Merge branch 'next' into for-linus

Documentation/kernel-parameters.txt

@@ -1452,6 +1452,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			instruction doesn't work correctly and not to
 			use it.
 
+	no_file_caps	Tells the kernel not to honor file capabilities.  The
+			only way then for a file to be executed with privilege
+			is to be setuid root or executed by root.
+
 	nohalt		[IA-64] Tells the kernel not to use the power saving
 			function PAL_HALT_LIGHT when idle. This increases
 			power-consumption. On the positive side, it reduces

Documentation/scheduler/sched-design-CFS.txt

@@ -273,3 +273,24 @@ task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
 	# #Launch gmplayer (or your favourite movie player)
 	# echo <movie_player_pid> > multimedia/tasks
+
+8. Implementation note: user namespaces
+
+User namespaces are intended to be hierarchical.  But they are currently
+only partially implemented.  Each of those has ramifications for CFS.
+
+First, since user namespaces are hierarchical, the /sys/kernel/uids
+presentation is inadequate.  Eventually we will likely want to use sysfs
+tagging to provide private views of /sys/kernel/uids within each user
+namespace.
+
+Second, the hierarchical nature is intended to support completely
+unprivileged use of user namespaces.  So if using user groups, then
+we want the users in a user namespace to be children of the user
+who created it.
+
+That is currently unimplemented.  So instead, every user in a new
+user namespace will receive 1024 shares just like any user in the
+initial user namespace.  Note that at the moment creation of a new
+user namespace requires each of CAP_SYS_ADMIN, CAP_SETUID, and
+CAP_SETGID.

arch/alpha/kernel/asm-offsets.c

@@ -19,15 +19,18 @@ void foo(void)
 	BLANK();
 
         DEFINE(TASK_BLOCKED, offsetof(struct task_struct, blocked));
-        DEFINE(TASK_UID, offsetof(struct task_struct, uid));
-        DEFINE(TASK_EUID, offsetof(struct task_struct, euid));
-        DEFINE(TASK_GID, offsetof(struct task_struct, gid));
-        DEFINE(TASK_EGID, offsetof(struct task_struct, egid));
+        DEFINE(TASK_CRED, offsetof(struct task_struct, cred));
         DEFINE(TASK_REAL_PARENT, offsetof(struct task_struct, real_parent));
         DEFINE(TASK_GROUP_LEADER, offsetof(struct task_struct, group_leader));
         DEFINE(TASK_TGID, offsetof(struct task_struct, tgid));
         BLANK();
 
+        DEFINE(CRED_UID,  offsetof(struct cred, uid));
+        DEFINE(CRED_EUID, offsetof(struct cred, euid));
+        DEFINE(CRED_GID,  offsetof(struct cred, gid));
+        DEFINE(CRED_EGID, offsetof(struct cred, egid));
+        BLANK();
+
 	DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs));
 	DEFINE(PT_PTRACED, PT_PTRACED);
 	DEFINE(CLONE_VM, CLONE_VM);

arch/alpha/kernel/entry.S

@@ -850,8 +850,9 @@ osf_getpriority:
 sys_getxuid:
 	.prologue 0
 	ldq	$2, TI_TASK($8)
-	ldl	$0, TASK_UID($2)
-	ldl	$1, TASK_EUID($2)
+	ldq	$3, TASK_CRED($2)
+	ldl	$0, CRED_UID($3)
+	ldl	$1, CRED_EUID($3)
 	stq	$1, 80($sp)
 	ret
 .end sys_getxuid
@@ -862,8 +863,9 @@ sys_getxuid:
 sys_getxgid:
 	.prologue 0
 	ldq	$2, TI_TASK($8)
-	ldl	$0, TASK_GID($2)
-	ldl	$1, TASK_EGID($2)
+	ldq	$3, TASK_CRED($2)
+	ldl	$0, CRED_GID($3)
+	ldl	$1, CRED_EGID($3)
 	stq	$1, 80($sp)
 	ret
 .end sys_getxgid

arch/ia64/ia32/sys_ia32.c

@@ -1767,25 +1767,24 @@ groups16_from_user(struct group_info *group_info, short __user *grouplist)
 asmlinkage long
 sys32_getgroups16 (int gidsetsize, short __user *grouplist)
 {
+	const struct cred *cred = current_cred();
 	int i;
 
 	if (gidsetsize < 0)
 		return -EINVAL;
 
