Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull namespace updates from Eric Biederman:
 "Life has been busy and I have not gotten half as much done this round
  as I would have liked. I delayed it so that a minor conflict
  resolution with the mips tree could spend a little time in linux-next
  before I sent this pull request.

  This includes two long delayed user namespace changes from Kirill
  Tkhai. It also includes a very useful change from Serge Hallyn that
  allows the security capability attribute to be used inside of user
  namespaces. The practical effect of this is people can now untar
  tarballs and install rpms in user namespaces. It had been suggested to
  generalize this and encode some of the namespace information
  information in the xattr name. Upon close inspection that makes the
  things that should be hard easy and the things that should be easy
  more expensive.

  Then there is my bugfix/cleanup for signal injection that removes the
  magic encoding of the siginfo union member from the kernel internal
  si_code. The mips folks reported the case where I had used FPE_FIXME
  me is impossible so I have remove FPE_FIXME from mips, while at the
  same time including a return statement in that case to keep gcc from
  complaining about unitialized variables.

  I almost finished the work to get make copy_siginfo_to_user a trivial
  copy to user. The code is available at:

     git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace.git neuter-copy_siginfo_to_user-v3

  But I did not have time/energy to get the code posted and reviewed
  before the merge window opened.

  I was able to see that the security excuse for just copying fields
  that we know are initialized doesn't work in practice there are buggy
  initializations that don't initialize the proper fields in siginfo. So
  we still sometimes copy unitialized data to userspace"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  Introduce v3 namespaced file capabilities
  mips/signal: In force_fcr31_sig return in the impossible case
  signal: Remove kernel interal si_code magic
  fcntl: Don't use ambiguous SIG_POLL si_codes
  prctl: Allow local CAP_SYS_ADMIN changing exe_file
  security: Use user_namespace::level to avoid redundant iterations in cap_capable()
  userns,pidns: Verify the userns for new pid namespaces
  signal/testing: Don't look for __SI_FAULT in userspace
  signal/mips: Document a conflict with SI_USER with SIGFPE
  signal/sparc: Document a conflict with SI_USER with SIGFPE
  signal/ia64: Document a conflict with SI_USER with SIGFPE
  signal/alpha: Document a conflict with SI_USER for SIGTRAP

6 files changed, 99 insertions, 73 deletions

diff --git a/include/linux/capability.h b/include/linux/capability.h
index 6ffb67e10c06..b52e278e4744 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -248,4 +248,6 @@ extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
 
+extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size);
+
 #endif /* !_LINUX_CAPABILITY_H */
diff --git a/include/linux/security.h b/include/linux/security.h
index 974bb9b0996c..707b524874d8 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -90,6 +90,8 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name,
 extern int cap_inode_removexattr(struct dentry *dentry, const char *name);
 extern int cap_inode_need_killpriv(struct dentry *dentry);
 extern int cap_inode_killpriv(struct dentry *dentry);
+extern int cap_inode_getsecurity(struct inode *inode, const char *name,
+				 void **buffer, bool alloc);
 extern int cap_mmap_addr(unsigned long addr);
 extern int cap_mmap_file(struct file *file, unsigned long reqprot,
 			 unsigned long prot, unsigned long flags);
diff --git a/include/linux/signal.h b/include/linux/signal.h
index e2678b5dbb21..38564e3e54c7 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -21,6 +21,20 @@ static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
 
 int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from);
 
+enum siginfo_layout {
+	SIL_KILL,
+	SIL_TIMER,
+	SIL_POLL,
+	SIL_FAULT,
+	SIL_CHLD,
+	SIL_RT,
+#ifdef __ARCH_SIGSYS
+	SIL_SYS,
+#endif
+};
+
+enum siginfo_layout siginfo_layout(int sig, int si_code);
+
 /*
  * Define some primitives to manipulate sigset_t.
  */
@@ -380,10 +394,18 @@ int unhandled_signal(struct task_struct *tsk, int sig);
         rt_sigmask(SIGCONT)   |  rt_sigmask(SIGCHLD)   | \
 	rt_sigmask(SIGWINCH)  |  rt_sigmask(SIGURG)    )
 
+#define SIG_SPECIFIC_SICODES_MASK (\
+	rt_sigmask(SIGILL)    |  rt_sigmask(SIGFPE)    | \
+	rt_sigmask(SIGSEGV)   |  rt_sigmask(SIGBUS)    | \
+	rt_sigmask(SIGTRAP)   |  rt_sigmask(SIGCHLD)   | \
+	rt_sigmask(SIGPOLL)   |  rt_sigmask(SIGSYS)    | \
+	SIGEMT_MASK                                    )
+
 #define sig_kernel_only(sig)		siginmask(sig, SIG_KERNEL_ONLY_MASK)
 #define sig_kernel_coredump(sig)	siginmask(sig, SIG_KERNEL_COREDUMP_MASK)
 #define sig_kernel_ignore(sig)		siginmask(sig, SIG_KERNEL_IGNORE_MASK)
 #define sig_kernel_stop(sig)		siginmask(sig, SIG_KERNEL_STOP_MASK)
+#define sig_specific_sicodes(sig)	siginmask(sig, SIG_SPECIFIC_SICODES_MASK)
 
 #define sig_fatal(t, signr) \
 	(!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index b3575ce29148..c18e01252346 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -112,8 +112,9 @@ extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t,
 extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
 extern int proc_setgroups_show(struct seq_file *m, void *v);
 extern bool userns_may_setgroups(const struct user_namespace *ns);
+extern bool in_userns(const struct user_namespace *ancestor,
+		       const struct user_namespace *child);
 extern bool current_in_userns(const struct user_namespace *target_ns);
-
 struct ns_common *ns_get_owner(struct ns_common *ns);
 #else
 
@@ -144,6 +145,12 @@ static inline bool userns_may_setgroups(const struct user_namespace *ns)
 	return true;
 }
 
+static inline bool in_userns(const struct user_namespace *ancestor,
+			     const struct user_namespace *child)
+{
+	return true;
+}
+
 static inline bool current_in_userns(const struct user_namespace *target_ns)
 {
 	return true;
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 9c4eca6b374a..e5aa6794cea4 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -151,29 +151,6 @@ typedef struct siginfo {
 #define si_arch		_sifields._sigsys._arch
 #endif
 
-#ifdef __KERNEL__
-#define __SI_MASK	0xffff0000u
-#define __SI_KILL	(0 << 16)
-#define __SI_TIMER	(1 << 16)
-#define __SI_POLL	(2 << 16)
-#define __SI_FAULT	(3 << 16)
-#define __SI_CHLD	(4 << 16)
-#define __SI_RT		(5 << 16)
-#define __SI_MESGQ	(6 << 16)
-#define __SI_SYS	(7 << 16)
-#define __SI_CODE(T,N)	((T) | ((N) & 0xffff))
-#else /* __KERNEL__ */
-#define __SI_KILL	0
-#define __SI_TIMER	0
-#define __SI_POLL	0
-#define __SI_FAULT	0
-#define __SI_CHLD	0
-#define __SI_RT		0
-#define __SI_MESGQ	0
-#define __SI_SYS	0
-#define __SI_CODE(T,N)	(N)
-#endif /* __KERNEL__ */
-
 /*
  * si_code values
  * Digital reserves positive values for kernel-generated signals.
@@ -181,8 +158,8 @@ typedef struct siginfo {
 #define SI_USER		0		/* sent by kill, sigsend, raise */
 #define SI_KERNEL	0x80		/* sent by the kernel from somewhere */
 #define SI_QUEUE	-1		/* sent by sigqueue */
-#define SI_TIMER __SI_CODE(__SI_TIMER,-2) /* sent by timer expiration */
-#define SI_MESGQ __SI_CODE(__SI_MESGQ,-3) /* sent by real time mesq state change */
+#define SI_TIMER	-2		/* sent by timer expiration */
+#define SI_MESGQ	-3		/* sent by real time mesq state change */
 #define SI_ASYNCIO	-4		/* sent by AIO completion */
 #define SI_SIGIO	-5		/* sent by queued SIGIO */
 #define SI_TKILL	-6		/* sent by tkill system call */
@@ -194,86 +171,86 @@ typedef struct siginfo {
 /*
  * SIGILL si_codes
  */
-#define ILL_ILLOPC	(__SI_FAULT|1)	/* illegal opcode */
-#define ILL_ILLOPN	(__SI_FAULT|2)	/* illegal operand */
-#define ILL_ILLADR	(__SI_FAULT|3)	/* illegal addressing mode */
-#define ILL_ILLTRP	(__SI_FAULT|4)	/* illegal trap */
-#define ILL_PRVOPC	(__SI_FAULT|5)	/* privileged opcode */
-#define ILL_PRVREG	(__SI_FAULT|6)	/* privileged register */
-#define ILL_COPROC	(__SI_FAULT|7)	/* coprocessor error */
-#define ILL_BADSTK	(__SI_FAULT|8)	/* internal stack error */
+#define ILL_ILLOPC	1	/* illegal opcode */
+#define ILL_ILLOPN	2	/* illegal operand */
+#define ILL_ILLADR	3	/* illegal addressing mode */
+#define ILL_ILLTRP	4	/* illegal trap */
+#define ILL_PRVOPC	5	/* privileged opcode */
+#define ILL_PRVREG	6	/* privileged register */
+#define ILL_COPROC	7	/* coprocessor error */
+#define ILL_BADSTK	8	/* internal stack error */
 #define NSIGILL		8
 
 /*
  * SIGFPE si_codes
  */
-#define FPE_INTDIV	(__SI_FAULT|1)	/* integer divide by zero */
-#define FPE_INTOVF	(__SI_FAULT|2)	/* integer overflow */
-#define FPE_FLTDIV	(__SI_FAULT|3)	/* floating point divide by zero */
-#define FPE_FLTOVF	(__SI_FAULT|4)	/* floating point overflow */
-#define FPE_FLTUND	(__SI_FAULT|5)	/* floating point underflow */
-#define FPE_FLTRES	(__SI_FAULT|6)	/* floating point inexact result */
-#define FPE_FLTINV	(__SI_FAULT|7)	/* floating point invalid operation */
-#define FPE_FLTSUB	(__SI_FAULT|8)	/* subscript out of range */
+#define FPE_INTDIV	1	/* integer divide by zero */
+#define FPE_INTOVF	2	/* integer overflow */
+#define FPE_FLTDIV	3	/* floating point divide by zero */
+#define FPE_FLTOVF	4	/* floating point overflow */
+#define FPE_FLTUND	5	/* floating point underflow */
+#define FPE_FLTRES	6	/* floating point inexact result */
+#define FPE_FLTINV	7	/* floating point invalid operation */
+#define FPE_FLTSUB	8	/* subscript out of range */
 #define NSIGFPE		8
 
 /*
  * SIGSEGV si_codes
  */
-#define SEGV_MAPERR	(__SI_FAULT|1)	/* address not mapped to object */
-#define SEGV_ACCERR	(__SI_FAULT|2)	/* invalid permissions for mapped object */
-#define SEGV_BNDERR	(__SI_FAULT|3)  /* failed address bound checks */
-#define SEGV_PKUERR	(__SI_FAULT|4)  /* failed protection key checks */
+#define SEGV_MAPERR	1	/* address not mapped to object */
+#define SEGV_ACCERR	2	/* invalid permissions for mapped object */
+#define SEGV_BNDERR	3	/* failed address bound checks */
+#define SEGV_PKUERR	4	/* failed protection key checks */
 #define NSIGSEGV	4
 
 /*
  * SIGBUS si_codes
  */
-#define BUS_ADRALN	(__SI_FAULT|1)	/* invalid address alignment */
-#define BUS_ADRERR	(__SI_FAULT|2)	/* non-existent physical address */
-#define BUS_OBJERR	(__SI_FAULT|3)	/* object specific hardware error */
+#define BUS_ADRALN	1	/* invalid address alignment */
+#define BUS_ADRERR	2	/* non-existent physical address */
+#define BUS_OBJERR	3	/* object specific hardware error */
 /* hardware memory error consumed on a machine check: action required */
-#define BUS_MCEERR_AR	(__SI_FAULT|4)
+#define BUS_MCEERR_AR	4
 /* hardware memory error detected in process but not consumed: action optional*/
-#define BUS_MCEERR_AO	(__SI_FAULT|5)
+#define BUS_MCEERR_AO	5
 #define NSIGBUS		5
 
