Merge tag 'gic-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core

GIC updates for Linux 4.4 from Marc Zyngier:

- Enable basic GICv3 support on 32bit ARM (mostly for running VMs with
  more than 8 virtual CPUs)
- arm64 changes to deal with firmware limitations that forces a GICv3
  to be used as a GICv2
- A GICv2m erratum workaround on Applied Micro X-Gene2

13 files changed, 487 insertions, 177 deletions

diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 7d9d3c2286b2..369a4f48eb0d 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -173,13 +173,22 @@ Before jumping into the kernel, the following conditions must be met:
   the kernel image will be entered must be initialised by software at a
   higher exception level to prevent execution in an UNKNOWN state.
 
-  For systems with a GICv3 interrupt controller:
+  For systems with a GICv3 interrupt controller to be used in v3 mode:
   - If EL3 is present:
     ICC_SRE_EL3.Enable (bit 3) must be initialiased to 0b1.
     ICC_SRE_EL3.SRE (bit 0) must be initialised to 0b1.
   - If the kernel is entered at EL1:
     ICC.SRE_EL2.Enable (bit 3) must be initialised to 0b1
     ICC_SRE_EL2.SRE (bit 0) must be initialised to 0b1.
+  - The DT or ACPI tables must describe a GICv3 interrupt controller.
+
+  For systems with a GICv3 interrupt controller to be used in
+  compatibility (v2) mode:
+  - If EL3 is present:
+    ICC_SRE_EL3.SRE (bit 0) must be initialised to 0b0.
+  - If the kernel is entered at EL1:
+    ICC_SRE_EL2.SRE (bit 0) must be initialised to 0b0.
+  - The DT or ACPI tables must describe a GICv2 interrupt controller.
 
 The requirements described above for CPU mode, caches, MMUs, architected
 timers, coherency and system registers apply to all CPUs.  All CPUs must
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 72ad724c67ae..0d72535ed01d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -819,6 +819,7 @@ config ARCH_VIRT
 	bool "Dummy Virtual Machine" if ARCH_MULTI_V7
 	select ARM_AMBA
 	select ARM_GIC
+	select ARM_GIC_V3
 	select ARM_PSCI
 	select HAVE_ARM_ARCH_TIMER
 
