From a2b426267c56773201f968fdb5eda6ab9ae94e34 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 29 Apr 2017 14:12:15 -0500
Subject: userns,pidns: Verify the userns for new pid namespaces

It is pointless and confusing to allow a pid namespace hierarchy and
the user namespace hierarchy to get out of sync.  The owner of a child
pid namespace should be the owner of the parent pid namespace or
a descendant of the owner of the parent pid namespace.

Otherwise it is possible to construct scenarios where a process has a
capability over a parent pid namespace but does not have the
capability over a child pid namespace.  Which confusingly makes
permission checks non-transitive.

It requires use of setns into a pid namespace (but not into a user
namespace) to create such a scenario.

Add the function in_userns to help in making this determination.

v2: Optimized in_userns by using level as suggested
    by: Kirill Tkhai <ktkhai@virtuozzo.com>

Ref: 49f4d8b93ccf ("pidns: Capture the user namespace and filter ns_last_pid")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/user_namespace.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 32354b4b4b2b..4005877bb8b6 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;
-- 
cgit v1.2.3-58-ga151


From d08477aa975e97f1dc64c0ae59cebf98520456ce Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 29 Jun 2017 09:28:50 -0500
Subject: fcntl: Don't use ambiguous SIG_POLL si_codes

We have a weird and problematic intersection of features that when
they all come together result in ambiguous siginfo values, that
we can not support properly.

- Supporting fcntl(F_SETSIG,...) with arbitrary valid signals.

- Using positive values for POLL_IN, POLL_OUT, POLL_MSG, ..., etc
  that imply they are signal specific si_codes and using the
  aforementioned arbitrary signal to deliver them.

- Supporting injection of arbitrary siginfo values for debugging and
  checkpoint/restore.

The result is that just looking at siginfo si_codes of 1 to 6 are
ambigious.  It could either be a signal specific si_code or it could
be a generic si_code.

For most of the kernel this is a non-issue but for sending signals
with siginfo it is impossible to play back the kernel signals and
get the same result.

Strictly speaking when the si_code was changed from SI_SIGIO to
POLL_IN and friends between 2.2 and 2.4 this functionality was not
ambiguous, as only real time signals were supported.  Before 2.4 was
released the kernel began supporting siginfo with non realtime signals
so they could give details of why the signal was sent.

The result is that if F_SETSIG is set to one of the signals with signal
specific si_codes then user space can not know why the signal was sent.

I grepped through a bunch of userspace programs using debian code
search to get a feel for how often people choose a signal that results
in an ambiguous si_code.  I only found one program doing so and it was
using SIGCHLD to test the F_SETSIG functionality, and did not appear
to be a real world usage.

Therefore the ambiguity does not appears to be a real world problem in
practice.  Remove the ambiguity while introducing the smallest chance
of breakage by changing the si_code to SI_SIGIO when signals with
signal specific si_codes are targeted.

Fixes: v2.3.40 -- Added support for queueing non-rt signals
Fixes: v2.3.21 -- Changed the si_code from SI_SIGIO
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/fcntl.c                         | 13 ++++++++++++-
 include/linux/signal.h             |  8 ++++++++
 include/uapi/asm-generic/siginfo.h |  4 ++--
 3 files changed, 22 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/fcntl.c b/fs/fcntl.c
index 3b01b646e528..0491da3b28c3 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -741,10 +741,21 @@ static void send_sigio_to_task(struct task_struct *p,
 			si.si_signo = signum;
 			si.si_errno = 0;
 		        si.si_code  = reason;
+			/*
+			 * Posix definies POLL_IN and friends to be signal
+			 * specific si_codes for SIG_POLL.  Linux extended
+			 * these si_codes to other signals in a way that is
+			 * ambiguous if other signals also have signal
+			 * specific si_codes.  In that case use SI_SIGIO instead
+			 * to remove the ambiguity.
+			 */
+			if (sig_specific_sicodes(signum))
+				si.si_code = SI_SIGIO;
+
 			/* Make sure we are called with one of the POLL_*
 			   reasons, otherwise we could leak kernel stack into
 			   userspace.  */
-			BUG_ON((reason & __SI_MASK) != __SI_POLL);
+			BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL));
 			if (reason - POLL_IN >= NSIGPOLL)
 				si.si_band  = ~0L;
 			else
diff --git a/include/linux/signal.h b/include/linux/signal.h
index e2678b5dbb21..c97cc20369c0 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -380,10 +380,18 @@ 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/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 9c4eca6b374a..9e956ea94d57 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -184,7 +184,7 @@ typedef struct siginfo {
 #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_ASYNCIO	-4		/* sent by AIO completion */
-#define SI_SIGIO	-5		/* sent by queued SIGIO */
+#define SI_SIGIO __SI_CODE(__SI_POLL,-5) /* sent by queued SIGIO */
 #define SI_TKILL	-6		/* sent by tkill system call */
 #define SI_DETHREAD	-7		/* sent by execve() killing subsidiary threads */
 
@@ -259,7 +259,7 @@ typedef struct siginfo {
 #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 */
-- 
cgit v1.2.3-58-ga151


From cc731525f26af85a1c3537da41e0abd1d35e0bdb Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sun, 16 Jul 2017 22:36:59 -0500
Subject: signal: Remove kernel interal si_code magic

struct siginfo is a union and the kernel since 2.4 has been hiding a union
tag in the high 16bits of si_code using the values:
__SI_KILL
__SI_TIMER
__SI_POLL
__SI_FAULT
__SI_CHLD
__SI_RT
__SI_MESGQ
__SI_SYS

While this looks plausible on the surface, in practice this situation has
not worked well.

- Injected positive signals are not copied to user space properly
  unless they have these magic high bits set.

- Injected positive signals are not reported properly by signalfd
  unless they have these magic high bits set.

- These kernel internal values leaked to userspace via ptrace_peek_siginfo

- It was possible to inject these kernel internal values and cause the
  the kernel to misbehave.

- Kernel developers got confused and expected these kernel internal values
  in userspace in kernel self tests.

- Kernel developers got confused and set si_code to __SI_FAULT which
  is SI_USER in userspace which causes userspace to think an ordinary user
  sent the signal and that it was not kernel generated.

- The values make it impossible to reorganize the code to transform
  siginfo_copy_to_user into a plain copy_to_user.  As si_code must
  be massaged before being passed to userspace.

So remove these kernel internal si codes and make the kernel code simpler
and more maintainable.

To replace these kernel internal magic si_codes introduce the helper
function siginfo_layout, that takes a signal number and an si_code and
computes which union member of siginfo is being used.  Have
siginfo_layout return an enumeration so that gcc will have enough
information to warn if a switch statement does not handle all of union
members.

A couple of architectures have a messed up ABI that defines signal
specific duplications of SI_USER which causes more special cases in
siginfo_layout than I would like.  The good news is only problem
architectures pay the cost.

Update all of the code that used the previous magic __SI_ values to
use the new SIL_ values and to call siginfo_layout to get those
values.  Escept where not all of the cases are handled remove the
defaults in the switch statements so that if a new case is missed in
the future the lack will show up at compile time.

Modify the code that copies siginfo si_code to userspace to just copy
the value and not cast si_code to a short first.  The high bits are no
longer used to hold a magic union member.

Fixup the siginfo header files to stop including the __SI_ values in
their constants and for the headers that were missing it to properly
update the number of si_codes for each signal type.

The fixes to copy_siginfo_from_user32 implementations has the
interesting property that several of them perviously should never have
worked as the __SI_ values they depended up where kernel internal.
With that dependency gone those implementations should work much
better.

The idea of not passing the __SI_ values out to userspace and then
not reinserting them has been tested with criu and criu worked without
changes.

Ref: 2.4.0-test1
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/alpha/include/uapi/asm/siginfo.h    |   4 +-
 arch/arm64/kernel/signal32.c             |  23 +++----
 arch/blackfin/include/uapi/asm/siginfo.h |  30 +++++---
 arch/frv/include/uapi/asm/siginfo.h      |   2 +-
 arch/ia64/include/uapi/asm/siginfo.h     |  20 +++---
 arch/ia64/kernel/signal.c                |  17 +++--
 arch/mips/include/uapi/asm/siginfo.h     |   6 +-
 arch/mips/kernel/signal32.c              |  19 +++--
 arch/parisc/kernel/signal32.c            |  31 ++++-----
 arch/powerpc/kernel/signal_32.c          |  20 +++---
 arch/s390/kernel/compat_signal.c         |  32 ++++-----
 arch/sparc/include/uapi/asm/siginfo.h    |   4 +-
 arch/sparc/kernel/signal32.c             |  16 ++---
 arch/tile/include/uapi/asm/siginfo.h     |   4 +-
 arch/tile/kernel/compat_signal.c         |  18 +++--
 arch/tile/kernel/traps.c                 |   2 +-
 arch/x86/kernel/signal_compat.c          |  21 +++---
 fs/signalfd.c                            |  22 +++---
 include/linux/signal.h                   |  14 ++++
 include/uapi/asm-generic/siginfo.h       | 115 +++++++++++++------------------
 kernel/exit.c                            |   4 +-
 kernel/ptrace.c                          |   6 +-
 kernel/signal.c                          |  72 ++++++++++++++-----
 23 files changed, 257 insertions(+), 245 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/uapi/asm/siginfo.h b/arch/alpha/include/uapi/asm/siginfo.h
index 972f547d9e41..70494d1d8f29 100644
--- a/arch/alpha/include/uapi/asm/siginfo.h
+++ b/arch/alpha/include/uapi/asm/siginfo.h
@@ -10,14 +10,14 @@
  * SIGFPE si_codes
  */
 #ifdef __KERNEL__
-#define FPE_FIXME	(__SI_FAULT|0)	/* Broken dup of SI_USER */
+#define FPE_FIXME	0	/* Broken dup of SI_USER */
 #endif /* __KERNEL__ */
 
 /*
  * SIGTRAP si_codes
  */
 #ifdef __KERNEL__
-#define TRAP_FIXME	(__SI_FAULT|0)	/* Broken dup of SI_USER */
+#define TRAP_FIXME	0	/* Broken dup of SI_USER */
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index c747a0fc5d7d..9b95a935c21d 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -142,25 +142,25 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 	 */
 	err = __put_user(from->si_signo, &to->si_signo);
 	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
+	err |= __put_user(from->si_code, &to->si_code);
 	if (from->si_code < 0)
 		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad,
 				      SI_PAD_SIZE);
-	else switch (from->si_code & __SI_MASK) {
-	case __SI_KILL:
+	else switch (siginfo_layout(from->si_signo, from->si_code)) {
+	case SIL_KILL:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		break;
-	case __SI_TIMER:
+	case SIL_TIMER:
 		 err |= __put_user(from->si_tid, &to->si_tid);
 		 err |= __put_user(from->si_overrun, &to->si_overrun);
 		 err |= __put_user(from->si_int, &to->si_int);
 		break;
-	case __SI_POLL:
+	case SIL_POLL:
 		err |= __put_user(from->si_band, &to->si_band);
 		err |= __put_user(from->si_fd, &to->si_fd);
 		break;
-	case __SI_FAULT:
+	case SIL_FAULT:
 		err |= __put_user((compat_uptr_t)(unsigned long)from->si_addr,
 				  &to->si_addr);
 #ifdef BUS_MCEERR_AO
@@ -173,29 +173,24 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
-	case __SI_CHLD:
+	case SIL_CHLD:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		err |= __put_user(from->si_status, &to->si_status);
 		err |= __put_user(from->si_utime, &to->si_utime);
 		err |= __put_user(from->si_stime, &to->si_stime);
 		break;
-	case __SI_RT: /* This is not generated by the kernel as of now. */
-	case __SI_MESGQ: /* But this is */
+	case SIL_RT:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		err |= __put_user(from->si_int, &to->si_int);
 		break;
-	case __SI_SYS:
+	case SIL_SYS:
 		err |= __put_user((compat_uptr_t)(unsigned long)
 				from->si_call_addr, &to->si_call_addr);
 		err |= __put_user(from->si_syscall, &to->si_syscall);
 		err |= __put_user(from->si_arch, &to->si_arch);
 		break;
-	default: /* this is just in case for now ... */
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		break;
 	}
 	return err;
 }
diff --git a/arch/blackfin/include/uapi/asm/siginfo.h b/arch/blackfin/include/uapi/asm/siginfo.h
index c72f4e6e386f..79dfe3979123 100644
--- a/arch/blackfin/include/uapi/asm/siginfo.h
+++ b/arch/blackfin/include/uapi/asm/siginfo.h
@@ -14,28 +14,36 @@
 
 #define si_uid16	_sifields._kill._uid
 
-#define ILL_ILLPARAOP	(__SI_FAULT|2)	/* illegal opcode combine ********** */
-#define ILL_ILLEXCPT	(__SI_FAULT|4)	/* unrecoverable exception ********** */
-#define ILL_CPLB_VI	(__SI_FAULT|9)	/* D/I CPLB protect violation ******** */
-#define ILL_CPLB_MISS	(__SI_FAULT|10)	/* D/I CPLB miss ******** */
-#define ILL_CPLB_MULHIT	(__SI_FAULT|11)	/* D/I CPLB multiple hit ******** */
+#define ILL_ILLPARAOP	2	/* illegal opcode combine ********** */
+#define ILL_ILLEXCPT	4	/* unrecoverable exception ********** */
+#define ILL_CPLB_VI	9	/* D/I CPLB protect violation ******** */
+#define ILL_CPLB_MISS	10	/* D/I CPLB miss ******** */
+#define ILL_CPLB_MULHIT	11	/* D/I CPLB multiple hit ******** */
+#undef NSIGILL
+#define NSIGILL         11
 
 /*
  * SIGBUS si_codes
  */
-#define BUS_OPFETCH	(__SI_FAULT|4)	/* error from instruction fetch ******** */
+#define BUS_OPFETCH	4	/* error from instruction fetch ******** */
+#undef NSIGBUS
+#define NSIGBUS		4
 
 /*
  * SIGTRAP si_codes
  */
-#define TRAP_STEP	(__SI_FAULT|1)	/* single-step breakpoint************* */
-#define TRAP_TRACEFLOW	(__SI_FAULT|2)	/* trace buffer overflow ************* */
-#define TRAP_WATCHPT	(__SI_FAULT|3)	/* watchpoint match      ************* */
-#define TRAP_ILLTRAP	(__SI_FAULT|4)	/* illegal trap          ************* */
+#define TRAP_STEP	1	/* single-step breakpoint************* */
+#define TRAP_TRACEFLOW	2	/* trace buffer overflow ************* */
+#define TRAP_WATCHPT	3	/* watchpoint match      ************* */
+#define TRAP_ILLTRAP	4	/* illegal trap          ************* */
+#undef NSIGTRAP
+#define NSIGTRAP	4
 
 /*
  * SIGSEGV si_codes
  */
-#define SEGV_STACKFLOW	(__SI_FAULT|3)	/* stack overflow */
+#define SEGV_STACKFLOW	3	/* stack overflow */
+#undef NSIGSEGV
+#define NSIGSEGV	3
 
 #endif /* _UAPI_BFIN_SIGINFO_H */
diff --git a/arch/frv/include/uapi/asm/siginfo.h b/arch/frv/include/uapi/asm/siginfo.h
index d3fd1ca45653..f55d9e0e9068 100644
--- a/arch/frv/include/uapi/asm/siginfo.h
+++ b/arch/frv/include/uapi/asm/siginfo.h
@@ -4,7 +4,7 @@
 #include <linux/types.h>
 #include <asm-generic/siginfo.h>
 
-#define FPE_MDAOVF	(__SI_FAULT|9)	/* media overflow */
+#define FPE_MDAOVF	9	/* media overflow */
 #undef NSIGFPE
 #define NSIGFPE		9
 
diff --git a/arch/ia64/include/uapi/asm/siginfo.h b/arch/ia64/include/uapi/asm/siginfo.h
index 3282f8b992fc..33389fc36f23 100644
--- a/arch/ia64/include/uapi/asm/siginfo.h
+++ b/arch/ia64/include/uapi/asm/siginfo.h
@@ -98,9 +98,9 @@ typedef struct siginfo {
 /*
  * SIGILL si_codes
  */
-#define ILL_BADIADDR	(__SI_FAULT|9)	/* unimplemented instruction address */
-#define __ILL_BREAK	(__SI_FAULT|10)	/* illegal break */
-#define __ILL_BNDMOD	(__SI_FAULT|11)	/* bundle-update (modification) in progress */
+#define ILL_BADIADDR	9	/* unimplemented instruction address */
+#define __ILL_BREAK	10	/* illegal break */
+#define __ILL_BNDMOD	11	/* bundle-update (modification) in progress */
 #undef NSIGILL
 #define NSIGILL		11
 
@@ -108,20 +108,20 @@ typedef struct siginfo {
  * SIGFPE si_codes
  */
 #ifdef __KERNEL__
-#define FPE_FIXME	(__SI_FAULT|0)	/* Broken dup of SI_USER */
+#define FPE_FIXME	0	/* Broken dup of SI_USER */
 #endif /* __KERNEL__ */
-#define __FPE_DECOVF	(__SI_FAULT|9)	/* decimal overflow */
-#define __FPE_DECDIV	(__SI_FAULT|10)	/* decimal division by zero */
-#define __FPE_DECERR	(__SI_FAULT|11)	/* packed decimal error */
-#define __FPE_INVASC	(__SI_FAULT|12)	/* invalid ASCII digit */
-#define __FPE_INVDEC	(__SI_FAULT|13)	/* invalid decimal digit */
+#define __FPE_DECOVF	9	/* decimal overflow */
+#define __FPE_DECDIV	10	/* decimal division by zero */
+#define __FPE_DECERR	11	/* packed decimal error */
+#define __FPE_INVASC	12	/* invalid ASCII digit */
+#define __FPE_INVDEC	13	/* invalid decimal digit */
 #undef NSIGFPE
 #define NSIGFPE		13
 
 /*
  * SIGSEGV si_codes
  */
-#define __SEGV_PSTKOVF	(__SI_FAULT|4)	/* paragraph stack overflow */
+#define __SEGV_PSTKOVF	4	/* paragraph stack overflow */
 #undef NSIGSEGV
 #define NSIGSEGV	4
 
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 5db52c6813c4..6146d53b6ad7 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -124,31 +124,30 @@ copy_siginfo_to_user (siginfo_t __user *to, const siginfo_t *from)
 		 */
 		err = __put_user(from->si_signo, &to->si_signo);
 		err |= __put_user(from->si_errno, &to->si_errno);
-		err |= __put_user((short)from->si_code, &to->si_code);
-		switch (from->si_code >> 16) {
-		      case __SI_FAULT >> 16:
+		err |= __put_user(from->si_code, &to->si_code);
+		switch (siginfo_layout(from->si_signo, from->si_code)) {
+		      case SIL_FAULT:
 			err |= __put_user(from->si_flags, &to->si_flags);
 			err |= __put_user(from->si_isr, &to->si_isr);
-		      case __SI_POLL >> 16:
+		      case SIL_POLL:
 			err |= __put_user(from->si_addr, &to->si_addr);
 			err |= __put_user(from->si_imm, &to->si_imm);
 			break;
-		      case __SI_TIMER >> 16:
+		      case SIL_TIMER:
 			err |= __put_user(from->si_tid, &to->si_tid);
 			err |= __put_user(from->si_overrun, &to->si_overrun);
 			err |= __put_user(from->si_ptr, &to->si_ptr);
 			break;
-		      case __SI_RT >> 16:	/* Not generated by the kernel as of now.  */
-		      case __SI_MESGQ >> 16:
+		      case SIL_RT:
 			err |= __put_user(from->si_uid, &to->si_uid);
 			err |= __put_user(from->si_pid, &to->si_pid);
 			err |= __put_user(from->si_ptr, &to->si_ptr);
 			break;
-		      case __SI_CHLD >> 16:
+		      case SIL_CHLD:
 			err |= __put_user(from->si_utime, &to->si_utime);
 			err |= __put_user(from->si_stime, &to->si_stime);
 			err |= __put_user(from->si_status, &to->si_status);
-		      default:
+		      case SIL_KILL:
 			err |= __put_user(from->si_uid, &to->si_uid);
 			err |= __put_user(from->si_pid, &to->si_pid);
 			break;
diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h
index 9becfd102132..22a86d84a504 100644
--- a/arch/mips/include/uapi/asm/siginfo.h
+++ b/arch/mips/include/uapi/asm/siginfo.h
@@ -120,14 +120,14 @@ typedef struct siginfo {
 #undef SI_TIMER
 #undef SI_MESGQ
 #define SI_ASYNCIO	-2	/* sent by AIO completion */
-#define SI_TIMER __SI_CODE(__SI_TIMER, -3) /* sent by timer expiration */
-#define SI_MESGQ __SI_CODE(__SI_MESGQ, -4) /* sent by real time mesq state change */
+#define SI_TIMER	-3	/* sent by timer expiration */
+#define SI_MESGQ	-4	/* sent by real time mesq state change */
 
 /*
  * SIGFPE si_codes
  */
 #ifdef __KERNEL__
-#define FPE_FIXME	(__SI_FAULT|0)	/* Broken dup of SI_USER */
+#define FPE_FIXME	0	/* Broken dup of SI_USER */
 #endif /* __KERNEL__ */
 
 #endif /* _UAPI_ASM_SIGINFO_H */
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 84165f2b31ff..cf5c7c05e5a3 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -93,38 +93,37 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 	   at the same time.  */
 	err = __put_user(from->si_signo, &to->si_signo);
 	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
+	err |= __put_user(from->si_code, &to->si_code);
 	if (from->si_code < 0)
 		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
 	else {
-		switch (from->si_code >> 16) {
-		case __SI_TIMER >> 16:
+		switch (siginfo_layout(from->si_signo, from->si_code)) {
+		case SIL_TIMER:
 			err |= __put_user(from->si_tid, &to->si_tid);
 			err |= __put_user(from->si_overrun, &to->si_overrun);
 			err |= __put_user(from->si_int, &to->si_int);
 			break;
-		case __SI_CHLD >> 16:
+		case SIL_CHLD:
 			err |= __put_user(from->si_utime, &to->si_utime);
 			err |= __put_user(from->si_stime, &to->si_stime);
 			err |= __put_user(from->si_status, &to->si_status);
-		default:
+		case SIL_KILL:
 			err |= __put_user(from->si_pid, &to->si_pid);
 			err |= __put_user(from->si_uid, &to->si_uid);
 			break;
-		case __SI_FAULT >> 16:
+		case SIL_FAULT:
 			err |= __put_user((unsigned long)from->si_addr, &to->si_addr);
 			break;
-		case __SI_POLL >> 16:
+		case SIL_POLL:
 			err |= __put_user(from->si_band, &to->si_band);
 			err |= __put_user(from->si_fd, &to->si_fd);
 			break;
-		case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
-		case __SI_MESGQ >> 16:
+		case SIL_RT:
 			err |= __put_user(from->si_pid, &to->si_pid);
 			err |= __put_user(from->si_uid, &to->si_uid);
 			err |= __put_user(from->si_int, &to->si_int);
 			break;
-		case __SI_SYS >> 16:
+		case SIL_SYS:
 			err |= __copy_to_user(&to->si_call_addr, &from->si_call_addr,
 					      sizeof(compat_uptr_t));
 			err |= __put_user(from->si_syscall, &to->si_syscall);
diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c
index 70aaabb8b3cb..9e0cb6a577d6 100644
--- a/arch/parisc/kernel/signal32.c
+++ b/arch/parisc/kernel/signal32.c
@@ -290,25 +290,25 @@ copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from)
 	if (to->si_code < 0)
 		err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
 	else {
-		switch (to->si_code >> 16) {
-		      case __SI_CHLD >> 16:
+		switch (siginfo_layout(to->si_signo, to->si_code)) {
+		      case SIL_CHLD:
 			err |= __get_user(to->si_utime, &from->si_utime);
 			err |= __get_user(to->si_stime, &from->si_stime);
 			err |= __get_user(to->si_status, &from->si_status);
 		      default:
+		      case SIL_KILL:
 			err |= __get_user(to->si_pid, &from->si_pid);
 			err |= __get_user(to->si_uid, &from->si_uid);
 			break;
-		      case __SI_FAULT >> 16:
+		      case SIL_FAULT:
 			err |= __get_user(addr, &from->si_addr);
 			to->si_addr = compat_ptr(addr);
 			break;
-		      case __SI_POLL >> 16:
+		      case SIL_POLL:
 			err |= __get_user(to->si_band, &from->si_band);
 			err |= __get_user(to->si_fd, &from->si_fd);
 			break;
-		      case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
-		      case __SI_MESGQ >> 16:
+		      case SIL_RT:
 			err |= __get_user(to->si_pid, &from->si_pid);
 			err |= __get_user(to->si_uid, &from->si_uid);
 			err |= __get_user(to->si_int, &from->si_int);
@@ -337,41 +337,40 @@ copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from)
 	   at the same time.  */
 	err = __put_user(from->si_signo, &to->si_signo);
 	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
+	err |= __put_user(from->si_code, &to->si_code);
 	if (from->si_code < 0)
 		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
 	else {
-		switch (from->si_code >> 16) {
-		case __SI_CHLD >> 16:
+		switch (siginfo_layout(from->si_signo, from->si_code)) {
+		case SIL_CHLD:
 			err |= __put_user(from->si_utime, &to->si_utime);
 			err |= __put_user(from->si_stime, &to->si_stime);
 			err |= __put_user(from->si_status, &to->si_status);
-		default:
+		case SIL_KILL:
 			err |= __put_user(from->si_pid, &to->si_pid);
 			err |= __put_user(from->si_uid, &to->si_uid);
 			break;
-		case __SI_FAULT >> 16:
+		case SIL_FAULT:
 			addr = ptr_to_compat(from->si_addr);
 			err |= __put_user(addr, &to->si_addr);
 			break;
-		case __SI_POLL >> 16:
+		case SIL_POLL:
 			err |= __put_user(from->si_band, &to->si_band);
 			err |= __put_user(from->si_fd, &to->si_fd);
 			break;
-		case __SI_TIMER >> 16:
+		case SIL_TIMER:
 			err |= __put_user(from->si_tid, &to->si_tid);
 			err |= __put_user(from->si_overrun, &to->si_overrun);
 			val = (compat_int_t)from->si_int;
 			err |= __put_user(val, &to->si_int);
 			break;
-		case __SI_RT >> 16:	/* Not generated by the kernel as of now.  */
-		case __SI_MESGQ >> 16:
+		case SIL_RT:
 			err |= __put_user(from->si_uid, &to->si_uid);
 			err |= __put_user(from->si_pid, &to->si_pid);
 			val = (compat_int_t)from->si_int;
 			err |= __put_user(val, &to->si_int);
 			break;
-		case __SI_SYS >> 16:
+		case SIL_SYS:
 			err |= __put_user(ptr_to_compat(from->si_call_addr), &to->si_call_addr);
 			err |= __put_user(from->si_syscall, &to->si_syscall);
 			err |= __put_user(from->si_arch, &to->si_arch);
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 97bb1385e771..92fb1c8dbbd8 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -913,42 +913,40 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
 	 */
 	err = __put_user(s->si_signo, &d->si_signo);
 	err |= __put_user(s->si_errno, &d->si_errno);
-	err |= __put_user((short)s->si_code, &d->si_code);
+	err |= __put_user(s->si_code, &d->si_code);
 	if (s->si_code < 0)
 		err |= __copy_to_user(&d->_sifields._pad, &s->_sifields._pad,
 				      SI_PAD_SIZE32);
-	else switch(s->si_code >> 16) {
-	case __SI_CHLD >> 16:
+	else switch(siginfo_layout(s->si_signo, s->si_code)) {
+	case SIL_CHLD:
 		err |= __put_user(s->si_pid, &d->si_pid);
 		err |= __put_user(s->si_uid, &d->si_uid);
 		err |= __put_user(s->si_utime, &d->si_utime);
 		err |= __put_user(s->si_stime, &d->si_stime);
 		err |= __put_user(s->si_status, &d->si_status);
 		break;
-	case __SI_FAULT >> 16:
+	case SIL_FAULT:
 		err |= __put_user((unsigned int)(unsigned long)s->si_addr,
 				  &d->si_addr);
 		break;
-	case __SI_POLL >> 16:
+	case SIL_POLL:
 		err |= __put_user(s->si_band, &d->si_band);
 		err |= __put_user(s->si_fd, &d->si_fd);
 		break;
-	case __SI_TIMER >> 16:
+	case SIL_TIMER:
 		err |= __put_user(s->si_tid, &d->si_tid);
 		err |= __put_user(s->si_overrun, &d->si_overrun);
 		err |= __put_user(s->si_int, &d->si_int);
 		break;
-	case __SI_SYS >> 16:
+	case SIL_SYS:
 		err |= __put_user(ptr_to_compat(s->si_call_addr), &d->si_call_addr);
 		err |= __put_user(s->si_syscall, &d->si_syscall);
 		err |= __put_user(s->si_arch, &d->si_arch);
 		break;
-	case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
-	case __SI_MESGQ >> 16:
+	case SIL_RT:
 		err |= __put_user(s->si_int, &d->si_int);
 		/* fallthrough */
-	case __SI_KILL >> 16:
-	default:
+	case SIL_KILL:
 		err |= __put_user(s->si_pid, &d->si_pid);
 		err |= __put_user(s->si_uid, &d->si_uid);
 		break;
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index c620049c61f2..f549c4657376 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -75,35 +75,34 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 	   at the same time.  */
 	err = __put_user(from->si_signo, &to->si_signo);
 	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
+	err |= __put_user(from->si_code, &to->si_code);
 	if (from->si_code < 0)
 		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
 	else {
-		switch (from->si_code >> 16) {
-		case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
-		case __SI_MESGQ >> 16:
+		switch (siginfo_layout(from->si_signo, from->si_code)) {
+		case SIL_RT:
 			err |= __put_user(from->si_int, &to->si_int);
 			/* fallthrough */
-		case __SI_KILL >> 16:
+		case SIL_KILL:
 			err |= __put_user(from->si_pid, &to->si_pid);
 			err |= __put_user(from->si_uid, &to->si_uid);
 			break;
-		case __SI_CHLD >> 16:
+		case SIL_CHLD:
 			err |= __put_user(from->si_pid, &to->si_pid);
 			err |= __put_user(from->si_uid, &to->si_uid);
 			err |= __put_user(from->si_utime, &to->si_utime);
 			err |= __put_user(from->si_stime, &to->si_stime);
 			err |= __put_user(from->si_status, &to->si_status);
 			break;
-		case __SI_FAULT >> 16:
+		case SIL_FAULT:
 			err |= __put_user((unsigned long) from->si_addr,
 					  &to->si_addr);
 			break;
-		case __SI_POLL >> 16:
+		case SIL_POLL:
 			err |= __put_user(from->si_band, &to->si_band);
 			err |= __put_user(from->si_fd, &to->si_fd);
 			break;
-		case __SI_TIMER >> 16:
+		case SIL_TIMER:
 			err |= __put_user(from->si_tid, &to->si_tid);
 			err |= __put_user(from->si_overrun, &to->si_overrun);
 			err |= __put_user(from->si_int, &to->si_int);
@@ -127,32 +126,31 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	if (to->si_code < 0)
 		err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
 	else {
-		switch (to->si_code >> 16) {
-		case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
-		case __SI_MESGQ >> 16:
+		switch (siginfo_layout(to->si_signo, to->si_code)) {
+		case SIL_RT:
 			err |= __get_user(to->si_int, &from->si_int);
 			/* fallthrough */
-		case __SI_KILL >> 16:
+		case SIL_KILL:
 			err |= __get_user(to->si_pid, &from->si_pid);
 			err |= __get_user(to->si_uid, &from->si_uid);
 			break;
-		case __SI_CHLD >> 16:
+		case SIL_CHLD:
 			err |= __get_user(to->si_pid, &from->si_pid);
 			err |= __get_user(to->si_uid, &from->si_uid);
 			err |= __get_user(to->si_utime, &from->si_utime);
 			err |= __get_user(to->si_stime, &from->si_stime);
 			err |= __get_user(to->si_status, &from->si_status);
 			break;
-		case __SI_FAULT >> 16:
+		case SIL_FAULT:
 			err |= __get_user(tmp, &from->si_addr);
 			to->si_addr = (void __force __user *)
 				(u64) (tmp & PSW32_ADDR_INSN);
 			break;
-		case __SI_POLL >> 16:
+		case SIL_POLL:
 			err |= __get_user(to->si_band, &from->si_band);
 			err |= __get_user(to->si_fd, &from->si_fd);
 			break;
-		case __SI_TIMER >> 16:
+		case SIL_TIMER:
 			err |= __get_user(to->si_tid, &from->si_tid);
 			err |= __get_user(to->si_overrun, &from->si_overrun);
 			err |= __get_user(to->si_int, &from->si_int);
diff --git a/arch/sparc/include/uapi/asm/siginfo.h b/arch/sparc/include/uapi/asm/siginfo.h
index da2126e0c536..157f46fe374f 100644
--- a/arch/sparc/include/uapi/asm/siginfo.h
+++ b/arch/sparc/include/uapi/asm/siginfo.h
@@ -20,13 +20,13 @@
  * SIGFPE si_codes
  */
 #ifdef __KERNEL__
-#define FPE_FIXME	(__SI_FAULT|0)	/* Broken dup of SI_USER */
+#define FPE_FIXME	0	/* Broken dup of SI_USER */
 #endif /* __KERNEL__ */
 
 /*
  * SIGEMT si_codes
  */
-#define EMT_TAGOVF	(__SI_FAULT|1)	/* tag overflow */
+#define EMT_TAGOVF	1	/* tag overflow */
 #define NSIGEMT		1
 