-	get_group_info(current->group_info);
-	i = current->group_info->ngroups;
+	i = cred->group_info->ngroups;
 	if (gidsetsize) {
 		if (i > gidsetsize) {
 			i = -EINVAL;
 			goto out;
 		}
-		if (groups16_to_user(grouplist, current->group_info)) {
+		if (groups16_to_user(grouplist, cred->group_info)) {
 			i = -EFAULT;
 			goto out;
 		}
 	}
 out:
-	put_group_info(current->group_info);
 	return i;
 }
 

arch/ia64/kernel/mca_drv.c

@@ -158,7 +158,7 @@ mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr)
 	ia64_mlogbuf_dump();
 	printk(KERN_ERR "OS_MCA: process [cpu %d, pid: %d, uid: %d, "
 		"iip: %p, psr: 0x%lx,paddr: 0x%lx](%s) encounters MCA.\n",
-		raw_smp_processor_id(), current->pid, current->uid,
+	       raw_smp_processor_id(), current->pid, current_uid(),
 		iip, ipsr, paddr, current->comm);
 
 	spin_lock(&mca_bh_lock);

arch/ia64/kernel/perfmon.c

@@ -2220,8 +2220,8 @@ pfm_alloc_file(pfm_context_t *ctx)
 	DPRINT(("new inode ino=%ld @%p\n", inode->i_ino, inode));
 
 	inode->i_mode = S_IFCHR|S_IRUGO;
-	inode->i_uid  = current->fsuid;
-	inode->i_gid  = current->fsgid;
+	inode->i_uid  = current_fsuid();
+	inode->i_gid  = current_fsgid();
 
 	sprintf(name, "[%lu]", inode->i_ino);
 	this.name = name;
@@ -2399,22 +2399,33 @@ error_kmem:
 static int
 pfm_bad_permissions(struct task_struct *task)
 {
+	const struct cred *tcred;
+	uid_t uid = current_uid();
+	gid_t gid = current_gid();
+	int ret;
+
+	rcu_read_lock();
+	tcred = __task_cred(task);
+
 	/* inspired by ptrace_attach() */
 	DPRINT(("cur: uid=%d gid=%d task: euid=%d suid=%d uid=%d egid=%d sgid=%d\n",
-		current->uid,
-		current->gid,
-		task->euid,
-		task->suid,
-		task->uid,
-		task->egid,
-		task->sgid));
+		uid,
+		gid,
+		tcred->euid,
+		tcred->suid,
+		tcred->uid,
+		tcred->egid,
+		tcred->sgid));
 
-	return ((current->uid != task->euid)
-	    || (current->uid != task->suid)
-	    || (current->uid != task->uid)
-	    || (current->gid != task->egid)
-	    || (current->gid != task->sgid)
-	    || (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE);
+	ret = ((uid != tcred->euid)
+	       || (uid != tcred->suid)
+	       || (uid != tcred->uid)
+	       || (gid != tcred->egid)
+	       || (gid != tcred->sgid)
+	       || (gid != tcred->gid)) && !capable(CAP_SYS_PTRACE);
+
+	rcu_read_unlock();
+	return ret;
 }
 
 static int

arch/ia64/kernel/signal.c

@@ -229,7 +229,7 @@ ia64_rt_sigreturn (struct sigscratch *scr)
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
 	si.si_pid = task_pid_vnr(current);
-	si.si_uid = current->uid;
+	si.si_uid = current_uid();
 	si.si_addr = sc;
 	force_sig_info(SIGSEGV, &si, current);
 	return retval;
@@ -326,7 +326,7 @@ force_sigsegv_info (int sig, void __user *addr)
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
 	si.si_pid = task_pid_vnr(current);
-	si.si_uid = current->uid;
+	si.si_uid = current_uid();
 	si.si_addr = addr;
 	force_sig_info(SIGSEGV, &si, current);
 	return 0;

