seccomp: Add SECCOMP_RET_TRAP

Adds a new return value to seccomp filters that triggers a SIGSYS to be
delivered with the new SYS_SECCOMP si_code.

This allows in-process system call emulation, including just specifying
an errno or cleanly dumping core, rather than just dying.

Suggested-by: Markus Gutschke <markus@chromium.org>
Suggested-by: Julien Tinnes <jln@chromium.org>
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>

v18: - acked-by, rebase
     - don't mention secure_computing_int() anymore
v15: - use audit_seccomp/skip
     - pad out error spacing; clean up switch (indan@nul.nu)
v14: - n/a
v13: - rebase on to 88ebdda615
v12: - rebase on to linux-next
v11: - clarify the comment (indan@nul.nu)
     - s/sigtrap/sigsys
v10: - use SIGSYS, syscall_get_arch, updates arch/Kconfig
       note suggested-by (though original suggestion had other behaviors)
v9:  - changes to SIGILL
v8:  - clean up based on changes to dependent patches
v7:  - introduction
Signed-off-by: James Morris <james.l.morris@oracle.com>

arch/Kconfig

@@ -219,11 +219,15 @@ config ARCH_WANT_OLD_COMPAT_IPC
 config HAVE_ARCH_SECCOMP_FILTER
 	bool
 	help
-	  This symbol should be selected by an architecure if it provides
+	  This symbol should be selected by an architecure if it provides:
-	  asm/syscall.h, specifically syscall_get_arguments(),
+	  asm/syscall.h:
-	  syscall_get_arch(), and syscall_set_return_value().  Additionally,
+	  - syscall_get_arch()
-	  its system call entry path must respect a return value of -1 from
+	  - syscall_get_arguments()
-	  __secure_computing() and/or secure_computing().
+	  - syscall_rollback()
+	  - syscall_set_return_value()
+	  SIGSYS siginfo_t support must be implemented.
+	  __secure_computing()/secure_computing()'s return value must be
+	  checked, with -1 resulting in the syscall being skipped.
 
 config SECCOMP_FILTER
 	def_bool y

include/asm-generic/siginfo.h

@@ -93,7 +93,7 @@ typedef struct siginfo {
 
 		/* SIGSYS */
 		struct {
-			void __user *_call_addr; /* calling insn */
+			void __user *_call_addr; /* calling user insn */
 			int _syscall;	/* triggering system call number */
 			unsigned int _arch;	/* AUDIT_ARCH_* of syscall */
 		} _sigsys;

include/linux/seccomp.h

@@ -19,6 +19,7 @@
  * 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_ALLOW	0x7fff0000U /* allow */
 

kernel/seccomp.c

@@ -332,6 +332,26 @@ void put_seccomp_filter(struct task_struct *tsk)
 		kfree(freeme);
 	}
 }
+
+/**
+ * seccomp_send_sigsys - signals the task to allow in-process syscall emulation
+ * @syscall: syscall number to send to userland
+ * @reason: filter-supplied reason code to send to userland (via si_errno)
+ *
+ * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
+ */
+static void seccomp_send_sigsys(int syscall, int reason)
+{
+	struct siginfo info;
+	memset(&info, 0, sizeof(info));
+	info.si_signo = SIGSYS;
+	info.si_code = SYS_SECCOMP;
+	info.si_call_addr = (void __user *)KSTK_EIP(current);
+	info.si_errno = reason;
+	info.si_arch = syscall_get_arch(current, task_pt_regs(current));
+	info.si_syscall = syscall;
+	force_sig_info(SIGSYS, &info, current);
+}
 #endif	/* CONFIG_SECCOMP_FILTER */
 
 /*
@@ -382,6 +402,12 @@ int __secure_computing(int this_syscall)
 			syscall_set_return_value(current, task_pt_regs(current),
 						 -data, 0);
 			goto skip;
+		case SECCOMP_RET_TRAP:
+			/* Show the handler the original registers. */
+			syscall_rollback(current, task_pt_regs(current));
+			/* Let the filter pass back 16 bits of data. */
+			seccomp_send_sigsys(this_syscall, data);
+			goto skip;
 		case SECCOMP_RET_ALLOW:
 			return 0;
 		case SECCOMP_RET_KILL: