aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cpuset.c4
-rw-r--r--kernel/exit.c26
-rw-r--r--kernel/fork.c101
-rw-r--r--kernel/rcupdate.c14
-rw-r--r--kernel/sched.c1
5 files changed, 102 insertions, 44 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1f06e769010..712d0202997 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -972,6 +972,10 @@ static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
*s++ = '\n';
*s = '\0';
+ /* Do nothing if *ppos is at the eof or beyond the eof. */
+ if (s - page <= *ppos)
+ return 0;
+
start = page + *ppos;
n = s - start;
retval = n - copy_to_user(buf, start, min(n, nbytes));
diff --git a/kernel/exit.c b/kernel/exit.c
index 5b0fb9f09f2..6d2089a1bce 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -368,17 +368,19 @@ EXPORT_SYMBOL(daemonize);
static inline void close_files(struct files_struct * files)
{
int i, j;
+ struct fdtable *fdt;
j = 0;
+ fdt = files_fdtable(files);
for (;;) {
unsigned long set;
i = j * __NFDBITS;
- if (i >= files->max_fdset || i >= files->max_fds)
+ if (i >= fdt->max_fdset || i >= fdt->max_fds)
break;
- set = files->open_fds->fds_bits[j++];
+ set = fdt->open_fds->fds_bits[j++];
while (set) {
if (set & 1) {
- struct file * file = xchg(&files->fd[i], NULL);
+ struct file * file = xchg(&fdt->fd[i], NULL);
if (file)
filp_close(file, files);
}
@@ -403,18 +405,22 @@ struct files_struct *get_files_struct(struct task_struct *task)
void fastcall put_files_struct(struct files_struct *files)
{
+ struct fdtable *fdt;
+
if (atomic_dec_and_test(&files->count)) {
close_files(files);
/*
* Free the fd and fdset arrays if we expanded them.
+ * If the fdtable was embedded, pass files for freeing
+ * at the end of the RCU grace period. Otherwise,
+ * you can free files immediately.
*/
- if (files->fd != &files->fd_array[0])
- free_fd_array(files->fd, files->max_fds);
- if (files->max_fdset > __FD_SETSIZE) {
- free_fdset(files->open_fds, files->max_fdset);
- free_fdset(files->close_on_exec, files->max_fdset);
- }
- kmem_cache_free(files_cachep, files);
+ fdt = files_fdtable(files);
+ if (fdt == &files->fdtab)
+ fdt->free_files = files;
+ else
+ kmem_cache_free(files_cachep, files);
+ free_fdtable(fdt);
}
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 7e1ead9a6ba..8149f360288 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -35,6 +35,7 @@
#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>
@@ -176,6 +177,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
/* 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;
}
@@ -564,24 +566,53 @@ static inline int copy_fs(unsigned long clone_flags, struct task_struct * tsk)
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 ...
@@ -602,35 +633,27 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
*/
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;
}
@@ -642,14 +665,21 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
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++;
@@ -662,24 +692,24 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
* 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;
@@ -688,9 +718,9 @@ out:
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;
}
@@ -1115,6 +1145,9 @@ static task_t *copy_process(unsigned long clone_flags,
__get_cpu_var(process_counts)++;
}
+ if (!current->signal->tty && p->signal->tty)
+ p->signal->tty = NULL;
+
nr_threads++;
total_forks++;
write_unlock_irq(&tasklist_lock);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index f436993bd59..bef3b6901b7 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -45,6 +45,7 @@
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/rcupdate.h>
+#include <linux/rcuref.h>
#include <linux/cpu.h>
/* Definition for rcupdate control block. */
@@ -72,6 +73,19 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL};
static int maxbatch = 10;
+#ifndef __HAVE_ARCH_CMPXCHG
+/*
+ * We use an array of spinlocks for the rcurefs -- similar to ones in sparc
+ * 32 bit atomic_t implementations, and a hash function similar to that
+ * for our refcounting needs.
+ * Can't help multiprocessors which donot have cmpxchg :(
+ */
+
+spinlock_t __rcuref_hash[RCUREF_HASH_SIZE] = {
+ [0 ... (RCUREF_HASH_SIZE-1)] = SPIN_LOCK_UNLOCKED
+};
+#endif
+
/**
* call_rcu - Queue an RCU callback for invocation after a grace period.
* @head: structure to be used for queueing the RCU updates.
diff --git a/kernel/sched.c b/kernel/sched.c
index 18b95520a2e..2632b812cf2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2888,6 +2888,7 @@ switch_tasks:
if (next == rq->idle)
schedstat_inc(rq, sched_goidle);
prefetch(next);
+ prefetch_stack(next);
clear_tsk_need_resched(prev);
rcu_qsctr_inc(task_cpu(prev));