Merge samba.org:/home/anton/ppc64/linux-2.5

into samba.org:/home/anton/ppc64/for-linus-ppc64

Makefile

 VERSION = 2
 PATCHLEVEL = 5
-SUBLEVEL = 26
+SUBLEVEL = 27
 EXTRAVERSION =
 
 # *DOCUMENTATION*
@@ -157,7 +157,8 @@ objtree := $(TOPDIR)
 
 export srctree objtree
 
-SUBDIRS		:= init kernel mm fs ipc lib drivers sound net
+SUBDIRS		:= init kernel mm fs ipc lib drivers sound net security
+
 
 noconfig_targets := xconfig menuconfig config oldconfig randconfig \
 		    defconfig allyesconfig allnoconfig allmodconfig \
@@ -223,7 +224,7 @@ endif
 # ---------------------------------------------------------------------------
 
 INIT		:= init/init.o
-CORE_FILES	:= kernel/kernel.o mm/mm.o fs/fs.o ipc/ipc.o
+CORE_FILES	:= kernel/kernel.o mm/mm.o fs/fs.o ipc/ipc.o security/built-in.o
 LIBS		:= lib/lib.a
 DRIVERS		:= drivers/built-in.o sound/sound.o
 NETWORKS	:= net/network.o

arch/arm/kernel/isa.c

@@ -38,7 +38,7 @@ static ctl_table ctl_isa_vars[4] = {
 
 static struct ctl_table_header *isa_sysctl_header;
 
-static ctl_table ctl_isa[2] = {{BUS_ISA, "isa", NULL, 0, 0555, ctl_isa_vars},
+static ctl_table ctl_isa[2] = {{CTL_BUS_ISA, "isa", NULL, 0, 0555, ctl_isa_vars},
 			       {0}};
 static ctl_table ctl_bus[2] = {{CTL_BUS, "bus", NULL, 0, 0555, ctl_isa},
 			       {0}};

arch/i386/config.in

@@ -423,4 +423,5 @@ fi
 
 endmenu
 
+source security/Config.in
 source lib/Config.in

arch/i386/kernel/entry.S

@@ -744,7 +744,7 @@ ENTRY(sys_call_table)
 	.long sys_getdents64	/* 220 */
 	.long sys_fcntl64
 	.long sys_ni_syscall	/* reserved for TUX */
-	.long sys_ni_syscall	/* reserved for Security */
+	.long sys_security	/* reserved for Security */
 	.long sys_gettid
 	.long sys_readahead	/* 225 */
 	.long sys_setxattr

arch/i386/kernel/ptrace.c

@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
+#include <linux/security.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -159,6 +160,9 @@ asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
 		/* are we already being traced? */
 		if (current->ptrace & PT_PTRACED)
 			goto out;
+		ret = security_ops->ptrace(current->parent, current);
+		if (ret)
+			goto out;
 		/* set the ptrace bit in the process flags. */
 		current->ptrace |= PT_PTRACED;
 		ret = 0;

fs/buffer.c

@@ -2078,7 +2078,7 @@ int generic_cont_expand(struct inode *inode, loff_t size)
  */
 
 int cont_prepare_write(struct page *page, unsigned offset,
-		unsigned to, get_block_t *get_block, unsigned long *bytes)
+		unsigned to, get_block_t *get_block, loff_t *bytes)
 {
 	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;

fs/exec.c

@@ -623,6 +623,7 @@ int prepare_binprm(struct linux_binprm *bprm)
 {
 	int mode;
 	struct inode * inode = bprm->file->f_dentry->d_inode;
+	int retval;
 
 	mode = inode->i_mode;
 	/*
@@ -652,27 +653,10 @@ int prepare_binprm(struct linux_binprm *bprm)
 			bprm->e_gid = inode->i_gid;
 	}
 
-	/* We don't have VFS support for capabilities yet */
-	cap_clear(bprm->cap_inheritable);
-	cap_clear(bprm->cap_permitted);
-	cap_clear(bprm->cap_effective);
-
-	/*  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 (bprm->e_uid == 0 || current->uid == 0) {
-			cap_set_full(bprm->cap_inheritable);
-			cap_set_full(bprm->cap_permitted);
-		}
-		if (bprm->e_uid == 0) 
-			cap_set_full(bprm->cap_effective);
-	}
+	/* fill in binprm security blob */
+	retval = security_ops->bprm_set_security(bprm);
+	if (retval)
+		return retval;
 
 	memset(bprm->buf,0,BINPRM_BUF_SIZE);
 	return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
@@ -695,16 +679,9 @@ int prepare_binprm(struct linux_binprm *bprm)
 
 void compute_creds(struct linux_binprm *bprm) 
 {
-	kernel_cap_t new_permitted, working;
 	int do_unlock = 0;
 
-	new_permitted = cap_intersect(bprm->cap_permitted, 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)) {
+	if (bprm->e_uid != current->uid || bprm->e_gid != current->gid) {
                 current->mm->dumpable = 0;
 		
 		lock_kernel();
@@ -716,32 +693,17 @@ void compute_creds(struct linux_binprm *bprm)
 				bprm->e_uid = current->uid;
 				bprm->e_gid = current->gid;
 			}
-			if(!capable(CAP_SETPCAP)) {
-				new_permitted = cap_intersect(new_permitted,
-							current->cap_permitted);
-			}
 		}
 		do_unlock = 1;
 	}
 
-
-	/* For init, we want to retain the capabilities set
-         * in the init_task struct. Thus we skip the usual
-         * capability rules */
-	if (current->pid != 1) {
-		current->cap_permitted = new_permitted;
-		current->cap_effective =
-			cap_intersect(new_permitted, bprm->cap_effective);
-	}
-	
-        /* AUD: Audit candidate if current->cap_effective is set */
-
         current->suid = current->euid = current->fsuid = bprm->e_uid;
         current->sgid = current->egid = current->fsgid = bprm->e_gid;
 
 	if(do_unlock)
 		unlock_kernel();
-	current->keep_capabilities = 0;
+
+	security_ops->bprm_compute_creds(bprm);
 }
 
 
@@ -811,6 +773,10 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	    }
 	}
 #endif
+	retval = security_ops->bprm_check_security(bprm);
+	if (retval) 
+		return retval;
+
 	/* kernel module loader fixup */
 	/* so we don't try to load run modprobe in kernel space. */
 	set_fs(USER_DS);
@@ -887,7 +853,7 @@ int do_execve(char * filename, char ** argv, char ** envp, struct pt_regs * regs
 	bprm.sh_bang = 0;
 	bprm.loader = 0;
 	bprm.exec = 0;
-
+	bprm.security = NULL;
 	bprm.mm = mm_alloc();
 	retval = -ENOMEM;
 	if (!bprm.mm)
@@ -905,6 +871,10 @@ int do_execve(char * filename, char ** argv, char ** envp, struct pt_regs * regs
 	if ((retval = bprm.envc) < 0)
 		goto out_mm;
 
+	retval = security_ops->bprm_alloc_security(&bprm);
+	if (retval) 
+		goto out;
+
 	retval = prepare_binprm(&bprm);
 	if (retval < 0) 
 		goto out; 
@@ -923,9 +893,11 @@ int do_execve(char * filename, char ** argv, char ** envp, struct pt_regs * regs
 		goto out; 
 
 	retval = search_binary_handler(&bprm,regs);
-	if (retval >= 0)
+	if (retval >= 0) {
 		/* execve success */
+		security_ops->bprm_free_security(&bprm);
 		return retval;
+	}
 
 out:
 	/* Something went wrong, return the inode and free the argument pages*/
@@ -935,6 +907,9 @@ int do_execve(char * filename, char ** argv, char ** envp, struct pt_regs * regs
 			__free_page(page);
 	}
 
+	if (bprm.security)
+		security_ops->bprm_free_security(&bprm);
+
 out_mm:
 	mmdrop(bprm.mm);
 

fs/fat/file.c

@@ -54,7 +54,7 @@ int fat_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_r
 	}
 	if (!create)
 		return 0;
-	if (iblock << sb->s_blocksize_bits != MSDOS_I(inode)->mmu_private) {
+	if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) {
 		BUG();
 		return -EIO;
 	}

fs/fat/inode.c

@@ -417,7 +417,7 @@ static int fat_read_root(struct inode *inode)
 	}
 	inode->i_blksize = 1 << sbi->cluster_bits;
 	inode->i_blocks = ((inode->i_size + inode->i_blksize - 1)
-			   & ~(inode->i_blksize - 1)) >> 9;
+			   & ~((loff_t)inode->i_blksize - 1)) >> 9;
 	MSDOS_I(inode)->i_logstart = 0;
 	MSDOS_I(inode)->mmu_private = inode->i_size;
 
@@ -775,6 +775,8 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
 		sbi->fat_length = CF_LE_L(b->fat32_length);
 		sbi->root_cluster = CF_LE_L(b->root_cluster);
 
