aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/devicetree/bindings/numa.txt275
-rw-r--r--Documentation/kernel-parameters.txt3
-rw-r--r--arch/arm64/Kconfig30
-rw-r--r--arch/arm64/include/asm/acpi.h24
-rw-r--r--arch/arm64/include/asm/mmu.h1
-rw-r--r--arch/arm64/include/asm/mmzone.h12
-rw-r--r--arch/arm64/include/asm/numa.h47
-rw-r--r--arch/arm64/include/asm/pgtable.h15
-rw-r--r--arch/arm64/include/asm/topology.h10
-rw-r--r--arch/arm64/kernel/Makefile1
-rw-r--r--arch/arm64/kernel/acpi.c11
-rw-r--r--arch/arm64/kernel/acpi_numa.c149
-rw-r--r--arch/arm64/kernel/pci.c36
-rw-r--r--arch/arm64/kernel/setup.c17
-rw-r--r--arch/arm64/kernel/smp.c6
-rw-r--r--arch/arm64/mm/Makefile1
-rw-r--r--arch/arm64/mm/init.c35
-rw-r--r--arch/arm64/mm/mm.h1
-rw-r--r--arch/arm64/mm/mmu.c2
-rw-r--r--arch/arm64/mm/numa.c402
-rw-r--r--arch/ia64/include/asm/acpi.h3
-rw-r--r--arch/ia64/kernel/acpi.c2
-rw-r--r--arch/ia64/kernel/setup.c1
-rw-r--r--arch/x86/include/asm/acpi.h1
-rw-r--r--arch/x86/kernel/acpi/apei.c3
-rw-r--r--arch/x86/mm/numa.c2
-rw-r--r--arch/x86/mm/srat.c116
-rw-r--r--drivers/acpi/Kconfig27
-rw-r--r--drivers/acpi/Makefile4
-rw-r--r--drivers/acpi/apei/Kconfig1
-rw-r--r--drivers/acpi/apei/Makefile2
-rw-r--r--drivers/acpi/apei/apei-internal.h2
-rw-r--r--drivers/acpi/apei/bert.c150
-rw-r--r--drivers/acpi/apei/hest.c18
-rw-r--r--drivers/acpi/gtdt.c367
-rw-r--r--drivers/acpi/iort.c344
-rw-r--r--drivers/acpi/numa.c224
-rw-r--r--drivers/acpi/pci_mcfg.c97
-rw-r--r--drivers/acpi/pci_root.c35
-rw-r--r--drivers/acpi/pci_root_generic.c149
-rw-r--r--drivers/acpi/scan.c3
-rw-r--r--drivers/acpi/spcr.c111
-rw-r--r--drivers/clocksource/arm_arch_timer.c187
-rw-r--r--drivers/firmware/efi/arm-init.c8
-rw-r--r--drivers/firmware/efi/libstub/fdt.c24
-rw-r--r--drivers/irqchip/Kconfig1
-rw-r--r--drivers/irqchip/irq-gic-common.c13
-rw-r--r--drivers/irqchip/irq-gic-common.h3
-rw-r--r--drivers/irqchip/irq-gic-v3-its-pci-msi.c84
-rw-r--r--drivers/irqchip/irq-gic-v3-its.c182
-rw-r--r--drivers/irqchip/irq-gic-v3.c183
-rw-r--r--drivers/irqchip/irq-gic.c87
-rw-r--r--drivers/net/ethernet/smsc/smc91x.c10
-rw-r--r--drivers/of/Kconfig3
-rw-r--r--drivers/of/Makefile1
-rw-r--r--drivers/of/address.c116
-rw-r--r--drivers/of/fdt.c11
-rw-r--r--drivers/of/of_numa.c211
-rw-r--r--drivers/pci/Kconfig3
-rw-r--r--drivers/pci/Makefile2
-rw-r--r--drivers/pci/ecam.c161
-rw-r--r--drivers/pci/ecam.h72
-rw-r--r--drivers/pci/host/Kconfig1
-rw-r--r--drivers/pci/host/pci-host-common.c114
-rw-r--r--drivers/pci/host/pci-host-common.h47
-rw-r--r--drivers/pci/host/pci-host-generic.c52
-rw-r--r--drivers/pci/host/pci-thunder-ecam.c39
-rw-r--r--drivers/pci/host/pci-thunder-pem.c92
-rw-r--r--drivers/pci/msi.c11
-rw-r--r--drivers/pci/pci.c150
-rw-r--r--drivers/pci/probe.c2
-rw-r--r--drivers/tty/serial/amba-pl011.c56
-rw-r--r--drivers/tty/serial/earlycon.c19
-rw-r--r--include/acpi/acpi_numa.h4
-rw-r--r--include/acpi/actbl2.h7
-rw-r--r--include/clocksource/arm_arch_timer.h32
-rw-r--r--include/kvm/arm_vgic.h7
-rw-r--r--include/linux/acpi.h41
-rw-r--r--include/linux/iort.h38
-rw-r--r--include/linux/irqchip/arm-gic-common.h34
-rw-r--r--include/linux/irqchip/arm-gic-v3.h4
-rw-r--r--include/linux/of.h9
-rw-r--r--include/linux/of_address.h9
-rw-r--r--include/linux/of_fdt.h2
-rw-r--r--include/linux/pci-acpi.h14
-rw-r--r--include/linux/pci.h11
-rw-r--r--include/linux/serial_core.h6
-rw-r--r--virt/kvm/arm/arch_timer.c40
-rw-r--r--virt/kvm/arm/vgic-v2.c61
-rw-r--r--virt/kvm/arm/vgic-v3.c47
-rw-r--r--virt/kvm/arm/vgic.c50
91 files changed, 4210 insertions, 891 deletions
diff --git a/Documentation/devicetree/bindings/numa.txt b/Documentation/devicetree/bindings/numa.txt
new file mode 100644
index 000000000000..21b35053ca5a
--- /dev/null
+++ b/Documentation/devicetree/bindings/numa.txt
@@ -0,0 +1,275 @@
+==============================================================================
+NUMA binding description.
+==============================================================================
+
+==============================================================================
+1 - Introduction
+==============================================================================
+
+Systems employing a Non Uniform Memory Access (NUMA) architecture contain
+collections of hardware resources including processors, memory, and I/O buses,
+that comprise what is commonly known as a NUMA node.
+Processor accesses to memory within the local NUMA node is generally faster
+than processor accesses to memory outside of the local NUMA node.
+DT defines interfaces that allow the platform to convey NUMA node
+topology information to OS.
+
+==============================================================================
+2 - numa-node-id
+==============================================================================
+
+For the purpose of identification, each NUMA node is associated with a unique
+token known as a node id. For the purpose of this binding
+a node id is a 32-bit integer.
+
+A device node is associated with a NUMA node by the presence of a
+numa-node-id property which contains the node id of the device.
+
+Example:
+ /* numa node 0 */
+ numa-node-id = <0>;
+
+ /* numa node 1 */
+ numa-node-id = <1>;
+
+==============================================================================
+3 - distance-map
+==============================================================================
+
+The optional device tree node distance-map describes the relative
+distance (memory latency) between all numa nodes.
+
+- compatible : Should at least contain "numa-distance-map-v1".
+
+- distance-matrix
+ This property defines a matrix to describe the relative distances
+ between all numa nodes.
+ It is represented as a list of node pairs and their relative distance.
+
+ Note:
+ 1. Each entry represents distance from first node to second node.
+ The distances are equal in either direction.
+ 2. The distance from a node to self (local distance) is represented
+ with value 10 and all internode distance should be represented with
+ a value greater than 10.
+ 3. distance-matrix should have entries in lexicographical ascending
+ order of nodes.
+ 4. There must be only one device node distance-map which must
+ reside in the root node.
+ 5. If the distance-map node is not present, a default
+ distance-matrix is used.
+
+Example:
+ 4 nodes connected in mesh/ring topology as below,
+
+ 0_______20______1
+ | |
+ | |
+ 20 20
+ | |
+ | |
+ |_______________|
+ 3 20 2
+
+ if relative distance for each hop is 20,
+ then internode distance would be,
+ 0 -> 1 = 20
+ 1 -> 2 = 20
+ 2 -> 3 = 20
+ 3 -> 0 = 20
+ 0 -> 2 = 40
+ 1 -> 3 = 40
+
+ and dt presentation for this distance matrix is,
+
+ distance-map {
+ compatible = "numa-distance-map-v1";
+ distance-matrix = <0 0 10>,
+ <0 1 20>,
+ <0 2 40>,
+ <0 3 20>,
+ <1 0 20>,
+ <1 1 10>,
+ <1 2 20>,
+ <1 3 40>,
+ <2 0 40>,
+ <2 1 20>,
+ <2 2 10>,
+ <2 3 20>,
+ <3 0 20>,
+ <3 1 40>,
+ <3 2 20>,
+ <3 3 10>;
+ };
+
+==============================================================================
+4 - Example dts
+==============================================================================
+
+Dual socket system consists of 2 boards connected through ccn bus and
+each board having one socket/soc of 8 cpus, memory and pci bus.
+
+ memory@c00000 {
+ device_type = "memory";
+ reg = <0x0 0xc00000 0x0 0x80000000>;
+ /* node 0 */
+ numa-node-id = <0>;
+ };
+
+ memory@10000000000 {
+ device_type = "memory";
+ reg = <0x100 0x0 0x0 0x80000000>;
+ /* node 1 */
+ numa-node-id = <1>;
+ };
+
+ cpus {
+ #address-cells = <2>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x0>;
+ enable-method = "psci";
+ /* node 0 */
+ numa-node-id = <0>;
+ };
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x1>;
+ enable-method = "psci";
+ numa-node-id = <0>;
+ };
+ cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x2>;
+ enable-method = "psci";
+ numa-node-id = <0>;
+ };
+ cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x3>;
+ enable-method = "psci";
+ numa-node-id = <0>;
+ };
+ cpu@4 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x4>;
+ enable-method = "psci";
+ numa-node-id = <0>;
+ };
+ cpu@5 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x5>;
+ enable-method = "psci";
+ numa-node-id = <0>;
+ };
+ cpu@6 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x6>;
+ enable-method = "psci";
+ numa-node-id = <0>;
+ };
+ cpu@7 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x7>;
+ enable-method = "psci";
+ numa-node-id = <0>;
+ };
+ cpu@8 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x8>;
+ enable-method = "psci";
+ /* node 1 */
+ numa-node-id = <1>;
+ };
+ cpu@9 {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0x9>;
+ enable-method = "psci";
+ numa-node-id = <1>;
+ };
+ cpu@a {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0xa>;
+ enable-method = "psci";
+ numa-node-id = <1>;
+ };
+ cpu@b {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0xb>;
+ enable-method = "psci";
+ numa-node-id = <1>;
+ };
+ cpu@c {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0xc>;
+ enable-method = "psci";
+ numa-node-id = <1>;
+ };
+ cpu@d {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0xd>;
+ enable-method = "psci";
+ numa-node-id = <1>;
+ };
+ cpu@e {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0xe>;
+ enable-method = "psci";
+ numa-node-id = <1>;
+ };
+ cpu@f {
+ device_type = "cpu";
+ compatible = "arm,armv8";
+ reg = <0x0 0xf>;
+ enable-method = "psci";
+ numa-node-id = <1>;
+ };
+ };
+
+ pcie0: pcie0@848000000000 {
+ compatible = "arm,armv8";
+ device_type = "pci";
+ bus-range = <0 255>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ reg = <0x8480 0x00000000 0 0x10000000>; /* Configuration space */
+ ranges = <0x03000000 0x8010 0x00000000 0x8010 0x00000000 0x70 0x00000000>;
+ /* node 0 */
+ numa-node-id = <0>;
+ };
+
+ pcie1: pcie1@948000000000 {
+ compatible = "arm,armv8";
+ device_type = "pci";
+ bus-range = <0 255>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ reg = <0x9480 0x00000000 0 0x10000000>; /* Configuration space */
+ ranges = <0x03000000 0x9010 0x00000000 0x9010 0x00000000 0x70 0x00000000>;
+ /* node 1 */
+ numa-node-id = <1>;
+ };
+
+ distance-map {
+ compatible = "numa-distance-map-v1";
+ distance-matrix = <0 0 10>,
+ <0 1 20>,
+ <1 1 10>;
+ };
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 0b3de80ec8f6..21fe24e46910 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -570,6 +570,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
bootmem_debug [KNL] Enable bootmem allocator debug messages.
+ bert_disable [ACPI]
+ Disable BERT OS support on buggy BIOSes.
+
bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards)
bttv.radio= Most important insmod options are available as
kernel args too.
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4f436220384f..0189dd5dc770 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2,7 +2,10 @@ config ARM64
def_bool y
select ACPI_CCA_REQUIRED if ACPI
select ACPI_GENERIC_GSI if ACPI
+ select ACPI_PCI_HOST_GENERIC if ACPI
select ACPI_REDUCED_HARDWARE_ONLY if ACPI
+ select ACPI_SPCR_TABLE if ACPI
+ select HAVE_ACPI_APEI if ACPI
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_ELF_RANDOMIZE
@@ -11,6 +14,7 @@ config ARM64
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_SUPPORTS_ATOMIC_RMW
+ select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_WANT_OPTIONAL_GPIOLIB
select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
select ARCH_WANT_FRAME_POINTERS
@@ -76,6 +80,7 @@ config ARM64
select HAVE_HW_BREAKPOINT if PERF_EVENTS
select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_MEMBLOCK
+ select HAVE_MEMBLOCK_NODE_MAP if NUMA
select HAVE_PATA_PLATFORM
select HAVE_PERF_EVENTS
select HAVE_PERF_REGS
@@ -98,6 +103,7 @@ config ARM64
select SYSCTL_EXCEPTION_TRACE
select HAVE_CONTEXT_TRACKING
select HAVE_ARM_SMCCC
+ select OF_NUMA if NUMA && OF
help
ARM 64-bit (AArch64) Linux support.
@@ -546,6 +552,30 @@ config HOTPLUG_CPU
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu.
+# Common NUMA Features
+config NUMA
+ bool "Numa Memory Allocation and Scheduler Support"
+ depends on SMP
+ help
+ Enable NUMA (Non Uniform Memory Access) support.
+
+ The kernel will try to allocate memory used by a CPU on the
+ local memory of the CPU and add some more
+ NUMA awareness to the kernel.
+
+config NODES_SHIFT
+ int "Maximum NUMA Nodes (as a power of 2)"
+ range 1 10
+ default "2"
+ depends on NEED_MULTIPLE_NODES
+ help
+ Specify the maximum number of NUMA Nodes available on the target
+ system. Increases memory reserved to accommodate various tables.
+
+config USE_PERCPU_NUMA_NODE_ID
+ def_bool y
+ depends on NUMA
+
source kernel/Kconfig.preempt
source kernel/Kconfig.hz
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index aee323b13802..355a28fb7261 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -17,6 +17,7 @@
#include <asm/cputype.h>
#include <asm/smp_plat.h>
+#include <asm/tlbflush.h>
/* Macros for consistency checks of the GICC subtable of MADT */
#define ACPI_MADT_GICC_LENGTH \
@@ -110,7 +111,28 @@ static inline const char *acpi_get_enable_method(int cpu)
}
#ifdef CONFIG_ACPI_APEI
+#define acpi_disable_cmcff 1
pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
-#endif
+
+/*
+ * This inline function is used in IRQ context (by GHES driver now),
+ * see ghes_iounmap_irq and ghes_iounmap_nmi in drivers/acpi/apei/ghes.c.
+ * The page mapped is reserved for firmware in kernel. This invalidate TLB
+ * maintenance should be broadcasted safely to make sure that all the cores
+ * will do TLB invalidation, then get the right pages.
+ */
+static inline void arch_apei_flush_tlb_one(unsigned long addr)
+{
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+}
+#endif /* CONFIG_ACPI_APEI */
+
+#ifdef CONFIG_ACPI_NUMA
+int arm64_acpi_numa_init(void);
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid);
+#else
+static inline int arm64_acpi_numa_init(void) { return -ENOSYS; }
+static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; }
+#endif /* CONFIG_ACPI_NUMA */
#endif /*_ASM_ACPI_H*/
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 990124a67eeb..97b1d8f26b9c 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -29,6 +29,7 @@ typedef struct {
#define ASID(mm) ((mm)->context.id.counter & 0xffff)
extern void paging_init(void);
+extern void bootmem_init(void);
extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
extern void init_mem_pgprot(void);
extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
diff --git a/arch/arm64/include/asm/mmzone.h b/arch/arm64/include/asm/mmzone.h
new file mode 100644
index 000000000000..a0de9e6ba73f
--- /dev/null
+++ b/arch/arm64/include/asm/mmzone.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_MMZONE_H
+#define __ASM_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+#include <asm/numa.h>
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid) (node_data[(nid)])
+
+#endif /* CONFIG_NUMA */
+#endif /* __ASM_MMZONE_H */
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
new file mode 100644
index 000000000000..600887e491fd
--- /dev/null
+++ b/arch/arm64/include/asm/numa.h
@@ -0,0 +1,47 @@
+#ifndef __ASM_NUMA_H
+#define __ASM_NUMA_H
+
+#include <asm/topology.h>
+
+#ifdef CONFIG_NUMA
+
+#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2)
+
+/* currently, arm64 implements flat NUMA topology */
+#define parent_node(node) (node)
+
+int __node_distance(int from, int to);
+#define node_distance(a, b) __node_distance(a, b)
+
+extern nodemask_t numa_nodes_parsed __initdata;
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+void numa_clear_node(unsigned int cpu);
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+const struct cpumask *cpumask_of_node(int node);
+#else
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const struct cpumask *cpumask_of_node(int node)
+{
+ return node_to_cpumask_map[node];
+}
+#endif
+
+void __init arm64_numa_init(void);
+int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+void __init numa_set_distance(int from, int to, int distance);
+void __init numa_free_distance(void);
+void __init early_map_cpu_to_node(unsigned int cpu, int nid);
+void numa_store_cpu_info(unsigned int cpu);
+
+#else /* CONFIG_NUMA */
+
+static inline void numa_store_cpu_info(unsigned int cpu) { }
+static inline void arm64_numa_init(void) { }
+static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
+
+#endif /* CONFIG_NUMA */
+
+#endif /* __ASM_NUMA_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 989fef16d461..89b8f205a14c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -272,6 +272,21 @@ static inline pgprot_t mk_sect_prot(pgprot_t prot)
return __pgprot(pgprot_val(prot) & ~PTE_TABLE_BIT);
}
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * See the comment in include/asm-generic/pgtable.h
+ */
+static inline int pte_protnone(pte_t pte)
+{
+ return (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) == PTE_PROT_NONE;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+ return pte_protnone(pmd_pte(pmd));
+}
+#endif
+
/*
* THP definitions.
*/
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index a3e9d6fdbf21..8b57339823e9 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -22,6 +22,16 @@ void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
const struct cpumask *cpu_coregroup_mask(int cpu);
+#ifdef CONFIG_NUMA
+
+struct pci_bus;
+int pcibus_to_node(struct pci_bus *bus);
+#define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \
+ cpu_all_mask : \
+ cpumask_of_node(pcibus_to_node(bus)))
+
+#endif /* CONFIG_NUMA */
+
#include <asm-generic/topology.h>
#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 3793003e16a2..69569c6fa97f 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -42,6 +42,7 @@ arm64-obj-$(CONFIG_EFI) += efi.o efi-entry.stub.o
arm64-obj-$(CONFIG_PCI) += pci.o
arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o
arm64-obj-$(CONFIG_ACPI) += acpi.o
+arm64-obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o
arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o
arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o
arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index d1ce8e2f98b9..f331ebb70d87 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -24,6 +24,7 @@
#include <linux/memblock.h>
#include <linux/of_fdt.h>
#include <linux/smp.h>
+#include <linux/serial_core.h>
#include <asm/cputype.h>
#include <asm/cpu_ops.h>
@@ -189,7 +190,7 @@ void __init acpi_boot_table_init(void)
*/
if (param_acpi_off ||
(!param_acpi_force && of_scan_flat_dt(dt_scan_depth1_nodes, NULL)))
- return;
+ goto done;
/*
* ACPI is disabled at this point. Enable it in order to parse
@@ -209,6 +210,14 @@ void __init acpi_boot_table_init(void)
if (!param_acpi_force)
disable_acpi();
}
+
+done:
+ if (acpi_disabled) {
+ if (earlycon_init_is_deferred)
+ early_init_dt_scan_chosen_stdout();
+ } else {
+ parse_spcr(earlycon_init_is_deferred);
+ }
}
#ifdef CONFIG_ACPI_APEI
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
new file mode 100644
index 000000000000..94a6b35fab92
--- /dev/null
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -0,0 +1,149 @@
+/*
+ * ACPI 5.1 based NUMA setup for ARM64
+ * Lots of code was borrowed from arch/x86/mm/srat.c
+ *
+ * Copyright 2004 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2013-2016, Linaro Ltd.
+ * Author: Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
+ *
+ * Called from acpi_numa_init while reading the SRAT and SLIT tables.
+ * Assumes all memory regions belonging to a single proximity domain
+ * are in one chunk. Holes between them will be included in the node.
+ */
+
+#define pr_fmt(fmt) "ACPI: NUMA: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/bootmem.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include <acpi/processor.h>
+#include <asm/numa.h>
+
+static int cpus_in_srat;
+
+struct __node_cpu_hwid {
+ u32 node_id; /* logical node containing this CPU */
+ u64 cpu_hwid; /* MPIDR for this CPU */
+};
+
+static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = {
+[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} };
+
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid)
+{
+ int i;
+
+ for (i = 0; i < cpus_in_srat; i++) {
+ if (hwid == early_node_cpu_hwid[i].cpu_hwid)
+ return early_node_cpu_hwid[i].node_id;
+ }
+
+ return NUMA_NO_NODE;
+}
+
+static int __init get_mpidr_in_madt(int acpi_id, u64 *mpidr)
+{
+ unsigned long madt_end, entry;
+ struct acpi_table_madt *madt;
+ acpi_size tbl_size;
+
+ if (ACPI_FAILURE(acpi_get_table_with_size(ACPI_SIG_MADT, 0,
+ (struct acpi_table_header **)&madt, &tbl_size)))
+ return -ENODEV;
+
+ entry = (unsigned long)madt;
+ madt_end = entry + madt->header.length;
+
+ /* Parse all entries looking for a match. */
+ entry += sizeof(struct acpi_table_madt);
+ while (entry + sizeof(struct acpi_subtable_header) < madt_end) {
+ struct acpi_subtable_header *header =
+ (struct acpi_subtable_header *)entry;
+
+ if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT) {
+ struct acpi_madt_generic_interrupt *gicc =
+ container_of(header,
+ struct acpi_madt_generic_interrupt, header);
+
+ if ((gicc->flags & ACPI_MADT_ENABLED) &&
+ (gicc->uid == acpi_id)) {
+ *mpidr = gicc->arm_mpidr;
+ early_acpi_os_unmap_memory(madt, tbl_size);
+ return 0;
+ }
+ }
+ entry += header->length;
+ }
+
+ early_acpi_os_unmap_memory(madt, tbl_size);
+ return -ENODEV;
+}
+
+/* Callback for Proximity Domain -> ACPI processor UID mapping */
+void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
+{
+ int pxm, node;
+ u64 mpidr;
+
+ if (srat_disabled())
+ return;
+
+ if (pa->header.length < sizeof(struct acpi_srat_gicc_affinity)) {
+ pr_err("SRAT: Invalid SRAT header length: %d\n",
+ pa->header.length);
+ bad_srat();
+ return;
+ }
+
+ if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
+ return;
+
+ if (cpus_in_srat >= NR_CPUS) {
+ pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n",
+ NR_CPUS);
+ return;
+ }
+
+ pxm = pa->proximity_domain;
+ node = acpi_map_pxm_to_node(pxm);
+
+ if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+ pr_err("SRAT: Too many proximity domains %d\n", pxm);
+ bad_srat();
+ return;
+ }
+
+ if (get_mpidr_in_madt(pa->acpi_processor_uid, &mpidr)) {
+ pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n",
+ pxm, pa->acpi_processor_uid);
+ bad_srat();
+ return;
+ }
+
+ early_node_cpu_hwid[cpus_in_srat].node_id = node;
+ early_node_cpu_hwid[cpus_in_srat].cpu_hwid = mpidr;
+ node_set(node, numa_nodes_parsed);
+ cpus_in_srat++;
+ pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n",
+ pxm, mpidr, node);
+}
+
+int __init arm64_acpi_numa_init(void)
+{
+ int ret;
+
+ ret = acpi_numa_init();
+ if (ret)
+ return ret;
+
+ return srat_disabled() ? -EINVAL : 0;
+}
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index c72de668e1d4..ea120a847806 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -17,6 +17,7 @@
#include <linux/mm.h>
#include <linux/of_pci.h>
#include <linux/of_platform.h>
+#include <linux/pci-acpi.h>
#include <linux/slab.h>
/*
@@ -50,35 +51,36 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
}
/*
- * Try to assign the IRQ number from DT when adding a new device
+ * Try to assign the IRQ number when probing a new device
*/
-int pcibios_add_device(struct pci_dev *dev)
+int pcibios_alloc_irq(struct pci_dev *dev)
{
- dev->irq = of_irq_parse_and_map_pci(dev, 0, 0);
+ if (acpi_disabled)
+ dev->irq = of_irq_parse_and_map_pci(dev, 0, 0);
+#ifdef CONFIG_ACPI
+ else
+ return acpi_pci_irq_enable(dev);
+#endif
return 0;
}
-/*
- * raw_pci_read/write - Platform-specific PCI config space access.