 #endif /* _UAPI__SPARC_SIGINFO_H */
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index b4096bb665b2..0e4c08c45a37 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -85,34 +85,34 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 	   at the same time.  */
 	err = __put_user(from->si_signo, &to->si_signo);
 	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
+	err |= __put_user(from->si_code, &to->si_code);
 	if (from->si_code < 0)
 		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
 	else {
-		switch (from->si_code >> 16) {
-		case __SI_TIMER >> 16:
+		switch (siginfo_layout(from->si_signo, from->si_code)) {
+		case SIL_TIMER:
 			err |= __put_user(from->si_tid, &to->si_tid);
 			err |= __put_user(from->si_overrun, &to->si_overrun);
 			err |= __put_user(from->si_int, &to->si_int);
 			break;
-		case __SI_CHLD >> 16:
+		case SIL_CHLD:
 			err |= __put_user(from->si_utime, &to->si_utime);
 			err |= __put_user(from->si_stime, &to->si_stime);
 			err |= __put_user(from->si_status, &to->si_status);
 		default:
+		case SIL_KILL:
 			err |= __put_user(from->si_pid, &to->si_pid);
 			err |= __put_user(from->si_uid, &to->si_uid);
 			break;
-		case __SI_FAULT >> 16:
+		case SIL_FAULT:
 			err |= __put_user(from->si_trapno, &to->si_trapno);
 			err |= __put_user((unsigned long)from->si_addr, &to->si_addr);
 			break;
-		case __SI_POLL >> 16:
+		case SIL_POLL:
 			err |= __put_user(from->si_band, &to->si_band);
 			err |= __put_user(from->si_fd, &to->si_fd);
 			break;
-		case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
-		case __SI_MESGQ >> 16:
+		case SIL_RT:
 			err |= __put_user(from->si_pid, &to->si_pid);
 			err |= __put_user(from->si_uid, &to->si_uid);
 			err |= __put_user(from->si_int, &to->si_int);
diff --git a/arch/tile/include/uapi/asm/siginfo.h b/arch/tile/include/uapi/asm/siginfo.h
index 56d661bb010b..e83f931aa1f0 100644
--- a/arch/tile/include/uapi/asm/siginfo.h
+++ b/arch/tile/include/uapi/asm/siginfo.h
@@ -26,8 +26,8 @@
 /*
  * Additional Tile-specific SIGILL si_codes
  */
-#define ILL_DBLFLT	(__SI_FAULT|9)	/* double fault */
-#define ILL_HARDWALL	(__SI_FAULT|10)	/* user networks hardwall violation */
+#define ILL_DBLFLT	9	/* double fault */
+#define ILL_HARDWALL	10	/* user networks hardwall violation */
 #undef NSIGILL
 #define NSIGILL		10
 
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index 0e863f1ee08c..971d87a1d8cf 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -64,7 +64,7 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *fr
 	   3 ints plus the relevant union member.  */
 	err = __put_user(from->si_signo, &to->si_signo);
 	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
+	err |= __put_user(from->si_code, &to->si_code);
 
 	if (from->si_code < 0) {
 		err |= __put_user(from->si_pid, &to->si_pid);
@@ -77,28 +77,26 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *fr
 		 */
 		err |= __put_user(from->_sifields._pad[0],
 				  &to->_sifields._pad[0]);
-		switch (from->si_code >> 16) {
-		case __SI_FAULT >> 16:
+		switch (siginfo_layout(from->si_signo, from->si_code)) {
+		case SIL_FAULT:
 			break;
-		case __SI_CHLD >> 16:
+		case SIL_CHLD:
 			err |= __put_user(from->si_utime, &to->si_utime);
 			err |= __put_user(from->si_stime, &to->si_stime);
 			err |= __put_user(from->si_status, &to->si_status);
 			/* FALL THROUGH */
 		default:
-		case __SI_KILL >> 16:
+		case SIL_KILL:
 			err |= __put_user(from->si_uid, &to->si_uid);
 			break;
-		case __SI_POLL >> 16:
+		case SIL_POLL:
 			err |= __put_user(from->si_fd, &to->si_fd);
 			break;
-		case __SI_TIMER >> 16:
+		case SIL_TIMER:
 			err |= __put_user(from->si_overrun, &to->si_overrun);
 			err |= __put_user(from->si_int, &to->si_int);
 			break;
-			 /* This is not generated by the kernel as of now.  */
-		case __SI_RT >> 16:
-		case __SI_MESGQ >> 16:
+		case SIL_RT:
 			err |= __put_user(from->si_uid, &to->si_uid);
 			err |= __put_user(from->si_int, &to->si_int);
 			break;
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 54804866f238..9b08c6055f15 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -188,7 +188,7 @@ static int special_ill(tile_bundle_bits bundle, int *sigp, int *codep)
 
 	/* Make it the requested signal. */
 	*sigp = sig;
-	*codep = code | __SI_FAULT;
+	*codep = code;
 	return 1;
 }
 
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 71beb28600d4..ab9feb5887b1 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -129,7 +129,7 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
 		   3 ints plus the relevant union member.  */
 		put_user_ex(from->si_signo, &to->si_signo);
 		put_user_ex(from->si_errno, &to->si_errno);
-		put_user_ex((short)from->si_code, &to->si_code);
+		put_user_ex(from->si_code, &to->si_code);
 
 		if (from->si_code < 0) {
 			put_user_ex(from->si_pid, &to->si_pid);
@@ -142,8 +142,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
 			 */
 			put_user_ex(from->_sifields._pad[0],
 					  &to->_sifields._pad[0]);
-			switch (from->si_code >> 16) {
-			case __SI_FAULT >> 16:
+			switch (siginfo_layout(from->si_signo, from->si_code)) {
+			case SIL_FAULT:
 				if (from->si_signo == SIGBUS &&
 				    (from->si_code == BUS_MCEERR_AR ||
 				     from->si_code == BUS_MCEERR_AO))
@@ -160,11 +160,11 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
 						put_user_ex(from->si_pkey, &to->si_pkey);
 				}
 				break;
-			case __SI_SYS >> 16:
+			case SIL_SYS:
 				put_user_ex(from->si_syscall, &to->si_syscall);
 				put_user_ex(from->si_arch, &to->si_arch);
 				break;
-			case __SI_CHLD >> 16:
+			case SIL_CHLD:
 				if (!x32_ABI) {
 					put_user_ex(from->si_utime, &to->si_utime);
 					put_user_ex(from->si_stime, &to->si_stime);
@@ -174,21 +174,18 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
 				}
 				put_user_ex(from->si_status, &to->si_status);
 				/* FALL THROUGH */
-			default:
-			case __SI_KILL >> 16:
+			case SIL_KILL:
 				put_user_ex(from->si_uid, &to->si_uid);
 				break;
-			case __SI_POLL >> 16:
+			case SIL_POLL:
 				put_user_ex(from->si_fd, &to->si_fd);
 				break;
-			case __SI_TIMER >> 16:
+			case SIL_TIMER:
 				put_user_ex(from->si_overrun, &to->si_overrun);
 				put_user_ex(ptr_to_compat(from->si_ptr),
 					    &to->si_ptr);
 				break;
-				 /* This is not generated by the kernel as of now.  */
-			case __SI_RT >> 16:
-			case __SI_MESGQ >> 16:
+			case SIL_RT:
 				put_user_ex(from->si_uid, &to->si_uid);
 				put_user_ex(from->si_int, &to->si_int);
 				break;
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 593b022ac11b..d2c434112f42 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -95,23 +95,23 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 	 */
 	err |= __put_user(kinfo->si_signo, &uinfo->ssi_signo);
 	err |= __put_user(kinfo->si_errno, &uinfo->ssi_errno);
-	err |= __put_user((short) kinfo->si_code, &uinfo->ssi_code);
-	switch (kinfo->si_code & __SI_MASK) {
-	case __SI_KILL:
+	err |= __put_user(kinfo->si_code, &uinfo->ssi_code);
+	switch (siginfo_layout(kinfo->si_signo, kinfo->si_code)) {
+	case SIL_KILL:
 		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
 		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
 		break;
-	case __SI_TIMER:
+	case SIL_TIMER:
 		 err |= __put_user(kinfo->si_tid, &uinfo->ssi_tid);
 		 err |= __put_user(kinfo->si_overrun, &uinfo->ssi_overrun);
 		 err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
 		 err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
 		break;
-	case __SI_POLL:
+	case SIL_POLL:
 		err |= __put_user(kinfo->si_band, &uinfo->ssi_band);
 		err |= __put_user(kinfo->si_fd, &uinfo->ssi_fd);
 		break;
-	case __SI_FAULT:
+	case SIL_FAULT:
 		err |= __put_user((long) kinfo->si_addr, &uinfo->ssi_addr);
 #ifdef __ARCH_SI_TRAPNO
 		err |= __put_user(kinfo->si_trapno, &uinfo->ssi_trapno);
@@ -128,20 +128,14 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 					  &uinfo->ssi_addr_lsb);
 #endif
 		break;
-	case __SI_CHLD:
+	case SIL_CHLD:
 		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
 		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
 		err |= __put_user(kinfo->si_status, &uinfo->ssi_status);
 		err |= __put_user(kinfo->si_utime, &uinfo->ssi_utime);
 		err |= __put_user(kinfo->si_stime, &uinfo->ssi_stime);
 		break;
-	case __SI_RT: /* This is not generated by the kernel as of now. */
-	case __SI_MESGQ: /* But this is */
-		err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
-		err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
-		err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
-		err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
-		break;
+	case SIL_RT:
 	default:
 		/*
 		 * This case catches also the signals queued by sigqueue().
diff --git a/include/linux/signal.h b/include/linux/signal.h
index c97cc20369c0..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.
  */
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 9e956ea94d57..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.
@@ -181,10 +158,10 @@ 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 __SI_CODE(__SI_POLL,-5) /* sent by queued SIGIO */
+#define SI_SIGIO	-5		/* sent by queued SIGIO */
 #define SI_TKILL	-6		/* sent by tkill system call */
 #define SI_DETHREAD	-7		/* sent by execve() killing subsidiary threads */
 
