- spin_lock(&mm->page_table_lock);
*pprev = tmp;
pprev = &tmp->vm_next;
rb_parent = &tmp->vm_rb;
mm->map_count++;
- retval = copy_page_range(mm, current->mm, tmp);
- spin_unlock(&mm->page_table_lock);
+ retval = copy_page_range(mm, oldmm, tmp);
if (tmp->vm_ops && tmp->vm_ops->open)
tmp->vm_ops->open(tmp);
goto out;
}
retval = 0;
-
out:
- flush_tlb_mm(current->mm);
+ up_write(&mm->mmap_sem);
+ flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
return retval;
fail_nomem_policy:
INIT_LIST_HEAD(&mm->mmlist);
mm->core_waiters = 0;
mm->nr_ptes = 0;
+ set_mm_counter(mm, file_rss, 0);
+ set_mm_counter(mm, anon_rss, 0);
spin_lock_init(&mm->page_table_lock);
rwlock_init(&mm->ioctx_list_lock);
mm->ioctx_list = NULL;
if (retval)
goto free_pt;
- mm->hiwater_rss = get_mm_counter(mm,rss);
+ mm->hiwater_rss = get_mm_rss(mm);
mm->hiwater_vm = mm->total_vm;
good_mm:
return 0;
}
-static int count_open_files(struct files_struct *files, int size)
+static int count_open_files(struct fdtable *fdt)
{
+ int size = fdt->max_fdset;
int i;
/* Find the last open fd */
for (i = size/(8*sizeof(long)); i > 0; ) {
- if (files->open_fds->fds_bits[--i])
+ if (fdt->open_fds->fds_bits[--i])
break;
}
i = (i+1) * 8 * sizeof(long);
return i;
}
+static struct files_struct *alloc_files(void)
+{
+ struct files_struct *newf;
+ struct fdtable *fdt;
+
+ newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL);
+ if (!newf)
+ goto out;
+
+ atomic_set(&newf->count, 1);
+
+ spin_lock_init(&newf->file_lock);
+ fdt = &newf->fdtab;
+ fdt->next_fd = 0;
+ fdt->max_fds = NR_OPEN_DEFAULT;
+ fdt->max_fdset = __FD_SETSIZE;
+ fdt->close_on_exec = &newf->close_on_exec_init;
+ fdt->open_fds = &newf->open_fds_init;
+ fdt->fd = &newf->fd_array[0];
+ INIT_RCU_HEAD(&fdt->rcu);
+ fdt->free_files = NULL;
+ fdt->next = NULL;
+ rcu_assign_pointer(newf->fdt, fdt);
+out:
+ return newf;
+}
+
static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
{
struct files_struct *oldf, *newf;
struct file **old_fds, **new_fds;
int open_files, size, i, error = 0, expand;
+ struct fdtable *old_fdt, *new_fdt;
/*
* A background process may not have any files ...
*/
tsk->files = NULL;
error = -ENOMEM;
- newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL);
- if (!newf)
+ newf = alloc_files();
+ if (!newf)
goto out;
- atomic_set(&newf->count, 1);
-
- spin_lock_init(&newf->file_lock);
- newf->next_fd = 0;
- newf->max_fds = NR_OPEN_DEFAULT;
- newf->max_fdset = __FD_SETSIZE;
- newf->close_on_exec = &newf->close_on_exec_init;
- newf->open_fds = &newf->open_fds_init;
- newf->fd = &newf->fd_array[0];
-
spin_lock(&oldf->file_lock);
-
- open_files = count_open_files(oldf, oldf->max_fdset);
+ old_fdt = files_fdtable(oldf);
+ new_fdt = files_fdtable(newf);
+ size = old_fdt->max_fdset;
+ open_files = count_open_files(old_fdt);
expand = 0;
/*
* Check whether we need to allocate a larger fd array or fd set.
* Note: we're not a clone task, so the open count won't change.
*/
- if (open_files > newf->max_fdset) {
- newf->max_fdset = 0;
+ if (open_files > new_fdt->max_fdset) {
+ new_fdt->max_fdset = 0;
expand = 1;
}
- if (open_files > newf->max_fds) {
- newf->max_fds = 0;
+ if (open_files > new_fdt->max_fds) {
+ new_fdt->max_fds = 0;
expand = 1;
}
spin_unlock(&newf->file_lock);
if (error < 0)
goto out_release;
+ new_fdt = files_fdtable(newf);
+ /*
+ * Reacquire the oldf lock and a pointer to its fd table
+ * who knows it may have a new bigger fd table. We need
+ * the latest pointer.
+ */
spin_lock(&oldf->file_lock);
+ old_fdt = files_fdtable(oldf);
}
- old_fds = oldf->fd;
- new_fds = newf->fd;
+ old_fds = old_fdt->fd;
+ new_fds = new_fdt->fd;
- memcpy(newf->open_fds->fds_bits, oldf->open_fds->fds_bits, open_files/8);
- memcpy(newf->close_on_exec->fds_bits, oldf->close_on_exec->fds_bits, open_files/8);
+ memcpy(new_fdt->open_fds->fds_bits, old_fdt->open_fds->fds_bits, open_files/8);
+ memcpy(new_fdt->close_on_exec->fds_bits, old_fdt->close_on_exec->fds_bits, open_files/8);
for (i = open_files; i != 0; i--) {
struct file *f = *old_fds++;
* is partway through open(). So make sure that this
* fd is available to the new process.
*/
- FD_CLR(open_files - i, newf->open_fds);
+ FD_CLR(open_files - i, new_fdt->open_fds);
}
- *new_fds++ = f;
+ rcu_assign_pointer(*new_fds++, f);
}
spin_unlock(&oldf->file_lock);
/* compute the remainder to be cleared */
- size = (newf->max_fds - open_files) * sizeof(struct file *);
+ size = (new_fdt->max_fds - open_files) * sizeof(struct file *);
/* This is long word aligned thus could use a optimized version */
memset(new_fds, 0, size);
- if (newf->max_fdset > open_files) {
- int left = (newf->max_fdset-open_files)/8;
+ if (new_fdt->max_fdset > open_files) {
+ int left = (new_fdt->max_fdset-open_files)/8;
int start = open_files / (8 * sizeof(unsigned long));
- memset(&newf->open_fds->fds_bits[start], 0, left);
- memset(&newf->close_on_exec->fds_bits[start], 0, left);
+ memset(&new_fdt->open_fds->fds_bits[start], 0, left);
+ memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
}
tsk->files = newf;
return error;
out_release:
- free_fdset (newf->close_on_exec, newf->max_fdset);
- free_fdset (newf->open_fds, newf->max_fdset);
- free_fd_array(newf->fd, newf->max_fds);
+ free_fdset (new_fdt->close_on_exec, new_fdt->max_fdset);
+ free_fdset (new_fdt->open_fds, new_fdt->max_fdset);
+ free_fd_array(new_fdt->fd, new_fdt->max_fds);
kmem_cache_free(files_cachep, newf);
goto out;
}
{
unsigned long new_flags = p->flags;
- new_flags &= ~PF_SUPERPRIV;
+ new_flags &= ~(PF_SUPERPRIV | PF_NOFREEZE);
new_flags |= PF_FORKNOEXEC;
if (!(clone_flags & CLONE_PTRACE))
p->ptrace = 0;
* of CLONE_PTRACE.
*/
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
+#ifdef TIF_SYSCALL_EMU
+ clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
+#endif
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
* parent's CPU). This avoids alot of nasty races.
*/
p->cpus_allowed = current->cpus_allowed;
- if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed)))
+ if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
+ !cpu_online(task_cpu(p))))
set_task_cpu(p, smp_processor_id());
/*
spin_unlock(¤t->sighand->siglock);
}
+ /*
+ * inherit ioprio
+ */
+ p->ioprio = current->ioprio;
+
SET_LINKS(p);
if (unlikely(p->ptrace & PT_PTRACED))
__ptrace_link(p, current->parent);
__get_cpu_var(process_counts)++;
}
+ proc_fork_connector(p);
+ if (!current->signal->tty && p->signal->tty)
+ p->signal->tty = NULL;
+
nr_threads++;
total_forks++;
write_unlock_irq(&tasklist_lock);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff