namespaces: cleanup the code managed with PID_NS option

[linux-2.6-omap-h63xx.git] / kernel / fork.c

diff --git a/kernel/fork.c b/kernel/fork.c
index 39d22b3357dea001d75e37bc70e0ae8190321d2c..b2ef8e4fad70da87632b315f3be76f829371c99b 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -40,6 +40,7 @@
 #include <linux/ptrace.h>
 #include <linux/mount.h>
 #include <linux/audit.h>
+#include <linux/memcontrol.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
 #include <linux/acct.h>
@@ -51,6 +52,7 @@
 #include <linux/random.h>
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
+#include <linux/blkdev.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -324,7 +326,7 @@ static inline int mm_alloc_pgd(struct mm_struct * mm)
 
 static inline void mm_free_pgd(struct mm_struct * mm)
 {
-       pgd_free(mm->pgd);
+       pgd_free(mm, mm->pgd);
 }
 #else
 #define dup_mmap(mm, oldmm)    (0)
@@ -339,7 +341,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);
 
 #include <linux/init_task.h>
 
-static struct mm_struct * mm_init(struct mm_struct * mm)
+static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
        atomic_set(&mm->mm_users, 1);
        atomic_set(&mm->mm_count, 1);
@@ -356,11 +358,14 @@ static struct mm_struct * mm_init(struct mm_struct * mm)
        mm->ioctx_list = NULL;
        mm->free_area_cache = TASK_UNMAPPED_BASE;
        mm->cached_hole_size = ~0UL;
+       mm_init_cgroup(mm, p);
 
        if (likely(!mm_alloc_pgd(mm))) {
                mm->def_flags = 0;
                return mm;
        }
+
+       mm_free_cgroup(mm);
        free_mm(mm);
        return NULL;
 }
@@ -375,7 +380,7 @@ struct mm_struct * mm_alloc(void)
        mm = allocate_mm();
        if (mm) {
                memset(mm, 0, sizeof(*mm));
-               mm = mm_init(mm);
+               mm = mm_init(mm, current);
        }
        return mm;
 }
@@ -389,9 +394,11 @@ void fastcall __mmdrop(struct mm_struct *mm)
 {
        BUG_ON(mm == &init_mm);
        mm_free_pgd(mm);
+       mm_free_cgroup(mm);
        destroy_context(mm);
        free_mm(mm);
 }
+EXPORT_SYMBOL_GPL(__mmdrop);
 
 /*
  * Decrement the use count and release all resources for an mm.
@@ -509,7 +516,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
        mm->token_priority = 0;
        mm->last_interval = 0;
 
-       if (!mm_init(mm))
+       if (!mm_init(mm, tsk))
                goto fail_nomem;
 
        if (init_new_context(tsk, mm))
@@ -791,6 +798,31 @@ out:
        return error;
 }
 
+static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
+{
+#ifdef CONFIG_BLOCK
+       struct io_context *ioc = current->io_context;
+
+       if (!ioc)
+               return 0;
+       /*
+        * Share io context with parent, if CLONE_IO is set
+        */
+       if (clone_flags & CLONE_IO) {
+               tsk->io_context = ioc_task_link(ioc);
+               if (unlikely(!tsk->io_context))
+                       return -ENOMEM;
+       } else if (ioprio_valid(ioc->ioprio)) {
+               tsk->io_context = alloc_io_context(GFP_KERNEL, -1);
+               if (unlikely(!tsk->io_context))
+                       return -ENOMEM;
+
+               tsk->io_context->ioprio = ioc->ioprio;
+       }
+#endif
+       return 0;
+}
+
 /*
  *     Helper to unshare the files of the current task.
  *     We don't want to expose copy_files internals to
@@ -1091,6 +1123,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_SECURITY
        p->security = NULL;
 #endif
+       p->cap_bset = current->cap_bset;
        p->io_context = NULL;
        p->audit_context = NULL;
        cgroup_fork(p);
@@ -1156,15 +1189,17 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                goto bad_fork_cleanup_mm;
        if ((retval = copy_namespaces(clone_flags, p)))
                goto bad_fork_cleanup_keys;
+       if ((retval = copy_io(clone_flags, p)))
+               goto bad_fork_cleanup_namespaces;
        retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
        if (retval)
-               goto bad_fork_cleanup_namespaces;
+               goto bad_fork_cleanup_io;
 
        if (pid != &init_struct_pid) {
                retval = -ENOMEM;
                pid = alloc_pid(task_active_pid_ns(p));
                if (!pid)
-                       goto bad_fork_cleanup_namespaces;
+                       goto bad_fork_cleanup_io;
 
                if (clone_flags & CLONE_NEWPID) {
                        retval = pid_ns_prepare_proc(task_active_pid_ns(p));
@@ -1234,9 +1269,6 @@ 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.
@@ -1328,6 +1360,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 bad_fork_free_pid:
        if (pid != &init_struct_pid)
                free_pid(pid);
+bad_fork_cleanup_io:
+       put_io_context(p->io_context);
 bad_fork_cleanup_namespaces:
        exit_task_namespaces(p);
 bad_fork_cleanup_keys:
@@ -1370,7 +1404,7 @@ fork_out:
        return ERR_PTR(retval);
 }
 
-noinline struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
+noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
 {
        memset(regs, 0, sizeof(struct pt_regs));
        return regs;
@@ -1422,6 +1456,23 @@ long do_fork(unsigned long clone_flags,
        int trace = 0;
        long nr;
 
+       /*
+        * We hope to recycle these flags after 2.6.26
+        */
+       if (unlikely(clone_flags & CLONE_STOPPED)) {
+               static int __read_mostly count = 100;
+
+               if (count > 0 && printk_ratelimit()) {
+                       char comm[TASK_COMM_LEN];
+
+                       count--;
+                       printk(KERN_INFO "fork(): process `%s' used deprecated "
+                                       "clone flags 0x%lx\n",
+                               get_task_comm(comm, current),
+                               clone_flags & CLONE_STOPPED);
+               }
+       }
+
        if (unlikely(current->ptrace)) {
                trace = fork_traceflag (clone_flags);
                if (trace)
@@ -1464,7 +1515,7 @@ long do_fork(unsigned long clone_flags,
                if (!(clone_flags & CLONE_STOPPED))
                        wake_up_new_task(p, clone_flags);
                else
-                       p->state = TASK_STOPPED;
+                       __set_task_state(p, TASK_STOPPED);
 
                if (unlikely (trace)) {
                        current->ptrace_message = nr;