@@ -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 (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/kernel/exit.c b/kernel/exit.c
index c5548faa9f37..c8f23613df5b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1616,7 +1616,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
-	unsafe_put_user((short)info.cause, &infop->si_code, Efault);
+	unsafe_put_user(info.cause, &infop->si_code, Efault);
 	unsafe_put_user(info.pid, &infop->si_pid, Efault);
 	unsafe_put_user(info.uid, &infop->si_uid, Efault);
 	unsafe_put_user(info.status, &infop->si_status, Efault);
@@ -1742,7 +1742,7 @@ COMPAT_SYSCALL_DEFINE5(waitid,
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
-	unsafe_put_user((short)info.cause, &infop->si_code, Efault);
+	unsafe_put_user(info.cause, &infop->si_code, Efault);
 	unsafe_put_user(info.pid, &infop->si_pid, Efault);
 	unsafe_put_user(info.uid, &infop->si_uid, Efault);
 	unsafe_put_user(info.status, &infop->si_status, Efault);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 60f356d91060..84b1367935e4 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -728,8 +728,7 @@ static int ptrace_peek_siginfo(struct task_struct *child,
 		if (unlikely(in_compat_syscall())) {
 			compat_siginfo_t __user *uinfo = compat_ptr(data);
 
-			if (copy_siginfo_to_user32(uinfo, &info) ||
-			    __put_user(info.si_code, &uinfo->si_code)) {
+			if (copy_siginfo_to_user32(uinfo, &info)) {
 				ret = -EFAULT;
 				break;
 			}
@@ -739,8 +738,7 @@ static int ptrace_peek_siginfo(struct task_struct *child,
 		{
 			siginfo_t __user *uinfo = (siginfo_t __user *) data;
 
-			if (copy_siginfo_to_user(uinfo, &info) ||
-			    __put_user(info.si_code, &uinfo->si_code)) {
+			if (copy_siginfo_to_user(uinfo, &info)) {
 				ret = -EFAULT;
 				break;
 			}
diff --git a/kernel/signal.c b/kernel/signal.c
index caed9133ae52..6bd53c8189f0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2682,6 +2682,51 @@ COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset,
 }
 #endif
 
+enum siginfo_layout siginfo_layout(int sig, int si_code)
+{
+	enum siginfo_layout layout = SIL_KILL;
+	if ((si_code > SI_USER) && (si_code < SI_KERNEL)) {
+		static const struct {
+			unsigned char limit, layout;
+		} filter[] = {
+			[SIGILL]  = { NSIGILL,  SIL_FAULT },
+			[SIGFPE]  = { NSIGFPE,  SIL_FAULT },
+			[SIGSEGV] = { NSIGSEGV, SIL_FAULT },
+			[SIGBUS]  = { NSIGBUS,  SIL_FAULT },
+			[SIGTRAP] = { NSIGTRAP, SIL_FAULT },
+#if defined(SIGMET) && defined(NSIGEMT)
+			[SIGEMT]  = { NSIGEMT,  SIL_FAULT },
+#endif
+			[SIGCHLD] = { NSIGCHLD, SIL_CHLD },
+			[SIGPOLL] = { NSIGPOLL, SIL_POLL },
+#ifdef __ARCH_SIGSYS
+			[SIGSYS]  = { NSIGSYS,  SIL_SYS },
+#endif
+		};
+		if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit))
+			layout = filter[sig].layout;
+		else if (si_code <= NSIGPOLL)
+			layout = SIL_POLL;
+	} else {
+		if (si_code == SI_TIMER)
+			layout = SIL_TIMER;
+		else if (si_code == SI_SIGIO)
+			layout = SIL_POLL;
+		else if (si_code < 0)
+			layout = SIL_RT;
+		/* Tests to support buggy kernel ABIs */
+#ifdef TRAP_FIXME
+		if ((sig == SIGTRAP) && (si_code == TRAP_FIXME))
+			layout = SIL_FAULT;
+#endif
+#ifdef FPE_FIXME
+		if ((sig == SIGFPE) && (si_code == FPE_FIXME))
+			layout = SIL_FAULT;
+#endif
+	}
+	return layout;
+}
+
 #ifndef HAVE_ARCH_COPY_SIGINFO_TO_USER
 
 int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
@@ -2704,22 +2749,20 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 	 */
 	err = __put_user(from->si_signo, &to->si_signo);
 	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
-	switch (from->si_code & __SI_MASK) {
-	case __SI_KILL:
+	err |= __put_user(from->si_code, &to->si_code);
+	switch (siginfo_layout(from->si_signo, from->si_code)) {
+	case SIL_KILL:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		break;
-	case __SI_TIMER:
-		 err |= __put_user(from->si_tid, &to->si_tid);
-		 err |= __put_user(from->si_overrun, &to->si_overrun);
-		 err |= __put_user(from->si_ptr, &to->si_ptr);
+	case SIL_TIMER:
+		/* Unreached SI_TIMER is negative */
 		break;
-	case __SI_POLL:
+	case SIL_POLL:
 		err |= __put_user(from->si_band, &to->si_band);
 		err |= __put_user(from->si_fd, &to->si_fd);
 		break;
-	case __SI_FAULT:
+	case SIL_FAULT:
 		err |= __put_user(from->si_addr, &to->si_addr);
 #ifdef __ARCH_SI_TRAPNO
 		err |= __put_user(from->si_trapno, &to->si_trapno);
@@ -2744,30 +2787,25 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 			err |= __put_user(from->si_pkey, &to->si_pkey);
 #endif
 		break;
-	case __SI_CHLD:
+	case SIL_CHLD:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		err |= __put_user(from->si_status, &to->si_status);
 		err |= __put_user(from->si_utime, &to->si_utime);
 		err |= __put_user(from->si_stime, &to->si_stime);
 		break;
-	case __SI_RT: /* This is not generated by the kernel as of now. */
-	case __SI_MESGQ: /* But this is */
+	case SIL_RT:
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
 		err |= __put_user(from->si_ptr, &to->si_ptr);
 		break;
 #ifdef __ARCH_SIGSYS
-	case __SI_SYS:
+	case SIL_SYS:
 		err |= __put_user(from->si_call_addr, &to->si_call_addr);
 		err |= __put_user(from->si_syscall, &to->si_syscall);
 		err |= __put_user(from->si_arch, &to->si_arch);
 		break;
 #endif
-	default: /* this is just in case for now ... */
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		break;
 	}
 	return err;
 }
-- 
cgit v1.2.3-58-ga151


From 8db6c34f1dbc8e06aa016a9b829b06902c3e1340 Mon Sep 17 00:00:00 2001
From: "Serge E. Hallyn" <serge@hallyn.com>
Date: Mon, 8 May 2017 13:11:56 -0500
Subject: Introduce v3 namespaced file capabilities

Root in a non-initial user ns cannot be trusted to write a traditional
security.capability xattr.  If it were allowed to do so, then any
unprivileged user on the host could map his own uid to root in a private
namespace, write the xattr, and execute the file with privilege on the
host.

