* Manage the dynamic fd arrays in the process files_struct.
*/
+#include <linux/module.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/time.h>
+#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/file.h>
};
int sysctl_nr_open __read_mostly = 1024*1024;
+int sysctl_nr_open_min = BITS_PER_LONG;
+int sysctl_nr_open_max = 1024 * 1024; /* raised later */
/*
* We use this list to defer free fdtables that have vmalloced
unsigned int cpy, set;
BUG_ON(nfdt->max_fds < ofdt->max_fds);
- if (ofdt->max_fds == 0)
- return;
cpy = ofdt->max_fds * sizeof(struct file *);
set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *);
struct fdtable *fdt;
fdt = files_fdtable(files);
+
+ /*
+ * N.B. For clone tasks sharing a files structure, this test
+ * will limit the total number of files that can be opened.
+ */
+ if (nr >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
+ return -EMFILE;
+
/* Do we need to expand? */
if (nr < fdt->max_fds)
return 0;
+
/* Can we expand? */
if (nr >= sysctl_nr_open)
return -EMFILE;
return i;
}
-static struct files_struct *alloc_files(void)
-{
- struct files_struct *newf;
- struct fdtable *fdt;
-
- newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
- if (!newf)
- goto out;
-
- atomic_set(&newf->count, 1);
-
- spin_lock_init(&newf->file_lock);
- newf->next_fd = 0;
- fdt = &newf->fdtab;
- fdt->max_fds = NR_OPEN_DEFAULT;
- fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
- fdt->open_fds = (fd_set *)&newf->open_fds_init;
- fdt->fd = &newf->fd_array[0];
- INIT_RCU_HEAD(&fdt->rcu);
- fdt->next = NULL;
- rcu_assign_pointer(newf->fdt, fdt);
-out:
- return newf;
-}
-
/*
* Allocate a new files structure and copy contents from the
* passed in files structure.
struct fdtable *old_fdt, *new_fdt;
*errorp = -ENOMEM;
- newf = alloc_files();
+ newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
if (!newf)
goto out;
+ atomic_set(&newf->count, 1);
+
+ spin_lock_init(&newf->file_lock);
+ newf->next_fd = 0;
+ new_fdt = &newf->fdtab;
+ new_fdt->max_fds = NR_OPEN_DEFAULT;
+ new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
+ new_fdt->open_fds = (fd_set *)&newf->open_fds_init;
+ new_fdt->fd = &newf->fd_array[0];
+ INIT_RCU_HEAD(&new_fdt->rcu);
+ new_fdt->next = NULL;
+
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
- new_fdt = files_fdtable(newf);
open_files = count_open_files(old_fdt);
/*
* Check whether we need to allocate a larger fd array and fd set.
- * Note: we're not a clone task, so the open count won't change.
*/
- if (open_files > new_fdt->max_fds) {
- new_fdt->max_fds = 0;
+ while (unlikely(open_files > new_fdt->max_fds)) {
spin_unlock(&oldf->file_lock);
- spin_lock(&newf->file_lock);
- *errorp = expand_files(newf, open_files-1);
- spin_unlock(&newf->file_lock);
- if (*errorp < 0)
+
+ if (new_fdt != &newf->fdtab) {
+ free_fdarr(new_fdt);
+ free_fdset(new_fdt);
+ kfree(new_fdt);
+ }
+
+ new_fdt = alloc_fdtable(open_files - 1);
+ if (!new_fdt) {
+ *errorp = -ENOMEM;
+ goto out_release;
+ }
+
+ /* beyond sysctl_nr_open; nothing to do */
+ if (unlikely(new_fdt->max_fds < open_files)) {
+ free_fdarr(new_fdt);
+ free_fdset(new_fdt);
+ kfree(new_fdt);
+ *errorp = -EMFILE;
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
*/
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
+ open_files = count_open_files(old_fdt);
}
old_fds = old_fdt->fd;
memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
}
+ rcu_assign_pointer(newf->fdt, new_fdt);
+
return newf;
out_release:
int i;
for_each_possible_cpu(i)
fdtable_defer_list_init(i);
+ sysctl_nr_open_max = min((size_t)INT_MAX, ~(size_t)0/sizeof(void *)) &
+ -BITS_PER_LONG;
}
struct files_struct init_files = {
},
.file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock),
};
+
+/*
+ * allocate a file descriptor, mark it busy.
+ */
+int alloc_fd(unsigned start, unsigned flags)
+{
+ struct files_struct *files = current->files;
+ unsigned int fd;
+ int error;
+ struct fdtable *fdt;
+
+ spin_lock(&files->file_lock);
+repeat:
+ fdt = files_fdtable(files);
+ fd = start;
+ if (fd < files->next_fd)
+ fd = files->next_fd;
+
+ if (fd < fdt->max_fds)
+ fd = find_next_zero_bit(fdt->open_fds->fds_bits,
+ fdt->max_fds, fd);
+
+ error = expand_files(files, fd);
+ if (error < 0)
+ goto out;
+
+ /*
+ * If we needed to expand the fs array we
+ * might have blocked - try again.
+ */
+ if (error)
+ goto repeat;
+
+ if (start <= files->next_fd)
+ files->next_fd = fd + 1;
+
+ FD_SET(fd, fdt->open_fds);
+ if (flags & O_CLOEXEC)
+ FD_SET(fd, fdt->close_on_exec);
+ else
+ FD_CLR(fd, fdt->close_on_exec);
+ error = fd;
+#if 1
+ /* Sanity check */
+ if (rcu_dereference(fdt->fd[fd]) != NULL) {
+ printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
+ rcu_assign_pointer(fdt->fd[fd], NULL);
+ }
+#endif
+
+out:
+ spin_unlock(&files->file_lock);
+ return error;
+}
+
+int get_unused_fd(void)
+{
+ return alloc_fd(0, 0);
+}
+EXPORT_SYMBOL(get_unused_fd);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff