sparc: Fix context switch on SMP

We must not load registers (e.g. PSR) from the heir context area before
the heir stopped execution.

With this patch the write to PSR is divided into two steps. We first update
the current window pointer and then we restore the status registers and
enable traps. This allows us to move the first write to PSR to be before
the write to WIM, as there is now no risk that we get an interrupt where
the CWP and WIM would be inconsistent. We only need to make sure that we
do not use any of the non-global registers or instructions that affects
CWP for three instructions after the write.

In the earlier code the non-global %o1 register was used right after the
write to PSR, which required the use of three nop:s.

Close #2472.

c/src/lib/libbsp/sparc/shared/irq_asm.S

@@ -127,14 +127,9 @@ SYM(_CPU_Context_restore_heir):
          *      g5 = scratch
          */
 
-        ld      [%o1 + PSR_OFFSET], %g1       ! g1 = saved psr
-
         and     %o2, SPARC_PSR_CWP_MASK, %g3  ! g3 = CWP
-                                              ! g1 = psr w/o cwp
-        andn    %g1, SPARC_PSR_ET_MASK | SPARC_PSR_CWP_MASK, %g1
-        or      %g1, %g3, %g1                 ! g1 = heirs psr
-        mov     %g1, %psr                     ! restore status register and
-                                              ! **** DISABLE TRAPS ****
+        andn    %o2, SPARC_PSR_ET_MASK, %g1   ! g1 = psr with traps disabled
+        mov     %g1, %psr                     ! **** DISABLE TRAPS ****
         mov     %wim, %g2                     ! g2 = wim
         mov     1, %g4
         sll     %g4, %g3, %g4                 ! g4 = WIM mask for CW invalid
@@ -173,19 +168,15 @@ save_frame_loop:
 
 done_flushing:
 
-        add     %g3, 1, %g3                   ! calculate desired WIM
-        and     %g3, SPARC_NUMBER_OF_REGISTER_WINDOWS - 1, %g3
+        ! Wait three instructions after the write to PSR before using
+        ! non-global registers or instructions affecting the CWP
+        mov     %g1, %psr                     ! restore cwp
+        add     %g3, 1, %g2                   ! calculate desired WIM
+        and     %g2, SPARC_NUMBER_OF_REGISTER_WINDOWS - 1, %g2
         mov     1, %g4
-        sll     %g4, %g3, %g4                 ! g4 = new WIM
+        sll     %g4, %g2, %g4                 ! g4 = new WIM
         mov     %g4, %wim
 
-        or      %g1, SPARC_PSR_ET_MASK, %g1
-        mov     %g1, %psr                     ! **** ENABLE TRAPS ****
-                                              !   and restore CWP
-        nop
-        nop
-        nop
-
 #if defined(RTEMS_SMP)
         ! The executing context no longer executes on this processor
         st      %g0, [%o0 + SPARC_CONTEXT_CONTROL_IS_EXECUTING_OFFSET]
@@ -202,6 +193,12 @@ try_update_is_executing:
         ! The next load is in a delay slot, which is all right
 #endif
 
+        ld      [%o1 + PSR_OFFSET], %g1       ! g1 = heir psr with traps enabled
+        andn    %g1, SPARC_PSR_CWP_MASK, %g1  ! g1 = heir psr w/o cwp
+        or      %g1, %g3, %g1                 ! g1 = heir psr with cwp
+        mov     %g1, %psr                     ! restore status register and
+                                              ! **** ENABLE TRAPS ****
+
         ld      [%o1 + G5_OFFSET], %g5        ! restore the global registers
         ld      [%o1 + G7_OFFSET], %g7
 

cpukit/score/cpu/sparc/cpu.c

@@ -356,6 +356,9 @@ void _CPU_Context_Initialize(
     tmp_psr |= (new_level << 8) & SPARC_PSR_PIL_MASK;
     tmp_psr &= ~SPARC_PSR_EF_MASK;      /* disabled by default */
 
+    /* _CPU_Context_restore_heir() relies on this */
+    _Assert( ( tmp_psr & SPARC_PSR_ET_MASK ) != 0 );
+
 #if (SPARC_HAS_FPU == 1)
     /*
      *  If this bit is not set, then a task gets a fault when it accesses