From 3898b1b4ebff8dcfbcf1807e0661585e06c9a91c Mon Sep 17 00:00:00 2001 From: "Andrew G. Morgan" Date: Mon, 28 Apr 2008 02:13:40 -0700 Subject: capabilities: implement per-process securebits Filesystem capability support makes it possible to do away with (set)uid-0 based privilege and use capabilities instead. That is, with filesystem support for capabilities but without this present patch, it is (conceptually) possible to manage a system with capabilities alone and never need to obtain privilege via (set)uid-0. Of course, conceptually isn't quite the same as currently possible since few user applications, certainly not enough to run a viable system, are currently prepared to leverage capabilities to exercise privilege. Further, many applications exist that may never get upgraded in this way, and the kernel will continue to want to support their setuid-0 base privilege needs. Where pure-capability applications evolve and replace setuid-0 binaries, it is desirable that there be a mechanisms by which they can contain their privilege. In addition to leveraging the per-process bounding and inheritable sets, this should include suppressing the privilege of the uid-0 superuser from the process' tree of children. The feature added by this patch can be leveraged to suppress the privilege associated with (set)uid-0. This suppression requires CAP_SETPCAP to initiate, and only immediately affects the 'current' process (it is inherited through fork()/exec()). This reimplementation differs significantly from the historical support for securebits which was system-wide, unwieldy and which has ultimately withered to a dead relic in the source of the modern kernel. With this patch applied a process, that is capable(CAP_SETPCAP), can now drop all legacy privilege (through uid=0) for itself and all subsequently fork()'d/exec()'d children with: prctl(PR_SET_SECUREBITS, 0x2f); This patch represents a no-op unless CONFIG_SECURITY_FILE_CAPABILITIES is enabled at configure time. [akpm@linux-foundation.org: fix uninitialised var warning] [serue@us.ibm.com: capabilities: use cap_task_prctl when !CONFIG_SECURITY] Signed-off-by: Andrew G. Morgan Acked-by: Serge Hallyn Reviewed-by: James Morris Cc: Stephen Smalley Cc: Paul Moore Signed-off-by: Serge E. Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/init_task.h') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 37a6f5bc4a92..bf6b8a61f8db 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #define INIT_FDTABLE \ @@ -172,7 +173,7 @@ extern struct group_info init_groups; .cap_inheritable = CAP_INIT_INH_SET, \ .cap_permitted = CAP_FULL_SET, \ .cap_bset = CAP_INIT_BSET, \ - .keep_capabilities = 0, \ + .securebits = SECUREBITS_DEFAULT, \ .user = INIT_USER, \ .comm = "swapper", \ .thread = INIT_THREAD, \ -- cgit v1.2.3 From 9f3acc3140444a900ab280de942291959f0f615d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Apr 2008 07:44:08 -0400 Subject: [PATCH] split linux/file.h Initial splitoff of the low-level stuff; taken to fdtable.h Signed-off-by: Al Viro --- arch/mips/kernel/kspd.c | 1 + arch/powerpc/platforms/cell/spufs/coredump.c | 1 + drivers/char/tty_audit.c | 1 + drivers/char/tty_io.c | 1 + fs/compat.c | 1 + fs/dnotify.c | 2 +- fs/exec.c | 1 + fs/fcntl.c | 1 + fs/file.c | 1 + fs/file_table.c | 1 + fs/locks.c | 1 + fs/open.c | 1 + fs/proc/array.c | 1 + fs/proc/base.c | 1 + fs/select.c | 1 + include/linux/fdtable.h | 99 ++++++++++++++++++++++++++++ include/linux/file.h | 86 +----------------------- include/linux/init_task.h | 2 +- kernel/exit.c | 1 + kernel/fork.c | 1 + kernel/kmod.c | 1 + security/selinux/hooks.c | 1 + 22 files changed, 121 insertions(+), 86 deletions(-) create mode 100644 include/linux/fdtable.h (limited to 'include/linux/init_task.h') diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c index 998c4efcce88..ceb62dce1c9c 100644 --- a/arch/mips/kernel/kspd.c +++ b/arch/mips/kernel/kspd.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index b962c3ab470c..af116aadba10 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -22,6 +22,7 @@ #include #include +#include #include #include #include diff --git a/drivers/char/tty_audit.c b/drivers/char/tty_audit.c index 6342b0534f4d..3582f43345a8 100644 --- a/drivers/char/tty_audit.c +++ b/drivers/char/tty_audit.c @@ -11,6 +11,7 @@ #include #include +#include #include struct tty_audit_buf { diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index 1d298c2cf930..49c1a2267a55 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -78,6 +78,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/compat.c b/fs/compat.c index 139dc93c092d..332a869d2c53 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/dnotify.c b/fs/dnotify.c index eaecc4cfe540..676073b8dda5 100644 --- a/fs/dnotify.c +++ b/fs/dnotify.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include int dir_notify_enable __read_mostly = 1; diff --git a/fs/exec.c b/fs/exec.c index 9f9f931ef949..aeaa9791d8be 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -24,6 +24,7 @@ #include #include +#include #include #include #include diff --git a/fs/fcntl.c b/fs/fcntl.c index 3f3ac630ccde..bfd776509a72 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/file.c b/fs/file.c index 5110acb1c9ef..f6fbcb49faf7 100644 --- a/fs/file.c +++ b/fs/file.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/file_table.c b/fs/file_table.c index 7a0a9b872251..83084225b4c3 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/locks.c b/fs/locks.c index 44d9a6a7ec50..663c069b59b3 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -116,6 +116,7 @@ #include #include +#include #include #include #include diff --git a/fs/open.c b/fs/open.c index 7af1f05d5978..a1450086e92f 100644 --- a/fs/open.c +++ b/fs/open.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/proc/array.c b/fs/proc/array.c index c135cbdd9127..dca997a93bff 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -73,6 +73,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/proc/base.c b/fs/proc/base.c index fcf02f2deeba..808cbdc193d3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/select.c b/fs/select.c index 80d70387e790..8dda969614a9 100644 --- a/fs/select.c +++ b/fs/select.c @@ -21,6 +21,7 @@ #include #include /* for STICKY_TIMEOUTS */ #include +#include #include #include diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h new file mode 100644 index 000000000000..a118f3c0b240 --- /dev/null +++ b/include/linux/fdtable.h @@ -0,0 +1,99 @@ +/* + * descriptor table internals; you almost certainly want file.h instead. + */ + +#ifndef __LINUX_FDTABLE_H +#define __LINUX_FDTABLE_H + +#include +#include +#include +#include +#include +#include + +/* + * The default fd array needs to be at least BITS_PER_LONG, + * as this is the granularity returned by copy_fdset(). + */ +#define NR_OPEN_DEFAULT BITS_PER_LONG + +/* + * The embedded_fd_set is a small fd_set, + * suitable for most tasks (which open <= BITS_PER_LONG files) + */ +struct embedded_fd_set { + unsigned long fds_bits[1]; +}; + +struct fdtable { + unsigned int max_fds; + struct file ** fd; /* current fd array */ + fd_set *close_on_exec; + fd_set *open_fds; + struct rcu_head rcu; + struct fdtable *next; +}; + +/* + * Open file table structure + */ +struct files_struct { + /* + * read mostly part + */ + atomic_t count; + struct fdtable *fdt; + struct fdtable fdtab; + /* + * written part on a separate cache line in SMP + */ + spinlock_t file_lock ____cacheline_aligned_in_smp; + int next_fd; + struct embedded_fd_set close_on_exec_init; + struct embedded_fd_set open_fds_init; + struct file * fd_array[NR_OPEN_DEFAULT]; +}; + +#define files_fdtable(files) (rcu_dereference((files)->fdt)) + +extern struct kmem_cache *filp_cachep; + +struct file_operations; +struct vfsmount; +struct dentry; + +extern int expand_files(struct files_struct *, int nr); +extern void free_fdtable_rcu(struct rcu_head *rcu); +extern void __init files_defer_init(void); + +static inline void free_fdtable(struct fdtable *fdt) +{ + call_rcu(&fdt->rcu, free_fdtable_rcu); +} + +static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd) +{ + struct file * file = NULL; + struct fdtable *fdt = files_fdtable(files); + + if (fd < fdt->max_fds) + file = rcu_dereference(fdt->fd[fd]); + return file; +} + +/* + * Check whether the specified fd has an open file. + */ +#define fcheck(fd) fcheck_files(current->files, fd) + +struct task_struct; + +struct files_struct *get_files_struct(struct task_struct *); +void put_files_struct(struct files_struct *fs); +void reset_files_struct(struct files_struct *); +int unshare_files(struct files_struct **); + +extern struct kmem_cache *files_cachep; + +#endif /* __LINUX_FDTABLE_H */ diff --git a/include/linux/file.h b/include/linux/file.h index 69baf5a4f0a5..27c64bdc68c9 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -5,59 +5,11 @@ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H -#include -#include #include -#include -#include #include +#include -/* - * The default fd array needs to be at least BITS_PER_LONG, - * as this is the granularity returned by copy_fdset(). - */ -#define NR_OPEN_DEFAULT BITS_PER_LONG - -/* - * The embedded_fd_set is a small fd_set, - * suitable for most tasks (which open <= BITS_PER_LONG files) - */ -struct embedded_fd_set { - unsigned long fds_bits[1]; -}; - -struct fdtable { - unsigned int max_fds; - struct file ** fd; /* current fd array */ - fd_set *close_on_exec; - fd_set *open_fds; - struct rcu_head rcu; - struct fdtable *next; -}; - -/* - * Open file table structure - */ -struct files_struct { - /* - * read mostly part - */ - atomic_t count; - struct fdtable *fdt; - struct fdtable fdtab; - /* - * written part on a separate cache line in SMP - */ - spinlock_t file_lock ____cacheline_aligned_in_smp; - int next_fd; - struct embedded_fd_set close_on_exec_init; - struct embedded_fd_set open_fds_init; - struct file * fd_array[NR_OPEN_DEFAULT]; -}; - -#define files_fdtable(files) (rcu_dereference((files)->fdt)) - -extern struct kmem_cache *filp_cachep; +struct file; extern void __fput(struct file *); extern void fput(struct file *); @@ -85,41 +37,7 @@ extern void put_filp(struct file *); extern int get_unused_fd(void); extern int get_unused_fd_flags(int flags); extern void put_unused_fd(unsigned int fd); -struct kmem_cache; - -extern int expand_files(struct files_struct *, int nr); -extern void free_fdtable_rcu(struct rcu_head *rcu); -extern void __init files_defer_init(void); - -static inline void free_fdtable(struct fdtable *fdt) -{ - call_rcu(&fdt->rcu, free_fdtable_rcu); -} - -static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd) -{ - struct file * file = NULL; - struct fdtable *fdt = files_fdtable(files); - - if (fd < fdt->max_fds) - file = rcu_dereference(fdt->fd[fd]); - return file; -} - -/* - * Check whether the specified fd has an open file. - */ -#define fcheck(fd) fcheck_files(current->files, fd) extern void fd_install(unsigned int fd, struct file *file); -struct task_struct; - -struct files_struct *get_files_struct(struct task_struct *); -void put_files_struct(struct files_struct *fs); -void reset_files_struct(struct files_struct *); -int unshare_files(struct files_struct **); - -extern struct kmem_cache *files_cachep; - #endif /* __LINUX_FILE_H */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index bf6b8a61f8db..b24c2875aa05 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -1,7 +1,7 @@ #ifndef _LINUX__INIT_TASK_H #define _LINUX__INIT_TASK_H -#include +#include #include #include #include diff --git a/kernel/exit.c b/kernel/exit.c index d3ad54677f9c..1510f78a0ffa 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include diff --git a/kernel/fork.c b/kernel/fork.c index 2bb675af4de3..933e60ebccae 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/kernel/kmod.c b/kernel/kmod.c index e2764047ec03..8df97d3dfda8 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 1b50a6ebc55f..1c864c0efe2b 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3