14 files changed, 186 insertions, 36 deletions

diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index 5e5e3865f1ed..8ed67779fc09 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -98,9 +98,18 @@ typedef struct siginfo {
                         __ARCH_SI_BAND_T _band; /* POLL_IN, POLL_OUT, POLL_MSG */
                         int _fd;
                 } _sigpoll;
+
+                /* SIGSYS */
+                struct {
+                        void __user *_call_addr; /* calling user insn */
+                        int _syscall;   /* triggering system call number */
+                        unsigned int _arch;     /* AUDIT_ARCH_* of syscall */
+                } _sigsys;
         } _sifields;
 } __ARCH_SI_ATTRIBUTES siginfo_t;
 
+/* If the arch shares siginfo, then it has SIGSYS. */
+#define __ARCH_SIGSYS
 #endif
 
 /*
@@ -124,6 +133,11 @@ typedef struct siginfo {
 #define si_addr_lsb     _sifields._sigfault._addr_lsb
 #define si_band         _sifields._sigpoll._band
 #define si_fd           _sifields._sigpoll._fd
+#ifdef __ARCH_SIGSYS
+#define si_call_addr    _sifields._sigsys._call_addr
+#define si_syscall      _sifields._sigsys._syscall
+#define si_arch         _sifields._sigsys._arch
+#endif
 
 #ifdef __KERNEL__
 #define __SI_MASK       0xffff0000u
@@ -134,6 +148,7 @@ typedef struct siginfo {
 #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
 #define __SI_KILL       0
@@ -143,6 +158,7 @@ typedef struct siginfo {
 #define __SI_CHLD       0
 #define __SI_RT         0
 #define __SI_MESGQ      0
+#define __SI_SYS        0
 #define __SI_CODE(T,N)  (N)
 #endif
 
@@ -240,6 +256,12 @@ typedef struct siginfo {
 #define NSIGPOLL        6
 
 /*
+ * SIGSYS si_codes
+ */
+#define SYS_SECCOMP             (__SI_SYS|1)    /* seccomp triggered */
+#define NSIGSYS 1
+
+/*
  * sigevent definitions
  * 
  * It seems likely that SIGEV_THREAD will have to be handled from 
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 5c122ae6bfa6..5b09392db673 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -142,4 +142,18 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
                            unsigned int i, unsigned int n,
                            const unsigned long *args);
 
+/**
+ * syscall_get_arch - return the AUDIT_ARCH for the current system call
+ * @task:       task of interest, must be in system call entry tracing
+ * @regs:       task_pt_regs() of @task
+ *
+ * Returns the AUDIT_ARCH_* based on the system call convention in use.
+ *
+ * It's only valid to call this when @task is stopped on entry to a system
+ * call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %TIF_SECCOMP.
+ *
+ * Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
+ * provide an implementation of this.
+ */
+int syscall_get_arch(struct task_struct *task, struct pt_regs *regs);
 #endif  /* _ASM_SYSCALL_H */
diff --git a/include/keys/keyring-type.h b/include/keys/keyring-type.h
index 843f872a4b63..cf49159b0e3a 100644
--- a/include/keys/keyring-type.h
+++ b/include/keys/keyring-type.h
@@ -24,7 +24,7 @@ struct keyring_list {
         unsigned short  maxkeys;        /* max keys this list can hold */
         unsigned short  nkeys;          /* number of keys currently held */
         unsigned short  delkey;         /* key to be unlinked by RCU */
-        struct key      *keys[0];
+        struct key __rcu *keys[0];
 };
 
 
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index b5d568fa19e8..0237b84ba541 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -330,6 +330,7 @@ header-y += scc.h
 header-y += sched.h
 header-y += screen_info.h
 header-y += sdla.h
+header-y += seccomp.h
 header-y += securebits.h
 header-y += selinux_netlink.h
 header-y += sem.h
diff --git a/include/linux/audit.h b/include/linux/audit.h
index ed3ef1972496..22f292a917a3 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -463,7 +463,7 @@ extern void audit_putname(const char *name);
 extern void __audit_inode(const char *name, const struct dentry *dentry);
 extern void __audit_inode_child(const struct dentry *dentry,
                                 const struct inode *parent);
-extern void __audit_seccomp(unsigned long syscall);
+extern void __audit_seccomp(unsigned long syscall, long signr, int code);
 extern void __audit_ptrace(struct task_struct *t);
 
 static inline int audit_dummy_context(void)
@@ -508,10 +508,10 @@ static inline void audit_inode_child(const struct dentry *dentry,
 }
 void audit_core_dumps(long signr);
 
