Skip to contentSkip to conversation

security: capabilities patch (version 0.4.3), part 1/4: enlarge capability sets

PATCH New David Madore 1 participant 4 messages Sep 8, 2006

Subsystems (8)
VFS MM core Scheduler Security (LSM) +4 more subsystems
lore
Share & tools
lore
#0 lore raw

PATCH 1/4 security: capabilities patch (version 0.4.3), part 1/4: enlarge capability sets

Increase the size of capability sets to 64 bits:

* bits 32-47 are "regular", i.e., present by default on non-root processes;

* maintain compatibility with former kernel interface for capset() and capget().

See <URL: http://www.madore.org/~david/linux/newcaps/ > for more detailed explanations.

---
 fs/open.c                  |    3 ++-
 fs/proc/array.c            |    6 +++---
 include/linux/capability.h |   30 ++++++++++++++++++-----------
 kernel/capability.c        |   46 +++++++++++++++++++++++++++++++++++---------
 security/commoncap.c       |   16 +++++++++++----
 security/dummy.c           |    6 +++---
 6 files changed, 75 insertions(+), 32 deletions(-)
fs/open.c +2 -1
index 303f06d..e58a525 100644
@@ -515,7 +515,8 @@ asmlinkage long sys_faccessat(int dfd, c
 	 * but we cannot because user_path_walk can sleep.
 	 */
 	if (current->uid)
-		cap_clear(current->cap_effective);
+		current->cap_effective = cap_intersect(current->cap_effective,
+						       CAP_REGULAR_SET);
 	else
 		current->cap_effective = current->cap_permitted;
 
fs/proc/array.c +3 -3
index 0b615d6..6724fc2 100644
@@ -285,9 +285,9 @@ static inline char * task_sig(struct tas
 
 static inline char *task_cap(struct task_struct *p, char *buffer)
 {
-    return buffer + sprintf(buffer, "CapInh:\t%016x\n"
-			    "CapPrm:\t%016x\n"
-			    "CapEff:\t%016x\n",
+    return buffer + sprintf(buffer, "CapInh:\t%016llx\n"
+			    "CapPrm:\t%016llx\n"
+			    "CapEff:\t%016llx\n",
 			    cap_t(p->cap_inheritable),
 			    cap_t(p->cap_permitted),
 			    cap_t(p->cap_effective));
include/linux/capability.h +19 -11
index 6548b35..aa00b60 100644
@@ -27,7 +27,8 @@ #include <linux/compiler.h>
    library since the draft standard requires the use of malloc/free
    etc.. */
  
-#define _LINUX_CAPABILITY_VERSION  0x19980330
+#define _LINUX_CAPABILITY_VERSION  0x20060903
+#define _LINUX_CAPABILITY_OLD_VERSION  0x19980330
 
 typedef struct __user_cap_header_struct {
 	__u32 version;
@@ -35,10 +36,16 @@ typedef struct __user_cap_header_struct 
 } __user *cap_user_header_t;
  
 typedef struct __user_cap_data_struct {
+        __u64 effective;
+        __u64 permitted;
+        __u64 inheritable;
+} __user *cap_user_data_t;
+ 
+typedef struct __user_cap_data_old_struct {
         __u32 effective;
         __u32 permitted;
         __u32 inheritable;
-} __user *cap_user_data_t;
+} __user *cap_user_data_old_t;
   
 #ifdef __KERNEL__
 
@@ -50,12 +57,12 @@ #include <asm/current.h>
 #ifdef STRICT_CAP_T_TYPECHECKS
 
 typedef struct kernel_cap_struct {
-	__u32 cap;
+	__u64 cap;
 } kernel_cap_t;
 
 #else
 
-typedef __u32 kernel_cap_t;
+typedef __u64 kernel_cap_t;
 
 #endif
   
@@ -310,12 +317,13 @@ #define cap_t(x) (x)
 
 #endif
 
-#define CAP_EMPTY_SET       to_cap_t(0)
-#define CAP_FULL_SET        to_cap_t(~0)
-#define CAP_INIT_EFF_SET    to_cap_t(~0 & ~CAP_TO_MASK(CAP_SETPCAP))
-#define CAP_INIT_INH_SET    to_cap_t(0)
+#define CAP_EMPTY_SET       to_cap_t(0ULL)
+#define CAP_FULL_SET        to_cap_t(~0ULL)
+#define CAP_REGULAR_SET     to_cap_t(0x0000ffff00000000ULL)
+#define CAP_INIT_EFF_SET    to_cap_t(~0ULL)
+#define CAP_INIT_INH_SET    to_cap_t(~0ULL)
 