- */
-int raw_pci_read(unsigned int domain, unsigned int bus,
- unsigned int devfn, int reg, int len, u32 *val)
+void pcibios_add_bus(struct pci_bus *bus)
{
- return -ENXIO;
+ acpi_pci_add_bus(bus);
}
-int raw_pci_write(unsigned int domain, unsigned int bus,
- unsigned int devfn, int reg, int len, u32 val)
+void pcibios_remove_bus(struct pci_bus *bus)
{
- return -ENXIO;
+ acpi_pci_remove_bus(bus);
}
-#ifdef CONFIG_ACPI
-/* Root bridge scanning */
-struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
+#ifdef CONFIG_NUMA
+
+int pcibus_to_node(struct pci_bus *bus)
{
- /* TODO: Should be revisited when implementing PCI on ACPI */
- return NULL;
+ return dev_to_node(&bus->dev);
}
+EXPORT_SYMBOL(pcibus_to_node);
+
#endif
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 9dc67769b6a4..0ad4b7770c05 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -53,6 +53,7 @@
#include <asm/cpufeature.h>
#include <asm/cpu_ops.h>
#include <asm/kasan.h>
+#include <asm/numa.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
@@ -327,6 +328,12 @@ void __init setup_arch(char **cmdline_p)
acpi_boot_table_init();
paging_init();
+
+ if (acpi_disabled)
+ unflatten_device_tree();
+
+ bootmem_init();
+
relocate_initrd();
kasan_init();
@@ -335,12 +342,11 @@ void __init setup_arch(char **cmdline_p)
early_ioremap_reset();
- if (acpi_disabled) {
- unflatten_device_tree();
+ if (acpi_disabled)
psci_dt_init();
- } else {
+ else
psci_acpi_init();
- }
+
xen_early_init();
cpu_read_bootcpu_ops();
@@ -379,6 +385,9 @@ static int __init topology_init(void)
{
int i;
+ for_each_online_node(i)
+ register_one_node(i);
+
for_each_possible_cpu(i) {
struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
cpu->hotpluggable = 1;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b2d5f4ee9a1c..6c7ef8f25a90 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -45,6 +45,7 @@
#include <asm/cputype.h>
#include <asm/cpu_ops.h>
#include <asm/mmu_context.h>
+#include <asm/numa.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/processor.h>
@@ -166,6 +167,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
static void smp_store_cpu_info(unsigned int cpuid)
{
store_cpu_topology(cpuid);
+ numa_store_cpu_info(cpuid);
}
/*
@@ -522,6 +524,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
*/
acpi_set_mailbox_entry(cpu_count, processor);
+ early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid));
+
cpu_count++;
}
@@ -595,6 +599,8 @@ static void __init of_parse_and_init_cpus(void)
pr_debug("cpu logical map 0x%llx\n", hwid);
cpu_logical_map(cpu_count) = hwid;
+
+ early_map_cpu_to_node(cpu_count, of_node_to_nid(dn));
next:
cpu_count++;
}
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 57f57fde5722..54bb209cae8e 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,6 +4,7 @@ obj-y := dma-mapping.o extable.o fault.o init.o \
context.o proc.o pageattr.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_ARM64_PTDUMP) += dump.o
+obj-$(CONFIG_NUMA) += numa.o
obj-$(CONFIG_KASAN) += kasan_init.o
KASAN_SANITIZE_kasan_init.o := n
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index ea989d83ea9b..b1ff1511f472 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -40,6 +40,7 @@
#include <asm/kasan.h>
#include <asm/kernel-pgtable.h>
#include <asm/memory.h>
+#include <asm/numa.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/sizes.h>
@@ -86,6 +87,21 @@ static phys_addr_t __init max_zone_dma_phys(void)
return min(offset + (1ULL << 32), memblock_end_of_DRAM());
}
+#ifdef CONFIG_NUMA
+
+static void __init zone_sizes_init(unsigned long min, unsigned long max)
+{
+ unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
+
+ if (IS_ENABLED(CONFIG_ZONE_DMA))
+ max_zone_pfns[ZONE_DMA] = PFN_DOWN(max_zone_dma_phys());
+ max_zone_pfns[ZONE_NORMAL] = max;
+
+ free_area_init_nodes(max_zone_pfns);
+}
+
+#else
+
static void __init zone_sizes_init(unsigned long min, unsigned long max)
{
struct memblock_region *reg;
@@ -126,6 +142,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
free_area_init_node(0, zone_size, min, zhole_size);
}
+#endif /* CONFIG_NUMA */
+
#ifdef CONFIG_HAVE_ARCH_PFN_VALID
int pfn_valid(unsigned long pfn)
{
@@ -142,10 +160,15 @@ static void __init arm64_memory_present(void)
static void __init arm64_memory_present(void)
{
struct memblock_region *reg;
+ int nid = 0;
- for_each_memblock(memory, reg)
- memory_present(0, memblock_region_memory_base_pfn(reg),
- memblock_region_memory_end_pfn(reg));
+ for_each_memblock(memory, reg) {
+#ifdef CONFIG_NUMA
+ nid = reg->nid;
+#endif
+ memory_present(nid, memblock_region_memory_base_pfn(reg),
+ memblock_region_memory_end_pfn(reg));
+ }
}
#endif
@@ -245,7 +268,6 @@ void __init arm64_memblock_init(void)
dma_contiguous_reserve(arm64_dma_phys_limit);
memblock_allow_resize();
- memblock_dump_all();
}
void __init bootmem_init(void)
@@ -257,6 +279,9 @@ void __init bootmem_init(void)
early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
+ max_pfn = max_low_pfn = max;
+
+ arm64_numa_init();
/*
* Sparsemem tries to allocate bootmem in memory_present(), so must be
* done after the fixed reservations.
@@ -267,7 +292,7 @@ void __init bootmem_init(void)
zone_sizes_init(min, max);
high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
- max_pfn = max_low_pfn = max;
+ memblock_dump_all();
}
#ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/arm64/mm/mm.h b/arch/arm64/mm/mm.h
index ef47d99b5cbc..71fe98985455 100644
--- a/arch/arm64/mm/mm.h
+++ b/arch/arm64/mm/mm.h
@@ -1,3 +1,2 @@
-extern void __init bootmem_init(void);
void fixup_init(void);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f3e5c74233f3..267903b59ced 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -564,8 +564,6 @@ void __init paging_init(void)
*/
memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE,
SWAPPER_DIR_SIZE - PAGE_SIZE);
-
- bootmem_init();
}
/*
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
new file mode 100644
index 000000000000..c7fe3ec70774
--- /dev/null
+++ b/arch/arm64/mm/numa.c
@@ -0,0 +1,402 @@
+/*
+ * NUMA support, based on the x86 implementation.
+ *
+ * Copyright (C) 2015 Cavium Inc.
+ * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com>
+ *
+ * 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/>.
+ */
+
+#include <linux/acpi.h>
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_data);
+nodemask_t numa_nodes_parsed __initdata;
+static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
+
+static int numa_distance_cnt;
+static u8 *numa_distance;
+static bool numa_off;
+
+static __init int numa_parse_early_param(char *opt)
+{
+ if (!opt)
+ return -EINVAL;
+ if (!strncmp(opt, "off", 3)) {
+ pr_info("%s\n", "NUMA turned off");
+ numa_off = true;
+ }
+ return 0;
+}
+early_param("numa", numa_parse_early_param);
+
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+ if (WARN_ON(node >= nr_node_ids))
+ return cpu_none_mask;
+
+ if (WARN_ON(node_to_cpumask_map[node] == NULL))
+ return cpu_online_mask;
+
+ return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+
+#endif
+
+static void map_cpu_to_node(unsigned int cpu, int nid)
+{
+ set_cpu_numa_node(cpu, nid);
+ if (nid >= 0)
+ cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+}
+
+void numa_clear_node(unsigned int cpu)
+{
+ int nid = cpu_to_node(cpu);
+
+ if (nid >= 0)
+ cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+ set_cpu_numa_node(cpu, NUMA_NO_NODE);
+}
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: cpumask_of_node() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+static void __init setup_node_to_cpumask_map(void)
+{
+ unsigned int cpu;
+ int node;
+
+ /* setup nr_node_ids if not done yet */
+ if (nr_node_ids == MAX_NUMNODES)
+ setup_nr_node_ids();
+
+ /* allocate and clear the mapping */
+ for (node = 0; node < nr_node_ids; node++) {
+ alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+ cpumask_clear(node_to_cpumask_map[node]);
+ }
+
+ for_each_possible_cpu(cpu)
+ set_cpu_numa_node(cpu, NUMA_NO_NODE);
+
+ /* cpumask_of_node() will now work */
+ pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+/*
+ * Set the cpu to node and mem mapping
+ */
+void numa_store_cpu_info(unsigned int cpu)
+{
+ map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
+}
+
+void __init early_map_cpu_to_node(unsigned int cpu, int nid)
+{
+ /* fallback to node 0 */
+ if (nid < 0 || nid >= MAX_NUMNODES)
+ nid = 0;
+
+ cpu_to_node_map[cpu] = nid;
+}
+
+/**
+ * numa_add_memblk - Set node id to memblk
+ * @nid: NUMA node ID of the new memblk
+ * @start: Start address of the new memblk
+ * @end: End address of the new memblk
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_add_memblk(int nid, u64 start, u64 end)
+{
+ int ret;
+
+ ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
+ if (ret < 0) {
+ pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
+ start, (end - 1), nid);
+ return ret;
+ }
+
+ node_set(nid, numa_nodes_parsed);
+ pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
+ start, (end - 1), nid);
+ return ret;
+}
+
+/**
+ * Initialize NODE_DATA for a node on the local memory
+ */
+static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
+{
+ const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
+ u64 nd_pa;
+ void *nd;
+ int tnid;
+
+ pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+ nid, start_pfn << PAGE_SHIFT,
+ (end_pfn << PAGE_SHIFT) - 1);
+
+ nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+ nd = __va(nd_pa);
+
+ /* report and initialize */
+ pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n",
+ nd_pa, nd_pa + nd_size - 1);
+ tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+ if (tnid != nid)
+ pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid);
+
+ node_data[nid] = nd;
+ memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+ NODE_DATA(nid)->node_id = nid;
+ NODE_DATA(nid)->node_start_pfn = start_pfn;
+ NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
+}
+
+/**
+ * numa_free_distance
+ *
+ * The current table is freed.
+ */
+void __init numa_free_distance(void)
+{
+ size_t size;
+
+ if (!numa_distance)
+ return;
+
+ size = numa_distance_cnt * numa_distance_cnt *
+ sizeof(numa_distance[0]);
+
+ memblock_free(__pa(numa_distance), size);
+ numa_distance_cnt = 0;
+ numa_distance = NULL;
+}
+
+/**
+ *
+ * Create a new NUMA distance table.
+ *
+ */
+static int __init numa_alloc_distance(void)
+{
+ size_t size;
+ u64 phys;
+ int i, j;
+
+ size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
+ phys = memblock_find_in_range(0, PFN_PHYS(max_pfn),
+ size, PAGE_SIZE);
+ if (WARN_ON(!phys))
+ return -ENOMEM;
+
+ memblock_reserve(phys, size);
+
+ numa_distance = __va(phys);
+ numa_distance_cnt = nr_node_ids;
+
+ /* fill with the default distances */
+ for (i = 0; i < numa_distance_cnt; i++)
+ for (j = 0; j < numa_distance_cnt; j++)
+ numa_distance[i * numa_distance_cnt + j] = i == j ?
+ LOCAL_DISTANCE : REMOTE_DISTANCE;
+
+ pr_debug("NUMA: Initialized distance table, cnt=%d\n",
+ numa_distance_cnt);
+
+ return 0;
+}
+
+/**
+ * numa_set_distance - Set inter node NUMA distance from node to node.
+ * @from: the 'from' node to set distance
+ * @to: the 'to' node to set distance
+ * @distance: NUMA distance
+ *
+ * Set the distance from node @from to @to to @distance.
+ * If distance table doesn't exist, a warning is printed.
+ *
+ * If @from or @to is higher than the highest known node or lower than zero
+ * or @distance doesn't make sense, the call is ignored.
+ *
+ */
+void __init numa_set_distance(int from, int to, int distance)
+{
+ if (!numa_distance) {
+ pr_warn_once("NUMA: Warning: distance table not allocated yet\n");
+ return;
+ }
+
+ if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
+ from < 0 || to < 0) {
+ pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+ from, to, distance);
+ return;
+ }
+
+ if ((u8)distance != distance ||
+ (from == to && distance != LOCAL_DISTANCE)) {
+ pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+ from, to, distance);
+ return;
+ }
+
+ numa_distance[from * numa_distance_cnt + to] = distance;
+}
+
+/**
+ * Return NUMA distance @from to @to
+ */
+int __node_distance(int from, int to)
+{
+ if (from >= numa_distance_cnt || to >= numa_distance_cnt)
+ return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+ return numa_distance[from * numa_distance_cnt + to];
+}
+EXPORT_SYMBOL(__node_distance);
+
+static int __init numa_register_nodes(void)
+{
+ int nid;
+ struct memblock_region *mblk;
+
+ /* Check that valid nid is set to memblks */
+ for_each_memblock(memory, mblk)
+ if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) {
+ pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+ mblk->nid, mblk->base,
+ mblk->base + mblk->size - 1);
+ return -EINVAL;
+ }
+
+ /* Finally register nodes. */
+ for_each_node_mask(nid, numa_nodes_parsed) {
+ unsigned long start_pfn, end_pfn;
+
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+ setup_node_data(nid, start_pfn, end_pfn);
+ node_set_online(nid);
+ }
+
+ /* Setup online nodes to actual nodes*/
+ node_possible_map = numa_nodes_parsed;
+
+ return 0;
+}
+
+static int __init numa_init(int (*init_func)(void))
+{
+ int ret;
+
+ nodes_clear(numa_nodes_parsed);
+ nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
+ numa_free_distance();
+
+ ret = numa_alloc_distance();
+ if (ret < 0)
+ return ret;
+
+ ret = init_func();
+ if (ret < 0)
+ return ret;
+
+ if (nodes_empty(numa_nodes_parsed))
+ return -EINVAL;
+
+ ret = numa_register_nodes();
+ if (ret < 0)
+ return ret;
+
+ setup_node_to_cpumask_map();
+
+ /* init boot processor */
+ cpu_to_node_map[0] = 0;
+ map_cpu_to_node(0, 0);
+
+ return 0;
+}
+
+/**
+ * dummy_numa_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node (node 0) and add memory blocks that cover all
+ * allowed memory. It is unlikely that this function fails.
+ */
+static int __init dummy_numa_init(void)
+{
+ int ret;
+ struct memblock_region *mblk;
+
+ if (numa_off)
+ pr_info("NUMA disabled\n"); /* Forced off on command line. */
+ else
+ pr_info("No NUMA configuration found\n");
+ pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
+ 0LLU, PFN_PHYS(max_pfn) - 1);
+
+ for_each_memblock(memory, mblk) {
+ ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
+ if (!ret)
+ continue;
+
+ pr_err("NUMA init failed\n");
+ return ret;
+ }
+
+ numa_off = true;
+ return 0;
+}
+
+/**
+ * arm64_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds. The
+ * last fallback is dummy single node config encomapssing whole memory.
+ */
+void __init arm64_numa_init(void)
+{
+ if (!numa_off) {
+ if (!acpi_disabled && !numa_init(arm64_acpi_numa_init))
+ return;
+ if (acpi_disabled && !numa_init(of_numa_init))
+ return;
+ }
+
+ numa_init(dummy_numa_init);
+}
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index aa0fdf125aba..a3d0211970e9 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -140,6 +140,9 @@ static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus)
}
}
}
+
+extern void acpi_numa_fixup(void);
+
#endif /* CONFIG_ACPI_NUMA */
#endif /*__KERNEL__*/
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index b1698bc042c8..92b7bc956795 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -524,7 +524,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
return 0;
}
-void __init acpi_numa_arch_fixup(void)
+void __init acpi_numa_fixup(void)
{
int i, j, node_from, node_to;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 2029a38a72ae..afddb3e80a29 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -552,6 +552,7 @@ setup_arch (char **cmdline_p)
early_acpi_boot_init();
# ifdef CONFIG_ACPI_NUMA
acpi_numa_init();
+ acpi_numa_fixup();
# ifdef CONFIG_ACPI_HOTPLUG_CPU
prefill_possible_map();
# endif
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 94c18ebfd68c..65f1e95cade9 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -145,7 +145,6 @@ static inline void disable_acpi(void) { }
#define ARCH_HAS_POWER_INIT 1
#ifdef CONFIG_ACPI_NUMA
-extern int acpi_numa;
extern int x86_acpi_numa_init(void);
#endif /* CONFIG_ACPI_NUMA */
diff --git a/arch/x86/kernel/acpi/apei.c b/arch/x86/kernel/acpi/apei.c
index c280df6b2aa2..ea3046e0b0cf 100644
--- a/arch/x86/kernel/acpi/apei.c
+++ b/arch/x86/kernel/acpi/apei.c
@@ -24,9 +24,6 @@ int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data)
struct acpi_hest_ia_corrected *cmc;
struct acpi_hest_ia_error_bank *mc_bank;
- if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
- return 0;
-
cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
if (!cmc->enabled)
return 0;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index f70c1ff46125..57673f5cb120 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -1,4 +1,5 @@
/* Common code for 32 and 64-bit NUMA */
+#include <linux/acpi.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
@@ -15,7 +16,6 @@
#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/dma.h>
-#include <asm/acpi.h>
#include <asm/amd_nb.h>
#include "numa_internal.h"
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index b5f821881465..b1ecff460a46 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -15,8 +15,6 @@
#include <linux/bitmap.h>
#include <linux/module.h>
#include <linux/topology.h>
-#include <linux/bootmem.h>
-#include <linux/memblock.h>
#include <linux/mm.h>
#include <asm/proto.h>
#include <asm/numa.h>
@@ -24,51 +22,6 @@
#include <asm/apic.h>
#include <asm/uv/uv.h>
-int acpi_numa __initdata;
-
-static __init int setup_node(int pxm)
-{
- return acpi_map_pxm_to_node(pxm);
-}
-
-static __init void bad_srat(void)
-{
- printk(KERN_ERR "SRAT: SRAT not used.\n");
- acpi_numa = -1;
-}
-
-static __init inline int srat_disabled(void)
-{
- return acpi_numa < 0;
-}
-
-/*
- * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them. I/O localities are
- * not supported at this point.
- */
-void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
-{
- int i, j;
-
- for (i = 0; i < slit->locality_count; i++) {
- const int from_node = pxm_to_node(i);
-
- if (from_node == NUMA_NO_NODE)
- continue;
-
- for (j = 0; j < slit->locality_count; j++) {
- const int to_node = pxm_to_node(j);
-
- if (to_node == NUMA_NO_NODE)
- continue;
-
- numa_set_distance(from_node, to_node,
- slit->entry[slit->locality_count * i + j]);
- }
- }
-}
-
/* Callback for Proximity Domain -> x2APIC mapping */
void __init
acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
@@ -91,7 +44,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
pxm, apic_id);
return;
}
- node = setup_node(pxm);
+ node = acpi_map_pxm_to_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
bad_srat();
@@ -104,7 +57,6 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
}
set_apicid_to_node(apic_id, node);
node_set(node, numa_nodes_parsed);
- acpi_numa = 1;
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n",
pxm, apic_id, node);
}
@@ -127,7 +79,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
pxm = pa->proximity_domain_lo;
if (acpi_srat_revision >= 2)
pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
- node = setup_node(pxm);
+ node = acpi_map_pxm_to_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
bad_srat();
@@ -146,74 +98,10 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
set_apicid_to_node(apic_id, node);
node_set(node, numa_nodes_parsed);
- acpi_numa = 1;
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n",
pxm, apic_id, node);
}
-#ifdef CONFIG_MEMORY_HOTPLUG
-static inline int save_add_info(void) {return 1;}
-#else
-static inline int save_add_info(void) {return 0;}
-#endif
-
-/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
-int __init
-acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
-{
- u64 start, end;
- u32 hotpluggable;
- int node, pxm;
-
- if (srat_disabled())
- goto out_err;
- if (ma->header.length != sizeof(struct acpi_srat_mem_affinity))
- goto out_err_bad_srat;
- if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
- goto out_err;
- hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
- if (hotpluggable && !save_add_info())
- goto out_err;
-
- start = ma->base_address;
- end = start + ma->length;
- pxm = ma->proximity_domain;
- if (acpi_srat_revision <= 1)
- pxm &= 0xff;
-
- node = setup_node(pxm);
- if (node < 0) {
- printk(KERN_ERR "SRAT: Too many proximity domains.\n");
- goto out_err_bad_srat;
- }
-
- if (numa_add_memblk(node, start, end) < 0)
- goto out_err_bad_srat;
-
- node_set(node, numa_nodes_parsed);
-
- pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n",
- node, pxm,
- (unsigned long long) start, (unsigned long long) end - 1,
- hotpluggable ? " hotplug" : "",
- ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : "");
-
- /* Mark hotplug range in memblock. */
- if (hotpluggable && memblock_mark_hotplug(start, ma->length))
- pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
- (unsigned long long)start, (unsigned long long)end - 1);
-
- max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
-
- return 0;
-out_err_bad_srat:
- bad_srat();
-out_err:
- return -1;
-}
-
-void __init acpi_numa_arch_fixup(void) {}
-
int __init x86_acpi_numa_init(void)
{
int ret;
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 82b96ee8624c..64d8fce05adb 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -57,6 +57,9 @@ config ACPI_SYSTEM_POWER_STATES_SUPPORT
config ACPI_CCA_REQUIRED
bool
+config IORT_TABLE
+ bool
+
config ACPI_DEBUGGER
bool "AML debugger interface"
select ACPI_DEBUG
@@ -77,6 +80,9 @@ config ACPI_DEBUGGER_USER
endif
+config ACPI_SPCR_TABLE
+ bool
+
config ACPI_SLEEP
bool
depends on SUSPEND || HIBERNATION
@@ -291,8 +297,8 @@ config ACPI_THERMAL
config ACPI_NUMA
bool "NUMA support"
depends on NUMA
- depends on (X86 || IA64)
- default y if IA64_GENERIC || IA64_SGI_SN2
+ depends on (X86 || IA64 || ARM64)
+ default y if IA64_GENERIC || IA64_SGI_SN2 || ARM64
config ACPI_CUSTOM_DSDT_FILE
string "Custom DSDT Table file to include"
@@ -343,6 +349,14 @@ config ACPI_PCI_SLOT
i.e., segment/bus/device/function tuples, with physical slots in
the system. If you are unsure, say N.
+config ACPI_PCI_HOST_GENERIC
+ bool
+ select PCI_ECAM
+ help
+ Select this config option from the architecture Kconfig,
+ if it is preferred to enable ACPI PCI host controller driver which
+ has no arch-specific assumptions.
+
config X86_PM_TIMER
bool "Power Management Timer Support" if EXPERT
depends on X86
@@ -521,4 +535,13 @@ config XPOWER_PMIC_OPREGION
endif
+config ACPI_GTDT
+ bool "ACPI GTDT Support"
+ depends on ARM64
+ help
+ GTDT (Generic Timer Description Table) provides information
+ for per-processor timers and Platform (memory-mapped) timers
+ for ARM platforms. Select this option to provide information
+ needed for the timers init.
+
endif # ACPI
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index edeb2d1d99be..2b8899c28d59 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -40,6 +40,7 @@ acpi-$(CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC) += processor_pdc.o
acpi-y += ec.o
acpi-$(CONFIG_ACPI_DOCK) += dock.o
acpi-y += pci_root.o pci_link.o pci_irq.o
+obj-$(CONFIG_ACPI_PCI_HOST_GENERIC) += pci_root_generic.o pci_mcfg.o
acpi-y += acpi_lpss.o acpi_apd.o
acpi-y += acpi_platform.o
acpi-y += acpi_pnp.o
@@ -80,7 +81,9 @@ obj-$(CONFIG_ACPI_EC_DEBUGFS) += ec_sys.o
obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
obj-$(CONFIG_ACPI_BGRT) += bgrt.o
obj-$(CONFIG_ACPI_CPPC_LIB) += cppc_acpi.o
+obj-$(CONFIG_ACPI_SPCR_TABLE) += spcr.o
obj-$(CONFIG_ACPI_DEBUGGER_USER) += acpi_dbg.o
+obj-$(CONFIG_IORT_TABLE) += iort.o
# processor has its own "processor." module_param namespace
processor-y := processor_driver.o
@@ -98,5 +101,6 @@ obj-$(CONFIG_ACPI_EXTLOG) += acpi_extlog.o
obj-$(CONFIG_PMIC_OPREGION) += pmic/intel_pmic.o
obj-$(CONFIG_CRC_PMIC_OPREGION) += pmic/intel_pmic_crc.o
obj-$(CONFIG_XPOWER_PMIC_OPREGION) += pmic/intel_pmic_xpower.o
+obj-$(CONFIG_ACPI_GTDT) += gtdt.o
video-objs += acpi_video.o video_detect.o
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index b0140c8fc733..b037c5c6db97 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -8,6 +8,7 @@ config ACPI_APEI
bool "ACPI Platform Error Interface (APEI)"
select MISC_FILESYSTEMS
select PSTORE
+ select EFI if ARM64
select UEFI_CPER
depends on HAVE_ACPI_APEI
help
diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile
index 5d575a955940..e50573de25f1 100644
--- a/drivers/acpi/apei/Makefile
+++ b/drivers/acpi/apei/Makefile
@@ -3,4 +3,4 @@ obj-$(CONFIG_ACPI_APEI_GHES) += ghes.o
obj-$(CONFIG_ACPI_APEI_EINJ) += einj.o
obj-$(CONFIG_ACPI_APEI_ERST_DEBUG) += erst-dbg.o
-apei-y := apei-base.o hest.o erst.o
+apei-y := apei-base.o hest.o erst.o bert.o
diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index 16129c78b489..6e9f14c0a71b 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -1,6 +1,6 @@
/*
* apei-internal.h - ACPI Platform Error Interface internal
- * definations.
+ * definitions.
*/
#ifndef APEI_INTERNAL_H
diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c
new file mode 100644
index 000000000000..a05b5c0cf181
--- /dev/null
+++ b/drivers/acpi/apei/bert.c
@@ -0,0 +1,150 @@
+/*
+ * APEI Boot Error Record Table (BERT) support
+ *
+ * Copyright 2011 Intel Corp.
+ * Author: Huang Ying <ying.huang@intel.com>
+ *
+ * Under normal circumstances, when a hardware error occurs, the error
+ * handler receives control and processes the error. This gives OSPM a
+ * chance to process the error condition, report it, and optionally attempt
+ * recovery. In some cases, the system is unable to process an error.
+ * For example, system firmware or a management controller may choose to
+ * reset the system or the system might experience an uncontrolled crash
+ * or reset.The boot error source is used to report unhandled errors that
+ * occurred in a previous boot. This mechanism is described in the BERT
+ * table.
+ *
+ * For more information about BERT, please refer to ACPI Specification
+ * version 4.0, section 17.3.1
+ *
+ * This file is licensed under GPLv2.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+
+#include "apei-internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "BERT: " fmt
+
+static int bert_disable;
+
+static void __init bert_print_all(struct acpi_bert_region *region,
+ unsigned int region_len)
+{
+ struct acpi_hest_generic_status *estatus =
+ (struct acpi_hest_generic_status *)region;
+ int remain = region_len;
+ u32 estatus_len;
+
+ if (!estatus->block_status)
+ return;
+
+ while (remain > sizeof(struct acpi_bert_region)) {
+ if (cper_estatus_check(estatus)) {
+ pr_err(FW_BUG "Invalid error record.\n");
+ return;
+ }
+
+ estatus_len = cper_estatus_len(estatus);
+ if (remain < estatus_len) {
+ pr_err(FW_BUG "Truncated status block (length: %u).\n",
+ estatus_len);
+ return;
+ }
+
+ pr_info_once("Error records from previous boot:\n");
+
+ cper_estatus_print(KERN_INFO HW_ERR, estatus);
+
+ /*
+ * Because the boot error source is "one-time polled" type,
+ * clear Block Status of current Generic Error Status Block,
+ * once it's printed.
+ */
+ estatus->block_status = 0;
+
+ estatus = (void *)estatus + estatus_len;
+ /* No more error records. */
+ if (!estatus->block_status)
+ return;
+
+ remain -= estatus_len;
+ }
+}
+
+static int __init setup_bert_disable(char *str)
+{
+ bert_disable = 1;
+
+ return 0;
+}
+__setup("bert_disable", setup_bert_disable);
+
+static int __init bert_check_table(struct acpi_table_bert *bert_tab)
+{
+ if (bert_tab->header.length < sizeof(struct acpi_table_bert) ||
+ bert_tab->region_length < sizeof(struct acpi_bert_region))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int __init bert_init(void)
+{
+ struct acpi_bert_region *boot_error_region;
+ struct acpi_table_bert *bert_tab;
+ unsigned int region_len;
+ acpi_status status;
+ int rc = 0;
+
+ if (acpi_disabled)
+ return 0;
+
+ if (bert_disable) {
+ pr_info("Boot Error Record Table support is disabled.\n");
+ return 0;
+ }
+
+ status = acpi_get_table(ACPI_SIG_BERT, 0, (struct acpi_table_header **)&bert_tab);
+ if (status == AE_NOT_FOUND)
+ return 0;
+
+ if (ACPI_FAILURE(status)) {
+ pr_err("get table failed, %s.\n", acpi_format_exception(status));
+ return -EINVAL;
+ }
+
+ rc = bert_check_table(bert_tab);
+ if (rc) {
+ pr_err(FW_BUG "table invalid.\n");
+ return rc;
+ }
+
+ region_len = bert_tab->region_length;
+ if (!request_mem_region(bert_tab->address, region_len, "APEI BERT")) {
+ pr_err("Can't request iomem region <%016llx-%016llx>.\n",
+ (unsigned long long)bert_tab->address,
+ (unsigned long long)bert_tab->address + region_len - 1);
+ return -EIO;
+ }
+
+ boot_error_region = ioremap_cache(bert_tab->address, region_len);
+ if (boot_error_region) {
+ bert_print_all(boot_error_region, region_len);
+ iounmap(boot_error_region);
+ } else {
+ rc = -ENOMEM;
+ }
+
+ release_mem_region(bert_tab->address, region_len);
+
+ return rc;
+}
+
+late_initcall(bert_init);
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 20b3fcf4007c..792a0d988d13 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -123,7 +123,18 @@ EXPORT_SYMBOL_GPL(apei_hest_parse);
*/
static int __init hest_parse_cmc(struct acpi_hest_header *hest_hdr, void *data)
{
- return arch_apei_enable_cmcff(hest_hdr, data);
+ if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
+ return 0;
+
+ if (!acpi_disable_cmcff)
+ return !arch_apei_enable_cmcff(hest_hdr, data);
+
+ return 0;
+}
+
+static inline int __init hest_ia32_init(void)
+{
+ return apei_hest_parse(hest_parse_cmc, NULL);
}
struct ghes_arr {
@@ -232,8 +243,9 @@ void __init acpi_hest_init(void)
goto err;
}
- if (!acpi_disable_cmcff)
- apei_hest_parse(hest_parse_cmc, NULL);
+ rc = hest_ia32_init();
+ if (rc)
+ goto err;
if (!ghes_disable) {
rc = apei_hest_parse(hest_parse_ghes_count, &ghes_count);
diff --git a/drivers/acpi/gtdt.c b/drivers/acpi/gtdt.c
new file mode 100644
index 000000000000..d15ea919edec
--- /dev/null
+++ b/drivers/acpi/gtdt.c
@@ -0,0 +1,367 @@
+/*
+ * ARM Specific GTDT table Support
+ *
+ * Copyright (C) 2015, Linaro Ltd.
+ * Author: Fu Wei <fu.wei@linaro.org>
+ * Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+static u32 platform_timer_count __initdata;
+static int gtdt_timers_existence __initdata;
+
+/*
+ * Get some basic info from GTDT table, and init the global variables above
+ * for all timers initialization of Generic Timer.
+ * This function does some validation on GTDT table, and will be run only once.
+ */
+static void __init *platform_timer_info_init(struct acpi_table_header *table)
+{
+ void *gtdt_end, *platform_timer_struct, *platform_timer;
+ struct acpi_gtdt_header *header;
+ struct acpi_table_gtdt *gtdt;
+ u32 i;
+
+ gtdt = container_of(table, struct acpi_table_gtdt, header);
+ if (!gtdt) {
+ pr_err("GTDT: table pointer error, bad table.\n");
+ return NULL;
+ }
+ gtdt_end = (void *)table + table->length;
+ gtdt_timers_existence |= ARCH_CP15_TIMER;
+
+ if (table->revision < 2) {
+ pr_info("GTDT: Revision:%d doesn't support Platform Timers.\n",
+ table->revision);
+ return NULL;
+ }
+
+ platform_timer_count = gtdt->platform_timer_count;
+ if (!platform_timer_count) {
+ pr_info("GTDT: No Platform Timer structures.\n");
+ return NULL;
+ }
+
+ platform_timer_struct = (void *)gtdt + gtdt->platform_timer_offset;
+ if (platform_timer_struct < (void *)table +
+ sizeof(struct acpi_table_gtdt)) {
+ pr_err("GTDT: Platform Timer pointer error, bad table.\n");
+ return NULL;
+ }
+
+ platform_timer = platform_timer_struct;
+ for (i = 0; i < platform_timer_count; i++) {
+ if (platform_timer > gtdt_end) {
+ pr_warn("GTDT: subtable pointer overflows, bad table\n");
+ platform_timer_count = i;
+ break;
+ }
+ header = (struct acpi_gtdt_header *)platform_timer;
+ if (header->type == ACPI_GTDT_TYPE_TIMER_BLOCK)
+ gtdt_timers_existence |= ARCH_MEM_TIMER;
+ else if (header->type == ACPI_GTDT_TYPE_WATCHDOG)
+ gtdt_timers_existence |= ARCH_WD_TIMER;
+ platform_timer += header->length;
+ }
+
+ return platform_timer_struct;
+}
+
+static int __init map_generic_timer_interrupt(u32 interrupt, u32 flags)
+{
+ int trigger, polarity;
+
+ if (!interrupt)
+ return 0;
+
+ trigger = (flags & ACPI_GTDT_INTERRUPT_MODE) ? ACPI_EDGE_SENSITIVE
+ : ACPI_LEVEL_SENSITIVE;
+
+ polarity = (flags & ACPI_GTDT_INTERRUPT_POLARITY) ? ACPI_ACTIVE_LOW
+ : ACPI_ACTIVE_HIGH;
+
+ return acpi_register_gsi(NULL, interrupt, trigger, polarity);
+}
+
+/*
+ * Get the necessary info of arch_timer from GTDT table.
+ */
+int __init gtdt_arch_timer_data_init(struct acpi_table_header *table,
+ struct arch_timer_data *data)
+{
+ struct acpi_table_gtdt *gtdt;
+
+ if (acpi_disabled)
+ return -EINVAL;
+
+ if (!gtdt_timers_existence)
+ platform_timer_info_init(table);
+
+ gtdt = container_of(table, struct acpi_table_gtdt, header);
+ if (!gtdt || !data)
+ return -EINVAL;
+
+ data->phys_secure_ppi =
+ map_generic_timer_interrupt(gtdt->secure_el1_interrupt,
+ gtdt->secure_el1_flags);
+
+ data->phys_nonsecure_ppi =
+ map_generic_timer_interrupt(gtdt->non_secure_el1_interrupt,
+ gtdt->non_secure_el1_flags);
+
+ data->virt_ppi =
+ map_generic_timer_interrupt(gtdt->virtual_timer_interrupt,
+ gtdt->virtual_timer_flags);
+
+ data->hyp_ppi =
+ map_generic_timer_interrupt(gtdt->non_secure_el2_interrupt,
+ gtdt->non_secure_el2_flags);
+
+ data->c3stop = !(gtdt->non_secure_el1_flags & ACPI_GTDT_ALWAYS_ON);
+
+ return 0;
+}
+
+bool __init gtdt_timer_is_available(int type)
+{
+ return gtdt_timers_existence | type;
+}
+
+/*
+ * Helper function for getting the pointer of platform_timer_struct.
+ */
+static void __init *get_platform_timer_struct(struct acpi_table_header *table)
+{
+ struct acpi_table_gtdt *gtdt;
+
+ gtdt = container_of(table, struct acpi_table_gtdt, header);
+ if (gtdt)
+ return (void *)gtdt + gtdt->platform_timer_offset;
+
+ pr_err("GTDT: table pointer error, bad table.\n");
+ return NULL;
+}
+
+ /*
+ * Get the pointer of GT Block Structure in GTDT table
+ */
+void __init *gtdt_gt_block(struct acpi_table_header *table, int index)
+{
+ struct acpi_gtdt_header *header;
+ void *platform_timer;
+ int i, j;
+
+ if (!gtdt_timers_existence)
+ platform_timer = platform_timer_info_init(table);
+ else
+ platform_timer = get_platform_timer_struct(table);
+
+ if (!gtdt_timer_is_available(ARCH_MEM_TIMER))
+ return NULL;
+
+ for (i = 0, j = 0; i < platform_timer_count; i++) {
+ header = (struct acpi_gtdt_header *)platform_timer;
+ if (header->type == ACPI_GTDT_TYPE_TIMER_BLOCK && j++ == index)
+ return platform_timer;
+ platform_timer += header->length;
+ }
+
+ return NULL;
+}
+
+/*
+ * Get the timer_count(the number of timer frame) of a GT Block in GTDT table
+ */
+u32 __init gtdt_gt_timer_count(struct acpi_gtdt_timer_block *gt_block)
+{
+ if (!gt_block) {
+ pr_err("GTDT: invalid GT Block baseaddr.\n");
+ return 0;
+ }
+
+ return gt_block->timer_count;
+}
+
+/*
+ * Get the physical address of GT Block in GTDT table
+ */
+void __init *gtdt_gt_cntctlbase(struct acpi_gtdt_timer_block *gt_block)
+{
+ if (!gt_block) {
+ pr_err("GTDT: invalid GT Block baseaddr.\n");
+ return NULL;
+ }
+
+ return (void *)gt_block->block_address;
+}
+
+/*
+ * Helper function for getting the pointer of a timer frame in GT block.
+ */
+static void __init *gtdt_gt_timer_frame(struct acpi_gtdt_timer_block *gt_block,
+ int index)
+{
+ void *timer_frame;
+
+ if (!(gt_block && gt_block->timer_count))
+ return NULL;
+
+ timer_frame = (void *)gt_block + gt_block->timer_offset +
+ sizeof(struct acpi_gtdt_timer_entry) * index;
+
+ if (timer_frame <= (void *)gt_block + gt_block->header.length -
+ sizeof(struct acpi_gtdt_timer_entry))
+ return timer_frame;
+
+ pr_err("GTDT: invalid GT Block timer frame entry addr.\n");
+ return NULL;
+}
+
+/*
+ * Get the GT timer Frame Number(ID) in a GT Block Timer Structure.
+ * The maximum Frame Number(ID) is (ARCH_TIMER_MEM_MAX_FRAME - 1),
+ * so returning ARCH_TIMER_MEM_MAX_FRAME means error.
+ */
+u32 __init gtdt_gt_frame_number(struct acpi_gtdt_timer_block *gt_block,
+ int index)
+{
+ struct acpi_gtdt_timer_entry *frame;
+
+ frame = (struct acpi_gtdt_timer_entry *)gtdt_gt_timer_frame(gt_block,
+ index);
+ if (frame)
+ return frame->frame_number;
+
+ return ARCH_TIMER_MEM_MAX_FRAME;
+}
+
+/*
+ * Get the GT timer Frame data in a GT Block Timer Structure
+ */
+int __init gtdt_gt_timer_data(struct acpi_gtdt_timer_block *gt_block,
+ int index, bool virt,
+ struct arch_timer_mem_data *data)
+{
+ struct acpi_gtdt_timer_entry *frame;
+
+ frame = (struct acpi_gtdt_timer_entry *)gtdt_gt_timer_frame(gt_block,
+ index);
+ if (!frame)
+ return -EINVAL;
+
+ data->cntbase_phy = (phys_addr_t)frame->base_address;
+ if (virt)
+ data->irq = map_generic_timer_interrupt(
+ frame->virtual_timer_interrupt,
+ frame->virtual_timer_flags);
+ else
+ data->irq = map_generic_timer_interrupt(frame->timer_interrupt,
+ frame->timer_flags);
+
+ return 0;
+}
+
+/*
+ * Initialize a SBSA generic Watchdog platform device info from GTDT
+ */
+static int __init gtdt_import_sbsa_gwdt(struct acpi_gtdt_watchdog *wd,
+ int index)
+{
+ struct platform_device *pdev;
+ int irq = map_generic_timer_interrupt(wd->timer_interrupt,
+ wd->timer_flags);
+ /*
+ * According to SBSA specification the size of refresh and control
+ * frames of SBSA Generic Watchdog is SZ_4K(Offset 0x000 – 0xFFF).
+ */
+ struct resource res[] = {
+ DEFINE_RES_IRQ(irq),
+ DEFINE_RES_MEM(wd->control_frame_address, SZ_4K),
+ DEFINE_RES_MEM(wd->refresh_frame_address, SZ_4K),
+ };
+
+ pr_debug("GTDT: a Watchdog GT(0x%llx/0x%llx gsi:%u flags:0x%x)\n",
+ wd->refresh_frame_address, wd->control_frame_address,
+ wd->timer_interrupt, wd->timer_flags);
+
+ if (!(wd->refresh_frame_address &&
+ wd->control_frame_address &&
+ wd->timer_interrupt)) {
+ pr_err("GTDT: failed geting the device info.\n");
+ return -EINVAL;
+ }
+
+ if (irq < 0) {
+ pr_err("GTDT: failed to register GSI of the Watchdog GT.\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Add a platform device named "sbsa-gwdt" to match the platform driver.
+ * "sbsa-gwdt": SBSA(Server Base System Architecture) Generic Watchdog
+ * The platform driver (like drivers/watchdog/sbsa_gwdt.c)can get device
+ * info below by matching this name.
+ */
+ pdev = platform_device_register_simple("sbsa-gwdt", index, res,
+ ARRAY_SIZE(res));
+ if (IS_ERR(pdev)) {
+ acpi_unregister_gsi(wd->timer_interrupt);
+ return PTR_ERR(pdev);
+ }
+
+ return 0;
+}
+
+static int __init gtdt_sbsa_gwdt_parse(struct acpi_table_header *table)
+{
+ struct acpi_gtdt_header *header;
+ void *platform_timer;
+ int i, gwdt_index;
+ int ret = 0;
+
+ /*
+ * At this proint, we have got and validate some info about platform
+ * timer in platform_timer_info_init.
+ */
+ if (!gtdt_timer_is_available(ARCH_WD_TIMER))
+ return -EINVAL;
+
+ platform_timer = get_platform_timer_struct(table);
+
+ for (i = 0, gwdt_index = 0; i < platform_timer_count; i++) {
+ header = (struct acpi_gtdt_header *)platform_timer;
+ if (header->type == ACPI_GTDT_TYPE_WATCHDOG) {
+ ret = gtdt_import_sbsa_gwdt(platform_timer, gwdt_index);
+ if (ret)
+ pr_err("GTDT: failed to import subtable %d\n",
+ i);
+ else
+ gwdt_index++;
+ }
+ platform_timer += header->length;
+ }
+
+ return ret;
+}
+
+static int __init gtdt_sbsa_gwdt_init(void)
+{
+ if (acpi_disabled)
+ return 0;
+
+ return acpi_table_parse(ACPI_SIG_GTDT, gtdt_sbsa_gwdt_parse);
+}
+
+device_initcall(gtdt_sbsa_gwdt_init);
diff --git a/drivers/acpi/iort.c b/drivers/acpi/iort.c
new file mode 100644
index 000000000000..226eb6d6f92b
--- /dev/null
+++ b/drivers/acpi/iort.c
@@ -0,0 +1,344 @@
+/*
+ * Copyright (C) 2016, Semihalf
+ * Author: Tomasz Nowicki <tn@semihalf.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * This file implements early detection/parsing of I/O mapping
+ * reported to OS through firmware via I/O Remapping Table (IORT)
+ * IORT document number: ARM DEN 0049A
+ */
+
+#define pr_fmt(fmt) "ACPI: IORT: " fmt
+
+#include <linux/export.h>
+#include <linux/iort.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+
+struct iort_its_msi_chip {
+ struct list_head list;
+ struct fwnode_handle *fw_node;
+ u32 translation_id;
+};
+
+typedef acpi_status (*iort_find_node_callback)
+ (struct acpi_iort_node *node, void *context);
+
+/* Root pointer to the mapped IORT table */
+static struct acpi_table_header *iort_table;
+
+static LIST_HEAD(iort_msi_chip_list);
+
+/**
+ * iort_register_domain_token() - register domain token and related ITS ID
+ * to the list from where we can get it back
+ * later on.
+ * @translation_id: ITS ID
+ * @token: domain token
+ *
+ * Returns: 0 on success, -ENOMEM if not memory when allocating list element.
+ */
+int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node)
+{
+ struct iort_its_msi_chip *its_msi_chip;
+
+ its_msi_chip = kzalloc(sizeof(*its_msi_chip), GFP_KERNEL);
+ if (!its_msi_chip)
+ return -ENOMEM;
+
+ its_msi_chip->fw_node = fw_node;
+ its_msi_chip->translation_id = trans_id;
+
+ list_add(&its_msi_chip->list, &iort_msi_chip_list);
+ return 0;
+}
+
+/**
+ * iort_unregister_domain_token() - unregister domain token based on ITS ID.
+ * @translation_id: ITS ID
+ *
+ * Returns: none.
+ */
+void iort_deregister_domain_token(int trans_id)
+{
+ struct iort_its_msi_chip *its_msi_chip, *t;
+
+ list_for_each_entry_safe(its_msi_chip, t, &iort_msi_chip_list, list) {
+ if (its_msi_chip->translation_id == trans_id) {
+ list_del(&its_msi_chip->list);
+ kfree(its_msi_chip);
+ break;
+ }
+ }
+}
+
+/**
+ * iort_find_its_domain_token() - find domain token based on given ITS ID.
+ * @translation_id: ITS ID
+ *
+ * Returns: domain token when find on the list, NULL otherwise.
+ */
+struct fwnode_handle *iort_its_find_domain_token(int trans_id)
+{
+ struct iort_its_msi_chip *its_msi_chip;
+
+ list_for_each_entry(its_msi_chip, &iort_msi_chip_list, list) {
+ if (its_msi_chip->translation_id == trans_id)
+ return its_msi_chip->fw_node;
+ }
+
+ return NULL;
+}
+
+static struct acpi_iort_node *
+iort_scan_node(enum acpi_iort_node_type type,
+ iort_find_node_callback callback, void *context)
+{
+ struct acpi_iort_node *iort_node, *iort_end;
+ struct acpi_table_iort *iort;
+ int i;
+
+ if (!iort_table)
+ return NULL;
+
+ /*
+ * iort_table and iort both point to the start of IORT table, but
+ * have different struct types
+ */
+ iort = (struct acpi_table_iort *)iort_table;
+
+ /* Get the first IORT node */
+ iort_node = ACPI_ADD_PTR(struct acpi_iort_node, iort,
+ iort->node_offset);
+ iort_end = ACPI_ADD_PTR(struct acpi_iort_node, iort_table,
+ iort_table->length);
+
+ for (i = 0; i < iort->node_count; i++) {
+ if (iort_node >= iort_end) {
+ pr_err("iort node pointer overflows, bad table\n");
+ return NULL;
+ }
+
+ if (iort_node->type == type) {
+ if (ACPI_SUCCESS(callback(iort_node, context)))
+ return iort_node;
+ }
+
+ iort_node = ACPI_ADD_PTR(struct acpi_iort_node, iort_node,
+ iort_node->length);
+ }
+
+ return NULL;
+}
+
+static acpi_status
+iort_find_dev_callback(struct acpi_iort_node *node, void *context)
+{
+ struct acpi_iort_root_complex *pci_rc;
+ struct device *dev = context;
+ struct pci_bus *bus;
+
+ switch (node->type) {
+ case ACPI_IORT_NODE_PCI_ROOT_COMPLEX:
+ bus = to_pci_bus(dev);
+ pci_rc = (struct acpi_iort_root_complex *)node->node_data;
+
+ /*
+ * It is assumed that PCI segment numbers maps one-to-one
+ * with root complexes. Each segment number can represent only
+ * one root complex.
+ */
+ if (pci_rc->pci_segment_number == pci_domain_nr(bus))
+ return AE_OK;
+
+ break;
+ }
+
+ return AE_NOT_FOUND;
+}
+
+static struct acpi_iort_node *
+iort_dev_map_rid(struct acpi_iort_node *node, u32 rid_in,
+ u32 *rid_out)
+{
+
+ if (!node)
+ goto out;
+
+ /* Go upstream */
+ while (node->type != ACPI_IORT_NODE_ITS_GROUP) {
+ struct acpi_iort_id_mapping *id;
+ int i, found = 0;
+
+ /* Exit when no mapping array */
+ if (!node->mapping_offset || !node->mapping_count)
+ return NULL;
+
+ id = ACPI_ADD_PTR(struct acpi_iort_id_mapping, node,
+ node->mapping_offset);
+
+ for (i = 0, found = 0; i < node->mapping_count; i++, id++) {
+ /*
+ * Single mapping is not translation rule,
+ * lets move on for this case
+ */
+ if (id->flags & ACPI_IORT_ID_SINGLE_MAPPING) {
+ if (node->type != ACPI_IORT_NODE_SMMU) {
+ rid_in = id->output_base;
+ found = 1;
+ break;
+ }
+
+ pr_warn(FW_BUG "[node %p type %d] SINGLE MAPPING flag not allowed for SMMU node, skipping ID map\n",
+ node, node->type);
+ continue;
+ }
+
+ if (rid_in < id->input_base ||
+ (rid_in > id->input_base + id->id_count))
+ continue;
+
+ rid_in = id->output_base + (rid_in - id->input_base);
+ found = 1;
+ break;
+ }
+
+ if (!found)
+ return NULL;
+
+ /* Firmware bug! */
+ if (!id->output_reference) {
+ pr_err(FW_BUG "[node %p type %d] ID map has NULL parent reference\n",
+ node, node->type);
+ return NULL;
+ }
+
+ node = ACPI_ADD_PTR(struct acpi_iort_node, iort_table,
+ id->output_reference);
+ }
+
+out:
+ if (rid_out)
+ *rid_out = rid_in;
+ return node;
+}
+
+static struct acpi_iort_node *
+iort_its_find_node_and_map_rid(struct pci_dev *pdev, u32 req_id, u32 *dev_id)
+{
+ struct pci_bus *pbus = pdev->bus;
+ struct acpi_iort_node *node;
+
+ /* Find a PCI root bus */
+ while (!pci_is_root_bus(pbus))
+ pbus = pbus->parent;
+
+
+ node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX,
+ iort_find_dev_callback, &pbus->dev);
+ if (!node) {
+ dev_err(&pdev->dev, "can't find related IORT node\n");
+ return NULL;
+ }
+
+ return iort_dev_map_rid(node, req_id, dev_id);
+}
+
+/**
+ * iort_pci_domain_get_msi_rid() - find MSI RID based on PCI device ID
+ * @pdev: The PCI device
+ * @req_id: The PCI device requester ID
+ *
+ * Returns: MSI RID on success, input requester ID otherwise
+ */
+u32 iort_pci_get_msi_rid(struct pci_dev *pdev, u32 req_id)
+{
+ u32 dev_id;
+
+ if (!iort_its_find_node_and_map_rid(pdev, req_id, &dev_id))
+ return req_id;
+
+ return dev_id;
+}
+
+/**
+ * iort_pci_find_its_id() - find the ITS identifier based on specified device.
+ * @pdev: The PCI device
+ * @idx: Index of the ITS identifier list
+ * @its_id: ITS identifier
+ *
+ * Returns: 0 on success, appropriate error value otherwise
+ */
+static int
+iort_pci_find_its_id(struct pci_dev *pdev, u32 req_id, unsigned int idx,
+ int *its_id)
+{
+ struct acpi_iort_its_group *its;
+ struct acpi_iort_node *node;
+
+ node = iort_its_find_node_and_map_rid(pdev, req_id, NULL);
+ if (!node)
+ return -ENXIO;
+
+ /* Move to ITS specific data */
+ its = (struct acpi_iort_its_group *)node->node_data;
+ if (idx > its->its_count) {
+ dev_err(&pdev->dev, "requested ITS ID index [%d] is greater than available[%d]\n",
+ idx, its->its_count);
+ return -ENXIO;
+ }
+
+ *its_id = its->identifiers[idx];
+ return 0;
+}
+
+/**
+ * iort_pci_get_msi_domain_handle() - find registered domain token related to
+ * PCI device
+ * @pdev: The PCI device
+ * @req_id: The PCI device requester ID
+ *
+ * Returns: the MSI domain for this device, NULL otherwise
+ */
+struct irq_domain *
+iort_pci_get_domain(struct pci_dev *pdev, u32 req_id)
+{
+ static struct fwnode_handle *handle;
+ int its_id;
+
+ if (iort_pci_find_its_id(pdev, req_id, 0, &its_id))
+ return NULL;
+
+ handle = iort_its_find_domain_token(its_id);
+ if (!handle)
+ return NULL;
+
+ return irq_find_matching_fwnode(handle, DOMAIN_BUS_PCI_MSI);
+}
+
+static int __init iort_table_detect(void)
+{
+ acpi_status status;
+
+ if (acpi_disabled)
+ return -ENODEV;
+
+ status = acpi_get_table(ACPI_SIG_IORT, 0, &iort_table);
+ if (ACPI_FAILURE(status)) {
+ const char *msg = acpi_format_exception(status);
+ pr_err("Failed to get table, %s\n", msg);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+arch_initcall(iort_table_detect);
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 72b6e9ef0ae9..f6696ac45e41 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -18,22 +18,21 @@
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
*/
+
+#define pr_fmt(fmt) "ACPI: " fmt
+
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/acpi.h>
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/numa.h>
#include <linux/nodemask.h>
#include <linux/topology.h>
-#define PREFIX "ACPI: "
-
-#define ACPI_NUMA 0x80000000
-#define _COMPONENT ACPI_NUMA
-ACPI_MODULE_NAME("numa");
-
static nodemask_t nodes_found_map = NODE_MASK_NONE;
/* maps to convert between proximity domain and logical node ID */
@@ -43,6 +42,7 @@ static int node_to_pxm_map[MAX_NUMNODES]
= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
unsigned char acpi_srat_revision __initdata;
+int acpi_numa __initdata;
int pxm_to_node(int pxm)
{
@@ -128,68 +128,63 @@ EXPORT_SYMBOL(acpi_map_pxm_to_online_node);
static void __init
acpi_table_print_srat_entry(struct acpi_subtable_header *header)
{
-
- ACPI_FUNCTION_NAME("acpi_table_print_srat_entry");
-
- if (!header)
- return;
-
switch (header->type) {
-
case ACPI_SRAT_TYPE_CPU_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
{
struct acpi_srat_cpu_affinity *p =
(struct acpi_srat_cpu_affinity *)header;
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
- p->apic_id, p->local_sapic_eid,
- p->proximity_domain_lo,
- (p->flags & ACPI_SRAT_CPU_ENABLED)?
- "enabled" : "disabled"));
+ pr_debug("SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
+ p->apic_id, p->local_sapic_eid,
+ p->proximity_domain_lo,
+ (p->flags & ACPI_SRAT_CPU_ENABLED) ?
+ "enabled" : "disabled");
}
-#endif /* ACPI_DEBUG_OUTPUT */
break;
case ACPI_SRAT_TYPE_MEMORY_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
{
struct acpi_srat_mem_affinity *p =
(struct acpi_srat_mem_affinity *)header;
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n",
- (unsigned long)p->base_address,
- (unsigned long)p->length,
- p->proximity_domain,
- (p->flags & ACPI_SRAT_MEM_ENABLED)?
- "enabled" : "disabled",
- (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)?
- " hot-pluggable" : "",
- (p->flags & ACPI_SRAT_MEM_NON_VOLATILE)?
- " non-volatile" : ""));
+ pr_debug("SRAT Memory (0x%lx length 0x%lx) in proximity domain %d %s%s%s\n",
+ (unsigned long)p->base_address,
+ (unsigned long)p->length,
+ p->proximity_domain,
+ (p->flags & ACPI_SRAT_MEM_ENABLED) ?
+ "enabled" : "disabled",
+ (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ?
+ " hot-pluggable" : "",
+ (p->flags & ACPI_SRAT_MEM_NON_VOLATILE) ?
+ " non-volatile" : "");
}
-#endif /* ACPI_DEBUG_OUTPUT */
break;
case ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY:
-#ifdef ACPI_DEBUG_OUTPUT
{
struct acpi_srat_x2apic_cpu_affinity *p =
(struct acpi_srat_x2apic_cpu_affinity *)header;
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "SRAT Processor (x2apicid[0x%08x]) in"
- " proximity domain %d %s\n",
- p->apic_id,
- p->proximity_domain,
- (p->flags & ACPI_SRAT_CPU_ENABLED) ?
- "enabled" : "disabled"));
+ pr_debug("SRAT Processor (x2apicid[0x%08x]) in proximity domain %d %s\n",
+ p->apic_id,
+ p->proximity_domain,
+ (p->flags & ACPI_SRAT_CPU_ENABLED) ?
+ "enabled" : "disabled");
}
-#endif /* ACPI_DEBUG_OUTPUT */
break;
+
+ case ACPI_SRAT_TYPE_GICC_AFFINITY:
+ {
+ struct acpi_srat_gicc_affinity *p =
+ (struct acpi_srat_gicc_affinity *)header;
+ pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
+ p->acpi_processor_uid,
+ p->proximity_domain,
+ (p->flags & ACPI_SRAT_GICC_ENABLED) ?
+ "enabled" : "disabled");
+ }
+ break;
+
default:
- printk(KERN_WARNING PREFIX
- "Found unsupported SRAT entry (type = 0x%x)\n",
- header->type);
+ pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
+ header->type);
break;
}
}
@@ -217,12 +212,117 @@ static int __init slit_valid(struct acpi_table_slit *slit)
return 1;
}
+void __init bad_srat(void)
+{
+ pr_err("SRAT: SRAT not used.\n");
+ acpi_numa = -1;
+}
+
+int __init srat_disabled(void)
+{
+ return acpi_numa < 0;
+}
+
+#if defined(CONFIG_X86) || defined (CONFIG_ARM64)
+/*
+ * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for
+ * I/O localities since SRAT does not list them. I/O localities are
+ * not supported at this point.
+ */
+void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
+{
+ int i, j;
+
+ for (i = 0; i < slit->locality_count; i++) {
+ const int from_node = pxm_to_node(i);
+
+ if (from_node == NUMA_NO_NODE)
+ continue;
+
+ for (j = 0; j < slit->locality_count; j++) {
+ const int to_node = pxm_to_node(j);
+
+ if (to_node == NUMA_NO_NODE)
+ continue;
+
+ numa_set_distance(from_node, to_node,
+ slit->entry[slit->locality_count * i + j]);
+ }
+ }
+}
+
+/*
+ * Default callback for parsing of the Proximity Domain <-> Memory
+ * Area mappings
+ */
+int __init
+acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
+{
+ u64 start, end;
+ u32 hotpluggable;
+ int node, pxm;
+
+ if (srat_disabled())
+ goto out_err;
+ if (ma->header.length < sizeof(struct acpi_srat_mem_affinity)) {
+ pr_err("SRAT: Unexpected header length: %d\n",
+ ma->header.length);
+ goto out_err_bad_srat;
+ }
+ if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
+ goto out_err;
+ hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
+ if (hotpluggable && !IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+ goto out_err;
+
+ start = ma->base_address;
+ end = start + ma->length;
+ pxm = ma->proximity_domain;
+ if (acpi_srat_revision <= 1)
+ pxm &= 0xff;
+
+ node = acpi_map_pxm_to_node(pxm);
+ if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+ pr_err("SRAT: Too many proximity domains.\n");
+ goto out_err_bad_srat;
+ }
+
+ if (numa_add_memblk(node, start, end) < 0) {
+ pr_err("SRAT: Failed to add memblk to node %u [mem %#010Lx-%#010Lx]\n",
+ node, (unsigned long long) start,
+ (unsigned long long) end - 1);
+ goto out_err_bad_srat;
+ }
+
+ node_set(node, numa_nodes_parsed);
+
+ pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n",
+ node, pxm,
+ (unsigned long long) start, (unsigned long long) end - 1,
+ hotpluggable ? " hotplug" : "",
+ ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : "");
+
+ /* Mark hotplug range in memblock. */
+ if (hotpluggable && memblock_mark_hotplug(start, ma->length))
+ pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
+ (unsigned long long)start, (unsigned long long)end - 1);
+
+ max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
+
+ return 0;
+out_err_bad_srat:
+ bad_srat();
+out_err:
+ return -EINVAL;
+}
+#endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
+
static int __init acpi_parse_slit(struct acpi_table_header *table)
{
struct acpi_table_slit *slit = (struct acpi_table_slit *)table;
if (!slit_valid(slit)) {
- printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n");
+ pr_info("SLIT table looks invalid. Not used.\n");
return -EINVAL;
}
acpi_numa_slit_init(slit);
@@ -233,12 +333,9 @@ static int __init acpi_parse_slit(struct acpi_table_header *table)
void __init __weak
acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
{
- printk(KERN_WARNING PREFIX
- "Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id);
- return;
+ pr_warn("Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id);
}
-
static int __init
acpi_parse_x2apic_affinity(struct acpi_subtable_header *header,
const unsigned long end)
@@ -275,6 +372,24 @@ acpi_parse_processor_affinity(struct acpi_subtable_header *header,
return 0;
}
+static int __init
+acpi_parse_gicc_affinity(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+ struct acpi_srat_gicc_affinity *processor_affinity;
+
+ processor_affinity = (struct acpi_srat_gicc_affinity *)header;
+ if (!processor_affinity)
+ return -EINVAL;
+
+ acpi_table_print_srat_entry(header);
+
+ /* let architecture-dependent part to do it */
+ acpi_numa_gicc_affinity_init(processor_affinity);
+
+ return 0;
+}
+
static int __initdata parsed_numa_memblks;
static int __init
@@ -319,6 +434,9 @@ int __init acpi_numa_init(void)
{
int cnt = 0;
+ if (acpi_disabled)
+ return -EINVAL;
+
/*
* Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
* SRAT cpu entries could have different order with that in MADT.
@@ -331,6 +449,8 @@ int __init acpi_numa_init(void)
acpi_parse_x2apic_affinity, 0);
acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
acpi_parse_processor_affinity, 0);
+ acpi_table_parse_srat(ACPI_SRAT_TYPE_GICC_AFFINITY,
+ acpi_parse_gicc_affinity, 0);
cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
acpi_parse_memory_affinity,
NR_NODE_MEMBLKS);
@@ -339,8 +459,6 @@ int __init acpi_numa_init(void)
/* SLIT: System Locality Information Table */
acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
- acpi_numa_arch_fixup();
-
if (cnt < 0)
return cnt;
else if (!parsed_numa_memblks)
diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
new file mode 100644
index 000000000000..373d07954bc7
--- /dev/null
+++ b/drivers/acpi/pci_mcfg.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright (C) 2016 Broadcom
+ * Author: Jayachandran C <jchandra@broadcom.com>
+ * Copyright (C) 2016 Semihalf
+ * Author: Tomasz Nowicki <tn@semihalf.com>
+ *
+ * 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 (the "GPL").
+ *
+ * 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 version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+
+#define PREFIX "ACPI: "
+
+/* Root pointer to the mapped MCFG table */
+static struct acpi_table_mcfg *mcfg_table;
+
+#define MCFG_ENTRIES(mcfg_ptr) (((mcfg_ptr)->header.length - \
+ sizeof(struct acpi_table_mcfg)) / \
+ sizeof(struct acpi_mcfg_allocation))
+
+static phys_addr_t pci_mcfg_lookup_static(u16 seg, u8 bus_start, u8 bus_end)
+{
+ struct acpi_mcfg_allocation *mptr;
+ int i;
+
+ if (!mcfg_table) {
+ pr_err(PREFIX "MCFG table not available, lookup failed\n");
+ return -ENXIO;
+ }
+
+ mptr = (struct acpi_mcfg_allocation *) &mcfg_table[1];
+
+ /*
+ * We expect exact match, unless MCFG entry end bus covers more than
+ * specified by caller.
+ */
+ for (i = 0; i < MCFG_ENTRIES(mcfg_table); i++, mptr++) {
+ if (mptr->pci_segment == seg &&
+ mptr->start_bus_number == bus_start &&
+ mptr->end_bus_number >= bus_end) {
+ return mptr->address;
+ }
+ }
+
+ return -ENXIO;
+}
+
+phys_addr_t pci_mcfg_lookup(struct acpi_device *device, u16 seg,
+ struct resource *bus_res)
+{
+ phys_addr_t addr;
+
+ addr = acpi_pci_root_get_mcfg_addr(device->handle);
+ if (addr)
+ return addr;
+
+ return pci_mcfg_lookup_static(seg, bus_res->start, bus_res->end);
+}
+
+static __init int pci_mcfg_parse(struct acpi_table_header *header)
+{
+ struct acpi_table_mcfg *mcfg;
+ int n;
+
+ if (!header)
+ return -EINVAL;
+
+ mcfg = (struct acpi_table_mcfg *)header;
+ n = MCFG_ENTRIES(mcfg);
+ if (n <= 0 || n > 255) {
+ pr_err(PREFIX "MCFG has incorrect entries (%d).\n", n);
+ return -EINVAL;
+ }
+
+ mcfg_table = mcfg;
+ pr_info(PREFIX "MCFG table loaded, %d entries detected\n", n);
+ return 0;
+}
+
+/* Interface called by ACPI - parse and save MCFG table */
+void __init pci_mmcfg_late_init(void)
+{
+ int err = acpi_table_parse(ACPI_SIG_MCFG, pci_mcfg_parse);
+ if (err)
+ pr_err(PREFIX "Failed to parse MCFG (%d)\n", err);
+}
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index ae3fe4e64203..e634430fb613 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -33,7 +33,6 @@
#include <linux/acpi.h>
#include <linux/slab.h>
#include <linux/dmi.h>
-#include <acpi/apei.h> /* for acpi_hest_init() */
#include "internal.h"
@@ -719,6 +718,34 @@ next:
resource_list_add_tail(entry, resources);
}
}
+static void acpi_pci_root_remap_iospace(struct resource_entry *entry)
+{
+#ifdef PCI_IOBASE
+ struct resource *res = entry->res;
+ resource_size_t cpu_addr = res->start;
+ resource_size_t pci_addr = cpu_addr - entry->offset;
+ resource_size_t length = resource_size(res);
+ unsigned long port;
+
+ if (pci_register_io_range(cpu_addr, length))
+ goto err;
+
+ port = pci_address_to_pio(cpu_addr);
+ if (port == (unsigned long)-1)
+ goto err;
+
+ res->start = port;
+ res->end = port + length - 1;
+ entry->offset = port - pci_addr;
+
+ if (pci_remap_iospace(res, cpu_addr) < 0)
+ goto err;
+ pr_info("Remapped I/O %pa to %pR\n", &cpu_addr, res);
+ return;
+err:
+ res->flags |= IORESOURCE_DISABLED;
+#endif
+}
int acpi_pci_probe_root_resources(struct acpi_pci_root_info *info)
{
@@ -740,6 +767,9 @@ int acpi_pci_probe_root_resources(struct acpi_pci_root_info *info)
"no IO and memory resources present in _CRS\n");
else {
resource_list_for_each_entry_safe(entry, tmp, list) {
+ if (entry->res->flags & IORESOURCE_IO)
+ acpi_pci_root_remap_iospace(entry);
+
if (entry->res->flags & IORESOURCE_DISABLED)
resource_list_destroy_entry(entry);
else
@@ -811,6 +841,8 @@ static void acpi_pci_root_release_info(struct pci_host_bridge *bridge)
resource_list_for_each_entry(entry, &bridge->windows) {
res = entry->res;
+ if (res->flags & IORESOURCE_IO)
+ pci_unmap_iospace(res);
if (res->parent &&
(res->flags & (IORESOURCE_MEM | IORESOURCE_IO)))
release_resource(res);
@@ -865,7 +897,6 @@ out_release_info:
void __init acpi_pci_root_init(void)
{
- acpi_hest_init();
if (acpi_pci_disabled)
return;
diff --git a/drivers/acpi/pci_root_generic.c b/drivers/acpi/pci_root_generic.c
new file mode 100644
index 000000000000..6f4940a7262d
--- /dev/null
+++ b/drivers/acpi/pci_root_generic.c
@@ -0,0 +1,149 @@
+/*
+ * Copyright (C) 2016 Broadcom
+ * Author: Jayachandran C <jchandra@broadcom.com>
+ * Copyright (C) 2016 Semihalf
+ * Author: Tomasz Nowicki <tn@semihalf.com>
+ *
+ * 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 (the "GPL").
+ *
+ * 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 version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/slab.h>
+
+#include "../pci/ecam.h"
+
+#define PREFIX "ACPI PCI: "
+
+/* ACPI info for generic ACPI PCI controller */
+struct acpi_pci_generic_root_info {
+ struct acpi_pci_root_info common;
+ struct pci_config_window *cfg; /* config space mapping */
+};
+
+void acpi_pci_set_companion(struct pci_host_bridge *bridge)
+{
+ struct pci_config_window *cfg = bridge->bus->sysdata;
+
+ ACPI_COMPANION_SET(&bridge->dev, cfg->companion);
+}
+
+int acpi_pci_bus_domain_nr(struct pci_bus *bus)
+{
+ struct pci_config_window *cfg = bus->sysdata;
+
+ return cfg->domain;
+}
+
+/*
+ * Lookup the bus range for the domain in MCFG, and set up config space
+ * mapping.
+ */
+static int pci_acpi_setup_ecam_mapping(struct acpi_pci_root *root,
+ struct acpi_pci_generic_root_info *ri)
+{
+ struct resource *bus_res = &root->secondary;
+ u16 seg = root->segment;
+ struct pci_config_window *cfg;
+ struct resource cfgres;
+ unsigned int bsz;
+ phys_addr_t addr;
+
+ addr = pci_mcfg_lookup(root->device, seg, bus_res);
+ if (IS_ERR_VALUE(addr)) {
+ pr_err(PREFIX"%04x:%pR MCFG region not found\n", seg, bus_res);
+ return addr;
+ }
+
+ bsz = 1 << pci_generic_ecam_ops.bus_shift;
+ cfgres.start = addr + bus_res->start * bsz;
+ cfgres.end = addr + (bus_res->end + 1) * bsz - 1;
+ cfgres.flags = IORESOURCE_MEM;
+ cfg = pci_ecam_create(&root->device->dev, &cfgres, bus_res,
+ &pci_generic_ecam_ops);
+ if (IS_ERR(cfg)) {
+ pr_err("%04x:%pR error %ld mapping CAM\n", seg, bus_res,
+ PTR_ERR(cfg));
+ return PTR_ERR(cfg);
+ }
+
+ cfg->domain = seg;
+ cfg->companion = root->device;
+ ri->cfg = cfg;
+ return 0;
+}
+
+/* release_info: free resrouces allocated by init_info */
+static void pci_acpi_generic_release_info(struct acpi_pci_root_info *ci)
+{
+ struct acpi_pci_generic_root_info *ri;
+
+ ri = container_of(ci, struct acpi_pci_generic_root_info, common);
+ pci_ecam_free(ri->cfg);
+ kfree(ri);
+}
+
+static struct acpi_pci_root_ops acpi_pci_root_ops = {
+ .release_info = pci_acpi_generic_release_info,
+};
+
+/* Interface called from ACPI code to setup PCI host controller */
+struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
+{
+ int node = acpi_get_node(root->device->handle);
+ struct acpi_pci_generic_root_info *ri;
+ struct pci_bus *bus, *child;
+ int err;
+
+ ri = kzalloc_node(sizeof(*ri), GFP_KERNEL, node);
+ if (!ri)
+ return NULL;
+
+ err = pci_acpi_setup_ecam_mapping(root, ri);
+ if (err)
+ return NULL;
+
+ acpi_pci_root_ops.pci_ops = &ri->cfg->ops->pci_ops;
+ bus = acpi_pci_root_create(root, &acpi_pci_root_ops, &ri->common,
+ ri->cfg);
+ if (!bus)
+ return NULL;
+
+ pci_bus_size_bridges(bus);
+ pci_bus_assign_resources(bus);
+
+ list_for_each_entry(child, &bus->children, node)
+ pcie_bus_configure_settings(child);
+
+ return bus;
+}
+
+int raw_pci_read(unsigned int domain, unsigned int busn, unsigned int devfn,
+ int reg, int len, u32 *val)
+{
+ struct pci_bus *bus = pci_find_bus(domain, busn);
+
+ if (!bus)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+ return bus->ops->read(bus, devfn, reg, len, val);
+}
+
+int raw_pci_write(unsigned int domain, unsigned int busn, unsigned int devfn,
+ int reg, int len, u32 val)
+{
+ struct pci_bus *bus = pci_find_bus(domain, busn);
+
+ if (!bus)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+ return bus->ops->write(bus, devfn, reg, len, val);
+}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 5f28cf778349..e51dab7ebd6a 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -13,6 +13,8 @@
#include <linux/nls.h>
#include <linux/dma-mapping.h>
+#include <acpi/apei.h> /* for acpi_hest_init() */
+
#include <asm/pgtable.h>
#include "internal.h"
@@ -1920,6 +1922,7 @@ int __init acpi_scan_init(void)
{
int result;
+ acpi_hest_init();
acpi_pci_root_init();
acpi_pci_link_init();
acpi_processor_init();
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
new file mode 100644
index 000000000000..68ffc3319a5b
--- /dev/null
+++ b/drivers/acpi/spcr.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright (c) 2012, Intel Corporation
+ * Copyright (c) 2015, Red Hat, Inc.
+ * Copyright (c) 2015, 2016 Linaro 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.
+ *
+ */
+
+#define pr_fmt(fmt) "ACPI: SPCR: " fmt
+
+#include <linux/acpi.h>
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/serial_core.h>
+
+/**
+ * parse_spcr() - parse ACPI SPCR table and add preferred console
+ *
+ * @earlycon: set up earlycon for the console specified by the table
+ *
+ * For the architectures with support for ACPI, CONFIG_ACPI_SPCR_TABLE may be
+ * defined to parse ACPI SPCR table. As a result of the parsing preferred
+ * console is registered and if @earlycon is true, earlycon is set up.
+ *
+ * When CONFIG_ACPI_SPCR_TABLE is defined, this function should should be called
+ * from arch inintialization code as soon as the DT/ACPI decision is made.
+ *
+ */
+int __init parse_spcr(bool earlycon)
+{
+ static char opts[64];
+ struct acpi_table_spcr *table;
+ acpi_size table_size;
+ acpi_status status;
+ char *uart;
+ char *iotype;
+ int baud_rate;
+ int err;
+
+ if (acpi_disabled)
+ return -ENODEV;
+
+ status = acpi_get_table_with_size(ACPI_SIG_SPCR, 0,
+ (struct acpi_table_header **)&table,
+ &table_size);
+
+ if (ACPI_FAILURE(status))
+ return -ENOENT;
+
+ if (table->header.revision < 2) {
+ err = -ENOENT;
+ pr_err("wrong table version\n");
+ goto done;
+ }
+
+ iotype = table->serial_port.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY ?
+ "mmio" : "io";
+
+ switch (table->interface_type) {
+ case ACPI_DBG2_ARM_SBSA_32BIT:
+ iotype = "mmio32";
+ /* fall through */
+ case ACPI_DBG2_ARM_PL011:
+ case ACPI_DBG2_ARM_SBSA_GENERIC:
+ case ACPI_DBG2_BCM2835:
+ uart = "pl011";
+ break;
+ case ACPI_DBG2_16550_COMPATIBLE:
+ case ACPI_DBG2_16550_SUBSET:
+ uart = "uart";
+ break;
+ default:
+ err = -ENOENT;
+ goto done;
+ }
+
+ switch (table->baud_rate) {
+ case 3:
+ baud_rate = 9600;
+ break;
+ case 4:
+ baud_rate = 19200;
+ break;
+ case 6:
+ baud_rate = 57600;
+ break;
+ case 7:
+ baud_rate = 115200;
+ break;
+ default:
+ err = -ENOENT;
+ goto done;
+ }
+
+ snprintf(opts, sizeof(opts), "%s,%s,0x%llx,%d", uart, iotype,
+ table->serial_port.address, baud_rate);
+
+ pr_info("console: %s", opts);
+
+ if (earlycon)
+ setup_earlycon(opts);
+
+ err = add_preferred_console(uart, 0, opts + strlen(uart) + 1);
+
+done:
+ early_acpi_os_unmap_memory((void __iomem *)table, table_size);
+ return err;
+}
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 5152b3898155..a5ccb29f900c 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -48,8 +48,6 @@
#define CNTV_TVAL 0x38
#define CNTV_CTL 0x3c
-#define ARCH_CP15_TIMER BIT(0)
-#define ARCH_MEM_TIMER BIT(1)
static unsigned arch_timers_present __initdata;
static void __iomem *arch_counter_base;
@@ -468,11 +466,11 @@ static struct cyclecounter cyclecounter = {
.mask = CLOCKSOURCE_MASK(56),
};
-static struct timecounter timecounter;
+static struct arch_timer_kvm_info arch_timer_kvm_info;
-struct timecounter *arch_timer_get_timecounter(void)
+struct arch_timer_kvm_info *arch_timer_get_kvm_info(void)
{
- return &timecounter;
+ return &arch_timer_kvm_info;
}
static void __init arch_counter_register(unsigned type)
@@ -500,7 +498,8 @@ static void __init arch_counter_register(unsigned type)
clocksource_register_hz(&clocksource_counter, arch_timer_rate);
cyclecounter.mult = clocksource_counter.mult;
cyclecounter.shift = clocksource_counter.shift;
- timecounter_init(&timecounter, &cyclecounter, start_count);
+ timecounter_init(&arch_timer_kvm_info.timecounter,
+ &cyclecounter, start_count);
/* 56 bits minimum, so we assume worst case rollover */
sched_clock_register(arch_timer_read_counter, 56, arch_timer_rate);
@@ -689,6 +688,15 @@ arch_timer_needs_probing(int type, const struct of_device_id *matches)
needs_probing = true;
of_node_put(dn);
+#ifdef CONFIG_ACPI
+ /*
+ * Check if we have timer in GTDT table
+ */
+ if (!acpi_disabled && gtdt_timer_is_available(type) &&
+ !(arch_timers_present & type))
+ needs_probing = true;
+#endif
+
return needs_probing;
}
@@ -744,6 +752,8 @@ static void __init arch_timer_init(void)
arch_timer_register();
arch_timer_common_init();
+
+ arch_timer_kvm_info.virtual_irq = arch_timer_ppi[VIRT_PPI];
}
static void __init arch_timer_of_init(struct device_node *np)
@@ -855,60 +865,159 @@ CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
arch_timer_mem_init);
#ifdef CONFIG_ACPI
-static int __init map_generic_timer_interrupt(u32 interrupt, u32 flags)
+/* Initialize per-processor generic timer */
+static int __init arch_timer_acpi_init(struct acpi_table_header *table)
{
- int trigger, polarity;
+ struct arch_timer_data data;
- if (!interrupt)
- return 0;
+ if (arch_timers_present & ARCH_CP15_TIMER) {
+ pr_warn("arch_timer: already initialized, skipping\n");
+ return -EINVAL;
+ }
+
+ arch_timers_present |= ARCH_CP15_TIMER;
- trigger = (flags & ACPI_GTDT_INTERRUPT_MODE) ? ACPI_EDGE_SENSITIVE
- : ACPI_LEVEL_SENSITIVE;
+ if (gtdt_arch_timer_data_init(table, &data))
+ return -EINVAL;
+
+ arch_timer_ppi[PHYS_SECURE_PPI] = data.phys_secure_ppi;
+ arch_timer_ppi[PHYS_NONSECURE_PPI] = data.phys_nonsecure_ppi;
+ arch_timer_ppi[VIRT_PPI] = data.virt_ppi;
+ arch_timer_ppi[HYP_PPI] = data.hyp_ppi;
+ arch_timer_c3stop = data.c3stop; /* Always-on capability */
- polarity = (flags & ACPI_GTDT_INTERRUPT_POLARITY) ? ACPI_ACTIVE_LOW
- : ACPI_ACTIVE_HIGH;
+ /* Get the frequency from CNTFRQ */
+ arch_timer_detect_rate(NULL, NULL);
+ arch_timer_init();
- return acpi_register_gsi(NULL, interrupt, trigger, polarity);
+ return 0;
}
+CLOCKSOURCE_ACPI_DECLARE(arch_timer, ACPI_SIG_GTDT, arch_timer_acpi_init);
-/* Initialize per-processor generic timer */
-static int __init arch_timer_acpi_init(struct acpi_table_header *table)
+static u32 __init arch_timer_mem_cnttidr(struct acpi_gtdt_timer_block *gt_block)
{
- struct acpi_table_gtdt *gtdt;
+ phys_addr_t cntctlbase_phy;
+ void __iomem *cntctlbase;
+ u32 cnttidr;
- if (arch_timers_present & ARCH_CP15_TIMER) {
- pr_warn("arch_timer: already initialized, skipping\n");
+ cntctlbase_phy = (phys_addr_t)gtdt_gt_cntctlbase(gt_block);
+ if (!cntctlbase_phy) {
+ pr_err("arch_timer: Can't find CNTCTLBase.\n");
+ return 0;
+ }
+
+ /*
+ * According to ARMv8 Architecture Reference Manual(ARM),
+ * the size of CNTCTLBase frame of memory-mapped timer
+ * is SZ_4K(Offset 0x000 – 0xFFF).
+ */
+ cntctlbase = ioremap(cntctlbase_phy, SZ_4K);
+ if (!cntctlbase) {
+ pr_err("arch_timer: Can't map CNTCTLBase\n");
+ return 0;
+ }
+ cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
+ iounmap(cntctlbase);
+
+ return cnttidr;
+}
+
+static int __init arch_timer_mem_best_frame(struct acpi_table_header *table,
+ struct arch_timer_mem_data *data)
+{
+ struct acpi_gtdt_timer_block *gt_block;
+ u32 frame_number, timer_count, cnttidr;
+ int i;
+
+ gt_block = gtdt_gt_block(table, 0);
+ if (!gt_block) {
+ pr_err("arch_timer: Can't find GT Block.\n");
return -EINVAL;
}
- gtdt = container_of(table, struct acpi_table_gtdt, header);
+ timer_count = gtdt_gt_timer_count(gt_block);
+ if (!timer_count) {
+ pr_err("arch_timer: Can't find GT frame number.\n");
+ return -EINVAL;
+ }
- arch_timers_present |= ARCH_CP15_TIMER;
+ if (gtdt_gt_timer_data(gt_block, 0, false, data)) {
+ pr_err("arch_timer: Can't get first phy timer.\n");
+ return -EINVAL;
+ }
- arch_timer_ppi[PHYS_SECURE_PPI] =
- map_generic_timer_interrupt(gtdt->secure_el1_interrupt,
- gtdt->secure_el1_flags);
+ /*
+ * Get Generic Timer Counter-timer Timer ID Register
+ * for Virtual Timer Capability info
+ */
+ cnttidr = arch_timer_mem_cnttidr(gt_block);
- arch_timer_ppi[PHYS_NONSECURE_PPI] =
- map_generic_timer_interrupt(gtdt->non_secure_el1_interrupt,
- gtdt->non_secure_el1_flags);
+ /*
+ * Try to find a virtual capable frame.
+ * Otherwise fall back to the first physical capable frame.
+ */
+ for (i = 0; i < timer_count; i++) {
+ frame_number = gtdt_gt_frame_number(gt_block, i);
+ if (frame_number < ARCH_TIMER_MEM_MAX_FRAME &&
+ cnttidr & CNTTIDR_VIRT(frame_number)) {
+ if (!gtdt_gt_timer_data(gt_block, i, true, data)) {
+ arch_timer_mem_use_virtual = true;
+ return 0;
+ }
+ pr_warn("arch_timer: Can't get virt timer.\n");
+ }
+ }
- arch_timer_ppi[VIRT_PPI] =
- map_generic_timer_interrupt(gtdt->virtual_timer_interrupt,
- gtdt->virtual_timer_flags);
+ return 0;
+}
- arch_timer_ppi[HYP_PPI] =
- map_generic_timer_interrupt(gtdt->non_secure_el2_interrupt,
- gtdt->non_secure_el2_flags);
+/* Initialize memory-mapped timer(wake-up timer) */
+static int __init arch_timer_mem_acpi_init(struct acpi_table_header *table)
+{
+ struct arch_timer_mem_data data;
+ void __iomem *cntbase;
- /* Get the frequency from CNTFRQ */
+ if (arch_timers_present & ARCH_MEM_TIMER) {
+ pr_warn("arch_timer_mem: already initialized, skipping\n");
+ return -EINVAL;
+ }
+ arch_timers_present |= ARCH_MEM_TIMER;
+
+ if (arch_timer_mem_best_frame(table, &data))
+ return -EINVAL;
+
+ /*
+ * According to ARMv8 Architecture Reference Manual(ARM),
+ * the size of CNTBaseN frames of memory-mapped timer
+ * is SZ_4K(Offset 0x000 – 0xFFF).
+ */
+ cntbase = ioremap(data.cntbase_phy, SZ_4K);
+ if (!cntbase) {
+ pr_err("arch_timer: Can't map CntBase.\n");
+ return -EINVAL;
+ }
+ arch_counter_base = cntbase;
+
+ if (!data.irq) {
+ pr_err("arch_timer: Frame missing %s irq",
+ arch_timer_mem_use_virtual ? "virt" : "phys");
+ return -EINVAL;
+ }
+
+ /*
+ * Because in a system that implements both Secure and
+ * Non-secure states, CNTFRQ is only accessible in Secure state.
+ * So we try to get the system counter frequency from cntfrq_el0
+ * (system coprocessor register) here just like arch_timer.
+ */
arch_timer_detect_rate(NULL, NULL);
- /* Always-on capability */
- arch_timer_c3stop = !(gtdt->non_secure_el1_flags & ACPI_GTDT_ALWAYS_ON);
+ arch_timer_mem_register(cntbase, data.irq);
+ arch_timer_common_init();
- arch_timer_init();
return 0;
}
-CLOCKSOURCE_ACPI_DECLARE(arch_timer, ACPI_SIG_GTDT, arch_timer_acpi_init);
+
+CLOCKSOURCE_ACPI_DECLARE(arch_timer_mem, ACPI_SIG_GTDT,
+ arch_timer_mem_acpi_init);
#endif
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index 8714f8c271ba..434dd6065935 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -143,6 +143,14 @@ static __init void reserve_regions(void)
if (efi_enabled(EFI_DBG))
pr_info("Processing EFI memory map:\n");
+ /*
+ * Discard memblocks discovered so far: if there are any at this
+ * point, they originate from memory nodes in the DT, and UEFI
+ * uses its own memory map instead.
+ */
+ memblock_dump_all();
+ memblock_remove(0, ULLONG_MAX);
+
for_each_efi_memory_desc(&memmap, md) {
paddr = md->phys_addr;
npages = md->num_pages;
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index 6dba78aef337..e58abfa953cc 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -24,7 +24,7 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
unsigned long map_size, unsigned long desc_size,
u32 desc_ver)
{
- int node, prev, num_rsv;
+ int node, num_rsv;
int status;
u32 fdt_val32;
u64 fdt_val64;
@@ -54,28 +54,6 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
goto fdt_set_fail;
/*
- * Delete any memory nodes present. We must delete nodes which
- * early_init_dt_scan_memory may try to use.
- */
- prev = 0;
- for (;;) {
- const char *type;
- int len;
-
- node = fdt_next_node(fdt, prev, NULL);
- if (node < 0)
- break;
-
- type = fdt_getprop(fdt, node, "device_type", &len);
- if (type && strncmp(type, "memory", len) == 0) {
- fdt_del_node(fdt, node);
- continue;
- }
-
- prev = node;
- }
-
- /*
* Delete all memory reserve map entries. When booting via UEFI,
* kernel will use the UEFI memory map to find reserved regions.
*/
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 3e124793e224..f582e0d19df7 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -31,6 +31,7 @@ config ARM_GIC_V3
config ARM_GIC_V3_ITS
bool
select PCI_MSI_IRQ_DOMAIN
+ select IORT_TABLE if ACPI
config ARM_NVIC
bool
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index f174ce0ca361..2e9443be2b14 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -21,6 +21,19 @@
#include "irq-gic-common.h"
+static const struct gic_kvm_info *gic_kvm_info;
+
+const struct gic_kvm_info *gic_get_kvm_info(void)
+{
+ return gic_kvm_info;
+}
+
+void gic_set_kvm_info(const struct gic_kvm_info *info)
+{
+ BUG_ON(gic_kvm_info != NULL);
+ gic_kvm_info = info;
+}
+
void gic_enable_quirks(u32 iidr, const struct gic_quirk *quirks,
void *data)
{
diff --git a/drivers/irqchip/irq-gic-common.h b/drivers/irqchip/irq-gic-common.h
index fff697db8e22..205e5fddf6da 100644
--- a/drivers/irqchip/irq-gic-common.h
+++ b/drivers/irqchip/irq-gic-common.h
@@ -19,6 +19,7 @@
#include <linux/of.h>
#include <linux/irqdomain.h>
+#include <linux/irqchip/arm-gic-common.h>
struct gic_quirk {
const char *desc;
@@ -35,4 +36,6 @@ void gic_cpu_config(void __iomem *base, void (*sync_access)(void));
void gic_enable_quirks(u32 iidr, const struct gic_quirk *quirks,
void *data);
+void gic_set_kvm_info(const struct gic_kvm_info *info);
+
#endif /* _IRQ_GIC_COMMON_H */
diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index aee60ed025dc..eb29b217feb7 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -15,6 +15,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/iort.h>
#include <linux/msi.h>
#include <linux/of.h>
#include <linux/of_irq.h>
@@ -106,34 +107,87 @@ static struct of_device_id its_device_id[] = {
{},
};
-static int __init its_pci_msi_init(void)
+static int __init its_pci_msi_init_one(struct fwnode_handle *handle,
+ const char *name)
{
- struct device_node *np;
struct irq_domain *parent;
+ parent = irq_find_matching_fwnode(handle, DOMAIN_BUS_NEXUS);
+ if (!parent || !msi_get_domain_info(parent)) {
+ pr_err("%s: Unable to locate ITS domain\n", name);
+ return -ENXIO;
+ }
+
+ if (!pci_msi_create_irq_domain(handle, &its_pci_msi_domain_info,
+ parent)) {
+ pr_err("%s: Unable to create PCI domain\n", name);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int __init its_pci_of_msi_init(void)
+{
+ struct device_node *np;
+
for (np = of_find_matching_node(NULL, its_device_id); np;
np = of_find_matching_node(np, its_device_id)) {
if (!of_property_read_bool(np, "msi-controller"))
continue;
- parent = irq_find_matching_host(np, DOMAIN_BUS_NEXUS);
- if (!parent || !msi_get_domain_info(parent)) {
- pr_err("%s: unable to locate ITS domain\n",
- np->full_name);
- continue;
- }
-
- if (!pci_msi_create_irq_domain(of_node_to_fwnode(np),
- &its_pci_msi_domain_info,
- parent)) {
- pr_err("%s: unable to create PCI domain\n",
- np->full_name);
+ if (its_pci_msi_init_one(of_node_to_fwnode(np), np->full_name))
continue;
- }
pr_info("PCI/MSI: %s domain created\n", np->full_name);
}
return 0;
}
+
+#ifdef CONFIG_ACPI
+
+static int __init
+its_pci_msi_parse_madt(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+ struct acpi_madt_generic_translator *its_entry;
+ struct fwnode_handle *domain_handle;
+ char node_name[6 + 16 + 1];
+
+ its_entry = (struct acpi_madt_generic_translator *)header;
+ snprintf(node_name, 23, "ITS@0x%lx", (long)its_entry->base_address);
+ domain_handle = iort_its_find_domain_token(its_entry->translation_id);
+ if (!domain_handle) {
+ pr_err("%s: Unable to locate ITS domain handle\n", node_name);
+ return 0;
+ }
+
+ if (its_pci_msi_init_one(domain_handle, node_name))
+ return 0;
+
+ pr_info("PCI/MSI: %s domain created\n", node_name);
+ return 0;
+}
+
+static int __init its_pci_acpi_msi_init(void)
+{
+ acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR,
+ its_pci_msi_parse_madt, 0);
+ return 0;
+}
+#else
+inline static int __init its_pci_acpi_msi_init(void)
+{
+ return 0;
+}
+#endif
+
+static int __init its_pci_msi_init(void)
+{
+ its_pci_of_msi_init();
+ its_pci_acpi_msi_init();
+
+ return 0;
+}
early_initcall(its_pci_msi_init);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 39261798c59f..f403d8b05d9d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -15,10 +15,13 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/acpi.h>
#include <linux/bitmap.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/iort.h>
#include <linux/log2.h>
#include <linux/mm.h>
#include <linux/msi.h>
@@ -63,7 +66,7 @@ struct its_node {
raw_spinlock_t lock;
struct list_head entry;
void __iomem *base;
- unsigned long phys_base;
+ phys_addr_t phys_base;
struct its_cmd_block *cmd_base;
struct its_cmd_block *cmd_write;
struct {
@@ -104,6 +107,7 @@ struct its_device {
static LIST_HEAD(its_nodes);
static DEFINE_SPINLOCK(its_lock);
static struct rdists *gic_rdists;
+static struct irq_domain *its_parent;
#define gic_data_rdist() (raw_cpu_ptr(gic_rdists->rdist))
#define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base)
@@ -815,7 +819,7 @@ static void its_free_tables(struct its_node *its)
}
}
-static int its_alloc_tables(const char *node_name, struct its_node *its)
+static int its_alloc_tables(struct its_node *its)
{
int err;
int i;
@@ -869,8 +873,8 @@ static int its_alloc_tables(const char *node_name, struct its_node *its)
order);
if (order >= MAX_ORDER) {
order = MAX_ORDER - 1;
- pr_warn("%s: Device Table too large, reduce its page order to %u\n",
- node_name, order);
+ pr_warn("ITS@%pa: Device Table too large, reduce its page order to %u\n",
+ &its->phys_base, order);
}
}
@@ -879,8 +883,8 @@ retry_alloc_baser:
if (alloc_pages > GITS_BASER_PAGES_MAX) {
alloc_pages = GITS_BASER_PAGES_MAX;
order = get_order(GITS_BASER_PAGES_MAX * psz);
- pr_warn("%s: Device Table too large, reduce its page order to %u (%u pages)\n",
- node_name, order, alloc_pages);
+ pr_warn("ITS@%pa: Device Table too large, reduce its page order to %u (%u pages)\n",
+ &its->phys_base, order, alloc_pages);
}
base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
@@ -953,8 +957,8 @@ retry_baser:
}
if (val != tmp) {
- pr_err("ITS: %s: GITS_BASER%d doesn't stick: %lx %lx\n",
- node_name, i,
+ pr_err("ITS@%pa: GITS_BASER%d doesn't stick: %lx %lx\n",
+ &its->phys_base, i,
(unsigned long) val, (unsigned long) tmp);
err = -ENXIO;
goto out_free;
@@ -1277,6 +1281,11 @@ static int its_irq_gic_domain_alloc(struct irq_domain *domain,
fwspec.param[0] = GIC_IRQ_TYPE_LPI;
fwspec.param[1] = hwirq;
fwspec.param[2] = IRQ_TYPE_EDGE_RISING;
+ } else if (is_fwnode_irqchip(domain->parent->fwnode)) {
+ fwspec.fwnode = domain->parent->fwnode;
+ fwspec.param_count = 2;
+ fwspec.param[0] = hwirq;
+ fwspec.param[1] = IRQ_TYPE_EDGE_RISING;
} else {
return -EINVAL;
}
@@ -1429,44 +1438,59 @@ static void its_enable_quirks(struct its_node *its)
gic_enable_quirks(iidr, its_quirks, its);
}
-static int __init its_probe(struct device_node *node,
- struct irq_domain *parent)
+static int its_init_domain(struct fwnode_handle *handle, struct its_node *its)
+{
+ struct irq_domain *inner_domain;
+ struct msi_domain_info *info;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return -ENOMEM;
+
+ inner_domain = irq_domain_create_tree(handle, &its_domain_ops, its);
+ if (!inner_domain) {
+ kfree(info);
+ return -ENOMEM;
+ }
+
+ inner_domain->parent = its_parent;
+ inner_domain->bus_token = DOMAIN_BUS_NEXUS;
+ info->ops = &its_msi_domain_ops;
+ info->data = its;
+ inner_domain->host_data = info;
+
+ return 0;
+}
+
+static int __init its_probe_one(struct resource *res,
+ struct fwnode_handle *handle)
{
- struct resource res;
struct its_node *its;
void __iomem *its_base;
- struct irq_domain *inner_domain;
u32 val;
u64 baser, tmp;
int err;
- err = of_address_to_resource(node, 0, &res);
- if (err) {
- pr_warn("%s: no regs?\n", node->full_name);
- return -ENXIO;
- }
-
- its_base = ioremap(res.start, resource_size(&res));
+ its_base = ioremap(res->start, resource_size(res));
if (!its_base) {
- pr_warn("%s: unable to map registers\n", node->full_name);
+ pr_warn("ITS@%pa: Unable to map ITS registers\n", &res->start);
return -ENOMEM;
}
val = readl_relaxed(its_base + GITS_PIDR2) & GIC_PIDR2_ARCH_MASK;
if (val != 0x30 && val != 0x40) {
- pr_warn("%s: no ITS detected, giving up\n", node->full_name);
+ pr_warn("ITS@%pa: No ITS detected, giving up\n", &res->start);
err = -ENODEV;
goto out_unmap;
}
err = its_force_quiescent(its_base);
if (err) {
- pr_warn("%s: failed to quiesce, giving up\n",
- node->full_name);
+ pr_warn("ITS@%pa: Failed to quiesce, giving up\n", &res->start);
goto out_unmap;
}
- pr_info("ITS: %s\n", node->full_name);
+ pr_info("ITS@%pa\n", &res->start);
its = kzalloc(sizeof(*its), GFP_KERNEL);
if (!its) {
@@ -1478,7 +1502,7 @@ static int __init its_probe(struct device_node *node,
INIT_LIST_HEAD(&its->entry);
INIT_LIST_HEAD(&its->its_device_list);
its->base = its_base;
- its->phys_base = res.start;
+ its->phys_base = res->start;
its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
@@ -1490,7 +1514,7 @@ static int __init its_probe(struct device_node *node,
its_enable_quirks(its);
- err = its_alloc_tables(node->full_name, its);
+ err = its_alloc_tables(its);
if (err)
goto out_free_cmd;
@@ -1526,28 +1550,9 @@ static int __init its_probe(struct device_node *node,
writeq_relaxed(0, its->base + GITS_CWRITER);
writel_relaxed(GITS_CTLR_ENABLE, its->base + GITS_CTLR);
- if (of_property_read_bool(node, "msi-controller")) {
- struct msi_domain_info *info;
-
- info = kzalloc(sizeof(*info), GFP_KERNEL);
- if (!info) {
- err = -ENOMEM;
- goto out_free_tables;
- }
-
- inner_domain = irq_domain_add_tree(node, &its_domain_ops, its);
- if (!inner_domain) {
- err = -ENOMEM;
- kfree(info);
- goto out_free_tables;
- }
-
- inner_domain->parent = parent;
- inner_domain->bus_token = DOMAIN_BUS_NEXUS;
- info->ops = &its_msi_domain_ops;
- info->data = its;
- inner_domain->host_data = info;
- }
+ err = its_init_domain(handle, its);
+ if (err)
+ goto out_free_tables;
spin_lock(&its_lock);
list_add(&its->entry, &its_nodes);
@@ -1563,7 +1568,7 @@ out_free_its:
kfree(its);
out_unmap:
iounmap(its_base);
- pr_err("ITS: failed probing %s (%d)\n", node->full_name, err);
+ pr_err("ITS@%pa: failed probing (%d)\n", &res->start, err);
return err;
}
@@ -1591,15 +1596,88 @@ static struct of_device_id its_device_id[] = {
{},
};
-int __init its_init(struct device_node *node, struct rdists *rdists,
- struct irq_domain *parent_domain)
+static int __init
+its_of_probe(struct device_node *node)
{
struct device_node *np;
+ struct resource res;
for (np = of_find_matching_node(node, its_device_id); np;
np = of_find_matching_node(np, its_device_id)) {
- its_probe(np, parent_domain);
+ if (!of_property_read_bool(np, "msi-controller")) {
+ pr_warn("%s: no msi-controller property, ITS ignored\n",
+ np->full_name);
+ continue;
+ }
+
+ if (of_address_to_resource(np, 0, &res)) {
+ pr_warn("%s: no regs?\n", np->full_name);
+ continue;
+ }
+
+ its_probe_one(&res, &np->fwnode);
+ }
+ return 0;
+}
+
+#ifdef CONFIG_ACPI
+
+#define ACPI_GICV3_ITS_MEM_SIZE (2 * SZ_64K)
+
+static int __init
+gic_acpi_parse_madt_its(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+ struct acpi_madt_generic_translator *its_entry;
+ struct fwnode_handle *domain_handle;
+ struct resource res;
+ int err;
+
+ its_entry = (struct acpi_madt_generic_translator *)header;
+ domain_handle = irq_domain_alloc_fwnode((void *)its_entry->base_address);
+ if (!domain_handle) {
+ pr_err("Unable to allocate GICv3 ITS domain token\n");
+ return -ENOMEM;
+ }
+
+ err = iort_register_domain_token(its_entry->translation_id, domain_handle);
+ if (err) {
+ irq_domain_free_fwnode(domain_handle);
+ goto out;
+ }
+
+ res.start = its_entry->base_address;
+ res.end = its_entry->base_address + ACPI_GICV3_ITS_MEM_SIZE - 1;
+ err = its_probe_one(&res, domain_handle);
+ if (err) {
+ iort_deregister_domain_token(its_entry->translation_id);
+ irq_domain_free_fwnode(domain_handle);
}
+out:
+ return err;
+}
+
+void __init its_acpi_probe(void)
+{
+ if (acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR,
+ gic_acpi_parse_madt_its, 0) <= 0)
+ pr_info("No valid GIC ITS entries exist\n");
+}
+#else
+static inline void __init its_acpi_probe(struct irq_domain *parent_domain) { }
+#endif
+
+int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
+ struct irq_domain *parent_domain)
+{
+ struct device_node *of_node;
+
+ its_parent = parent_domain;
+ of_node = to_of_node(handle);
+ if (of_node)
+ its_of_probe(of_node);
+ else
+ its_acpi_probe();
if (list_empty(&its_nodes)) {
pr_warn("ITS: No ITS available, not enabling LPIs\n");
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 5b7d3c2129d8..971d57149471 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -15,6 +15,8 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#define pr_fmt(fmt) "GICv3: " fmt
+
#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpu_pm.h>
@@ -28,6 +30,7 @@
#include <linux/slab.h>
#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic-common.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <asm/cputype.h>
@@ -56,6 +59,8 @@ struct gic_chip_data {
static struct gic_chip_data gic_data __read_mostly;
static struct static_key supports_deactivate = STATIC_KEY_INIT_TRUE;
+static struct gic_kvm_info gic_v3_kvm_info;
+
#define gic_data_rdist() (this_cpu_ptr(gic_data.rdists.rdist))
#define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base)
#define gic_data_rdist_sgi_base() (gic_data_rdist_rd_base() + SZ_64K)
@@ -832,7 +837,6 @@ static int __init gic_init_bases(void __iomem *dist_base,
u64 redist_stride,
struct fwnode_handle *handle)
{
- struct device_node *node;
u32 typer;
int gic_irqs;
int err;
@@ -872,10 +876,8 @@ static int __init gic_init_bases(void __iomem *dist_base,
set_handle_irq(gic_handle_irq);
- node = to_of_node(handle);
- if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis() &&
- node) /* Temp hack to prevent ITS init for ACPI */
- its_init(node, &gic_data.rdists, gic_data.domain);
+ if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis())
+ its_init(handle, &gic_data.rdists, gic_data.domain);
gic_smp_init();
gic_dist_init();
@@ -901,6 +903,30 @@ static int __init gic_validate_dist_version(void __iomem *dist_base)
return 0;
}
+static void __init gic_of_setup_kvm_info(struct device_node *node)
+{
+ int ret;
+ struct resource r;
+ u32 gicv_idx;
+
+ gic_v3_kvm_info.type = GIC_V3;
+
+ gic_v3_kvm_info.maint_irq = irq_of_parse_and_map(node, 0);
+ if (!gic_v3_kvm_info.maint_irq)
+ return;
+
+ if (of_property_read_u32(node, "#redistributor-regions",
+ &gicv_idx))
+ gicv_idx = 1;
+
+ gicv_idx += 3; /* Also skip GICD, GICC, GICH */
+ ret = of_address_to_resource(node, gicv_idx, &r);
+ if (!ret)
+ gic_v3_kvm_info.vcpu = r;
+
+ gic_set_kvm_info(&gic_v3_kvm_info);
+}
+
static int __init gic_of_init(struct device_node *node, struct device_node *parent)
{
void __iomem *dist_base;
@@ -952,8 +978,10 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare
err = gic_init_bases(dist_base, rdist_regs, nr_redist_regions,
redist_stride, &node->fwnode);
- if (!err)
+ if (!err) {
+ gic_of_setup_kvm_info(node);
return 0;
+ }
out_unmap_rdist:
for (i = 0; i < nr_redist_regions; i++)
@@ -968,19 +996,25 @@ out_unmap_dist:
IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
#ifdef CONFIG_ACPI
-static void __iomem *dist_base;
-static struct redist_region *redist_regs __initdata;
-static u32 nr_redist_regions __initdata;
-static bool single_redist;
+static struct
+{
+ void __iomem *dist_base;
+ struct redist_region *redist_regs;
+ u32 nr_redist_regions;
+ bool single_redist;
+ u32 maint_irq;
+ int maint_irq_mode;
+ phys_addr_t vcpu_base;
+} acpi_data __initdata;
static void __init
gic_acpi_register_redist(phys_addr_t phys_base, void __iomem *redist_base)
{
static int count = 0;
- redist_regs[count].phys_base = phys_base;
- redist_regs[count].redist_base = redist_base;
- redist_regs[count].single_redist = single_redist;
+ acpi_data.redist_regs[count].phys_base = phys_base;
+ acpi_data.redist_regs[count].redist_base = redist_base;
+ acpi_data.redist_regs[count].single_redist = acpi_data.single_redist;
count++;
}
@@ -1008,7 +1042,7 @@ gic_acpi_parse_madt_gicc(struct acpi_subtable_header *header,
{
struct acpi_madt_generic_interrupt *gicc =
(struct acpi_madt_generic_interrupt *)header;
- u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
+ u32 reg = readl_relaxed(acpi_data.dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2;
void __iomem *redist_base;
@@ -1025,7 +1059,7 @@ static int __init gic_acpi_collect_gicr_base(void)
acpi_tbl_entry_handler redist_parser;
enum acpi_madt_type type;
- if (single_redist) {
+ if (acpi_data.single_redist) {
type = ACPI_MADT_TYPE_GENERIC_INTERRUPT;
redist_parser = gic_acpi_parse_madt_gicc;
} else {
@@ -1076,14 +1110,14 @@ static int __init gic_acpi_count_gicr_regions(void)
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR,
gic_acpi_match_gicr, 0);
if (count > 0) {
- single_redist = false;
+ acpi_data.single_redist = false;
return count;
}
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
gic_acpi_match_gicc, 0);
if (count > 0)
- single_redist = true;
+ acpi_data.single_redist = true;
return count;
}
@@ -1103,36 +1137,117 @@ static bool __init acpi_validate_gic_table(struct acpi_subtable_header *header,
if (count <= 0)
return false;
- nr_redist_regions = count;
+ acpi_data.nr_redist_regions = count;
return true;
}
+static int __init gic_acpi_parse_virt_madt_gicc(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+ struct acpi_madt_generic_interrupt *gicc =
+ (struct acpi_madt_generic_interrupt *)header;
+ int maint_irq_mode;
+ static int first_madt = true;
+
+ /* Skip unusable CPUs */
+ if (!(gicc->flags & ACPI_MADT_ENABLED))
+ return 0;
+
+ maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ?
+ ACPI_EDGE_SENSITIVE : ACPI_LEVEL_SENSITIVE;
+
+ if (first_madt) {
+ first_madt = false;
+
+ acpi_data.maint_irq = gicc->vgic_interrupt;
+ acpi_data.maint_irq_mode = maint_irq_mode;
+ acpi_data.vcpu_base = gicc->gicv_base_address;
+
+ return 0;
+ }
+
+ /*
+ * The maintenance interrupt and GICV should be the same for every CPU
+ */
+ if ((acpi_data.maint_irq != gicc->vgic_interrupt) ||
+ (acpi_data.maint_irq_mode != maint_irq_mode) ||
+ (acpi_data.vcpu_base != gicc->gicv_base_address))
+ return -EINVAL;
+
+ return 0;
+}
+
+static bool __init gic_acpi_collect_virt_info(void)
+{
+ int count;
+
+ count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
+ gic_acpi_parse_virt_madt_gicc, 0);
+
+ return (count > 0);
+}
+
#define ACPI_GICV3_DIST_MEM_SIZE (SZ_64K)
+#define ACPI_GICV2_VCTRL_MEM_SIZE (SZ_4K)
+#define ACPI_GICV2_VCPU_MEM_SIZE (SZ_8K)
+
+static void __init gic_acpi_setup_kvm_info(void)
+{
+ int irq;
+
+ if (!gic_acpi_collect_virt_info()) {
+ pr_warn("Unable to get hardware information used for virtualization\n");
+ return;
+ }
+
+ gic_v3_kvm_info.type = GIC_V3;
+
+ irq = acpi_register_gsi(NULL, acpi_data.maint_irq,
+ acpi_data.maint_irq_mode,
+ ACPI_ACTIVE_HIGH);
+ if (irq <= 0)
+ return;
+
+ gic_v3_kvm_info.maint_irq = irq;
+
+ if (acpi_data.vcpu_base) {
+ struct resource *vcpu = &gic_v3_kvm_info.vcpu;
+
+ vcpu->flags = IORESOURCE_MEM;
+ vcpu->start = acpi_data.vcpu_base;
+ vcpu->end = vcpu->start + ACPI_GICV2_VCPU_MEM_SIZE - 1;
+ }
+
+ gic_set_kvm_info(&gic_v3_kvm_info);
+}
static int __init
gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end)
{
struct acpi_madt_generic_distributor *dist;
struct fwnode_handle *domain_handle;
+ size_t size;
int i, err;
/* Get distributor base address */
dist = (struct acpi_madt_generic_distributor *)header;
- dist_base = ioremap(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE);
- if (!dist_base) {
+ acpi_data.dist_base = ioremap(dist->base_address,
+ ACPI_GICV3_DIST_MEM_SIZE);
+ if (!acpi_data.dist_base) {
pr_err("Unable to map GICD registers\n");
return -ENOMEM;
}
- err = gic_validate_dist_version(dist_base);
+ err = gic_validate_dist_version(acpi_data.dist_base);
if (err) {
- pr_err("No distributor detected at @%p, giving up", dist_base);
+ pr_err("No distributor detected at @%p, giving up",
+ acpi_data.dist_base);
goto out_dist_unmap;
}
- redist_regs = kzalloc(sizeof(*redist_regs) * nr_redist_regions,
- GFP_KERNEL);
- if (!redist_regs) {
+ size = sizeof(*acpi_data.redist_regs) * acpi_data.nr_redist_regions;
+ acpi_data.redist_regs = kzalloc(size, GFP_KERNEL);
+ if (!acpi_data.redist_regs) {
err = -ENOMEM;
goto out_dist_unmap;
}
@@ -1141,29 +1256,31 @@ gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end)
if (err)
goto out_redist_unmap;
- domain_handle = irq_domain_alloc_fwnode(dist_base);
+ domain_handle = irq_domain_alloc_fwnode(acpi_data.dist_base);
if (!domain_handle) {
err = -ENOMEM;
goto out_redist_unmap;
}
- err = gic_init_bases(dist_base, redist_regs, nr_redist_regions, 0,
- domain_handle);
+ err = gic_init_bases(acpi_data.dist_base, acpi_data.redist_regs,
+ acpi_data.nr_redist_regions, 0, domain_handle);
if (err)
goto out_fwhandle_free;
acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, domain_handle);
+ gic_acpi_setup_kvm_info();
+
return 0;
out_fwhandle_free:
irq_domain_free_fwnode(domain_handle);
out_redist_unmap:
- for (i = 0; i < nr_redist_regions; i++)
- if (redist_regs[i].redist_base)
- iounmap(redist_regs[i].redist_base);
- kfree(redist_regs);
+ for (i = 0; i < acpi_data.nr_redist_regions; i++)
+ if (acpi_data.redist_regs[i].redist_base)
+ iounmap(acpi_data.redist_regs[i].redist_base);
+ kfree(acpi_data.redist_regs);
out_dist_unmap:
- iounmap(dist_base);
+ iounmap(acpi_data.dist_base);
return err;
}
IRQCHIP_ACPI_DECLARE(gic_v3, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 282344b95ec2..3f1d9fd3a462 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -102,6 +102,8 @@ static struct static_key supports_deactivate = STATIC_KEY_INIT_TRUE;
static struct gic_chip_data gic_data[CONFIG_ARM_GIC_MAX_NR] __read_mostly;
+static struct gic_kvm_info gic_v2_kvm_info;
+
#ifdef CONFIG_GIC_NON_BANKED
static void __iomem *gic_get_percpu_base(union gic_base *base)
{
@@ -1189,6 +1191,29 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
return true;
}
+static void __init gic_of_setup_kvm_info(struct device_node *node)
+{
+ int ret;
+ struct resource *vctrl_res = &gic_v2_kvm_info.vctrl;
+ struct resource *vcpu_res = &gic_v2_kvm_info.vcpu;
+
+ gic_v2_kvm_info.type = GIC_V2;
+
+ gic_v2_kvm_info.maint_irq = irq_of_parse_and_map(node, 0);
+ if (!gic_v2_kvm_info.maint_irq)
+ return;
+
+ ret = of_address_to_resource(node, 2, vctrl_res);
+ if (ret)
+ return;
+
+ ret = of_address_to_resource(node, 3, vcpu_res);
+ if (ret)
+ return;
+
+ gic_set_kvm_info(&gic_v2_kvm_info);
+}
+
int __init
gic_of_init(struct device_node *node, struct device_node *parent)
{
@@ -1218,8 +1243,10 @@ gic_of_init(struct device_node *node, struct device_node *parent)
__gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset,
&node->fwnode);
- if (!gic_cnt)
+ if (!gic_cnt) {
gic_init_physaddr(node);
+ gic_of_setup_kvm_info(node);
+ }
if (parent) {
irq = irq_of_parse_and_map(node, 0);
@@ -1245,7 +1272,14 @@ IRQCHIP_DECLARE(pl390, "arm,pl390", gic_of_init);
#endif
#ifdef CONFIG_ACPI
-static phys_addr_t cpu_phy_base __initdata;
+static struct
+{
+ phys_addr_t cpu_phys_base;
+ u32 maint_irq;
+ int maint_irq_mode;
+ phys_addr_t vctrl_base;
+ phys_addr_t vcpu_base;
+} acpi_data __initdata;
static int __init
gic_acpi_parse_madt_cpu(struct acpi_subtable_header *header,
@@ -1265,10 +1299,16 @@ gic_acpi_parse_madt_cpu(struct acpi_subtable_header *header,
* All CPU interface addresses have to be the same.