+		sb->s_maxbytes = 0xffffffff;
+		
 		/* MC - if info_sector is 0, don't multiply by 0 */
 		sbi->fsinfo_sector = CF_LE_W(b->info_sector);
 		if (sbi->fsinfo_sector == 0)
@@ -1063,7 +1065,7 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 	/* this is as close to the truth as we can get ... */
 	inode->i_blksize = 1 << sbi->cluster_bits;
 	inode->i_blocks = ((inode->i_size + inode->i_blksize - 1)
-			   & ~(inode->i_blksize - 1)) >> 9;
+			   & ~((loff_t)inode->i_blksize - 1)) >> 9;
 	inode->i_mtime = inode->i_atime =
 		date_dos2unix(CF_LE_W(de->time),CF_LE_W(de->date));
 	inode->i_ctime =

include/linux/adfs_fs_i.h

@@ -11,7 +11,7 @@
  * adfs file system inode data in memory
  */
 struct adfs_inode_info {
-	unsigned long	mmu_private;
+	loff_t		mmu_private;
 	unsigned long	parent_id;	/* object id of parent		*/
 	__u32		loadaddr;	/* RISC OS load address		*/
 	__u32		execaddr;	/* RISC OS exec address		*/

include/linux/affs_fs_i.h

@@ -35,7 +35,7 @@ struct affs_inode_info {
 	struct affs_ext_key *i_ac;		/* associative cache of extended blocks */
 	u32	 i_ext_last;			/* last accessed extended block */
 	struct buffer_head *i_ext_bh;		/* bh of last extended block */
-	unsigned long mmu_private;
+	loff_t	 mmu_private;
 	u32	 i_protect;			/* unused attribute bits */
 	u32	 i_lastalloc;			/* last allocated block */
 	int	 i_pa_cnt;			/* number of preallocated blocks */

include/linux/binfmts.h

@@ -28,6 +28,7 @@ struct linux_binprm{
 	struct file * file;
 	int e_uid, e_gid;
 	kernel_cap_t cap_inheritable, cap_permitted, cap_effective;
+	void *security;
 	int argc, envc;
 	char * filename;	/* Name of binary */
 	unsigned long loader, exec;

include/linux/buffer_head.h

@@ -178,7 +178,7 @@ int block_write_full_page(struct page*, get_block_t*);
 int block_read_full_page(struct page*, get_block_t*);
 int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
 int cont_prepare_write(struct page*, unsigned, unsigned, get_block_t*,
-				unsigned long *);
+				loff_t *);
 int generic_cont_expand(struct inode *inode, loff_t size) ;
 int block_commit_write(struct page *page, unsigned from, unsigned to);
 int block_sync_page(struct page *);

include/linux/hfs_fs_i.h

@@ -19,7 +19,7 @@
 struct hfs_inode_info {
 	int				magic;     /* A magic number */
 
-	unsigned long			mmu_private;
+	loff_t				mmu_private;
 	struct hfs_cat_entry		*entry;
 
 	/* For a regular or header file */

include/linux/hpfs_fs_i.h

@@ -2,7 +2,7 @@
 #define _HPFS_FS_I
 
 struct hpfs_inode_info {
-	unsigned long mmu_private;
+	loff_t mmu_private;
 	ino_t i_parent_dir;	/* (directories) gives fnode of parent dir */
 	unsigned i_dno;		/* (directories) root dnode */
 	unsigned i_dpos;	/* (directories) temp for readdir */

include/linux/msdos_fs_i.h

@@ -8,7 +8,7 @@
  */
 
 struct msdos_inode_info {
-	unsigned long mmu_private;
+	loff_t mmu_private;
 	int i_start;	/* first cluster or 0 */
 	int i_logstart;	/* logical first cluster */
 	int i_attrs;	/* unused attribute bits */

include/linux/qnx4_fs.h

@@ -106,7 +106,7 @@ struct qnx4_sb_info {
 
 struct qnx4_inode_info {
 	struct qnx4_inode_entry raw;
-	unsigned long mmu_private;
+	loff_t mmu_private;
 	struct inode vfs_inode;
 };
 

include/linux/sched.h

@@ -354,6 +354,8 @@ struct task_struct {
 	void *notifier_data;
 	sigset_t *notifier_mask;
 	
+	void *security;
+
 /* Thread group tracking */
    	u32 parent_exec_id;
    	u32 self_exec_id;
@@ -587,10 +589,9 @@ extern int request_irq(unsigned int,
 		       unsigned long, const char *, void *);
 extern void free_irq(unsigned int, void *);
 
-/*
- * capable() checks for a particular capability.
- * See include/linux/capability.h for defined capabilities.
- */
+/* capable prototype and code moved to security.[hc] */
+#include <linux/security.h>
+#if 0
 static inline int capable(int cap)
 {
 	if (cap_raised(current->cap_effective, cap)) {
@@ -599,6 +600,7 @@ static inline int capable(int cap)
 	}
 	return 0;
 }
+#endif	/* if 0 */
 