-#define CAP_TO_MASK(x) (1 << (x))
+#define CAP_TO_MASK(x) (1ULL << (x))
 #define cap_raise(c, flag)   (cap_t(c) |=  CAP_TO_MASK(flag))
 #define cap_lower(c, flag)   (cap_t(c) &= ~CAP_TO_MASK(flag))
 #define cap_raised(c, flag)  (cap_t(c) & CAP_TO_MASK(flag))
@@ -351,8 +359,8 @@ static inline kernel_cap_t cap_invert(ke
 #define cap_isclear(c)       (!cap_t(c))
 #define cap_issubset(a,set)  (!(cap_t(a) & ~cap_t(set)))
 
-#define cap_clear(c)         do { cap_t(c) =  0; } while(0)
-#define cap_set_full(c)      do { cap_t(c) = ~0; } while(0)
+#define cap_clear(c)         do { cap_t(c) =  0ULL; } while(0)
+#define cap_set_full(c)      do { cap_t(c) = ~0ULL; } while(0)
 #define cap_mask(c,mask)     do { cap_t(c) &= cap_t(mask); } while(0)
 
 #define cap_is_fs_cap(c)     (CAP_TO_MASK(c) & CAP_FS_MASK)
kernel/capability.c +37 -9

76 lines not on this page · raw message

security/commoncap.c +11 -5
index f50fc29..91dc53d 100644
@@ -244,13 +244,19 @@ static inline void cap_emulate_setxuid (
 					int old_suid)
 {
 	if ((old_ruid == 0 || old_euid == 0 || old_suid == 0) &&
-	    (current->uid != 0 && current->euid != 0 && current->suid != 0) &&
-	    !current->keep_capabilities) {
-		cap_clear (current->cap_permitted);
-		cap_clear (current->cap_effective);
+	    (current->uid != 0 && current->euid != 0 && current->suid != 0)) {
+		if (!current->keep_capabilities) {
+			current->cap_permitted
+				= cap_intersect (current->cap_permitted,
+						 CAP_REGULAR_SET);
+			current->cap_effective
+				= cap_intersect (current->cap_effective,
+						 CAP_REGULAR_SET);
+		}
 	}
 	if (old_euid == 0 && current->euid != 0) {
-		cap_clear (current->cap_effective);
+		current->cap_effective = cap_intersect (current->cap_effective,
+							CAP_REGULAR_SET);
 	}
 	if (old_euid != 0 && current->euid == 0) {
 		current->cap_effective = current->cap_permitted;
security/dummy.c +3 -3
index 58c6d39..572a15b 100644
@@ -37,11 +37,11 @@ static int dummy_ptrace (struct task_str
 static int dummy_capget (struct task_struct *target, kernel_cap_t * effective,
 			 kernel_cap_t * inheritable, kernel_cap_t * permitted)
 {
-	*effective = *inheritable = *permitted = 0;
+	*effective = *inheritable = *permitted = CAP_REGULAR_SET;
 	if (!issecure(SECURE_NOROOT)) {
 		if (target->euid == 0) {
-			*permitted |= (~0 & ~CAP_FS_MASK);
-			*effective |= (~0 & ~CAP_TO_MASK(CAP_SETPCAP) & ~CAP_FS_MASK);
+			*permitted |= (CAP_FULL_SET & ~CAP_FS_MASK);
+			*effective |= (CAP_FULL_SET & ~CAP_TO_MASK(CAP_SETPCAP) & ~CAP_FS_MASK);
 		}
 		if (target->fsuid == 0) {
 			*permitted |= CAP_FS_MASK;
#1 lore raw

PATCH 2/4 security: capabilities patch (version 0.4.3), part 2/4: change inheritance semantics

Make capabilities inheritable by default. The following remarks apply:

* executables are assumed by default to have a full set of "inheritable" (allowed) and "effective" capabilities,

* w.r.t. capabilities(7)-documented behavior, inheritance of the effective bits is changed (use P(eff) rather than F(eff) in half of the formula),

* also, inheritance of the inheritable set is based on the new permitted set rather than on the old inheritable.

See <URL: http://www.madore.org/~david/linux/newcaps/ > for more detailed explanations.

