Merge branch 'linus' into x86/header-guards

Conflicts:

	include/asm-x86/gpio.h
	include/asm-x86/ide.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 128 insertions, 141 deletions

diff --git a/security/Kconfig b/security/Kconfig
index 62ed4717d33..559293922a4 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -74,8 +74,7 @@ config SECURITY_NETWORK_XFRM
 	  If you are unsure how to answer this question, answer N.
 
 config SECURITY_FILE_CAPABILITIES
-	bool "File POSIX Capabilities (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	bool "File POSIX Capabilities"
 	default n
 	help
 	  This enables filesystem capabilities, allowing you to give
diff --git a/security/commoncap.c b/security/commoncap.c
index 0b6537a3672..4afbece37a0 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -162,8 +162,7 @@ void cap_capset_set (struct task_struct *target, kernel_cap_t *effective,
 
 static inline void bprm_clear_caps(struct linux_binprm *bprm)
 {
-	cap_clear(bprm->cap_inheritable);
-	cap_clear(bprm->cap_permitted);
+	cap_clear(bprm->cap_post_exec_permitted);
 	bprm->cap_effective = false;
 }
 
@@ -198,6 +197,7 @@ static inline int cap_from_disk(struct vfs_cap_data *caps,
 {
 	__u32 magic_etc;
 	unsigned tocopy, i;
+	int ret;
 
 	if (size < sizeof(magic_etc))
 		return -EINVAL;
@@ -225,19 +225,40 @@ static inline int cap_from_disk(struct vfs_cap_data *caps,
 		bprm->cap_effective = false;
 	}
 
-	for (i = 0; i < tocopy; ++i) {
-		bprm->cap_permitted.cap[i] =
-			le32_to_cpu(caps->data[i].permitted);
-		bprm->cap_inheritable.cap[i] =
-			le32_to_cpu(caps->data[i].inheritable);
-	}
-	while (i < VFS_CAP_U32) {
-		bprm->cap_permitted.cap[i] = 0;
-		bprm->cap_inheritable.cap[i] = 0;
-		i++;
+	ret = 0;
+
+	CAP_FOR_EACH_U32(i) {
+		__u32 value_cpu;
+
+		if (i >= tocopy) {
+			/*
+			 * Legacy capability sets have no upper bits
+			 */
+			bprm->cap_post_exec_permitted.cap[i] = 0;
+			continue;
+		}
+		/*
+		 * pP' = (X & fP) | (pI & fI)
+		 */
+		value_cpu = le32_to_cpu(caps->data[i].permitted);
+		bprm->cap_post_exec_permitted.cap[i] =
+			(current->cap_bset.cap[i] & value_cpu) |
+			(current->cap_inheritable.cap[i] &
+				le32_to_cpu(caps->data[i].inheritable));
+		if (value_cpu & ~bprm->cap_post_exec_permitted.cap[i]) {
+			/*
+			 * insufficient to execute correctly
+			 */
+			ret = -EPERM;
+		}
 	}
 
-	return 0;
+	/*
+	 * For legacy apps, with no internal support for recognizing they
+	 * do not have enough capabilities, we return an error if they are
+	 * missing some "forced" (aka file-permitted) capabilities.
+	 */
+	return bprm->cap_effective ? ret : 0;
 }
 
 /* Locate any VFS capabilities: */
@@ -269,9 +290,9 @@ static int get_file_caps(struct linux_binprm *bprm)
 		goto out;
 
 	rc = cap_from_disk(&vcaps, bprm, rc);
-	if (rc)
+	if (rc == -EINVAL)
 		printk(KERN_NOTICE "%s: cap_from_disk returned %d for %s\n",
-			__func__, rc, bprm->filename);
+		       __func__, rc, bprm->filename);
 
 out:
 	dput(dentry);
@@ -304,25 +325,24 @@ int cap_bprm_set_security (struct linux_binprm *bprm)
 	int ret;
 
 	ret = get_file_caps(bprm);
-	if (ret)
-		printk(KERN_NOTICE "%s: get_file_caps returned %d for %s\n",
-			__func__, ret, bprm->filename);
-
-	/*  To support inheritance of root-permissions and suid-root
-	 *  executables under compatibility mode, we raise all three
-	 *  capability sets for the file.
-	 *
-	 *  If only the real uid is 0, we only raise the inheritable
-	 *  and permitted sets of the executable file.
-	 */
 