 /*
  * SIGTRAP si_codes
  */
-#define TRAP_BRKPT	(__SI_FAULT|1)	/* process breakpoint */
-#define TRAP_TRACE	(__SI_FAULT|2)	/* process trace trap */
-#define TRAP_BRANCH     (__SI_FAULT|3)  /* process taken branch trap */
-#define TRAP_HWBKPT     (__SI_FAULT|4)  /* hardware breakpoint/watchpoint */
+#define TRAP_BRKPT	1	/* process breakpoint */
+#define TRAP_TRACE	2	/* process trace trap */
+#define TRAP_BRANCH     3	/* process taken branch trap */
+#define TRAP_HWBKPT     4	/* hardware breakpoint/watchpoint */
 #define NSIGTRAP	4
 
 /*
  * SIGCHLD si_codes
  */
-#define CLD_EXITED	(__SI_CHLD|1)	/* child has exited */
-#define CLD_KILLED	(__SI_CHLD|2)	/* child was killed */
-#define CLD_DUMPED	(__SI_CHLD|3)	/* child terminated abnormally */
-#define CLD_TRAPPED	(__SI_CHLD|4)	/* traced child has trapped */
-#define CLD_STOPPED	(__SI_CHLD|5)	/* child has stopped */
-#define CLD_CONTINUED	(__SI_CHLD|6)	/* stopped child has continued */
+#define CLD_EXITED	1	/* child has exited */
+#define CLD_KILLED	2	/* child was killed */
+#define CLD_DUMPED	3	/* child terminated abnormally */
+#define CLD_TRAPPED	4	/* traced child has trapped */
+#define CLD_STOPPED	5	/* child has stopped */
+#define CLD_CONTINUED	6	/* stopped child has continued */
 #define NSIGCHLD	6
 
 /*
- * SIGPOLL si_codes
+ * SIGPOLL (or any other signal without signal specific si_codes) si_codes
  */
-#define POLL_IN		(__SI_POLL|1)	/* data input available */
-#define POLL_OUT	(__SI_POLL|2)	/* output buffers available */
-#define POLL_MSG	(__SI_POLL|3)	/* input message available */
-#define POLL_ERR	(__SI_POLL|4)	/* i/o error */
-#define POLL_PRI	(__SI_POLL|5)	/* high priority input available */
-#define POLL_HUP	(__SI_POLL|6)	/* device disconnected */
+#define POLL_IN		1	/* data input available */
+#define POLL_OUT	2	/* output buffers available */
+#define POLL_MSG	3	/* input message available */
+#define POLL_ERR	4	/* i/o error */
+#define POLL_PRI	5	/* high priority input available */
+#define POLL_HUP	6	/* device disconnected */
 #define NSIGPOLL	6
 
 /*
  * SIGSYS si_codes
  */
-#define SYS_SECCOMP		(__SI_SYS|1)	/* seccomp triggered */
-#define NSIGSYS	1
+#define SYS_SECCOMP	1	/* seccomp triggered */
+#define NSIGSYS		1
 
 /*
  * sigevent definitions
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 6fe14d001f68..230e05d35191 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -60,9 +60,13 @@ typedef struct __user_cap_data_struct {
 #define VFS_CAP_U32_2           2
 #define XATTR_CAPS_SZ_2         (sizeof(__le32)*(1 + 2*VFS_CAP_U32_2))
 
-#define XATTR_CAPS_SZ           XATTR_CAPS_SZ_2
-#define VFS_CAP_U32             VFS_CAP_U32_2
-#define VFS_CAP_REVISION	VFS_CAP_REVISION_2
+#define VFS_CAP_REVISION_3	0x03000000
+#define VFS_CAP_U32_3           2
+#define XATTR_CAPS_SZ_3         (sizeof(__le32)*(2 + 2*VFS_CAP_U32_3))
+
+#define XATTR_CAPS_SZ           XATTR_CAPS_SZ_3
+#define VFS_CAP_U32             VFS_CAP_U32_3
+#define VFS_CAP_REVISION	VFS_CAP_REVISION_3
 
 struct vfs_cap_data {
 	__le32 magic_etc;            /* Little endian */
@@ -72,6 +76,18 @@ struct vfs_cap_data {
 	} data[VFS_CAP_U32];
 };
 
+/*
+ * same as vfs_cap_data but with a rootid at the end
+ */
+struct vfs_ns_cap_data {
+	__le32 magic_etc;
+	struct {
+		__le32 permitted;    /* Little endian */
+		__le32 inheritable;  /* Little endian */
+	} data[VFS_CAP_U32];
+	__le32 rootid;
+};
+
 #ifndef __KERNEL__
 
 /*