*/
gic_cpu_base = processor->base_address;
- if (cpu_base_assigned && gic_cpu_base != cpu_phy_base)
+ if (cpu_base_assigned && gic_cpu_base != acpi_data.cpu_phys_base)
return -EINVAL;
- cpu_phy_base = gic_cpu_base;
+ acpi_data.cpu_phys_base = gic_cpu_base;
+ acpi_data.maint_irq = processor->vgic_interrupt;
+ acpi_data.maint_irq_mode = (processor->flags & ACPI_MADT_VGIC_IRQ_MODE) ?
+ ACPI_EDGE_SENSITIVE : ACPI_LEVEL_SENSITIVE;
+ acpi_data.vctrl_base = processor->gich_base_address;
+ acpi_data.vcpu_base = processor->gicv_base_address;
+
cpu_base_assigned = 1;
return 0;
}
@@ -1299,6 +1339,41 @@ static bool __init gic_validate_dist(struct acpi_subtable_header *header,
#define ACPI_GICV2_DIST_MEM_SIZE (SZ_4K)
#define ACPI_GIC_CPU_IF_MEM_SIZE (SZ_8K)
+#define ACPI_GICV2_VCTRL_MEM_SIZE (SZ_4K)
+#define ACPI_GICV2_VCPU_MEM_SIZE (SZ_8K)
+
+static void __init gic_acpi_setup_kvm_info(void)
+{
+ int irq;
+ struct resource *vctrl_res = &gic_v2_kvm_info.vctrl;
+ struct resource *vcpu_res = &gic_v2_kvm_info.vcpu;
+
+ gic_v2_kvm_info.type = GIC_V2;
+
+ if (!acpi_data.vctrl_base)
+ return;
+
+ vctrl_res->flags = IORESOURCE_MEM;
+ vctrl_res->start = acpi_data.vctrl_base;
+ vctrl_res->end = vctrl_res->start + ACPI_GICV2_VCTRL_MEM_SIZE - 1;
+
+ if (!acpi_data.vcpu_base)
+ return;
+
+ vcpu_res->flags = IORESOURCE_MEM;
+ vcpu_res->start = acpi_data.vcpu_base;
+ vcpu_res->end = vcpu_res->start + ACPI_GICV2_VCPU_MEM_SIZE - 1;
+
+ irq = acpi_register_gsi(NULL, acpi_data.maint_irq,
+ acpi_data.maint_irq_mode,
+ ACPI_ACTIVE_HIGH);
+ if (irq <= 0)
+ return;
+
+ gic_v2_kvm_info.maint_irq = irq;
+
+ gic_set_kvm_info(&gic_v2_kvm_info);
+}
static int __init gic_v2_acpi_init(struct acpi_subtable_header *header,
const unsigned long end)
@@ -1316,7 +1391,7 @@ static int __init gic_v2_acpi_init(struct acpi_subtable_header *header,
return -EINVAL;
}
- cpu_base = ioremap(cpu_phy_base, ACPI_GIC_CPU_IF_MEM_SIZE);
+ cpu_base = ioremap(acpi_data.cpu_phys_base, ACPI_GIC_CPU_IF_MEM_SIZE);
if (!cpu_base) {
pr_err("Unable to map GICC registers\n");
return -ENOMEM;
@@ -1356,6 +1431,8 @@ static int __init gic_v2_acpi_init(struct acpi_subtable_header *header,
if (IS_ENABLED(CONFIG_ARM_GIC_V2M))
gicv2m_init(NULL, gic_data[0].domain);
+ gic_acpi_setup_kvm_info();
+
return 0;
}
IRQCHIP_ACPI_DECLARE(gic_v2, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index c5ed27c54724..993630359fe4 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -82,6 +82,7 @@ static const char version[] =
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_gpio.h>
+#include <linux/acpi.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
@@ -2472,6 +2473,14 @@ static struct dev_pm_ops smc_drv_pm_ops = {
.resume = smc_drv_resume,
};
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id smc91x_acpi_match[] = {
+ { "LNRO0003", },
+ { }
+};
+MODULE_DEVICE_TABLE(acpi, smc91x_acpi_match);
+#endif
+
static struct platform_driver smc_driver = {
.probe = smc_drv_probe,
.remove = smc_drv_remove,
@@ -2479,6 +2488,7 @@ static struct platform_driver smc_driver = {
.name = CARDNAME,
.pm = &smc_drv_pm_ops,
.of_match_table = of_match_ptr(smc91x_match),
+ .acpi_match_table = ACPI_PTR(smc91x_acpi_match),
},
};
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index e2a48415d969..b3bec3aaa45d 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -112,4 +112,7 @@ config OF_OVERLAY
While this option is selected automatically when needed, you can
enable it manually to improve device tree unit test coverage.
+config OF_NUMA
+ bool
+
endif # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index 156c072b3117..bee3fa96b981 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -14,5 +14,6 @@ obj-$(CONFIG_OF_MTD) += of_mtd.o
obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
obj-$(CONFIG_OF_RESOLVE) += resolver.o
obj-$(CONFIG_OF_OVERLAY) += overlay.o
+obj-$(CONFIG_OF_NUMA) += of_numa.o
obj-$(CONFIG_OF_UNITTEST) += unittest-data/
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 91a469d55b8f..0a553c084a81 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -4,6 +4,7 @@
#include <linux/ioport.h>
#include <linux/module.h>
#include <linux/of_address.h>
+#include <linux/pci.h>
#include <linux/pci_regs.h>
#include <linux/sizes.h>
#include <linux/slab.h>
@@ -673,121 +674,6 @@ const __be32 *of_get_address(struct device_node *dev, int index, u64 *size,
}
EXPORT_SYMBOL(of_get_address);
-#ifdef PCI_IOBASE
-struct io_range {
- struct list_head list;
- phys_addr_t start;
- resource_size_t size;
-};
-
-static LIST_HEAD(io_range_list);
-static DEFINE_SPINLOCK(io_range_lock);
-#endif
-
-/*
- * Record the PCI IO range (expressed as CPU physical address + size).
- * Return a negative value if an error has occured, zero otherwise
- */
-int __weak pci_register_io_range(phys_addr_t addr, resource_size_t size)
-{
- int err = 0;
-
-#ifdef PCI_IOBASE
- struct io_range *range;
- resource_size_t allocated_size = 0;
-
- /* check if the range hasn't been previously recorded */
- spin_lock(&io_range_lock);
- list_for_each_entry(range, &io_range_list, list) {
- if (addr >= range->start && addr + size <= range->start + size) {
- /* range already registered, bail out */
- goto end_register;
- }
- allocated_size += range->size;
- }
-
- /* range not registed yet, check for available space */
- if (allocated_size + size - 1 > IO_SPACE_LIMIT) {
- /* if it's too big check if 64K space can be reserved */
- if (allocated_size + SZ_64K - 1 > IO_SPACE_LIMIT) {
- err = -E2BIG;
- goto end_register;
- }
-
- size = SZ_64K;
- pr_warn("Requested IO range too big, new size set to 64K\n");
- }
-
- /* add the range to the list */
- range = kzalloc(sizeof(*range), GFP_ATOMIC);
- if (!range) {
- err = -ENOMEM;
- goto end_register;
- }
-
- range->start = addr;
- range->size = size;
-
- list_add_tail(&range->list, &io_range_list);
-
-end_register:
- spin_unlock(&io_range_lock);
-#endif
-
- return err;
-}
-
-phys_addr_t pci_pio_to_address(unsigned long pio)
-{
- phys_addr_t address = (phys_addr_t)OF_BAD_ADDR;
-
-#ifdef PCI_IOBASE
- struct io_range *range;
- resource_size_t allocated_size = 0;
-
- if (pio > IO_SPACE_LIMIT)
- return address;
-
- spin_lock(&io_range_lock);
- list_for_each_entry(range, &io_range_list, list) {
- if (pio >= allocated_size && pio < allocated_size + range->size) {
- address = range->start + pio - allocated_size;
- break;
- }
- allocated_size += range->size;
- }
- spin_unlock(&io_range_lock);
-#endif
-
- return address;
-}
-
-unsigned long __weak pci_address_to_pio(phys_addr_t address)
-{
-#ifdef PCI_IOBASE
- struct io_range *res;
- resource_size_t offset = 0;
- unsigned long addr = -1;
-
- spin_lock(&io_range_lock);
- list_for_each_entry(res, &io_range_list, list) {
- if (address >= res->start && address < res->start + res->size) {
- addr = address - res->start + offset;
- break;
- }
- offset += res->size;
- }
- spin_unlock(&io_range_lock);
-
- return addr;
-#else
- if (address > IO_SPACE_LIMIT)
- return (unsigned long)-1;
-
- return (unsigned long) address;
-#endif
-}
-
static int __of_address_to_resource(struct device_node *dev,
const __be32 *addrp, u64 size, unsigned int flags,
const char *name, struct resource *r)
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 3349d2aa6634..b50f77543ad0 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -805,7 +805,7 @@ static inline void early_init_dt_check_for_initrd(unsigned long node)
#ifdef CONFIG_SERIAL_EARLYCON
-static int __init early_init_dt_scan_chosen_serial(void)
+int __init early_init_dt_scan_chosen_stdout(void)
{
int offset;
const char *p, *q, *options = NULL;
@@ -849,15 +849,6 @@ static int __init early_init_dt_scan_chosen_serial(void)
}
return -ENODEV;
}
-
-static int __init setup_of_earlycon(char *buf)
-{
- if (buf)
- return 0;
-
- return early_init_dt_scan_chosen_serial();
-}
-early_param("earlycon", setup_of_earlycon);
#endif
/**
diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c
new file mode 100644
index 000000000000..ed5a097f0801
--- /dev/null
+++ b/drivers/of/of_numa.c
@@ -0,0 +1,211 @@
+/*
+ * OF NUMA Parsing support.
+ *
+ * Copyright (C) 2015 - 2016 Cavium Inc.
+ *
+ * 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/>.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/nodemask.h>
+
+#include <asm/numa.h>
+
+/* define default numa node to 0 */
+#define DEFAULT_NODE 0
+
+/*
+ * Even though we connect cpus to numa domains later in SMP
+ * init, we need to know the node ids now for all cpus.
+*/
+static void __init of_numa_parse_cpu_nodes(void)
+{
+ u32 nid;
+ int r;
+ struct device_node *cpus;
+ struct device_node *np = NULL;
+
+ cpus = of_find_node_by_path("/cpus");
+ if (!cpus)
+ return;
+
+ for_each_child_of_node(cpus, np) {
+ /* Skip things that are not CPUs */
+ if (of_node_cmp(np->type, "cpu") != 0)
+ continue;
+
+ r = of_property_read_u32(np, "numa-node-id", &nid);
+ if (r)
+ continue;
+
+ pr_debug("NUMA: CPU on %u\n", nid);
+ if (nid >= MAX_NUMNODES)
+ pr_warn("NUMA: Node id %u exceeds maximum value\n",
+ nid);
+ else
+ node_set(nid, numa_nodes_parsed);
+ }
+}
+
+static int __init of_numa_parse_memory_nodes(void)
+{
+ struct device_node *np = NULL;
+ struct resource rsrc;
+ u32 nid;
+ int r = 0;
+
+ for (;;) {
+ np = of_find_node_by_type(np, "memory");
+ if (!np)
+ break;
+
+ r = of_property_read_u32(np, "numa-node-id", &nid);
+ if (r == -EINVAL)
+ /*
+ * property doesn't exist if -EINVAL, continue
+ * looking for more memory nodes with
+ * "numa-node-id" property
+ */
+ continue;
+ else if (r)
+ /* some other error */
+ break;
+
+ r = of_address_to_resource(np, 0, &rsrc);
+ if (r) {
+ pr_err("NUMA: bad reg property in memory node\n");
+ break;
+ }
+
+ pr_debug("NUMA: base = %llx len = %llx, node = %u\n",
+ rsrc.start, rsrc.end - rsrc.start + 1, nid);
+
+
+ r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
+ if (r)
+ break;
+ }
+ of_node_put(np);
+
+ return r;
+}
+
+static int __init of_numa_parse_distance_map_v1(struct device_node *map)
+{
+ const __be32 *matrix;
+ int entry_count;
+ int i;
+
+ pr_info("NUMA: parsing numa-distance-map-v1\n");
+
+ matrix = of_get_property(map, "distance-matrix", NULL);
+ if (!matrix) {
+ pr_err("NUMA: No distance-matrix property in distance-map\n");
+ return -EINVAL;
+ }
+
+ entry_count = of_property_count_u32_elems(map, "distance-matrix");
+ if (entry_count <= 0) {
+ pr_err("NUMA: Invalid distance-matrix\n");
+ return -EINVAL;
+ }
+
+ for (i = 0; i + 2 < entry_count; i += 3) {
+ u32 nodea, nodeb, distance;
+
+ nodea = of_read_number(matrix, 1);
+ matrix++;
+ nodeb = of_read_number(matrix, 1);
+ matrix++;
+ distance = of_read_number(matrix, 1);
+ matrix++;
+
+ numa_set_distance(nodea, nodeb, distance);
+ pr_debug("NUMA: distance[node%d -> node%d] = %d\n",
+ nodea, nodeb, distance);
+
+ /* Set default distance of node B->A same as A->B */
+ if (nodeb > nodea)
+ numa_set_distance(nodeb, nodea, distance);
+ }
+
+ return 0;
+}
+
+static int __init of_numa_parse_distance_map(void)
+{
+ int ret = 0;
+ struct device_node *np;
+
+ np = of_find_compatible_node(NULL, NULL,
+ "numa-distance-map-v1");
+ if (np)
+ ret = of_numa_parse_distance_map_v1(np);
+
+ of_node_put(np);
+ return ret;
+}
+
+int of_node_to_nid(struct device_node *device)
+{
+ struct device_node *np;
+ u32 nid;
+ int r = -ENODATA;
+
+ np = of_node_get(device);
+
+ while (np) {
+ struct device_node *parent;
+
+ r = of_property_read_u32(np, "numa-node-id", &nid);
+ /*
+ * -EINVAL indicates the property was not found, and
+ * we walk up the tree trying to find a parent with a
+ * "numa-node-id". Any other type of error indicates
+ * a bad device tree and we give up.
+ */
+ if (r != -EINVAL)
+ break;
+
+ parent = of_get_parent(np);
+ of_node_put(np);
+ np = parent;
+ }
+ if (np && r)
+ pr_warn("NUMA: Invalid \"numa-node-id\" property in node %s\n",
+ np->name);
+ of_node_put(np);
+
+ if (!r) {
+ if (nid >= MAX_NUMNODES)
+ pr_warn("NUMA: Node id %u exceeds maximum value\n",
+ nid);
+ else
+ return nid;
+ }
+
+ return NUMA_NO_NODE;
+}
+EXPORT_SYMBOL(of_node_to_nid);
+
+int __init of_numa_init(void)
+{
+ int r;
+
+ of_numa_parse_cpu_nodes();
+ r = of_numa_parse_memory_nodes();
+ if (r)
+ return r;
+ return of_numa_parse_distance_map();
+}
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 209292e067d2..56389be5d08b 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -83,6 +83,9 @@ config HT_IRQ
config PCI_ATS
bool
+config PCI_ECAM
+ bool
+
config PCI_IOV
bool "PCI IOV support"
depends on PCI
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 2154092ddee8..1fa6925733d3 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -55,6 +55,8 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o
obj-$(CONFIG_PCI_STUB) += pci-stub.o
+obj-$(CONFIG_PCI_ECAM) += ecam.o
+
obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
obj-$(CONFIG_OF) += of.o
diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c
new file mode 100644
index 000000000000..3d52005c09f8
--- /dev/null
+++ b/drivers/pci/ecam.c
@@ -0,0 +1,161 @@
+/*
+ * Copyright 2016 Broadcom
+ *
+ * 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 (the "GPL").
+ *
+ * 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 version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+
+#include "ecam.h"
+
+/*
+ * On 64 bit systems, we do a single ioremap for the whole config space
+ * since we have enough virtual address range available. On 32 bit, do an
+ * ioremap per bus.
+ */
+static const bool per_bus_mapping = !config_enabled(CONFIG_64BIT);
+
+/*
+ * Create a PCI config space window
+ * - reserve mem region
+ * - alloc struct pci_config_window with space for all mappings
+ * - ioremap the config space
+ */
+struct pci_config_window *pci_ecam_create(struct device *dev,
+ struct resource *cfgres, struct resource *busr,
+ struct pci_ecam_ops *ops)
+{
+ struct pci_config_window *cfg;
+ unsigned int bus_range, bus_range_max, bsz;
+ int i, err;
+
+ if (busr->start > busr->end)
+ return ERR_PTR(-EINVAL);
+
+ cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+ if (!cfg)
+ return ERR_PTR(-ENOMEM);
+
+ cfg->ops = ops;
+ cfg->busr.start = busr->start;
+ cfg->busr.end = busr->end;
+ cfg->busr.flags = IORESOURCE_BUS;
+ bus_range = resource_size(&cfg->busr);
+ bus_range_max = resource_size(cfgres) >> ops->bus_shift;
+ if (bus_range > bus_range_max) {
+ dev_warn(dev, "bus max %#x reduced to %#x",
+ bus_range, bus_range_max);
+ bus_range = bus_range_max;
+ cfg->busr.end = busr->start + bus_range - 1;
+ }
+ bsz = 1 << ops->bus_shift;
+
+ cfg->res.start = cfgres->start;
+ cfg->res.end = cfgres->end;
+ cfg->res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ cfg->res.name = "PCI ECAM";
+
+ err = request_resource(&iomem_resource, &cfg->res);
+ if (err) {
+ dev_err(dev, "request ECAM res %pR failed\n", &cfg->res);
+ goto err_exit;
+ }
+
+ if (per_bus_mapping) {
+ cfg->winp = kcalloc(bus_range, sizeof(*cfg->winp), GFP_KERNEL);
+ if (!cfg->winp)
+ goto err_exit_malloc;
+ for (i = 0; i < bus_range; i++) {
+ cfg->winp[i] = ioremap(cfgres->start + i * bsz, bsz);
+ if (!cfg->winp[i])
+ goto err_exit_iomap;
+ }
+ } else {
+ cfg->win = ioremap(cfgres->start, bus_range * bsz);
+ if (!cfg->win)
+ goto err_exit_iomap;
+ }
+
+ if (ops->init) {
+ err = ops->init(dev, cfg);
+ if (err)
+ goto err_exit;
+ }
+ dev_info(dev, "ECAM at %pR for %pR\n", &cfg->res, &cfg->busr);
+ return cfg;
+
+err_exit_iomap:
+ dev_err(dev, "ECAM ioremap failed\n");
+err_exit_malloc:
+ err = -ENOMEM;
+err_exit:
+ pci_ecam_free(cfg);
+ return ERR_PTR(err);
+}
+
+void pci_ecam_free(struct pci_config_window *cfg)
+{
+ int i;
+
+ if (per_bus_mapping) {
+ if (cfg->winp) {
+ for (i = 0; i < resource_size(&cfg->busr); i++)
+ if (cfg->winp[i])
+ iounmap(cfg->winp[i]);
+ kfree(cfg->winp);
+ }
+ } else {
+ if (cfg->win)
+ iounmap(cfg->win);
+ }
+ if (cfg->res.parent)
+ release_resource(&cfg->res);
+ kfree(cfg);
+}
+
+/*
+ * Function to implement the pci_ops ->map_bus method
+ */
+void __iomem *pci_ecam_map_bus(struct pci_bus *bus, unsigned int devfn,
+ int where)
+{
+ struct pci_config_window *cfg = bus->sysdata;
+ unsigned int devfn_shift = cfg->ops->bus_shift - 8;
+ unsigned int busn = bus->number;
+ void __iomem *base;
+
+ if (busn < cfg->busr.start || busn > cfg->busr.end)
+ return NULL;
+
+ busn -= cfg->busr.start;
+ if (per_bus_mapping)
+ base = cfg->winp[busn];
+ else
+ base = cfg->win + (busn << cfg->ops->bus_shift);
+ return base + (devfn << devfn_shift) + where;
+}
+
+/* ECAM ops */
+struct pci_ecam_ops pci_generic_ecam_ops = {
+ .bus_shift = 20,
+ .pci_ops = {
+ .map_bus = pci_ecam_map_bus,
+ .read = pci_generic_config_read,
+ .write = pci_generic_config_write,
+ }
+};
diff --git a/drivers/pci/ecam.h b/drivers/pci/ecam.h
new file mode 100644
index 000000000000..1cccf575ba7c
--- /dev/null
+++ b/drivers/pci/ecam.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2016 Broadcom
+ *
+ * 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 (the "GPL").
+ *
+ * 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 version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+#ifndef DRIVERS_PCI_ECAM_H
+#define DRIVERS_PCI_ECAM_H
+
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+/*
+ * struct to hold pci ops and bus shift of the config window
+ * for a PCI controller.
+ */
+struct pci_config_window;
+struct pci_ecam_ops {
+ unsigned int bus_shift;
+ struct pci_ops pci_ops;
+ int (*init)(struct device *,
+ struct pci_config_window *);
+};
+
+/*
+ * struct to hold the mappings of a config space window. This
+ * is expected to be used as sysdata for PCI controlllers which
+ * use ECAM.
