6 files changed, 472 insertions, 23 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 684eb5af439d..91c2c730fc1a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -216,4 +216,21 @@ config HAVE_CMPXCHG_DOUBLE
 config ARCH_WANT_OLD_COMPAT_IPC
         bool
 
+config HAVE_ARCH_SECCOMP_FILTER
+        bool
+        help
+          This symbol should be selected by an architecure if it provides
+          asm/syscall.h, specifically syscall_get_arguments() and
+          syscall_get_arch().
+
+config SECCOMP_FILTER
+        def_bool y
+        depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
+        help
+          Enable tasks to build secure computing environments defined
+          in terms of Berkeley Packet Filter programs which implement
+          task-defined system call filtering polices.
+
+          See Documentation/prctl/seccomp_filter.txt for details.
+
 source "kernel/gcov/Kconfig"
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 3c9b616c834a..5c93d6c5d591 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -332,6 +332,7 @@ 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/seccomp.h b/include/linux/seccomp.h
index d61f27fcaa97..86bb68fc7683 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -1,14 +1,67 @@
 #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 reserved for future use.
+ * 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_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>
 
+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 void __secure_computing(int);
@@ -19,7 +72,7 @@ static inline void secure_computing(int this_syscall)
 }
 
 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(struct seccomp *s)
 {
@@ -31,15 +84,16 @@ static inline int seccomp_mode(struct seccomp *s)
 #include <linux/errno.h>
 
 struct seccomp { };
+struct seccomp_filter { };
 
-#define secure_computing(x) do { } while (0)
+#define secure_computing(x) 0
 
 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;
 }
@@ -48,7 +102,21 @@ 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/kernel/fork.c b/kernel/fork.c
index b9372a0bff18..f7cf6fb107ec 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -34,6 +34,7 @@
 #include <linux/cgroup.h>
 #include <linux/security.h>
 #include <linux/hugetlb.h>
+#include <linux/seccomp.h>
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
@@ -170,6 +171,7 @@ void free_task(struct task_struct *tsk)
         free_thread_info(tsk->stack);
         rt_mutex_debug_task_free(tsk);
         ftrace_graph_exit_task(tsk);
+        put_seccomp_filter(tsk);
         free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -1162,6 +1164,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 goto fork_out;
 
         ftrace_graph_init_task(p);
+        get_seccomp_filter(p);
 
         rt_mutex_init_task(p);
 
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index e8d76c5895ea..0aeec1960f91 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -3,16 +3,343 @@
  *
  * Copyright 2004-2005  Andrea Arcangeli <andrea@cpushare.com>
  *
- * This defines a simple but solid secure-computing mode.
+ * Copyright (C) 2012 Google, Inc.
+ * Will Drewry <wad@chromium.org>
+ *
+ * This defines a simple but solid secure-computing facility.
+ *
+ * Mode 1 uses a fixed list of allowed system calls.
+ * Mode 2 allows user-defined system call filters in the form
+ *        of Berkeley Packet Filters/Linux Socket Filters.
  */
 
+#include <linux/atomic.h>
 #include <linux/audit.h>
-#include <linux/seccomp.h>
-#include <linux/sched.h>
 #include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/seccomp.h>
 
