sparc64: speed up etrap/rtrap on NG2 and later processors

For many sun4v processor types, reading or writing a privileged register
has a latency of 40 to 70 cycles.  Use a combination of the low-latency
allclean, otherw, normalw, and nop instructions in etrap and rtrap to
replace 2 rdpr and 5 wrpr instructions and improve etrap/rtrap
performance.  allclean, otherw, and normalw are available on NG2 and
later processors.

The average ticks to execute the flush windows trap ("ta 0x3") with and
without this patch on select platforms:

 CPU            Not patched     Patched    % Latency Reduction

 NG2            1762            1558            -11.58
 NG4            3619            3204            -11.47
 M7             3015            2624            -12.97
 SPARC64-X      829             770              -7.12
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/include/asm/trap_block.h

@@ -73,6 +73,8 @@ struct sun4v_1insn_patch_entry {
 };
 extern struct sun4v_1insn_patch_entry __sun4v_1insn_patch,
 	__sun4v_1insn_patch_end;
+extern struct sun4v_1insn_patch_entry __fast_win_ctrl_1insn_patch,
+	__fast_win_ctrl_1insn_patch_end;
 
 struct sun4v_2insn_patch_entry {
 	unsigned int	addr;

arch/sparc/kernel/etrap_64.S

@@ -38,7 +38,11 @@ etrap_syscall:	TRAP_LOAD_THREAD_REG(%g6, %g1)
 		or	%g1, %g3, %g1
 		bne,pn	%xcc, 1f
 		 sub	%sp, STACKFRAME_SZ+TRACEREG_SZ-STACK_BIAS, %g2
-		wrpr	%g0, 7, %cleanwin
+661:		wrpr	%g0, 7, %cleanwin
+		.section .fast_win_ctrl_1insn_patch, "ax"
+		.word	661b
+		.word	0x85880000	! allclean
+		.previous
 
 		sethi	%hi(TASK_REGOFF), %g2
 		sethi	%hi(TSTATE_PEF), %g3
@@ -88,16 +92,30 @@ etrap_save:	save	%g2, -STACK_BIAS, %sp
 
 		bne,pn	%xcc, 3f
 		 mov	PRIMARY_CONTEXT, %l4
-		rdpr	%canrestore, %g3
+661:		rdpr	%canrestore, %g3
+		.section .fast_win_ctrl_1insn_patch, "ax"
+		.word	661b
+		nop
+		.previous
+
 		rdpr	%wstate, %g2
-		wrpr	%g0, 0, %canrestore
+661:		wrpr	%g0, 0, %canrestore
+		.section .fast_win_ctrl_1insn_patch, "ax"
+		.word	661b
+		nop
+		.previous
 		sll	%g2, 3, %g2
 
 		/* Set TI_SYS_FPDEPTH to 1 and clear TI_SYS_NOERROR.  */
 		mov	1, %l5
 		sth	%l5, [%l6 + TI_SYS_NOERROR]
 
-		wrpr	%g3, 0, %otherwin
+661:		wrpr	%g3, 0, %otherwin
+		.section .fast_win_ctrl_1insn_patch, "ax"
+		.word	661b
+		.word	0x87880000	! otherw
+		.previous
+
 		wrpr	%g2, 0, %wstate
 		sethi	%hi(sparc64_kern_pri_context), %g2
 		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g3

arch/sparc/kernel/rtrap_64.S

@@ -224,10 +224,19 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
 		rdpr			%otherwin, %l2
 		srl			%l1, 3, %l1
 
-		wrpr			%l2, %g0, %canrestore
+661:		wrpr			%l2, %g0, %canrestore
+		.section		.fast_win_ctrl_1insn_patch, "ax"
+		.word			661b
+		.word			0x89880000	! normalw
+		.previous
+
 		wrpr			%l1, %g0, %wstate
 		brnz,pt			%l2, user_rtt_restore
-		 wrpr			%g0, %g0, %otherwin
+661:		 wrpr			%g0, %g0, %otherwin
+		.section		.fast_win_ctrl_1insn_patch, "ax"
+		.word			661b
+		 nop
+		.previous
 
 		ldx			[%g6 + TI_FLAGS], %g3
 		wr			%g0, ASI_AIUP, %asi

arch/sparc/kernel/setup_64.c

@@ -300,6 +300,11 @@ static void __init sun4v_patch(void)
 		break;
 	}
 
+	if (sun4v_chip_type != SUN4V_CHIP_NIAGARA1) {
+		sun4v_patch_1insn_range(&__fast_win_ctrl_1insn_patch,
+					&__fast_win_ctrl_1insn_patch_end);
+	}
+
 	sun4v_hvapi_init();
 }
 

arch/sparc/kernel/vmlinux.lds.S

@@ -159,6 +159,11 @@ SECTIONS
 		*(.pud_huge_patch)
 		__pud_huge_patch_end = .;
 	}
+	.fast_win_ctrl_1insn_patch : {
+		__fast_win_ctrl_1insn_patch = .;
+		*(.fast_win_ctrl_1insn_patch)
+		__fast_win_ctrl_1insn_patch_end = .;
+	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 #ifdef CONFIG_JUMP_LABEL