aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile5
-rw-r--r--kernel/acct.c30
-rw-r--r--kernel/compat.c2
-rw-r--r--kernel/cpuset.c8
-rw-r--r--kernel/exit.c12
-rw-r--r--kernel/fork.c82
-rw-r--r--kernel/futex.c2
-rw-r--r--kernel/kallsyms.c1
-rw-r--r--kernel/kmod.c62
-rw-r--r--kernel/kprobes.c53
-rw-r--r--kernel/latency.c279
-rw-r--r--kernel/lockdep.c6
-rw-r--r--kernel/module.c37
-rw-r--r--kernel/nsproxy.c139
-rw-r--r--kernel/pid.c111
-rw-r--r--kernel/power/snapshot.c10
-rw-r--r--kernel/sched.c5
-rw-r--r--kernel/signal.c65
-rw-r--r--kernel/spinlock.c4
-rw-r--r--kernel/sys.c102
-rw-r--r--kernel/sysctl.c352
-rw-r--r--kernel/taskstats.c10
-rw-r--r--kernel/time.c173
-rw-r--r--kernel/time/Makefile2
-rw-r--r--kernel/time/ntp.c350
-rw-r--r--kernel/timer.c230
-rw-r--r--kernel/tsacct.c124
-rw-r--r--kernel/utsname.c95
28 files changed, 1685 insertions, 666 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index d62ec66c1af..d948ca12acf 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -8,7 +8,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
signal.o sys.o kmod.o workqueue.o pid.o \
rcupdate.o extable.o params.o posix-timers.o \
kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
- hrtimer.o rwsem.o
+ hrtimer.o rwsem.o latency.o nsproxy.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += time/
@@ -48,8 +48,9 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_RELAY) += relay.o
+obj-$(CONFIG_UTS_NS) += utsname.o
obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
-obj-$(CONFIG_TASKSTATS) += taskstats.o
+obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/acct.c b/kernel/acct.c
index f4330acead4..0aad5ca36a8 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -602,33 +602,3 @@ void acct_process(void)
do_acct_process(file);
fput(file);
}
-
-
-/**
- * acct_update_integrals - update mm integral fields in task_struct
- * @tsk: task_struct for accounting
- */
-void acct_update_integrals(struct task_struct *tsk)
-{
- if (likely(tsk->mm)) {
- long delta =
- cputime_to_jiffies(tsk->stime) - tsk->acct_stimexpd;
-
- if (delta == 0)
- return;
- tsk->acct_stimexpd = tsk->stime;
- tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
- tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
- }
-}
-
-/**
- * acct_clear_integrals - clear the mm integral fields in task_struct
- * @tsk: task_struct whose accounting fields are cleared
- */
-void acct_clear_integrals(struct task_struct *tsk)
-{
- tsk->acct_stimexpd = 0;
- tsk->acct_rss_mem1 = 0;
- tsk->acct_vm_mem1 = 0;
-}
diff --git a/kernel/compat.c b/kernel/compat.c
index b4fbd838cd7..75573e5d27b 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -26,8 +26,6 @@
#include <asm/uaccess.h>
-extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);
-
int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
{
return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 8c3c400cce9..9d850ae13b1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -377,7 +377,7 @@ static int cpuset_fill_super(struct super_block *sb, void *unused_data,
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directories start off with i_nlink == 2 (for "." entry) */
- inode->i_nlink++;
+ inc_nlink(inode);
} else {
return -ENOMEM;
}
@@ -1565,7 +1565,7 @@ static int cpuset_create_file(struct dentry *dentry, int mode)
inode->i_fop = &simple_dir_operations;
/* start off with i_nlink == 2 (for "." entry) */
- inode->i_nlink++;
+ inc_nlink(inode);
} else if (S_ISREG(mode)) {
inode->i_size = 0;
inode->i_fop = &cpuset_file_operations;
@@ -1598,7 +1598,7 @@ static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode)
error = cpuset_create_file(dentry, S_IFDIR | mode);
if (!error) {
dentry->d_fsdata = cs;
- parent->d_inode->i_nlink++;
+ inc_nlink(parent->d_inode);
cs->dentry = dentry;
}
dput(dentry);
@@ -2033,7 +2033,7 @@ int __init cpuset_init(void)
}
root = cpuset_mount->mnt_sb->s_root;
root->d_fsdata = &top_cpuset;
- root->d_inode->i_nlink++;
+ inc_nlink(root->d_inode);
top_cpuset.dentry = root;
root->d_inode->i_op = &cpuset_dir_inode_operations;
number_of_cpusets = 1;
diff --git a/kernel/exit.c b/kernel/exit.c
index c189de2927a..f250a5e3e28 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -18,8 +18,10 @@
#include <linux/security.h>
#include <linux/cpu.h>
#include <linux/acct.h>
+#include <linux/tsacct_kern.h>
#include <linux/file.h>
#include <linux/binfmts.h>
+#include <linux/nsproxy.h>
#include <linux/ptrace.h>
#include <linux/profile.h>
#include <linux/mount.h>
@@ -396,9 +398,11 @@ void daemonize(const char *name, ...)
fs = init_task.fs;
current->fs = fs;
atomic_inc(&fs->count);
- exit_namespace(current);
- current->namespace = init_task.namespace;
- get_namespace(current->namespace);
+
+ exit_task_namespaces(current);
+ current->nsproxy = init_task.nsproxy;
+ get_task_namespaces(current);
+
exit_files(current);
current->files = init_task.files;
atomic_inc(&current->files->count);
@@ -916,7 +920,6 @@ fastcall NORET_TYPE void do_exit(long code)
exit_sem(tsk);
__exit_files(tsk);
__exit_fs(tsk);
- exit_namespace(tsk);
exit_thread();
cpuset_exit(tsk);
exit_keys(tsk);
@@ -931,6 +934,7 @@ fastcall NORET_TYPE void do_exit(long code)
tsk->exit_code = code;
proc_exit_connector(tsk);
exit_notify(tsk);
+ exit_task_namespaces(tsk);
#ifdef CONFIG_NUMA
mpol_free(tsk->mempolicy);
tsk->mempolicy = NULL;
diff --git a/kernel/fork.c b/kernel/fork.c
index 1c999f3e0b4..7dc6140baac 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -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>
@@ -42,6 +43,7 @@
#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>
@@ -1115,11 +1117,11 @@ 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;
/*
@@ -1211,7 +1213,7 @@ 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) {
@@ -1259,8 +1261,8 @@ 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:
@@ -1513,10 +1515,9 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
*/
static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs)
{
- struct namespace *ns = current->namespace;
+ struct namespace *ns = current->nsproxy->namespace;
- if ((unshare_flags & CLONE_NEWNS) &&
- (ns && atomic_read(&ns->count) > 1)) {
+ if ((unshare_flags & CLONE_NEWNS) && ns) {
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1588,6 +1589,16 @@ 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_*
@@ -1605,13 +1616,17 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
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)))
@@ -1628,11 +1643,30 @@ 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_sigh || 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;
@@ -1640,8 +1674,8 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
}
if (new_ns) {
- ns = current->namespace;
- current->namespace = new_ns;
+ ns = current->nsproxy->namespace;
+ current->nsproxy->namespace = new_ns;
new_ns = ns;
}
@@ -1666,9 +1700,33 @@ 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);
diff --git a/kernel/futex.c b/kernel/futex.c
index 4b6770e9806..4aaf91951a4 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1527,7 +1527,7 @@ static int futex_fd(u32 __user *uaddr, int signal)
filp->f_mapping = filp->f_dentry->d_inode->i_mapping;
if (signal) {
- err = f_setown(filp, current->pid, 1);
+ err = __f_setown(filp, task_pid(current), PIDTYPE_PID, 1);
if (err < 0) {
goto error;
}
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index ab16a5a4cfe..342bca62c49 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -154,7 +154,6 @@ unsigned long kallsyms_lookup_name(const char *name)
}
return module_kallsyms_lookup_name(name);
}
-EXPORT_SYMBOL_GPL(kallsyms_lookup_name);
/*
* Lookup an address
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 842f8015d7f..bb4e29d924e 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -18,8 +18,6 @@
call_usermodehelper wait flag, and remove exec_usermodehelper.
Rusty Russell <rusty@rustcorp.com.au> Jan 2003
*/
-#define __KERNEL_SYSCALLS__
-
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
@@ -35,6 +33,7 @@
#include <linux/mount.h>
#include <linux/kernel.h>
#include <linux/init.h>
+#include <linux/resource.h>
#include <asm/uaccess.h>
extern int max_threads;
@@ -122,6 +121,7 @@ struct subprocess_info {
struct key *ring;
int wait;
int retval;
+ struct file *stdin;
};
/*
@@ -145,12 +145,30 @@ static int ____call_usermodehelper(void *data)
key_put(old_session);
+ /* Install input pipe when needed */
+ if (sub_info->stdin) {
+ struct files_struct *f = current->files;
+ struct fdtable *fdt;
+ /* no races because files should be private here */
+ sys_close(0);
+ fd_install(0, sub_info->stdin);
+ spin_lock(&f->file_lock);
+ fdt = files_fdtable(f);
+ FD_SET(0, fdt->open_fds);
+ FD_CLR(0, fdt->close_on_exec);
+ spin_unlock(&f->file_lock);
+
+ /* and disallow core files too */
+ current->signal->rlim[RLIMIT_CORE] = (struct rlimit){0, 0};
+ }
+
/* We can run anywhere, unlike our parent keventd(). */
set_cpus_allowed(current, CPU_MASK_ALL);
retval = -EPERM;
if (current->fs->root)
- retval = execve(sub_info->path, sub_info->argv,sub_info->envp);
+ retval = kernel_execve(sub_info->path,
+ sub_info->argv, sub_info->envp);
/* Exec failed? */
sub_info->retval = retval;
@@ -268,6 +286,44 @@ int call_usermodehelper_keys(char *path, char **argv, char **envp,
}
EXPORT_SYMBOL(call_usermodehelper_keys);
+int call_usermodehelper_pipe(char *path, char **argv, char **envp,
+ struct file **filp)
+{
+ DECLARE_COMPLETION(done);
+ struct subprocess_info sub_info = {
+ .complete = &done,
+ .path = path,
+ .argv = argv,
+ .envp = envp,
+ .retval = 0,
+ };
+ struct file *f;
+ DECLARE_WORK(work, __call_usermodehelper, &sub_info);
+
+ if (!khelper_wq)
+ return -EBUSY;
+
+ if (path[0] == '\0')
+ return 0;
+
+ f = create_write_pipe();
+ if (!f)
+ return -ENOMEM;
+ *filp = f;
+
+ f = create_read_pipe(f);
+ if (!f) {
+ free_write_pipe(*filp);
+ return -ENOMEM;
+ }
+ sub_info.stdin = f;
+
+ queue_work(khelper_wq, &work);
+ wait_for_completion(&done);
+ return sub_info.retval;
+}
+EXPORT_SYMBOL(call_usermodehelper_pipe);
+
void __init usermodehelper_init(void)
{
khelper_wq = create_singlethread_workqueue("khelper");
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 3f57dfdc8f9..610c837ad9e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -37,6 +37,7 @@
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/moduleloader.h>
+#include <linux/kallsyms.h>
#include <asm-generic/sections.h>
#include <asm/cacheflush.h>
#include <asm/errno.h>
@@ -45,6 +46,16 @@
#define KPROBE_HASH_BITS 6
#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
+
+/*
+ * Some oddball architectures like 64bit powerpc have function descriptors
+ * so this must be overridable.
+ */
+#ifndef kprobe_lookup_name
+#define kprobe_lookup_name(name, addr) \
+ addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name)))
+#endif
+
static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
static atomic_t kprobe_count;
@@ -308,7 +319,8 @@ void __kprobes add_rp_inst(struct kretprobe_instance *ri)
}
/* Called with kretprobe_lock held */
-void __kprobes recycle_rp_inst(struct kretprobe_instance *ri)
+void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
+ struct hlist_head *head)
{
/* remove rp inst off the rprobe_inst_table */
hlist_del(&ri->hlist);
@@ -320,7 +332,7 @@ void __kprobes recycle_rp_inst(struct kretprobe_instance *ri)
hlist_add_head(&ri->uflist, &ri->rp->free_instances);
} else
/* Unregistering */
- kfree(ri);
+ hlist_add_head(&ri->hlist, head);
}
struct hlist_head __kprobes *kretprobe_inst_table_head(struct task_struct *tsk)
@@ -336,18 +348,24 @@ struct hlist_head __kprobes *kretprobe_inst_table_head(struct task_struct *tsk)
*/
void __kprobes kprobe_flush_task(struct task_struct *tk)
{
- struct kretprobe_instance *ri;
- struct hlist_head *head;
+ struct kretprobe_instance *ri;
+ struct hlist_head *head, empty_rp;
struct hlist_node *node, *tmp;
unsigned long flags = 0;
+ INIT_HLIST_HEAD(&empty_rp);
spin_lock_irqsave(&kretprobe_lock, flags);
- head = kretprobe_inst_table_head(tk);
- hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
- if (ri->task == tk)
- recycle_rp_inst(ri);
- }
+ head = kretprobe_inst_table_head(tk);
+ hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+ if (ri->task == tk)
+ recycle_rp_inst(ri, &empty_rp);
+ }
spin_unlock_irqrestore(&kretprobe_lock, flags);
+
+ hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
+ hlist_del(&ri->hlist);
+ kfree(ri);
+ }
}
static inline void free_rp_inst(struct kretprobe *rp)
@@ -447,6 +465,21 @@ static int __kprobes __register_kprobe(struct kprobe *p,
struct kprobe *old_p;
struct module *probed_mod;
+ /*
+ * If we have a symbol_name argument look it up,
+ * and add it to the address. That way the addr
+ * field can either be global or relative to a symbol.
+ */
+ if (p->symbol_name) {
+ if (p->addr)
+ return -EINVAL;
+ kprobe_lookup_name(p->symbol_name, p->addr);
+ }
+
+ if (!p->addr)
+ return -EINVAL;
+ p->addr = (kprobe_opcode_t *)(((char *)p->addr)+ p->offset);
+
if ((!kernel_text_address((unsigned long) p->addr)) ||
in_kprobes_functions((unsigned long) p->addr))
return -EINVAL;
@@ -488,7 +521,7 @@ static int __kprobes __register_kprobe(struct kprobe *p,
(ARCH_INACTIVE_KPROBE_COUNT + 1))
register_page_fault_notifier(&kprobe_page_fault_nb);
- arch_arm_kprobe(p);
+ arch_arm_kprobe(p);
out:
mutex_unlock(&kprobe_mutex);
diff --git a/kernel/latency.c b/kernel/latency.c
new file mode 100644
index 00000000000..258f2555abb
--- /dev/null
+++ b/kernel/latency.c
@@ -0,0 +1,279 @@
+/*
+ * latency.c: Explicit system-wide latency-expectation infrastructure
+ *
+ * The purpose of this infrastructure is to allow device drivers to set
+ * latency constraint they have and to collect and summarize these
+ * expectations globally. The cummulated result can then be used by
+ * power management and similar users to make decisions that have
+ * tradoffs with a latency component.
+ *
+ * An example user of this are the x86 C-states; each higher C state saves
+ * more power, but has a higher exit latency. For the idle loop power
+ * code to make a good decision which C-state to use, information about
+ * acceptable latencies is required.
+ *
+ * An example announcer of latency is an audio driver that knowns it
+ * will get an interrupt when the hardware has 200 usec of samples
+ * left in the DMA buffer; in that case the driver can set a latency
+ * constraint of, say, 150 usec.
+ *
+ * Multiple drivers can each announce their maximum accepted latency,
+ * to keep these appart, a string based identifier is used.
+ *
+ *
+ * (C) Copyright 2006 Intel Corporation
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/latency.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <asm/atomic.h>
+
+struct latency_info {
+ struct list_head list;
+ int usecs;
+ char *identifier;
+};
+
+/*
+ * locking rule: all modifications to current_max_latency and
+ * latency_list need to be done while holding the latency_lock.
+ * latency_lock needs to be taken _irqsave.
+ */
+static atomic_t current_max_latency;
+static DEFINE_SPINLOCK(latency_lock);
+
+static LIST_HEAD(latency_list);
+static BLOCKING_NOTIFIER_HEAD(latency_notifier);
+
+/*
+ * This function returns the maximum latency allowed, which
+ * happens to be the minimum of all maximum latencies on the
+ * list.
+ */
+static int __find_max_latency(void)
+{
+ int min = INFINITE_LATENCY;
+ struct latency_info *info;
+
+ list_for_each_entry(info, &latency_list, list) {
+ if (info->usecs < min)
+ min = info->usecs;
+ }
+ return min;
+}
+
+/**
+ * set_acceptable_latency - sets the maximum latency acceptable
+ * @identifier: string that identifies this driver
+ * @usecs: maximum acceptable latency for this driver
+ *
+ * This function informs the kernel that this device(driver)
+ * can accept at most usecs latency. This setting is used for
+ * power management and similar tradeoffs.
+ *
+ * This function sleeps and can only be called from process
+ * context.
+ * Calling this function with an existing identifier is valid
+ * and will cause the existing latency setting to be changed.
+ */
+void set_acceptable_latency(char *identifier, int usecs)
+{
+ struct latency_info *info, *iter;
+ unsigned long flags;
+ int found_old = 0;
+
+ info = kzalloc(sizeof(struct latency_info), GFP_KERNEL);
+ if (!info)
+ return;
+ info->usecs = usecs;
+ info->identifier = kstrdup(identifier, GFP_KERNEL);
+ if (!info->identifier)
+ goto free_info;
+
+ spin_lock_irqsave(&latency_lock, flags);
+ list_for_each_entry(iter, &latency_list, list) {
+ if (strcmp(iter->identifier, identifier)==0) {
+ found_old = 1;
+ iter->usecs = usecs;
+ break;
+ }
+ }
+ if (!found_old)
+ list_add(&info->list, &latency_list);
+
+ if (usecs < atomic_read(&current_max_latency))
+ atomic_set(&current_max_latency, usecs);
+
+ spin_unlock_irqrestore(&latency_lock, flags);
+
+ blocking_notifier_call_chain(&latency_notifier,
+ atomic_read(&current_max_latency), NULL);
+
+ /*
+ * if we inserted the new one, we're done; otherwise there was
+ * an existing one so we need to free the redundant data
+ */
+ if (!found_old)
+ return;
+
+ kfree(info->identifier);
+free_info:
+ kfree(info);
+}
+EXPORT_SYMBOL_GPL(set_acceptable_latency);
+
+/**
+ * modify_acceptable_latency - changes the maximum latency acceptable
+ * @identifier: string that identifies this driver
+ * @usecs: maximum acceptable latency for this driver
+ *
+ * This function informs the kernel that this device(driver)
+ * can accept at most usecs latency. This setting is used for
+ * power management and similar tradeoffs.
+ *
+ * This function does not sleep and can be called in any context.
+ * Trying to use a non-existing identifier silently gets ignored.
+ *
+ * Due to the atomic nature of this function, the modified latency
+ * value will only be used for future decisions; past decisions
+ * can still lead to longer latencies in the near future.
+ */
+void modify_acceptable_latency(char *identifier, int usecs)
+{
+ struct latency_info *iter;
+ unsigned long flags;
+
+ spin_lock_irqsave(&latency_lock, flags);
+ list_for_each_entry(iter, &latency_list, list) {
+ if (strcmp(iter->identifier, identifier) == 0) {
+ iter->usecs = usecs;
+ break;
+ }
+ }
+ if (usecs < atomic_read(&current_max_latency))
+ atomic_set(&current_max_latency, usecs);
+ spin_unlock_irqrestore(&latency_lock, flags);
+}
+EXPORT_SYMBOL_GPL(modify_acceptable_latency);
+
+/**
+ * remove_acceptable_latency - removes the maximum latency acceptable
+ * @identifier: string that identifies this driver
+ *
+ * This function removes a previously set maximum latency setting
+ * for the driver and frees up any resources associated with the
+ * bookkeeping needed for this.
+ *
+ * This function does not sleep and can be called in any context.
+ * Trying to use a non-existing identifier silently gets ignored.
+ */
+void remove_acceptable_latency(char *identifier)
+{
+ unsigned long flags;
+ int newmax = 0;
+ struct latency_info *iter, *temp;
+
+ spin_lock_irqsave(&latency_lock, flags);
+
+ list_for_each_entry_safe(iter, temp, &latency_list, list) {
+ if (strcmp(iter->identifier, identifier) == 0) {
+ list_del(&iter->list);
+ newmax = iter->usecs;
+ kfree(iter->identifier);
+ kfree(iter);
+ break;
+ }
+ }
+
+ /* If we just deleted the system wide value, we need to
+ * recalculate with a full search
+ */
+ if (newmax == atomic_read(&current_max_latency)) {
+ newmax = __find_max_latency();
+ atomic_set(&current_max_latency, newmax);
+ }
+ spin_unlock_irqrestore(&latency_lock, flags);
+}
+EXPORT_SYMBOL_GPL(remove_acceptable_latency);
+
+/**
+ * system_latency_constraint - queries the system wide latency maximum
+ *
+ * This function returns the system wide maximum latency in
+ * microseconds.
+ *
+ * This function does not sleep and can be called in any context.
+ */
+int system_latency_constraint(void)
+{
+ return atomic_read(&current_max_latency);
+}
+EXPORT_SYMBOL_GPL(system_latency_constraint);
+
+/**
+ * synchronize_acceptable_latency - recalculates all latency decisions
+ *
+ * This function will cause a callback to various kernel pieces that
+ * will make those pieces rethink their latency decisions. This implies
+ * that if there are overlong latencies in hardware state already, those
+ * latencies get taken right now. When this call completes no overlong
+ * latency decisions should be active anymore.
+ *
+ * Typical usecase of this is after a modify_acceptable_latency() call,
+ * which in itself is non-blocking and non-synchronizing.
+ *
+ * This function blocks and should not be called with locks held.
+ */
+
+void synchronize_acceptable_latency(void)
+{
+ blocking_notifier_call_chain(&latency_notifier,
+ atomic_read(&current_max_latency), NULL);
+}
+EXPORT_SYMBOL_GPL(synchronize_acceptable_latency);
+
+/*
+ * Latency notifier: this notifier gets called when a non-atomic new
+ * latency value gets set. The expectation nof the caller of the
+ * non-atomic set is that when the call returns, future latencies
+ * are within bounds, so the functions on the notifier list are
+ * expected to take the overlong latencies immediately, inside the
+ * callback, and not make a overlong latency decision anymore.
+ *
+ * The callback gets called when the new latency value is made
+ * active so system_latency_constraint() returns the new latency.
+ */
+int register_latency_notifier(struct notifier_block * nb)
+{
+ return blocking_notifier_chain_register(&latency_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(register_latency_notifier);
+
+int unregister_latency_notifier(struct notifier_block * nb)
+{
+ return blocking_notifier_chain_unregister(&latency_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_latency_notifier);
+
+static __init int latency_init(void)
+{
+ atomic_set(&current_max_latency, INFINITE_LATENCY);
+ /*
+ * we don't want by default to have longer latencies than 2 ticks,
+ * since that would cause lost ticks
+ */
+ set_acceptable_latency("kernel", 2*1000000/HZ);
+ return 0;
+}
+
+module_init(latency_init);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index e596525669e..4c055346100 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -518,9 +518,9 @@ print_circular_bug_entry(struct lock_list *target, unsigned int depth)
static void print_kernel_version(void)
{
- printk("%s %.*s\n", system_utsname.release,
- (int)strcspn(system_utsname.version, " "),
- system_utsname.version);
+ printk("%s %.*s\n", init_utsname()->release,
+ (int)strcspn(init_utsname()->version, " "),
+ init_utsname()->version);
}
/*
diff --git a/kernel/module.c b/kernel/module.c
index 05625d5dc75..7c77a0a9275 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -851,6 +851,7 @@ static int check_version(Elf_Shdr *sechdrs,
printk("%s: no version for \"%s\" found: kernel tainted.\n",
mod->name, symname);
add_taint(TAINT_FORCED_MODULE);
+ mod->taints |= TAINT_FORCED_MODULE;
}
return 1;
}
@@ -1339,6 +1340,7 @@ static void set_license(struct module *mod, const char *license)
printk(KERN_WARNING "%s: module license '%s' taints kernel.\n",
mod->name, license);
add_taint(TAINT_PROPRIETARY_MODULE);
+ mod->taints |= TAINT_PROPRIETARY_MODULE;
}
}
@@ -1618,6 +1620,7 @@ static struct module *load_module(void __user *umod,
/* This is allowed: modprobe --force will invalidate it. */
if (!modmagic) {
add_taint(TAINT_FORCED_MODULE);
+ mod->taints |= TAINT_FORCED_MODULE;
printk(KERN_WARNING "%s: no version magic, tainting kernel.\n",
mod->name);
} else if (!same_magic(modmagic, vermagic)) {
@@ -1711,10 +1714,14 @@ static struct module *load_module(void __user *umod,
/* Set up license info based on the info section */
set_license(mod, get_modinfo(sechdrs, infoindex, "license"));
- if (strcmp(mod->name, "ndiswrapper") == 0)
+ if (strcmp(mod->name, "ndiswrapper") == 0) {
add_taint(TAINT_PROPRIETARY_MODULE);
- if (strcmp(mod->name, "driverloader") == 0)
+ mod->taints |= TAINT_PROPRIETARY_MODULE;
+ }
+ if (strcmp(mod->name, "driverloader") == 0) {
add_taint(TAINT_PROPRIETARY_MODULE);
+ mod->taints |= TAINT_PROPRIETARY_MODULE;
+ }
/* Set up MODINFO_ATTR fields */
setup_modinfo(mod, sechdrs, infoindex);
@@ -1760,6 +1767,7 @@ static struct module *load_module(void __user *umod,
printk(KERN_WARNING "%s: No versions for exported symbols."
" Tainting kernel.\n", mod->name);
add_taint(TAINT_FORCED_MODULE);
+ mod->taints |= TAINT_FORCED_MODULE;
}
#endif
@@ -2226,14 +2234,37 @@ struct module *module_text_address(unsigned long addr)
return mod;
}
+static char *taint_flags(unsigned int taints, char *buf)
+{
+ *buf = '\0';
+ if (taints) {
+ int bx;
+
+ buf[0] = '(';
+ bx = 1;
+ if (taints & TAINT_PROPRIETARY_MODULE)
+ buf[bx++] = 'P';
+ if (taints & TAINT_FORCED_MODULE)
+ buf[bx++] = 'F';
+ /*
+ * TAINT_FORCED_RMMOD: could be added.
+ * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
+ * apply to modules.
+ */
+ buf[bx] = ')';
+ }
+ return buf;
+}
+
/* Don't grab lock, we're oopsing. */
void print_modules(void)
{
struct module *mod;
+ char buf[8];
printk("Modules linked in:");
list_for_each_entry(mod, &modules, list)
- printk(" %s", mod->name);
+ printk(" %s%s", mod->name, taint_flags(mod->taints, buf));
printk("\n");
}
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
new file mode 100644
index 00000000000..6ebdb82a0ce
--- /dev/null
+++ b/kernel/nsproxy.c
@@ -0,0 +1,139 @@
+/*
+ * Copyright (C) 2006 IBM Corporation
+ *
+ * Author: Serge Hallyn <serue@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ *
+ * Jun 2006 - namespaces support
+ * OpenVZ, SWsoft Inc.
+ * Pavel Emelianov <xemul@openvz.org>
+ */
+
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/nsproxy.h>
+#include <linux/init_task.h>
+#include <linux/namespace.h>
+#include <linux/utsname.h>
+
+struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
+
+static inline void get_nsproxy(struct nsproxy *ns)
+{
+ atomic_inc(&ns->count);
+}
+
+void get_task_namespaces(struct task_struct *tsk)
+{
+ struct nsproxy *ns = tsk->nsproxy;
+ if (ns) {
+ get_nsproxy(ns);
+ }
+}
+
+/*
+ * creates a copy of "orig" with refcount 1.
+ * This does not grab references to the contained namespaces,
+ * so that needs to be done by dup_namespaces.
+ */
+static inline struct nsproxy *clone_namespaces(struct nsproxy *orig)
+{
+ struct nsproxy *ns;
+
+ ns = kmalloc(sizeof(struct nsproxy), GFP_KERNEL);
+ if (ns) {
+ memcpy(ns, orig, sizeof(struct nsproxy));
+ atomic_set(&ns->count, 1);
+ }
+ return ns;
+}
+
+/*
+ * copies the nsproxy, setting refcount to 1, and grabbing a
+ * reference to all contained namespaces. Called from
+ * sys_unshare()
+ */
+struct nsproxy *dup_namespaces(struct nsproxy *orig)
+{
+ struct nsproxy *ns = clone_namespaces(orig);
+
+ if (ns) {
+ if (ns->namespace)
+ get_namespace(ns->namespace);
+ if (ns->uts_ns)
+ get_uts_ns(ns->uts_ns);
+ if (ns->ipc_ns)
+ get_ipc_ns(ns->ipc_ns);
+ }
+
+ return ns;
+}
+
+/*
+ * called from clone. This now handles copy for nsproxy and all
+ * namespaces therein.
+ */
+int copy_namespaces(int flags, struct task_struct *tsk)
+{
+ struct nsproxy *old_ns = tsk->nsproxy;
+ struct nsproxy *new_ns;
+ int err = 0;
+
+ if (!old_ns)
+ return 0;
+
+ get_nsproxy(old_ns);
+
+ if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC)))
+ return 0;
+
+ new_ns = clone_namespaces(old_ns);
+ if (!new_ns) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ tsk->nsproxy = new_ns;
+
+ err = copy_namespace(flags, tsk);
+ if (err)
+ goto out_ns;
+
+ err = copy_utsname(flags, tsk);
+ if (err)
+ goto out_uts;
+
+ err = copy_ipcs(flags, tsk);
+ if (err)
+ goto out_ipc;
+
+out:
+ put_nsproxy(old_ns);
+ return err;
+
+out_ipc:
+ if (new_ns->uts_ns)
+ put_uts_ns(new_ns->uts_ns);
+out_uts:
+ if (new_ns->namespace)
+ put_namespace(new_ns->namespace);
+out_ns:
+ tsk->nsproxy = old_ns;
+ kfree(new_ns);
+ goto out;
+}
+
+void free_nsproxy(struct nsproxy *ns)
+{
+ if (ns->namespace)
+ put_namespace(ns->namespace);
+ if (ns->uts_ns)
+ put_uts_ns(ns->uts_ns);
+ if (ns->ipc_ns)
+ put_ipc_ns(ns->ipc_ns);
+ kfree(ns);
+}
diff --git a/kernel/pid.c b/kernel/pid.c
index 8387e8c6819..b914392085f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -26,6 +26,7 @@
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/hash.h>
+#include <linux/pspace.h>
#define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift)
static struct hlist_head *pid_hash;
@@ -33,17 +34,20 @@ static int pidhash_shift;
static kmem_cache_t *pid_cachep;
int pid_max = PID_MAX_DEFAULT;
-int last_pid;
#define RESERVED_PIDS 300
int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;
-#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8)
#define BITS_PER_PAGE (PAGE_SIZE*8)
#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1)
-#define mk_pid(map, off) (((map) - pidmap_array)*BITS_PER_PAGE + (off))
+
+static inline int mk_pid(struct pspace *pspace, struct pidmap *map, int off)
+{
+ return (map - pspace->pidmap)*BITS_PER_PAGE + off;
+}
+
#define find_next_offset(map, off) \
find_next_zero_bit((map)->page, BITS_PER_PAGE, off)
@@ -53,13 +57,12 @@ int pid_max_max = PID_MAX_LIMIT;
* value does not cause lots of bitmaps to be allocated, but
* the scheme scales to up to 4 million PIDs, runtime.
*/
-typedef struct pidmap {
- atomic_t nr_free;
- void *page;
-} pidmap_t;
-
-static pidmap_t pidmap_array[PIDMAP_ENTRIES] =
- { [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } };
+struct pspace init_pspace = {
+ .pidmap = {
+ [ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
+ },
+ .last_pid = 0
+};
/*
* Note: disable interrupts while the pidmap_lock is held as an
@@ -74,40 +77,41 @@ static pidmap_t pidmap_array[PIDMAP_ENTRIES] =
* irq handlers that take it we can leave the interrupts enabled.
* For now it is easier to be safe than to prove it can't happen.
*/
+
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
-static fastcall void free_pidmap(int pid)
+static fastcall void free_pidmap(struct pspace *pspace, int pid)
{
- pidmap_t *map = pidmap_array + pid / BITS_PER_PAGE;
+ struct pidmap *map = pspace->pidmap + pid / BITS_PER_PAGE;
int offset = pid & BITS_PER_PAGE_MASK;
clear_bit(offset, map->page);
atomic_inc(&map->nr_free);
}
-static int alloc_pidmap(void)
+static int alloc_pidmap(struct pspace *pspace)
{
- int i, offset, max_scan, pid, last = last_pid;
- pidmap_t *map;
+ int i, offset, max_scan, pid, last = pspace->last_pid;
+ struct pidmap *map;
pid = last + 1;
if (pid >= pid_max)
pid = RESERVED_PIDS;
offset = pid & BITS_PER_PAGE_MASK;
- map = &pidmap_array[pid/BITS_PER_PAGE];
+ map = &pspace->pidmap[pid/BITS_PER_PAGE];
max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset;
for (i = 0; i <= max_scan; ++i) {
if (unlikely(!map->page)) {
- unsigned long page = get_zeroed_page(GFP_KERNEL);
+ void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
/*
* Free the page if someone raced with us
* installing it:
*/
spin_lock_irq(&pidmap_lock);
if (map->page)
- free_page(page);
+ kfree(page);
else
- map->page = (void *)page;
+ map->page = page;
spin_unlock_irq(&pidmap_lock);
if (unlikely(!map->page))
break;
@@ -116,11 +120,11 @@ static int alloc_pidmap(void)
do {
if (!test_and_set_bit(offset, map->page)) {
atomic_dec(&map->nr_free);
- last_pid = pid;
+ pspace->last_pid = pid;
return pid;
}
offset = find_next_offset(map, offset);
- pid = mk_pid(map, offset);
+ pid = mk_pid(pspace, map, offset);
/*
* find_next_offset() found a bit, the pid from it
* is in-bounds, and if we fell back to the last
@@ -131,16 +135,34 @@ static int alloc_pidmap(void)
(i != max_scan || pid < last ||
!((last+1) & BITS_PER_PAGE_MASK)));
}
- if (map < &pidmap_array[(pid_max-1)/BITS_PER_PAGE]) {
+ if (map < &pspace->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
++map;
offset = 0;
} else {
- map = &pidmap_array[0];
+ map = &pspace->pidmap[0];
offset = RESERVED_PIDS;
if (unlikely(last == offset))
break;
}
- pid = mk_pid(map, offset);
+ pid = mk_pid(pspace, map, offset);
+ }
+ return -1;
+}
+
+static int next_pidmap(struct pspace *pspace, int last)
+{
+ int offset;
+ struct pidmap *map, *end;
+
+ offset = (last + 1) & BITS_PER_PAGE_MASK;
+ map = &pspace->pidmap[(last + 1)/BITS_PER_PAGE];
+ end = &pspace->pidmap[PIDMAP_ENTRIES];
+ for (; map < end; map++, offset = 0) {
+ if (unlikely(!map->page))
+ continue;
+ offset = find_next_bit((map)->page, BITS_PER_PAGE, offset);
+ if (offset < BITS_PER_PAGE)
+ return mk_pid(pspace, map, offset);
}
return -1;
}
@@ -153,6 +175,7 @@ fastcall void put_pid(struct pid *pid)
atomic_dec_and_test(&pid->count))
kmem_cache_free(pid_cachep, pid);
}
+EXPORT_SYMBOL_GPL(put_pid);
static void delayed_put_pid(struct rcu_head *rhp)
{
@@ -169,7 +192,7 @@ fastcall void free_pid(struct pid *pid)
hlist_del_rcu(&pid->pid_chain);
spin_unlock_irqrestore(&pidmap_lock, flags);
- free_pidmap(pid->nr);
+ free_pidmap(&init_pspace, pid->nr);
call_rcu(&pid->rcu, delayed_put_pid);
}
@@ -183,7 +206,7 @@ struct pid *alloc_pid(void)
if (!pid)
goto out;
- nr = alloc_pidmap();
+ nr = alloc_pidmap(&init_pspace);
if (nr < 0)
goto out_free;
@@ -217,6 +240,7 @@ struct pid * fastcall find_pid(int nr)
}
return NULL;
}
+EXPORT_SYMBOL_GPL(find_pid);
int fastcall attach_pid(struct task_struct *task, enum pid_type type, int nr)
{
@@ -280,6 +304,15 @@ struct task_struct *find_task_by_pid_type(int type, int nr)
EXPORT_SYMBOL(find_task_by_pid_type);
+struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
+{
+ struct pid *pid;
+ rcu_read_lock();
+ pid = get_pid(task->pids[type].pid);
+ rcu_read_unlock();
+ return pid;
+}
+
struct task_struct *fastcall get_pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result;
@@ -303,6 +336,26 @@ struct pid *find_get_pid(pid_t nr)
}
/*
+ * Used by proc to find the first pid that is greater then or equal to nr.
+ *
+ * If there is a pid at nr this function is exactly the same as find_pid.
+ */
+struct pid *find_ge_pid(int nr)
+{
+ struct pid *pid;
+
+ do {
+ pid = find_pid(nr);
+ if (pid)
+ break;
+ nr = next_pidmap(&init_pspace, nr);
+ } while (nr > 0);
+
+ return pid;
+}
+EXPORT_SYMBOL_GPL(find_get_pid);
+
+/*
* The pid hash table is scaled according to the amount of memory in the
* machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or
* more.
