Merge tag 'seccomp-v5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull seccomp updates from Kees Cook:
 "The bulk of the changes are with the seccomp selftests to accommodate
  some powerpc-specific behavioral characteristics. Additional cleanups,
  fixes, and improvements are also included:

   - heavily refactor seccomp selftests (and clone3 selftests
     dependency) to fix powerpc (Kees Cook, Thadeu Lima de Souza
     Cascardo)

   - fix style issue in selftests (Zou Wei)

   - upgrade "unknown action" from KILL_THREAD to KILL_PROCESS (Rich
     Felker)

   - replace task_pt_regs(current) with current_pt_regs() (Denis
     Efremov)

   - fix corner-case race in USER_NOTIF (Jann Horn)

   - make CONFIG_SECCOMP no longer per-arch (YiFei Zhu)"

* tag 'seccomp-v5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux: (23 commits)
  seccomp: Make duplicate listener detection non-racy
  seccomp: Move config option SECCOMP to arch/Kconfig
  selftests/clone3: Avoid OS-defined clone_args
  selftests/seccomp: powerpc: Set syscall return during ptrace syscall exit
  selftests/seccomp: Allow syscall nr and ret value to be set separately
  selftests/seccomp: Record syscall during ptrace entry
  selftests/seccomp: powerpc: Fix seccomp return value testing
  selftests/seccomp: Remove SYSCALL_NUM_RET_SHARE_REG in favor of SYSCALL_RET_SET
  selftests/seccomp: Avoid redundant register flushes
  selftests/seccomp: Convert REGSET calls into ARCH_GETREG/ARCH_SETREG
  selftests/seccomp: Convert HAVE_GETREG into ARCH_GETREG/ARCH_SETREG
  selftests/seccomp: Remove syscall setting #ifdefs
  selftests/seccomp: mips: Remove O32-specific macro
  selftests/seccomp: arm64: Define SYSCALL_NUM_SET macro
  selftests/seccomp: arm: Define SYSCALL_NUM_SET macro
  selftests/seccomp: mips: Define SYSCALL_NUM_SET macro
  selftests/seccomp: Provide generic syscall setting macro
  selftests/seccomp: Refactor arch register macros to avoid xtensa special case
  selftests/seccomp: Use __NR_mknodat instead of __NR_mknod
  selftests/seccomp: Use bitwise instead of arithmetic operator for flags
  ...

Author: torvalds

arch/Kconfig

@@ -450,10 +450,23 @@ config ARCH_WANT_OLD_COMPAT_IPC
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	bool
 
+config HAVE_ARCH_SECCOMP
+	bool
+	help
+	  An arch should select this symbol to support seccomp mode 1 (the fixed
+	  syscall policy), and must provide an overrides for __NR_seccomp_sigreturn,
+	  and compat syscalls if the asm-generic/seccomp.h defaults need adjustment:
+	  - __NR_seccomp_read_32
+	  - __NR_seccomp_write_32
+	  - __NR_seccomp_exit_32
+	  - __NR_seccomp_sigreturn_32
+
 config HAVE_ARCH_SECCOMP_FILTER
 	bool
+	select HAVE_ARCH_SECCOMP
 	help
 	  An arch should select this symbol if it provides all of these things:
+	  - all the requirements for HAVE_ARCH_SECCOMP
 	  - syscall_get_arch()
 	  - syscall_get_arguments()
 	  - syscall_rollback()
@@ -464,6 +477,23 @@ config HAVE_ARCH_SECCOMP_FILTER
 	    results in the system call being skipped immediately.
 	  - seccomp syscall wired up
 
+config SECCOMP
+	prompt "Enable seccomp to safely execute untrusted bytecode"
+	def_bool y
+	depends on HAVE_ARCH_SECCOMP
+	help
+	  This kernel feature is useful for number crunching applications
+	  that may need to handle untrusted bytecode during their
+	  execution. By using pipes or other transports made available
+	  to the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in their
+	  own address space using seccomp. Once seccomp is enabled via
+	  prctl(PR_SET_SECCOMP) or the seccomp() syscall, it cannot be
+	  disabled and the task is only allowed to execute a few safe
+	  syscalls defined by each seccomp mode.
+
+	  If unsure, say Y.
+
 config SECCOMP_FILTER
 	def_bool y
 	depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET

arch/arm/Kconfig

@@ -68,6 +68,7 @@ config ARM
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
+	select HAVE_ARCH_SECCOMP
 	select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
@@ -1618,20 +1619,6 @@ config UACCESS_WITH_MEMCPY
 	  However, if the CPU data cache is using a write-allocate mode,
 	  this option is unlikely to provide any performance gain.
 
-config SECCOMP
-	bool
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
 config PARAVIRT
 	bool "Enable paravirtualization code"
 	help

arch/arm64/Kconfig

@@ -1041,19 +1041,6 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 config CC_HAVE_SHADOW_CALL_STACK
 	def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18)
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
 config PARAVIRT
 	bool "Enable paravirtualization code"
 	help

arch/csky/Kconfig

@@ -309,16 +309,3 @@ endmenu
 source "arch/csky/Kconfig.platforms"
 
 source "kernel/Kconfig.hz"
-
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.

arch/microblaze/Kconfig

@@ -26,6 +26,7 @@ config MICROBLAZE
 	select GENERIC_SCHED_CLOCK
 	select HAVE_ARCH_HASH
 	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
@@ -120,23 +121,6 @@ config CMDLINE_FORCE
 	  Set this to have arguments from the default kernel command string
 	  override those passed by the boot loader.
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 endmenu
 
 menu "Kernel features"

arch/mips/Kconfig

@@ -3006,23 +3006,6 @@ config PHYSICAL_START
 	  specified in the "crashkernel=YM@XM" command line boot parameter
 	  passed to the panic-ed kernel).
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 config MIPS_O32_FP64_SUPPORT
 	bool "Support for O32 binaries using 64-bit FP" if !CPU_MIPSR6
 	depends on 32BIT || MIPS32_O32

arch/parisc/Kconfig

@@ -378,19 +378,3 @@ endmenu
 
 
 source "drivers/parisc/Kconfig"
-
-config SECCOMP
-	def_bool y
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.

arch/powerpc/Kconfig

@@ -946,23 +946,6 @@ config ARCH_WANTS_FREEZER_CONTROL
 
 source "kernel/power/Kconfig"
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 config PPC_MEM_KEYS
 	prompt "PowerPC Memory Protection Keys"
 	def_bool y

arch/riscv/Kconfig

@@ -334,19 +334,6 @@ menu "Kernel features"
 
 source "kernel/Kconfig.hz"
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
 config RISCV_SBI_V01
 	bool "SBI v0.1 support"
 	default y

arch/s390/Kconfig

@@ -792,23 +792,6 @@ config CRASH_DUMP
 
 endmenu
 
-config SECCOMP
-	def_bool y
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y.
-
 config CCW
 	def_bool y