summaryrefslogtreecommitdiff
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c224
1 files changed, 140 insertions, 84 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index a0dad84567c9..d16c566eb645 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -18,7 +18,7 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
-#include <linux/namespace.h>
+#include <linux/mnt_namespace.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
@@ -27,6 +27,7 @@
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/fs.h>
+#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
@@ -35,6 +36,7 @@
#include <linux/syscalls.h>
#include <linux/jiffies.h>
#include <linux/futex.h>
+#include <linux/task_io_accounting_ops.h>
#include <linux/rcupdate.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
@@ -42,6 +44,7 @@
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/acct.h>
+#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
@@ -80,26 +83,26 @@ int nr_processes(void)
#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
# define alloc_task_struct() kmem_cache_alloc(task_struct_cachep, GFP_KERNEL)
# define free_task_struct(tsk) kmem_cache_free(task_struct_cachep, (tsk))
-static kmem_cache_t *task_struct_cachep;
+static struct kmem_cache *task_struct_cachep;
#endif
/* SLAB cache for signal_struct structures (tsk->signal) */
-static kmem_cache_t *signal_cachep;
+static struct kmem_cache *signal_cachep;
/* SLAB cache for sighand_struct structures (tsk->sighand) */
-kmem_cache_t *sighand_cachep;
+struct kmem_cache *sighand_cachep;
/* SLAB cache for files_struct structures (tsk->files) */
-kmem_cache_t *files_cachep;
+struct kmem_cache *files_cachep;
/* SLAB cache for fs_struct structures (tsk->fs) */
-kmem_cache_t *fs_cachep;
+struct kmem_cache *fs_cachep;
/* SLAB cache for vm_area_struct structures */
-kmem_cache_t *vm_area_cachep;
+struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
-static kmem_cache_t *mm_cachep;
+static struct kmem_cache *mm_cachep;
void free_task(struct task_struct *tsk)
{
@@ -183,7 +186,9 @@ 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);
+#ifdef CONFIG_BLK_DEV_IO_TRACE
tsk->btrace_seq = 0;
+#endif
tsk->splice_pipe = NULL;
return tsk;
}
@@ -233,7 +238,7 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
goto fail_nomem;
charge = len;
}
- tmp = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
@@ -248,7 +253,7 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
anon_vma_link(tmp);
file = tmp->vm_file;
if (file) {
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file->f_path.dentry->d_inode;
get_file(file);
if (tmp->vm_flags & VM_DENYWRITE)
atomic_dec(&inode->i_writecount);
@@ -315,7 +320,7 @@ static inline void mm_free_pgd(struct mm_struct * mm)
__cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);
-#define allocate_mm() (kmem_cache_alloc(mm_cachep, SLAB_KERNEL))
+#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL))
#define free_mm(mm) (kmem_cache_free(mm_cachep, (mm)))
#include <linux/init_task.h>
@@ -444,7 +449,16 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
tsk->vfork_done = NULL;
complete(vfork_done);
}
- if (tsk->clear_child_tid && atomic_read(&mm->mm_users) > 1) {
+
+ /*
+ * If we're exiting normally, clear a user-space tid field if
+ * requested. We leave this alone when dying by signal, to leave
+ * the value intact in a core dump, and to save the unnecessary
+ * trouble otherwise. Userland only wants this done for a sys_exit.