-static inline void audit_seccomp(unsigned long syscall)
+static inline void audit_seccomp(unsigned long syscall, long signr, int code)
 {
         if (unlikely(!audit_dummy_context()))
-                __audit_seccomp(syscall);
+                __audit_seccomp(syscall, signr, code);
 }
 
 static inline void audit_ptrace(struct task_struct *t)
@@ -634,7 +634,7 @@ extern int audit_signals;
 #define audit_inode(n,d) do { (void)(d); } while (0)
 #define audit_inode_child(i,p) do { ; } while (0)
 #define audit_core_dumps(i) do { ; } while (0)
-#define audit_seccomp(i) do { ; } while (0)
+#define audit_seccomp(i,s,c) do { ; } while (0)
 #define auditsc_get_stamp(c,t,s) (0)
 #define audit_get_loginuid(t) (-1)
 #define audit_get_sessionid(t) (-1)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 72090994d789..82b01357af8b 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -10,6 +10,7 @@
 
 #ifdef __KERNEL__
 #include <linux/atomic.h>
+#include <linux/compat.h>
 #endif
 
 /*
@@ -133,6 +134,16 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 
 #ifdef __KERNEL__
 
+#ifdef CONFIG_COMPAT
+/*
+ * A struct sock_filter is architecture independent.
+ */
+struct compat_sock_fprog {
+        u16             len;
+        compat_uptr_t   filter;         /* struct sock_filter * */
+};
+#endif
+
 struct sk_buff;
 struct sock;
 
@@ -233,6 +244,7 @@ enum {
         BPF_S_ANC_RXHASH,
         BPF_S_ANC_CPU,
         BPF_S_ANC_ALU_XOR_X,
+        BPF_S_ANC_SECCOMP_LD_W,
 };
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/key.h b/include/linux/key.h
index 96933b1e5d24..5231800770e1 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -124,7 +124,10 @@ static inline unsigned long is_key_possessed(const key_ref_t key_ref)
 struct key {
         atomic_t                usage;          /* number of references */
         key_serial_t            serial;         /* key serial number */
-        struct rb_node          serial_node;
+        union {
+                struct list_head graveyard_link;
+                struct rb_node  serial_node;
+        };
         struct key_type         *type;          /* type of key */
         struct rw_semaphore     sem;            /* change vs change sem */
         struct key_user         *user;          /* owner of this key */
@@ -133,6 +136,7 @@ struct key {
                 time_t          expiry;         /* time at which key expires (or 0) */
                 time_t          revoked_at;     /* time at which key was revoked */
         };
+        time_t                  last_used_at;   /* last time used for LRU keyring discard */
         uid_t                   uid;
         gid_t                   gid;
         key_perm_t              perm;           /* access permissions */
@@ -156,6 +160,7 @@ struct key {
 #define KEY_FLAG_USER_CONSTRUCT 4       /* set if key is being constructed in userspace */
 #define KEY_FLAG_NEGATIVE       5       /* set if key is negative */
 #define KEY_FLAG_ROOT_CAN_CLEAR 6       /* set if key can be cleared by root without permission */
+#define KEY_FLAG_INVALIDATED    7       /* set if key has been invalidated */
 
         /* the description string
          * - this is used to match a key against search criteria
@@ -199,6 +204,7 @@ extern struct key *key_alloc(struct key_type *type,
 #define KEY_ALLOC_NOT_IN_QUOTA  0x0002  /* not in quota */
 
 extern void key_revoke(struct key *key);
+extern void key_invalidate(struct key *key);
 extern void key_put(struct key *key);
 
 static inline struct key *key_get(struct key *key)
@@ -236,7 +242,7 @@ extern struct key *request_key_async_with_auxdata(struct key_type *type,
 
 extern int wait_for_key_construction(struct key *key, bool intr);
 