 /*
  * Routines for handling mm_structs

include/linux/security.h

+/*
+ * Linux Security plug
+ *
+ * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com>
+ * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com>
+ * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com>
+ * Copyright (C) 2001 James Morris <jmorris@intercode.com.au>
+ * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group)
+ *
+ *	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.
+ *
+ *	Due to this file being licensed under the GPL there is controversy over
+ *	whether this permits you to write a module that #includes this file
+ *	without placing your module under the GPL.  Please consult a lawyer for
+ *	advice before doing this.
+ *
+ */
+
+#ifndef __LINUX_SECURITY_H
+#define __LINUX_SECURITY_H
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/binfmts.h>
+#include <linux/signal.h>
+#include <linux/resource.h>
+#include <linux/sem.h>
+#include <linux/sysctl.h>
+#include <linux/shm.h>
+#include <linux/msg.h>
+
+/*
+ * Values used in the task_security_ops calls
+ */
+/* setuid or setgid, id0 == uid or gid */
+#define LSM_SETID_ID	1
+
+/* setreuid or setregid, id0 == real, id1 == eff */
+#define LSM_SETID_RE	2
+
+/* setresuid or setresgid, id0 == real, id1 == eff, uid2 == saved */
+#define LSM_SETID_RES	4
+
+/* setfsuid or setfsgid, id0 == fsuid or fsgid */
+#define LSM_SETID_FS	8
+
+/* forward declares to avoid warnings */
+struct sk_buff;
+struct net_device;
+struct nfsctl_arg;
+struct sched_param;
+struct swap_info_struct;
+
+/**
+ * struct security_operations - main security structure
+ *
+ * Security hooks for program execution operations.
+ *
+ * @bprm_alloc_security:
+ *	Allocate and attach a security structure to the @bprm->security field.
+ *	The security field is initialized to NULL when the bprm structure is
+ *	allocated.
+ *	@bprm contains the linux_binprm structure to be modified.
+ *	Return 0 if operation was successful.
+ * @bprm_free_security:
+ *	@bprm contains the linux_binprm structure to be modified.
+ *	Deallocate and clear the @bprm->security field.
+ * @bprm_compute_creds:
+ *	Compute and set the security attributes of a process being transformed
+ *	by an execve operation based on the old attributes (current->security)
+ *	and the information saved in @bprm->security by the set_security hook.
+ *	Since this hook function (and its caller) are void, this hook can not
+ *	return an error.  However, it can leave the security attributes of the
+ *	process unchanged if an access failure occurs at this point. It can
+ *	also perform other state changes on the process (e.g.  closing open
+ *	file descriptors to which access is no longer granted if the attributes
+ *	were changed). 
+ *	@bprm contains the linux_binprm structure.
+ * @bprm_set_security:
+ *	Save security information in the bprm->security field, typically based
+ *	on information about the bprm->file, for later use by the compute_creds
+ *	hook.  This hook may also optionally check permissions (e.g. for
+ *	transitions between security domains).
+ *	This hook may be called multiple times during a single execve, e.g. for
+ *	interpreters.  The hook can tell whether it has already been called by
+ *	checking to see if @bprm->security is non-NULL.  If so, then the hook
+ *	may decide either to retain the security information saved earlier or
+ *	to replace it.
+ *	@bprm contains the linux_binprm structure.
+ *	Return 0 if the hook is successful and permission is granted.
+ * @bprm_check_security:
+ * 	This hook mediates the point when a search for a binary handler	will
+ * 	begin.  It allows a check the @bprm->security value which is set in
+ * 	the preceding set_security call.  The primary difference from
+ * 	set_security is that the argv list and envp list are reliably
+ * 	available in @bprm.  This hook may be called multiple times
+ * 	during a single execve; and in each pass set_security is called
+ * 	first.
+ * 	@bprm contains the linux_binprm structure.
+ *	Return 0 if the hook is successful and permission is granted.
+ *
+ * Security hooks for task operations.
+ *
+ * @task_create:
+ *	Check permission before creating a child process.  See the clone(2)
+ *	manual page for definitions of the @clone_flags.
+ *	@clone_flags contains the flags indicating what should be shared.
+ *	Return 0 if permission is granted.
+ * @task_alloc_security:
+ *	@p contains the task_struct for child process.
+ *	Allocate and attach a security structure to the p->security field. The
+ *	security field is initialized to NULL when the task structure is
+ *	allocated.
+ *	Return 0 if operation was successful.
+ * @task_free_security:
+ *	@p contains the task_struct for process.
+ *	Deallocate and clear the p->security field.
+ * @task_setuid:
+ *	Check permission before setting one or more of the user identity
+ *	attributes of the current process.  The @flags parameter indicates
+ *	which of the set*uid system calls invoked this hook and how to
+ *	interpret the @id0, @id1, and @id2 parameters.  See the LSM_SETID
+ *	definitions at the beginning of this file for the @flags values and
+ *	their meanings.
+ *	@id0 contains a uid.
+ *	@id1 contains a uid.
+ *	@id2 contains a uid.
+ *	@flags contains one of the LSM_SETID_* values.
+ *	Return 0 if permission is granted.
+ * @task_post_setuid:
+ *	Update the module's state after setting one or more of the user
+ *	identity attributes of the current process.  The @flags parameter
+ *	indicates which of the set*uid system calls invoked this hook.  If
+ *	@flags is LSM_SETID_FS, then @old_ruid is the old fs uid and the other
+ *	parameters are not used.
+ *	@old_ruid contains the old real uid (or fs uid if LSM_SETID_FS).
+ *	@old_euid contains the old effective uid (or -1 if LSM_SETID_FS).
+ *	@old_suid contains the old saved uid (or -1 if LSM_SETID_FS).
+ *	@flags contains one of the LSM_SETID_* values.
+ *	Return 0 on success.
+ * @task_setgid:
+ *	Check permission before setting one or more of the group identity
+ *	attributes of the current process.  The @flags parameter indicates
+ *	which of the set*gid system calls invoked this hook and how to
+ *	interpret the @id0, @id1, and @id2 parameters.  See the LSM_SETID
+ *	definitions at the beginning of this file for the @flags values and
+ *	their meanings.
+ *	@id0 contains a gid.
+ *	@id1 contains a gid.
+ *	@id2 contains a gid.
+ *	@flags contains one of the LSM_SETID_* values.
+ *	Return 0 if permission is granted.
+ * @task_setpgid:
+ *	Check permission before setting the process group identifier of the
+ *	process @p to @pgid.
+ *	@p contains the task_struct for process being modified.
+ *	@pgid contains the new pgid.
+ *	Return 0 if permission is granted.
+ * @task_getpgid:
+ *	Check permission before getting the process group identifier of the
+ *	process @p.
+ *	@p contains the task_struct for the process.
+ *	Return 0 if permission is granted.
+ * @task_getsid:
+ *	Check permission before getting the session identifier of the process
+ *	@p.
+ *	@p contains the task_struct for the process.
+ *	Return 0 if permission is granted.
+ * @task_setgroups:
+ *	Check permission before setting the supplementary group set of the
+ *	current process to @grouplist.
+ *	@gidsetsize contains the number of elements in @grouplist.
+ *	@grouplist contains the array of gids.
+ *	Return 0 if permission is granted.
+ * @task_setnice:
+ *	Check permission before setting the nice value of @p to @nice.
+ *	@p contains the task_struct of process.
+ *	@nice contains the new nice value.
+ *	Return 0 if permission is granted.
+ * @task_setrlimit:
+ *	Check permission before setting the resource limits of the current
+ *	process for @resource to @new_rlim.  The old resource limit values can
+ *	be examined by dereferencing (current->rlim + resource).
+ *	@resource contains the resource whose limit is being set.
+ *	@new_rlim contains the new limits for @resource.
+ *	Return 0 if permission is granted.
+ * @task_setscheduler:
+ *	Check permission before setting scheduling policy and/or parameters of
+ *	process @p based on @policy and @lp.
+ *	@p contains the task_struct for process.
+ *	@policy contains the scheduling policy.
+ *	@lp contains the scheduling parameters.
+ *	Return 0 if permission is granted.
+ * @task_getscheduler:
+ *	Check permission before obtaining scheduling information for process
+ *	@p.
+ *	@p contains the task_struct for process.
+ *	Return 0 if permission is granted.
+ * @task_kill:
+ *	Check permission before sending signal @sig to @p.  @info can be NULL,
+ *	the constant 1, or a pointer to a siginfo structure.  If @info is 1 or
+ *	SI_FROMKERNEL(info) is true, then the signal should be viewed as coming
+ *	from the kernel and should typically be permitted.
+ *	SIGIO signals are handled separately by the send_sigiotask hook in
+ *	file_security_ops.
+ *	@p contains the task_struct for process.
+ *	@info contains the signal information.
+ *	@sig contains the signal value.
+ *	Return 0 if permission is granted.
+ * @task_wait:
+ *	Check permission before allowing a process to reap a child process @p
+ *	and collect its status information.
+ *	@p contains the task_struct for process.
+ *	Return 0 if permission is granted.
+ * @task_prctl:
+ *	Check permission before performing a process control operation on the
+ *	current process.
+ *	@option contains the operation.
+ *	@arg2 contains a argument.
+ *	@arg3 contains a argument.
+ *	@arg4 contains a argument.
+ *	@arg5 contains a argument.
+ *	Return 0 if permission is granted.
+ * @task_kmod_set_label:
+ *	Set the security attributes in current->security for the kernel module
+ *	loader thread, so that it has the permissions needed to perform its
+ *	function.
+ * @task_reparent_to_init:
+ * 	Set the security attributes in @p->security for a kernel thread that
+ * 	is being reparented to the init task.
+ *	@p contains the task_struct for the kernel thread.
+ *
+ * @ptrace:
+ *	Check permission before allowing the @parent process to trace the
+ *	@child process.
+ *	Security modules may also want to perform a process tracing check
+ *	during an execve in the set_security or compute_creds hooks of
+ *	binprm_security_ops if the process is being traced and its security
+ *	attributes would be changed by the execve.
+ *	@parent contains the task_struct structure for parent process.
+ *	@child contains the task_struct structure for child process.
+ *	Return 0 if permission is granted.
+ * @capget:
+ *	Get the @effective, @inheritable, and @permitted capability sets for
+ *	the @target process.  The hook may also perform permission checking to
+ *	determine if the current process is allowed to see the capability sets
+ *	of the @target process.
+ *	@target contains the task_struct structure for target process.
+ *	@effective contains the effective capability set.
+ *	@inheritable contains the inheritable capability set.
+ *	@permitted contains the permitted capability set.
+ *	Return 0 if the capability sets were successfully obtained.
+ * @capset_check:
+ *	Check permission before setting the @effective, @inheritable, and
+ *	@permitted capability sets for the @target process.
+ *	Caveat:  @target is also set to current if a set of processes is
+ *	specified (i.e. all processes other than current and init or a
+ *	particular process group).  Hence, the capset_set hook may need to
+ *	revalidate permission to the actual target process.
+ *	@target contains the task_struct structure for target process.
+ *	@effective contains the effective capability set.
+ *	@inheritable contains the inheritable capability set.
+ *	@permitted contains the permitted capability set.
+ *	Return 0 if permission is granted.
+ * @capset_set:
+ *	Set the @effective, @inheritable, and @permitted capability sets for
+ *	the @target process.  Since capset_check cannot always check permission
+ *	to the real @target process, this hook may also perform permission
+ *	checking to determine if the current process is allowed to set the
+ *	capability sets of the @target process.  However, this hook has no way
+ *	of returning an error due to the structure of the sys_capset code.
+ *	@target contains the task_struct structure for target process.
+ *	@effective contains the effective capability set.
+ *	@inheritable contains the inheritable capability set.
+ *	@permitted contains the permitted capability set.
+ * @capable:
+ *	Check whether the @tsk process has the @cap capability.
+ *	@tsk contains the task_struct for the process.
+ *	@cap contains the capability <include/linux/capability.h>.
+ *	Return 0 if the capability is granted for @tsk.
+ * @sys_security:
+ *	Security modules may use this hook to implement new system calls for
+ *	security-aware applications.  The interface is similar to socketcall,
+ *	but with an @id parameter to help identify the security module whose
+ *	call is being invoked.  The module is responsible for interpreting the
+ *	parameters, and must copy in the @args array from user space if it is
+ *	used.
+ *	The recommended convention for creating the hexadecimal @id value is
+ *	echo "Name_of_module" | md5sum | cut -c -8; by using this convention,
+ *	there is no need for a central registry.
+ *	@id contains the security module identifier.
+ *	@call contains the call value.
+ *	@args contains the call arguments (user space pointer).
+ *	The module should return -ENOSYS if it does not implement any new
+ *	system calls.
+ *
+ * @register_security:
+ * 	allow module stacking.
+ * 	@name contains the name of the security module being stacked.
+ * 	@ops contains a pointer to the struct security_operations of the module to stack.
+ * @unregister_security:
+ *	remove a stacked module.
+ *	@name contains the name of the security module being unstacked.
+ *	@ops contains a pointer to the struct security_operations of the module to unstack.
+ * 
+ * This is the main security structure.
+ */
+struct security_operations {
+	int (*ptrace) (struct task_struct * parent, struct task_struct * child);
+	int (*capget) (struct task_struct * target,
+		       kernel_cap_t * effective,
+		       kernel_cap_t * inheritable, kernel_cap_t * permitted);
+	int (*capset_check) (struct task_struct * target,
+			     kernel_cap_t * effective,
+			     kernel_cap_t * inheritable,
+			     kernel_cap_t * permitted);
+	void (*capset_set) (struct task_struct * target,
+			    kernel_cap_t * effective,
+			    kernel_cap_t * inheritable,
+			    kernel_cap_t * permitted);
+	int (*capable) (struct task_struct * tsk, int cap);
+	int (*sys_security) (unsigned int id, unsigned call,
+			     unsigned long *args);
+
+	int (*bprm_alloc_security) (struct linux_binprm * bprm);
+	void (*bprm_free_security) (struct linux_binprm * bprm);
+	void (*bprm_compute_creds) (struct linux_binprm * bprm);
+	int (*bprm_set_security) (struct linux_binprm * bprm);
+	int (*bprm_check_security) (struct linux_binprm * bprm);
+
+	int (*task_create) (unsigned long clone_flags);
+	int (*task_alloc_security) (struct task_struct * p);
+	void (*task_free_security) (struct task_struct * p);
+	int (*task_setuid) (uid_t id0, uid_t id1, uid_t id2, int flags);
+	int (*task_post_setuid) (uid_t old_ruid /* or fsuid */ ,
+				 uid_t old_euid, uid_t old_suid, int flags);
+	int (*task_setgid) (gid_t id0, gid_t id1, gid_t id2, int flags);
+	int (*task_setpgid) (struct task_struct * p, pid_t pgid);
+	int (*task_getpgid) (struct task_struct * p);
+	int (*task_getsid) (struct task_struct * p);
+	int (*task_setgroups) (int gidsetsize, gid_t * grouplist);
+	int (*task_setnice) (struct task_struct * p, int nice);
+	int (*task_setrlimit) (unsigned int resource, struct rlimit * new_rlim);
+	int (*task_setscheduler) (struct task_struct * p, int policy,
+				  struct sched_param * lp);
+	int (*task_getscheduler) (struct task_struct * p);
+	int (*task_kill) (struct task_struct * p,
+			  struct siginfo * info, int sig);
+	int (*task_wait) (struct task_struct * p);
+	int (*task_prctl) (int option, unsigned long arg2,
+			   unsigned long arg3, unsigned long arg4,
+			   unsigned long arg5);
+	void (*task_kmod_set_label) (void);
+	void (*task_reparent_to_init) (struct task_struct * p);
+
+	/* allow module stacking */
+	int (*register_security) (const char *name,
+	                          struct security_operations *ops);
+	int (*unregister_security) (const char *name,
+	                            struct security_operations *ops);
+};
+
+
+/* prototypes */
+extern int security_scaffolding_startup	(void);
+extern int register_security	(struct security_operations *ops);
+extern int unregister_security	(struct security_operations *ops);
+extern int mod_reg_security	(const char *name, struct security_operations *ops);
+extern int mod_unreg_security	(const char *name, struct security_operations *ops);
+extern int capable		(int cap);
+
+/* global variables */
+extern struct security_operations *security_ops;
+
+
+#endif /* __KERNEL__ */
+
+#endif /* ! __LINUX_SECURITY_H */
+

include/linux/sysctl.h

@@ -72,7 +72,7 @@ enum
 /* CTL_BUS names: */
 enum
 {
-	BUS_ISA=1		/* ISA */
+	CTL_BUS_ISA=1		/* ISA */
 };
 
