Merge tag 'fork-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull fork cleanups from Christian Brauner:
 "This is cleanup series from when we reworked a chunk of the process
  creation paths in the kernel and switched to struct
  {kernel_}clone_args.

  High-level this does two main things:

   - Remove the double export of both do_fork() and _do_fork() where
     do_fork() used the incosistent legacy clone calling convention.

     Now we only export _do_fork() which is based on struct
     kernel_clone_args.

   - Remove the copy_thread_tls()/copy_thread() split making the
     architecture specific HAVE_COYP_THREAD_TLS config option obsolete.

  This switches all remaining architectures to select
  HAVE_COPY_THREAD_TLS and thus to the copy_thread_tls() calling
  convention. The current split makes the process creation codepaths
  more convoluted than they need to be. Each architecture has their own
  copy_thread() function unless it selects HAVE_COPY_THREAD_TLS then it
  has a copy_thread_tls() function.

  The split is not needed anymore nowadays, all architectures support
  CLONE_SETTLS but quite a few of them never bothered to select
  HAVE_COPY_THREAD_TLS and instead simply continued to use copy_thread()
  and use the old calling convention. Removing this split cleans up the
  process creation codepaths and paves the way for implementing clone3()
  on such architectures since it requires the copy_thread_tls() calling
  convention.

  After having made each architectures support copy_thread_tls() this
  series simply renames that function back to copy_thread(). It also
  switches all architectures that call do_fork() directly over to
  _do_fork() and the struct kernel_clone_args calling convention. This
  is a corollary of switching the architectures that did not yet support
  it over to copy_thread_tls() since do_fork() is conditional on not
  supporting copy_thread_tls() (Mostly because it lacks a separate
  argument for tls which is trivial to fix but there's no need for this
  function to exist.).

  The do_fork() removal is in itself already useful as it allows to to
  remove the export of both do_fork() and _do_fork() we currently have
  in favor of only _do_fork(). This has already been discussed back when
  we added clone3(). The legacy clone() calling convention is - as is
  probably well-known - somewhat odd:

    #
    # ABI hall of shame
    #
    config CLONE_BACKWARDS
    config CLONE_BACKWARDS2
    config CLONE_BACKWARDS3

  that is aggravated by the fact that some architectures such as sparc
  follow the CLONE_BACKWARDSx calling convention but don't really select
  the corresponding config option since they call do_fork() directly.

  So do_fork() enforces a somewhat arbitrary calling convention in the
  first place that doesn't really help the individual architectures that
  deviate from it. They can thus simply be switched to _do_fork()
  enforcing a single calling convention. (I really hope that any new
  architectures will __not__ try to implement their own calling
  conventions...)

  Most architectures already have made a similar switch (m68k comes to
  mind).

  Overall this removes more code than it adds even with a good portion
  of added comments. It simplifies a chunk of arch specific assembly
  either by moving the code into C or by simply rewriting the assembly.

  Architectures that have been touched in non-trivial ways have all been
  actually boot and stress tested: sparc and ia64 have been tested with
  Debian 9 images. They are the two architectures which have been
  touched the most. All non-trivial changes to architectures have seen
  acks from the relevant maintainers. nios2 with a custom built
  buildroot image. h8300 I couldn't get something bootable to test on
  but the changes have been fairly automatic and I'm sure we'll hear
  people yell if I broke something there.

  All other architectures that have been touched in trivial ways have
  been compile tested for each single patch of the series via git rebase
  -x "make ..." v5.8-rc2. arm{64} and x86{_64} have been boot tested
  even though they have just been trivially touched (removal of the
  HAVE_COPY_THREAD_TLS macro from their Kconfig) because well they are
  basically "core architectures" and since it is trivial to get your
  hands on a useable image"