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
new file mode 100644
index 000000000000..6607d976e07d
--- /dev/null
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -0,0 +1,188 @@
+/*
+ * arch/arm/include/asm/arch_gicv3.h
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_ARCH_GICV3_H
+#define __ASM_ARCH_GICV3_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/io.h>
+
+#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	p15, Op1, %0, CRn, CRm, Op2
+#define __ACCESS_CP15_64(Op1, CRm)		p15, Op1, %Q0, %R0, CRm
+
+#define ICC_EOIR1			__ACCESS_CP15(c12, 0, c12, 1)
+#define ICC_DIR				__ACCESS_CP15(c12, 0, c11, 1)
+#define ICC_IAR1			__ACCESS_CP15(c12, 0, c12, 0)
+#define ICC_SGI1R			__ACCESS_CP15_64(0, c12)
+#define ICC_PMR				__ACCESS_CP15(c4, 0, c6, 0)
+#define ICC_CTLR			__ACCESS_CP15(c12, 0, c12, 4)
+#define ICC_SRE				__ACCESS_CP15(c12, 0, c12, 5)
+#define ICC_IGRPEN1			__ACCESS_CP15(c12, 0, c12, 7)
+
+#define ICC_HSRE			__ACCESS_CP15(c12, 4, c9, 5)
+
+#define ICH_VSEIR			__ACCESS_CP15(c12, 4, c9, 4)
+#define ICH_HCR				__ACCESS_CP15(c12, 4, c11, 0)
+#define ICH_VTR				__ACCESS_CP15(c12, 4, c11, 1)
+#define ICH_MISR			__ACCESS_CP15(c12, 4, c11, 2)
+#define ICH_EISR			__ACCESS_CP15(c12, 4, c11, 3)
+#define ICH_ELSR			__ACCESS_CP15(c12, 4, c11, 5)
+#define ICH_VMCR			__ACCESS_CP15(c12, 4, c11, 7)
+
+#define __LR0(x)			__ACCESS_CP15(c12, 4, c12, x)
+#define __LR8(x)			__ACCESS_CP15(c12, 4, c13, x)
+
+#define ICH_LR0				__LR0(0)
+#define ICH_LR1				__LR0(1)
+#define ICH_LR2				__LR0(2)
+#define ICH_LR3				__LR0(3)
+#define ICH_LR4				__LR0(4)
+#define ICH_LR5				__LR0(5)
+#define ICH_LR6				__LR0(6)
+#define ICH_LR7				__LR0(7)
+#define ICH_LR8				__LR8(0)
+#define ICH_LR9				__LR8(1)
+#define ICH_LR10			__LR8(2)
+#define ICH_LR11			__LR8(3)
+#define ICH_LR12			__LR8(4)
+#define ICH_LR13			__LR8(5)
+#define ICH_LR14			__LR8(6)
+#define ICH_LR15			__LR8(7)
+
+/* LR top half */
+#define __LRC0(x)			__ACCESS_CP15(c12, 4, c14, x)
+#define __LRC8(x)			__ACCESS_CP15(c12, 4, c15, x)
+
+#define ICH_LRC0			__LRC0(0)
+#define ICH_LRC1			__LRC0(1)
+#define ICH_LRC2			__LRC0(2)
+#define ICH_LRC3			__LRC0(3)
+#define ICH_LRC4			__LRC0(4)
+#define ICH_LRC5			__LRC0(5)
+#define ICH_LRC6			__LRC0(6)
+#define ICH_LRC7			__LRC0(7)
+#define ICH_LRC8			__LRC8(0)
+#define ICH_LRC9			__LRC8(1)
+#define ICH_LRC10			__LRC8(2)
+#define ICH_LRC11			__LRC8(3)
+#define ICH_LRC12			__LRC8(4)
+#define ICH_LRC13			__LRC8(5)
+#define ICH_LRC14			__LRC8(6)
+#define ICH_LRC15			__LRC8(7)
+
+#define __AP0Rx(x)			__ACCESS_CP15(c12, 4, c8, x)
+#define ICH_AP0R0			__AP0Rx(0)
+#define ICH_AP0R1			__AP0Rx(1)
+#define ICH_AP0R2			__AP0Rx(2)
+#define ICH_AP0R3			__AP0Rx(3)
+
+#define __AP1Rx(x)			__ACCESS_CP15(c12, 4, c9, x)
+#define ICH_AP1R0			__AP1Rx(0)
+#define ICH_AP1R1			__AP1Rx(1)
+#define ICH_AP1R2			__AP1Rx(2)
+#define ICH_AP1R3			__AP1Rx(3)
+
+/* Low-level accessors */
+
+static inline void gic_write_eoir(u32 irq)
+{
+	asm volatile("mcr " __stringify(ICC_EOIR1) : : "r" (irq));
+	isb();
+}
+
+static inline void gic_write_dir(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_DIR) : : "r" (val));
+	isb();
+}
+
+static inline u32 gic_read_iar(void)
+{
+	u32 irqstat;
+
+	asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat));
+	return irqstat;
+}
+
+static inline void gic_write_pmr(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_PMR) : : "r" (val));
+}
+
+static inline void gic_write_ctlr(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_CTLR) : : "r" (val));
+	isb();
+}
+
+static inline void gic_write_grpen1(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_IGRPEN1) : : "r" (val));
+	isb();
+}
+
+static inline void gic_write_sgi1r(u64 val)
+{
+	asm volatile("mcrr " __stringify(ICC_SGI1R) : : "r" (val));
+}
+
+static inline u32 gic_read_sre(void)
+{
+	u32 val;
+
+	asm volatile("mrc " __stringify(ICC_SRE) : "=r" (val));
+	return val;
+}
+
+static inline void gic_write_sre(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_SRE) : : "r" (val));
+	isb();
+}
+
+/*
+ * Even in 32bit systems that use LPAE, there is no guarantee that the I/O
+ * interface provides true 64bit atomic accesses, so using strd/ldrd doesn't
+ * make much sense.
+ * Moreover, 64bit I/O emulation is extremely difficult to implement on
+ * AArch32, since the syndrome register doesn't provide any information for
+ * them.
+ * Consequently, the following IO helpers use 32bit accesses.
+ *
+ * There are only two registers that need 64bit accesses in this driver:
+ * - GICD_IROUTERn, contain the affinity values associated to each interrupt.
+ *   The upper-word (aff3) will always be 0, so there is no need for a lock.
+ * - GICR_TYPER is an ID register and doesn't need atomicity.
+ */
+static inline void gic_write_irouter(u64 val, volatile void __iomem *addr)
+{
+	writel_relaxed((u32)val, addr);
+	writel_relaxed((u32)(val >> 32), addr + 4);