-	if (!issecure (SECURE_NOROOT)) {
+	if (!issecure(SECURE_NOROOT)) {
+		/*
+		 * To support inheritance of root-permissions and suid-root
+		 * executables under compatibility mode, we override the
+		 * capability sets for the file.
+		 *
+		 * If only the real uid is 0, we do not set the effective
+		 * bit.
+		 */
 		if (bprm->e_uid == 0 || current->uid == 0) {
-			cap_set_full (bprm->cap_inheritable);
-			cap_set_full (bprm->cap_permitted);
+			/* pP' = (cap_bset & ~0) | (pI & ~0) */
+			bprm->cap_post_exec_permitted = cap_combine(
+				current->cap_bset, current->cap_inheritable
+				);
+			bprm->cap_effective = (bprm->e_uid == 0);
+			ret = 0;
 		}
-		if (bprm->e_uid == 0)
-			bprm->cap_effective = true;
 	}
 
 	return ret;
@@ -330,17 +350,9 @@ int cap_bprm_set_security (struct linux_binprm *bprm)
 
 void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
 {
-	/* Derived from fs/exec.c:compute_creds. */
-	kernel_cap_t new_permitted, working;
-
-	new_permitted = cap_intersect(bprm->cap_permitted,
-				 current->cap_bset);
-	working = cap_intersect(bprm->cap_inheritable,
-				 current->cap_inheritable);
-	new_permitted = cap_combine(new_permitted, working);
-
 	if (bprm->e_uid != current->uid || bprm->e_gid != current->gid ||
-	    !cap_issubset (new_permitted, current->cap_permitted)) {
+	    !cap_issubset(bprm->cap_post_exec_permitted,
+			  current->cap_permitted)) {
 		set_dumpable(current->mm, suid_dumpable);
 		current->pdeath_signal = 0;
 
@@ -350,9 +362,9 @@ void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
 				bprm->e_gid = current->gid;
 			}
 			if (cap_limit_ptraced_target()) {
-				new_permitted =
-					cap_intersect(new_permitted,
-						      current->cap_permitted);
+				bprm->cap_post_exec_permitted = cap_intersect(
+					bprm->cap_post_exec_permitted,
+					current->cap_permitted);
 			}
 		}
 	}
@@ -364,9 +376,9 @@ void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
 	 * in the init_task struct. Thus we skip the usual
 	 * capability rules */
 	if (!is_global_init(current)) {
-		current->cap_permitted = new_permitted;
+		current->cap_permitted = bprm->cap_post_exec_permitted;
 		if (bprm->cap_effective)
-			current->cap_effective = new_permitted;
+			current->cap_effective = bprm->cap_post_exec_permitted;
 		else
 			cap_clear(current->cap_effective);
 	}
@@ -381,9 +393,7 @@ int cap_bprm_secureexec (struct linux_binprm *bprm)
 	if (current->uid != 0) {
 		if (bprm->cap_effective)
 			return 1;
-		if (!cap_isclear(bprm->cap_permitted))
-			return 1;
-		if (!cap_isclear(bprm->cap_inheritable))
+		if (!cap_isclear(bprm->cap_post_exec_permitted))
 			return 1;
 	}
 
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index ddd92cec78e..7bd296cca04 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -41,6 +41,7 @@ struct dev_whitelist_item {
 	short type;
 	short access;
 	struct list_head list;
+	struct rcu_head rcu;
 };
 
 struct dev_cgroup {
@@ -59,6 +60,11 @@ static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup)
 	return css_to_devcgroup(cgroup_subsys_state(cgroup, devices_subsys_id));
 }
 
+static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
+{
+	return css_to_devcgroup(task_subsys_state(task, devices_subsys_id));
+}
+
 struct cgroup_subsys devices_subsys;
 
 static int devcgroup_can_attach(struct cgroup_subsys *ss,
@@ -128,11 +134,19 @@ static int dev_whitelist_add(struct dev_cgroup *dev_cgroup,
 	}
 
 	if (whcopy != NULL)
-		list_add_tail(&whcopy->list, &dev_cgroup->whitelist);
+		list_add_tail_rcu(&whcopy->list, &dev_cgroup->whitelist);
 	spin_unlock(&dev_cgroup->lock);
 	return 0;
 }
 
+static void whitelist_item_free(struct rcu_head *rcu)
+{
+	struct dev_whitelist_item *item;
+
+	item = container_of(rcu, struct dev_whitelist_item, rcu);
+	kfree(item);
+}
+
 /*
  * called under cgroup_lock()
  * since the list is visible to other tasks, we need the spinlock also
@@ -156,8 +170,8 @@ static void dev_whitelist_rm(struct dev_cgroup *dev_cgroup,
 remove:
 		walk->access &= ~wh->access;
 		if (!walk->access) {
-			list_del(&walk->list);
-			kfree(walk);
+			list_del_rcu(&walk->list);
+			call_rcu(&walk->rcu, whitelist_item_free);
 		}
 	}
 	spin_unlock(&dev_cgroup->lock);
@@ -188,7 +202,7 @@ static struct cgroup_subsys_state *devcgroup_create(struct cgroup_subsys *ss,
 		}
 		wh->minor = wh->major = ~0;
 		wh->type = DEV_ALL;
-		wh->access = ACC_MKNOD | ACC_READ | ACC_WRITE;
+		wh->access = ACC_MASK;
 		list_add(&wh->list, &dev_cgroup->whitelist);
 	} else {
 		parent_dev_cgroup = cgroup_to_devcgroup(parent_cgroup);
@@ -250,11 +264,10 @@ static char type_to_char(short type)
 