arch/mips/kernel/kspd.c

@@ -174,8 +174,8 @@ static unsigned int translate_open_flags(int flags)
 
 static void sp_setfsuidgid( uid_t uid, gid_t gid)
 {
-	current->fsuid = uid;
-	current->fsgid = gid;
+	current->cred->fsuid = uid;
+	current->cred->fsgid = gid;
 
 	key_fsuid_changed(current);
 	key_fsgid_changed(current);

arch/mips/kernel/mips-mt-fpaff.c

@@ -51,6 +51,7 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len,
 	int retval;
 	struct task_struct *p;
 	struct thread_info *ti;
+	uid_t euid;
 
 	if (len < sizeof(new_mask))
 		return -EINVAL;
@@ -76,9 +77,9 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len,
 	 */
 	get_task_struct(p);
 
+	euid = current_euid();
 	retval = -EPERM;
-	if ((current->euid != p->euid) && (current->euid != p->uid) &&
-			!capable(CAP_SYS_NICE)) {
+	if (euid != p->euid && euid != p->uid && !capable(CAP_SYS_NICE)) {
 		read_unlock(&tasklist_lock);
 		goto out_unlock;
 	}

arch/mips/kernel/vpe.c

@@ -1085,8 +1085,8 @@ static int vpe_open(struct inode *inode, struct file *filp)
 	v->load_addr = NULL;
 	v->len = 0;
 
-	v->uid = filp->f_uid;
-	v->gid = filp->f_gid;
+	v->uid = filp->f_cred->fsuid;
+	v->gid = filp->f_cred->fsgid;
 
 #ifdef CONFIG_MIPS_APSP_KSPD
 	/* get kspd to tell us when a syscall_exit happens */

arch/parisc/kernel/signal.c

@@ -182,7 +182,7 @@ give_sigsegv:
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
 	si.si_pid = task_pid_vnr(current);
-	si.si_uid = current->uid;
+	si.si_uid = current_uid();
 	si.si_addr = &frame->uc;
 	force_sig_info(SIGSEGV, &si, current);
 	return;

arch/powerpc/mm/fault.c

@@ -339,7 +339,7 @@ bad_area_nosemaphore:
 	    && printk_ratelimit())
 		printk(KERN_CRIT "kernel tried to execute NX-protected"
 		       " page (%lx) - exploit attempt? (uid: %d)\n",
-		       address, current->uid);
+		       address, current_uid());
 
 	return SIGSEGV;
 

arch/powerpc/platforms/cell/spufs/inode.c

@@ -95,8 +95,8 @@ spufs_new_inode(struct super_block *sb, int mode)
 		goto out;
 
 	inode->i_mode = mode;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
 	inode->i_blocks = 0;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 out:
@@ -323,7 +323,7 @@ static int spufs_context_open(struct dentry *dentry, struct vfsmount *mnt)
 		goto out;
 	}
 
-	filp = dentry_open(dentry, mnt, O_RDONLY);
+	filp = dentry_open(dentry, mnt, O_RDONLY, current_cred());
 	if (IS_ERR(filp)) {
 		put_unused_fd(ret);
 		ret = PTR_ERR(filp);
@@ -562,7 +562,7 @@ static int spufs_gang_open(struct dentry *dentry, struct vfsmount *mnt)
 		goto out;
 	}
 
-	filp = dentry_open(dentry, mnt, O_RDONLY);
+	filp = dentry_open(dentry, mnt, O_RDONLY, current_cred());
 	if (IS_ERR(filp)) {
 		put_unused_fd(ret);
 		ret = PTR_ERR(filp);

arch/s390/hypfs/inode.c

@@ -280,8 +280,8 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sbi)
 		return -ENOMEM;
 	mutex_init(&sbi->lock);
-	sbi->uid = current->uid;
-	sbi->gid = current->gid;
+	sbi->uid = current_uid();
+	sbi->gid = current_gid();
 	sb->s_fs_info = sbi;
 	sb->s_blocksize = PAGE_CACHE_SIZE;
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;

arch/s390/kernel/compat_linux.c

@@ -148,9 +148,9 @@ asmlinkage long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user
 {
 	int retval;
 
