MIPS: R12000: Enable branch prediction global history

The R12000 added a new feature to enhance branch prediction called
"global history".  Per the Vr10000 Series User Manual (U10278EJ4V0UM),
Coprocessor 0, Diagnostic Register (22):

"""
If bit 26 is set, branch prediction uses all eight bits of the global
history register.  If bit 26 is not set, then bits 25:23 specify a count
of the number of bits of global history to be used. Thus if bits 26:23
are all zero, global history is disabled.

The global history contains a record of the taken/not-taken status of
recently executed branches, and when used is XOR'ed with the PC of a
branch being predicted to produce a hashed value for indexing the BPT.
Some programs with small "working set of conditional branches" benefit
significantly from the use of such hashing, some see slight performance
degradation.
"""

This patch enables global history on R12000 CPUs and up by setting bit
26 in the branch prediction diagnostic register (CP0 $22) to '1'.  Bits
25:23 are left alone so that all eight bits of the global history
register are available for branch prediction.

Signed-off-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index f89eaa7..dbe0792 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -945,7 +945,7 @@
 		c->options = MIPS_CPU_TLB | MIPS_CPU_4K_CACHE | MIPS_CPU_4KEX |
 			     MIPS_CPU_FPU | MIPS_CPU_32FPR |
 			     MIPS_CPU_COUNTER | MIPS_CPU_WATCH |
-			     MIPS_CPU_LLSC;
+			     MIPS_CPU_LLSC | MIPS_CPU_BP_GHIST;
 		c->tlbsize = 64;
 		break;
 	case PRID_IMP_R14000:
@@ -960,7 +960,7 @@
 		c->options = MIPS_CPU_TLB | MIPS_CPU_4K_CACHE | MIPS_CPU_4KEX |
 			     MIPS_CPU_FPU | MIPS_CPU_32FPR |
 			     MIPS_CPU_COUNTER | MIPS_CPU_WATCH |
-			     MIPS_CPU_LLSC;
+			     MIPS_CPU_LLSC | MIPS_CPU_BP_GHIST;
 		c->tlbsize = 64;
 		break;
 	case PRID_IMP_LOONGSON_64:  /* Loongson-2/3 */
@@ -1480,6 +1480,10 @@
 	else
 		cpu_set_nofpu_opts(c);
 
+	if (cpu_has_bp_ghist)
+		write_c0_r10k_diag(read_c0_r10k_diag() |
+				   R10K_DIAG_E_GHIST);
+
 	if (cpu_has_mips_r2_r6) {
 		c->srsets = ((read_c0_srsctl() >> 26) & 0x0f) + 1;
 		/* R2 has Performance Counter Interrupt indicator */