parisc: optimizations in copy_thread() and friends

* in user thread case the registers had been copied as part of task_struct
already; no need to do it in copy_thread().
* no need to store kernel stack pointer into regs->r21; we know its offset
anyway.
* no need to clobber r3 in sys_fork_wrapper and friends - r28 will do just
as well and *it* will be overwritten anyway.
* no need to mess with storing the return address for child - it should just
use syscall_exit.
* no need to bother with separate stack frame for sys_clone() - just branch
there and be done with that.
* no need to bother with wrapper_exit - we need it only on the child_return,
so let's just do it there.
* use the same ksp for kernel threads and userland ones, while we are at it,
and let ret_from_kernel_execve() go through the normal syscall_exit.  More
straightforward is better here...

[fixes from jejb folded]

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

2 files changed, 27 insertions, 87 deletions

diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 7d22e97347b7..47fb6ddcf12e 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -719,7 +719,7 @@ ENTRY(ret_from_kernel_thread)
         BL      schedule_tail, %r2
         nop
 
-        LDREG   TI_TASK-THREAD_SZ_ALGN(%r30), %r1
+        LDREG   TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE(%r30), %r1
         LDREG   TASK_PT_GR25(%r1), %r26
 #ifdef CONFIG_64BIT
         LDREG   TASK_PT_GR27(%r1), %r27
@@ -743,9 +743,8 @@ ENDPROC(ret_from_kernel_thread)
 
 ENTRY(ret_from_kernel_execve)
         mfctl   %cr30, %r1
-        ldo     THREAD_SZ_ALGN(%r1), %r30
-        b       intr_return     /* forward */
-        copy    %r26,%r16       /* pt_regs into r16 */
+        b       syscall_exit    /* forward */
+        ldo     THREAD_SZ_ALGN+FRAME_SIZE(%r1), %r30
 ENDPROC(ret_from_kernel_execve)
 
 
@@ -1709,39 +1708,13 @@ ENTRY(sys_fork_wrapper)
         LDREG   TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE(%r30), %r1
         ldo     TASK_REGS(%r1),%r1
         reg_save %r1
-        mfctl   %cr27, %r3
-        STREG   %r3, PT_CR27(%r1)
-
-        STREG   %r2,-RP_OFFSET(%r30)
-        ldo     FRAME_SIZE(%r30),%r30
-#ifdef CONFIG_64BIT
-        ldo     -16(%r30),%r29          /* Reference param save area */
-#endif
-
-        /* These are call-clobbered registers and therefore
-           also syscall-clobbered (we hope). */
-        STREG   %r2,PT_GR19(%r1)        /* save for child */
-        STREG   %r30,PT_GR21(%r1)
+        mfctl   %cr27, %r28
+        STREG   %r28, PT_CR27(%r1)
 
         LDREG   PT_GR30(%r1),%r25
         copy    %r1,%r24
-        BL      sys_clone,%r2
+        b       sys_clone
         ldi     SIGCHLD,%r26
-
-        LDREG   -RP_OFFSET-FRAME_SIZE(%r30),%r2
-wrapper_exit:
-        ldo     -FRAME_SIZE(%r30),%r30          /* get the stackframe */
-        LDREG   TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1
-        ldo     TASK_REGS(%r1),%r1       /* get pt regs */
-
-        LDREG   PT_CR27(%r1), %r3
-        mtctl   %r3, %cr27
-        reg_restore %r1
-
-        /* strace expects syscall # to be preserved in r20 */
-        ldi     __NR_fork,%r20
-        bv %r0(%r2)
-        STREG   %r20,PT_GR20(%r1)
 ENDPROC(sys_fork_wrapper)
 
         /* Set the return value for the child */
@@ -1749,9 +1722,13 @@ ENTRY(child_return)
         BL      schedule_tail, %r2
         nop
 
-        LDREG   TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE-FRAME_SIZE(%r30), %r1
-        LDREG   TASK_PT_GR19(%r1),%r2
-        b       wrapper_exit
+        LDREG   TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE(%r30), %r1
+        ldo     TASK_REGS(%r1),%r1       /* get pt regs */
+
+        LDREG   PT_CR27(%r1), %r3
+        mtctl   %r3, %cr27
+        reg_restore %r1
+        b       syscall_exit
         copy    %r0,%r28
 ENDPROC(child_return)
 