+ */
+ if (tsk->clear_child_tid
+ && !(tsk->flags & PF_SIGNALED)
+ && atomic_read(&mm->mm_users) > 1) {
u32 __user * tidptr = tsk->clear_child_tid;
tsk->clear_child_tid = NULL;
@@ -475,6 +489,10 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
memcpy(mm, oldmm, sizeof(*mm));
+ /* Initializing for Swap token stuff */
+ mm->token_priority = 0;
+ mm->last_interval = 0;
+
if (!mm_init(mm))
goto fail_nomem;
@@ -538,6 +556,10 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
goto fail_nomem;
good_mm:
+ /* Initializing for Swap token stuff */
+ mm->token_priority = 0;
+ mm->last_interval = 0;
+
tsk->mm = mm;
tsk->active_mm = mm;
return 0;
@@ -592,7 +614,7 @@ static inline int copy_fs(unsigned long clone_flags, struct task_struct * tsk)
static int count_open_files(struct fdtable *fdt)
{
- int size = fdt->max_fdset;
+ int size = fdt->max_fds;
int i;
/* Find the last open fd */
@@ -609,7 +631,7 @@ static struct files_struct *alloc_files(void)
struct files_struct *newf;
struct fdtable *fdt;
- newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL);
+ newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
if (!newf)
goto out;
@@ -619,12 +641,10 @@ static struct files_struct *alloc_files(void)
newf->next_fd = 0;
fdt = &newf->fdtab;
fdt->max_fds = NR_OPEN_DEFAULT;
- fdt->max_fdset = EMBEDDED_FD_SET_SIZE;
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->free_files = NULL;
fdt->next = NULL;
rcu_assign_pointer(newf->fdt, fdt);
out:
@@ -640,7 +660,7 @@ static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
{
struct files_struct *newf;
struct file **old_fds, **new_fds;
- int open_files, size, i, expand;
+ int open_files, size, i;
struct fdtable *old_fdt, *new_fdt;
*errorp = -ENOMEM;
@@ -651,25 +671,14 @@ static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
spin_lock(&oldf->file_lock);
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.
+ * 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_fdset) {
- new_fdt->max_fdset = 0;
- expand = 1;
- }
if (open_files > new_fdt->max_fds) {
new_fdt->max_fds = 0;
- expand = 1;
- }
-
- /* if the old fdset gets grown now, we'll only copy up to "size" fds */
- if (expand) {
spin_unlock(&oldf->file_lock);
spin_lock(&newf->file_lock);
*errorp = expand_files(newf, open_files-1);
@@ -689,8 +698,10 @@ static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
- 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);
+ 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++;
@@ -715,22 +726,19 @@ static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
/* This is long word aligned thus could use a optimized version */
memset(new_fds, 0, size);
- if (new_fdt->max_fdset > open_files) {
- int left = (new_fdt->max_fdset-open_files)/8;
+ if (new_fdt->max_fds > open_files) {
+ int left = (new_fdt->max_fds-open_files)/8;
int start = open_files / (8 * sizeof(unsigned long));
memset(&new_fdt->open_fds->fds_bits[start], 0, left);
memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
}
-out:
return newf;
out_release:
- 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);
+out:
return NULL;
}
@@ -826,7 +834,6 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts
if (clone_flags & CLONE_THREAD) {
atomic_inc(&current->signal->count);
atomic_inc(&current->signal->live);
- taskstats_tgid_alloc(current->signal);
return 0;
}
sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
@@ -893,7 +900,6 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts
void __cleanup_signal(struct signal_struct *sig)
{
exit_thread_group_keys(sig);
- taskstats_tgid_free(sig);
kmem_cache_free(signal_cachep, sig);
}
@@ -980,6 +986,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (!p)
goto fork_out;
+ rt_mutex_init_task(p);
+
#ifdef CONFIG_TRACE_IRQFLAGS
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
@@ -1034,6 +1042,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->wchar = 0; /* I/O counter: bytes written */
p->syscr = 0; /* I/O counter: read syscalls */
p->syscw = 0; /* I/O counter: write syscalls */
+ task_io_accounting_init(p);
acct_clear_integrals(p);
p->it_virt_expires = cputime_zero;
@@ -1061,7 +1070,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+ p->hardirqs_enabled = 1;
+#else
p->hardirqs_enabled = 0;
+#endif
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
@@ -1080,8 +1093,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->lockdep_recursion = 0;
#endif
- rt_mutex_init_task(p);
-
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
@@ -1109,11 +1120,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_cleanup_signal;
if ((retval = copy_keys(clone_flags, p)))
goto bad_fork_cleanup_mm;
- if ((retval = copy_namespace(clone_flags, p)))
+ if ((retval = copy_namespaces(clone_flags, p)))
goto bad_fork_cleanup_keys;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
if (retval)
- goto bad_fork_cleanup_namespace;
+ goto bad_fork_cleanup_namespaces;
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
@@ -1144,7 +1155,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
/* Our parent execution domain becomes current domain
These must match for thread signalling to apply */
-
p->parent_exec_id = p->self_exec_id;
/* ok, now we should be set up.. */
@@ -1167,6 +1177,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
+ /* for sys_ioprio_set(IOPRIO_WHO_PGRP) */
+ p->ioprio = current->ioprio;
+
/*
* The task hasn't been attached yet, so its cpus_allowed mask will
* not be changed, nor will its assigned CPU.
