arch/sparc: Avoid DCTI Couples

Avoid un-intended DCTI Couples. Use of DCTI couples is deprecated.
Also address the "Programming Note" for optimal performance.

Here is the complete text from Oracle SPARC Architecture Specs.

6.3.4.7 DCTI Couples
"A delayed control transfer instruction (DCTI) in the delay slot of
another DCTI is referred to as a “DCTI couple”. The use of DCTI couples
is deprecated in the Oracle SPARC Architecture; no new software should
place a DCTI in the delay slot of another DCTI, because on future Oracle
SPARC Architecture implementations DCTI couples may execute either
slowly or differently than the programmer assumes it will.

SPARC V8 and SPARC V9 Compatibility Note
The SPARC V8 architecture left behavior undefined for a DCTI couple. The
SPARC V9 architecture defined behavior in that case, but as of
UltraSPARC Architecture 2005, use of DCTI couples was deprecated.
Software should not expect high performance from DCTI couples, and
performance of DCTI couples should be expected to decline further in
future processors.

Programming Note
As noted in TABLE 6-5 on page 115, an annulled branch-always
(branch-always with a = 1) instruction is not architecturally a DCTI.
However, since not all implementations make that distinction, for
optimal performance, a DCTI should not be placed in the instruction word
immediately following an annulled branch-always instruction (BA,A or
BPA,A)."

Signed-off-by: Babu Moger <babu.moger@oracle.com>
Reviewed-by: Rob Gardner <rob.gardner@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 18 insertions, 0 deletions

diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 6aa3da152c20..44101196d02b 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -96,6 +96,7 @@ sparc64_boot:
         andn    %g1, PSTATE_AM, %g1
         wrpr    %g1, 0x0, %pstate
         ba,a,pt %xcc, 1f
+         nop
 
         .globl  prom_finddev_name, prom_chosen_path, prom_root_node
         .globl  prom_getprop_name, prom_mmu_name, prom_peer_name
@@ -613,6 +614,7 @@ niagara_tlb_fixup:
          nop
 
         ba,a,pt %xcc, 80f
+         nop
 niagara4_patch:
         call    niagara4_patch_copyops
          nop
@@ -622,6 +624,7 @@ niagara4_patch:
          nop
 
         ba,a,pt %xcc, 80f
+         nop
 
 niagara2_patch:
         call    niagara2_patch_copyops
@@ -632,6 +635,7 @@ niagara2_patch:
          nop
 
         ba,a,pt %xcc, 80f
+         nop
 
 niagara_patch:
         call    niagara_patch_copyops
diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S
index 34b4933900bf..9276d2f0dd86 100644
--- a/arch/sparc/kernel/misctrap.S
+++ b/arch/sparc/kernel/misctrap.S
@@ -82,6 +82,7 @@ do_stdfmna:
         call            handle_stdfmna
          add            %sp, PTREGS_OFF, %o0
         ba,a,pt         %xcc, rtrap
+         nop
         .size           do_stdfmna,.-do_stdfmna
 
         .type           breakpoint_trap,#function
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 216948ca4382..709a82ebd294 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -237,6 +237,7 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
                 bne,pt                  %xcc, user_rtt_fill_32bit
                  wrpr                   %g1, %cwp
                 ba,a,pt                 %xcc, user_rtt_fill_64bit
+                 nop
 
 user_rtt_fill_fixup_dax:
                 ba,pt   %xcc, user_rtt_fill_fixup_common
diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S
index 4a73009f66a5..d7e540842809 100644
--- a/arch/sparc/kernel/spiterrs.S
+++ b/arch/sparc/kernel/spiterrs.S
@@ -86,6 +86,7 @@ __spitfire_cee_trap_continue:
          rd             %pc, %g7
 
         ba,a,pt         %xcc, 2f
+         nop
 
 1:      ba,pt           %xcc, etrap_irq
          rd             %pc, %g7
diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index 6179e19bc9b9..c19f352f46c7 100644
--- a/arch/sparc/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
@@ -352,6 +352,7 @@ sun4v_mna:
         call    sun4v_do_mna
          add    %sp, PTREGS_OFF, %o0
         ba,a,pt %xcc, rtrap
+         nop
 
         /* Privileged Action.  */
 sun4v_privact:
diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
index 5604a2b051d4..364af3250646 100644
--- a/arch/sparc/kernel/urtt_fill.S
+++ b/arch/sparc/kernel/urtt_fill.S
@@ -92,6 +92,7 @@ user_rtt_fill_fixup_common:
                 call    sun4v_data_access_exception
                  nop
                 ba,a,pt %xcc, rtrap
+                 nop
 
 1:              call    spitfire_data_access_exception
                  nop
diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S
index 855019a8590e..1ee173cc3c39 100644
--- a/arch/sparc/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
@@ -152,6 +152,8 @@ fill_fixup_dax:
         call    sun4v_data_access_exception
          nop
         ba,a,pt %xcc, rtrap
+         nop
 1:      call    spitfire_data_access_exception
          nop
         ba,a,pt %xcc, rtrap
+         nop
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index c629dbd121b6..64dcd6cdb606 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -326,11 +326,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         blu             170f
          nop
         ba,a,pt         %xcc, 180f
+         nop
 
 4:      /* 32 <= low bits < 48 */
         blu             150f
          nop
         ba,a,pt         %xcc, 160f
+         nop
 5:      /* 0 < low bits < 32 */
         blu,a           6f
          cmp            %g2, 8
@@ -338,6 +340,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         blu             130f
          nop
         ba,a,pt         %xcc, 140f
+         nop
 6:      /* 0 < low bits < 16 */
         bgeu            120f
          nop
@@ -475,6 +478,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         brz,pt          %o2, 85f
          sub            %o0, %o1, GLOBAL_SPARE
         ba,a,pt         %XCC, 90f
+         nop
 
         .align          64
 75: /* 16 < len <= 64 */
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 75bb93b1437f..78ea962edcbe 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -530,4 +530,5 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         bne,pt          %icc, 1b
          EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
         ba,a,pt         %icc, .Lexit
+         nop
         .size           FUNC_NAME, .-FUNC_NAME
diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S
index 41da4bdd95cb..7c0c81f18837 100644
--- a/arch/sparc/lib/NG4memset.S
+++ b/arch/sparc/lib/NG4memset.S
@@ -102,4 +102,5 @@ NG4bzero:
         bne,pt          %icc, 1b
          add            %o0, 0x30, %o0
         ba,a,pt         %icc, .Lpostloop
+         nop
         .size           NG4bzero,.-NG4bzero
diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S
index d88c4ed50a00..cd654a719b27 100644
--- a/arch/sparc/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
@@ -394,6 +394,7 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         brz,pt          %i2, 85f
          sub            %o0, %i1, %i3
         ba,a,pt         %XCC, 90f
+         nop
 
         .align          64
 70: /* 16 < len <= 64 */