@@ -329,10 +382,10 @@ void __init pidhash_init(void)
void __init pidmap_init(void)
{
- pidmap_array->page = (void *)get_zeroed_page(GFP_KERNEL);
+ init_pspace.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
/* Reserve PID 0. We never call free_pidmap(0) */
- set_bit(0, pidmap_array->page);
- atomic_dec(&pidmap_array->nr_free);
+ set_bit(0, init_pspace.pidmap[0].page);
+ atomic_dec(&init_pspace.pidmap[0].nr_free);
pid_cachep = kmem_cache_create("pid", sizeof(struct pid),
__alignof__(struct pid),
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 1b84313cbab..99f9b7d177d 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -906,7 +906,7 @@ static void init_header(struct swsusp_info *info)
memset(info, 0, sizeof(struct swsusp_info));
info->version_code = LINUX_VERSION_CODE;
info->num_physpages = num_physpages;
- memcpy(&info->uts, &system_utsname, sizeof(system_utsname));
+ memcpy(&info->uts, init_utsname(), sizeof(struct new_utsname));
info->cpus = num_online_cpus();
info->image_pages = nr_copy_pages;
info->pages = nr_copy_pages + nr_meta_pages + 1;
@@ -1050,13 +1050,13 @@ static inline int check_header(struct swsusp_info *info)
reason = "kernel version";
if (info->num_physpages != num_physpages)
reason = "memory size";
- if (strcmp(info->uts.sysname,system_utsname.sysname))
+ if (strcmp(info->uts.sysname,init_utsname()->sysname))
reason = "system type";
- if (strcmp(info->uts.release,system_utsname.release))
+ if (strcmp(info->uts.release,init_utsname()->release))
reason = "kernel release";
- if (strcmp(info->uts.version,system_utsname.version))
+ if (strcmp(info->uts.version,init_utsname()->version))
reason = "version";
- if (strcmp(info->uts.machine,system_utsname.machine))
+ if (strcmp(info->uts.machine,init_utsname()->machine))
reason = "machine";
if (reason) {
printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason);
diff --git a/kernel/sched.c b/kernel/sched.c
index 74f169ac077..e4e54e86f4a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -49,7 +49,7 @@
#include <linux/seq_file.h>
#include <linux/syscalls.h>
#include <linux/times.h>
-#include <linux/acct.h>
+#include <linux/tsacct_kern.h>
#include <linux/kprobes.h>
#include <linux/delayacct.h>
#include <asm/tlb.h>
@@ -4384,7 +4384,10 @@ EXPORT_SYMBOL(cpu_present_map);
#ifndef CONFIG_SMP
cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_online_map);
+
cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_possible_map);
#endif
long sched_getaffinity(pid_t pid, cpumask_t *mask)
diff --git a/kernel/signal.c b/kernel/signal.c
index fb5da6d19f1..7ed8d5304be 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1055,28 +1055,44 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
}
/*
- * kill_pg_info() sends a signal to a process group: this is what the tty
+ * kill_pgrp_info() sends a signal to a process group: this is what the tty
* control characters do (^C, ^Z etc)
*/
-int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp)
+int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
{
struct task_struct *p = NULL;
int retval, success;
- if (pgrp <= 0)
- return -EINVAL;
-
success = 0;
retval = -ESRCH;
- do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
+ do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
int err = group_send_sig_info(sig, info, p);
success |= !err;
retval = err;
- } while_each_task_pid(pgrp, PIDTYPE_PGID, p);
+ } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
return success ? 0 : retval;
}
+int kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
+{
+ int retval;
+
+ read_lock(&tasklist_lock);
+ retval = __kill_pgrp_info(sig, info, pgrp);
+ read_unlock(&tasklist_lock);
+
+ return retval;
+}
+
+int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp)
+{
+ if (pgrp <= 0)
+ return -EINVAL;
+
+ return __kill_pgrp_info(sig, info, find_pid(pgrp));
+}
+
int
kill_pg_info(int sig, struct siginfo *info, pid_t pgrp)
{
@@ -1089,8 +1105,7 @@ kill_pg_info(int sig, struct siginfo *info, pid_t pgrp)
return retval;
}
-int
-kill_proc_info(int sig, struct siginfo *info, pid_t pid)
+int kill_pid_info(int sig, struct siginfo *info, struct pid *pid)
{
int error;
int acquired_tasklist_lock = 0;
@@ -1101,7 +1116,7 @@ kill_proc_info(int sig, struct siginfo *info, pid_t pid)
read_lock(&tasklist_lock);
acquired_tasklist_lock = 1;
}
- p = find_task_by_pid(pid);
+ p = pid_task(pid, PIDTYPE_PID);
error = -ESRCH;
if (p)
error = group_send_sig_info(sig, info, p);
@@ -1111,8 +1126,18 @@ kill_proc_info(int sig, struct siginfo *info, pid_t pid)
return error;
}
-/* like kill_proc_info(), but doesn't use uid/euid of "current" */
-int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid,
+int
+kill_proc_info(int sig, struct siginfo *info, pid_t pid)
+{
+ int error;
+ rcu_read_lock();
+ error = kill_pid_info(sig, info, find_pid(pid));
+ rcu_read_unlock();
+ return error;
+}
+
+/* like kill_pid_info(), but doesn't use uid/euid of "current" */
+int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
uid_t uid, uid_t euid, u32 secid)
{
int ret = -EINVAL;
@@ -1122,7 +1147,7 @@ int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid,
return ret;
read_lock(&tasklist_lock);
- p = find_task_by_pid(pid);
+ p = pid_task(pid, PIDTYPE_PID);
if (!p) {
ret = -ESRCH;
goto out_unlock;
@@ -1146,7 +1171,7 @@ out_unlock:
read_unlock(&tasklist_lock);
return ret;
}
-EXPORT_SYMBOL_GPL(kill_proc_info_as_uid);
+EXPORT_SYMBOL_GPL(kill_pid_info_as_uid);
/*
* kill_something_info() interprets pid in interesting ways just like kill(2).
@@ -1264,6 +1289,18 @@ force_sigsegv(int sig, struct task_struct *p)
return 0;
}
+int kill_pgrp(struct pid *pid, int sig, int priv)
+{
+ return kill_pgrp_info(sig, __si_special(priv), pid);
+}
+EXPORT_SYMBOL(kill_pgrp);
+
+int kill_pid(struct pid *pid, int sig, int priv)
+{
+ return kill_pid_info(sig, __si_special(priv), pid);
+}
+EXPORT_SYMBOL(kill_pid);
+
int
kill_pg(pid_t pgrp, int sig, int priv)
{
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index d48143eafbf..476c3741511 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -215,7 +215,7 @@ void __lockfunc _##op##_lock(locktype##_t *lock) \
if (!(lock)->break_lock) \
(lock)->break_lock = 1; \
while (!op##_can_lock(lock) && (lock)->break_lock) \
- cpu_relax(); \
+ _raw_##op##_relax(&lock->raw_lock); \
} \
(lock)->break_lock = 0; \
} \
@@ -237,7 +237,7 @@ unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock) \
if (!(lock)->break_lock) \
(lock)->break_lock = 1; \
while (!op##_can_lock(lock) && (lock)->break_lock) \
- cpu_relax(); \
+ _raw_##op##_relax(&lock->raw_lock); \
} \
(lock)->break_lock = 0; \
return flags; \
diff --git a/kernel/sys.c b/kernel/sys.c
index b88806c6624..2314867ae34 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -92,7 +92,8 @@ EXPORT_SYMBOL(fs_overflowgid);
*/
int C_A_D = 1;
-int cad_pid = 1;
+struct pid *cad_pid;
+EXPORT_SYMBOL(cad_pid);
/*
* Notifier list for kernel code which wants to be called
@@ -221,7 +222,7 @@ EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
* of the last notifier function called.
*/
-int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
+int __kprobes atomic_notifier_call_chain(struct atomic_notifier_head *nh,
unsigned long val, void *v)
{
int ret;
@@ -607,11 +608,10 @@ static void kernel_restart_prepare(char *cmd)
void kernel_restart(char *cmd)
{
kernel_restart_prepare(cmd);
- if (!cmd) {
+ if (!cmd)
printk(KERN_EMERG "Restarting system.\n");
- } else {
+ else
printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
- }
machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);
@@ -627,9 +627,8 @@ static void kernel_kexec(void)
#ifdef CONFIG_KEXEC
struct kimage *image;
image = xchg(&kexec_image, NULL);
- if (!image) {
+ if (!image)
return;
- }
kernel_restart_prepare(NULL);
printk(KERN_EMERG "Starting new kernel\n");
machine_shutdown();
@@ -775,10 +774,9 @@ void ctrl_alt_del(void)
if (C_A_D)
schedule_work(&cad_work);
else
- kill_proc(cad_pid, SIGINT, 1);
+ kill_cad_pid(SIGINT, 1);
}
-
/*
* Unprivileged users may change the real gid to the effective gid
* or vice versa. (BSD-style)
@@ -823,12 +821,10 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
(current->sgid == egid) ||
capable(CAP_SETGID))
new_egid = egid;
- else {
+ else
return -EPERM;
- }
}
- if (new_egid != old_egid)
- {
+ if (new_egid != old_egid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -857,19 +853,14 @@ asmlinkage long sys_setgid(gid_t gid)
if (retval)
return retval;
- if (capable(CAP_SETGID))
- {
- if(old_egid != gid)
- {
+ if (capable(CAP_SETGID)) {
+ if (old_egid != gid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
current->gid = current->egid = current->sgid = current->fsgid = gid;
- }
- else if ((gid == current->gid) || (gid == current->sgid))
- {
- if(old_egid != gid)
- {
+ } else if ((gid == current->gid) || (gid == current->sgid)) {
+ if (old_egid != gid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -900,8 +891,7 @@ static int set_user(uid_t new_ruid, int dumpclear)
switch_uid(new_user);
- if(dumpclear)
- {
+ if (dumpclear) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -957,8 +947,7 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
return -EAGAIN;
- if (new_euid != old_euid)
- {
+ if (new_euid != old_euid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -1008,8 +997,7 @@ asmlinkage long sys_setuid(uid_t uid)
} else if ((uid != current->uid) && (uid != new_suid))
return -EPERM;
- if (old_euid != uid)
- {
+ if (old_euid != uid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -1054,8 +1042,7 @@ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
return -EAGAIN;
}
if (euid != (uid_t) -1) {
- if (euid != current->euid)
- {
+ if (euid != current->euid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -1105,8 +1092,7 @@ asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
return -EPERM;
}
if (egid != (gid_t) -1) {
- if (egid != current->egid)
- {
+ if (egid != current->egid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -1151,10 +1137,8 @@ asmlinkage long sys_setfsuid(uid_t uid)
if (uid == current->uid || uid == current->euid ||
uid == current->suid || uid == current->fsuid ||
- capable(CAP_SETUID))
- {
- if (uid != old_fsuid)
- {
+ capable(CAP_SETUID)) {
+ if (uid != old_fsuid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -1182,10 +1166,8 @@ asmlinkage long sys_setfsgid(gid_t gid)
if (gid == current->gid || gid == current->egid ||
gid == current->sgid || gid == current->fsgid ||
- capable(CAP_SETGID))
- {
- if (gid != old_fsgid)
- {
+ capable(CAP_SETGID)) {
+ if (gid != old_fsgid) {
current->mm->dumpable = suid_dumpable;
smp_wmb();
}
@@ -1321,9 +1303,9 @@ out:
asmlinkage long sys_getpgid(pid_t pid)
{
- if (!pid) {
+ if (!pid)
return process_group(current);
- } else {
+ else {
int retval;
struct task_struct *p;
@@ -1353,9 +1335,9 @@ asmlinkage long sys_getpgrp(void)
asmlinkage long sys_getsid(pid_t pid)
{
- if (!pid) {
+ if (!pid)
return current->signal->session;
- } else {
+ else {
int retval;
struct task_struct *p;
@@ -1363,7 +1345,7 @@ asmlinkage long sys_getsid(pid_t pid)
p = find_task_by_pid(pid);
retval = -ESRCH;
- if(p) {
+ if (p) {
retval = security_task_getsid(p);
if (!retval)
retval = p->signal->session;
@@ -1431,9 +1413,9 @@ struct group_info *groups_alloc(int gidsetsize)
group_info->nblocks = nblocks;
atomic_set(&group_info->usage, 1);
- if (gidsetsize <= NGROUPS_SMALL) {
+ if (gidsetsize <= NGROUPS_SMALL)
group_info->blocks[0] = group_info->small_block;
- } else {
+ else {
for (i = 0; i < nblocks; i++) {
gid_t *b;
b = (void *)__get_free_page(GFP_USER);
@@ -1489,7 +1471,7 @@ static int groups_to_user(gid_t __user *grouplist,
/* fill a group_info from a user-space array - it must be allocated already */
static int groups_from_user(struct group_info *group_info,
gid_t __user *grouplist)
- {
+{
int i;
int count = group_info->ngroups;
@@ -1647,9 +1629,8 @@ asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
int in_group_p(gid_t grp)
{
int retval = 1;
- if (grp != current->fsgid) {
+ if (grp != current->fsgid)
retval = groups_search(current->group_info, grp);
- }
return retval;
}
@@ -1658,9 +1639,8 @@ EXPORT_SYMBOL(in_group_p);
int in_egroup_p(gid_t grp)
{
int retval = 1;
- if (grp != current->egid) {
+ if (grp != current->egid)
retval = groups_search(current->group_info, grp);
- }
return retval;
}
@@ -1675,7 +1655,7 @@ asmlinkage long sys_newuname(struct new_utsname __user * name)
int errno = 0;
down_read(&uts_sem);
- if (copy_to_user(name,&system_utsname,sizeof *name))
+ if (copy_to_user(name, utsname(), sizeof *name))
errno = -EFAULT;
up_read(&uts_sem);
return errno;
@@ -1693,8 +1673,8 @@ asmlinkage long sys_sethostname(char __user *name, int len)
down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
- memcpy(system_utsname.nodename, tmp, len);
- system_utsname.nodename[len] = 0;
+ memcpy(utsname()->nodename, tmp, len);
+ utsname()->nodename[len] = 0;
errno = 0;
}
up_write(&uts_sem);
@@ -1710,11 +1690,11 @@ asmlinkage long sys_gethostname(char __user *name, int len)
if (len < 0)
return -EINVAL;
down_read(&uts_sem);
- i = 1 + strlen(system_utsname.nodename);
+ i = 1 + strlen(utsname()->nodename);
if (i > len)
i = len;
errno = 0;
- if (copy_to_user(name, system_utsname.nodename, i))
+ if (copy_to_user(name, utsname()->nodename, i))
errno = -EFAULT;
up_read(&uts_sem);
return errno;
@@ -1739,8 +1719,8 @@ asmlinkage long sys_setdomainname(char __user *name, int len)
down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
- memcpy(system_utsname.domainname, tmp, len);
- system_utsname.domainname[len] = 0;
+ memcpy(utsname()->domainname, tmp, len);
+ utsname()->domainname[len] = 0;
errno = 0;
}
up_write(&uts_sem);
@@ -1775,9 +1755,9 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
task_lock(current->group_leader);
x = current->signal->rlim[resource];
task_unlock(current->group_leader);
- if(x.rlim_cur > 0x7FFFFFFF)
+ if (x.rlim_cur > 0x7FFFFFFF)
x.rlim_cur = 0x7FFFFFFF;
- if(x.rlim_max > 0x7FFFFFFF)
+ if (x.rlim_max > 0x7FFFFFFF)
x.rlim_max = 0x7FFFFFFF;
return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c57c4532e29..8020fb273c4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -68,7 +68,6 @@ extern int sysrq_enabled;
extern int core_uses_pid;
extern int suid_dumpable;
extern char core_pattern[];
-extern int cad_pid;
extern int pid_max;
extern int min_free_kbytes;
extern int printk_ratelimit_jiffies;
@@ -92,13 +91,8 @@ extern char modprobe_path[];
extern int sg_big_buff;
#endif