 static void set_majmin(char *str, unsigned m)
 {
-	memset(str, 0, MAJMINLEN);
 	if (m == ~0)
-		sprintf(str, "*");
+		strcpy(str, "*");
 	else
-		snprintf(str, MAJMINLEN, "%u", m);
+		sprintf(str, "%u", m);
 }
 
 static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
@@ -264,15 +277,15 @@ static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
 	struct dev_whitelist_item *wh;
 	char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
 
-	spin_lock(&devcgroup->lock);
-	list_for_each_entry(wh, &devcgroup->whitelist, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(wh, &devcgroup->whitelist, list) {
 		set_access(acc, wh->access);
 		set_majmin(maj, wh->major);
 		set_majmin(min, wh->minor);
 		seq_printf(m, "%c %s:%s %s\n", type_to_char(wh->type),
 			   maj, min, acc);
 	}
-	spin_unlock(&devcgroup->lock);
+	rcu_read_unlock();
 
 	return 0;
 }
@@ -312,10 +325,10 @@ static int may_access_whitelist(struct dev_cgroup *c,
  * when adding a new allow rule to a device whitelist, the rule
  * must be allowed in the parent device
  */
-static int parent_has_perm(struct cgroup *childcg,
+static int parent_has_perm(struct dev_cgroup *childcg,
 				  struct dev_whitelist_item *wh)
 {
-	struct cgroup *pcg = childcg->parent;
+	struct cgroup *pcg = childcg->css.cgroup->parent;
 	struct dev_cgroup *parent;
 	int ret;
 
@@ -341,39 +354,19 @@ static int parent_has_perm(struct cgroup *childcg,
  * new access is only allowed if you're in the top-level cgroup, or your
  * parent cgroup has the access you're asking for.
  */
-static ssize_t devcgroup_access_write(struct cgroup *cgroup, struct cftype *cft,
-				struct file *file, const char __user *userbuf,
-				size_t nbytes, loff_t *ppos)
+static int devcgroup_update_access(struct dev_cgroup *devcgroup,
+				   int filetype, const char *buffer)
 {
-	struct cgroup *cur_cgroup;
-	struct dev_cgroup *devcgroup, *cur_devcgroup;
-	int filetype = cft->private;
-	char *buffer, *b;
+	struct dev_cgroup *cur_devcgroup;
+	const char *b;
+	char *endp;
 	int retval = 0, count;
 	struct dev_whitelist_item wh;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	devcgroup = cgroup_to_devcgroup(cgroup);
-	cur_cgroup = task_cgroup(current, devices_subsys.subsys_id);
-	cur_devcgroup = cgroup_to_devcgroup(cur_cgroup);
-
-	buffer = kmalloc(nbytes+1, GFP_KERNEL);
-	if (!buffer)
-		return -ENOMEM;
-
-	if (copy_from_user(buffer, userbuf, nbytes)) {
-		retval = -EFAULT;
-		goto out1;
-	}
-	buffer[nbytes] = 0;	/* nul-terminate */
-
-	cgroup_lock();
-	if (cgroup_is_removed(cgroup)) {
-		retval = -ENODEV;
-		goto out2;
-	}
+	cur_devcgroup = task_devcgroup(current);
 
 	memset(&wh, 0, sizeof(wh));
 	b = buffer;
@@ -392,32 +385,23 @@ static ssize_t devcgroup_access_write(struct cgroup *cgroup, struct cftype *cft,
 		wh.type = DEV_CHAR;
 		break;
 	default:
-		retval = -EINVAL;
-		goto out2;
+		return -EINVAL;
 	}
 	b++;
-	if (!isspace(*b)) {
-		retval = -EINVAL;
-		goto out2;
-	}
+	if (!isspace(*b))
+		return -EINVAL;
 	b++;
 	if (*b == '*') {
 		wh.major = ~0;
 		b++;
 	} else if (isdigit(*b)) {
-		wh.major = 0;
-		while (isdigit(*b)) {
-			wh.major = wh.major*10+(*b-'0');
-			b++;
-		}
+		wh.major = simple_strtoul(b, &endp, 10);
+		b = endp;
 	} else {
-		retval = -EINVAL;
-		goto out2;
-	}
-	if (*b != ':') {
-		retval = -EINVAL;
-		goto out2;
+		return -EINVAL;
 	}
+	if (*b != ':')
+		return -EINVAL;
 	b++;
 