+}
+
+static inline u64 gic_read_typer(const volatile void __iomem *addr)
+{
+	u64 val;
+
+	val = readl_relaxed(addr);
+	val |= (u64)readl_relaxed(addr + 4) << 32;
+	return val;
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif /* !__ASM_ARCH_GICV3_H */
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
new file mode 100644
index 000000000000..030cdcb46c6b
--- /dev/null
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -0,0 +1,170 @@
+/*
+ * arch/arm64/include/asm/arch_gicv3.h
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_ARCH_GICV3_H
+#define __ASM_ARCH_GICV3_H
+
+#include <asm/sysreg.h>
+
+#define ICC_EOIR1_EL1			sys_reg(3, 0, 12, 12, 1)
+#define ICC_DIR_EL1			sys_reg(3, 0, 12, 11, 1)
+#define ICC_IAR1_EL1			sys_reg(3, 0, 12, 12, 0)
+#define ICC_SGI1R_EL1			sys_reg(3, 0, 12, 11, 5)
+#define ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
+#define ICC_CTLR_EL1			sys_reg(3, 0, 12, 12, 4)
+#define ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
+#define ICC_GRPEN1_EL1			sys_reg(3, 0, 12, 12, 7)
+
+#define ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
+
+/*
+ * System register definitions
+ */
+#define ICH_VSEIR_EL2			sys_reg(3, 4, 12, 9, 4)
+#define ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
+#define ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
+#define ICH_MISR_EL2			sys_reg(3, 4, 12, 11, 2)
+#define ICH_EISR_EL2			sys_reg(3, 4, 12, 11, 3)
+#define ICH_ELSR_EL2			sys_reg(3, 4, 12, 11, 5)
+#define ICH_VMCR_EL2			sys_reg(3, 4, 12, 11, 7)
+
+#define __LR0_EL2(x)			sys_reg(3, 4, 12, 12, x)
+#define __LR8_EL2(x)			sys_reg(3, 4, 12, 13, x)
+
+#define ICH_LR0_EL2			__LR0_EL2(0)
+#define ICH_LR1_EL2			__LR0_EL2(1)
+#define ICH_LR2_EL2			__LR0_EL2(2)
+#define ICH_LR3_EL2			__LR0_EL2(3)
+#define ICH_LR4_EL2			__LR0_EL2(4)
+#define ICH_LR5_EL2			__LR0_EL2(5)
+#define ICH_LR6_EL2			__LR0_EL2(6)
+#define ICH_LR7_EL2			__LR0_EL2(7)
+#define ICH_LR8_EL2			__LR8_EL2(0)
+#define ICH_LR9_EL2			__LR8_EL2(1)
+#define ICH_LR10_EL2			__LR8_EL2(2)
+#define ICH_LR11_EL2			__LR8_EL2(3)
+#define ICH_LR12_EL2			__LR8_EL2(4)
+#define ICH_LR13_EL2			__LR8_EL2(5)
+#define ICH_LR14_EL2			__LR8_EL2(6)
+#define ICH_LR15_EL2			__LR8_EL2(7)
+
+#define __AP0Rx_EL2(x)			sys_reg(3, 4, 12, 8, x)
+#define ICH_AP0R0_EL2			__AP0Rx_EL2(0)
+#define ICH_AP0R1_EL2			__AP0Rx_EL2(1)
+#define ICH_AP0R2_EL2			__AP0Rx_EL2(2)
+#define ICH_AP0R3_EL2			__AP0Rx_EL2(3)
+
+#define __AP1Rx_EL2(x)			sys_reg(3, 4, 12, 9, x)
+#define ICH_AP1R0_EL2			__AP1Rx_EL2(0)
+#define ICH_AP1R1_EL2			__AP1Rx_EL2(1)
+#define ICH_AP1R2_EL2			__AP1Rx_EL2(2)
+#define ICH_AP1R3_EL2			__AP1Rx_EL2(3)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+
+/*
+ * Low-level accessors
+ *
+ * These system registers are 32 bits, but we make sure that the compiler
+ * sets the GP register's most significant bits to 0 with an explicit cast.
+ */
+
+static inline void gic_write_eoir(u32 irq)
+{
+	asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" ((u64)irq));
+	isb();
+}
+
+static inline void gic_write_dir(u32 irq)
+{
+	asm volatile("msr_s " __stringify(ICC_DIR_EL1) ", %0" : : "r" ((u64)irq));
+	isb();
+}
+
+static inline u64 gic_read_iar_common(void)
+{
+	u64 irqstat;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	return irqstat;
+}
+
+/*
+ * Cavium ThunderX erratum 23154
+ *
+ * The gicv3 of ThunderX requires a modified version for reading the
+ * IAR status to ensure data synchronization (access to icc_iar1_el1
+ * is not sync'ed before and after).
+ */
+static inline u64 gic_read_iar_cavium_thunderx(void)
+{
+	u64 irqstat;
+
+	asm volatile(
+		"nop;nop;nop;nop\n\t"
+		"nop;nop;nop;nop\n\t"
+		"mrs_s %0, " __stringify(ICC_IAR1_EL1) "\n\t"
+		"nop;nop;nop;nop"
+		: "=r" (irqstat));
+	mb();
+
+	return irqstat;
+}
+
+static inline void gic_write_pmr(u32 val)
+{
+	asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" ((u64)val));
+}
+
+static inline void gic_write_ctlr(u32 val)
+{
+	asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" ((u64)val));
+	isb();
+}
+
+static inline void gic_write_grpen1(u32 val)
+{
+	asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" ((u64)val));
+	isb();
+}
+
+static inline void gic_write_sgi1r(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
+}
+
+static inline u32 gic_read_sre(void)
+{
+	u64 val;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	return val;
+}
+
+static inline void gic_write_sre(u32 val)
+{
+	asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" ((u64)val));
+	isb();
+}
+
+#define gic_read_typer(c)		readq_relaxed(c)
+#define gic_write_irouter(v, c)		writeq_relaxed(v, c)
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_ARCH_GICV3_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 3c9aed32f70b..305f30dc9e63 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -23,6 +23,8 @@
 #include <asm/cpufeature.h>
 #include <asm/processor.h>
 
