intel/common: CAR setup CQOS

Enable CQOS on Geminilake.

In Apololake, CBM_LEN is 0x7. Whereas the same in Geminilake is 0xF.

Thus get CBM_LEN using cpuid instruction & generate CBM_LEN_MASK.

Later use the CBM_LEN_MASK when writing to IA32_L2_MASK_* to set right
bits.

BUG=None
TEST= Build for Geminilake platform i.e., glkrvp & check for successful
CAR setup. Even verified the same on APL platform i.e., on Reef

Change-Id: Ic736dba1a46629ff5bf3183082799c0c1468e6d9
Signed-off-by: Naresh G Solanki <naresh.solanki@intel.com
Reviewed-on: https://review.coreboot.org/21701
Reviewed-by: Aaron Durbin <adurbin@chromium.org>
Tested-by: build bot (Jenkins) <no-reply@coreboot.org>

src/soc/intel/common/block/cpu/car/cache_as_ram.S

@@ -254,6 +254,24 @@ car_nem:
 #elif IS_ENABLED(CONFIG_INTEL_CAR_CQOS)
 .global car_cqos
 car_cqos:
+	/*
+	 * Create CBM_LEN_MASK based on CBM_LEN
+	 * Get CPUID.(EAX=10H, ECX=2H):EAX.CBM_LEN[bits 4:0]
+	 */
+	mov $0x10, %eax
+	mov $0x2,  %ecx
+	cpuid
+	and $0x1F, %eax
+	add $1, %al
+
+	mov $1, %ebx
+	mov %al, %cl
+	shl %cl, %ebx
+	sub $1, %ebx
+
+	/* Store the CBM_LEN_MASK in mm3 for later use. */
+	movd %ebx, %mm3
+
 	/*
 	 * Disable both L1 and L2 prefetcher. For yet-to-understood reason,
 	 * prefetchers slow down filling cache with rep stos in CQOS mode.
@@ -284,7 +302,7 @@ car_cqos:
 	/* Set this mask for initial cache fill */
 	mov	$MSR_L2_QOS_MASK(0), %ecx
 	rdmsr
-	mov	%bl, %al
+	mov	%ebx, %eax
 	wrmsr
 
 	/* Set CLOS selector to 0 */
@@ -297,8 +315,15 @@ car_cqos:
 	mov	$MSR_L2_QOS_MASK(1), %ecx
 	rdmsr
 	/* Invert bits that are to be used for cache */
-	mov	%bl, %al
+	mov	%ebx, %eax
-	xor	$~0, %al			/* invert 8 bits */
+	xor	$~0, %eax			/* invert 32 bits */
+
+	/*
+	 * Use CBM_LEN_MASK stored in mm3 to set bits based on Capacity Bit
+	 * Mask Length.
+	 */
+	movd	%mm3, %ebx
+	and	%ebx, %eax
 	wrmsr
 
 	post_code(0x26)