 /* CTL_KERN names: */

init/main.c

@@ -29,6 +29,7 @@
 #include <linux/tty.h>
 #include <linux/percpu.h>
 #include <linux/kernel_stat.h>
+#include <linux/security.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -390,6 +391,7 @@ asmlinkage void __init start_kernel(void)
 
 	fork_init(mempages);
 	proc_caches_init();
+	security_scaffolding_startup();
 	buffer_init();
 	vfs_caches_init(mempages);
 	radix_tree_init();

kernel/capability.c

@@ -63,6 +63,7 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
      data.permitted = cap_t(target->cap_permitted);
      data.inheritable = cap_t(target->cap_inheritable); 
      data.effective = cap_t(target->cap_effective);
+     ret = security_ops->capget(target, &data.effective, &data.inheritable, &data.permitted);
 
 out:
      read_unlock(&tasklist_lock); 
@@ -87,9 +88,7 @@ static inline void cap_set_pg(int pgrp, kernel_cap_t *effective,
      for_each_task(target) {
              if (target->pgrp != pgrp)
                      continue;
-             target->cap_effective   = *effective;
-             target->cap_inheritable = *inheritable;
-             target->cap_permitted   = *permitted;
+	     security_ops->capset_set(target, effective, inheritable, permitted);
      }
 }
 
@@ -106,9 +105,7 @@ static inline void cap_set_all(kernel_cap_t *effective,
      for_each_task(target) {
              if (target == current || target->pid == 1)
                      continue;
-             target->cap_effective   = *effective;
-             target->cap_inheritable = *inheritable;
-             target->cap_permitted   = *permitted;
+	     security_ops->capset_set(target, effective, inheritable, permitted);
      }
 }
 
@@ -166,7 +163,9 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
 
      ret = -EPERM;
 
-     /* verify restrictions on target's new Inheritable set */
+     if (security_ops->capset_check(target, &effective, &inheritable, &permitted))
+	     goto out;
+
      if (!cap_issubset(inheritable, cap_combine(target->cap_inheritable,
                        current->cap_permitted)))
              goto out;
@@ -182,6 +181,8 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
 
      ret = 0;
 
+     /* having verified that the proposed changes are legal,
+           we now put them into effect. */
      if (pid < 0) {
              if (pid == -1)  /* all procs other than current and init */
                      cap_set_all(&effective, &inheritable, &permitted);
@@ -189,9 +190,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
              else            /* all procs in process group */
                      cap_set_pg(-pid, &effective, &inheritable, &permitted);
      } else {
-             target->cap_effective   = effective;
-             target->cap_inheritable = inheritable;
-             target->cap_permitted   = permitted;
+	     security_ops->capset_set(target, &effective, &inheritable, &permitted);
      }
 
 out:

kernel/exit.c

@@ -14,6 +14,7 @@
 #include <linux/personality.h>
 #include <linux/tty.h>
 #include <linux/namespace.h>
+#include <linux/security.h>
 #include <linux/acct.h>
 #include <linux/file.h>
 #include <linux/binfmts.h>
@@ -61,6 +62,7 @@ static void release_task(struct task_struct * p)
 	wait_task_inactive(p);
 #endif
 	atomic_dec(&p->user->processes);
+	security_ops->task_free_security(p);
 	free_uid(p->user);
 	unhash_process(p);
 
@@ -187,10 +189,7 @@ void reparent_to_init(void)
 	/* cpus_allowed? */
 	/* rt_priority? */
 	/* signals? */
-	current->cap_effective = CAP_INIT_EFF_SET;
-	current->cap_inheritable = CAP_INIT_INH_SET;
-	current->cap_permitted = CAP_FULL_SET;
-	current->keep_capabilities = 0;
+	security_ops->task_reparent_to_init(current);
 	memcpy(current->rlim, init_task.rlim, sizeof(*(current->rlim)));
 	current->user = INIT_USER;
 
@@ -625,6 +624,10 @@ asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struc
 			if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
 			    && !(options & __WALL))
 				continue;
+
+			if (security_ops->task_wait(p))
+				continue;
+
 			flag = 1;
 			switch (p->state) {
 			case TASK_STOPPED:

kernel/fork.c

@@ -24,7 +24,7 @@
 #include <linux/file.h>
 #include <linux/binfmts.h>
 #include <linux/fs.h>
-#include <linux/mm.h>
+#include <linux/security.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -618,6 +618,10 @@ struct task_struct *do_fork(unsigned long clone_flags,
 	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
 		return ERR_PTR(-EINVAL);
 
+	retval = security_ops->task_create(clone_flags);
+	if (retval)
+		goto fork_out;
+
 	retval = -ENOMEM;
 	p = dup_task_struct(current);
 	if (!p)
@@ -697,13 +701,16 @@ struct task_struct *do_fork(unsigned long clone_flags,
 	p->array = NULL;
 	p->lock_depth = -1;		/* -1 = no lock */
 	p->start_time = jiffies;
+	p->security = NULL;
 
 	INIT_LIST_HEAD(&p->local_pages);
 
 	retval = -ENOMEM;
+	if (security_ops->task_alloc_security(p))
+		goto bad_fork_cleanup;
 	/* copy all the process information */
 	if (copy_semundo(clone_flags, p))
-		goto bad_fork_cleanup;
+		goto bad_fork_cleanup_security;
 	if (copy_files(clone_flags, p))
 		goto bad_fork_cleanup_semundo;
 	if (copy_fs(clone_flags, p))
@@ -812,6 +819,8 @@ struct task_struct *do_fork(unsigned long clone_flags,
 	exit_files(p); /* blocking */
 bad_fork_cleanup_semundo:
 	exit_semundo(p);
+bad_fork_cleanup_security:
+	security_ops->task_free_security(p);
 bad_fork_cleanup:
 	put_exec_domain(p->thread_info->exec_domain);
 	if (p->binfmt && p->binfmt->module)

kernel/kmod.c

@@ -134,7 +134,7 @@ int exec_usermodehelper(char *program_path, char *argv[], char *envp[])
 	/* Give kmod all effective privileges.. */
 	curtask->euid = curtask->fsuid = 0;
 	curtask->egid = curtask->fsgid = 0;
-	cap_set_full(curtask->cap_effective);
+	security_ops->task_kmod_set_label();
 
 	/* Allow execve args to be in kernel space. */
 	set_fs(KERNEL_DS);

kernel/ptrace.c

@@ -41,7 +41,9 @@ int ptrace_check_attach(struct task_struct *child, int kill)
 
 int ptrace_attach(struct task_struct *task)
 {
+	int retval;
 	task_lock(task);
+	retval = -EPERM;
 	if (task->pid <= 1)
 		goto bad;
 	if (task == current)
@@ -53,7 +55,6 @@ int ptrace_attach(struct task_struct *task)
 	    (current->uid != task->uid) ||
  	    (current->gid != task->egid) ||
  	    (current->gid != task->sgid) ||
- 	    (!cap_issubset(task->cap_permitted, current->cap_permitted)) ||
  	    (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE))
 		goto bad;
 	rmb();
@@ -62,6 +63,9 @@ int ptrace_attach(struct task_struct *task)
 	/* the same process cannot be attached many times */
 	if (task->ptrace & PT_PTRACED)
 		goto bad;
+	retval = security_ops->ptrace(current, task);
+	if (retval)
+		goto bad;
 
 	/* Go */
 	task->ptrace |= PT_PTRACED;
@@ -82,7 +86,7 @@ int ptrace_attach(struct task_struct *task)
 
 bad:
 	task_unlock(task);
-	return -EPERM;
+	return retval;
 }
 
 int ptrace_detach(struct task_struct *child, unsigned int data)

kernel/sched.c

@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/completion.h>
 #include <linux/kernel_stat.h>
+#include <linux/security.h>
 
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
@@ -1123,6 +1124,7 @@ void set_user_nice(task_t *p, long nice)
 
 asmlinkage long sys_nice(int increment)
 {
+	int retval;
 	long nice;
 
 	/*
@@ -1144,6 +1146,11 @@ asmlinkage long sys_nice(int increment)
 		nice = -20;
 	if (nice > 19)
 		nice = 19;
+
+	retval = security_ops->task_setnice(current, nice);
+	if (retval)
+		return retval;
+
 	set_user_nice(current, nice);
 	return 0;
 }
@@ -1236,6 +1243,10 @@ static int setscheduler(pid_t pid, int policy, struct sched_param *param)
 	    !capable(CAP_SYS_NICE))
 		goto out_unlock;
 
+	retval = security_ops->task_setscheduler(p, policy, &lp);
+	if (retval)
+		goto out_unlock;
+
 	array = p->array;
 	if (array)
 		deactivate_task(p, task_rq(p));
@@ -1280,8 +1291,11 @@ asmlinkage long sys_sched_getscheduler(pid_t pid)
 	retval = -ESRCH;
 	read_lock(&tasklist_lock);
 	p = find_process_by_pid(pid);
-	if (p)
-		retval = p->policy;
+	if (p) {
+		retval = security_ops->task_getscheduler(p);
+		if (!retval)
+			retval = p->policy;
+	}
 	read_unlock(&tasklist_lock);
 
 out_nounlock:
@@ -1302,6 +1316,11 @@ asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param *param)
 	retval = -ESRCH;
 	if (!p)
 		goto out_unlock;
+
+	retval = security_ops->task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
 	lp.sched_priority = p->rt_priority;
 	read_unlock(&tasklist_lock);
 