@@ -1760,23 +1737,10 @@ ENTRY(sys_clone_wrapper)
         LDREG   TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1
         ldo     TASK_REGS(%r1),%r1      /* get pt regs */
         reg_save %r1
-        mfctl   %cr27, %r3
-        STREG   %r3, PT_CR27(%r1)
-
-        STREG   %r2,-RP_OFFSET(%r30)
-        ldo     FRAME_SIZE(%r30),%r30
-#ifdef CONFIG_64BIT
-        ldo     -16(%r30),%r29          /* Reference param save area */
-#endif
-
-        /* WARNING - Clobbers r19 and r21, userspace must save these! */
-        STREG   %r2,PT_GR19(%r1)        /* save for child */
-        STREG   %r30,PT_GR21(%r1)
-        BL      sys_clone,%r2
+        mfctl   %cr27, %r28
+        STREG   %r28, PT_CR27(%r1)
+        b       sys_clone
         copy    %r1,%r24
-
-        b       wrapper_exit
-        LDREG   -RP_OFFSET-FRAME_SIZE(%r30),%r2
 ENDPROC(sys_clone_wrapper)
 
 
@@ -1784,23 +1748,11 @@ ENTRY(sys_vfork_wrapper)
         LDREG   TI_TASK-THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1
         ldo     TASK_REGS(%r1),%r1      /* get pt regs */
         reg_save %r1
-        mfctl   %cr27, %r3
-        STREG   %r3, PT_CR27(%r1)
-
-        STREG   %r2,-RP_OFFSET(%r30)
-        ldo     FRAME_SIZE(%r30),%r30
-#ifdef CONFIG_64BIT
-        ldo     -16(%r30),%r29          /* Reference param save area */
-#endif
+        mfctl   %cr27, %r28
+        STREG   %r28, PT_CR27(%r1)
 
-        STREG   %r2,PT_GR19(%r1)        /* save for child */
-        STREG   %r30,PT_GR21(%r1)
-
-        BL      sys_vfork,%r2
+        b       sys_vfork
         copy    %r1,%r26
-
-        b       wrapper_exit
-        LDREG   -RP_OFFSET-FRAME_SIZE(%r30),%r2
 ENDPROC(sys_vfork_wrapper)
 
         
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 44e8534c52e9..38db36f64307 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -52,6 +52,7 @@
 
 #include <asm/io.h>
 #include <asm/asm-offsets.h>
+#include <asm/assembly.h>
 #include <asm/pdc.h>
 #include <asm/pdc_chassis.h>
 #include <asm/pgalloc.h>
@@ -253,14 +254,16 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 #ifdef CONFIG_HPUX
         extern void * const hpux_child_return;
 #endif
-
-        if (unlikely((p->flags & PF_KTHREAD) && usp != 0)) {
+        if (unlikely(p->flags & PF_KTHREAD)) {
                 memset(cregs, 0, sizeof(struct pt_regs));
+                if (!usp) /* idle thread */
+                        return 0;
+
                 /* kernel thread */
-                cregs->ksp = (unsigned long)stack + THREAD_SZ_ALGN;
                 /* Must exit via ret_from_kernel_thread in order
                  * to call schedule_tail()
                  */
+                cregs->ksp = (unsigned long)stack + THREAD_SZ_ALGN + FRAME_SIZE;
                 cregs->kpc = (unsigned long) &ret_from_kernel_thread;
                 /*
                  * Copy function and argument to be called from
@@ -275,22 +278,8 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
                 cregs->gr[25] = arg;
         } else {
                 /* user thread */
-                /*
-                 * Note that the fork wrappers are responsible
-                 * for setting gr[21].
-                 */
-
-                *cregs = *pregs;
-
-                /* Set the return value for the child.  Note that this is not
-                   actually restored by the syscall exit path, but we put it
-                   here for consistency in case of signals. */
-                cregs->gr[28] = 0; /* child */
-
-                /* Use same stack depth as parent */
-                cregs->ksp = (unsigned long)stack
-                        + (pregs->gr[21] & (THREAD_SIZE - 1));
                 cregs->gr[30] = usp;
+                cregs->ksp = (unsigned long)stack + THREAD_SZ_ALGN + FRAME_SIZE;
                 if (personality(p->personality) == PER_HPUX) {
 #ifdef CONFIG_HPUX
                         cregs->kpc = (unsigned long) &hpux_child_return;
@@ -302,8 +291,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
                 }
                 /* Setup thread TLS area from the 4th parameter in clone */
                 if (clone_flags & CLONE_SETTLS)
-                  cregs->cr27 = pregs->gr[23];
-        
+                        cregs->cr27 = pregs->gr[23];
         }
 
         return 0;