+#include <linux/irqchip/arm-gic-v3.h>
+
 static bool
 feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
 {
@@ -45,11 +47,26 @@ __ID_FEAT_CHK(id_aa64pfr0);
 __ID_FEAT_CHK(id_aa64mmfr1);
 __ID_FEAT_CHK(id_aa64isar0);
 
+static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry)
+{
+	bool has_sre;
+
+	if (!has_id_aa64pfr0_feature(entry))
+		return false;
+
+	has_sre = gic_enable_sre();
+	if (!has_sre)
+		pr_warn_once("%s present but disabled by higher exception level\n",
+			     entry->desc);
+
+	return has_sre;
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
 		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
-		.matches = has_id_aa64pfr0_feature,
+		.matches = has_useable_gicv3_cpuif,
 		.field_pos = 24,
 		.min_field_value = 1,
 	},
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 90d09eddd5b2..351a4de1b1e2 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -498,6 +498,8 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
 	msr_s	ICC_SRE_EL2, x0
 	isb					// Make sure SRE is now set
+	mrs_s	x0, ICC_SRE_EL2			// Read SRE back,
+	tbz	x0, #0, 3f			// and check that it sticks
 	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
 
 3:
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 5c7e920e4861..ff5292c6277c 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -16,6 +16,9 @@ menuconfig VIRTUALIZATION
 
 if VIRTUALIZATION
 
+config KVM_ARM_VGIC_V3
+	bool
+
 config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on OF
@@ -31,6 +34,7 @@ config KVM
 	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
+	select KVM_ARM_VGIC_V3
 	---help---
 	  Support hosting virtualized guest machines.
 
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index 12985daa66ab..9a36ab0b544c 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -37,12 +37,19 @@
 #define V2M_MSI_SETSPI_NS	       0x040
 #define V2M_MIN_SPI		       32
 #define V2M_MAX_SPI		       1019
+#define V2M_MSI_IIDR		       0xFCC
 
 #define V2M_MSI_TYPER_BASE_SPI(x)      \
 	       (((x) >> V2M_MSI_TYPER_BASE_SHIFT) & V2M_MSI_TYPER_BASE_MASK)
 
 #define V2M_MSI_TYPER_NUM_SPI(x)       ((x) & V2M_MSI_TYPER_NUM_MASK)
 
+/* APM X-Gene with GICv2m MSI_IIDR register value */
+#define XGENE_GICV2M_MSI_IIDR		0x06000170
+
+/* List of flags for specific v2m implementation */
+#define GICV2M_NEEDS_SPI_OFFSET		0x00000001
+
 struct v2m_data {
 	spinlock_t msi_cnt_lock;
 	struct resource res;	/* GICv2m resource */
@@ -50,6 +57,7 @@ struct v2m_data {
 	u32 spi_start;		/* The SPI number that MSIs start */
 	u32 nr_spis;		/* The number of SPIs for MSIs */
 	unsigned long *bm;	/* MSI vector bitmap */
+	u32 flags;		/* v2m flags for specific implementation */
 };
 
 static void gicv2m_mask_msi_irq(struct irq_data *d)
@@ -98,6 +106,9 @@ static void gicv2m_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	msg->address_hi = upper_32_bits(addr);
 	msg->address_lo = lower_32_bits(addr);
 	msg->data = data->hwirq;
+
+	if (v2m->flags & GICV2M_NEEDS_SPI_OFFSET)
+		msg->data -= v2m->spi_start;
 }
 
 static struct irq_chip gicv2m_irq_chip = {
@@ -266,6 +277,17 @@ static int __init gicv2m_init_one(struct device_node *node,
 		goto err_iounmap;
 	}
 