@@ -1509,14 +1528,22 @@ asmlinkage long sys_sched_rr_get_interval(pid_t pid, struct timespec *interval)
 	retval = -ESRCH;
 	read_lock(&tasklist_lock);
 	p = find_process_by_pid(pid);
-	if (p)
-		jiffies_to_timespec(p->policy & SCHED_FIFO ?
-					 0 : TASK_TIMESLICE(p), &t);
+	if (!p)
+		goto out_unlock;
+
+	retval = security_ops->task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	jiffies_to_timespec(p->policy & SCHED_FIFO ?
+				0 : TASK_TIMESLICE(p), &t);
 	read_unlock(&tasklist_lock);
-	if (p)
-		retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
+	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
 out_nounlock:
 	return retval;
+out_unlock:
+	read_unlock(&tasklist_lock);
+	return retval;
 }
 
 static void show_task(task_t * p)

kernel/signal.c

@@ -548,6 +548,9 @@ printk("SIG queue (%s:%d): %d ", t->comm, t->pid, sig);
 	ret = -EPERM;
 	if (bad_signal(sig, info, t))
 		goto out_nolock;
+	ret = security_ops->task_kill(t, info, sig);
+	if (ret)
+		goto out_nolock;
 
 	/* The null signal is a permissions and process existence probe.
 	   No signal is actually delivered.  Same goes for zombies. */

kernel/sys.c

@@ -19,6 +19,7 @@
 #include <linux/tqueue.h>
 #include <linux/device.h>
 #include <linux/times.h>
+#include <linux/security.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -234,6 +235,7 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
 
 	read_lock(&tasklist_lock);
 	for_each_task(p) {
+		int no_nice;
 		if (!proc_sel(p, which, who))
 			continue;
 		if (p->uid != current->euid &&
@@ -243,10 +245,17 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
 		}
 		if (error == -ESRCH)
 			error = 0;
-		if (niceval < task_nice(p) && !capable(CAP_SYS_NICE))
+		if (niceval < task_nice(p) && !capable(CAP_SYS_NICE)) {
 			error = -EACCES;
-		else
-			set_user_nice(p, niceval);
+			continue;
+		}
+		no_nice = security_ops->task_setnice(p, niceval);
+		if (no_nice) {
+			error = no_nice;
+			continue;
+		}
+		set_user_nice(p, niceval);
+
 	}
 	read_unlock(&tasklist_lock);
 
@@ -416,6 +425,11 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
 	int old_egid = current->egid;
 	int new_rgid = old_rgid;
 	int new_egid = old_egid;
+	int retval;
+
+	retval = security_ops->task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
+	if (retval)
+		return retval;
 
 	if (rgid != (gid_t) -1) {
 		if ((old_rgid == rgid) ||
@@ -457,6 +471,11 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
 asmlinkage long sys_setgid(gid_t gid)
 {
 	int old_egid = current->egid;
+	int retval;
+
+	retval = security_ops->task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
+	if (retval)
+		return retval;
 
 	if (capable(CAP_SETGID))
 	{
@@ -481,52 +500,6 @@ asmlinkage long sys_setgid(gid_t gid)
 	return 0;
 }
   
-/* 
- * cap_emulate_setxuid() fixes the effective / permitted capabilities of
- * a process after a call to setuid, setreuid, or setresuid.
- *
- *  1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of
- *  {r,e,s}uid != 0, the permitted and effective capabilities are
- *  cleared.
- *
- *  2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective
- *  capabilities of the process are cleared.
- *
- *  3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective
- *  capabilities are set to the permitted capabilities.
- *
- *  fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should 
- *  never happen.
- *
- *  -astor 
- *
- * cevans - New behaviour, Oct '99
- * A process may, via prctl(), elect to keep its capabilities when it
- * calls setuid() and switches away from uid==0. Both permitted and
- * effective sets will be retained.
- * Without this change, it was impossible for a daemon to drop only some
- * of its privilege. The call to setuid(!=0) would drop all privileges!
- * Keeping uid 0 is not an option because uid 0 owns too many vital
- * files..
- * Thanks to Olaf Kirch and Peter Benie for spotting this.
- */
-static inline void cap_emulate_setxuid(int old_ruid, int old_euid, 
-				       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);
-	}
-	if (old_euid == 0 && current->euid != 0) {
-		cap_clear(current->cap_effective);
-	}
-	if (old_euid != 0 && current->euid == 0) {
-		current->cap_effective = current->cap_permitted;
-	}
-}
-
 static int set_user(uid_t new_ruid, int dumpclear)
 {
 	struct user_struct *new_user, *old_user;
@@ -572,6 +545,11 @@ static int set_user(uid_t new_ruid, int dumpclear)
 asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
 {
 	int old_ruid, old_euid, old_suid, new_ruid, new_euid;
+	int retval;
+
+	retval = security_ops->task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
+	if (retval)
+		return retval;
 
 	new_ruid = old_ruid = current->uid;
 	new_euid = old_euid = current->euid;
@@ -608,11 +586,7 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
 		current->suid = current->euid;
 	current->fsuid = current->euid;
 
-	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
-		cap_emulate_setxuid(old_ruid, old_euid, old_suid);
-	}
-
-	return 0;
+	return security_ops->task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
 }
 
 
@@ -632,6 +606,11 @@ asmlinkage long sys_setuid(uid_t uid)
 {
 	int old_euid = current->euid;
 	int old_ruid, old_suid, new_ruid, new_suid;
+	int retval;
+
+	retval = security_ops->task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
+	if (retval)
+		return retval;
 
 	old_ruid = new_ruid = current->uid;
 	old_suid = current->suid;
@@ -652,11 +631,7 @@ asmlinkage long sys_setuid(uid_t uid)
 	current->fsuid = current->euid = uid;
 	current->suid = new_suid;
 
-	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
-		cap_emulate_setxuid(old_ruid, old_euid, old_suid);
-	}
-
-	return 0;
+	return security_ops->task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
 }
 
 
@@ -669,6 +644,11 @@ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 	int old_ruid = current->uid;
 	int old_euid = current->euid;
 	int old_suid = current->suid;
+	int retval;
+
+	retval = security_ops->task_setuid(ruid, euid, suid, LSM_SETID_RES);
+	if (retval)
+		return retval;
 
 	if (!capable(CAP_SETUID)) {
 		if ((ruid != (uid_t) -1) && (ruid != current->uid) &&
@@ -697,11 +677,7 @@ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 	if (suid != (uid_t) -1)
 		current->suid = suid;
 
-	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
-		cap_emulate_setxuid(old_ruid, old_euid, old_suid);
-	}
-
-	return 0;
+	return security_ops->task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
 }
 
 asmlinkage long sys_getresuid(uid_t *ruid, uid_t *euid, uid_t *suid)
@@ -720,6 +696,12 @@ asmlinkage long sys_getresuid(uid_t *ruid, uid_t *euid, uid_t *suid)
  */
 asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
 {
+	int retval;
+
+	retval = security_ops->task_setgid(rgid, egid, sgid, LSM_SETID_RES);
+	if (retval)
+		return retval;
+
 	if (!capable(CAP_SETGID)) {
 		if ((rgid != (gid_t) -1) && (rgid != current->gid) &&
 		    (rgid != current->egid) && (rgid != current->sgid))
@@ -768,6 +750,11 @@ asmlinkage long sys_getresgid(gid_t *rgid, gid_t *egid, gid_t *sgid)
 asmlinkage long sys_setfsuid(uid_t uid)
 {
 	int old_fsuid;
+	int retval;
+
+	retval = security_ops->task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
+	if (retval)
+		return retval;
 
 	old_fsuid = current->fsuid;
 	if (uid == current->uid || uid == current->euid ||
@@ -782,24 +769,9 @@ asmlinkage long sys_setfsuid(uid_t uid)
 		current->fsuid = uid;
 	}
 
-	/* We emulate fsuid by essentially doing a scaled-down version
-	 * of what we did in setresuid and friends. However, we only
-	 * operate on the fs-specific bits of the process' effective
-	 * capabilities 
-	 *
-	 * FIXME - is fsuser used for all CAP_FS_MASK capabilities?
-	 *          if not, we might be a bit too harsh here.
-	 */
-	
-	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
-		if (old_fsuid == 0 && current->fsuid != 0) {
-			cap_t(current->cap_effective) &= ~CAP_FS_MASK;
-		}
-		if (old_fsuid != 0 && current->fsuid == 0) {
-			cap_t(current->cap_effective) |=
-				(cap_t(current->cap_permitted) & CAP_FS_MASK);
-		}
-	}
+	retval = security_ops->task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
+	if (retval)
+		return retval;
 
 	return old_fsuid;
 }
@@ -810,6 +782,11 @@ asmlinkage long sys_setfsuid(uid_t uid)
 asmlinkage long sys_setfsgid(gid_t gid)
 {
 	int old_fsgid;
+	int retval;
+
+	retval = security_ops->task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS);
+	if (retval)
+		return retval;
 
 	old_fsgid = current->fsgid;
 	if (gid == current->gid || gid == current->egid ||
@@ -904,6 +881,10 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
 	}
 
 ok_pgid:
+	err = security_ops->task_setpgid(p, pgid);
+	if (err)
+		goto out;
+
 	p->pgrp = pgid;
 	err = 0;
 out:
@@ -924,8 +905,11 @@ asmlinkage long sys_getpgid(pid_t pid)
 		p = find_task_by_pid(pid);
 
 		retval = -ESRCH;
-		if (p)
-			retval = p->pgrp;
+		if (p) {
+			retval = security_ops->task_getpgid(p);
+			if (!retval)
+				retval = p->pgrp;
+		}
 		read_unlock(&tasklist_lock);
 		return retval;
 	}
@@ -949,8 +933,11 @@ asmlinkage long sys_getsid(pid_t pid)
 		p = find_task_by_pid(pid);
 
 		retval = -ESRCH;
-		if(p)
-			retval = p->session;
+		if(p) {
+			retval = security_ops->task_getsid(p);
+			if (!retval)
+				retval = p->session;
+		}
 		read_unlock(&tasklist_lock);
 		return retval;
 	}
@@ -1008,12 +995,19 @@ asmlinkage long sys_getgroups(int gidsetsize, gid_t *grouplist)
  
 asmlinkage long sys_setgroups(int gidsetsize, gid_t *grouplist)
 {
+	gid_t groups[NGROUPS];
+	int retval;
+
 	if (!capable(CAP_SETGID))
 		return -EPERM;
 	if ((unsigned) gidsetsize > NGROUPS)
 		return -EINVAL;
-	if(copy_from_user(current->groups, grouplist, gidsetsize * sizeof(gid_t)))
+	if(copy_from_user(groups, grouplist, gidsetsize * sizeof(gid_t)))
 		return -EFAULT;
+	retval = security_ops->task_setgroups(gidsetsize, groups);
+	if (retval)
+		return retval;
+	memcpy(current->groups, groups, gidsetsize * sizeof(gid_t));
 	current->ngroups = gidsetsize;
 	return 0;
 }
@@ -1158,6 +1152,7 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit *rlim)
 asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit *rlim)
 {
 	struct rlimit new_rlim, *old_rlim;
+	int retval;
 
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
@@ -1172,6 +1167,11 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit *rlim)
 		if (new_rlim.rlim_cur > NR_OPEN || new_rlim.rlim_max > NR_OPEN)
 			return -EPERM;
 	}
+
+	retval = security_ops->task_setrlimit(resource, &new_rlim);
+	if (retval)
+		return retval;
+
 	*old_rlim = new_rlim;
 	return 0;
 }
@@ -1243,6 +1243,10 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 	int error = 0;
 	int sig;
 
+	error = security_ops->task_prctl(option, arg2, arg3, arg4, arg5);
+	if (error)
+		return error;
+
 	switch (option) {
 		case PR_SET_PDEATHSIG:
 			sig = arg2;

kernel/uid16.c

@@ -12,6 +12,7 @@
 #include <linux/prctl.h>
 #include <linux/init.h>
 #include <linux/highuid.h>
+#include <linux/security.h>
 
 #include <asm/uaccess.h>
 
@@ -128,6 +129,7 @@ asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t *grouplist)
 asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t *grouplist)
 {
 	old_gid_t groups[NGROUPS];
+	gid_t new_groups[NGROUPS];
 	int i;
 
 	if (!capable(CAP_SETGID))
@@ -137,7 +139,11 @@ asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t *grouplist)
 	if (copy_from_user(groups, grouplist, gidsetsize * sizeof(old_gid_t)))
 		return -EFAULT;
 	for (i = 0 ; i < gidsetsize ; i++)
-		current->groups[i] = (gid_t)groups[i];
+		new_groups[i] = (gid_t)groups[i];
+	i = security_ops->task_setgroups(gidsetsize, new_groups);
+	if (i)
+		return i;
+	memcpy(current->groups, new_groups, gidsetsize * sizeof(gid_t));
 	current->ngroups = gidsetsize;
 	return 0;
 }

security/Config.help

+CONFIG_SECURITY_CAPABILITIES
+  This enables the "default" Linux capabilities functionality.
+  If you are unsure how to answer this question, answer Y.
+

security/Config.in

+#
+# Security configuration
+#
+mainmenu_option next_comment
+comment 'Security options'
+define_bool CONFIG_SECURITY_CAPABILITIES y
+endmenu

security/Makefile

+#
+# Makefile for the kernel security code
+#
+
+# Objects that export symbols
+export-objs	:= security.o
+
+# Object file lists
+obj-y		:= security.o dummy.o
+
+obj-$(CONFIG_SECURITY_CAPABILITIES)	+= capability.o
+
+include $(TOPDIR)/Rules.make

security/capability.c

+/*
+ *  Capabilities Linux Security Module
+ *
+ *	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.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/security.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/smp_lock.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+
+/* flag to keep track of how we were registered */
+static int secondary;
+
+static int cap_capable (struct task_struct *tsk, int cap)
+{
+	/* Derived from include/linux/sched.h:capable. */
+	if (cap_raised (tsk->cap_effective, cap))
+		return 0;
+	else
+		return -EPERM;
+}
+
+static int cap_sys_security (unsigned int id, unsigned int call,
+			     unsigned long *args)
+{
+	return -ENOSYS;
+}
+
+static int cap_ptrace (struct task_struct *parent, struct task_struct *child)
+{
+	/* Derived from arch/i386/kernel/ptrace.c:sys_ptrace. */
+	if (!cap_issubset (child->cap_permitted, current->cap_permitted) &&
+	    !capable (CAP_SYS_PTRACE))
+		return -EPERM;
+	else
+		return 0;
+}
+
+static int cap_capget (struct task_struct *target, kernel_cap_t * effective,
+		       kernel_cap_t * inheritable, kernel_cap_t * permitted)
+{
+	/* Derived from kernel/capability.c:sys_capget. */
+	*effective = cap_t (target->cap_effective);
+	*inheritable = cap_t (target->cap_inheritable);
+	*permitted = cap_t (target->cap_permitted);
+	return 0;
+}
+
+static int cap_capset_check (struct task_struct *target,
+			     kernel_cap_t * effective,
+			     kernel_cap_t * inheritable,
+			     kernel_cap_t * permitted)
+{
+	/* Derived from kernel/capability.c:sys_capset. */
+	/* verify restrictions on target's new Inheritable set */
+	if (!cap_issubset (*inheritable,
+			   cap_combine (target->cap_inheritable,
+					current->cap_permitted))) {
+		return -EPERM;
+	}
+
+	/* verify restrictions on target's new Permitted set */
+	if (!cap_issubset (*permitted,
+			   cap_combine (target->cap_permitted,
+					current->cap_permitted))) {
+		return -EPERM;
+	}
+
+	/* verify the _new_Effective_ is a subset of the _new_Permitted_ */
+	if (!cap_issubset (*effective, *permitted)) {
+		return -EPERM;
+	}
+
+	return 0;
+}
+
+static void cap_capset_set (struct task_struct *target,
+			    kernel_cap_t * effective,
+			    kernel_cap_t * inheritable,
+			    kernel_cap_t * permitted)
+{
+	target->cap_effective = *effective;
+	target->cap_inheritable = *inheritable;
+	target->cap_permitted = *permitted;
+}
+
+static int cap_bprm_alloc_security (struct linux_binprm *bprm)
+{
+	return 0;
+}
+
+static int cap_bprm_set_security (struct linux_binprm *bprm)
+{
+	/* Copied from fs/exec.c:prepare_binprm. */
+
+	/* We don't have VFS support for capabilities yet */
+	cap_clear (bprm->cap_inheritable);
+	cap_clear (bprm->cap_permitted);
+	cap_clear (bprm->cap_effective);
+
+	/*  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 (bprm->e_uid == 0 || current->uid == 0) {
+			cap_set_full (bprm->cap_inheritable);
+			cap_set_full (bprm->cap_permitted);
+		}
+		if (bprm->e_uid == 0)
+			cap_set_full (bprm->cap_effective);
+	}
+	return 0;
+}
+
+static int cap_bprm_check_security (struct linux_binprm *bprm)
+{
+	return 0;
+}
+
+static void cap_bprm_free_security (struct linux_binprm *bprm)
+{
+	return;
+}
+
+/* Copied from fs/exec.c */
+static inline int must_not_trace_exec (struct task_struct *p)
+{
+	return (p->ptrace & PT_PTRACED) && !(p->ptrace & PT_PTRACE_CAP);
+}
+
+static void cap_bprm_compute_creds (struct linux_binprm *bprm)
+{
+	/* Derived from fs/exec.c:compute_creds. */
+	kernel_cap_t new_permitted, working;
+	int do_unlock = 0;
+
+	new_permitted = cap_intersect (bprm->cap_permitted, cap_bset);
+	working = cap_intersect (bprm->cap_inheritable,
+				 current->cap_inheritable);
+	new_permitted = cap_combine (new_permitted, working);
+
+	if (!cap_issubset (new_permitted, current->cap_permitted)) {
+		current->mm->dumpable = 0;
+
+		lock_kernel ();
+		if (must_not_trace_exec (current)
+		    || atomic_read (&current->fs->count) > 1
+		    || atomic_read (&current->files->count) > 1
+		    || atomic_read (&current->sig->count) > 1) {
+			if (!capable (CAP_SETPCAP)) {
+				new_permitted = cap_intersect (new_permitted,
+							       current->
+							       cap_permitted);
+			}
+		}
+		do_unlock = 1;
+	}
+
+	/* For init, we want to retain the capabilities set
+	 * in the init_task struct. Thus we skip the usual
+	 * capability rules */
+	if (current->pid != 1) {
+		current->cap_permitted = new_permitted;
+		current->cap_effective =
+		    cap_intersect (new_permitted, bprm->cap_effective);
+	}
+
+	/* AUD: Audit candidate if current->cap_effective is set */
+
+	if (do_unlock)
+		unlock_kernel ();
+
+	current->keep_capabilities = 0;
+}
+
+static int cap_task_create (unsigned long clone_flags)
+{
+	return 0;
+}
+
+static int cap_task_alloc_security (struct task_struct *p)
+{
+	return 0;
+}
+
+static void cap_task_free_security (struct task_struct *p)
+{
+	return;
+}
+
+static int cap_task_setuid (uid_t id0, uid_t id1, uid_t id2, int flags)
+{
+	return 0;
+}
+
+/* moved from kernel/sys.c. */
+/* 
+ * cap_emulate_setxuid() fixes the effective / permitted capabilities of
+ * a process after a call to setuid, setreuid, or setresuid.
+ *
+ *  1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of
+ *  {r,e,s}uid != 0, the permitted and effective capabilities are
+ *  cleared.
+ *
+ *  2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective
+ *  capabilities of the process are cleared.
+ *
+ *  3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective
+ *  capabilities are set to the permitted capabilities.
+ *
+ *  fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should 
+ *  never happen.
+ *
+ *  -astor 
+ *
+ * cevans - New behaviour, Oct '99
+ * A process may, via prctl(), elect to keep its capabilities when it
+ * calls setuid() and switches away from uid==0. Both permitted and
+ * effective sets will be retained.
+ * Without this change, it was impossible for a daemon to drop only some
+ * of its privilege. The call to setuid(!=0) would drop all privileges!
+ * Keeping uid 0 is not an option because uid 0 owns too many vital
+ * files..
+ * Thanks to Olaf Kirch and Peter Benie for spotting this.
+ */
+static inline void cap_emulate_setxuid (int old_ruid, int old_euid,
+					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);
+	}
+	if (old_euid == 0 && current->euid != 0) {
+		cap_clear (current->cap_effective);
+	}
+	if (old_euid != 0 && current->euid == 0) {
+		current->cap_effective = current->cap_permitted;
+	}
+}
+
+static int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid,
+				 int flags)
+{
+	switch (flags) {
+	case LSM_SETID_RE:
+	case LSM_SETID_ID:
+	case LSM_SETID_RES:
+		/* Copied from kernel/sys.c:setreuid/setuid/setresuid. */
+		if (!issecure (SECURE_NO_SETUID_FIXUP)) {
+			cap_emulate_setxuid (old_ruid, old_euid, old_suid);
+		}
+		break;
+	case LSM_SETID_FS:
+		{
+			uid_t old_fsuid = old_ruid;
+
+			/* Copied from kernel/sys.c:setfsuid. */
+
+			/*
+			 * FIXME - is fsuser used for all CAP_FS_MASK capabilities?
+			 *          if not, we might be a bit too harsh here.
+			 */
+
+			if (!issecure (SECURE_NO_SETUID_FIXUP)) {
+				if (old_fsuid == 0 && current->fsuid != 0) {
+					cap_t (current->cap_effective) &=
+					    ~CAP_FS_MASK;
+				}
+				if (old_fsuid != 0 && current->fsuid == 0) {
+					cap_t (current->cap_effective) |=
+					    (cap_t (current->cap_permitted) &
+					     CAP_FS_MASK);
+				}
+			}
+			break;
+		}
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cap_task_setgid (gid_t id0, gid_t id1, gid_t id2, int flags)
+{
+	return 0;
+}
+
+static int cap_task_setpgid (struct task_struct *p, pid_t pgid)
+{
+	return 0;
+}
+
+static int cap_task_getpgid (struct task_struct *p)
+{
+	return 0;
+}
+
+static int cap_task_getsid (struct task_struct *p)
+{
+	return 0;
+}
+
+static int cap_task_setgroups (int gidsetsize, gid_t * grouplist)
+{
+	return 0;
+}
+
+static int cap_task_setnice (struct task_struct *p, int nice)
+{
+	return 0;
+}
+
+static int cap_task_setrlimit (unsigned int resource, struct rlimit *new_rlim)
+{
+	return 0;
+}
+
+static int cap_task_setscheduler (struct task_struct *p, int policy,
+				  struct sched_param *lp)
+{
+	return 0;
+}
+
+static int cap_task_getscheduler (struct task_struct *p)
+{
+	return 0;
+}
+
+static int cap_task_wait (struct task_struct *p)
+{
+	return 0;
+}
+
+static int cap_task_kill (struct task_struct *p, struct siginfo *info, int sig)
+{
+	return 0;
+}
+
+static int cap_task_prctl (int option, unsigned long arg2, unsigned long arg3,
+			   unsigned long arg4, unsigned long arg5)
+{
+	return 0;
+}
+
+static void cap_task_kmod_set_label (void)
+{
+	cap_set_full (current->cap_effective);
+	return;
+}
+
+static void cap_task_reparent_to_init (struct task_struct *p)
+{
+	p->cap_effective = CAP_INIT_EFF_SET;
+	p->cap_inheritable = CAP_INIT_INH_SET;
+	p->cap_permitted = CAP_FULL_SET;
+	p->keep_capabilities = 0;
+	return;
+}
+
+static int cap_register (const char *name, struct security_operations *ops)
+{
+	return -EINVAL;
+}
+
+static int cap_unregister (const char *name, struct security_operations *ops)
+{
+	return -EINVAL;
+}
+
+static struct security_operations capability_ops = {
+	ptrace:				cap_ptrace,
+	capget:				cap_capget,
+	capset_check:			cap_capset_check,
+	capset_set:			cap_capset_set,
+	capable:			cap_capable,
+	sys_security:			cap_sys_security,
+	
+	bprm_alloc_security:		cap_bprm_alloc_security,
+	bprm_free_security:		cap_bprm_free_security,
+	bprm_compute_creds:		cap_bprm_compute_creds,
+	bprm_set_security:		cap_bprm_set_security,
+	bprm_check_security:		cap_bprm_check_security,
+	
+	task_create:			cap_task_create,
+	task_alloc_security:		cap_task_alloc_security,
+	task_free_security:		cap_task_free_security,
+	task_setuid:			cap_task_setuid,
+	task_post_setuid:		cap_task_post_setuid,
+	task_setgid:			cap_task_setgid,
+	task_setpgid:			cap_task_setpgid,
+	task_getpgid:			cap_task_getpgid,
+	task_getsid:			cap_task_getsid,
+	task_setgroups:			cap_task_setgroups,
+	task_setnice:			cap_task_setnice,
+	task_setrlimit:			cap_task_setrlimit,
+	task_setscheduler:		cap_task_setscheduler,
+	task_getscheduler:		cap_task_getscheduler,
+	task_wait:			cap_task_wait,
+	task_kill:			cap_task_kill,
+	task_prctl:			cap_task_prctl,
+	task_kmod_set_label:		cap_task_kmod_set_label,
+	task_reparent_to_init:		cap_task_reparent_to_init,
+	
+	register_security:		cap_register,
+	unregister_security:		cap_unregister,
+};
+
+#if defined(CONFIG_SECURITY_CAPABILITIES_MODULE)
+#define MY_NAME THIS_MODULE->name
+#else
+#define MY_NAME "capability"
+#endif
+
+static int __init capability_init (void)
+{
+	/* register ourselves with the security framework */
+	if (register_security (&capability_ops)) {
+		printk (KERN_INFO
+			"Failure registering capabilities with the kernel\n");
+		/* try registering with primary module */
+		if (mod_reg_security (MY_NAME, &capability_ops)) {
+			printk (KERN_INFO "Failure registering capabilities "
+				"with primary security module.\n");
+			return -EINVAL;
+		}
+		secondary = 1;
+	}
+	printk (KERN_INFO "Capability LSM initialized\n");
+	return 0;
+}
+
+static void __exit capability_exit (void)
+{
+	/* remove ourselves from the security framework */
+	if (secondary) {
+		if (mod_unreg_security (MY_NAME, &capability_ops))
+			printk (KERN_INFO "Failure unregistering capabilities "
+				"with primary module.\n");
+		return;
+	}
+
+	if (unregister_security (&capability_ops)) {
+		printk (KERN_INFO
+			"Failure unregistering capabilities with the kernel\n");
+	}
+}
+
+module_init (capability_init);
+module_exit (capability_exit);
+
+MODULE_DESCRIPTION("Standard Linux Capabilities Security Module");
+MODULE_LICENSE("GPL");