---
 fs/exec.c               |    4 +++
 include/linux/binfmts.h |    1 +
 kernel/capability.c     |    2 +
 security/commoncap.c    |   69 ++++++++++++++++++++++++++++-------------------
 4 files changed, 47 insertions(+), 29 deletions(-)
fs/exec.c +4 -0
index 54135df..e4d0a2c 100644
@@ -925,10 +925,13 @@ int prepare_binprm(struct linux_binprm *
 
 	bprm->e_uid = current->euid;
 	bprm->e_gid = current->egid;
+	bprm->is_suid = 0;
+	bprm->is_sgid = 0;
 
 	if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) {
 		/* Set-uid? */
 		if (mode & S_ISUID) {
+			bprm->is_suid = 1;
 			current->personality &= ~PER_CLEAR_ON_SETID;
 			bprm->e_uid = inode->i_uid;
 		}
@@ -940,6 +943,7 @@ int prepare_binprm(struct linux_binprm *
 		 * executable.
 		 */
 		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
+			bprm->is_sgid = 1;
 			current->personality &= ~PER_CLEAR_ON_SETID;
 			bprm->e_gid = inode->i_gid;
 		}
include/linux/binfmts.h +1 -0
index c1e82c5..c7fb183 100644
@@ -29,6 +29,7 @@ struct linux_binprm{
 	struct file * file;
 	int e_uid, e_gid;
 	kernel_cap_t cap_inheritable, cap_permitted, cap_effective;
+	char is_suid, is_sgid;
 	void *security;
 	int argc, envc;
 	char * filename;	/* Name of binary as seen by procps */
kernel/capability.c +1 -1
index 32b2521..2bb802a 100644
@@ -15,7 +15,7 @@ #include <linux/syscalls.h>
 #include <asm/uaccess.h>
 
 unsigned securebits = SECUREBITS_DEFAULT; /* systemwide security settings */
-kernel_cap_t cap_bset = CAP_INIT_EFF_SET;
+kernel_cap_t cap_bset = CAP_INIT_INH_SET;
 
 EXPORT_SYMBOL(securebits);
 EXPORT_SYMBOL(cap_bset);
security/commoncap.c +41 -28

140 lines not on this page · raw message

#2 lore raw

PATCH 3/4 security: capabilities patch (version 0.4.3), part 3/4: introduce new capabilities

In reply to David Madore

Introduce six new "regular" (=on-by-default) capabilities:

* CAP_REG_FORK, CAP_REG_OPEN, CAP_REG_EXEC allow access to the fork(), open() and exec() syscalls,

* CAP_REG_SXID allows privilege gain on suid/sgid exec,

* CAP_REG_WRITE controls any write-access to the filesystem,

* CAP_REG_PTRACE allows ptrace().

See <URL: http://www.madore.org/~david/linux/newcaps/ > for more detailed explanations.

---
 fs/exec.c                  |    7 +++++--
 fs/namei.c                 |    2 +-
 fs/open.c                  |   26 ++++++++++++++++++++------
 fs/xattr.c                 |    3 ++-
 include/linux/capability.h |   23 +++++++++++++++++++++++
 kernel/fork.c              |    2 ++
 kernel/ptrace.c            |    2 ++
 7 files changed, 55 insertions(+), 10 deletions(-)
fs/exec.c +5 -2
index e4d0a2c..1cb5e34 100644
@@ -930,7 +930,7 @@ int prepare_binprm(struct linux_binprm *
 
 	if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) {
 		/* Set-uid? */
-		if (mode & S_ISUID) {
+		if (mode & S_ISUID && capable(CAP_REG_SXID)) {
 			bprm->is_suid = 1;
 			current->personality &= ~PER_CLEAR_ON_SETID;
 			bprm->e_uid = inode->i_uid;
@@ -942,7 +942,8 @@ int prepare_binprm(struct linux_binprm *
 		 * is a candidate for mandatory locking, not a setgid
 		 * executable.
 		 */
-		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
+		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)
+		    && capable(CAP_REG_SXID)) {
 			bprm->is_sgid = 1;
 			current->personality &= ~PER_CLEAR_ON_SETID;
 			bprm->e_gid = inode->i_gid;
@@ -1137,6 +1138,8 @@ int do_execve(char * filename,
 	int retval;
 	int i;
 
+	if (!capable(CAP_REG_EXEC))
+		return -EPERM;
 	retval = -ENOMEM;
 	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
 	if (!bprm)
fs/namei.c +1 -1
index 432d6bc..69a3bae 100644
@@ -242,7 +242,7 @@ int permission(struct inode *inode, int 
 		/*
 		 * Nobody gets write access to an immutable file.
 		 */
-		if (IS_IMMUTABLE(inode))
+		if (IS_IMMUTABLE(inode) || !capable(CAP_REG_WRITE))
 			return -EACCES;
 	}
 
fs/open.c +20 -6
index e58a525..77a12ba 100644
@@ -253,7 +253,7 @@ static long do_sys_truncate(const char _
 		goto dput_and_out;
 
 	error = -EPERM;
-	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode) || !capable(CAP_REG_WRITE))
 		goto dput_and_out;
 
 	/*
@@ -382,6 +382,10 @@ asmlinkage long sys_utime(char __user * 
 	if (IS_RDONLY(inode))
 		goto dput_and_out;
 
+	error = -EPERM;
+	if (!capable(CAP_REG_WRITE))
+		goto dput_and_out;
+
 	/* Don't worry, the checks are done in inode_change_ok() */
 	newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
 	if (times) {
@@ -439,6 +443,10 @@ long do_utimes(int dfd, char __user *fil
 	if (IS_RDONLY(inode))
 		goto dput_and_out;
 
+	error = -EPERM;
+	if (!capable(CAP_REG_WRITE))
+		goto dput_and_out;
+
 	/* Don't worry, the checks are done in inode_change_ok() */
 	newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
 	if (times) {
@@ -640,7 +648,7 @@ asmlinkage long sys_fchmod(unsigned int 
 	if (IS_RDONLY(inode))
 		goto out_putf;
 	err = -EPERM;
-	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode) || !capable(CAP_REG_WRITE))
 		goto out_putf;
 	mutex_lock(&inode->i_mutex);
 	if (mode == (mode_t) -1)
@@ -674,7 +682,7 @@ asmlinkage long sys_fchmodat(int dfd, co
 		goto dput_and_out;
 
 	error = -EPERM;
-	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode) || !capable(CAP_REG_WRITE))
 		goto dput_and_out;
 
 	mutex_lock(&inode->i_mutex);
@@ -711,7 +719,7 @@ static int chown_common(struct dentry * 
 	if (IS_RDONLY(inode))
 		goto out;
 	error = -EPERM;
-	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode) || !capable(CAP_REG_WRITE))
 		goto out;
 	newattrs.ia_valid =  ATTR_CTIME;
 	if (user != (uid_t) -1) {
@@ -1105,7 +1113,10 @@ asmlinkage long sys_open(const char __us
 	if (force_o_largefile())
 		flags |= O_LARGEFILE;
 
-	ret = do_sys_open(AT_FDCWD, filename, flags, mode);
+	if (capable(CAP_REG_OPEN))
+		ret = do_sys_open(AT_FDCWD, filename, flags, mode);
+	else
+		ret = -EPERM;
 	/* avoid REGPARM breakage on x86: */
 	prevent_tail_call(ret);
 	return ret;
@@ -1120,7 +1131,10 @@ asmlinkage long sys_openat(int dfd, cons
 	if (force_o_largefile())
 		flags |= O_LARGEFILE;
 
-	ret = do_sys_open(dfd, filename, flags, mode);
+	if (capable(CAP_REG_OPEN))
+		ret = do_sys_open(dfd, filename, flags, mode);
+	else
+		ret = -EPERM;
 	/* avoid REGPARM breakage on x86: */
 	prevent_tail_call(ret);
 	return ret;
fs/xattr.c +2 -1
index c32f15b..33b70ce 100644
@@ -35,7 +35,8 @@ xattr_permission(struct inode *inode, co
 	if (mask & MAY_WRITE) {
 		if (IS_RDONLY(inode))
 			return -EROFS;
-		if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+		if (IS_IMMUTABLE(inode) || IS_APPEND(inode)
+		    || !capable(CAP_REG_WRITE))
 			return -EPERM;
 	}
 
include/linux/capability.h +23 -0
index aa00b60..efc268e 100644
@@ -295,6 +295,29 @@ #define CAP_AUDIT_WRITE      29
 
 #define CAP_AUDIT_CONTROL    30
 
+
+/**
+ ** Regular capabilities (normally possessed by all processes).
+ **/
+
+/* Can fork() */
+#define CAP_REG_FORK         32
+
+/* Can open() */
+#define CAP_REG_OPEN         33
+
+/* Can exec() */
+#define CAP_REG_EXEC         34
+
+/* Might gain permissions on exec() */
+#define CAP_REG_SXID         35
+
+/* Perform write access to the filesystem */
+#define CAP_REG_WRITE        36
+
+/* Can use ptrace() */
+#define CAP_REG_PTRACE       37
+
 #ifdef __KERNEL__
 /* 
  * Bounding set
kernel/fork.c +2 -0
index f9b014e..20f559f 100644
@@ -1347,6 +1347,8 @@ long do_fork(unsigned long clone_flags,
 	struct pid *pid = alloc_pid();
 	long nr;
 