+	/*
+	 * APM X-Gene GICv2m implementation has an erratum where
+	 * the MSI data needs to be the offset from the spi_start
+	 * in order to trigger the correct MSI interrupt. This is
+	 * different from the standard GICv2m implementation where
+	 * the MSI data is the absolute value within the range from
+	 * spi_start to (spi_start + num_spis).
+	 */
+	if (readl_relaxed(v2m->base + V2M_MSI_IIDR) == XGENE_GICV2M_MSI_IIDR)
+		v2m->flags |= GICV2M_NEEDS_SPI_OFFSET;
+
 	v2m->bm = kzalloc(sizeof(long) * BITS_TO_LONGS(v2m->nr_spis),
 			  GFP_KERNEL);
 	if (!v2m->bm) {
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 149e3c6b3618..222f9cc0deae 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -108,37 +108,7 @@ static void gic_redist_wait_for_rwp(void)
 	gic_do_wait_for_rwp(gic_data_rdist_rd_base());
 }
 
-/* Low level accessors */
-static u64 gic_read_iar_common(void)
-{
-	u64 irqstat;
-
-	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
-	return irqstat;
-}
-
-/*
- * Cavium ThunderX erratum 23154
- *
- * The gicv3 of ThunderX requires a modified version for reading the
- * IAR status to ensure data synchronization (access to icc_iar1_el1
- * is not sync'ed before and after).
- */
-static u64 gic_read_iar_cavium_thunderx(void)
-{
-	u64 irqstat;
-
-	asm volatile(
-		"nop;nop;nop;nop\n\t"
-		"nop;nop;nop;nop\n\t"
-		"mrs_s %0, " __stringify(ICC_IAR1_EL1) "\n\t"
-		"nop;nop;nop;nop"
-		: "=r" (irqstat));
-	mb();
-
-	return irqstat;
-}
-
+#ifdef CONFIG_ARM64
 static DEFINE_STATIC_KEY_FALSE(is_cavium_thunderx);
 
 static u64 __maybe_unused gic_read_iar(void)
@@ -148,49 +118,7 @@ static u64 __maybe_unused gic_read_iar(void)
 	else
 		return gic_read_iar_common();
 }
-
-static void __maybe_unused gic_write_pmr(u64 val)
-{
-	asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" (val));
-}
-
-static void __maybe_unused gic_write_ctlr(u64 val)
-{
-	asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" (val));
-	isb();
-}
-
-static void __maybe_unused gic_write_grpen1(u64 val)
-{
-	asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" (val));
-	isb();
-}
-
-static void __maybe_unused gic_write_sgi1r(u64 val)
-{
-	asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
-}
-
-static void gic_enable_sre(void)
-{
-	u64 val;
-
-	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
-	val |= ICC_SRE_EL1_SRE;
-	asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" (val));
-	isb();
-
-	/*
-	 * Need to check that the SRE bit has actually been set. If
-	 * not, it means that SRE is disabled at EL2. We're going to
-	 * die painfully, and there is nothing we can do about it.
-	 *
-	 * Kindly inform the luser.
-	 */
-	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
-	if (!(val & ICC_SRE_EL1_SRE))
-		pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
-}
+#endif
 
 static void gic_enable_redist(bool enable)
 {
@@ -391,11 +319,11 @@ static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 	return 0;
 }
 
-static u64 gic_mpidr_to_affinity(u64 mpidr)
+static u64 gic_mpidr_to_affinity(unsigned long mpidr)
 {
 	u64 aff;
 
-	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
+	aff = ((u64)MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
 	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
 	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8  |
 	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
@@ -405,7 +333,7 @@ static u64 gic_mpidr_to_affinity(u64 mpidr)
 
 static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
-	u64 irqnr;
+	u32 irqnr;
 
 	do {
 		irqnr = gic_read_iar();
@@ -464,12 +392,12 @@ static void __init gic_dist_init(void)
 	 */
 	affinity = gic_mpidr_to_affinity(cpu_logical_map(smp_processor_id()));
 	for (i = 32; i < gic_data.irq_nr; i++)
-		writeq_relaxed(affinity, base + GICD_IROUTER + i * 8);
+		gic_write_irouter(affinity, base + GICD_IROUTER + i * 8);
 }
 