security/dummy.c

+/*
+ * Stub functions for the default security function pointers in case no
+ * security model is loaded.
+ *
+ * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com>
+ * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com>
+ * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.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.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/security.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+
+static int dummy_ptrace (struct task_struct *parent, struct task_struct *child)
+{
+	return 0;
+}
+
+static int dummy_capget (struct task_struct *target, kernel_cap_t * effective,
+			 kernel_cap_t * inheritable, kernel_cap_t * permitted)
+{
+	return 0;
+}
+
+static int dummy_capset_check (struct task_struct *target,
+			       kernel_cap_t * effective,
+			       kernel_cap_t * inheritable,
+			       kernel_cap_t * permitted)
+{
+	return 0;
+}
+
+static void dummy_capset_set (struct task_struct *target,
+			      kernel_cap_t * effective,
+			      kernel_cap_t * inheritable,
+			      kernel_cap_t * permitted)
+{
+	return;
+}
+
+static int dummy_capable (struct task_struct *tsk, int cap)
+{
+	if (cap_is_fs_cap (cap) ? tsk->fsuid == 0 : tsk->euid == 0)
+		/* capability granted */
+		return 0;
+
+	/* capability denied */
+	return -EPERM;
+}
+
+static int dummy_sys_security (unsigned int id, unsigned int call,
+			       unsigned long *args)
+{
+	return -ENOSYS;
+}
+
+static int dummy_bprm_alloc_security (struct linux_binprm *bprm)
+{
+	return 0;
+}
+
+static void dummy_bprm_free_security (struct linux_binprm *bprm)
+{
+	return;
+}
+
+static void dummy_bprm_compute_creds (struct linux_binprm *bprm)
+{
+	return;
+}
+
+static int dummy_bprm_set_security (struct linux_binprm *bprm)
+{
+	return 0;
+}
+
+static int dummy_bprm_check_security (struct linux_binprm *bprm)
+{
+	return 0;
+}
+
+static int dummy_task_create (unsigned long clone_flags)
+{
+	return 0;
+}
+
+static int dummy_task_alloc_security (struct task_struct *p)
+{
+	return 0;
+}
+
+static void dummy_task_free_security (struct task_struct *p)
+{
+	return;
+}
+
+static int dummy_task_setuid (uid_t id0, uid_t id1, uid_t id2, int flags)
+{
+	return 0;
+}
+
+static int dummy_task_post_setuid (uid_t id0, uid_t id1, uid_t id2, int flags)
+{
+	return 0;
+}
+
+static int dummy_task_setgid (gid_t id0, gid_t id1, gid_t id2, int flags)
+{
+	return 0;
+}
+
+static int dummy_task_setpgid (struct task_struct *p, pid_t pgid)
+{
+	return 0;
+}
+
+static int dummy_task_getpgid (struct task_struct *p)
+{
+	return 0;
+}
+
+static int dummy_task_getsid (struct task_struct *p)
+{
+	return 0;
+}
+
+static int dummy_task_setgroups (int gidsetsize, gid_t * grouplist)
+{
+	return 0;
+}
+
+static int dummy_task_setnice (struct task_struct *p, int nice)
+{
+	return 0;
+}
+
+static int dummy_task_setrlimit (unsigned int resource, struct rlimit *new_rlim)
+{
+	return 0;
+}
+
+static int dummy_task_setscheduler (struct task_struct *p, int policy,
+				    struct sched_param *lp)
+{
+	return 0;
+}
+
+static int dummy_task_getscheduler (struct task_struct *p)
+{
+	return 0;
+}
+
+static int dummy_task_wait (struct task_struct *p)
+{
+	return 0;
+}
+
+static int dummy_task_kill (struct task_struct *p, struct siginfo *info,
+			    int sig)
+{
+	return 0;
+}
+
+static int dummy_task_prctl (int option, unsigned long arg2, unsigned long arg3,
+			     unsigned long arg4, unsigned long arg5)
+{
+	return 0;
+}
+
+static void dummy_task_kmod_set_label (void)
+{
+	return;
+}
+
+static void dummy_task_reparent_to_init (struct task_struct *p)
+{
+	p->euid = p->fsuid = 0;
+	return;
+}
+
+static int dummy_register (const char *name, struct security_operations *ops)
+{
+	return -EINVAL;
+}
+
+static int dummy_unregister (const char *name, struct security_operations *ops)
+{
+	return -EINVAL;
+}
+
+struct security_operations dummy_security_ops = {
+	ptrace:				dummy_ptrace,
+	capget:				dummy_capget,
+	capset_check:			dummy_capset_check,
+	capset_set:			dummy_capset_set,
+	capable:			dummy_capable,
+	sys_security:			dummy_sys_security,
+	
+	bprm_alloc_security:		dummy_bprm_alloc_security,
+	bprm_free_security:		dummy_bprm_free_security,
+	bprm_compute_creds:		dummy_bprm_compute_creds,
+	bprm_set_security:		dummy_bprm_set_security,
+	bprm_check_security:		dummy_bprm_check_security,
+
+	task_create:			dummy_task_create,
+	task_alloc_security:		dummy_task_alloc_security,
+	task_free_security:		dummy_task_free_security,
+	task_setuid:			dummy_task_setuid,
+	task_post_setuid:		dummy_task_post_setuid,
+	task_setgid:			dummy_task_setgid,
+	task_setpgid:			dummy_task_setpgid,
+	task_getpgid:			dummy_task_getpgid,
+	task_getsid:			dummy_task_getsid,
+	task_setgroups:			dummy_task_setgroups,
+	task_setnice:			dummy_task_setnice,
+	task_setrlimit:			dummy_task_setrlimit,
+	task_setscheduler:		dummy_task_setscheduler,
+	task_getscheduler:		dummy_task_getscheduler,
+	task_wait:			dummy_task_wait,
+	task_kill:			dummy_task_kill,
+	task_prctl:			dummy_task_prctl,
+	task_kmod_set_label:		dummy_task_kmod_set_label,
+	task_reparent_to_init:		dummy_task_reparent_to_init,
+	
+	register_security:		dummy_register,
+	unregister_security:		dummy_unregister,
+};
+

