From b788d2ae4a0a898c7a4661256f62bf7d30da2deb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 13 Apr 2012 08:51:55 +1000 Subject: [PATCH] fs: hardlink creation restrictions On systems that have user-writable directories on the same partition as system files, a long-standing class of security issues is the hardlink-based time-of-check-time-of-use race, most commonly seen in world-writable directories like /tmp. The common method of exploitation of this flaw is to cross privilege boundaries when following a given hardlink (i.e. a root process follows a hardlink created by another user). Additionally, an issue exists where users can "pin" a potentially vulnerable setuid/setgid file so that an administrator will not actually upgrade a system fully. The solution is to permit hardlinks to only be created when the user is already the existing file's owner, or if they already have read/write access to the existing file. Many Linux users are surprised when they learn they can link to files they have no access to, so this change appears to follow the doctrine of "least surprise". Additionally, this change does not violate POSIX, which states "the implementation may require that the calling process has permission to access the existing file"[1]. This change is known to break some implementations of the "at" daemon, though the version used by Fedora and Ubuntu has been fixed[2] for a while. Otherwise, the change has been undisruptive while in use in Ubuntu for the last 1.5 years. This patch is based on the patch in Openwall and grsecurity. I have added a sysctl to enable the protected behavior, documentation, and an audit notification. [1] http://pubs.opengroup.org/onlinepubs/9699919799/functions/linkat.html [2] http://anonscm.debian.org/gitweb/?p=collab-maint/at.git;a=commitdiff;h=f4114656c3a6c6f6070e315ffdf940a49eda3279 [akpm@linux-foundation.org: uninline may_linkat() and audit_log_link_denied()] Signed-off-by: Kees Cook Acked-by: Ingo Molnar Cc: Matthew Wilcox Cc: Alexander Viro Cc: Rik van Riel Cc: Federica Teodori Cc: Lucian Adrian Grijincu Cc: Peter Zijlstra Cc: Eric Paris Cc: Randy Dunlap Cc: Dan Rosenberg Signed-off-by: Andrew Morton --- Documentation/sysctl/fs.txt | 21 ++++++ fs/Kconfig | 54 +++++++++++---- fs/namei.c | 134 ++++++++++++++++++++++++++++-------- include/linux/fs.h | 1 + kernel/sysctl.c | 11 ++- 5 files changed, 178 insertions(+), 43 deletions(-) diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 01daa8049323..9d29414db420 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -32,6 +32,7 @@ Currently, these files are in /proc/sys/fs: - nr_open - overflowuid - overflowgid +- protected_hardlinks - protected_symlinks - suid_dumpable - super-max @@ -158,6 +159,26 @@ The default is 65534. ============================================================== +protected_hardlinks: + +A long-standing class of security issues is the hardlink-based +time-of-check-time-of-use race, most commonly seen in world-writable +directories like /tmp. The common method of exploitation of this flaw +is to cross privilege boundaries when following a given hardlink (i.e. a +root process follows a hardlink created by another user). Additionally, +on systems without separated partitions, this stops unauthorized users +from "pinning" vulnerable setuid/setgid files against being upgraded by +the administrator, or linking to special files. + +When set to "0", hardlink creation behavior is unrestricted. + +When set to "1" hardlinks cannot be created by users if they do not +already own the source file, or do not have read/write access to it. + +This protection is based on the restrictions in Openwall and grsecurity. + +============================================================== + protected_symlinks: A long-standing class of security issues is the symlink-based diff --git a/fs/Kconfig b/fs/Kconfig index f54855b03109..ba8974ed6365 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -276,27 +276,29 @@ endif # NETWORK_FILESYSTEMS source "fs/nls/Kconfig" source "fs/dlm/Kconfig" -config PROTECTED_SYMLINKS - bool "Evaluate vulnerable symlink conditions" +config PROTECTED_LINKS + bool "Evaluate vulnerable link conditions" default y help - A long-standing class of security issues is the symlink-based + A long-standing class of security issues is the link-based time-of-check-time-of-use race, most commonly seen in world-writable directories like /tmp. The common method of exploitation of this flaw is to cross privilege boundaries - when following a given symlink (i.e. a root process follows - a malicious symlink belonging to another user). + when following a given link (i.e. a root process follows + a malicious symlink belonging to another user, or a hardlink + created to a root-owned file). - Enabling this adds the logic to examine these dangerous symlink - conditions. Whether or not the dangerous symlink situations are - allowed is controlled by PROTECTED_SYMLINKS_ENABLED. + Enabling this adds the logic to examine these dangerous link + conditions. Whether or not the dangerous link situations are + allowed is controlled by PROTECTED_HARDLINKS_ENABLED and + PROTECTED_SYMLINKS_ENABLED. -config PROTECTED_SYMLINKS_ENABLED - depends on PROTECTED_SYMLINKS +config PROTECTED_SYMLINKS + depends on PROTECTED_LINKS bool "Disallow symlink following in sticky world-writable dirs" default y help - Solve ToCToU symlink race vulnerablities by permitting symlinks + Solve ToCToU symlink race vulnerabilities by permitting symlinks to be followed only when outside a sticky world-writable directory, or when the uid of the symlink and follower match, or when the directory and symlink owners match. @@ -304,10 +306,34 @@ config PROTECTED_SYMLINKS_ENABLED When PROC_SYSCTL is enabled, this setting can also be controlled via /proc/sys/kernel/protected_symlinks. -config PROTECTED_SYMLINKS_ENABLED_SYSCTL - depends on PROTECTED_SYMLINKS + See Documentation/sysctl/fs.txt for details. + +config PROTECTED_SYMLINKS_SYSCTL + depends on PROTECTED_LINKS + int + default "1" if PROTECTED_SYMLINKS + default "0" + +config PROTECTED_HARDLINKS + depends on PROTECTED_LINKS + bool "Disallow hardlink creation to non-accessible files" + default y + help + Solve ToCToU hardlink race vulnerabilities by permitting hardlinks + to be created only when to a regular file that is owned by the user, + or is readable and writable by the user. Also blocks users from + "pinning" vulnerable setuid/setgid programs from being upgraded by + the administrator. + + When PROC_SYSCTL is enabled, this setting can also be controlled + via /proc/sys/kernel/protected_hardlinks. + + See Documentation/sysctl/fs.txt for details. + +config PROTECTED_HARDLINKS_SYSCTL + depends on PROTECTED_LINKS int - default "1" if PROTECTED_SYMLINKS_ENABLED + default "1" if PROTECTED_HARDLINKS default "0" endmenu diff --git a/fs/namei.c b/fs/namei.c index bec598ccdee8..1bb54dd130a4 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -623,16 +623,32 @@ static inline void put_link(struct nameidata *nd, struct path *link, void *cooki path_put(link); } -#ifdef CONFIG_PROTECTED_SYMLINKS +#ifdef CONFIG_PROTECTED_LINKS int sysctl_protected_symlinks __read_mostly = - CONFIG_PROTECTED_SYMLINKS_ENABLED_SYSCTL; + CONFIG_PROTECTED_SYMLINKS_SYSCTL; +int sysctl_protected_hardlinks __read_mostly = + CONFIG_PROTECTED_HARDLINKS_SYSCTL; + +static void audit_log_link_denied(const char *operation, struct path *link) +{ + struct audit_buffer *ab; + + ab = audit_log_start(current->audit_context, GFP_KERNEL, AUDIT_AVC); + audit_log_format(ab, "op=%s action=denied", operation); + audit_log_format(ab, " pid=%d comm=", current->pid); + audit_log_untrustedstring(ab, current->comm); + audit_log_d_path(ab, " path=", link); + audit_log_format(ab, " dev="); + audit_log_untrustedstring(ab, link->dentry->d_inode->i_sb->s_id); + audit_log_format(ab, " ino=%lu", link->dentry->d_inode->i_ino); + audit_log_end(ab); +} /** * may_follow_link - Check symlink following for unsafe situations - * @dentry: The inode/dentry of the symlink - * @nameidata: The path data of the symlink + * @link: The path of the symlink * - * In the case of the protected_symlinks sysctl being enabled, + * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out @@ -643,19 +659,20 @@ int sysctl_protected_symlinks __read_mostly = * * Returns 0 if following the symlink is allowed, -ve on error. */ -static inline int -may_follow_link(struct dentry *dentry, struct nameidata *nameidata) +static inline int may_follow_link(struct path *link) { int error = 0; const struct inode *parent; const struct inode *inode; const struct cred *cred; + struct dentry *dentry; if (!sysctl_protected_symlinks) return 0; /* Allowed if owner and follower match. */ cred = current_cred(); + dentry = link->dentry; inode = dentry->d_inode; if (cred->fsuid == inode->i_uid) return 0; @@ -669,29 +686,87 @@ may_follow_link(struct dentry *dentry, struct nameidata *nameidata) } spin_unlock(&dentry->d_lock); -#ifdef CONFIG_AUDIT - if (error) { - struct audit_buffer *ab; - - ab = audit_log_start(current->audit_context, - GFP_KERNEL, AUDIT_AVC); - audit_log_format(ab, "op=follow_link action=denied"); - audit_log_format(ab, " pid=%d comm=", current->pid); - audit_log_untrustedstring(ab, current->comm); - audit_log_d_path(ab, " path=", &nameidata->path); - audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, dentry->d_name.name); - audit_log_format(ab, " dev="); - audit_log_untrustedstring(ab, inode->i_sb->s_id); - audit_log_format(ab, " ino=%lu", inode->i_ino); - audit_log_end(ab); - } -#endif + if (error) + audit_log_link_denied("follow_link", link); + return error; } + +/** + * safe_hardlink_source - Check for safe hardlink conditions + * @inode: the source inode to hardlink from + * + * Return false if at least one of the following conditions: + * - inode is not a regular file + * - inode is setuid + * - inode is setgid and group-exec + * - access failure for read and write + * + * Otherwise returns true. + */ +static bool safe_hardlink_source(struct inode *inode) +{ + mode_t mode = inode->i_mode; + + /* Special files should not get pinned to the filesystem. */ + if (!S_ISREG(mode)) + return false; + + /* Setuid files should not get pinned to the filesystem. */ + if (mode & S_ISUID) + return false; + + /* Executable setgid files should not get pinned to the filesystem. */ + if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) + return false; + + /* Hardlinking to unreadable or unwritable sources is dangerous. */ + if (inode_permission(inode, MAY_READ | MAY_WRITE)) + return false; + + return true; +} + +/** + * may_linkat - Check permissions for creating a hardlink + * @link: the source to hardlink from + * + * Block hardlink when all of: + * - sysctl_protected_hardlinks enabled + * - fsuid does not match inode + * - hardlink source is unsafe (see safe_hardlink_source() above) + * - not CAP_FOWNER + * + * Returns 0 if successful, -ve on error. + */ +static int may_linkat(struct path *link) +{ + const struct cred *cred; + struct inode *inode; + + if (!sysctl_protected_hardlinks) + return 0; + + cred = current_cred(); + inode = link->dentry->d_inode; + + /* Source inode owner (or CAP_FOWNER) can hardlink all they like, + * otherwise, it must be a safe source. + */ + if (cred->fsuid == inode->i_uid || safe_hardlink_source(inode) || + capable(CAP_FOWNER)) + return 0; + + audit_log_link_denied("linkat", link); + return -EPERM; +} #else -static inline int -may_follow_link(struct dentry *dentry, struct nameidata *nameidata) +static inline int may_follow_link(struct path *link) +{ + return 0; +} + +static inline int may_linkat(struct path *link) { return 0; } @@ -720,7 +795,7 @@ follow_link(struct path *link, struct nameidata *nd, void **p, bool sensitive) nd_set_link(nd, NULL); if (sensitive) - error = may_follow_link(link->dentry, nd); + error = may_follow_link(link); if (!error) error = security_inode_follow_link(link->dentry, nd); if (error) { @@ -3135,6 +3210,9 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; + error = may_linkat(&old_path); + if (error) + goto out_dput; error = mnt_want_write(new_path.mnt); if (error) goto out_dput; diff --git a/include/linux/fs.h b/include/linux/fs.h index 58b6e5a07e84..f30a3a9481f5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -428,6 +428,7 @@ extern int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; +extern int sysctl_protected_hardlinks; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2cbace33ab1f..ba133ec3c4f5 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1493,7 +1493,7 @@ static struct ctl_table fs_table[] = { }, #endif #endif -#ifdef CONFIG_PROTECTED_SYMLINKS +#ifdef CONFIG_PROTECTED_LINKS { .procname = "protected_symlinks", .data = &sysctl_protected_symlinks, @@ -1503,6 +1503,15 @@ static struct ctl_table fs_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "protected_hardlinks", + .data = &sysctl_protected_hardlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, #endif { .procname = "suid_dumpable", -- 2.39.5