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()

2 files changed, 36 insertions, 25 deletions

diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index c5efac285bc3..e98e3dafffd8 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -112,19 +112,16 @@ GLOBAL_ENTRY(sys_clone2)
 	.prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(8)
 	alloc r16=ar.pfs,8,2,6,0
 	DO_SAVE_SWITCH_STACK
-	adds r2=PT(R16)+IA64_SWITCH_STACK_SIZE+16,sp
 	mov loc0=rp
-	mov loc1=r16				// save ar.pfs across do_fork
+	mov loc1=r16                             // save ar.pfs across ia64_clone
 	.body
+	mov out0=in0
 	mov out1=in1
 	mov out2=in2
-	tbit.nz p6,p0=in0,CLONE_SETTLS_BIT
-	mov out3=in3	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
-	;;
-(p6)	st8 [r2]=in5				// store TLS in r16 for copy_thread()
-	mov out4=in4	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
-	mov out0=in0				// out0 = clone_flags
-	br.call.sptk.many rp=do_fork
+	mov out3=in3
+	mov out4=in4
+	mov out5=in5
+	br.call.sptk.many rp=ia64_clone
 .ret1:	.restore sp
 	adds sp=IA64_SWITCH_STACK_SIZE,sp	// pop the switch stack
 	mov ar.pfs=loc1
@@ -143,19 +140,16 @@ GLOBAL_ENTRY(sys_clone)
 	.prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(8)
 	alloc r16=ar.pfs,8,2,6,0
 	DO_SAVE_SWITCH_STACK
-	adds r2=PT(R16)+IA64_SWITCH_STACK_SIZE+16,sp
 	mov loc0=rp
-	mov loc1=r16				// save ar.pfs across do_fork
+	mov loc1=r16                             // save ar.pfs across ia64_clone
 	.body
+	mov out0=in0
 	mov out1=in1
 	mov out2=16				// stacksize (compensates for 16-byte scratch area)
-	tbit.nz p6,p0=in0,CLONE_SETTLS_BIT
-	mov out3=in2	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
-	;;
-(p6)	st8 [r2]=in4				// store TLS in r13 (tp)
-	mov out4=in3	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
-	mov out0=in0				// out0 = clone_flags
-	br.call.sptk.many rp=do_fork
+	mov out3=in3
+	mov out4=in4
+	mov out5=in5
+	br.call.sptk.many rp=ia64_clone
 .ret2:	.restore sp
 	adds sp=IA64_SWITCH_STACK_SIZE,sp	// pop the switch stack
 	mov ar.pfs=loc1
@@ -590,7 +584,7 @@ GLOBAL_ENTRY(ia64_ret_from_clone)
 	nop.i 0
 	/*
 	 * We need to call schedule_tail() to complete the scheduling process.
-	 * Called by ia64_switch_to() after do_fork()->copy_thread().  r8 contains the
+	 * Called by ia64_switch_to() after ia64_clone()->copy_thread().  r8 contains the
 	 * address of the previously executing task.
 	 */
 	br.call.sptk.many rp=ia64_invoke_schedule_tail
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index da55b41ae33e..7a4de9d994c5 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -296,7 +296,7 @@ ia64_load_extra (struct task_struct *task)
 		pfm_load_regs(task);
 
 	info = __this_cpu_read(pfm_syst_info);
-	if (info & PFM_CPUINFO_SYST_WIDE) 
+	if (info & PFM_CPUINFO_SYST_WIDE)
 		pfm_syst_wide_update_task(task, info, 1);
 #endif
 }
@@ -310,7 +310,7 @@ ia64_load_extra (struct task_struct *task)
  *
  *	<clone syscall>	        <some kernel call frames>
  *	sys_clone		   :
- *	do_fork			do_fork
+ *	_do_fork		_do_fork
  *	copy_thread		copy_thread
  *
  * This means that the stack layout is as follows:
@@ -333,9 +333,8 @@ ia64_load_extra (struct task_struct *task)
  * so there is nothing to worry about.
  */
 int
-copy_thread(unsigned long clone_flags,
-	     unsigned long user_stack_base, unsigned long user_stack_size,
-	     struct task_struct *p)
+copy_thread(unsigned long clone_flags, unsigned long user_stack_base,
+	    unsigned long user_stack_size, struct task_struct *p, unsigned long tls)
 {
 	extern char ia64_ret_from_clone;
 	struct switch_stack *child_stack, *stack;
@@ -416,7 +415,7 @@ copy_thread(unsigned long clone_flags,
 	rbs_size = stack->ar_bspstore - rbs;
 	memcpy((void *) child_rbs, (void *) rbs, rbs_size);
 	if (clone_flags & CLONE_SETTLS)
-		child_ptregs->r13 = regs->r16;	/* see sys_clone2() in entry.S */
+		child_ptregs->r13 = tls;
 	if (user_stack_base) {
 		child_ptregs->r12 = user_stack_base + user_stack_size - 16;
 		child_ptregs->ar_bspstore = user_stack_base;
@@ -441,6 +440,24 @@ copy_thread(unsigned long clone_flags,
 	return retval;
 }
 
+asmlinkage long ia64_clone(unsigned long clone_flags, unsigned long stack_start,
+			   unsigned long stack_size, unsigned long parent_tidptr,
+			   unsigned long child_tidptr, unsigned long tls)
+{
+	struct kernel_clone_args args = {
+		.flags		= (lower_32_bits(clone_flags) & ~CSIGNAL),
+		.pidfd		= (int __user *)parent_tidptr,
+		.child_tid	= (int __user *)child_tidptr,
+		.parent_tid	= (int __user *)parent_tidptr,
+		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
+		.stack		= stack_start,
+		.stack_size	= stack_size,
+		.tls		= tls,
+	};
+
+	return _do_fork(&args);
+}
+
 static void
 do_copy_task_regs (struct task_struct *task, struct unw_frame_info *info, void *arg)
 {