ptrace,seccomp: Add PTRACE_SECCOMP support

This change adds support for a new ptrace option, PTRACE_O_TRACESECCOMP,
and a new return value for seccomp BPF programs, SECCOMP_RET_TRACE.

When a tracer specifies the PTRACE_O_TRACESECCOMP ptrace option, the
tracer will be notified, via PTRACE_EVENT_SECCOMP, for any syscall that
results in a BPF program returning SECCOMP_RET_TRACE.  The 16-bit
SECCOMP_RET_DATA mask of the BPF program return value will be passed as
the ptrace_message and may be retrieved using PTRACE_GETEVENTMSG.

If the subordinate process is not using seccomp filter, then no
system call notifications will occur even if the option is specified.

If there is no tracer with PTRACE_O_TRACESECCOMP when SECCOMP_RET_TRACE
is returned, the system call will not be executed and an -ENOSYS errno
will be returned to userspace.

This change adds a dependency on the system call slow path.  Any future
efforts to use the system call fast path for seccomp filter will need to
address this restriction.

Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>

v18: - rebase
     - comment fatal_signal check
     - acked-by
     - drop secure_computing_int comment
v17: - ...
v16: - update PT_TRACE_MASK to 0xbf4 so that STOP isn't clear on SETOPTIONS call (indan@nul.nu)
       [note PT_TRACE_MASK disappears in linux-next]
v15: - add audit support for non-zero return codes
     - clean up style (indan@nul.nu)
v14: - rebase/nochanges
v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc
       (Brings back a change to ptrace.c and the masks.)
v12: - rebase to linux-next
     - use ptrace_event and update arch/Kconfig to mention slow-path dependency
     - drop all tracehook changes and inclusion (oleg@redhat.com)
v11: - invert the logic to just make it a PTRACE_SYSCALL accelerator
       (indan@nul.nu)
v10: - moved to PTRACE_O_SECCOMP / PT_TRACE_SECCOMP
v9:  - n/a
v8:  - guarded PTRACE_SECCOMP use with an ifdef
v7:  - introduced
Signed-off-by: James Morris <james.l.morris@oracle.com>

4 files changed, 26 insertions, 6 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 66aef13f6038..c024b3ed6675 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -219,15 +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:
-          asm/syscall.h:
+          An arch should select this symbol if it provides all of these things:
           - syscall_get_arch()
           - syscall_get_arguments()
           - 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.
+          - SIGSYS siginfo_t support
+          - secure_computing is called from a ptrace_event()-safe context
+          - secure_computing return value is checked and a return value of -1
+            results in the system call being skipped immediately.
 
 config SECCOMP_FILTER
         def_bool y
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/seccomp.h b/include/linux/seccomp.h
index 317ccb78cf40..5818e869651b 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -21,6 +21,7 @@
 #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. */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 9c3830692a08..d9db6ec46bc9 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -24,6 +24,7 @@
 #ifdef CONFIG_SECCOMP_FILTER
 #include <asm/syscall.h>
 #include <linux/filter.h>
+#include <linux/ptrace.h>
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/tracehook.h>
@@ -408,6 +409,21 @@ int __secure_computing(int this_syscall)
                         /* Let the filter pass back 16 bits of data. */
                         seccomp_send_sigsys(this_syscall, data);
                         goto skip;
+                case SECCOMP_RET_TRACE:
+                        /* Skip these calls if there is no tracer. */
+                        if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP))
+                                goto skip;
+                        /* Allow the BPF to provide the event message */
+                        ptrace_event(PTRACE_EVENT_SECCOMP, data);
+                        /*
+                         * The delivery of a fatal signal during event
+                         * notification may silently skip tracer notification.
+                         * Terminating the task now avoids executing a system
+                         * call that may not be intended.
+                         */
+                        if (fatal_signal_pending(current))
+                                break;
+                        return 0;
                 case SECCOMP_RET_ALLOW:
                         return 0;
                 case SECCOMP_RET_KILL: