armv8/ls1043a: fixup GIC offset for ls1043a rev1

The LS1043A rev1.1 silicon supports two types of GIC offset: 4K
alignment and 64K alignment. The bit SCFG_GIC400_ALIGN[GIC_ADDR_BIT]
is used to choose which offset will be used.

The LS1043A rev1.0 silicon only supports the CIG offset with 4K
alignment.

If GIC_ADDR_BIT bit is set, 4K alignment is used, or else 64K alignment
is used. 64K alignment is the default setting.

Overriding the weak smp_kick_all_cpus, the new impletment is able to
detect GIC offset.

The default GIC offset in kernel device tree is using 4K alignment, it
need to be fixed if 64K alignment is detected.

Signed-off-by: Wenbin Song <wenbin.song@nxp.com>
Signed-off-by: Mingkai Hu <mingkai.hu@nxp.com>
Signed-off-by: Hou Zhiqiang <Zhiqiang.Hou@nxp.com>
Reviewed-by: York Sun <york.sun@nxp.com>
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/Kconfig b/arch/arm/cpu/armv8/fsl-layerscape/Kconfig
index 79e2dd6..dce1689 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/Kconfig
+++ b/arch/arm/cpu/armv8/fsl-layerscape/Kconfig
@@ -90,6 +90,11 @@
 	  This compatible is used to find pci controller node in Kernel DT
 	  to complete fixup.
 
+config HAS_FEATURE_GIC64K_ALIGN
+	bool
+	default y if ARCH_LS1043A
+
+
 menu "Layerscape PPA"
 config FSL_LS_PPA
 	bool "FSL Layerscape PPA firmware support"
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/fdt.c b/arch/arm/cpu/armv8/fsl-layerscape/fdt.c
index c10ccf9..f289172 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/fdt.c
+++ b/arch/arm/cpu/armv8/fsl-layerscape/fdt.c
@@ -133,6 +133,67 @@
 	}
 }
 
+#ifdef CONFIG_HAS_FEATURE_GIC64K_ALIGN
+static void fdt_fixup_gic(void *blob)
+{
+	int offset, err;
+	u64 reg[8];
+	struct ccsr_gur __iomem *gur = (void *)(CONFIG_SYS_FSL_GUTS_ADDR);
+	unsigned int val;
+	struct ccsr_scfg __iomem *scfg = (void *)CONFIG_SYS_FSL_SCFG_ADDR;
+	int align_64k = 0;
+
+	val = gur_in32(&gur->svr);
+
+	if (SVR_SOC_VER(val) != SVR_LS1043A) {
+		align_64k = 1;
+	} else if (SVR_REV(val) != REV1_0) {
+		val = scfg_in32(&scfg->gic_align) & (0x01 << GIC_ADDR_BIT);
+		if (!val)
+			align_64k = 1;
+	}
+
+	offset = fdt_subnode_offset(blob, 0, "interrupt-controller@1400000");
+	if (offset < 0) {
+		printf("WARNING: fdt_subnode_offset can't find node %s: %s\n",
+		       "interrupt-controller@1400000", fdt_strerror(offset));
+		return;
+	}
+
+	/* Fixup gic node align with 64K */
+	if (align_64k) {
+		reg[0] = cpu_to_fdt64(GICD_BASE_64K);
+		reg[1] = cpu_to_fdt64(GICD_SIZE_64K);
+		reg[2] = cpu_to_fdt64(GICC_BASE_64K);
+		reg[3] = cpu_to_fdt64(GICC_SIZE_64K);
+		reg[4] = cpu_to_fdt64(GICH_BASE_64K);
+		reg[5] = cpu_to_fdt64(GICH_SIZE_64K);
+		reg[6] = cpu_to_fdt64(GICV_BASE_64K);
+		reg[7] = cpu_to_fdt64(GICV_SIZE_64K);
+	} else {
+	/* Fixup gic node align with default */
+		reg[0] = cpu_to_fdt64(GICD_BASE);
+		reg[1] = cpu_to_fdt64(GICD_SIZE);
+		reg[2] = cpu_to_fdt64(GICC_BASE);
+		reg[3] = cpu_to_fdt64(GICC_SIZE);
+		reg[4] = cpu_to_fdt64(GICH_BASE);
+		reg[5] = cpu_to_fdt64(GICH_SIZE);
+		reg[6] = cpu_to_fdt64(GICV_BASE);
+		reg[7] = cpu_to_fdt64(GICV_SIZE);
+	}
+
+	err = fdt_setprop(blob, offset, "reg", reg, sizeof(reg));
+	if (err < 0) {
+		printf("WARNING: fdt_setprop can't set %s from node %s: %s\n",
+		       "reg", "interrupt-controller@1400000",
+		       fdt_strerror(err));
+		return;
+	}
+
+	return;
+}
+#endif
+
 void ft_cpu_setup(void *blob, bd_t *bd)
 {
 #ifdef CONFIG_FSL_LSCH2
@@ -177,4 +238,7 @@
 #endif
 	fsl_fdt_disable_usb(blob);
 