#ifdef CONFIG_SYSVIPC
-extern size_t shm_ctlmax;
-extern size_t shm_ctlall;
-extern int shm_ctlmni;
-extern int msg_ctlmax;
-extern int msg_ctlmnb;
-extern int msg_ctlmni;
-extern int sem_ctls[];
+static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
#ifdef __sparc__
@@ -139,7 +133,10 @@ static int parse_table(int __user *, int, void __user *, size_t __user *,
void __user *, size_t, ctl_table *, void **);
#endif
-static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
+
+static int proc_do_cad_pid(ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos);
static ctl_table root_table[];
@@ -229,51 +226,100 @@ static ctl_table root_table[] = {
};
static ctl_table kern_table[] = {
+#ifndef CONFIG_UTS_NS
+ {
+ .ctl_name = KERN_OSTYPE,
+ .procname = "ostype",
+ .data = init_uts_ns.name.sysname,
+ .maxlen = sizeof(init_uts_ns.name.sysname),
+ .mode = 0444,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+ {
+ .ctl_name = KERN_OSRELEASE,
+ .procname = "osrelease",
+ .data = init_uts_ns.name.release,
+ .maxlen = sizeof(init_uts_ns.name.release),
+ .mode = 0444,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+ {
+ .ctl_name = KERN_VERSION,
+ .procname = "version",
+ .data = init_uts_ns.name.version,
+ .maxlen = sizeof(init_uts_ns.name.version),
+ .mode = 0444,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+ {
+ .ctl_name = KERN_NODENAME,
+ .procname = "hostname",
+ .data = init_uts_ns.name.nodename,
+ .maxlen = sizeof(init_uts_ns.name.nodename),
+ .mode = 0644,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+ {
+ .ctl_name = KERN_DOMAINNAME,
+ .procname = "domainname",
+ .data = init_uts_ns.name.domainname,
+ .maxlen = sizeof(init_uts_ns.name.domainname),
+ .mode = 0644,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+#else /* !CONFIG_UTS_NS */
{
.ctl_name = KERN_OSTYPE,
.procname = "ostype",
- .data = system_utsname.sysname,
- .maxlen = sizeof(system_utsname.sysname),
+ .data = NULL,
+ /* could maybe use __NEW_UTS_LEN here? */
+ .maxlen = FIELD_SIZEOF(struct new_utsname, sysname),
.mode = 0444,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
{
.ctl_name = KERN_OSRELEASE,
.procname = "osrelease",
- .data = system_utsname.release,
- .maxlen = sizeof(system_utsname.release),
+ .data = NULL,
+ .maxlen = FIELD_SIZEOF(struct new_utsname, release),
.mode = 0444,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
{
.ctl_name = KERN_VERSION,
.procname = "version",
- .data = system_utsname.version,
- .maxlen = sizeof(system_utsname.version),
+ .data = NULL,
+ .maxlen = FIELD_SIZEOF(struct new_utsname, version),
.mode = 0444,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
{
.ctl_name = KERN_NODENAME,
.procname = "hostname",
- .data = system_utsname.nodename,
- .maxlen = sizeof(system_utsname.nodename),
+ .data = NULL,
+ .maxlen = FIELD_SIZEOF(struct new_utsname, nodename),
.mode = 0644,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
{
.ctl_name = KERN_DOMAINNAME,
.procname = "domainname",
- .data = system_utsname.domainname,
- .maxlen = sizeof(system_utsname.domainname),
+ .data = NULL,
+ .maxlen = FIELD_SIZEOF(struct new_utsname, domainname),
.mode = 0644,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
+#endif /* !CONFIG_UTS_NS */
{
.ctl_name = KERN_PANIC,
.procname = "panic",
@@ -294,7 +340,7 @@ static ctl_table kern_table[] = {
.ctl_name = KERN_CORE_PATTERN,
.procname = "core_pattern",
.data = core_pattern,
- .maxlen = 64,
+ .maxlen = 128,
.mode = 0644,
.proc_handler = &proc_dostring,
.strategy = &sysctl_string,
@@ -432,58 +478,58 @@ static ctl_table kern_table[] = {
{
.ctl_name = KERN_SHMMAX,
.procname = "shmmax",
- .data = &shm_ctlmax,
+ .data = NULL,
.maxlen = sizeof (size_t),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_SHMALL,
.procname = "shmall",
- .data = &shm_ctlall,
+ .data = NULL,
.maxlen = sizeof (size_t),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_SHMMNI,
.procname = "shmmni",
- .data = &shm_ctlmni,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_MSGMAX,
.procname = "msgmax",
- .data = &msg_ctlmax,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_MSGMNI,
.procname = "msgmni",
- .data = &msg_ctlmni,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_MSGMNB,
.procname = "msgmnb",
- .data = &msg_ctlmnb,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_SEM,
.procname = "sem",
- .data = &sem_ctls,
+ .data = NULL,
.maxlen = 4*sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
#endif
#ifdef CONFIG_MAGIC_SYSRQ
@@ -499,10 +545,10 @@ static ctl_table kern_table[] = {
{
.ctl_name = KERN_CADPID,
.procname = "cad_pid",
- .data = &cad_pid,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0600,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_cad_pid,
},
{
.ctl_name = KERN_MAX_THREADS,
@@ -1624,32 +1670,15 @@ static ssize_t proc_writesys(struct file * file, const char __user * buf,
return do_rw_proc(1, file, (char __user *) buf, count, ppos);
}
-/**
- * proc_dostring - read a string sysctl
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes a string from/to the user buffer. If the kernel
- * buffer provided is not large enough to hold the string, the
- * string is truncated. The copied string is %NULL-terminated.
- * If the string is being read by the user process, it is copied
- * and a newline '\n' is added. It is truncated if the buffer is
- * not large enough.
- *
- * Returns 0 on success.
- */
-int proc_dostring(ctl_table *table, int write, struct file *filp,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int _proc_do_string(void* data, int maxlen, int write,
+ struct file *filp, void __user *buffer,
+ size_t *lenp, loff_t *ppos)
{
size_t len;
char __user *p;
char c;
- if (!table->data || !table->maxlen || !*lenp ||
+ if (!data || !maxlen || !*lenp ||
(*ppos && !write)) {
*lenp = 0;
return 0;
@@ -1665,20 +1694,20 @@ int proc_dostring(ctl_table *table, int write, struct file *filp,
break;
len++;
}
- if (len >= table->maxlen)
- len = table->maxlen-1;
- if(copy_from_user(table->data, buffer, len))
+ if (len >= maxlen)
+ len = maxlen-1;
+ if(copy_from_user(data, buffer, len))
return -EFAULT;
- ((char *) table->data)[len] = 0;
+ ((char *) data)[len] = 0;
*ppos += *lenp;
} else {
- len = strlen(table->data);
- if (len > table->maxlen)
- len = table->maxlen;
+ len = strlen(data);
+ if (len > maxlen)
+ len = maxlen;
if (len > *lenp)
len = *lenp;
if (len)
- if(copy_to_user(buffer, table->data, len))
+ if(copy_to_user(buffer, data, len))
return -EFAULT;
if (len < *lenp) {
if(put_user('\n', ((char __user *) buffer) + len))
@@ -1691,12 +1720,38 @@ int proc_dostring(ctl_table *table, int write, struct file *filp,
return 0;
}
+/**
+ * proc_dostring - read a string sysctl
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @filp: the file structure
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes a string from/to the user buffer. If the kernel
+ * buffer provided is not large enough to hold the string, the
+ * string is truncated. The copied string is %NULL-terminated.
+ * If the string is being read by the user process, it is copied
+ * and a newline '\n' is added. It is truncated if the buffer is
+ * not large enough.
+ *
+ * Returns 0 on success.
+ */
+int proc_dostring(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return _proc_do_string(table->data, table->maxlen, write, filp,
+ buffer, lenp, ppos);
+}
+
/*
* Special case of dostring for the UTS structure. This has locks
* to observe. Should this be in kernel/sys.c ????
*/
-static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
+#ifndef CONFIG_UTS_NS
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int r;
@@ -1712,6 +1767,48 @@ static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
}
return r;
}
+#else /* !CONFIG_UTS_NS */
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int r;
+ struct uts_namespace* uts_ns = current->nsproxy->uts_ns;
+ char* which;
+
+ switch (table->ctl_name) {
+ case KERN_OSTYPE:
+ which = uts_ns->name.sysname;
+ break;
+ case KERN_NODENAME:
+ which = uts_ns->name.nodename;
+ break;
+ case KERN_OSRELEASE:
+ which = uts_ns->name.release;
+ break;
+ case KERN_VERSION:
+ which = uts_ns->name.version;
+ break;
+ case KERN_DOMAINNAME:
+ which = uts_ns->name.domainname;
+ break;
+ default:
+ r = -EINVAL;
+ goto out;
+ }
+
+ if (!write) {
+ down_read(&uts_sem);
+ r=_proc_do_string(which,table->maxlen,0,filp,buffer,lenp, ppos);
+ up_read(&uts_sem);
+ } else {
+ down_write(&uts_sem);
+ r=_proc_do_string(which,table->maxlen,1,filp,buffer,lenp, ppos);
+ up_write(&uts_sem);
+ }
+ out:
+ return r;
+}
+#endif /* !CONFIG_UTS_NS */
static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
int *valp,
@@ -1732,8 +1829,9 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
return 0;
}
-static int do_proc_dointvec(ctl_table *table, int write, struct file *filp,
- void __user *buffer, size_t *lenp, loff_t *ppos,
+static int __do_proc_dointvec(void *tbl_data, ctl_table *table,
+ int write, struct file *filp, void __user *buffer,
+ size_t *lenp, loff_t *ppos,
int (*conv)(int *negp, unsigned long *lvalp, int *valp,
int write, void *data),
void *data)
@@ -1746,13 +1844,13 @@ static int do_proc_dointvec(ctl_table *table, int write, struct file *filp,
char buf[TMPBUFLEN], *p;
char __user *s = buffer;
- if (!table->data || !table->maxlen || !*lenp ||
+ if (!tbl_data || !table->maxlen || !*lenp ||
(*ppos && !write)) {
*lenp = 0;
return 0;
}
- i = (int *) table->data;
+ i = (int *) tbl_data;
vleft = table->maxlen / sizeof(*i);
left = *lenp;
@@ -1841,6 +1939,16 @@ static int do_proc_dointvec(ctl_table *table, int write, struct file *filp,
#undef TMPBUFLEN
}
+static int do_proc_dointvec(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos,
+ int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+ int write, void *data),
+ void *data)
+{
+ return __do_proc_dointvec(table->data, table, write, filp,
+ buffer, lenp, ppos, conv, data);
+}
+
/**
* proc_dointvec - read a vector of integers
* @table: the sysctl table
@@ -1974,7 +2082,7 @@ int proc_dointvec_minmax(ctl_table *table, int write, struct file *filp,
do_proc_dointvec_minmax_conv, &param);
}
-static int do_proc_doulongvec_minmax(ctl_table *table, int write,
+static int __do_proc_doulongvec_minmax(void *data, ctl_table *table, int write,
struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos,
@@ -1988,13 +2096,13 @@ static int do_proc_doulongvec_minmax(ctl_table *table, int write,
char buf[TMPBUFLEN], *p;
char __user *s = buffer;
- if (!table->data || !table->maxlen || !*lenp ||
+ if (!data || !table->maxlen || !*lenp ||
(*ppos && !write)) {
*lenp = 0;
return 0;
}
- i = (unsigned long *) table->data;
+ i = (unsigned long *) data;
min = (unsigned long *) table->extra1;
max = (unsigned long *) table->extra2;
vleft = table->maxlen / sizeof(unsigned long);
@@ -2079,6 +2187,17 @@ static int do_proc_doulongvec_minmax(ctl_table *table, int write,
#undef TMPBUFLEN
}
+static int do_proc_doulongvec_minmax(ctl_table *table, int write,
+ struct file *filp,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos,
+ unsigned long convmul,
+ unsigned long convdiv)
+{
+ return __do_proc_doulongvec_minmax(table->data, table, write,
+ filp, buffer, lenp, ppos, convmul, convdiv);
+}
+
/**
* proc_doulongvec_minmax - read a vector of long integers with min/max values
* @table: the sysctl table
@@ -2267,6 +2386,71 @@ int proc_dointvec_ms_jiffies(ctl_table *table, int write, struct file *filp,
do_proc_dointvec_ms_jiffies_conv, NULL);
}
+#ifdef CONFIG_SYSVIPC
+static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ void *data;
+ struct ipc_namespace *ns;
+
+ ns = current->nsproxy->ipc_ns;
+
+ switch (table->ctl_name) {
+ case KERN_SHMMAX:
+ data = &ns->shm_ctlmax;
+ goto proc_minmax;
+ case KERN_SHMALL:
+ data = &ns->shm_ctlall;
+ goto proc_minmax;
+ case KERN_SHMMNI:
+ data = &ns->shm_ctlmni;
+ break;
+ case KERN_MSGMAX:
+ data = &ns->msg_ctlmax;
+ break;
+ case KERN_MSGMNI:
+ data = &ns->msg_ctlmni;
+ break;
+ case KERN_MSGMNB:
+ data = &ns->msg_ctlmnb;
+ break;
+ case KERN_SEM:
+ data = &ns->sem_ctls;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return __do_proc_dointvec(data, table, write, filp, buffer,
+ lenp, ppos, NULL, NULL);
+proc_minmax:
+ return __do_proc_doulongvec_minmax(data, table, write, filp, buffer,
+ lenp, ppos, 1l, 1l);
+}
+#endif
+
+static int proc_do_cad_pid(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct pid *new_pid;
+ pid_t tmp;
+ int r;
+
+ tmp = pid_nr(cad_pid);
+
+ r = __do_proc_dointvec(&tmp, table, write, filp, buffer,
+ lenp, ppos, NULL, NULL);
+ if (r || !write)
+ return r;
+
+ new_pid = find_get_pid(tmp);
+ if (!new_pid)
+ return -ESRCH;
+
+ put_pid(xchg(&cad_pid, new_pid));
+ return 0;
+}
+
#else /* CONFIG_PROC_FS */
int proc_dostring(ctl_table *table, int write, struct file *filp,
@@ -2275,12 +2459,20 @@ int proc_dostring(ctl_table *table, int write, struct file *filp,
return -ENOSYS;
}
-static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
+#ifdef CONFIG_SYSVIPC
+static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+#endif
+
int proc_dointvec(ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 2ed4040d0dc..5d6a8c54ee8 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -18,7 +18,9 @@
#include <linux/kernel.h>
#include <linux/taskstats_kern.h>
+#include <linux/tsacct_kern.h>
#include <linux/delayacct.h>
+#include <linux/tsacct_kern.h>
#include <linux/cpumask.h>
#include <linux/percpu.h>
#include <net/genetlink.h>
@@ -75,7 +77,7 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp,
/*
* If new attributes are added, please revisit this allocation
*/
- skb = nlmsg_new(size, GFP_KERNEL);
+ skb = nlmsg_new(genlmsg_total_size(size), GFP_KERNEL);
if (!skb)
return -ENOMEM;
@@ -198,7 +200,13 @@ static int fill_pid(pid_t pid, struct task_struct *pidtsk,
*/
delayacct_add_tsk(stats, tsk);
+
+ /* fill in basic acct fields */
stats->version = TASKSTATS_VERSION;
+ bacct_add_tsk(stats, tsk);
+
+ /* fill in extended acct fields */
+ xacct_add_tsk(stats, tsk);
/* Define err: label here if needed */
put_task_struct(tsk);
diff --git a/kernel/time.c b/kernel/time.c
index 5bd48974764..0e017bff4c1 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -202,179 +202,6 @@ asmlinkage long sys_settimeofday(struct timeval __user *tv,
return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
}
-/* we call this to notify the arch when the clock is being
- * controlled. If no such arch routine, do nothing.
- */
-void __attribute__ ((weak)) notify_arch_cmos_timer(void)
-{
- return;
-}
-
-/* adjtimex mainly allows reading (and writing, if superuser) of
- * kernel time-keeping variables. used by xntpd.
- */
-int do_adjtimex(struct timex *txc)
-{
- long ltemp, mtemp, save_adjust;
- int result;
-
- /* In order to modify anything, you gotta be super-user! */
- if (txc->modes && !capable(CAP_SYS_TIME))
- return -EPERM;
-
- /* Now we validate the data before disabling interrupts */
-
- if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
- /* singleshot must not be used with any other mode bits */
- if (txc->modes != ADJ_OFFSET_SINGLESHOT)
- return -EINVAL;
-
- if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET))
- /* adjustment Offset limited to +- .512 seconds */
- if (txc->offset <= - MAXPHASE || txc->offset >= MAXPHASE )
- return -EINVAL;
-
- /* if the quartz is off by more than 10% something is VERY wrong ! */
- if (txc->modes & ADJ_TICK)
- if (txc->tick < 900000/USER_HZ ||
- txc->tick > 1100000/USER_HZ)
- return -EINVAL;
-
- write_seqlock_irq(&xtime_lock);
- result = time_state; /* mostly `TIME_OK' */
-
- /* Save for later - semantics of adjtime is to return old value */
- save_adjust = time_next_adjust ? time_next_adjust : time_adjust;
-
-#if 0 /* STA_CLOCKERR is never set yet */
- time_status &= ~STA_CLOCKERR; /* reset STA_CLOCKERR */
-#endif
- /* If there are input parameters, then process them */
- if (txc->modes)
- {
- if (txc->modes & ADJ_STATUS) /* only set allowed bits */
- time_status = (txc->status & ~STA_RONLY) |
- (time_status & STA_RONLY);
-
- if (txc->modes & ADJ_FREQUENCY) { /* p. 22 */
- if (txc->freq > MAXFREQ || txc->freq < -MAXFREQ) {
- result = -EINVAL;
- goto leave;
- }
- time_freq = txc->freq;
- }
-
- if (txc->modes & ADJ_MAXERROR) {
- if (txc->maxerror < 0 || txc->maxerror >= NTP_PHASE_LIMIT) {
- result = -EINVAL;
- goto leave;
- }
- time_maxerror = txc->maxerror;
- }
-
- if (txc->modes & ADJ_ESTERROR) {
- if (txc->esterror < 0 || txc->esterror >= NTP_PHASE_LIMIT) {
- result = -EINVAL;
- goto leave;
- }
- time_esterror = txc->esterror;
- }
-
- if (txc->modes & ADJ_TIMECONST) { /* p. 24 */
- if (txc->constant < 0) { /* NTP v4 uses values > 6 */
- result = -EINVAL;
- goto leave;
- }
- time_constant = txc->constant;
- }
-
- if (txc->modes & ADJ_OFFSET) { /* values checked earlier */
- if (txc->modes == ADJ_OFFSET_SINGLESHOT) {
- /* adjtime() is independent from ntp_adjtime() */
- if ((time_next_adjust = txc->offset) == 0)
- time_adjust = 0;
- }
- else if (time_status & STA_PLL) {
- ltemp = txc->offset;
-
- /*
- * Scale the phase adjustment and
- * clamp to the operating range.
- */
- if (ltemp > MAXPHASE)
- time_offset = MAXPHASE << SHIFT_UPDATE;
- else if (ltemp < -MAXPHASE)
- time_offset = -(MAXPHASE << SHIFT_UPDATE);
- else
- time_offset = ltemp << SHIFT_UPDATE;
-
- /*
- * Select whether the frequency is to be controlled
- * and in which mode (PLL or FLL). Clamp to the operating
- * range. Ugly multiply/divide should be replaced someday.
- */
-
- if (time_status & STA_FREQHOLD || time_reftime == 0)
- time_reftime = xtime.tv_sec;
- mtemp = xtime.tv_sec - time_reftime;
- time_reftime = xtime.tv_sec;
- if (time_status & STA_FLL) {
- if (mtemp >= MINSEC) {
- ltemp = (time_offset / mtemp) << (SHIFT_USEC -
- SHIFT_UPDATE);
- time_freq += shift_right(ltemp, SHIFT_KH);
- } else /* calibration interval too short (p. 12) */
- result = TIME_ERROR;
- } else { /* PLL mode */
- if (mtemp < MAXSEC) {
- ltemp *= mtemp;
- time_freq += shift_right(ltemp,(time_constant +
- time_constant +
- SHIFT_KF - SHIFT_USEC));
- } else /* calibration interval too long (p. 12) */
- result = TIME_ERROR;
- }
- time_freq = min(time_freq, time_tolerance);
- time_freq = max(time_freq, -time_tolerance);
- } /* STA_PLL */
- } /* txc->modes & ADJ_OFFSET */
- if (txc->modes & ADJ_TICK) {
- tick_usec = txc->tick;
- tick_nsec = TICK_USEC_TO_NSEC(tick_usec);
- }
- } /* txc->modes */
-leave: if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
- result = TIME_ERROR;
-
- if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
- txc->offset = save_adjust;
- else {
- txc->offset = shift_right(time_offset, SHIFT_UPDATE);
- }
- txc->freq = time_freq;
- txc->maxerror = time_maxerror;
- txc->esterror = time_esterror;
- txc->status = time_status;
- txc->constant = time_constant;
- txc->precision = time_precision;
- txc->tolerance = time_tolerance;
- txc->tick = tick_usec;
-
- /* PPS is not implemented, so these are zero */
- txc->ppsfreq = 0;
- txc->jitter = 0;
- txc->shift = 0;
- txc->stabil = 0;
- txc->jitcnt = 0;
- txc->calcnt = 0;
- txc->errcnt = 0;
- txc->stbcnt = 0;
- write_sequnlock_irq(&xtime_lock);
- do_gettimeofday(&txc->time);
- notify_arch_cmos_timer();
- return(result);
-}
-
asmlinkage long sys_adjtimex(struct timex __user *txc_p)
{
struct timex txc; /* Local copy of parameter */
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index e1dfd8e86cc..61a3907d16f 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1 +1 @@
-obj-y += clocksource.o jiffies.o
+obj-y += ntp.o clocksource.o jiffies.o
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
new file mode 100644
index 00000000000..47195fa0ec4
--- /dev/null
+++ b/kernel/time/ntp.c
@@ -0,0 +1,350 @@
+/*
+ * linux/kernel/time/ntp.c
+ *
+ * NTP state machine interfaces and logic.
+ *
+ * This code was mainly moved from kernel/timer.c and kernel/time.c
+ * Please see those files for relevant copyright info and historical
+ * changelogs.
+ */
+
+#include <linux/mm.h>
+#include <linux/time.h>
+#include <linux/timex.h>
+
+#include <asm/div64.h>
+#include <asm/timex.h>
+
+/*
+ * Timekeeping variables
+ */
+unsigned long tick_usec = TICK_USEC; /* USER_HZ period (usec) */
+unsigned long tick_nsec; /* ACTHZ period (nsec) */
+static u64 tick_length, tick_length_base;
+
+#define MAX_TICKADJ 500 /* microsecs */
+#define MAX_TICKADJ_SCALED (((u64)(MAX_TICKADJ * NSEC_PER_USEC) << \
+ TICK_LENGTH_SHIFT) / HZ)
+
+/*
+ * phase-lock loop variables
+ */
+/* TIME_ERROR prevents overwriting the CMOS clock */
+static int time_state = TIME_OK; /* clock synchronization status */
+int time_status = STA_UNSYNC; /* clock status bits */
+static long time_offset; /* time adjustment (ns) */
+static long time_constant = 2; /* pll time constant */
+long time_maxerror = NTP_PHASE_LIMIT; /* maximum error (us) */
+long time_esterror = NTP_PHASE_LIMIT; /* estimated error (us) */
+long time_freq; /* frequency offset (scaled ppm)*/
+static long time_reftime; /* time at last adjustment (s) */
+long time_adjust;
+
+#define CLOCK_TICK_OVERFLOW (LATCH * HZ - CLOCK_TICK_RATE)
+#define CLOCK_TICK_ADJUST (((s64)CLOCK_TICK_OVERFLOW * NSEC_PER_SEC) / \
+ (s64)CLOCK_TICK_RATE)
+
+static void ntp_update_frequency(void)
+{
+ tick_length_base = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) << TICK_LENGTH_SHIFT;
+ tick_length_base += (s64)CLOCK_TICK_ADJUST << TICK_LENGTH_SHIFT;
+ tick_length_base += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC);
+
+ do_div(tick_length_base, HZ);
+
+ tick_nsec = tick_length_base >> TICK_LENGTH_SHIFT;
+}
+
+/**
+ * ntp_clear - Clears the NTP state variables
+ *
+ * Must be called while holding a write on the xtime_lock
+ */
+void ntp_clear(void)
+{
+ time_adjust = 0; /* stop active adjtime() */
+ time_status |= STA_UNSYNC;
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_esterror = NTP_PHASE_LIMIT;
+
+ ntp_update_frequency();
+
+ tick_length = tick_length_base;
+ time_offset = 0;
+}
+
+/*
+ * this routine handles the overflow of the microsecond field
+ *
+ * The tricky bits of code to handle the accurate clock support
+ * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
+ * They were originally developed for SUN and DEC kernels.
+ * All the kudos should go to Dave for this stuff.
+ */
+void second_overflow(void)
+{
+ long time_adj;
+
+ /* Bump the maxerror field */
+ time_maxerror += MAXFREQ >> SHIFT_USEC;
+ if (time_maxerror > NTP_PHASE_LIMIT) {
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_status |= STA_UNSYNC;
+ }
+
+ /*
+ * Leap second processing. If in leap-insert state at the end of the
+ * day, the system clock is set back one second; if in leap-delete
+ * state, the system clock is set ahead one second. The microtime()
+ * routine or external clock driver will insure that reported time is
+ * always monotonic. The ugly divides should be replaced.
+ */
+ switch (time_state) {
+ case TIME_OK:
+ if (time_status & STA_INS)
+ time_state = TIME_INS;
+ else if (time_status & STA_DEL)
+ time_state = TIME_DEL;
+ break;
+ case TIME_INS:
+ if (xtime.tv_sec % 86400 == 0) {
+ xtime.tv_sec--;
+ wall_to_monotonic.tv_sec++;
+ /*
+ * The timer interpolator will make time change
+ * gradually instead of an immediate jump by one second
+ */
+ time_interpolator_update(-NSEC_PER_SEC);
+ time_state = TIME_OOP;
+ clock_was_set();
+ printk(KERN_NOTICE "Clock: inserting leap second "
+ "23:59:60 UTC\n");
+ }
+ break;
+ case TIME_DEL:
+ if ((xtime.tv_sec + 1) % 86400 == 0) {
+ xtime.tv_sec++;
+ wall_to_monotonic.tv_sec--;
+ /*
+ * Use of time interpolator for a gradual change of
+ * time
+ */
+ time_interpolator_update(NSEC_PER_SEC);
+ time_state = TIME_WAIT;
+ clock_was_set();
+ printk(KERN_NOTICE "Clock: deleting leap second "
+ "23:59:59 UTC\n");
+ }
+ break;
+ case TIME_OOP:
+ time_state = TIME_WAIT;
+ break;
+ case TIME_WAIT:
+ if (!(time_status & (STA_INS | STA_DEL)))
+ time_state = TIME_OK;
+ }
+
+ /*
+ * Compute the phase adjustment for the next second. The offset is
+ * reduced by a fixed factor times the time constant.
+ */
+ tick_length = tick_length_base;
+ time_adj = shift_right(time_offset, SHIFT_PLL + time_constant);
+ time_offset -= time_adj;
+ tick_length += (s64)time_adj << (TICK_LENGTH_SHIFT - SHIFT_UPDATE);
+
+ if (unlikely(time_adjust)) {
+ if (time_adjust > MAX_TICKADJ) {
+ time_adjust -= MAX_TICKADJ;
+ tick_length += MAX_TICKADJ_SCALED;
+ } else if (time_adjust < -MAX_TICKADJ) {
+ time_adjust += MAX_TICKADJ;
+ tick_length -= MAX_TICKADJ_SCALED;
+ } else {
+ time_adjust = 0;
+ tick_length += (s64)(time_adjust * NSEC_PER_USEC /
+ HZ) << TICK_LENGTH_SHIFT;
+ }
+ }
+}
+
+/*
+ * Return how long ticks are at the moment, that is, how much time
+ * update_wall_time_one_tick will add to xtime next time we call it
+ * (assuming no calls to do_adjtimex in the meantime).
+ * The return value is in fixed-point nanoseconds shifted by the
+ * specified number of bits to the right of the binary point.
+ * This function has no side-effects.
+ */
+u64 current_tick_length(void)
+{
+ return tick_length;
+}
+
+
+void __attribute__ ((weak)) notify_arch_cmos_timer(void)
+{
+ return;
+}
+
+/* adjtimex mainly allows reading (and writing, if superuser) of
+ * kernel time-keeping variables. used by xntpd.
+ */
+int do_adjtimex(struct timex *txc)
+{
+ long ltemp, mtemp, save_adjust;
+ s64 freq_adj, temp64;
+ int result;
+
+ /* In order to modify anything, you gotta be super-user! */
+ if (txc->modes && !capable(CAP_SYS_TIME))
+ return -EPERM;
+
+ /* Now we validate the data before disabling interrupts */
+
+ if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
+ /* singleshot must not be used with any other mode bits */
+ if (txc->modes != ADJ_OFFSET_SINGLESHOT)
+ return -EINVAL;
+
+ if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET))
+ /* adjustment Offset limited to +- .512 seconds */
+ if (txc->offset <= - MAXPHASE || txc->offset >= MAXPHASE )
+ return -EINVAL;
+
+ /* if the quartz is off by more than 10% something is VERY wrong ! */
+ if (txc->modes & ADJ_TICK)
+ if (txc->tick < 900000/USER_HZ ||
+ txc->tick > 1100000/USER_HZ)
+ return -EINVAL;
+
+ write_seqlock_irq(&xtime_lock);
+ result = time_state; /* mostly `TIME_OK' */
+
+ /* Save for later - semantics of adjtime is to return old value */
+ save_adjust = time_adjust;
+
+#if 0 /* STA_CLOCKERR is never set yet */
+ time_status &= ~STA_CLOCKERR; /* reset STA_CLOCKERR */
+#endif
+ /* If there are input parameters, then process them */
+ if (txc->modes)
+ {
+ if (txc->modes & ADJ_STATUS) /* only set allowed bits */
+ time_status = (txc->status & ~STA_RONLY) |
+ (time_status & STA_RONLY);
+
+ if (txc->modes & ADJ_FREQUENCY) { /* p. 22 */
+ if (txc->freq > MAXFREQ || txc->freq < -MAXFREQ) {
+ result = -EINVAL;
+ goto leave;
+ }
+ time_freq = ((s64)txc->freq * NSEC_PER_USEC) >> (SHIFT_USEC - SHIFT_NSEC);
+ }
+
+ if (txc->modes & ADJ_MAXERROR) {
+ if (txc->maxerror < 0 || txc->maxerror >= NTP_PHASE_LIMIT) {
+ result = -EINVAL;
+ goto leave;
+ }
+ time_maxerror = txc->maxerror;
+ }
+
+ if (txc->modes & ADJ_ESTERROR) {
+ if (txc->esterror < 0 || txc->esterror >= NTP_PHASE_LIMIT) {
+ result = -EINVAL;
+ goto leave;
+ }
+ time_esterror = txc->esterror;
+ }
+
+ if (txc->modes & ADJ_TIMECONST) { /* p. 24 */
+ if (txc->constant < 0) { /* NTP v4 uses values > 6 */
+ result = -EINVAL;
+ goto leave;
+ }
+ time_constant = min(txc->constant + 4, (long)MAXTC);
+ }
+
+ if (txc->modes & ADJ_OFFSET) { /* values checked earlier */
+ if (txc->modes == ADJ_OFFSET_SINGLESHOT) {
+ /* adjtime() is independent from ntp_adjtime() */
+ time_adjust = txc->offset;
+ }
+ else if (time_status & STA_PLL) {
+ ltemp = txc->offset * NSEC_PER_USEC;
+
+ /*
+ * Scale the phase adjustment and
+ * clamp to the operating range.
+ */
+ time_offset = min(ltemp, MAXPHASE * NSEC_PER_USEC);
+ time_offset = max(time_offset, -MAXPHASE * NSEC_PER_USEC);
+
+ /*
+ * Select whether the frequency is to be controlled
+ * and in which mode (PLL or FLL). Clamp to the operating
+ * range. Ugly multiply/divide should be replaced someday.
+ */
+
+ if (time_status & STA_FREQHOLD || time_reftime == 0)
+ time_reftime = xtime.tv_sec;
+ mtemp = xtime.tv_sec - time_reftime;
+ time_reftime = xtime.tv_sec;
+
+ freq_adj = (s64)time_offset * mtemp;
+ freq_adj = shift_right(freq_adj, time_constant * 2 +
+ (SHIFT_PLL + 2) * 2 - SHIFT_NSEC);
+ if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) {
+ temp64 = (s64)time_offset << (SHIFT_NSEC - SHIFT_FLL);
+ if (time_offset < 0) {
+ temp64 = -temp64;
+ do_div(temp64, mtemp);
+ freq_adj -= temp64;
+ } else {
+ do_div(temp64, mtemp);
+ freq_adj += temp64;
+ }
+ }
+ freq_adj += time_freq;
+ freq_adj = min(freq_adj, (s64)MAXFREQ_NSEC);
+ time_freq = max(freq_adj, (s64)-MAXFREQ_NSEC);
+ time_offset = (time_offset / HZ) << SHIFT_UPDATE;
+ } /* STA_PLL */
+ } /* txc->modes & ADJ_OFFSET */
+ if (txc->modes & ADJ_TICK)
+ tick_usec = txc->tick;
+
+ if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET))
+ ntp_update_frequency();
+ } /* txc->modes */
+leave: if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
+ result = TIME_ERROR;
+
+ if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT)
+ txc->offset = save_adjust;
+ else
+ txc->offset = shift_right(time_offset, SHIFT_UPDATE) * HZ / 1000;
+ txc->freq = (time_freq / NSEC_PER_USEC) << (SHIFT_USEC - SHIFT_NSEC);
+ txc->maxerror = time_maxerror;
+ txc->esterror = time_esterror;
+ txc->status = time_status;
+ txc->constant = time_constant;
+ txc->precision = 1;
+ txc->tolerance = MAXFREQ;
+ txc->tick = tick_usec;
+
+ /* PPS is not implemented, so these are zero */
+ txc->ppsfreq = 0;
+ txc->jitter = 0;
+ txc->shift = 0;
+ txc->stabil = 0;
+ txc->jitcnt = 0;
+ txc->calcnt = 0;
+ txc->errcnt = 0;
+ txc->stbcnt = 0;
+ write_sequnlock_irq(&xtime_lock);
+ do_gettimeofday(&txc->time);
+ notify_arch_cmos_timer();
+ return(result);
+}
diff --git a/kernel/timer.c b/kernel/timer.c
index 4f55622b0d3..c1c7fbcffec 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -41,12 +41,6 @@
#include <asm/timex.h>
#include <asm/io.h>
-#ifdef CONFIG_TIME_INTERPOLATION
-static void time_interpolator_update(long delta_nsec);
-#else
-#define time_interpolator_update(x)
-#endif
-
u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
EXPORT_SYMBOL(jiffies_64);
@@ -568,12 +562,6 @@ found:
/******************************************************************/
-/*
- * Timekeeping variables
- */
-unsigned long tick_usec = TICK_USEC; /* USER_HZ period (usec) */
-unsigned long tick_nsec = TICK_NSEC; /* ACTHZ period (nsec) */
-
/*
* The current time
* wall_to_monotonic is what we need to add to xtime (or xtime corrected
@@ -587,209 +575,6 @@ struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
EXPORT_SYMBOL(xtime);
-/* Don't completely fail for HZ > 500. */
-int tickadj = 500/HZ ? : 1; /* microsecs */
-
-
-/*
- * phase-lock loop variables
- */
-/* TIME_ERROR prevents overwriting the CMOS clock */
-int time_state = TIME_OK; /* clock synchronization status */
-int time_status = STA_UNSYNC; /* clock status bits */
-long time_offset; /* time adjustment (us) */
-long time_constant = 2; /* pll time constant */
-long time_tolerance = MAXFREQ; /* frequency tolerance (ppm) */
-long time_precision = 1; /* clock precision (us) */
-long time_maxerror = NTP_PHASE_LIMIT; /* maximum error (us) */
-long time_esterror = NTP_PHASE_LIMIT; /* estimated error (us) */
-long time_freq = (((NSEC_PER_SEC + HZ/2) % HZ - HZ/2) << SHIFT_USEC) / NSEC_PER_USEC;
- /* frequency offset (scaled ppm)*/
-static long time_adj; /* tick adjust (scaled 1 / HZ) */
-long time_reftime; /* time at last adjustment (s) */
-long time_adjust;
-long time_next_adjust;
-
-/*
- * this routine handles the overflow of the microsecond field
- *
- * The tricky bits of code to handle the accurate clock support
- * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
- * They were originally developed for SUN and DEC kernels.
- * All the kudos should go to Dave for this stuff.
- *
- */
-static void second_overflow(void)
-{
- long ltemp;
-
- /* Bump the maxerror field */
- time_maxerror += time_tolerance >> SHIFT_USEC;
- if (time_maxerror > NTP_PHASE_LIMIT) {
- time_maxerror = NTP_PHASE_LIMIT;
- time_status |= STA_UNSYNC;
- }
-
- /*
- * Leap second processing. If in leap-insert state at the end of the
- * day, the system clock is set back one second; if in leap-delete
- * state, the system clock is set ahead one second. The microtime()
- * routine or external clock driver will insure that reported time is
- * always monotonic. The ugly divides should be replaced.