-	if (!(retval = put_user(high2lowuid(current->uid), ruid)) &&
-	    !(retval = put_user(high2lowuid(current->euid), euid)))
-		retval = put_user(high2lowuid(current->suid), suid);
+	if (!(retval = put_user(high2lowuid(current->cred->uid), ruid)) &&
+	    !(retval = put_user(high2lowuid(current->cred->euid), euid)))
+		retval = put_user(high2lowuid(current->cred->suid), suid);
 
 	return retval;
 }
@@ -165,9 +165,9 @@ asmlinkage long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user
 {
 	int retval;
 
-	if (!(retval = put_user(high2lowgid(current->gid), rgid)) &&
-	    !(retval = put_user(high2lowgid(current->egid), egid)))
-		retval = put_user(high2lowgid(current->sgid), sgid);
+	if (!(retval = put_user(high2lowgid(current->cred->gid), rgid)) &&
+	    !(retval = put_user(high2lowgid(current->cred->egid), egid)))
+		retval = put_user(high2lowgid(current->cred->sgid), sgid);
 
 	return retval;
 }
@@ -217,20 +217,20 @@ asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist)
 	if (gidsetsize < 0)
 		return -EINVAL;
 
-	get_group_info(current->group_info);
-	i = current->group_info->ngroups;
+	get_group_info(current->cred->group_info);
+	i = current->cred->group_info->ngroups;
 	if (gidsetsize) {
 		if (i > gidsetsize) {
 			i = -EINVAL;
 			goto out;
 		}
-		if (groups16_to_user(grouplist, current->group_info)) {
+		if (groups16_to_user(grouplist, current->cred->group_info)) {
 			i = -EFAULT;
 			goto out;
 		}
 	}
 out:
-	put_group_info(current->group_info);
+	put_group_info(current->cred->group_info);
 	return i;
 }
 
@@ -261,22 +261,22 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
 
 asmlinkage long sys32_getuid16(void)
 {
-	return high2lowuid(current->uid);
+	return high2lowuid(current->cred->uid);
 }
 
 asmlinkage long sys32_geteuid16(void)
 {
-	return high2lowuid(current->euid);
+	return high2lowuid(current->cred->euid);
 }
 
 asmlinkage long sys32_getgid16(void)
 {
-	return high2lowgid(current->gid);
+	return high2lowgid(current->cred->gid);
 }
 
 asmlinkage long sys32_getegid16(void)
 {
-	return high2lowgid(current->egid);
+	return high2lowgid(current->cred->egid);
 }
 
 /*

arch/um/drivers/mconsole_kern.c

@@ -161,7 +161,8 @@ void mconsole_proc(struct mc_request *req)
 		goto out_kill;
 	}
 
-	file = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY);
+	file = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY,
+			   current_cred());
 	if (IS_ERR(file)) {
 		mconsole_reply(req, "Failed to open file", 1, 0);
 		goto out_kill;

arch/x86/ia32/ia32_aout.c

@@ -327,7 +327,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	current->mm->cached_hole_size = 0;
 
 	current->mm->mmap = NULL;
-	compute_creds(bprm);
+	install_exec_creds(bprm);
 	current->flags &= ~PF_FORKNOEXEC;
 
 	if (N_MAGIC(ex) == OMAGIC) {

arch/x86/mm/fault.c

@@ -393,7 +393,7 @@ static void show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		if (pte && pte_present(*pte) && !pte_exec(*pte))
 			printk(KERN_CRIT "kernel tried to execute "
 				"NX-protected page - exploit attempt? "
-				"(uid: %d)\n", current->uid);
+				"(uid: %d)\n", current_uid());
 	}
 #endif