@@ -1203,7 +1216,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
- goto bad_fork_cleanup_namespace;
+ goto bad_fork_cleanup_namespaces;
}
if (clone_flags & CLONE_THREAD) {
@@ -1226,11 +1239,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
}
}
- /*
- * inherit ioprio
- */
- p->ioprio = current->ioprio;
-
if (likely(p->pid)) {
add_parent(p);
if (unlikely(p->ptrace & PT_PTRACED))
@@ -1239,9 +1247,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (thread_group_leader(p)) {
p->signal->tty = current->signal->tty;
p->signal->pgrp = process_group(current);
- p->signal->session = current->signal->session;
+ set_signal_session(p->signal, process_session(current));
attach_pid(p, PIDTYPE_PGID, process_group(p));
- attach_pid(p, PIDTYPE_SID, p->signal->session);
+ attach_pid(p, PIDTYPE_SID, process_session(p));
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__get_cpu_var(process_counts)++;
@@ -1256,8 +1264,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
proc_fork_connector(p);
return p;
-bad_fork_cleanup_namespace:
- exit_namespace(p);
+bad_fork_cleanup_namespaces:
+ exit_task_namespaces(p);
bad_fork_cleanup_keys:
exit_keys(p);
bad_fork_cleanup_mm:
@@ -1299,7 +1307,7 @@ fork_out:
return ERR_PTR(retval);
}
-struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
+noinline struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
{
memset(regs, 0, sizeof(struct pt_regs));
return regs;
@@ -1311,9 +1319,8 @@ struct task_struct * __devinit fork_idle(int cpu)
struct pt_regs regs;
task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL, NULL, 0);
- if (!task)
- return ERR_PTR(-ENOMEM);
- init_idle(task, cpu);
+ if (!IS_ERR(task))
+ init_idle(task, cpu);
return task;
}
@@ -1410,7 +1417,7 @@ long do_fork(unsigned long clone_flags,
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif
-static void sighand_ctor(void *data, kmem_cache_t *cachep, unsigned long flags)
+static void sighand_ctor(void *data, struct kmem_cache *cachep, unsigned long flags)
{
struct sighand_struct *sighand = data;
@@ -1506,18 +1513,18 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
}
/*
- * Unshare the namespace structure if it is being shared
+ * Unshare the mnt_namespace structure if it is being shared
*/
-static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs)
+static int unshare_mnt_namespace(unsigned long unshare_flags,
+ struct mnt_namespace **new_nsp, struct fs_struct *new_fs)
{
- struct namespace *ns = current->namespace;
+ struct mnt_namespace *ns = current->nsproxy->mnt_ns;
- if ((unshare_flags & CLONE_NEWNS) &&
- (ns && atomic_read(&ns->count) > 1)) {
+ if ((unshare_flags & CLONE_NEWNS) && ns) {
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- *new_nsp = dup_namespace(current, new_fs ? new_fs : current->fs);
+ *new_nsp = dup_mnt_ns(current, new_fs ? new_fs : current->fs);
if (!*new_nsp)
return -ENOMEM;
}
@@ -1526,15 +1533,13 @@ static int unshare_namespace(unsigned long unshare_flags, struct namespace **new
}
/*
- * Unsharing of sighand for tasks created with CLONE_SIGHAND is not
- * supported yet
+ * Unsharing of sighand is not supported yet
*/
static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp)
{
struct sighand_struct *sigh = current->sighand;
- if ((unshare_flags & CLONE_SIGHAND) &&
- (sigh && atomic_read(&sigh->count) > 1))
+ if ((unshare_flags & CLONE_SIGHAND) && atomic_read(&sigh->count) > 1)
return -EINVAL;
else
return 0;
@@ -1585,6 +1590,16 @@ static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **n
return 0;
}
+#ifndef CONFIG_IPC_NS
+static inline int unshare_ipcs(unsigned long flags, struct ipc_namespace **ns)
+{