 /* #define SECCOMP_DEBUG 1 */
-#define NR_SECCOMP_MODES 1
+
+#ifdef CONFIG_SECCOMP_FILTER
+#include <asm/syscall.h>
+#include <linux/filter.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/tracehook.h>
+#include <linux/uaccess.h>
+
+/**
+ * struct seccomp_filter - container for seccomp BPF programs
+ *
+ * @usage: reference count to manage the object lifetime.
+ *         get/put helpers should be used when accessing an instance
+ *         outside of a lifetime-guarded section.  In general, this
+ *         is only needed for handling filters shared across tasks.
+ * @prev: points to a previously installed, or inherited, filter
+ * @len: the number of instructions in the program
+ * @insns: the BPF program instructions to evaluate
+ *
+ * seccomp_filter objects are organized in a tree linked via the @prev
+ * pointer.  For any task, it appears to be a singly-linked list starting
+ * with current->seccomp.filter, the most recently attached or inherited filter.
+ * However, multiple filters may share a @prev node, by way of fork(), which
+ * results in a unidirectional tree existing in memory.  This is similar to
+ * how namespaces work.
+ *
+ * seccomp_filter objects should never be modified after being attached
+ * to a task_struct (other than @usage).
+ */
+struct seccomp_filter {
+        atomic_t usage;
+        struct seccomp_filter *prev;
+        unsigned short len;  /* Instruction count */
+        struct sock_filter insns[];
+};
+
+/* Limit any path through the tree to 256KB worth of instructions. */
+#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
+
+static void seccomp_filter_log_failure(int syscall)
+{
+        int compat = 0;
+#ifdef CONFIG_COMPAT
+        compat = is_compat_task();
+#endif
+        pr_info("%s[%d]: %ssystem call %d blocked at 0x%lx\n",
+                current->comm, task_pid_nr(current),
+                (compat ? "compat " : ""),
+                syscall, KSTK_EIP(current));
+}
+
+/**
+ * get_u32 - returns a u32 offset into data
+ * @data: a unsigned 64 bit value
+ * @index: 0 or 1 to return the first or second 32-bits
+ *
+ * This inline exists to hide the length of unsigned long.  If a 32-bit
+ * unsigned long is passed in, it will be extended and the top 32-bits will be
+ * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
+ * properly returned.
+ *
+ * Endianness is explicitly ignored and left for BPF program authors to manage
+ * as per the specific architecture.
+ */
+static inline u32 get_u32(u64 data, int index)
+{
+        return ((u32 *)&data)[index];
+}
+
+/* Helper for bpf_load below. */
+#define BPF_DATA(_name) offsetof(struct seccomp_data, _name)
+/**
+ * bpf_load: checks and returns a pointer to the requested offset
+ * @off: offset into struct seccomp_data to load from
+ *
+ * Returns the requested 32-bits of data.
+ * seccomp_check_filter() should assure that @off is 32-bit aligned
+ * and not out of bounds.  Failure to do so is a BUG.
+ */
+u32 seccomp_bpf_load(int off)
+{
+        struct pt_regs *regs = task_pt_regs(current);
+        if (off == BPF_DATA(nr))
+                return syscall_get_nr(current, regs);
+        if (off == BPF_DATA(arch))
+                return syscall_get_arch(current, regs);
+        if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) {
+                unsigned long value;
+                int arg = (off - BPF_DATA(args[0])) / sizeof(u64);
+                int index = !!(off % sizeof(u64));
+                syscall_get_arguments(current, regs, arg, 1, &value);
+                return get_u32(value, index);
+        }
+        if (off == BPF_DATA(instruction_pointer))
+                return get_u32(KSTK_EIP(current), 0);
+        if (off == BPF_DATA(instruction_pointer) + sizeof(u32))
+                return get_u32(KSTK_EIP(current), 1);
+        /* seccomp_check_filter should make this impossible. */
+        BUG();
+}
+
+/**
+ *      seccomp_check_filter - verify seccomp filter code
+ *      @filter: filter to verify
+ *      @flen: length of filter
+ *
+ * Takes a previously checked filter (by sk_chk_filter) and
+ * redirects all filter code that loads struct sk_buff data
+ * and related data through seccomp_bpf_load.  It also
+ * enforces length and alignment checking of those loads.
+ *
+ * Returns 0 if the rule set is legal or -EINVAL if not.
+ */
+static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
+{
+        int pc;
+        for (pc = 0; pc < flen; pc++) {
+                struct sock_filter *ftest = &filter[pc];
+                u16 code = ftest->code;
+                u32 k = ftest->k;
+
+                switch (code) {
+                case BPF_S_LD_W_ABS:
+                        ftest->code = BPF_S_ANC_SECCOMP_LD_W;
+                        /* 32-bit aligned and not out of bounds. */
+                        if (k >= sizeof(struct seccomp_data) || k & 3)
+                                return -EINVAL;
+                        continue;
+                case BPF_S_LD_W_LEN:
+                        ftest->code = BPF_S_LD_IMM;
+                        ftest->k = sizeof(struct seccomp_data);
+                        continue;
+                case BPF_S_LDX_W_LEN:
+                        ftest->code = BPF_S_LDX_IMM;
+                        ftest->k = sizeof(struct seccomp_data);
+                        continue;
+                /* Explicitly include allowed calls. */
+                case BPF_S_RET_K:
+                case BPF_S_RET_A:
+                case BPF_S_ALU_ADD_K:
+                case BPF_S_ALU_ADD_X:
+                case BPF_S_ALU_SUB_K:
+                case BPF_S_ALU_SUB_X:
+                case BPF_S_ALU_MUL_K:
+                case BPF_S_ALU_MUL_X:
+                case BPF_S_ALU_DIV_X:
+                case BPF_S_ALU_AND_K:
+                case BPF_S_ALU_AND_X:
+                case BPF_S_ALU_OR_K:
+                case BPF_S_ALU_OR_X:
+                case BPF_S_ALU_LSH_K:
+                case BPF_S_ALU_LSH_X:
+                case BPF_S_ALU_RSH_K:
+                case BPF_S_ALU_RSH_X:
+                case BPF_S_ALU_NEG:
+                case BPF_S_LD_IMM:
+                case BPF_S_LDX_IMM:
+                case BPF_S_MISC_TAX:
+                case BPF_S_MISC_TXA:
+                case BPF_S_ALU_DIV_K:
+                case BPF_S_LD_MEM:
+                case BPF_S_LDX_MEM:
+                case BPF_S_ST:
+                case BPF_S_STX:
+                case BPF_S_JMP_JA:
+                case BPF_S_JMP_JEQ_K:
+                case BPF_S_JMP_JEQ_X:
+                case BPF_S_JMP_JGE_K:
+                case BPF_S_JMP_JGE_X:
+                case BPF_S_JMP_JGT_K:
+                case BPF_S_JMP_JGT_X:
+                case BPF_S_JMP_JSET_K:
+                case BPF_S_JMP_JSET_X:
+                        continue;
+                default:
+                        return -EINVAL;
+                }
+        }
+        return 0;
+}
+
+/**
+ * seccomp_run_filters - evaluates all seccomp filters against @syscall
+ * @syscall: number of the current system call
+ *
+ * Returns valid seccomp BPF response codes.
+ */
+static u32 seccomp_run_filters(int syscall)
+{
+        struct seccomp_filter *f;
+        u32 ret = SECCOMP_RET_KILL;
+        /*
+         * All filters in the list are evaluated and the lowest BPF return
+         * value always takes priority.
+         */
+        for (f = current->seccomp.filter; f; f = f->prev) {
+                ret = sk_run_filter(NULL, f->insns);
+                if (ret != SECCOMP_RET_ALLOW)
+                        break;
+        }
+        return ret;
+}
+
+/**
+ * seccomp_attach_filter: Attaches a seccomp filter to current.
+ * @fprog: BPF program to install
+ *
+ * Returns 0 on success or an errno on failure.
+ */
+static long seccomp_attach_filter(struct sock_fprog *fprog)
+{
+        struct seccomp_filter *filter;
+        unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
+        unsigned long total_insns = fprog->len;
+        long ret;
+
+        if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
+                return -EINVAL;
+
+        for (filter = current->seccomp.filter; filter; filter = filter->prev)
+                total_insns += filter->len + 4;  /* include a 4 instr penalty */
+        if (total_insns > MAX_INSNS_PER_PATH)
+                return -ENOMEM;
+
+        /*
+         * Installing a seccomp filter requires that the task have
+         * CAP_SYS_ADMIN in its namespace or be running with no_new_privs.
+         * This avoids scenarios where unprivileged tasks can affect the
+         * behavior of privileged children.
+         */
+        if (!current->no_new_privs &&
+            security_capable_noaudit(current_cred(), current_user_ns(),
+                                     CAP_SYS_ADMIN) != 0)
+                return -EACCES;
+
+        /* Allocate a new seccomp_filter */
+        filter = kzalloc(sizeof(struct seccomp_filter) + fp_size,
+                         GFP_KERNEL|__GFP_NOWARN);
+        if (!filter)
+                return -ENOMEM;
+        atomic_set(&filter->usage, 1);
+        filter->len = fprog->len;
+
+        /* Copy the instructions from fprog. */
+        ret = -EFAULT;
+        if (copy_from_user(filter->insns, fprog->filter, fp_size))
+                goto fail;
+
+        /* Check and rewrite the fprog via the skb checker */
+        ret = sk_chk_filter(filter->insns, filter->len);
+        if (ret)
+                goto fail;
+
+        /* Check and rewrite the fprog for seccomp use */
+        ret = seccomp_check_filter(filter->insns, filter->len);
+        if (ret)
+                goto fail;
+
+        /*
+         * If there is an existing filter, make it the prev and don't drop its
+         * task reference.
+         */
+        filter->prev = current->seccomp.filter;
+        current->seccomp.filter = filter;
+        return 0;
+fail:
+        kfree(filter);
+        return ret;
+}
+
+/**
+ * seccomp_attach_user_filter - attaches a user-supplied sock_fprog
+ * @user_filter: pointer to the user data containing a sock_fprog.
+ *
+ * Returns 0 on success and non-zero otherwise.
+ */
+long seccomp_attach_user_filter(char __user *user_filter)
+{
+        struct sock_fprog fprog;
+        long ret = -EFAULT;
+
+#ifdef CONFIG_COMPAT
+        if (is_compat_task()) {
+                struct compat_sock_fprog fprog32;
+                if (copy_from_user(&fprog32, user_filter, sizeof(fprog32)))
+                        goto out;
+                fprog.len = fprog32.len;
+                fprog.filter = compat_ptr(fprog32.filter);
+        } else /* falls through to the if below. */
+#endif
+        if (copy_from_user(&fprog, user_filter, sizeof(fprog)))
+                goto out;
+        ret = seccomp_attach_filter(&fprog);
+out:
+        return ret;
+}
+
+/* get_seccomp_filter - increments the reference count of the filter on @tsk */
+void get_seccomp_filter(struct task_struct *tsk)
+{
+        struct seccomp_filter *orig = tsk->seccomp.filter;
+        if (!orig)
+                return;
+        /* Reference count is bounded by the number of total processes. */
+        atomic_inc(&orig->usage);
+}
+
+/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
+void put_seccomp_filter(struct task_struct *tsk)
+{
+        struct seccomp_filter *orig = tsk->seccomp.filter;
+        /* Clean up single-reference branches iteratively. */
+        while (orig && atomic_dec_and_test(&orig->usage)) {
+                struct seccomp_filter *freeme = orig;
+                orig = orig->prev;
+                kfree(freeme);
+        }
+}
+#endif  /* CONFIG_SECCOMP_FILTER */
 
