Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753228AbZL3S3u (ORCPT ); Wed, 30 Dec 2009 13:29:50 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752896AbZL3S3t (ORCPT ); Wed, 30 Dec 2009 13:29:49 -0500 Received: from e33.co.us.ibm.com ([32.97.110.151]:53217 "EHLO e33.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752856AbZL3S3s (ORCPT ); Wed, 30 Dec 2009 13:29:48 -0500 Date: Wed, 30 Dec 2009 12:29:33 -0600 From: "Serge E. Hallyn" To: "Eric W. Biederman" Cc: Bryan Donlan , Alan Cox , Benny Amorsen , Michael Stone , linux-kernel@vger.kernel.org, netdev@vger.kernel.org, linux-security-module@vger.kernel.org, Andi Kleen , David Lang , Oliver Hartkopp , Herbert Xu , Valdis Kletnieks , Evgeniy Polyakov , "C. Scott Ananian" , James Morris , Bernie Innocenti , Mark Seaborn , Randy Dunlap , =?iso-8859-1?Q?Am=E9rico?= Wang , Tetsuo Handa , Samir Bellabes , Casey Schaufler , Pavel Machek , Al Viro Subject: Re: [RFC][PATCH v2] Unprivileged: Disable raising of privileges Message-ID: <20091230182933.GB14493@us.ibm.com> References: <20091229211139.0732a0c1@lxorguk.ukuu.org.uk> <20091229223631.GB22578@us.ibm.com> <3e8340490912291954v5a837a26p64bd776102d281d7@mail.gmail.com> <3e8340490912292057g3e87eaabn115f85b78af2b08c@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7273 Lines: 208 Quoting Eric W. Biederman (ebiederm@xmission.com): > > If we can know that a process will never raise > it's priveleges we can enable a lot of features > that otherwise would be unsafe, because they > could break assumptions of existing suid executables. > > To allow this to be used as a sand boxing feature > also disable ptracing other executables without > this new restriction. > > For the moment I have used a per thread flag because > we are out of per process flags. > > To ensure all descendants get this flag I rely on > the default copying of procss structures. > > Added bprm->nosuid to make remove the need to add > duplicate error prone checks. This ensures that > the disabling of suid executables is exactly the > same as MNT_NOSUID. > > Signed-off-by: Eric W. Biederman > --- > arch/x86/include/asm/thread_info.h | 2 ++ > fs/exec.c | 6 ++++-- > include/linux/binfmts.h | 1 + > include/linux/prctl.h | 2 ++ > kernel/ptrace.c | 4 ++++ > kernel/sys.c | 16 ++++++++++++++++ > security/commoncap.c | 14 +++++++++++++- > security/selinux/hooks.c | 2 +- > 8 files changed, 43 insertions(+), 4 deletions(-) > > diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h > index 375c917..e716203 100644 > --- a/arch/x86/include/asm/thread_info.h > +++ b/arch/x86/include/asm/thread_info.h > @@ -82,6 +82,7 @@ struct thread_info { > #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ > #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ > #define TIF_SECCOMP 8 /* secure computing */ > +#define TIF_NOSUID 9 /* suid exec permanently disabled */ > #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ > #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ > #define TIF_NOTSC 16 /* TSC is not accessible in userland */ > @@ -107,6 +108,7 @@ struct thread_info { > #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) > #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) > #define _TIF_SECCOMP (1 << TIF_SECCOMP) > +#define _TIF_NOSUID (1 << TIF_NOSUID) > #define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) > #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) > #define _TIF_NOTSC (1 << TIF_NOTSC) > diff --git a/fs/exec.c b/fs/exec.c > index 632b02e..5cba5ac 100644 > --- a/fs/exec.c > +++ b/fs/exec.c > @@ -1131,8 +1131,10 @@ int prepare_binprm(struct linux_binprm *bprm) > /* clear any previous set[ug]id data from a previous binary */ > bprm->cred->euid = current_euid(); > bprm->cred->egid = current_egid(); > - > - if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) { > + bprm->nosuid = > + (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) || > + test_tsk_thread_flag(current, TIF_NOSUID); > + if (bprm->nosuid) { > /* Set-uid? */ > if (mode & S_ISUID) { > bprm->per_clear |= PER_CLEAR_ON_SETID; > diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h > index cd4349b..c3b5a30 100644 > --- a/include/linux/binfmts.h > +++ b/include/linux/binfmts.h > @@ -44,6 +44,7 @@ struct linux_binprm{ > #ifdef __alpha__ > unsigned int taso:1; > #endif > + unsigned int nosuid:1; /* True if suid bits are ignored */ > unsigned int recursion_depth; > struct file * file; > struct cred *cred; /* new credentials */ > diff --git a/include/linux/prctl.h b/include/linux/prctl.h > index a3baeb2..acb3516 100644 > --- a/include/linux/prctl.h > +++ b/include/linux/prctl.h > @@ -102,4 +102,6 @@ > > #define PR_MCE_KILL_GET 34 > > +#define PR_SET_NOSUID 35 > + > #endif /* _LINUX_PRCTL_H */ > diff --git a/kernel/ptrace.c b/kernel/ptrace.c > index 23bd09c..b91040c 100644 > --- a/kernel/ptrace.c > +++ b/kernel/ptrace.c > @@ -152,6 +152,10 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) > if (!dumpable && !capable(CAP_SYS_PTRACE)) > return -EPERM; > > + if (test_tsk_thread_flag(current, TIF_NOSUID) && > + !test_tsk_thread_flag(task, TIF_NOSUID)) > + return -EPERM; > + > return security_ptrace_access_check(task, mode); > } > > diff --git a/kernel/sys.c b/kernel/sys.c > index 26a6b73..1d1902a 100644 > --- a/kernel/sys.c > +++ b/kernel/sys.c > @@ -1578,6 +1578,22 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, > else > error = PR_MCE_KILL_DEFAULT; > break; > + case PR_SET_NOSUID: > + { > + const struct cred *cred = current->cred; > + error = -EINVAL; > + if ( (cred->uid != cred->suid) || > + (cred->uid != cred->euid) || > + (cred->uid != cred->fsuid) || > + (cred->gid != cred->sgid) || > + (cred->gid != cred->egid) || > + (cred->gid != cred->fsgid) || > + (atomic_read(¤t->signal->count) != 1)) > + break; > + error = 0; > + set_tsk_thread_flag(current, TIF_NOSUID); > + break; > + } > default: > error = -EINVAL; > break; > diff --git a/security/commoncap.c b/security/commoncap.c > index f800fdb..28ab286 100644 > --- a/security/commoncap.c > +++ b/security/commoncap.c > @@ -389,7 +389,7 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective) > if (!file_caps_enabled) > return 0; > > - if (bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID) > + if (bprm->nosuid) > return 0; > > dentry = dget(bprm->file->f_dentry); > @@ -869,6 +869,18 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, > new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); > goto changed; > > + case PR_SET_NOSUID: > + { > + const struct cred *cred = current->cred; > + error = -EINVAL; Should this be -EPERM? not sure... > + /* Perform the capabilities checks */ > + if (!cap_isclear(cred->cap_permitted) || > + !cap_isclear(cred->cap_effective)) No need to check cap_effective, as no bits can be there which are not in cap_permitted. To be honest, I don't think there is much reason to not have this check done in the main sys_prctl(0 - capabilities themselves are not optional in the kernel, while cap_task_prctl() is. So you are setting us up to have cases where say an apparmor user can call this with uid 0 and/or active capabilities. > + goto error; > + /* Have the default perform the rest of the work. */ > + error = -ENOSYS; > + goto error; > + } > default: > /* No functionality available - continue with default */ > error = -ENOSYS; > diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c > index 7a374c2..d14cd24 100644 > --- a/security/selinux/hooks.c > +++ b/security/selinux/hooks.c > @@ -2147,7 +2147,7 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm) > COMMON_AUDIT_DATA_INIT(&ad, FS); > ad.u.fs.path = bprm->file->f_path; > > - if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) > + if (bprm->nosid) typo - nosuid? > new_tsec->sid = old_tsec->sid; > > if (new_tsec->sid == old_tsec->sid) { > -- > 1.6.5.2.143.g8cc62 Thanks, I think this looks good. -serge -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/