 	/* read minor */
@@ -425,19 +409,13 @@ static ssize_t devcgroup_access_write(struct cgroup *cgroup, struct cftype *cft,
 		wh.minor = ~0;
 		b++;
 	} else if (isdigit(*b)) {
-		wh.minor = 0;
-		while (isdigit(*b)) {
-			wh.minor = wh.minor*10+(*b-'0');
-			b++;
-		}
+		wh.minor = simple_strtoul(b, &endp, 10);
+		b = endp;
 	} else {
-		retval = -EINVAL;
-		goto out2;
-	}
-	if (!isspace(*b)) {
-		retval = -EINVAL;
-		goto out2;
+		return -EINVAL;
 	}
+	if (!isspace(*b))
+		return -EINVAL;
 	for (b++, count = 0; count < 3; count++, b++) {
 		switch (*b) {
 		case 'r':
@@ -454,8 +432,7 @@ static ssize_t devcgroup_access_write(struct cgroup *cgroup, struct cftype *cft,
 			count = 3;
 			break;
 		default:
-			retval = -EINVAL;
-			goto out2;
+			return -EINVAL;
 		}
 	}
 
@@ -463,38 +440,39 @@ handle:
 	retval = 0;
 	switch (filetype) {
 	case DEVCG_ALLOW:
-		if (!parent_has_perm(cgroup, &wh))
-			retval = -EPERM;
-		else
-			retval = dev_whitelist_add(devcgroup, &wh);
-		break;
+		if (!parent_has_perm(devcgroup, &wh))
+			return -EPERM;
+		return dev_whitelist_add(devcgroup, &wh);
 	case DEVCG_DENY:
 		dev_whitelist_rm(devcgroup, &wh);
 		break;
 	default:
-		retval = -EINVAL;
-		goto out2;
+		return -EINVAL;
 	}
+	return 0;
+}
 
-	if (retval == 0)
-		retval = nbytes;
-
-out2:
+static int devcgroup_access_write(struct cgroup *cgrp, struct cftype *cft,
+				  const char *buffer)
+{
+	int retval;
+	if (!cgroup_lock_live_group(cgrp))
+		return -ENODEV;
+	retval = devcgroup_update_access(cgroup_to_devcgroup(cgrp),
+					 cft->private, buffer);
 	cgroup_unlock();
-out1:
-	kfree(buffer);
 	return retval;
 }
 
 static struct cftype dev_cgroup_files[] = {
 	{
 		.name = "allow",
-		.write  = devcgroup_access_write,
+		.write_string  = devcgroup_access_write,
 		.private = DEVCG_ALLOW,
 	},
 	{
 		.name = "deny",
-		.write = devcgroup_access_write,
+		.write_string = devcgroup_access_write,
 		.private = DEVCG_DENY,
 	},
 	{
@@ -535,8 +513,8 @@ int devcgroup_inode_permission(struct inode *inode, int mask)
 	if (!dev_cgroup)
 		return 0;
 
-	spin_lock(&dev_cgroup->lock);
-	list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(wh, &dev_cgroup->whitelist, list) {
 		if (wh->type & DEV_ALL)
 			goto acc_check;
 		if ((wh->type & DEV_BLOCK) && !S_ISBLK(inode->i_mode))
@@ -552,10 +530,10 @@ acc_check:
 			continue;
 		if ((mask & MAY_READ) && !(wh->access & ACC_READ))
 			continue;
-		spin_unlock(&dev_cgroup->lock);
+		rcu_read_unlock();
 		return 0;
 	}
-	spin_unlock(&dev_cgroup->lock);
+	rcu_read_unlock();
 
 	return -EPERM;
 }
@@ -570,7 +548,7 @@ int devcgroup_inode_mknod(int mode, dev_t dev)
 	if (!dev_cgroup)
 		return 0;
 
-	spin_lock(&dev_cgroup->lock);
+	rcu_read_lock();
 	list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
 		if (wh->type & DEV_ALL)
 			goto acc_check;
@@ -585,9 +563,9 @@ int devcgroup_inode_mknod(int mode, dev_t dev)
 acc_check:
 		if (!(wh->access & ACC_MKNOD))
 			continue;
-		spin_unlock(&dev_cgroup->lock);
+		rcu_read_unlock();
 		return 0;
 	}
-	spin_unlock(&dev_cgroup->lock);
+	rcu_read_unlock();
 	return -EPERM;
 }