+#ifdef CONFIG_HAS_FEATURE_GIC64K_ALIGN
+	fdt_fixup_gic(blob);
+#endif
 }
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S b/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
index 04a2598..62efa90 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
+++ b/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
@@ -10,15 +10,66 @@
 #include <linux/linkage.h>
 #include <asm/gic.h>
 #include <asm/macro.h>
+#include <asm/arch-fsl-layerscape/soc.h>
 #ifdef CONFIG_MP
 #include <asm/arch/mp.h>
 #endif
 #ifdef CONFIG_FSL_LSCH3
 #include <asm/arch-fsl-layerscape/immap_lsch3.h>
-#include <asm/arch-fsl-layerscape/soc.h>
 #endif
 #include <asm/u-boot.h>
 
+/* Get GIC offset
+* For LS1043a rev1.0, GIC base address align with 4k.
+* For LS1043a rev1.1, if DCFG_GIC400_ALIGN[GIC_ADDR_BIT]
+* is set, GIC base address align with 4K, or else align
+* with 64k.
+* output:
+*	x0: the base address of GICD
+*	x1: the base address of GICC
+*/
+ENTRY(get_gic_offset)
+	ldr     x0, =GICD_BASE
+#ifdef CONFIG_GICV2
+	ldr     x1, =GICC_BASE
+#endif
+#ifdef CONFIG_HAS_FEATURE_GIC64K_ALIGN
+	ldr     x2, =DCFG_CCSR_SVR
+	ldr	w2, [x2]
+	rev	w2, w2
+	mov	w3, w2
+	ands	w3, w3, #SVR_WO_E << 8
+	mov	w4, #SVR_LS1043A << 8
+	cmp	w3, w4
+	b.ne	1f
+	ands	w2, w2, #0xff
+	cmp	w2, #REV1_0
+	b.eq	1f
+	ldr	x2, =SCFG_GIC400_ALIGN
+	ldr	w2, [x2]
+	rev	w2, w2
+	tbnz	w2, #GIC_ADDR_BIT, 1f
+	ldr     x0, =GICD_BASE_64K
+#ifdef CONFIG_GICV2
+	ldr     x1, =GICC_BASE_64K
+#endif
+1:
+#endif
+	ret
+ENDPROC(get_gic_offset)
+
+ENTRY(smp_kick_all_cpus)
+	/* Kick secondary cpus up by SGI 0 interrupt */
+#if defined(CONFIG_GICV2) || defined(CONFIG_GICV3)
+	mov	x29, lr			/* Save LR */
+	bl	get_gic_offset
+	bl	gic_kick_secondary_cpus
+	mov	lr, x29			/* Restore LR */
+#endif
+	ret
+ENDPROC(smp_kick_all_cpus)
+
+
 ENTRY(lowlevel_init)
 	mov	x29, lr			/* Save LR */
 
@@ -130,15 +181,14 @@
 	/* Initialize GIC Secure Bank Status */
 #if defined(CONFIG_GICV2) || defined(CONFIG_GICV3)
 	branch_if_slave x0, 1f
-	ldr	x0, =GICD_BASE
+	bl	get_gic_offset
 	bl	gic_init_secure
 1:
 #ifdef CONFIG_GICV3
 	ldr	x0, =GICR_BASE
 	bl	gic_init_secure_percpu
 #elif defined(CONFIG_GICV2)
-	ldr	x0, =GICD_BASE
-	ldr	x1, =GICC_BASE
+	bl	get_gic_offset
 	bl	gic_init_secure_percpu
 #endif
 #endif
@@ -413,7 +463,8 @@
 #if defined(CONFIG_GICV3)
 	gic_wait_for_interrupt_m x0
 #elif defined(CONFIG_GICV2)
-        ldr     x0, =GICC_BASE
+	bl	get_gic_offset
+	mov	x0, x1
         gic_wait_for_interrupt_m x0, w1
 #endif