security/security.c

+/*
+ * Security plug functions
+ *
+ * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com>
+ * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com>
+ * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.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.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/security.h>
+
+#define SECURITY_SCAFFOLD_VERSION	"1.0.0"
+
+extern struct security_operations dummy_security_ops;	/* lives in dummy.c */
+
+struct security_operations *security_ops;	/* Initialized to NULL */
+
+/* This macro checks that all pointers in a struct are non-NULL.  It 
+ * can be fooled by struct padding for object tile alignment and when
+ * pointers to data and pointers to functions aren't the same size.
+ * Yes it's ugly, we'll replace it if it becomes a problem.
+ */
+#define VERIFY_STRUCT(struct_type, s, e) \
+	do { \
+		unsigned long * __start = (unsigned long *)(s); \
+		unsigned long * __end = __start + \
+				sizeof(struct_type)/sizeof(unsigned long *); \
+		while (__start != __end) { \
+			if (!*__start) { \
+				printk(KERN_INFO "%s is missing something\n",\
+					#struct_type); \
+				e++; \
+				break; \
+			} \
+			__start++; \
+		} \
+	} while (0)
+
+static int inline verify (struct security_operations *ops)
+{
+	int err;
+
+	/* verify the security_operations structure exists */
+	if (!ops) {
+		printk (KERN_INFO "Passed a NULL security_operations "
+			"pointer, " __FUNCTION__ " failed.\n");
+		return -EINVAL;
+	}
+
+	/* Perform a little sanity checking on our inputs */
+	err = 0;
+
+	/* This first check scans the whole security_ops struct for
+	 * missing structs or functions.
+	 *
+	 * (There is no further check now, but will leave as is until
+	 *  the lazy registration stuff is done -- JM).
+	 */
+	VERIFY_STRUCT(struct security_operations, ops, err);
+
+	if (err) {
+		printk (KERN_INFO "Not enough functions specified in the "
+			"security_operation structure, " __FUNCTION__
+			" failed.\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * security_scaffolding_startup - initialzes the security scaffolding framework
+ *
+ * This should be called early in the kernel initialization sequence.
+ */
+int security_scaffolding_startup (void)
+{
+	printk (KERN_INFO "Security Scaffold v" SECURITY_SCAFFOLD_VERSION
+		" initialized\n");
+
+	security_ops = &dummy_security_ops;
+
+	return 0;
+}
+
+/**
+ * register_security - registers a security framework with the kernel
+ * @ops: a pointer to the struct security_options that is to be registered
+ *
+ * This function is to allow a security module to register itself with the
+ * kernel security subsystem.  Some rudimentary checking is done on the @ops
+ * value passed to this function.  A call to unregister_security() should be
+ * done to remove this security_options structure from the kernel.
+ *
+ * If the @ops structure does not contain function pointers for all hooks in
+ * the structure, or there is already a security module registered with the
+ * kernel, an error will be returned.  Otherwise 0 is returned on success.
+ */
+int register_security (struct security_operations *ops)
+{
+
+	if (verify (ops)) {
+		printk (KERN_INFO __FUNCTION__ " could not verify "
+			"security_operations structure.\n");
+		return -EINVAL;
+	}
+	if (security_ops != &dummy_security_ops) {
+		printk (KERN_INFO "There is already a security "
+			"framework initialized, " __FUNCTION__ " failed.\n");
+		return -EINVAL;
+	}
+
+	security_ops = ops;
+
+	return 0;
+}
+
+/**
+ * unregister_security - unregisters a security framework with the kernel
+ * @ops: a pointer to the struct security_options that is to be registered
+ *
+ * This function removes a struct security_operations variable that had
+ * previously been registered with a successful call to register_security().
+ *
+ * If @ops does not match the valued previously passed to register_security()
+ * an error is returned.  Otherwise the default security options is set to the
+ * the dummy_security_ops structure, and 0 is returned.
+ */
+int unregister_security (struct security_operations *ops)
+{
+	if (ops != security_ops) {
+		printk (KERN_INFO __FUNCTION__ ": trying to unregister "
+			"a security_opts structure that is not "
+			"registered, failing.\n");
+		return -EINVAL;
+	}
+
+	security_ops = &dummy_security_ops;
+
+	return 0;
+}
+
+/**
+ * mod_reg_security - allows security modules to be "stacked"
+ * @name: a pointer to a string with the name of the security_options to be registered
+ * @ops: a pointer to the struct security_options that is to be registered
+ *
+ * This function allows security modules to be stacked if the currently loaded
+ * security module allows this to happen.  It passes the @name and @ops to the
+ * register_security function of the currently loaded security module.
+ *
+ * The return value depends on the currently loaded security module, with 0 as
+ * success.
+ */
+int mod_reg_security (const char *name, struct security_operations *ops)
+{
+	if (verify (ops)) {
+		printk (KERN_INFO __FUNCTION__ " could not verify "
+			"security operations.\n");
+		return -EINVAL;
+	}
+
+	if (ops == security_ops) {
+		printk (KERN_INFO __FUNCTION__ " security operations "
+			"already registered.\n");
+		return -EINVAL;
+	}
+
+	return security_ops->register_security (name, ops);
+}
+
+/**
+ * mod_unreg_security - allows a security module registered with mod_reg_security() to be unloaded
+ * @name: a pointer to a string with the name of the security_options to be removed
+ * @ops: a pointer to the struct security_options that is to be removed
+ *
+ * This function allows security modules that have been successfully registered
+ * with a call to mod_reg_security() to be unloaded from the system.
+ * This calls the currently loaded security module's unregister_security() call
+ * with the @name and @ops variables.
+ *
+ * The return value depends on the currently loaded security module, with 0 as
+ * success.
+ */
+int mod_unreg_security (const char *name, struct security_operations *ops)
+{
+	if (ops == security_ops) {
+		printk (KERN_INFO __FUNCTION__ " invalid attempt to unregister "
+			" primary security ops.\n");
+		return -EINVAL;
+	}
+
+	return security_ops->unregister_security (name, ops);
+}
+
+/**
+ * capable - calls the currently loaded security module's capable() function with the specified capability
+ * @cap: the requested capability level.
+ *
+ * This function calls the currently loaded security module's cabable()
+ * function with a pointer to the current task and the specified @cap value.
+ *
+ * This allows the security module to implement the capable function call
+ * however it chooses to.
+ */
+int capable (int cap)
+{
+	if (security_ops->capable (current, cap)) {
+		/* capability denied */
+		return 0;
+	}
+
+	/* capability granted */
+	current->flags |= PF_SUPERPRIV;
+	return 1;
+}
+
+/**
+ * sys_security - security syscall multiplexor.
+ * @id: module id
+ * @call: call identifier
+ * @args: arg list for call
+ *
+ * Similar to sys_socketcall.  Can use id to help identify which module user
+ * app is talking to.  The recommended convention for creating the
+ * hexadecimal id value is:
+ * 'echo "Name_of_module" | md5sum | cut -c -8'.
+ * By following this convention, there's no need for a central registry.
+ */
+asmlinkage long sys_security (unsigned int id, unsigned int call,
+			      unsigned long *args)
+{
+	return security_ops->sys_security (id, call, args);
+}
+
+EXPORT_SYMBOL (register_security);
+EXPORT_SYMBOL (unregister_security);
+EXPORT_SYMBOL (mod_reg_security);
+EXPORT_SYMBOL (mod_unreg_security);
+EXPORT_SYMBOL (capable);
+EXPORT_SYMBOL (security_ops);