 static int gic_populate_rdist(void)
 {
-	u64 mpidr = cpu_logical_map(smp_processor_id());
+	unsigned long mpidr = cpu_logical_map(smp_processor_id());
 	u64 typer;
 	u32 aff;
 	int i;
@@ -495,15 +423,14 @@ static int gic_populate_rdist(void)
 		}
 
 		do {
-			typer = readq_relaxed(ptr + GICR_TYPER);
+			typer = gic_read_typer(ptr + GICR_TYPER);
 			if ((typer >> 32) == aff) {
 				u64 offset = ptr - gic_data.redist_regions[i].redist_base;
 				gic_data_rdist_rd_base() = ptr;
 				gic_data_rdist()->phys_base = gic_data.redist_regions[i].phys_base + offset;
-				pr_info("CPU%d: found redistributor %llx region %d:%pa\n",
-					smp_processor_id(),
-					(unsigned long long)mpidr,
-					i, &gic_data_rdist()->phys_base);
+				pr_info("CPU%d: found redistributor %lx region %d:%pa\n",
+					smp_processor_id(), mpidr, i,
+					&gic_data_rdist()->phys_base);
 				return 0;
 			}
 
@@ -518,15 +445,22 @@ static int gic_populate_rdist(void)
 	}
 
 	/* We couldn't even deal with ourselves... */
-	WARN(true, "CPU%d: mpidr %llx has no re-distributor!\n",
-	     smp_processor_id(), (unsigned long long)mpidr);
+	WARN(true, "CPU%d: mpidr %lx has no re-distributor!\n",
+	     smp_processor_id(), mpidr);
 	return -ENODEV;
 }
 
 static void gic_cpu_sys_reg_init(void)
 {
-	/* Enable system registers */
-	gic_enable_sre();
+	/*
+	 * Need to check that the SRE bit has actually been set. If
+	 * not, it means that SRE is disabled at EL2. We're going to
+	 * die painfully, and there is nothing we can do about it.
+	 *
+	 * Kindly inform the luser.
+	 */
+	if (!gic_enable_sre())
+		pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
 
 	/* Set priority mask register */
 	gic_write_pmr(DEFAULT_PMR_VALUE);
@@ -589,10 +523,10 @@ static struct notifier_block gic_cpu_notifier = {
 };
 
 static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
-				   u64 cluster_id)
+				   unsigned long cluster_id)
 {
 	int cpu = *base_cpu;
-	u64 mpidr = cpu_logical_map(cpu);
+	unsigned long mpidr = cpu_logical_map(cpu);
 	u16 tlist = 0;
 
 	while (cpu < nr_cpu_ids) {
@@ -653,7 +587,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 	smp_wmb();
 
 	for_each_cpu(cpu, mask) {
-		u64 cluster_id = cpu_logical_map(cpu) & ~0xffUL;
+		unsigned long cluster_id = cpu_logical_map(cpu) & ~0xffUL;
 		u16 tlist;
 
 		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
@@ -689,7 +623,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	reg = gic_dist_base(d) + GICD_IROUTER + (gic_irq(d) * 8);
 	val = gic_mpidr_to_affinity(cpu_logical_map(cpu));
 
-	writeq_relaxed(val, reg);
+	gic_write_irouter(val, reg);
 
 	/*
 	 * If the interrupt was enabled, enabled it again. Otherwise,
@@ -870,8 +804,10 @@ static const struct irq_domain_ops gic_irq_domain_ops = {
 
 static void gicv3_enable_quirks(void)
 {
+#ifdef CONFIG_ARM64
 	if (cpus_have_cap(ARM64_WORKAROUND_CAVIUM_23154))
 		static_branch_enable(&is_cavium_thunderx);
+#endif
 }
 
 static int __init gic_of_init(struct device_node *node, struct device_node *parent)
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index d0ce7ed1ac8a..a9f23cfa9c96 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -51,6 +51,19 @@
 
 #include "irq-gic-common.h"
 
+#ifdef CONFIG_ARM64
+#include <asm/cpufeature.h>
+
+static void gic_check_cpu_features(void)
+{
+	WARN_TAINT_ONCE(cpus_have_cap(ARM64_HAS_SYSREG_GIC_CPUIF),
+			TAINT_CPU_OUT_OF_SPEC,
+			"GICv3 system registers enabled, broken firmware!\n");
+}
+#else
+#define gic_check_cpu_features()	do { } while(0)
+#endif
+
 union gic_base {
 	void __iomem *common_base;
 	void __percpu * __iomem *percpu_base;
@@ -987,6 +1000,8 @@ static void __init __gic_init_bases(unsigned int gic_nr, int irq_start,
 
 	BUG_ON(gic_nr >= MAX_GIC_NR);
 
+	gic_check_cpu_features();
+
 	gic = &gic_data[gic_nr];
 #ifdef CONFIG_GIC_NON_BANKED
 	if (percpu_offset) { /* Frankein-GIC without banked registers... */
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 4e14dac282bb..6a3538ef7275 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -282,7 +282,7 @@ struct vgic_v2_cpu_if {
 };
 
 struct vgic_v3_cpu_if {
-#ifdef CONFIG_ARM_GIC_V3
+#ifdef CONFIG_KVM_ARM_VGIC_V3
 	u32		vgic_hcr;
 	u32		vgic_vmcr;
 	u32		vgic_sre;	/* Restored only, change ignored */
@@ -364,7 +364,7 @@ void kvm_vgic_set_phys_irq_active(struct irq_phys_map *map, bool active);
 int vgic_v2_probe(struct device_node *vgic_node,
 		  const struct vgic_ops **ops,
 		  const struct vgic_params **params);
-#ifdef CONFIG_ARM_GIC_V3
+#ifdef CONFIG_KVM_ARM_VGIC_V3
 int vgic_v3_probe(struct device_node *vgic_node,
 		  const struct vgic_ops **ops,
 		  const struct vgic_params **params);
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index c0c8a2ef9d90..c9ae0c6ec050 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -18,8 +18,6 @@
 #ifndef __LINUX_IRQCHIP_ARM_GIC_V3_H
 #define __LINUX_IRQCHIP_ARM_GIC_V3_H
 
-#include <asm/sysreg.h>
-
 /*
  * Distributor registers. We assume we're running non-secure, with ARE
  * being set. Secure-only and non-ARE registers are not described.
@@ -267,16 +265,16 @@
 /*
  * Hypervisor interface registers (SRE only)
  */
-#define ICH_LR_VIRTUAL_ID_MASK		((1UL << 32) - 1)
-
-#define ICH_LR_EOI			(1UL << 41)
-#define ICH_LR_GROUP			(1UL << 60)
-#define ICH_LR_HW			(1UL << 61)
-#define ICH_LR_STATE			(3UL << 62)
-#define ICH_LR_PENDING_BIT		(1UL << 62)
-#define ICH_LR_ACTIVE_BIT		(1UL << 63)
+#define ICH_LR_VIRTUAL_ID_MASK		((1ULL << 32) - 1)
+
+#define ICH_LR_EOI			(1ULL << 41)
+#define ICH_LR_GROUP			(1ULL << 60)
+#define ICH_LR_HW			(1ULL << 61)
+#define ICH_LR_STATE			(3ULL << 62)
+#define ICH_LR_PENDING_BIT		(1ULL << 62)
+#define ICH_LR_ACTIVE_BIT		(1ULL << 63)
 #define ICH_LR_PHYS_ID_SHIFT		32
-#define ICH_LR_PHYS_ID_MASK		(0x3ffUL << ICH_LR_PHYS_ID_SHIFT)
+#define ICH_LR_PHYS_ID_MASK		(0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
 
 #define ICH_MISR_EOI			(1 << 0)
 #define ICH_MISR_U			(1 << 1)
@@ -293,19 +291,8 @@
 #define ICH_VMCR_PMR_SHIFT		24
 #define ICH_VMCR_PMR_MASK		(0xffUL << ICH_VMCR_PMR_SHIFT)
 
-#define ICC_EOIR1_EL1			sys_reg(3, 0, 12, 12, 1)
-#define ICC_DIR_EL1			sys_reg(3, 0, 12, 11, 1)
-#define ICC_IAR1_EL1			sys_reg(3, 0, 12, 12, 0)
-#define ICC_SGI1R_EL1			sys_reg(3, 0, 12, 11, 5)
-#define ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
-#define ICC_CTLR_EL1			sys_reg(3, 0, 12, 12, 4)
-#define ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
-#define ICC_GRPEN1_EL1			sys_reg(3, 0, 12, 12, 7)
-
 #define ICC_IAR1_EL1_SPURIOUS		0x3ff
 
-#define ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-
 #define ICC_SRE_EL2_SRE			(1 << 0)
 #define ICC_SRE_EL2_ENABLE		(1 << 3)
 
@@ -321,54 +308,10 @@
 #define ICC_SGI1R_AFFINITY_3_SHIFT	48
 #define ICC_SGI1R_AFFINITY_3_MASK	(0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
 
-/*
- * System register definitions
- */
-#define ICH_VSEIR_EL2			sys_reg(3, 4, 12, 9, 4)
-#define ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
-#define ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
-#define ICH_MISR_EL2			sys_reg(3, 4, 12, 11, 2)
-#define ICH_EISR_EL2			sys_reg(3, 4, 12, 11, 3)
-#define ICH_ELSR_EL2			sys_reg(3, 4, 12, 11, 5)
-#define ICH_VMCR_EL2			sys_reg(3, 4, 12, 11, 7)
-
-#define __LR0_EL2(x)			sys_reg(3, 4, 12, 12, x)
-#define __LR8_EL2(x)			sys_reg(3, 4, 12, 13, x)
-
-#define ICH_LR0_EL2			__LR0_EL2(0)
-#define ICH_LR1_EL2			__LR0_EL2(1)
-#define ICH_LR2_EL2			__LR0_EL2(2)
-#define ICH_LR3_EL2			__LR0_EL2(3)
-#define ICH_LR4_EL2			__LR0_EL2(4)
-#define ICH_LR5_EL2			__LR0_EL2(5)
-#define ICH_LR6_EL2			__LR0_EL2(6)
-#define ICH_LR7_EL2			__LR0_EL2(7)
-#define ICH_LR8_EL2			__LR8_EL2(0)
-#define ICH_LR9_EL2			__LR8_EL2(1)
-#define ICH_LR10_EL2			__LR8_EL2(2)
-#define ICH_LR11_EL2			__LR8_EL2(3)
-#define ICH_LR12_EL2			__LR8_EL2(4)
-#define ICH_LR13_EL2			__LR8_EL2(5)
-#define ICH_LR14_EL2			__LR8_EL2(6)
-#define ICH_LR15_EL2			__LR8_EL2(7)
-
-#define __AP0Rx_EL2(x)			sys_reg(3, 4, 12, 8, x)
-#define ICH_AP0R0_EL2			__AP0Rx_EL2(0)
-#define ICH_AP0R1_EL2			__AP0Rx_EL2(1)
-#define ICH_AP0R2_EL2			__AP0Rx_EL2(2)
-#define ICH_AP0R3_EL2			__AP0Rx_EL2(3)
-
-#define __AP1Rx_EL2(x)			sys_reg(3, 4, 12, 9, x)
-#define ICH_AP1R0_EL2			__AP1Rx_EL2(0)
-#define ICH_AP1R1_EL2			__AP1Rx_EL2(1)
-#define ICH_AP1R2_EL2			__AP1Rx_EL2(2)
-#define ICH_AP1R3_EL2			__AP1Rx_EL2(3)
+#include <asm/arch_gicv3.h>
 
 #ifndef __ASSEMBLY__
 
-#include <linux/stringify.h>
-#include <asm/msi.h>
-
 /*
  * We need a value to serve as a irq-type for LPIs. Choose one that will
  * hopefully pique the interest of the reviewer.
@@ -386,23 +329,26 @@ struct rdists {
 	u64			flags;
 };
 
-static inline void gic_write_eoir(u64 irq)
-{
-	asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" (irq));
-	isb();
-}
-
-static inline void gic_write_dir(u64 irq)
-{
-	asm volatile("msr_s " __stringify(ICC_DIR_EL1) ", %0" : : "r" (irq));
-	isb();
-}
-
 struct irq_domain;
 int its_cpu_init(void);
 int its_init(struct device_node *node, struct rdists *rdists,
 	     struct irq_domain *domain);
 
+static inline bool gic_enable_sre(void)
+{
+	u32 val;
+
+	val = gic_read_sre();
+	if (val & ICC_SRE_EL1_SRE)
+		return true;
+
+	val |= ICC_SRE_EL1_SRE;
+	gic_write_sre(val);
+	val = gic_read_sre();
+
+	return !!(val & ICC_SRE_EL1_SRE);
+}
+
 #endif
 
 #endif
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 6bd1c9bf7ae7..77b0176b0484 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -2122,7 +2122,7 @@ static int init_vgic_model(struct kvm *kvm, int type)
 	case KVM_DEV_TYPE_ARM_VGIC_V2:
 		vgic_v2_init_emulation(kvm);
 		break;
-#ifdef CONFIG_ARM_GIC_V3
+#ifdef CONFIG_KVM_ARM_VGIC_V3
 	case KVM_DEV_TYPE_ARM_VGIC_V3:
 		vgic_v3_init_emulation(kvm);
 		break;
@@ -2284,7 +2284,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
 		block_size = KVM_VGIC_V2_CPU_SIZE;
 		alignment = SZ_4K;
 		break;
-#ifdef CONFIG_ARM_GIC_V3
+#ifdef CONFIG_KVM_ARM_VGIC_V3
 	case KVM_VGIC_V3_ADDR_TYPE_DIST:
 		type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
 		addr_ptr = &vgic->vgic_dist_base;