-extern int key_validate(struct key *key);
+extern int key_validate(const struct key *key);
 
 extern key_ref_t key_create_or_update(key_ref_t keyring,
                                       const char *type,
@@ -319,6 +325,7 @@ extern void key_init(void);
 #define key_serial(k)                   0
 #define key_get(k)                      ({ NULL; })
 #define key_revoke(k)                   do { } while(0)
+#define key_invalidate(k)               do { } while(0)
 #define key_put(k)                      do { } while(0)
 #define key_ref_put(k)                  do { } while(0)
 #define make_key_ref(k, p)              NULL
diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h
index 9b0b865ce622..c9b7f4faf97a 100644
--- a/include/linux/keyctl.h
+++ b/include/linux/keyctl.h
@@ -55,5 +55,6 @@
 #define KEYCTL_SESSION_TO_PARENT        18      /* apply session keyring to parent process */
 #define KEYCTL_REJECT                   19      /* reject a partially constructed key */
 #define KEYCTL_INSTANTIATE_IOV          20      /* instantiate a partially constructed key */
+#define KEYCTL_INVALIDATE               21      /* invalidate a key */
 
 #endif /*  _LINUX_KEYCTL_H */
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index fad48aab893b..1cc89e9df480 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -53,7 +53,6 @@ struct common_audit_data {
 #define LSM_AUDIT_DATA_KMOD     8
 #define LSM_AUDIT_DATA_INODE    9
 #define LSM_AUDIT_DATA_DENTRY   10
-        struct task_struct *tsk;
         union   {
                 struct path path;
                 struct dentry *dentry;
@@ -93,11 +92,6 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 int ipv6_skb_to_auditdata(struct sk_buff *skb,
                 struct common_audit_data *ad, u8 *proto);
 
-/* Initialize an LSM audit data structure. */
-#define COMMON_AUDIT_DATA_INIT(_d, _t) \
-        { memset((_d), 0, sizeof(struct common_audit_data)); \
-         (_d)->type = LSM_AUDIT_DATA_##_t; }
-
 void common_lsm_audit(struct common_audit_data *a,
         void (*pre_audit)(struct audit_buffer *, void *),
         void (*post_audit)(struct audit_buffer *, void *));
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index e0cfec2490aa..78b76e24cc7e 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -124,4 +124,19 @@
 #define PR_SET_CHILD_SUBREAPER 36
 #define PR_GET_CHILD_SUBREAPER 37
 
+/*
+ * If no_new_privs is set, then operations that grant new privileges (i.e.
+ * execve) will either fail or not grant them.  This affects suid/sgid,
+ * file capabilities, and LSMs.
+ *
+ * Operations that merely manipulate or drop existing privileges (setresuid,
+ * capset, etc.) will still work.  Drop those privileges if you want them gone.
+ *
+ * Changing LSM security domain is considered a new privilege.  So, for example,
+ * asking selinux for a specific new context (e.g. with runcon) will result
+ * in execve returning -EPERM.
+ */
+#define PR_SET_NO_NEW_PRIVS 38
+#define PR_GET_NO_NEW_PRIVS 39
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 5c719627c2aa..597e4fdb97fe 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -58,6 +58,7 @@
 #define PTRACE_EVENT_EXEC       4
 #define PTRACE_EVENT_VFORK_DONE 5
 #define PTRACE_EVENT_EXIT       6
+#define PTRACE_EVENT_SECCOMP    7
 /* Extended result codes which enabled by means other than options.  */
 #define PTRACE_EVENT_STOP       128
 
@@ -69,8 +70,9 @@
 #define PTRACE_O_TRACEEXEC      (1 << PTRACE_EVENT_EXEC)
 #define PTRACE_O_TRACEVFORKDONE (1 << PTRACE_EVENT_VFORK_DONE)
 #define PTRACE_O_TRACEEXIT      (1 << PTRACE_EVENT_EXIT)
+#define PTRACE_O_TRACESECCOMP   (1 << PTRACE_EVENT_SECCOMP)
 
-#define PTRACE_O_MASK           0x0000007f
+#define PTRACE_O_MASK           0x000000ff
 