However supporting file capabilities in a user namespace is very
desirable.  Not doing so means that any programs designed to run with
limited privilege must continue to support other methods of gaining and
dropping privilege.  For instance a program installer must detect
whether file capabilities can be assigned, and assign them if so but set
setuid-root otherwise.  The program in turn must know how to drop
partial capabilities, and do so only if setuid-root.

This patch introduces v3 of the security.capability xattr.  It builds a
vfs_ns_cap_data struct by appending a uid_t rootid to struct
vfs_cap_data.  This is the absolute uid_t (that is, the uid_t in user
namespace which mounted the filesystem, usually init_user_ns) of the
root id in whose namespaces the file capabilities may take effect.

When a task asks to write a v2 security.capability xattr, if it is
privileged with respect to the userns which mounted the filesystem, then
nothing should change.  Otherwise, the kernel will transparently rewrite
the xattr as a v3 with the appropriate rootid.  This is done during the
execution of setxattr() to catch user-space-initiated capability writes.
Subsequently, any task executing the file which has the noted kuid as
its root uid, or which is in a descendent user_ns of such a user_ns,
will run the file with capabilities.

Similarly when asking to read file capabilities, a v3 capability will
be presented as v2 if it applies to the caller's namespace.

If a task writes a v3 security.capability, then it can provide a uid for
the xattr so long as the uid is valid in its own user namespace, and it
is privileged with CAP_SETFCAP over its namespace.  The kernel will
translate that rootid to an absolute uid, and write that to disk.  After
this, a task in the writer's namespace will not be able to use those
capabilities (unless rootid was 0), but a task in a namespace where the
given uid is root will.

Only a single security.capability xattr may exist at a time for a given
file.  A task may overwrite an existing xattr so long as it is
privileged over the inode.  Note this is a departure from previous
semantics, which required privilege to remove a security.capability
xattr.  This check can be re-added if deemed useful.

This allows a simple setxattr to work, allows tar/untar to work, and
allows us to tar in one namespace and untar in another while preserving
the capability, without risking leaking privilege into a parent
namespace.

Example using tar:

 $ cp /bin/sleep sleepx
 $ mkdir b1 b2
 $ lxc-usernsexec -m b:0:100000:1 -m b:1:$(id -u):1 -- chown 0:0 b1
 $ lxc-usernsexec -m b:0:100001:1 -m b:1:$(id -u):1 -- chown 0:0 b2
 $ lxc-usernsexec -m b:0:100000:1000 -- tar --xattrs-include=security.capability --xattrs -cf b1/sleepx.tar sleepx
 $ lxc-usernsexec -m b:0:100001:1000 -- tar --xattrs-include=security.capability --xattrs -C b2 -xf b1/sleepx.tar
 $ lxc-usernsexec -m b:0:100001:1000 -- getcap b2/sleepx
   b2/sleepx = cap_sys_admin+ep
 # /opt/ltp/testcases/bin/getv3xattr b2/sleepx
   v3 xattr, rootid is 100001

A patch to linux-test-project adding a new set of tests for this
functionality is in the nsfscaps branch at github.com/hallyn/ltp

Changelog:
   Nov 02 2016: fix invalid check at refuse_fcap_overwrite()
   Nov 07 2016: convert rootid from and to fs user_ns
   (From ebiederm: mar 28 2017)
     commoncap.c: fix typos - s/v4/v3
     get_vfs_caps_from_disk: clarify the fs_ns root access check
     nsfscaps: change the code split for cap_inode_setxattr()
   Apr 09 2017:
       don't return v3 cap for caps owned by current root.
      return a v2 cap for a true v2 cap in non-init ns
   Apr 18 2017:
      . Change the flow of fscap writing to support s_user_ns writing.
      . Remove refuse_fcap_overwrite().  The value of the previous
        xattr doesn't matter.
   Apr 24 2017:
      . incorporate Eric's incremental diff
      . move cap_convert_nscap to setxattr and simplify its usage
   May 8, 2017:
      . fix leaking dentry refcount in cap_inode_getsecurity

Signed-off-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/xattr.c                      |   6 +
 include/linux/capability.h      |   2 +
 include/linux/security.h        |   2 +
 include/uapi/linux/capability.h |  22 +++-
 security/commoncap.c            | 270 +++++++++++++++++++++++++++++++++++++---
 5 files changed, 280 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/xattr.c b/fs/xattr.c
index 464c94bf65f9..7b03df6b8be2 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -441,6 +441,12 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
 		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
 			posix_acl_fix_xattr_from_user(kvalue, size);
+		else if (strcmp(kname, XATTR_NAME_CAPS) == 0) {
+			error = cap_convert_nscap(d, &kvalue, size);
+			if (error < 0)
+				goto out;
+			size = error;
+		}
 	}
 
 	error = vfs_setxattr(d, kname, kvalue, size, flags);
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 b6ea1dc9cc9d..6fff8c924718 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -91,6 +91,8 @@ 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/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__
 
 /*
diff --git a/security/commoncap.c b/security/commoncap.c
index d59320282294..c37d27dd1e2c 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -335,6 +335,209 @@ int cap_inode_killpriv(struct dentry *dentry)
 	return error;
 }
 
+static bool rootid_owns_currentns(kuid_t kroot)
+{
+	struct user_namespace *ns;
+
+	if (!uid_valid(kroot))
+		return false;
+
+	for (ns = current_user_ns(); ; ns = ns->parent) {
+		if (from_kuid(ns, kroot) == 0)
+			return true;
+		if (ns == &init_user_ns)
+			break;
+	}
+
+	return false;
+}
+
+static __u32 sansflags(__u32 m)
+{
+	return m & ~VFS_CAP_FLAGS_EFFECTIVE;
+}
+
+static bool is_v2header(size_t size, __le32 magic)
+{
+	__u32 m = le32_to_cpu(magic);
+	if (size != XATTR_CAPS_SZ_2)
+		return false;
+	return sansflags(m) == VFS_CAP_REVISION_2;
+}
+
+static bool is_v3header(size_t size, __le32 magic)
+{
+	__u32 m = le32_to_cpu(magic);
+
+	if (size != XATTR_CAPS_SZ_3)
+		return false;
+	return sansflags(m) == VFS_CAP_REVISION_3;
+}
+
+/*
+ * getsecurity: We are called for security.* before any attempt to read the
+ * xattr from the inode itself.
+ *
+ * This gives us a chance to read the on-disk value and convert it.  If we
+ * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler.
+ *
+ * Note we are not called by vfs_getxattr_alloc(), but that is only called
+ * by the integrity subsystem, which really wants the unconverted values -
+ * so that's good.
+ */
+int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
+			  bool alloc)
+{
+	int size, ret;
+	kuid_t kroot;
+	uid_t root, mappedroot;
+	char *tmpbuf = NULL;
+	struct vfs_cap_data *cap;
+	struct vfs_ns_cap_data *nscap;
+	struct dentry *dentry;
+	struct user_namespace *fs_ns;
+
+	if (strcmp(name, "capability") != 0)
+		return -EOPNOTSUPP;
+
+	dentry = d_find_alias(inode);
+	if (!dentry)
+		return -EINVAL;
+
+	size = sizeof(struct vfs_ns_cap_data);
+	ret = (int) vfs_getxattr_alloc(dentry, XATTR_NAME_CAPS,
+				 &tmpbuf, size, GFP_NOFS);
+	dput(dentry);
+
+	if (ret < 0)
+		return ret;
+
+	fs_ns = inode->i_sb->s_user_ns;
+	cap = (struct vfs_cap_data *) tmpbuf;
+	if (is_v2header((size_t) ret, cap->magic_etc)) {
+		/* If this is sizeof(vfs_cap_data) then we're ok with the
+		 * on-disk value, so return that.  */
+		if (alloc)
+			*buffer = tmpbuf;
+		else
+			kfree(tmpbuf);
+		return ret;
+	} else if (!is_v3header((size_t) ret, cap->magic_etc)) {
+		kfree(tmpbuf);
+		return -EINVAL;
+	}
+
+	nscap = (struct vfs_ns_cap_data *) tmpbuf;
+	root = le32_to_cpu(nscap->rootid);
+	kroot = make_kuid(fs_ns, root);
+
+	/* If the root kuid maps to a valid uid in current ns, then return
+	 * this as a nscap. */
+	mappedroot = from_kuid(current_user_ns(), kroot);
+	if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) {
+		if (alloc) {
+			*buffer = tmpbuf;
+			nscap->rootid = cpu_to_le32(mappedroot);
+		} else
+			kfree(tmpbuf);
+		return size;
+	}
+
+	if (!rootid_owns_currentns(kroot)) {
+		kfree(tmpbuf);
+		return -EOPNOTSUPP;
+	}
+
+	/* This comes from a parent namespace.  Return as a v2 capability */
+	size = sizeof(struct vfs_cap_data);
+	if (alloc) {
+		*buffer = kmalloc(size, GFP_ATOMIC);
+		if (*buffer) {
+			struct vfs_cap_data *cap = *buffer;
+			__le32 nsmagic, magic;
+			magic = VFS_CAP_REVISION_2;
+			nsmagic = le32_to_cpu(nscap->magic_etc);
+			if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE)
+				magic |= VFS_CAP_FLAGS_EFFECTIVE;
+			memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+			cap->magic_etc = cpu_to_le32(magic);
+		}
+	}
+	kfree(tmpbuf);
+	return size;
+}
+
+static kuid_t rootid_from_xattr(const void *value, size_t size,
+				struct user_namespace *task_ns)
+{
+	const struct vfs_ns_cap_data *nscap = value;
+	uid_t rootid = 0;
+
+	if (size == XATTR_CAPS_SZ_3)
+		rootid = le32_to_cpu(nscap->rootid);
+
+	return make_kuid(task_ns, rootid);
+}
+
+static bool validheader(size_t size, __le32 magic)
+{
+	return is_v2header(size, magic) || is_v3header(size, magic);
+}
+
+/*
+ * User requested a write of security.capability.  If needed, update the
+ * xattr to change from v2 to v3, or to fixup the v3 rootid.
+ *
+ * If all is ok, we return the new size, on error return < 0.
+ */
+int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size)
+{
+	struct vfs_ns_cap_data *nscap;
+	uid_t nsrootid;
+	const struct vfs_cap_data *cap = *ivalue;
+	__u32 magic, nsmagic;
+	struct inode *inode = d_backing_inode(dentry);
+	struct user_namespace *task_ns = current_user_ns(),
+		*fs_ns = inode->i_sb->s_user_ns;
+	kuid_t rootid;
+	size_t newsize;
+
+	if (!*ivalue)
+		return -EINVAL;
+	if (!validheader(size, cap->magic_etc))
+		return -EINVAL;
+	if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP))
+		return -EPERM;
+	if (size == XATTR_CAPS_SZ_2)
+		if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP))
+			/* user is privileged, just write the v2 */
+			return size;
+
+	rootid = rootid_from_xattr(*ivalue, size, task_ns);
+	if (!uid_valid(rootid))
+		return -EINVAL;
+
+	nsrootid = from_kuid(fs_ns, rootid);
+	if (nsrootid == -1)
+		return -EINVAL;
+
+	newsize = sizeof(struct vfs_ns_cap_data);
+	nscap = kmalloc(newsize, GFP_ATOMIC);
+	if (!nscap)
+		return -ENOMEM;
+	nscap->rootid = cpu_to_le32(nsrootid);
+	nsmagic = VFS_CAP_REVISION_3;
+	magic = le32_to_cpu(cap->magic_etc);
+	if (magic & VFS_CAP_FLAGS_EFFECTIVE)
+		nsmagic |= VFS_CAP_FLAGS_EFFECTIVE;
+	nscap->magic_etc = cpu_to_le32(nsmagic);
+	memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+
+	kvfree(*ivalue);
+	*ivalue = nscap;
+	return newsize;
+}
+
 /*
  * Calculate the new process capability sets from the capability sets attached
  * to a file.
@@ -388,7 +591,10 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
 	__u32 magic_etc;
 	unsigned tocopy, i;
 	int size;
-	struct vfs_cap_data caps;
+	struct vfs_ns_cap_data data, *nscaps = &data;
+	struct vfs_cap_data *caps = (struct vfs_cap_data *) &data;
+	kuid_t rootkuid;
+	struct user_namespace *fs_ns = inode->i_sb->s_user_ns;
 
 	memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data));
 
@@ -396,18 +602,20 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
 		return -ENODATA;
 
 	size = __vfs_getxattr((struct dentry *)dentry, inode,
-			      XATTR_NAME_CAPS, &caps, XATTR_CAPS_SZ);
+			      XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ);
 	if (size == -ENODATA || size == -EOPNOTSUPP)
 		/* no data, that's ok */
 		return -ENODATA;
+
 	if (size < 0)
 		return size;
 
 	if (size < sizeof(magic_etc))
 		return -EINVAL;
 
-	cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps.magic_etc);
+	cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc);
 
+	rootkuid = make_kuid(fs_ns, 0);
 	switch (magic_etc & VFS_CAP_REVISION_MASK) {
 	case VFS_CAP_REVISION_1:
 		if (size != XATTR_CAPS_SZ_1)
@@ -419,15 +627,27 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
 			return -EINVAL;
 		tocopy = VFS_CAP_U32_2;
 		break;
+	case VFS_CAP_REVISION_3:
+		if (size != XATTR_CAPS_SZ_3)
+			return -EINVAL;
+		tocopy = VFS_CAP_U32_3;
+		rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid));
+		break;
+
 	default:
 		return -EINVAL;
 	}
+	/* Limit the caps to the mounter of the filesystem
+	 * or the more limited uid specified in the xattr.
+	 */
+	if (!rootid_owns_currentns(rootkuid))
+		return -ENODATA;
 
 	CAP_FOR_EACH_U32(i) {
 		if (i >= tocopy)
 			break;
-		cpu_caps->permitted.cap[i] = le32_to_cpu(caps.data[i].permitted);
-		cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable);
+		cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted);
+		cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable);
 	}
 
 	cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
@@ -465,8 +685,8 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_c
 	rc = get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps);
 	if (rc < 0) {
 		if (rc == -EINVAL)
-			printk(KERN_NOTICE "%s: get_vfs_caps_from_disk returned %d for %s\n",
-				__func__, rc, bprm->filename);
+			printk(KERN_NOTICE "Invalid argument reading file caps for %s\n",
+					bprm->filename);
 		else if (rc == -ENODATA)
 			rc = 0;
 		goto out;
@@ -663,15 +883,19 @@ int cap_bprm_secureexec(struct linux_binprm *bprm)
 int cap_inode_setxattr(struct dentry *dentry, const char *name,
 		       const void *value, size_t size, int flags)
 {
-	if (!strcmp(name, XATTR_NAME_CAPS)) {
-		if (!capable(CAP_SETFCAP))
-			return -EPERM;
+	/* Ignore non-security xattrs */
+	if (strncmp(name, XATTR_SECURITY_PREFIX,
+			sizeof(XATTR_SECURITY_PREFIX) - 1) != 0)
+		return 0;
+
+	/*
+	 * For XATTR_NAME_CAPS the check will be done in
+	 * cap_convert_nscap(), called by setxattr()
+	 */
+	if (strcmp(name, XATTR_NAME_CAPS) == 0)
 		return 0;
-	}
 
-	if (!strncmp(name, XATTR_SECURITY_PREFIX,
-		     sizeof(XATTR_SECURITY_PREFIX) - 1) &&
-	    !capable(CAP_SYS_ADMIN))
+	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	return 0;
 }
@@ -689,15 +913,22 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name,
  */
 int cap_inode_removexattr(struct dentry *dentry, const char *name)
 {
-	if (!strcmp(name, XATTR_NAME_CAPS)) {
-		if (!capable(CAP_SETFCAP))
+	/* Ignore non-security xattrs */
+	if (strncmp(name, XATTR_SECURITY_PREFIX,
+			sizeof(XATTR_SECURITY_PREFIX) - 1) != 0)
+		return 0;
+
+	if (strcmp(name, XATTR_NAME_CAPS) == 0) {
+		/* security.capability gets namespaced */
+		struct inode *inode = d_backing_inode(dentry);
+		if (!inode)
+			return -EINVAL;
+		if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP))
 			return -EPERM;
 		return 0;
 	}
 
-	if (!strncmp(name, XATTR_SECURITY_PREFIX,
-		     sizeof(XATTR_SECURITY_PREFIX) - 1) &&
-	    !capable(CAP_SYS_ADMIN))
+	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	return 0;
 }
@@ -1085,6 +1316,7 @@ struct security_hook_list capability_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(bprm_secureexec, cap_bprm_secureexec),
 	LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv),
 	LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv),
+	LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity),
 	LSM_HOOK_INIT(mmap_addr, cap_mmap_addr),
 	LSM_HOOK_INIT(mmap_file, cap_mmap_file),
 	LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid),
-- 
cgit v1.2.3-58-ga151