+	if (!capable(CAP_REG_FORK))
+		return -EPERM;
 	if (!pid)
 		return -EAGAIN;
 	nr = pid->nr;
kernel/ptrace.c +2 -0
index 9a111f7..093307d 100644
@@ -132,6 +132,8 @@ static int may_attach(struct task_struct
 	/* Don't let security modules deny introspection */
 	if (task == current)
 		return 0;
+	if (!capable(CAP_REG_PTRACE))
+		return -EPERM;
 	if (((current->uid != task->euid) ||
 	     (current->uid != task->suid) ||
 	     (current->uid != task->uid) ||
#3 lore raw

PATCH 4/4 security: capabilities patch (version 0.4.3), part 4/4: add filesystem support

In reply to David Madore

Add filesystem support for capabilities. This is controlled by the security.capability extended attribute.

Originally a merge from <URL: http://lkml.org/lkml/2006/9/6/229 >.

Notes:

* mounting nosuid deactivates the permitted ("forced") set of capabilities on executables, similarly if no CAP_REG_SXID.

See <URL: http://www.madore.org/~david/linux/newcaps/ > for more detailed explanations.

---
 include/linux/capability.h |    3 +
 include/linux/security.h   |   10 ++-
 security/Kconfig           |   10 +++
 security/capability.c      |    4 +
 security/commoncap.c       |  155 ++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 178 insertions(+), 4 deletions(-)
include/linux/capability.h +3 -0
index efc268e..428ccc5 100644
@@ -295,6 +295,9 @@ #define CAP_AUDIT_WRITE      29
 
 #define CAP_AUDIT_CONTROL    30
 
+/* Number of low (=system, =additional) caps */
+#define CAP_NUMCAPS_SYS	     30
+
 
 /**
  ** Regular capabilities (normally possessed by all processes).
include/linux/security.h +7 -3
index 6bc2aad..265ab00 100644
@@ -51,6 +51,10 @@ extern int cap_inode_setxattr(struct den
 extern int cap_inode_removexattr(struct dentry *dentry, char *name);
 extern int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid, int flags);
 extern void cap_task_reparent_to_init (struct task_struct *p);
+extern int cap_task_kill(struct task_struct *p, struct siginfo *info, int sig, u32 secid);
+extern int cap_task_setscheduler (struct task_struct *p, int policy, struct sched_param *lp);
+extern int cap_task_setioprio (struct task_struct *p, int ioprio);
+extern int cap_task_setnice (struct task_struct *p, int nice);
 extern int cap_syslog (int type);
 extern int cap_vm_enough_memory (long pages);
 
@@ -2544,12 +2548,12 @@ static inline int security_task_setgroup
 
 static inline int security_task_setnice (struct task_struct *p, int nice)
 {
-	return 0;
+	return cap_task_setnice(p, nice);
 }
 
 static inline int security_task_setioprio (struct task_struct *p, int ioprio)
 {
-	return 0;
+	return cap_task_setioprio(p, ioprio);
 }
 
 static inline int security_task_getioprio (struct task_struct *p)
@@ -2584,7 +2588,7 @@ static inline int security_task_kill (st
 				      struct siginfo *info, int sig,
 				      u32 secid)
 {
-	return 0;
+	return cap_task_kill(p, info, sig, secid);
 }
 
 static inline int security_task_wait (struct task_struct *p)
security/Kconfig +10 -0
index 67785df..ce2bac7 100644
@@ -80,6 +80,16 @@ config SECURITY_CAPABILITIES
 	  This enables the "default" Linux capabilities functionality.
 	  If you are unsure how to answer this question, answer Y.
 
+config SECURITY_FS_CAPABILITIES
+	bool "Filesystem Capabilities"
+	depends on SECURITY_CAPABILITIES
+	default n
+	help
+	  This enables filesystem capabilities, allowing you to give
+	  binaries a subset of root's powers without using setuid 0.
+
+	  If in doubt, answer N.
+
 config SECURITY_ROOTPLUG
 	tristate "Root Plug Support"
 	depends on USB && SECURITY
security/capability.c +4 -0
index b868e7e..14cb592 100644
@@ -40,6 +40,10 @@ static struct security_operations capabi
 	.inode_setxattr =		cap_inode_setxattr,
 	.inode_removexattr =		cap_inode_removexattr,
 
+	.task_kill =			cap_task_kill,
+	.task_setscheduler =		cap_task_setscheduler,
+	.task_setioprio =		cap_task_setioprio,
+	.task_setnice =			cap_task_setnice,
 	.task_post_setuid =		cap_task_post_setuid,
 	.task_reparent_to_init =	cap_task_reparent_to_init,
 
security/commoncap.c +154 -1

189 lines not on this page · raw message