 #include <asm/ptrace.h>
 
@@ -98,6 +100,7 @@
 #define PT_TRACE_EXEC           PT_EVENT_FLAG(PTRACE_EVENT_EXEC)
 #define PT_TRACE_VFORK_DONE     PT_EVENT_FLAG(PTRACE_EVENT_VFORK_DONE)
 #define PT_TRACE_EXIT           PT_EVENT_FLAG(PTRACE_EVENT_EXIT)
+#define PT_TRACE_SECCOMP        PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP)
 
 /* single stepping state bits (used on ARM and PA-RISC) */
 #define PT_SINGLESTEP_BIT       31
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8f3fd945070f..f774d88cd0aa 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1341,6 +1341,8 @@ struct task_struct {
                                  * execve */
         unsigned in_iowait:1;
 
+        /* task may not gain privileges */
+        unsigned no_new_privs:1;
 
         /* Revert to default priority/policy when forking */
         unsigned sched_reset_on_fork:1;
@@ -1450,7 +1452,7 @@ struct task_struct {
         uid_t loginuid;
         unsigned int sessionid;
 #endif
-        seccomp_t seccomp;
+        struct seccomp seccomp;
 
 /* Thread group tracking */
         u32 parent_exec_id;
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index cc7a4e9cc7ad..84f6320da50f 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -1,25 +1,90 @@
 #ifndef _LINUX_SECCOMP_H
 #define _LINUX_SECCOMP_H
 
-
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+
+/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */
+#define SECCOMP_MODE_DISABLED   0 /* seccomp is not in use. */
+#define SECCOMP_MODE_STRICT     1 /* uses hard-coded filter. */
+#define SECCOMP_MODE_FILTER     2 /* uses user-supplied filter. */
+
+/*
+ * All BPF programs must return a 32-bit value.
+ * The bottom 16-bits are for optional return data.
+ * The upper 16-bits are ordered from least permissive values to most.
+ *
+ * The ordering ensures that a min_t() over composed return values always
+ * selects the least permissive choice.
+ */
+#define SECCOMP_RET_KILL        0x00000000U /* kill the task immediately */
+#define SECCOMP_RET_TRAP        0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO       0x00050000U /* returns an errno */
+#define SECCOMP_RET_TRACE       0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_ALLOW       0x7fff0000U /* allow */
+
+/* Masks for the return value sections. */
+#define SECCOMP_RET_ACTION      0x7fff0000U
+#define SECCOMP_RET_DATA        0x0000ffffU
+
+/**
+ * struct seccomp_data - the format the BPF program executes over.
+ * @nr: the system call number
+ * @arch: indicates system call convention as an AUDIT_ARCH_* value
+ *        as defined in <linux/audit.h>.
+ * @instruction_pointer: at the time of the system call.
+ * @args: up to 6 system call arguments always stored as 64-bit values
+ *        regardless of the architecture.
+ */
+struct seccomp_data {
+        int nr;
+        __u32 arch;
+        __u64 instruction_pointer;
+        __u64 args[6];
+};
+
+#ifdef __KERNEL__
 #ifdef CONFIG_SECCOMP
 
 #include <linux/thread_info.h>
 #include <asm/seccomp.h>
 
-typedef struct { int mode; } seccomp_t;
-
-extern void __secure_computing(int);
-static inline void secure_computing(int this_syscall)
+struct seccomp_filter;
+/**
+ * struct seccomp - the state of a seccomp'ed process
+ *
+ * @mode:  indicates one of the valid values above for controlled
+ *         system calls available to a process.
+ * @filter: The metadata and ruleset for determining what system calls
+ *          are allowed for a task.
+ *
+ *          @filter must only be accessed from the context of current as there
+ *          is no locking.
+ */
+struct seccomp {
+        int mode;
+        struct seccomp_filter *filter;
+};
+
+extern int __secure_computing(int);
+static inline int secure_computing(int this_syscall)
 {
         if (unlikely(test_thread_flag(TIF_SECCOMP)))
-                __secure_computing(this_syscall);
+                return  __secure_computing(this_syscall);
+        return 0;
+}
+
+/* A wrapper for architectures supporting only SECCOMP_MODE_STRICT. */
+static inline void secure_computing_strict(int this_syscall)
+{
+        BUG_ON(secure_computing(this_syscall) != 0);
 }
 
 extern long prctl_get_seccomp(void);
-extern long prctl_set_seccomp(unsigned long);
+extern long prctl_set_seccomp(unsigned long, char __user *);
 