 /*
  * Secure computing mode 1 allows only read/write/exit/sigreturn.
@@ -34,10 +361,11 @@ static int mode1_syscalls_32[] = {
 void __secure_computing(int this_syscall)
 {
         int mode = current->seccomp.mode;
-        int * syscall;
+        int exit_sig = 0;
+        int *syscall;
 
         switch (mode) {
-        case 1:
+        case SECCOMP_MODE_STRICT:
                 syscall = mode1_syscalls;
 #ifdef CONFIG_COMPAT
                 if (is_compat_task())
@@ -47,7 +375,16 @@ void __secure_computing(int this_syscall)
                         if (*syscall == this_syscall)
                                 return;
                 } while (*++syscall);
+                exit_sig = SIGKILL;
                 break;
+#ifdef CONFIG_SECCOMP_FILTER
+        case SECCOMP_MODE_FILTER:
+                if (seccomp_run_filters(this_syscall) == SECCOMP_RET_ALLOW)
+                        return;
+                seccomp_filter_log_failure(this_syscall);
+                exit_sig = SIGSYS;
+                break;
+#endif
         default:
                 BUG();
         }
@@ -56,7 +393,7 @@ void __secure_computing(int this_syscall)
         dump_stack();
 #endif
         audit_seccomp(this_syscall);
-        do_exit(SIGKILL);
+        do_exit(exit_sig);
 }
 
 long prctl_get_seccomp(void)
@@ -64,25 +401,48 @@ long prctl_get_seccomp(void)
         return current->seccomp.mode;
 }
 
-long prctl_set_seccomp(unsigned long seccomp_mode)
+/**
+ * prctl_set_seccomp: configures current->seccomp.mode
+ * @seccomp_mode: requested mode to use
+ * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
+ *
+ * This function may be called repeatedly with a @seccomp_mode of
+ * SECCOMP_MODE_FILTER to install additional filters.  Every filter
+ * successfully installed will be evaluated (in reverse order) for each system
+ * call the task makes.
+ *
+ * Once current->seccomp.mode is non-zero, it may not be changed.
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
 {
-        long ret;
+        long ret = -EINVAL;
 
-        /* can set it only once to be even more secure */
-        ret = -EPERM;
-        if (unlikely(current->seccomp.mode))
+        if (current->seccomp.mode &&
+            current->seccomp.mode != seccomp_mode)
                 goto out;
 
-        ret = -EINVAL;
-        if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) {
-                current->seccomp.mode = seccomp_mode;
-                set_thread_flag(TIF_SECCOMP);
+        switch (seccomp_mode) {
+        case SECCOMP_MODE_STRICT:
+                ret = 0;
 #ifdef TIF_NOTSC
                 disable_TSC();
 #endif
-                ret = 0;
+                break;
+#ifdef CONFIG_SECCOMP_FILTER
+        case SECCOMP_MODE_FILTER:
+                ret = seccomp_attach_user_filter(filter);
+                if (ret)
+                        goto out;
+                break;
+#endif
+        default:
+                goto out;
         }
 
- out:
+        current->seccomp.mode = seccomp_mode;
+        set_thread_flag(TIF_SECCOMP);
+out:
         return ret;
 }
diff --git a/kernel/sys.c b/kernel/sys.c
index b82568b7d201..ba0ae8eea6fb 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1908,7 +1908,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
                         error = prctl_get_seccomp();
                         break;
                 case PR_SET_SECCOMP:
-                        error = prctl_set_seccomp(arg2);
+                        error = prctl_set_seccomp(arg2, (char __user *)arg3);
                         break;
                 case PR_GET_TSC:
                         error = GET_TSC_CTL(arg2);