- */
- switch (time_state) {
- case TIME_OK:
- if (time_status & STA_INS)
- time_state = TIME_INS;
- else if (time_status & STA_DEL)
- time_state = TIME_DEL;
- break;
- case TIME_INS:
- if (xtime.tv_sec % 86400 == 0) {
- xtime.tv_sec--;
- wall_to_monotonic.tv_sec++;
- /*
- * The timer interpolator will make time change
- * gradually instead of an immediate jump by one second
- */
- time_interpolator_update(-NSEC_PER_SEC);
- time_state = TIME_OOP;
- clock_was_set();
- printk(KERN_NOTICE "Clock: inserting leap second "
- "23:59:60 UTC\n");
- }
- break;
- case TIME_DEL:
- if ((xtime.tv_sec + 1) % 86400 == 0) {
- xtime.tv_sec++;
- wall_to_monotonic.tv_sec--;
- /*
- * Use of time interpolator for a gradual change of
- * time
- */
- time_interpolator_update(NSEC_PER_SEC);
- time_state = TIME_WAIT;
- clock_was_set();
- printk(KERN_NOTICE "Clock: deleting leap second "
- "23:59:59 UTC\n");
- }
- break;
- case TIME_OOP:
- time_state = TIME_WAIT;
- break;
- case TIME_WAIT:
- if (!(time_status & (STA_INS | STA_DEL)))
- time_state = TIME_OK;
- }
-
- /*
- * Compute the phase adjustment for the next second. In PLL mode, the
- * offset is reduced by a fixed factor times the time constant. In FLL
- * mode the offset is used directly. In either mode, the maximum phase
- * adjustment for each second is clamped so as to spread the adjustment
- * over not more than the number of seconds between updates.
- */
- ltemp = time_offset;
- if (!(time_status & STA_FLL))
- ltemp = shift_right(ltemp, SHIFT_KG + time_constant);
- ltemp = min(ltemp, (MAXPHASE / MINSEC) << SHIFT_UPDATE);
- ltemp = max(ltemp, -(MAXPHASE / MINSEC) << SHIFT_UPDATE);
- time_offset -= ltemp;
- time_adj = ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE);
-
- /*
- * Compute the frequency estimate and additional phase adjustment due
- * to frequency error for the next second.
- */
- ltemp = time_freq;
- time_adj += shift_right(ltemp,(SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE));
-
-#if HZ == 100
- /*
- * Compensate for (HZ==100) != (1 << SHIFT_HZ). Add 25% and 3.125% to
- * get 128.125; => only 0.125% error (p. 14)
- */
- time_adj += shift_right(time_adj, 2) + shift_right(time_adj, 5);
-#endif
-#if HZ == 250
- /*
- * Compensate for (HZ==250) != (1 << SHIFT_HZ). Add 1.5625% and
- * 0.78125% to get 255.85938; => only 0.05% error (p. 14)
- */
- time_adj += shift_right(time_adj, 6) + shift_right(time_adj, 7);
-#endif
-#if HZ == 1000
- /*
- * Compensate for (HZ==1000) != (1 << SHIFT_HZ). Add 1.5625% and
- * 0.78125% to get 1023.4375; => only 0.05% error (p. 14)
- */
- time_adj += shift_right(time_adj, 6) + shift_right(time_adj, 7);
-#endif
-}
-
-/*
- * Returns how many microseconds we need to add to xtime this tick
- * in doing an adjustment requested with adjtime.
- */
-static long adjtime_adjustment(void)
-{
- long time_adjust_step;
-
- time_adjust_step = time_adjust;
- if (time_adjust_step) {
- /*
- * We are doing an adjtime thing. Prepare time_adjust_step to
- * be within bounds. Note that a positive time_adjust means we
- * want the clock to run faster.
- *
- * Limit the amount of the step to be in the range
- * -tickadj .. +tickadj
- */
- time_adjust_step = min(time_adjust_step, (long)tickadj);
- time_adjust_step = max(time_adjust_step, (long)-tickadj);
- }
- return time_adjust_step;
-}
-
-/* in the NTP reference this is called "hardclock()" */
-static void update_ntp_one_tick(void)
-{
- long time_adjust_step;
-
- time_adjust_step = adjtime_adjustment();
- if (time_adjust_step)
- /* Reduce by this step the amount of time left */
- time_adjust -= time_adjust_step;
-
- /* Changes by adjtime() do not take effect till next tick. */
- if (time_next_adjust != 0) {
- time_adjust = time_next_adjust;
- time_next_adjust = 0;
- }
-}
-
-/*
- * Return how long ticks are at the moment, that is, how much time
- * update_wall_time_one_tick will add to xtime next time we call it
- * (assuming no calls to do_adjtimex in the meantime).
- * The return value is in fixed-point nanoseconds shifted by the
- * specified number of bits to the right of the binary point.
- * This function has no side-effects.
- */
-u64 current_tick_length(void)
-{
- long delta_nsec;
- u64 ret;
-
- /* calculate the finest interval NTP will allow.
- * ie: nanosecond value shifted by (SHIFT_SCALE - 10)
- */
- delta_nsec = tick_nsec + adjtime_adjustment() * 1000;
- ret = (u64)delta_nsec << TICK_LENGTH_SHIFT;
- ret += (s64)time_adj << (TICK_LENGTH_SHIFT - (SHIFT_SCALE - 10));
-
- return ret;
-}
/* XXX - all of this timekeeping code should be later moved to time.c */
#include <linux/clocksource.h>
@@ -966,10 +751,13 @@ void __init timekeeping_init(void)
unsigned long flags;
write_seqlock_irqsave(&xtime_lock, flags);
+
+ ntp_clear();
+
clock = clocksource_get_next();
clocksource_calculate_interval(clock, tick_nsec);
clock->cycle_last = clocksource_read(clock);
- ntp_clear();
+
write_sequnlock_irqrestore(&xtime_lock, flags);
}
@@ -980,7 +768,7 @@ static int timekeeping_suspended;
* @dev: unused
*
* This is for the generic clocksource timekeeping.
- * xtime/wall_to_monotonic/jiffies/wall_jiffies/etc are
+ * xtime/wall_to_monotonic/jiffies/etc are
* still managed by arch specific suspend/resume code.
*/
static int timekeeping_resume(struct sys_device *dev)
@@ -1149,8 +937,6 @@ static void update_wall_time(void)
/* interpolator bits */
time_interpolator_update(clock->xtime_interval
>> clock->shift);
- /* increment the NTP state machine */
- update_ntp_one_tick();
/* accumulate error between NTP and clock interval */
clock->error += current_tick_length();
@@ -1230,9 +1016,6 @@ static inline void calc_load(unsigned long ticks)
}
}
-/* jiffies at the most recent update of wall time */
-unsigned long wall_jiffies = INITIAL_JIFFIES;
-
/*
* This read-write spinlock protects us from races in SMP while
* playing with xtime and avenrun.
@@ -1270,7 +1053,6 @@ void run_local_timers(void)
*/
static inline void update_times(unsigned long ticks)
{
- wall_jiffies += ticks;
update_wall_time();
calc_load(ticks);
}
@@ -1775,7 +1557,7 @@ unsigned long time_interpolator_get_offset(void)
#define INTERPOLATOR_ADJUST 65536
#define INTERPOLATOR_MAX_SKIP 10*INTERPOLATOR_ADJUST
-static void time_interpolator_update(long delta_nsec)
+void time_interpolator_update(long delta_nsec)
{
u64 counter;
unsigned long offset;
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
new file mode 100644
index 00000000000..db443221ba5
--- /dev/null
+++ b/kernel/tsacct.c
@@ -0,0 +1,124 @@
+/*
+ * tsacct.c - System accounting over taskstats interface
+ *
+ * Copyright (C) Jay Lan, <jlan@sgi.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/tsacct_kern.h>
+#include <linux/acct.h>
+#include <linux/jiffies.h>
+
+
+#define USEC_PER_TICK (USEC_PER_SEC/HZ)
+/*
+ * fill in basic accounting fields
+ */
+void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
+{
+ struct timespec uptime, ts;
+ s64 ac_etime;
+
+ BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN);
+
+ /* calculate task elapsed time in timespec */
+ do_posix_clock_monotonic_gettime(&uptime);
+ ts = timespec_sub(uptime, current->group_leader->start_time);
+ /* rebase elapsed time to usec */
+ ac_etime = timespec_to_ns(&ts);
+ do_div(ac_etime, NSEC_PER_USEC);
+ stats->ac_etime = ac_etime;
+ stats->ac_btime = xtime.tv_sec - ts.tv_sec;
+ if (thread_group_leader(tsk)) {
+ stats->ac_exitcode = tsk->exit_code;
+ if (tsk->flags & PF_FORKNOEXEC)
+ stats->ac_flag |= AFORK;
+ }
+ if (tsk->flags & PF_SUPERPRIV)
+ stats->ac_flag |= ASU;
+ if (tsk->flags & PF_DUMPCORE)
+ stats->ac_flag |= ACORE;
+ if (tsk->flags & PF_SIGNALED)
+ stats->ac_flag |= AXSIG;
+ stats->ac_nice = task_nice(tsk);
+ stats->ac_sched = tsk->policy;
+ stats->ac_uid = tsk->uid;
+ stats->ac_gid = tsk->gid;
+ stats->ac_pid = tsk->pid;
+ stats->ac_ppid = (tsk->parent) ? tsk->parent->pid : 0;
+ stats->ac_utime = cputime_to_msecs(tsk->utime) * USEC_PER_MSEC;
+ stats->ac_stime = cputime_to_msecs(tsk->stime) * USEC_PER_MSEC;
+ stats->ac_minflt = tsk->min_flt;
+ stats->ac_majflt = tsk->maj_flt;
+
+ strncpy(stats->ac_comm, tsk->comm, sizeof(stats->ac_comm));
+}
+
+
+#ifdef CONFIG_TASK_XACCT
+
+#define KB 1024
+#define MB (1024*KB)
+/*
+ * fill in extended accounting fields
+ */
+void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
+{
+ /* convert pages-jiffies to Mbyte-usec */
+ stats->coremem = jiffies_to_usecs(p->acct_rss_mem1) * PAGE_SIZE / MB;
+ stats->virtmem = jiffies_to_usecs(p->acct_vm_mem1) * PAGE_SIZE / MB;
+ if (p->mm) {
+ /* adjust to KB unit */
+ stats->hiwater_rss = p->mm->hiwater_rss * PAGE_SIZE / KB;
+ stats->hiwater_vm = p->mm->hiwater_vm * PAGE_SIZE / KB;
+ }
+ stats->read_char = p->rchar;
+ stats->write_char = p->wchar;
+ stats->read_syscalls = p->syscr;
+ stats->write_syscalls = p->syscw;
+}
+#undef KB
+#undef MB
+
+/**
+ * acct_update_integrals - update mm integral fields in task_struct
+ * @tsk: task_struct for accounting
+ */
+void acct_update_integrals(struct task_struct *tsk)
+{
+ if (likely(tsk->mm)) {
+ long delta = cputime_to_jiffies(
+ cputime_sub(tsk->stime, tsk->acct_stimexpd));
+
+ if (delta == 0)
+ return;
+ tsk->acct_stimexpd = tsk->stime;
+ tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
+ tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
+ }
+}
+
+/**
+ * acct_clear_integrals - clear the mm integral fields in task_struct
+ * @tsk: task_struct whose accounting fields are cleared
+ */
+void acct_clear_integrals(struct task_struct *tsk)
+{
+ tsk->acct_stimexpd = 0;
+ tsk->acct_rss_mem1 = 0;
+ tsk->acct_vm_mem1 = 0;
+}
+#endif
diff --git a/kernel/utsname.c b/kernel/utsname.c
new file mode 100644
index 00000000000..c859164a699
--- /dev/null
+++ b/kernel/utsname.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright (C) 2004 IBM Corporation
+ *
+ * Author: Serge Hallyn <serue@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <linux/version.h>
+
+/*
+ * Clone a new ns copying an original utsname, setting refcount to 1
+ * @old_ns: namespace to clone
+ * Return NULL on error (failure to kmalloc), new ns otherwise
+ */
+static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns)
+{
+ struct uts_namespace *ns;
+
+ ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL);
+ if (ns) {
+ memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
+ kref_init(&ns->kref);
+ }
+ return ns;
+}
+
+/*
+ * unshare the current process' utsname namespace.
+ * called only in sys_unshare()
+ */
+int unshare_utsname(unsigned long unshare_flags, struct uts_namespace **new_uts)
+{
+ if (unshare_flags & CLONE_NEWUTS) {
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ *new_uts = clone_uts_ns(current->nsproxy->uts_ns);
+ if (!*new_uts)
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+/*
+ * Copy task tsk's utsname namespace, or clone it if flags
+ * specifies CLONE_NEWUTS. In latter case, changes to the
+ * utsname of this process won't be seen by parent, and vice
+ * versa.
+ */
+int copy_utsname(int flags, struct task_struct *tsk)
+{
+ struct uts_namespace *old_ns = tsk->nsproxy->uts_ns;
+ struct uts_namespace *new_ns;
+ int err = 0;
+
+ if (!old_ns)
+ return 0;
+
+ get_uts_ns(old_ns);
+
+ if (!(flags & CLONE_NEWUTS))
+ return 0;
+
+ if (!capable(CAP_SYS_ADMIN)) {
+ err = -EPERM;
+ goto out;
+ }
+
+ new_ns = clone_uts_ns(old_ns);
+ if (!new_ns) {
+ err = -ENOMEM;
+ goto out;
+ }
+ tsk->nsproxy->uts_ns = new_ns;
+
+out:
+ put_uts_ns(old_ns);
+ return err;
+}
+
+void free_uts_ns(struct kref *kref)
+{
+ struct uts_namespace *ns;
+
+ ns = container_of(kref, struct uts_namespace, kref);
+ kfree(ns);
+}
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-23 03:05:42 +0000