+ */
+struct pci_config_window {
+ struct resource res;
+ struct resource busr;
+ void *priv;
+ struct pci_ecam_ops *ops;
+ union {
+ void __iomem *win; /* 64-bit single mapping */
+ void __iomem **winp; /* 32-bit per bus mapping */
+ };
+#ifdef CONFIG_ACPI_PCI_HOST_GENERIC
+ struct acpi_device *companion; /* ACPI companion device */
+#endif
+ int domain;
+
+};
+
+/* create and free for pci_config_window */
+struct pci_config_window *pci_ecam_create(struct device *dev,
+ struct resource *cfgres, struct resource *busr,
+ struct pci_ecam_ops *ops);
+void pci_ecam_free(struct pci_config_window *cfg);
+
+/* map_bus when ->sysdata is an instance of pci_config_window */
+void __iomem *pci_ecam_map_bus(struct pci_bus *bus, unsigned int devfn,
+ int where);
+/* default ECAM ops, bus shift 20, generic read and write */
+extern struct pci_ecam_ops pci_generic_ecam_ops;
+
+#ifdef CONFIG_PCI_HOST_GENERIC
+/* for DT based pci controllers that support ECAM */
+int pci_host_common_probe(struct platform_device *pdev,
+ struct pci_ecam_ops *ops);
+#endif
+#endif
diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index 7a0780d56d2d..963300dffcba 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -77,6 +77,7 @@ config PCI_RCAR_GEN2_PCIE
config PCI_HOST_COMMON
bool
+ select PCI_ECAM
config PCI_HOST_GENERIC
bool "Generic PCI host controller"
diff --git a/drivers/pci/host/pci-host-common.c b/drivers/pci/host/pci-host-common.c
index e9f850f07968..8cba7ab73df9 100644
--- a/drivers/pci/host/pci-host-common.c
+++ b/drivers/pci/host/pci-host-common.c
@@ -22,27 +22,21 @@
#include <linux/of_pci.h>
#include <linux/platform_device.h>
-#include "pci-host-common.h"
+#include "../ecam.h"
-static void gen_pci_release_of_pci_ranges(struct gen_pci *pci)
-{
- pci_free_resource_list(&pci->resources);
-}
-
-static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
+static int gen_pci_parse_request_of_pci_ranges(struct device *dev,
+ struct list_head *resources, struct resource **bus_range)
{
int err, res_valid = 0;
- struct device *dev = pci->host.dev.parent;
struct device_node *np = dev->of_node;
resource_size_t iobase;
struct resource_entry *win;
- err = of_pci_get_host_bridge_resources(np, 0, 0xff, &pci->resources,
- &iobase);
+ err = of_pci_get_host_bridge_resources(np, 0, 0xff, resources, &iobase);
if (err)
return err;
- resource_list_for_each_entry(win, &pci->resources) {
+ resource_list_for_each_entry(win, resources) {
struct resource *parent, *res = win->res;
switch (resource_type(res)) {
@@ -60,7 +54,7 @@ static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
res_valid |= !(res->flags & IORESOURCE_PREFETCH);
break;
case IORESOURCE_BUS:
- pci->cfg.bus_range = res;
+ *bus_range = res;
default:
continue;
}
@@ -79,65 +73,60 @@ static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
return 0;
out_release_res:
- gen_pci_release_of_pci_ranges(pci);
return err;
}
-static int gen_pci_parse_map_cfg_windows(struct gen_pci *pci)
+static void gen_pci_unmap_cfg(void *ptr)
+{
+ pci_ecam_free((struct pci_config_window *)ptr);
+}
+
+static struct pci_config_window *gen_pci_init(struct device *dev,
+ struct list_head *resources, struct pci_ecam_ops *ops)
{
int err;
- u8 bus_max;
- resource_size_t busn;
- struct resource *bus_range;
- struct device *dev = pci->host.dev.parent;
- struct device_node *np = dev->of_node;
- u32 sz = 1 << pci->cfg.ops->bus_shift;
+ struct resource cfgres;
+ struct resource *bus_range = NULL;
+ struct pci_config_window *cfg;
- err = of_address_to_resource(np, 0, &pci->cfg.res);
+ /* Parse our PCI ranges and request their resources */
+ err = gen_pci_parse_request_of_pci_ranges(dev, resources, &bus_range);
+ if (err)
+ goto err_out;
+
+ err = of_address_to_resource(dev->of_node, 0, &cfgres);
if (err) {
dev_err(dev, "missing \"reg\" property\n");
- return err;
+ goto err_out;
}
- /* Limit the bus-range to fit within reg */
- bus_max = pci->cfg.bus_range->start +
- (resource_size(&pci->cfg.res) >> pci->cfg.ops->bus_shift) - 1;
- pci->cfg.bus_range->end = min_t(resource_size_t,
- pci->cfg.bus_range->end, bus_max);
-
- pci->cfg.win = devm_kcalloc(dev, resource_size(pci->cfg.bus_range),
- sizeof(*pci->cfg.win), GFP_KERNEL);
- if (!pci->cfg.win)
- return -ENOMEM;
-
- /* Map our Configuration Space windows */
- if (!devm_request_mem_region(dev, pci->cfg.res.start,
- resource_size(&pci->cfg.res),
- "Configuration Space"))
- return -ENOMEM;
-
- bus_range = pci->cfg.bus_range;
- for (busn = bus_range->start; busn <= bus_range->end; ++busn) {
- u32 idx = busn - bus_range->start;
-
- pci->cfg.win[idx] = devm_ioremap(dev,
- pci->cfg.res.start + idx * sz,
- sz);
- if (!pci->cfg.win[idx])
- return -ENOMEM;
+ cfg = pci_ecam_create(dev, &cfgres, bus_range, ops);
+ if (IS_ERR(cfg)) {
+ err = PTR_ERR(cfg);
+ goto err_out;
}
- return 0;
+ err = devm_add_action(dev, gen_pci_unmap_cfg, cfg);
+ if (err) {
+ gen_pci_unmap_cfg(cfg);
+ goto err_out;
+ }
+ return cfg;
+
+err_out:
+ pci_free_resource_list(resources);
+ return ERR_PTR(err);
}
int pci_host_common_probe(struct platform_device *pdev,
- struct gen_pci *pci)
+ struct pci_ecam_ops *ops)
{
- int err;
const char *type;
struct device *dev = &pdev->dev;
struct device_node *np = dev->of_node;
struct pci_bus *bus, *child;
+ struct pci_config_window *cfg;
+ struct list_head resources;
type = of_get_property(np, "device_type", NULL);
if (!type || strcmp(type, "pci")) {
@@ -147,29 +136,18 @@ int pci_host_common_probe(struct platform_device *pdev,
of_pci_check_probe_only();
- pci->host.dev.parent = dev;
- INIT_LIST_HEAD(&pci->host.windows);
- INIT_LIST_HEAD(&pci->resources);
-
- /* Parse our PCI ranges and request their resources */
- err = gen_pci_parse_request_of_pci_ranges(pci);
- if (err)
- return err;
-
/* Parse and map our Configuration Space windows */
- err = gen_pci_parse_map_cfg_windows(pci);
- if (err) {
- gen_pci_release_of_pci_ranges(pci);
- return err;
- }
+ INIT_LIST_HEAD(&resources);
+ cfg = gen_pci_init(dev, &resources, ops);
+ if (IS_ERR(cfg))
+ return PTR_ERR(cfg);
/* Do not reassign resources if probe only */
if (!pci_has_flag(PCI_PROBE_ONLY))
pci_add_flags(PCI_REASSIGN_ALL_RSRC | PCI_REASSIGN_ALL_BUS);
-
- bus = pci_scan_root_bus(dev, pci->cfg.bus_range->start,
- &pci->cfg.ops->ops, pci, &pci->resources);
+ bus = pci_scan_root_bus(dev, cfg->busr.start, &ops->pci_ops, cfg,
+ &resources);
if (!bus) {
dev_err(dev, "Scanning rootbus failed");
return -ENODEV;
diff --git a/drivers/pci/host/pci-host-common.h b/drivers/pci/host/pci-host-common.h
deleted file mode 100644
index 09f3fa0a55d7..000000000000
--- a/drivers/pci/host/pci-host-common.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * 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/>.
- *
- * Copyright (C) 2014 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#ifndef _PCI_HOST_COMMON_H
-#define _PCI_HOST_COMMON_H
-
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-
-struct gen_pci_cfg_bus_ops {
- u32 bus_shift;
- struct pci_ops ops;
-};
-
-struct gen_pci_cfg_windows {
- struct resource res;
- struct resource *bus_range;
- void __iomem **win;
-
- struct gen_pci_cfg_bus_ops *ops;
-};
-
-struct gen_pci {
- struct pci_host_bridge host;
- struct gen_pci_cfg_windows cfg;
- struct list_head resources;
-};
-
-int pci_host_common_probe(struct platform_device *pdev,
- struct gen_pci *pci);
-
-#endif /* _PCI_HOST_COMMON_H */
diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c
index e8aa78faa16d..6eaceab1bf04 100644
--- a/drivers/pci/host/pci-host-generic.c
+++ b/drivers/pci/host/pci-host-generic.c
@@ -25,41 +25,12 @@
#include <linux/of_pci.h>
#include <linux/platform_device.h>
-#include "pci-host-common.h"
+#include "../ecam.h"
-static void __iomem *gen_pci_map_cfg_bus_cam(struct pci_bus *bus,
- unsigned int devfn,
- int where)
-{
- struct gen_pci *pci = bus->sysdata;
- resource_size_t idx = bus->number - pci->cfg.bus_range->start;
-
- return pci->cfg.win[idx] + ((devfn << 8) | where);
-}
-
-static struct gen_pci_cfg_bus_ops gen_pci_cfg_cam_bus_ops = {
+static struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = {
.bus_shift = 16,
- .ops = {
- .map_bus = gen_pci_map_cfg_bus_cam,
- .read = pci_generic_config_read,
- .write = pci_generic_config_write,
- }
-};
-
-static void __iomem *gen_pci_map_cfg_bus_ecam(struct pci_bus *bus,
- unsigned int devfn,
- int where)
-{
- struct gen_pci *pci = bus->sysdata;
- resource_size_t idx = bus->number - pci->cfg.bus_range->start;
-
- return pci->cfg.win[idx] + ((devfn << 12) | where);
-}
-
-static struct gen_pci_cfg_bus_ops gen_pci_cfg_ecam_bus_ops = {
- .bus_shift = 20,
- .ops = {
- .map_bus = gen_pci_map_cfg_bus_ecam,
+ .pci_ops = {
+ .map_bus = pci_ecam_map_bus,
.read = pci_generic_config_read,
.write = pci_generic_config_write,
}
@@ -70,25 +41,22 @@ static const struct of_device_id gen_pci_of_match[] = {
.data = &gen_pci_cfg_cam_bus_ops },
{ .compatible = "pci-host-ecam-generic",
- .data = &gen_pci_cfg_ecam_bus_ops },
+ .data = &pci_generic_ecam_ops },
{ },
};
+
MODULE_DEVICE_TABLE(of, gen_pci_of_match);
static int gen_pci_probe(struct platform_device *pdev)
{
- struct device *dev = &pdev->dev;
const struct of_device_id *of_id;
- struct gen_pci *pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
-
- if (!pci)
- return -ENOMEM;
+ struct pci_ecam_ops *ops;
- of_id = of_match_node(gen_pci_of_match, dev->of_node);
- pci->cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
+ of_id = of_match_node(gen_pci_of_match, pdev->dev.of_node);
+ ops = (struct pci_ecam_ops *)of_id->data;
- return pci_host_common_probe(pdev, pci);
+ return pci_host_common_probe(pdev, ops);
}
static struct platform_driver gen_pci_driver = {
diff --git a/drivers/pci/host/pci-thunder-ecam.c b/drivers/pci/host/pci-thunder-ecam.c
index d71935cb2678..540d030613eb 100644
--- a/drivers/pci/host/pci-thunder-ecam.c
+++ b/drivers/pci/host/pci-thunder-ecam.c
@@ -13,18 +13,7 @@
#include <linux/of.h>
#include <linux/platform_device.h>
-#include "pci-host-common.h"
-
-/* Mapping is standard ECAM */
-static void __iomem *thunder_ecam_map_bus(struct pci_bus *bus,
- unsigned int devfn,
- int where)
-{
- struct gen_pci *pci = bus->sysdata;
- resource_size_t idx = bus->number - pci->cfg.bus_range->start;
-
- return pci->cfg.win[idx] + ((devfn << 12) | where);
-}
+#include "../ecam.h"
static void set_val(u32 v, int where, int size, u32 *val)
{
@@ -99,7 +88,7 @@ static int handle_ea_bar(u32 e0, int bar, struct pci_bus *bus,
static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn,
int where, int size, u32 *val)
{
- struct gen_pci *pci = bus->sysdata;
+ struct pci_config_window *cfg = bus->sysdata;
int where_a = where & ~3;
void __iomem *addr;
u32 node_bits;
@@ -129,7 +118,7 @@ static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn,
* the config space access window. Since we are working with
* the high-order 32 bits, shift everything down by 32 bits.
*/
- node_bits = (pci->cfg.res.start >> 32) & (1 << 12);
+ node_bits = (cfg->res.start >> 32) & (1 << 12);
v |= node_bits;
set_val(v, where, size, val);
@@ -358,36 +347,24 @@ static int thunder_ecam_config_write(struct pci_bus *bus, unsigned int devfn,
return pci_generic_config_write(bus, devfn, where, size, val);
}
-static struct gen_pci_cfg_bus_ops thunder_ecam_bus_ops = {
+static struct pci_ecam_ops pci_thunder_ecam_ops = {
.bus_shift = 20,
- .ops = {
- .map_bus = thunder_ecam_map_bus,
+ .pci_ops = {
+ .map_bus = pci_ecam_map_bus,
.read = thunder_ecam_config_read,
.write = thunder_ecam_config_write,
}
};
static const struct of_device_id thunder_ecam_of_match[] = {
- { .compatible = "cavium,pci-host-thunder-ecam",
- .data = &thunder_ecam_bus_ops },
-
+ { .compatible = "cavium,pci-host-thunder-ecam" },
{ },
};
MODULE_DEVICE_TABLE(of, thunder_ecam_of_match);
static int thunder_ecam_probe(struct platform_device *pdev)
{
- struct device *dev = &pdev->dev;
- const struct of_device_id *of_id;
- struct gen_pci *pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
-
- if (!pci)
- return -ENOMEM;
-
- of_id = of_match_node(thunder_ecam_of_match, dev->of_node);
- pci->cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
-
- return pci_host_common_probe(pdev, pci);
+ return pci_host_common_probe(pdev, &pci_thunder_ecam_ops);
}
static struct platform_driver thunder_ecam_driver = {
diff --git a/drivers/pci/host/pci-thunder-pem.c b/drivers/pci/host/pci-thunder-pem.c
index cabb92a514ac..a7b61ce35117 100644
--- a/drivers/pci/host/pci-thunder-pem.c
+++ b/drivers/pci/host/pci-thunder-pem.c
@@ -20,34 +20,22 @@
#include <linux/of_pci.h>
#include <linux/platform_device.h>
-#include "pci-host-common.h"
+#include "../ecam.h"
#define PEM_CFG_WR 0x28
#define PEM_CFG_RD 0x30
struct thunder_pem_pci {
- struct gen_pci gen_pci;
u32 ea_entry[3];
void __iomem *pem_reg_base;
};
-static void __iomem *thunder_pem_map_bus(struct pci_bus *bus,
- unsigned int devfn, int where)
-{
- struct gen_pci *pci = bus->sysdata;
- resource_size_t idx = bus->number - pci->cfg.bus_range->start;
-
- return pci->cfg.win[idx] + ((devfn << 16) | where);
-}
-
static int thunder_pem_bridge_read(struct pci_bus *bus, unsigned int devfn,
int where, int size, u32 *val)
{
u64 read_val;
- struct thunder_pem_pci *pem_pci;
- struct gen_pci *pci = bus->sysdata;
-
- pem_pci = container_of(pci, struct thunder_pem_pci, gen_pci);
+ struct pci_config_window *cfg = bus->sysdata;
+ struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv;
if (devfn != 0 || where >= 2048) {
*val = ~0;
@@ -132,17 +120,17 @@ static int thunder_pem_bridge_read(struct pci_bus *bus, unsigned int devfn,
static int thunder_pem_config_read(struct pci_bus *bus, unsigned int devfn,
int where, int size, u32 *val)
{
- struct gen_pci *pci = bus->sysdata;
+ struct pci_config_window *cfg = bus->sysdata;
- if (bus->number < pci->cfg.bus_range->start ||
- bus->number > pci->cfg.bus_range->end)
+ if (bus->number < cfg->busr.start ||
+ bus->number > cfg->busr.end)
return PCIBIOS_DEVICE_NOT_FOUND;
/*
* The first device on the bus is the PEM PCIe bridge.
* Special case its config access.
*/
- if (bus->number == pci->cfg.bus_range->start)
+ if (bus->number == cfg->busr.start)
return thunder_pem_bridge_read(bus, devfn, where, size, val);
return pci_generic_config_read(bus, devfn, where, size, val);
@@ -187,12 +175,11 @@ static u32 thunder_pem_bridge_w1c_bits(int where)
static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
int where, int size, u32 val)
{
- struct gen_pci *pci = bus->sysdata;
- struct thunder_pem_pci *pem_pci;
+ struct pci_config_window *cfg = bus->sysdata;
+ struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv;
u64 write_val, read_val;
u32 mask = 0;
- pem_pci = container_of(pci, struct thunder_pem_pci, gen_pci);
if (devfn != 0 || where >= 2048)
return PCIBIOS_DEVICE_NOT_FOUND;
@@ -256,53 +243,38 @@ static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
static int thunder_pem_config_write(struct pci_bus *bus, unsigned int devfn,
int where, int size, u32 val)
{
- struct gen_pci *pci = bus->sysdata;
+ struct pci_config_window *cfg = bus->sysdata;
- if (bus->number < pci->cfg.bus_range->start ||
- bus->number > pci->cfg.bus_range->end)
+ if (bus->number < cfg->busr.start ||
+ bus->number > cfg->busr.end)
return PCIBIOS_DEVICE_NOT_FOUND;
/*
* The first device on the bus is the PEM PCIe bridge.
* Special case its config access.
*/
- if (bus->number == pci->cfg.bus_range->start)
+ if (bus->number == cfg->busr.start)
return thunder_pem_bridge_write(bus, devfn, where, size, val);
return pci_generic_config_write(bus, devfn, where, size, val);
}
-static struct gen_pci_cfg_bus_ops thunder_pem_bus_ops = {
- .bus_shift = 24,
- .ops = {
- .map_bus = thunder_pem_map_bus,
- .read = thunder_pem_config_read,
- .write = thunder_pem_config_write,
- }
-};
-
-static const struct of_device_id thunder_pem_of_match[] = {
- { .compatible = "cavium,pci-host-thunder-pem",
- .data = &thunder_pem_bus_ops },
-
- { },
-};
-MODULE_DEVICE_TABLE(of, thunder_pem_of_match);
-
-static int thunder_pem_probe(struct platform_device *pdev)
+static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg)
{
- struct device *dev = &pdev->dev;
- const struct of_device_id *of_id;
resource_size_t bar4_start;
struct resource *res_pem;
struct thunder_pem_pci *pem_pci;
+ struct platform_device *pdev;
+
+ /* Only OF support for now */
+ if (!dev->of_node)
+ return -EINVAL;
pem_pci = devm_kzalloc(dev, sizeof(*pem_pci), GFP_KERNEL);
if (!pem_pci)
return -ENOMEM;
- of_id = of_match_node(thunder_pem_of_match, dev->of_node);
- pem_pci->gen_pci.cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
+ pdev = to_platform_device(dev);
/*
* The second register range is the PEM bridge to the PCIe
@@ -330,7 +302,29 @@ static int thunder_pem_probe(struct platform_device *pdev)
pem_pci->ea_entry[1] = (u32)(res_pem->end - bar4_start) & ~3u;
pem_pci->ea_entry[2] = (u32)(bar4_start >> 32);
- return pci_host_common_probe(pdev, &pem_pci->gen_pci);
+ cfg->priv = pem_pci;
+ return 0;
+}
+
+static struct pci_ecam_ops pci_thunder_pem_ops = {
+ .bus_shift = 24,
+ .init = thunder_pem_init,
+ .pci_ops = {
+ .map_bus = pci_ecam_map_bus,
+ .read = thunder_pem_config_read,
+ .write = thunder_pem_config_write,
+ }
+};
+
+static const struct of_device_id thunder_pem_of_match[] = {
+ { .compatible = "cavium,pci-host-thunder-pem" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, thunder_pem_of_match);
+
+static int thunder_pem_probe(struct platform_device *pdev)
+{
+ return pci_host_common_probe(pdev, &pci_thunder_pem_ops);
}
static struct platform_driver thunder_pem_driver = {
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index a080f4496fe2..ba49df7afd6b 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -18,6 +18,7 @@
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/io.h>
+#include <linux/iort.h>
#include <linux/slab.h>
#include <linux/irqdomain.h>
#include <linux/of_irq.h>
@@ -1364,8 +1365,8 @@ u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
of_node = irq_domain_get_of_node(domain);
- if (of_node)
- rid = of_msi_map_rid(&pdev->dev, of_node, rid);
+ rid = of_node ? of_msi_map_rid(&pdev->dev, of_node, rid) :
+ iort_pci_get_msi_rid(pdev, rid);
return rid;
}
@@ -1381,9 +1382,13 @@ u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
*/
struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
{
+ struct irq_domain *dom;
u32 rid = 0;
pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
- return of_msi_map_get_device_domain(&pdev->dev, rid);
+ dom = of_msi_map_get_device_domain(&pdev->dev, rid);
+ if (!dom)
+ dom = iort_pci_get_domain(pdev, rid);
+ return dom;
}
#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 25e0327d4429..a1d7bcfbf569 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -19,12 +19,14 @@
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/log2.h>
+#include <linux/pci-acpi.h>
#include <linux/pci-aspm.h>
#include <linux/pm_wakeup.h>
#include <linux/interrupt.h>
#include <linux/device.h>
#include <linux/pm_runtime.h>
#include <linux/pci_hotplug.h>
+#include <linux/vmalloc.h>
#include <asm/setup.h>
#include <linux/aer.h>
#include "pci.h"
@@ -3021,6 +3023,121 @@ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
}
EXPORT_SYMBOL(pci_request_regions_exclusive);
+#ifdef PCI_IOBASE
+struct io_range {
+ struct list_head list;
+ phys_addr_t start;
+ resource_size_t size;
+};
+
+static LIST_HEAD(io_range_list);
+static DEFINE_SPINLOCK(io_range_lock);
+#endif
+
+/*
+ * Record the PCI IO range (expressed as CPU physical address + size).
+ * Return a negative value if an error has occured, zero otherwise
+ */
+int __weak pci_register_io_range(phys_addr_t addr, resource_size_t size)
+{
+ int err = 0;
+
+#ifdef PCI_IOBASE
+ struct io_range *range;
+ resource_size_t allocated_size = 0;
+
+ /* check if the range hasn't been previously recorded */
+ spin_lock(&io_range_lock);
+ list_for_each_entry(range, &io_range_list, list) {
+ if (addr >= range->start && addr + size <= range->start + size) {
+ /* range already registered, bail out */
+ goto end_register;
+ }
+ allocated_size += range->size;
+ }
+
+ /* range not registed yet, check for available space */
+ if (allocated_size + size - 1 > IO_SPACE_LIMIT) {
+ /* if it's too big check if 64K space can be reserved */
+ if (allocated_size + SZ_64K - 1 > IO_SPACE_LIMIT) {
+ err = -E2BIG;
+ goto end_register;
+ }
+
+ size = SZ_64K;
+ pr_warn("Requested IO range too big, new size set to 64K\n");
+ }
+
+ /* add the range to the list */
+ range = kzalloc(sizeof(*range), GFP_ATOMIC);
+ if (!range) {
+ err = -ENOMEM;
+ goto end_register;
+ }
+
+ range->start = addr;
+ range->size = size;
+
+ list_add_tail(&range->list, &io_range_list);
+
+end_register:
+ spin_unlock(&io_range_lock);
+#endif
+
+ return err;
+}
+
+phys_addr_t pci_pio_to_address(unsigned long pio)
+{
+ phys_addr_t address = (phys_addr_t)OF_BAD_ADDR;
+
+#ifdef PCI_IOBASE
+ struct io_range *range;
+ resource_size_t allocated_size = 0;
+
+ if (pio > IO_SPACE_LIMIT)
+ return address;
+
+ spin_lock(&io_range_lock);
+ list_for_each_entry(range, &io_range_list, list) {
+ if (pio >= allocated_size && pio < allocated_size + range->size) {
+ address = range->start + pio - allocated_size;
+ break;
+ }
+ allocated_size += range->size;
+ }
+ spin_unlock(&io_range_lock);
+#endif
+
+ return address;
+}
+
+unsigned long __weak pci_address_to_pio(phys_addr_t address)
+{
+#ifdef PCI_IOBASE
+ struct io_range *res;
+ resource_size_t offset = 0;
+ unsigned long addr = -1;
+
+ spin_lock(&io_range_lock);
+ list_for_each_entry(res, &io_range_list, list) {
+ if (address >= res->start && address < res->start + res->size) {
+ addr = address - res->start + offset;
+ break;
+ }
+ offset += res->size;
+ }
+ spin_unlock(&io_range_lock);
+
+ return addr;
+#else
+ if (address > IO_SPACE_LIMIT)
+ return (unsigned long)-1;
+
+ return (unsigned long) address;
+#endif
+}
+
/**
* pci_remap_iospace - Remap the memory mapped I/O space
* @res: Resource describing the I/O space
@@ -3052,6 +3169,29 @@ int __weak pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
#endif
}
+/**
+ * pci_unmap_iospace - Unmap the memory mapped I/O space
+ * @res: resource to be unmapped
+ *
+ * Unmap the CPU virtual address @res from virtual address space.
+ * Only architectures that have memory mapped IO functions defined
+ * (and the PCI_IOBASE value defined) should call this function.
+ */
+void pci_unmap_iospace(struct resource *res)
+{
+#if defined(PCI_IOBASE) && defined(CONFIG_MMU)
+ unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start;
+
+ unmap_kernel_range(vaddr, resource_size(res));
+#else
+ /*
+ * This architecture does not have memory mapped I/O space,
+ * so this function should never be called.
+ */
+ WARN_ONCE(1, "This architecture does not support memory mapped I/O\n");
+#endif
+}
+
static void __pci_set_master(struct pci_dev *dev, bool enable)
{
u16 old_cmd, cmd;
@@ -4779,7 +4919,7 @@ int pci_get_new_domain_nr(void)
}
#ifdef CONFIG_PCI_DOMAINS_GENERIC
-void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent)
+static int of_pci_bus_domain_nr(struct device *parent)
{
static int use_dt_domains = -1;
int domain = -1;
@@ -4823,7 +4963,13 @@ void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent)
domain = -1;
}
- bus->domain_nr = domain;
+ return domain;
+}
+
+void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent)
+{
+ bus->domain_nr = acpi_disabled ? of_pci_bus_domain_nr(parent) :
+ acpi_pci_bus_domain_nr(bus);
}
#endif
#endif
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 8004f67c57ec..fb0b75219e02 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -12,6 +12,7 @@
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/cpumask.h>
+#include <linux/pci-acpi.h>
#include <linux/pci-aspm.h>
#include <linux/aer.h>
#include <linux/acpi.h>
@@ -2141,6 +2142,7 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
bridge->dev.parent = parent;
bridge->dev.release = pci_release_host_bridge_dev;
dev_set_name(&bridge->dev, "pci%04x:%02x", pci_domain_nr(b), bus);
+ acpi_pci_set_companion(bridge);
error = pcibios_root_bridge_prepare(bridge);
if (error) {
kfree(bridge);
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 7c198e0a3178..4139b64c80e0 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2287,12 +2287,68 @@ static int __init pl011_console_setup(struct console *co, char *options)
return uart_set_options(&uap->port, co, baud, parity, bits, flow);
}
+/**
+ * pl011_console_match - non-standard console matching
+ * @co: registering console
+ * @name: name from console command line
+ * @idx: index from console command line
+ * @options: ptr to option string from console command line
+ *
+ * Only attempts to match console command lines of the form:
+ * console=pl011,mmio|mmio32,<addr>[,<options>]
+ * console=pl011,0x<addr>[,<options>]
+ * This form is used to register an initial earlycon boot console and
+ * replace it with the amba_console at pl011 driver init.
+ *
+ * Performs console setup for a match (as required by interface)
+ * If no <options> are specified, then assume the h/w is already setup.
+ *
+ * Returns 0 if console matches; otherwise non-zero to use default matching
+ */
+static int __init pl011_console_match(struct console *co, char *name, int idx,
+ char *options)
+{
+ char match[] = "pl011"; /* pl011-specific earlycon name */
+ unsigned char iotype;
+ unsigned long addr;
+ int i;
+
+ if (strncmp(name, match, 5) != 0)
+ return -ENODEV;
+
+ if (uart_parse_earlycon(options, &iotype, &addr, &options))
+ return -ENODEV;
+
+ /* try to match the port specified on the command line */
+ for (i = 0; i < ARRAY_SIZE(amba_ports); i++) {
+ struct uart_port *port;
+
+ if (!amba_ports[i])
+ continue;
+
+ port = &amba_ports[i]->port;
+
+ if (port->iotype != iotype)
+ continue;
+ if ((iotype == UPIO_MEM || iotype == UPIO_MEM32) &&
+ (port->mapbase != addr))
+ continue;
+
+ co->index = i;
+ port->cons = co;
+ return pl011_console_setup(co, options);
+ }
+
+ return -ENODEV;
+}
+
static struct uart_driver amba_reg;
static struct console amba_console = {
.name = "ttyAMA",
.write = pl011_console_write,
.device = uart_console_device,
.setup = pl011_console_setup,
+ .match = pl011_console_match,
.flags = CON_PRINTBUFFER,
.index = -1,
.data = &amba_reg,
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
index 067783f0523c..ea00b9fde04f 100644
--- a/drivers/tty/serial/earlycon.c
+++ b/drivers/tty/serial/earlycon.c
@@ -21,6 +21,7 @@
#include <linux/sizes.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
+#include <linux/acpi.h>
#ifdef CONFIG_FIX_EARLYCON_MEM
#include <asm/fixmap.h>
@@ -199,6 +200,14 @@ int __init setup_earlycon(char *buf)
return -ENOENT;
}
+/*
+ * When CONFIG_ACPI_SPCR_TABLE is defined, "earlycon" without parameters in
+ * command line does not start DT earlycon immediately, instead it defers
+ * starting it until DT/ACPI decision is made. At that time if ACPI is enabled
+ * call parse_spcr(), else call early_init_dt_scan_chosen_stdout()
+ */
+bool earlycon_init_is_deferred __initdata;
+
/* early_param wrapper for setup_earlycon() */
static int __init param_setup_earlycon(char *buf)
{
@@ -208,8 +217,14 @@ static int __init param_setup_earlycon(char *buf)
* Just 'earlycon' is a valid param for devicetree earlycons;
* don't generate a warning from parse_early_params() in that case
*/
- if (!buf || !buf[0])
- return 0;
+ if (!buf || !buf[0]) {
+ if (IS_ENABLED(CONFIG_ACPI_SPCR_TABLE)) {
+ earlycon_init_is_deferred = true;
+ return 0;
+ } else {
+ return early_init_dt_scan_chosen_stdout();
+ }
+ }
err = setup_earlycon(buf);
if (err == -ENOENT || err == -EALREADY)
diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index 94a37cd7fbda..d4b72944ccda 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -15,6 +15,10 @@ extern int pxm_to_node(int);
extern int node_to_pxm(int);
extern int acpi_map_pxm_to_node(int);
extern unsigned char acpi_srat_revision;
+extern int acpi_numa __initdata;
+
+extern void bad_srat(void);
+extern int srat_disabled(void);
#endif /* CONFIG_ACPI_NUMA */
#endif /* __ACP_NUMA_H */
diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index a4ef62537cac..7702b27a18ed 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -321,7 +321,7 @@ struct acpi_csrt_descriptor {
* DBG2 - Debug Port Table 2
* Version 0 (Both main table and subtables)
*
- * Conforms to "Microsoft Debug Port Table 2 (DBG2)", May 22 2012.