-static inline int seccomp_mode(seccomp_t *s)
+static inline int seccomp_mode(struct seccomp *s)
 {
         return s->mode;
 }
@@ -28,25 +93,41 @@ static inline int seccomp_mode(seccomp_t *s)
 
 #include <linux/errno.h>
 
-typedef struct { } seccomp_t;
+struct seccomp { };
+struct seccomp_filter { };
 
-#define secure_computing(x) do { } while (0)
+static inline int secure_computing(int this_syscall) { return 0; }
+static inline void secure_computing_strict(int this_syscall) { return; }
 
 static inline long prctl_get_seccomp(void)
 {
         return -EINVAL;
 }
 
-static inline long prctl_set_seccomp(unsigned long arg2)
+static inline long prctl_set_seccomp(unsigned long arg2, char __user *arg3)
 {
         return -EINVAL;
 }
 
-static inline int seccomp_mode(seccomp_t *s)
+static inline int seccomp_mode(struct seccomp *s)
 {
         return 0;
 }
-
 #endif /* CONFIG_SECCOMP */
 
+#ifdef CONFIG_SECCOMP_FILTER
+extern void put_seccomp_filter(struct task_struct *tsk);
+extern void get_seccomp_filter(struct task_struct *tsk);
+extern u32 seccomp_bpf_load(int off);
+#else  /* CONFIG_SECCOMP_FILTER */
+static inline void put_seccomp_filter(struct task_struct *tsk)
+{
+        return;
+}
+static inline void get_seccomp_filter(struct task_struct *tsk)
+{
+        return;
+}
+#endif /* CONFIG_SECCOMP_FILTER */
+#endif /* __KERNEL__ */
 #endif /* _LINUX_SECCOMP_H */
diff --git a/include/linux/security.h b/include/linux/security.h
index 673afbb8238a..ab0e091ce5fa 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -144,6 +144,7 @@ struct request_sock;
 #define LSM_UNSAFE_SHARE        1
 #define LSM_UNSAFE_PTRACE       2
 #define LSM_UNSAFE_PTRACE_CAP   4
+#define LSM_UNSAFE_NO_NEW_PRIVS 8
 
 #ifdef CONFIG_MMU
 extern int mmap_min_addr_handler(struct ctl_table *table, int write,
@@ -639,10 +640,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *      to receive an open file descriptor via socket IPC.
  *      @file contains the file structure being received.
  *      Return 0 if permission is granted.
- *
- * Security hook for dentry
- *
- * @dentry_open
+ * @file_open
  *      Save open-time permission checking state for later use upon
  *      file_permission, and recheck access if anything has changed
  *      since inode_permission.
@@ -1497,7 +1495,7 @@ struct security_operations {
         int (*file_send_sigiotask) (struct task_struct *tsk,
                                     struct fown_struct *fown, int sig);
         int (*file_receive) (struct file *file);
-        int (*dentry_open) (struct file *file, const struct cred *cred);
+        int (*file_open) (struct file *file, const struct cred *cred);
 
         int (*task_create) (unsigned long clone_flags);
         void (*task_free) (struct task_struct *task);
@@ -1756,7 +1754,7 @@ int security_file_set_fowner(struct file *file);
 int security_file_send_sigiotask(struct task_struct *tsk,
                                  struct fown_struct *fown, int sig);
 int security_file_receive(struct file *file);
-int security_dentry_open(struct file *file, const struct cred *cred);
+int security_file_open(struct file *file, const struct cred *cred);
 int security_task_create(unsigned long clone_flags);
 void security_task_free(struct task_struct *task);
 int security_cred_alloc_blank(struct cred *cred, gfp_t gfp);
@@ -2227,8 +2225,8 @@ static inline int security_file_receive(struct file *file)
         return 0;
 }
 
-static inline int security_dentry_open(struct file *file,
-                                       const struct cred *cred)
+static inline int security_file_open(struct file *file,
+                                     const struct cred *cred)
 {
         return 0;
 }