+ if (flags & CLONE_NEWIPC)
+ return -EINVAL;
+
+ return 0;
+}
+#endif
+
/*
* unshare allows a process to 'unshare' part of the process
* context which was originally shared using clone. copy_*
@@ -1597,25 +1612,29 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
{
int err = 0;
struct fs_struct *fs, *new_fs = NULL;
- struct namespace *ns, *new_ns = NULL;
- struct sighand_struct *sigh, *new_sigh = NULL;
+ struct mnt_namespace *ns, *new_ns = NULL;
+ struct sighand_struct *new_sigh = NULL;
struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
struct files_struct *fd, *new_fd = NULL;
struct sem_undo_list *new_ulist = NULL;
+ struct nsproxy *new_nsproxy = NULL, *old_nsproxy = NULL;
+ struct uts_namespace *uts, *new_uts = NULL;
+ struct ipc_namespace *ipc, *new_ipc = NULL;
check_unshare_flags(&unshare_flags);
/* Return -EINVAL for all unsupported flags */
err = -EINVAL;
if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
- CLONE_VM|CLONE_FILES|CLONE_SYSVSEM))
+ CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
+ CLONE_NEWUTS|CLONE_NEWIPC))
goto bad_unshare_out;
if ((err = unshare_thread(unshare_flags)))
goto bad_unshare_out;
if ((err = unshare_fs(unshare_flags, &new_fs)))
goto bad_unshare_cleanup_thread;
- if ((err = unshare_namespace(unshare_flags, &new_ns, new_fs)))
+ if ((err = unshare_mnt_namespace(unshare_flags, &new_ns, new_fs)))
goto bad_unshare_cleanup_fs;
if ((err = unshare_sighand(unshare_flags, &new_sigh)))
goto bad_unshare_cleanup_ns;
@@ -1625,11 +1644,30 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
goto bad_unshare_cleanup_vm;
if ((err = unshare_semundo(unshare_flags, &new_ulist)))
goto bad_unshare_cleanup_fd;
+ if ((err = unshare_utsname(unshare_flags, &new_uts)))
+ goto bad_unshare_cleanup_semundo;
+ if ((err = unshare_ipcs(unshare_flags, &new_ipc)))
+ goto bad_unshare_cleanup_uts;
+
+ if (new_ns || new_uts || new_ipc) {
+ old_nsproxy = current->nsproxy;
+ new_nsproxy = dup_namespaces(old_nsproxy);
+ if (!new_nsproxy) {
+ err = -ENOMEM;
+ goto bad_unshare_cleanup_ipc;
+ }
+ }
- if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist) {
+ if (new_fs || new_ns || new_mm || new_fd || new_ulist ||
+ new_uts || new_ipc) {
task_lock(current);
+ if (new_nsproxy) {
+ current->nsproxy = new_nsproxy;
+ new_nsproxy = old_nsproxy;
+ }
+
if (new_fs) {
fs = current->fs;
current->fs = new_fs;
@@ -1637,17 +1675,11 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
}
if (new_ns) {
- ns = current->namespace;
- current->namespace = new_ns;
+ ns = current->nsproxy->mnt_ns;
+ current->nsproxy->mnt_ns = new_ns;
new_ns = ns;
}
- if (new_sigh) {
- sigh = current->sighand;
- rcu_assign_pointer(current->sighand, new_sigh);
- new_sigh = sigh;
- }
-
if (new_mm) {
mm = current->mm;
active_mm = current->active_mm;
@@ -1663,9 +1695,33 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
new_fd = fd;
}
+ if (new_uts) {
+ uts = current->nsproxy->uts_ns;
+ current->nsproxy->uts_ns = new_uts;
+ new_uts = uts;
+ }
+
+ if (new_ipc) {
+ ipc = current->nsproxy->ipc_ns;
+ current->nsproxy->ipc_ns = new_ipc;
+ new_ipc = ipc;
+ }
+
task_unlock(current);
}
+ if (new_nsproxy)
+ put_nsproxy(new_nsproxy);
+
+bad_unshare_cleanup_ipc:
+ if (new_ipc)
+ put_ipc_ns(new_ipc);
+
+bad_unshare_cleanup_uts:
+ if (new_uts)
+ put_uts_ns(new_uts);
+
+bad_unshare_cleanup_semundo:
bad_unshare_cleanup_fd:
if (new_fd)
put_files_struct(new_fd);
@@ -1681,7 +1737,7 @@ bad_unshare_cleanup_sigh:
bad_unshare_cleanup_ns:
if (new_ns)
- put_namespace(new_ns);
+ put_mnt_ns(new_ns);
bad_unshare_cleanup_fs:
if (new_fs)
generated by cgit v1.2.3 (git 2.25.1) at 2026-04-27 13:40:50 +0000