+ * Conforms to "Microsoft Debug Port Table 2 (DBG2)", December 10, 2015
*
******************************************************************************/
@@ -371,6 +371,11 @@ struct acpi_dbg2_device {
#define ACPI_DBG2_16550_COMPATIBLE 0x0000
#define ACPI_DBG2_16550_SUBSET 0x0001
+#define ACPI_DBG2_ARM_PL011 0x0003
+#define ACPI_DBG2_ARM_SBSA_32BIT 0x000D
+#define ACPI_DBG2_ARM_SBSA_GENERIC 0x000E
+#define ACPI_DBG2_ARM_DCC 0x000F
+#define ACPI_DBG2_BCM2835 0x0010
#define ACPI_DBG2_1394_STANDARD 0x0000
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index 25d0914481a2..233d4e459bb9 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -19,6 +19,10 @@
#include <linux/timecounter.h>
#include <linux/types.h>
+#define ARCH_CP15_TIMER BIT(0)
+#define ARCH_MEM_TIMER BIT(1)
+#define ARCH_WD_TIMER BIT(2)
+
#define ARCH_TIMER_CTRL_ENABLE (1 << 0)
#define ARCH_TIMER_CTRL_IT_MASK (1 << 1)
#define ARCH_TIMER_CTRL_IT_STAT (1 << 2)
@@ -39,6 +43,8 @@ enum arch_timer_reg {
#define ARCH_TIMER_MEM_PHYS_ACCESS 2
#define ARCH_TIMER_MEM_VIRT_ACCESS 3
+#define ARCH_TIMER_MEM_MAX_FRAME 8
+
#define ARCH_TIMER_USR_PCT_ACCESS_EN (1 << 0) /* physical counter */
#define ARCH_TIMER_USR_VCT_ACCESS_EN (1 << 1) /* virtual counter */
#define ARCH_TIMER_VIRT_EVT_EN (1 << 2)
@@ -49,11 +55,30 @@ enum arch_timer_reg {
#define ARCH_TIMER_EVT_STREAM_FREQ 10000 /* 100us */
+
+struct arch_timer_kvm_info {
+ struct timecounter timecounter;
+ int virtual_irq;
+};
+
+struct arch_timer_data {
+ int phys_secure_ppi;
+ int phys_nonsecure_ppi;
+ int virt_ppi;
+ int hyp_ppi;
+ bool c3stop;
+};
+
+struct arch_timer_mem_data {
+ phys_addr_t cntbase_phy;
+ int irq;
+};
+
#ifdef CONFIG_ARM_ARCH_TIMER
extern u32 arch_timer_get_rate(void);
extern u64 (*arch_timer_read_counter)(void);
-extern struct timecounter *arch_timer_get_timecounter(void);
+extern struct arch_timer_kvm_info *arch_timer_get_kvm_info(void);
#else
@@ -67,11 +92,6 @@ static inline u64 arch_timer_read_counter(void)
return 0;
}
-static inline struct timecounter *arch_timer_get_timecounter(void)
-{
- return NULL;
-}
-
#endif
#endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 281caf847fad..be6037aa703d 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -25,6 +25,7 @@
#include <linux/spinlock.h>
#include <linux/types.h>
#include <kvm/iodev.h>
+#include <linux/irqchip/arm-gic-common.h>
#define VGIC_NR_IRQS_LEGACY 256
#define VGIC_NR_SGIS 16
@@ -353,15 +354,15 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
#define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus))
#define vgic_ready(k) ((k)->arch.vgic.ready)
-int vgic_v2_probe(struct device_node *vgic_node,
+int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params);
#ifdef CONFIG_KVM_ARM_VGIC_V3
-int vgic_v3_probe(struct device_node *vgic_node,
+int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params);
#else
-static inline int vgic_v3_probe(struct device_node *vgic_node,
+static inline int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params)
{
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 06ed7e54033e..e7d04c241635 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -239,12 +239,26 @@ int acpi_table_parse_madt(enum acpi_madt_type id,
int acpi_parse_mcfg (struct acpi_table_header *header);
void acpi_table_print_madt_entry (struct acpi_subtable_header *madt);
-/* the following four functions are architecture-dependent */
+/* the following numa functions are architecture-dependent */
void acpi_numa_slit_init (struct acpi_table_slit *slit);
+
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa);
+#else
+static inline void
+acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { }
+#endif
+
void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa);
+
+#ifdef CONFIG_ARM64
+void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa);
+#else
+static inline void
+acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
+#endif
+
int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
-void acpi_numa_arch_fixup(void);
#ifndef PHYS_CPUID_INVALID
typedef u32 phys_cpuid_t;
@@ -540,6 +554,23 @@ void acpi_walk_dep_device_list(acpi_handle handle);
struct platform_device *acpi_create_platform_device(struct acpi_device *);
#define ACPI_PTR(_ptr) (_ptr)
+#ifdef CONFIG_ACPI_GTDT
+bool __init gtdt_timer_is_available(int type);
+
+struct arch_timer_data;
+int __init gtdt_arch_timer_data_init(struct acpi_table_header *table,
+ struct arch_timer_data *data);
+struct arch_timer_mem_data;
+void __init *gtdt_gt_block(struct acpi_table_header *table, int index);
+u32 __init gtdt_gt_timer_count(struct acpi_gtdt_timer_block *gt_block);
+void __init *gtdt_gt_cntctlbase(struct acpi_gtdt_timer_block *gt_block);
+u32 __init gtdt_gt_frame_number(struct acpi_gtdt_timer_block *gt_block,
+ int index);
+int __init gtdt_gt_timer_data(struct acpi_gtdt_timer_block *gt_block,
+ int index, bool virt,
+ struct arch_timer_mem_data *data);
+#endif
+
#else /* !CONFIG_ACPI */
#define acpi_disabled 1
@@ -1004,4 +1035,10 @@ static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
#define acpi_probe_device_table(t) ({ int __r = 0; __r;})
#endif
+#ifdef CONFIG_ACPI_SPCR_TABLE
+int parse_spcr(bool earlycon);
+#else
+static inline int parse_spcr(bool earlycon) { return 0; }
+#endif
+
#endif /*_LINUX_ACPI_H*/
diff --git a/include/linux/iort.h b/include/linux/iort.h
new file mode 100644
index 000000000000..490ff4de2eec
--- /dev/null
+++ b/include/linux/iort.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2016, Semihalf
+ * Author: Tomasz Nowicki <tn@semihalf.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#ifndef __IORT_H__
+#define __IORT_H__
+
+#include <linux/acpi.h>
+
+struct fwnode_handle;
+int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node);
+void iort_deregister_domain_token(int trans_id);
+struct fwnode_handle *iort_its_find_domain_token(int trans_id);
+#ifdef CONFIG_IORT_TABLE
+u32 iort_pci_get_msi_rid(struct pci_dev *pdev, u32 req_id);
+struct irq_domain *iort_pci_get_domain(struct pci_dev *pdev, u32 req_id);
+#else
+static inline u32 iort_pci_get_msi_rid(struct pci_dev *pdev, u32 req_id)
+{ return req_id; }
+static inline struct irq_domain *
+iort_pci_get_domain(struct pci_dev *pdev, u32 req_id) { return NULL; }
+#endif
+
+#endif /* __IORT_H__ */
diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h
new file mode 100644
index 000000000000..c647b0547bcd
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-common.h
@@ -0,0 +1,34 @@
+/*
+ * include/linux/irqchip/arm-gic-common.h
+ *
+ * Copyright (C) 2016 ARM Limited, All Rights Reserved.
+ *
+ * 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.
+ */
+#ifndef __LINUX_IRQCHIP_ARM_GIC_COMMON_H
+#define __LINUX_IRQCHIP_ARM_GIC_COMMON_H
+
+#include <linux/types.h>
+#include <linux/ioport.h>
+
+enum gic_type {
+ GIC_V2,
+ GIC_V3,
+};
+
+struct gic_kvm_info {
+ /* GIC type */
+ enum gic_type type;
+ /* Virtual CPU interface */
+ struct resource vcpu;
+ /* Interrupt number */
+ unsigned int maint_irq;
+ /* Virtual control interface */
+ struct resource vctrl;
+};
+
+const struct gic_kvm_info *gic_get_kvm_info(void);
+
+#endif /* __LINUX_IRQCHIP_ARM_GIC_COMMON_H */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index d5d798b35c1f..589ddcd1ef43 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -330,9 +330,9 @@ struct rdists {
};
struct irq_domain;
-struct device_node;
+struct fwnode_handle;
int its_cpu_init(void);
-int its_init(struct device_node *node, struct rdists *rdists,
+int its_init(struct fwnode_handle *handle, struct rdists *rdists,
struct irq_domain *domain);
static inline bool gic_enable_sre(void)
diff --git a/include/linux/of.h b/include/linux/of.h
index 31758036787c..77ddace575e8 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -685,6 +685,15 @@ static inline int of_node_to_nid(struct device_node *device)
}
#endif
+#ifdef CONFIG_OF_NUMA
+extern int of_numa_init(void);
+#else
+static inline int of_numa_init(void)
+{
+ return -ENOSYS;
+}
+#endif
+
static inline struct device_node *of_find_matching_node(
struct device_node *from,
const struct of_device_id *matches)
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index 01c0a556448b..37864734ca50 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -47,10 +47,6 @@ void __iomem *of_io_request_and_map(struct device_node *device,
extern const __be32 *of_get_address(struct device_node *dev, int index,
u64 *size, unsigned int *flags);
-extern int pci_register_io_range(phys_addr_t addr, resource_size_t size);
-extern unsigned long pci_address_to_pio(phys_addr_t addr);
-extern phys_addr_t pci_pio_to_address(unsigned long pio);
-
extern int of_pci_range_parser_init(struct of_pci_range_parser *parser,
struct device_node *node);
extern struct of_pci_range *of_pci_range_parser_one(
@@ -86,11 +82,6 @@ static inline const __be32 *of_get_address(struct device_node *dev, int index,
return NULL;
}
-static inline phys_addr_t pci_pio_to_address(unsigned long pio)
-{
- return 0;
-}
-
static inline int of_pci_range_parser_init(struct of_pci_range_parser *parser,
struct device_node *node)
{
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 2fbe8682a66f..5cfe3221b0cb 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -63,6 +63,7 @@ extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
int depth, void *data);
extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
int depth, void *data);
+extern int early_init_dt_scan_chosen_stdout(void);
extern void early_init_fdt_scan_reserved_mem(void);
extern void early_init_fdt_reserve_self(void);
extern void early_init_dt_add_memory_arch(u64 base, u64 size);
@@ -91,6 +92,7 @@ extern void early_get_first_memblock_info(void *, phys_addr_t *);
extern u64 of_flat_dt_translate_address(unsigned long node);
extern void of_fdt_limit_memory(int limit);
#else /* CONFIG_OF_FLATTREE */
+static inline int early_init_dt_scan_chosen_stdout(void) { return -ENODEV; }
static inline void early_init_fdt_scan_reserved_mem(void) {}
static inline void early_init_fdt_reserve_self(void) {}
static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h
index 89ab0572dbc6..42ff844bfff2 100644
--- a/include/linux/pci-acpi.h
+++ b/include/linux/pci-acpi.h
@@ -111,6 +111,20 @@ static inline void acpi_pci_add_bus(struct pci_bus *bus) { }
static inline void acpi_pci_remove_bus(struct pci_bus *bus) { }
#endif /* CONFIG_ACPI */
+#ifdef CONFIG_ACPI_PCI_HOST_GENERIC
+void acpi_pci_set_companion(struct pci_host_bridge *bridge);
+int acpi_pci_bus_domain_nr(struct pci_bus *bus);
+#else
+static inline void acpi_pci_set_companion(struct pci_host_bridge *bridge)
+{
+}
+
+static inline int acpi_pci_bus_domain_nr(struct pci_bus *bus)
+{
+ return 0;
+}
+#endif
+
#ifdef CONFIG_ACPI_APEI
extern bool aer_acpi_firmware_first(void);
#else
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 932ec74909c6..b2e88860c083 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1165,7 +1165,11 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus,
void *alignf_data);
+int pci_register_io_range(phys_addr_t addr, resource_size_t size);
+unsigned long pci_address_to_pio(phys_addr_t addr);
+phys_addr_t pci_pio_to_address(unsigned long pio);
int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+void pci_unmap_iospace(struct resource *res);
static inline pci_bus_addr_t pci_bus_address(struct pci_dev *pdev, int bar)
{
@@ -1481,6 +1485,8 @@ static inline int pci_request_regions(struct pci_dev *dev, const char *res_name)
{ return -EIO; }
static inline void pci_release_regions(struct pci_dev *dev) { }
+static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; }
+
static inline void pci_block_cfg_access(struct pci_dev *dev) { }
static inline int pci_block_cfg_access_in_atomic(struct pci_dev *dev)
{ return 0; }
@@ -1716,7 +1722,10 @@ void pcibios_free_irq(struct pci_dev *dev);
extern struct dev_pm_ops pcibios_pm_ops;
#endif
-#ifdef CONFIG_PCI_MMCONFIG
+#if defined(CONFIG_PCI_MMCONFIG) || defined(CONFIG_ACPI_PCI_HOST_GENERIC)
+struct acpi_device;
+phys_addr_t pci_mcfg_lookup(struct acpi_device *device, u16 seg,
+ struct resource *bus_res);
void __init pci_mmcfg_early_init(void);
void __init pci_mmcfg_late_init(void);
#else
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index cbfcf38e220d..de6750fe9f73 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -363,6 +363,12 @@ extern int of_setup_earlycon(const struct earlycon_id *match,
unsigned long node,
const char *options);
+#ifdef CONFIG_SERIAL_EARLYCON
+extern bool earlycon_init_is_deferred __initdata;
+#else
+static const bool earlycon_init_is_deferred;
+#endif
+
struct uart_port *uart_get_console(struct uart_port *ports, int nr,
struct console *c);
int uart_parse_earlycon(char *p, unsigned char *iotype, unsigned long *addr,
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 9aaa35dd9144..409db3304471 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -17,7 +17,6 @@
*/
#include <linux/cpu.h>
-#include <linux/of_irq.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
@@ -438,45 +437,29 @@ static struct notifier_block kvm_timer_cpu_nb = {
.notifier_call = kvm_timer_cpu_notify,
};
-static const struct of_device_id arch_timer_of_match[] = {
- { .compatible = "arm,armv7-timer", },
- { .compatible = "arm,armv8-timer", },
- {},
-};
-
int kvm_timer_hyp_init(void)
{
- struct device_node *np;
- unsigned int ppi;
+ struct arch_timer_kvm_info *info;
int err;
- timecounter = arch_timer_get_timecounter();
- if (!timecounter)
- return -ENODEV;
+ info = arch_timer_get_kvm_info();
+ timecounter = &info->timecounter;
- np = of_find_matching_node(NULL, arch_timer_of_match);
- if (!np) {
- kvm_err("kvm_arch_timer: can't find DT node\n");
+ if (info->virtual_irq <= 0) {
+ kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n",
+ info->virtual_irq);
return -ENODEV;
}
+ host_vtimer_irq = info->virtual_irq;
- ppi = irq_of_parse_and_map(np, 2);
- if (!ppi) {
- kvm_err("kvm_arch_timer: no virtual timer interrupt\n");
- err = -EINVAL;
- goto out;
- }
-
- err = request_percpu_irq(ppi, kvm_arch_timer_handler,
+ err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler,
"kvm guest timer", kvm_get_running_vcpus());
if (err) {
kvm_err("kvm_arch_timer: can't request interrupt %d (%d)\n",
- ppi, err);
+ host_vtimer_irq, err);
goto out;
}
- host_vtimer_irq = ppi;
-
err = __register_cpu_notifier(&kvm_timer_cpu_nb);
if (err) {
kvm_err("Cannot register timer CPU notifier\n");
@@ -489,14 +472,13 @@ int kvm_timer_hyp_init(void)
goto out_free;
}
- kvm_info("%s IRQ%d\n", np->name, ppi);
+ kvm_info("virtual timer IRQ%d\n", host_vtimer_irq);
on_each_cpu(kvm_timer_init_interrupt, NULL, 1);
goto out;
out_free:
- free_percpu_irq(ppi, kvm_get_running_vcpus());
+ free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus());
out:
- of_node_put(np);
return err;
}
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index 67ec334ce1d0..7e826c9b2b0a 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -20,9 +20,6 @@
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
#include <linux/irqchip/arm-gic.h>
@@ -186,38 +183,39 @@ static void vgic_cpu_init_lrs(void *params)
}
/**
- * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT
- * @node: pointer to the DT node
- * @ops: address of a pointer to the GICv2 operations
- * @params: address of a pointer to HW-specific parameters
+ * vgic_v2_probe - probe for a GICv2 compatible interrupt controller
+ * @gic_kvm_info: pointer to the GIC description
+ * @ops: address of a pointer to the GICv2 operations
+ * @params: address of a pointer to HW-specific parameters
*
* Returns 0 if a GICv2 has been found, with the low level operations
* in *ops and the HW parameters in *params. Returns an error code
* otherwise.
*/
-int vgic_v2_probe(struct device_node *vgic_node,
- const struct vgic_ops **ops,
- const struct vgic_params **params)
+int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
+ const struct vgic_ops **ops,
+ const struct vgic_params **params)
{
int ret;
- struct resource vctrl_res;
- struct resource vcpu_res;
struct vgic_params *vgic = &vgic_v2_params;
+ const struct resource *vctrl_res = &gic_kvm_info->vctrl;
+ const struct resource *vcpu_res = &gic_kvm_info->vcpu;
- vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0);
- if (!vgic->maint_irq) {
- kvm_err("error getting vgic maintenance irq from DT\n");
+ if (!gic_kvm_info->maint_irq) {
+ kvm_err("error getting vgic maintenance irq\n");
ret = -ENXIO;
goto out;
}
+ vgic->maint_irq = gic_kvm_info->maint_irq;
- ret = of_address_to_resource(vgic_node, 2, &vctrl_res);
- if (ret) {
- kvm_err("Cannot obtain GICH resource\n");
+ if (!gic_kvm_info->vctrl.start) {
+ kvm_err("GICH not present in the firmware table\n");
+ ret = -ENXIO;
goto out;
}
- vgic->vctrl_base = of_iomap(vgic_node, 2);
+ vgic->vctrl_base = ioremap(gic_kvm_info->vctrl.start,
+ resource_size(&gic_kvm_info->vctrl));
if (!vgic->vctrl_base) {
kvm_err("Cannot ioremap GICH\n");
ret = -ENOMEM;
@@ -228,29 +226,23 @@ int vgic_v2_probe(struct device_node *vgic_node,
vgic->nr_lr = (vgic->nr_lr & 0x3f) + 1;
ret = create_hyp_io_mappings(vgic->vctrl_base,
- vgic->vctrl_base + resource_size(&vctrl_res),
- vctrl_res.start);
+ vgic->vctrl_base + resource_size(vctrl_res),
+ vctrl_res->start);
if (ret) {
kvm_err("Cannot map VCTRL into hyp\n");
goto out_unmap;
}
- if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
- kvm_err("Cannot obtain GICV resource\n");
- ret = -ENXIO;
- goto out_unmap;
- }
-
- if (!PAGE_ALIGNED(vcpu_res.start)) {
+ if (!PAGE_ALIGNED(vcpu_res->start)) {
kvm_err("GICV physical address 0x%llx not page aligned\n",
- (unsigned long long)vcpu_res.start);
+ (unsigned long long)vcpu_res->start);
ret = -ENXIO;
goto out_unmap;
}
- if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+ if (!PAGE_ALIGNED(resource_size(vcpu_res))) {
kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
- (unsigned long long)resource_size(&vcpu_res),
+ (unsigned long long)resource_size(vcpu_res),
PAGE_SIZE);
ret = -ENXIO;
goto out_unmap;
@@ -259,10 +251,10 @@ int vgic_v2_probe(struct device_node *vgic_node,
vgic->can_emulate_gicv2 = true;
kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2);
- vgic->vcpu_base = vcpu_res.start;
+ vgic->vcpu_base = vcpu_res->start;
- kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
- vctrl_res.start, vgic->maint_irq);
+ kvm_info("GICH base=0x%llx, GICV base=0x%llx, IRQ=%d\n",
+ gic_kvm_info->vctrl.start, vgic->vcpu_base, vgic->maint_irq);
vgic->type = VGIC_V2;
vgic->max_gic_vcpus = VGIC_V2_MAX_CPUS;
@@ -276,6 +268,5 @@ int vgic_v2_probe(struct device_node *vgic_node,
out_unmap:
iounmap(vgic->vctrl_base);
out:
- of_node_put(vgic_node);
return ret;
}
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 999bdc6d9d9f..c02a1b1cf855 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -20,11 +20,9 @@
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
#include <linux/irqchip/arm-gic-v3.h>
+#include <linux/irqchip/arm-gic-common.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_arm.h>
@@ -222,30 +220,24 @@ static void vgic_cpu_init_lrs(void *params)
}
/**
- * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
- * @node: pointer to the DT node
- * @ops: address of a pointer to the GICv3 operations
- * @params: address of a pointer to HW-specific parameters
+ * vgic_v3_probe - probe for a GICv3 compatible interrupt controller
+ * @gic_kvm_info: pointer to the GIC description
+ * @ops: address of a pointer to the GICv3 operations
+ * @params: address of a pointer to HW-specific parameters
*
* Returns 0 if a GICv3 has been found, with the low level operations
* in *ops and the HW parameters in *params. Returns an error code
* otherwise.
*/
-int vgic_v3_probe(struct device_node *vgic_node,
+int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params)
{
int ret = 0;
- u32 gicv_idx;
- struct resource vcpu_res;
struct vgic_params *vgic = &vgic_v3_params;
+ const struct resource *vcpu_res = &gic_kvm_info->vcpu;
- vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0);
- if (!vgic->maint_irq) {
- kvm_err("error getting vgic maintenance irq from DT\n");
- ret = -ENXIO;
- goto out;
- }
+ vgic->maint_irq = gic_kvm_info->maint_irq;
ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2);
@@ -256,24 +248,19 @@ int vgic_v3_probe(struct device_node *vgic_node,
vgic->nr_lr = (ich_vtr_el2 & 0xf) + 1;
vgic->can_emulate_gicv2 = false;
- if (of_property_read_u32(vgic_node, "#redistributor-regions", &gicv_idx))
- gicv_idx = 1;
-
- gicv_idx += 3; /* Also skip GICD, GICC, GICH */
- if (of_address_to_resource(vgic_node, gicv_idx, &vcpu_res)) {
+ if (!vcpu_res->start) {
kvm_info("GICv3: no GICV resource entry\n");
vgic->vcpu_base = 0;
- } else if (!PAGE_ALIGNED(vcpu_res.start)) {
+ } else if (!PAGE_ALIGNED(vcpu_res->start)) {
pr_warn("GICV physical address 0x%llx not page aligned\n",
- (unsigned long long)vcpu_res.start);
+ (unsigned long long)vcpu_res->start);
vgic->vcpu_base = 0;
- } else if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+ } else if (!PAGE_ALIGNED(resource_size(vcpu_res))) {
pr_warn("GICV size 0x%llx not a multiple of page size 0x%lx\n",
- (unsigned long long)resource_size(&vcpu_res),
+ (unsigned long long)resource_size(vcpu_res),
PAGE_SIZE);
- vgic->vcpu_base = 0;
} else {
- vgic->vcpu_base = vcpu_res.start;
+ vgic->vcpu_base = vcpu_res->start;
vgic->can_emulate_gicv2 = true;
kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
KVM_DEV_TYPE_ARM_VGIC_V2);
@@ -286,15 +273,13 @@ int vgic_v3_probe(struct device_node *vgic_node,
vgic->type = VGIC_V3;
vgic->max_gic_vcpus = VGIC_V3_MAX_CPUS;
- kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
- vcpu_res.start, vgic->maint_irq);
+ kvm_info("GICV base=0x%llx, IRQ=%d\n",
+ vgic->vcpu_base, vgic->maint_irq);
on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
*ops = &vgic_v3_ops;
*params = vgic;
-out:
- of_node_put(vgic_node);
return ret;
}
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 00429b392c61..60668a7f319a 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -21,9 +21,7 @@
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
+#include <linux/irq.h>
#include <linux/rculist.h>
#include <linux/uaccess.h>
@@ -33,6 +31,7 @@
#include <trace/events/kvm.h>
#include <asm/kvm.h>
#include <kvm/iodev.h>
+#include <linux/irqchip/arm-gic-common.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -2389,33 +2388,38 @@ static struct notifier_block vgic_cpu_nb = {
.notifier_call = vgic_cpu_notify,
};
-static const struct of_device_id vgic_ids[] = {
- { .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
- { .compatible = "arm,cortex-a7-gic", .data = vgic_v2_probe, },
- { .compatible = "arm,gic-400", .data = vgic_v2_probe, },
- { .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
- {},
-};
-
-int kvm_vgic_hyp_init(void)
+static int kvm_vgic_probe(void)
{
- const struct of_device_id *matched_id;
- const int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
- const struct vgic_params **);
- struct device_node *vgic_node;
+ const struct gic_kvm_info *gic_kvm_info;
int ret;
- vgic_node = of_find_matching_node_and_match(NULL,
- vgic_ids, &matched_id);
- if (!vgic_node) {
- kvm_err("error: no compatible GIC node found\n");
+ gic_kvm_info = gic_get_kvm_info();
+ if (!gic_kvm_info)
return -ENODEV;
+
+ switch (gic_kvm_info->type) {
+ case GIC_V2:
+ ret = vgic_v2_probe(gic_kvm_info, &vgic_ops, &vgic);
+ break;
+ case GIC_V3:
+ ret = vgic_v3_probe(gic_kvm_info, &vgic_ops, &vgic);
+ break;
+ default:
+ ret = -ENODEV;
}
- vgic_probe = matched_id->data;
- ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
- if (ret)
+ return ret;
+}
+
+int kvm_vgic_hyp_init(void)
+{
+ int ret;
+
+ ret = kvm_vgic_probe();
+ if (ret) {
+ kvm_err("error: KVM vGIC probing failed\n");
return ret;
+ }
ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
"vgic", kvm_get_running_vcpus());