* tag 'fork-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  arch: rename copy_thread_tls() back to copy_thread()
  arch: remove HAVE_COPY_THREAD_TLS
  unicore: switch to copy_thread_tls()
  sh: switch to copy_thread_tls()
  nds32: switch to copy_thread_tls()
  microblaze: switch to copy_thread_tls()
  hexagon: switch to copy_thread_tls()
  c6x: switch to copy_thread_tls()
  alpha: switch to copy_thread_tls()
  fork: remove do_fork()
  h8300: select HAVE_COPY_THREAD_TLS, switch to kernel_clone_args
  nios2: enable HAVE_COPY_THREAD_TLS, switch to kernel_clone_args
  ia64: enable HAVE_COPY_THREAD_TLS, switch to kernel_clone_args
  sparc: unconditionally enable HAVE_COPY_THREAD_TLS
  sparc: share process creation helpers between sparc and sparc64
  sparc64: enable HAVE_COPY_THREAD_TLS
  fork: fold legacy_clone_args_valid() into _do_fork()

Author: torvalds

arch/Kconfig

@@ -754,13 +754,6 @@ config ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	depends on MMU
 	select ARCH_HAS_ELF_RANDOMIZE
 
-config HAVE_COPY_THREAD_TLS
-	bool
-	help
-	  Architecture provides copy_thread_tls to accept tls argument via
-	  normal C parameter passing, rather than extracting the syscall
-	  argument from pt_regs.
-
 config HAVE_STACK_VALIDATION
 	bool
 	help

arch/alpha/kernel/process.c

@@ -233,10 +233,9 @@ release_thread(struct task_struct *dead_task)
 /*
  * Copy architecture-specific thread state
  */
-int
-copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long kthread_arg,
-	    struct task_struct *p)
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+		unsigned long kthread_arg, struct task_struct *p,
+		unsigned long tls)
 {
 	extern void ret_from_fork(void);
 	extern void ret_from_kernel_thread(void);
@@ -267,7 +266,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 	   required for proper operation in the case of a threaded
 	   application calling fork.  */
 	if (clone_flags & CLONE_SETTLS)
-		childti->pcb.unique = regs->r20;
+		childti->pcb.unique = tls;
 	else
 		regs->r20 = 0;	/* OSF/1 has some strange fork() semantics.  */
 	childti->pcb.usp = usp ?: rdusp();

arch/arc/Kconfig

@@ -29,7 +29,6 @@ config ARC
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_FUTEX_CMPXCHG if FUTEX

arch/arc/kernel/process.c

@@ -173,8 +173,9 @@ asmlinkage void ret_from_fork(void);
  * |    user_r25    |
  * ------------------  <===== END of PAGE
  */
-int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
-	unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+		unsigned long kthread_arg, struct task_struct *p,
+		unsigned long tls)
 {
 	struct pt_regs *c_regs;        /* child's pt_regs */
 	unsigned long *childksp;       /* to unwind out of __switch_to() */

arch/arm/Kconfig

@@ -72,7 +72,6 @@ config ARM
 	select HAVE_ARM_SMCCC if CPU_V7
 	select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
 	select HAVE_CONTEXT_TRACKING
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK if !XIP_KERNEL
 	select HAVE_DMA_CONTIGUOUS if MMU

arch/arm/kernel/process.c

@@ -225,9 +225,8 @@ void release_thread(struct task_struct *dead_task)
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
-int
-copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long stack_start,
+		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);

arch/arm64/Kconfig

@@ -149,7 +149,6 @@ config ARM64
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_CONTEXT_TRACKING
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS

arch/arm64/kernel/process.c

@@ -375,7 +375,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 asmlinkage void ret_from_fork(void) asm("ret_from_fork");
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
+int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);

arch/c6x/kernel/process.c

@@ -105,8 +105,8 @@ void start_thread(struct pt_regs *regs, unsigned int pc, unsigned long usp)
  * Copy a new thread context in its stack.
  */
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long ustk_size,
-		struct task_struct *p)
+		unsigned long ustk_size, struct task_struct *p,
+		unsigned long tls)
 {
 	struct pt_regs *childregs;
 

arch/csky/Kconfig

@@ -38,7 +38,6 @@ config CSKY
 	select GX6605S_TIMER if CPU_CK610
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_AUDITSYSCALL
-	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS