Merge tag 'arm-apple-m1-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc

Pull ARM Apple M1 platform support from Arnd Bergmann:
"The Apple M1 is the processor used it all current generation Apple
Macintosh computers. Support for this platform so far is rudimentary,
but it boots and can use framebuffer and serial console over a special
USB cable.

Support for several essential on-chip devices (USB, PCIe, IOMMU, NVMe)
is work in progress but was not ready in time.

A very detailed description of what works is in the commit message of
commit 1bb2fd3880d4 ("Merge tag 'm1-soc-bringup-v5' [..]") and on the
AsahiLinux wiki"

Link: https://lore.kernel.org/linux-arm-kernel/[e-mail]/

* tag 'arm-apple-m1-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc:
asm-generic/io.h: Unbork ioremap_np() declaration
arm64: apple: Add initial Apple Mac mini (M1, 2020) devicetree
dt-bindings: display: Add apple,simple-framebuffer
arm64: Kconfig: Introduce CONFIG_ARCH_APPLE
irqchip/apple-aic: Add support for the Apple Interrupt Controller
dt-bindings: interrupt-controller: Add DT bindings for apple-aic
arm64: Move ICH_ sysreg bits from arm-gic-v3.h to sysreg.h
of/address: Add infrastructure to declare MMIO as non-posted
asm-generic/io.h: implement pci_remap_cfgspace using ioremap_np
arm64: Implement ioremap_np() to map MMIO as nGnRnE
docs: driver-api: device-io: Document ioremap() variants & access funcs
docs: driver-api: device-io: Document I/O access functions
asm-generic/io.h: Add a non-posted variant of ioremap()
arm64: arch_timer: Implement support for interrupt-names
dt-bindings: timer: arm,arch_timer: Add interrupt-names support
arm64: cputype: Add CPU implementor & types for the Apple M1 cores
dt-bindings: arm: cpus: Add apple,firestorm & icestorm compatibles
dt-bindings: arm: apple: Add bindings for Apple ARM platforms
dt-bindings: vendor-prefixes: Add apple prefix

Documentation/devicetree/bindings/arm/apple.yaml

···
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/apple.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Apple ARM Machine Device Tree Bindings
+
+maintainers:
+  - Hector Martin <[e-mail]>
+
+description: |
+  ARM platforms using SoCs designed by Apple Inc., branded "Apple Silicon".
+
+  This currently includes devices based on the "M1" SoC, starting with the
+  three Mac models released in late 2020:
+
+  - Mac mini (M1, 2020)
+  - MacBook Pro (13-inch, M1, 2020)
+  - MacBook Air (M1, 2020)
+
+  The compatible property should follow this format:
+
+  compatible = "apple,<targettype>", "apple,<socid>", "apple,arm-platform";
+
+  <targettype> represents the board/device and comes from the `target-type`
+  property of the root node of the Apple Device Tree, lowercased. It can be
+  queried on macOS using the following command:
+
+  $ ioreg -d2 -l | grep target-type
+
+  <socid> is the lowercased SoC ID. Apple uses at least *five* different
+  names for their SoCs:
+
+  - Marketing name ("M1")
+  - Internal name ("H13G")
+  - Codename ("Tonga")
+  - SoC ID ("T8103")
+  - Package/IC part number ("APL1102")
+
+  Devicetrees should use the lowercased SoC ID, to avoid confusion if
+  multiple SoCs share the same marketing name. This can be obtained from
+  the `compatible` property of the arm-io node of the Apple Device Tree,
+  which can be queried as follows on macOS:
+
+  $ ioreg -n arm-io | grep compatible
+
+properties:
+  $nodename:
+    const: "/"
+  compatible:
+    oneOf:
+      - description: Apple M1 SoC based platforms
+        items:
+          - enum:
+              - apple,j274 # Mac mini (M1, 2020)
+              - apple,j293 # MacBook Pro (13-inch, M1, 2020)
+              - apple,j313 # MacBook Air (M1, 2020)
+          - const: apple,t8103
+          - const: apple,arm-platform
+
+additionalProperties: true
+
+...

Documentation/devicetree/bindings/arm/cpus.yaml

···
 
   compatible:
     enum:
+      - apple,icestorm
+      - apple,firestorm
       - arm,arm710t
       - arm,arm720t
       - arm,arm740t

Documentation/devicetree/bindings/display/simple-framebuffer.yaml

···
   compatible:
     items:
       - enum:
+          - apple,simple-framebuffer
           - allwinner,simple-framebuffer
           - amlogic,simple-framebuffer
       - const: simple-framebuffer
···
       Format of the framebuffer:
         * `a8b8g8r8` - 32-bit pixels, d[31:24]=a, d[23:16]=b, d[15:8]=g, d[7:0]=r
         * `r5g6b5` - 16-bit pixels, d[15:11]=r, d[10:5]=g, d[4:0]=b
+        * `x2r10g10b10` - 32-bit pixels, d[29:20]=r, d[19:10]=g, d[9:0]=b
+        * `x8r8g8b8` - 32-bit pixels, d[23:16]=r, d[15:8]=g, d[7:0]=b
     enum:
       - a8b8g8r8
       - r5g6b5
+      - x2r10g10b10
+      - x8r8g8b8
 
   display:
     $ref: /schemas/types.yaml#/definitions/phandle

Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml

···
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/apple,aic.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Apple Interrupt Controller
+
+maintainers:
+  - Hector Martin <[e-mail]>
+
+description: |
+  The Apple Interrupt Controller is a simple interrupt controller present on
+  Apple ARM SoC platforms, including various iPhone and iPad devices and the
+  "Apple Silicon" Macs.
+
+  It provides the following features:
+
+  - Level-triggered hardware IRQs wired to SoC blocks
+    - Single mask bit per IRQ
+    - Per-IRQ affinity setting
+    - Automatic masking on event delivery (auto-ack)
+    - Software triggering (ORed with hw line)
+  - 2 per-CPU IPIs (meant as "self" and "other", but they are interchangeable
+    if not symmetric)
+  - Automatic prioritization (single event/ack register per CPU, lower IRQs =
+    higher priority)
+  - Automatic masking on ack
+  - Default "this CPU" register view and explicit per-CPU views
+
+  This device also represents the FIQ interrupt sources on platforms using AIC,
+  which do not go through a discrete interrupt controller.
+
+allOf:
+  - $ref: /schemas/interrupt-controller.yaml#
+
+properties:
+  compatible:
+    items:
+      - const: apple,t8103-aic
+      - const: apple,aic
+
+  interrupt-controller: true
+
+  '#interrupt-cells':
+    const: 3
+    description: |
+      The 1st cell contains the interrupt type:
+        - 0: Hardware IRQ
+        - 1: FIQ
+
+      The 2nd cell contains the interrupt number.
+        - HW IRQs: interrupt number
+        - FIQs:
+          - 0: physical HV timer
+          - 1: virtual HV timer
+          - 2: physical guest timer
+          - 3: virtual guest timer
+
+      The 3rd cell contains the interrupt flags. This is normally
+      IRQ_TYPE_LEVEL_HIGH (4).
+
+  reg:
+    description: |
+      Specifies base physical address and size of the AIC registers.
+    maxItems: 1
+
+required:
+  - compatible
+  - '#interrupt-cells'
+  - interrupt-controller
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        aic: interrupt-controller@23b100000 {
+            compatible = "apple,t8103-aic", "apple,aic";
+            #interrupt-cells = <3>;
+            interrupt-controller;
+            reg = <0x2 0x3b100000 0x0 0x8000>;
+        };
+    };

Documentation/devicetree/bindings/timer/arm,arch_timer.yaml

···
               - arm,armv8-timer
 
   interrupts:
+    minItems: 1
+    maxItems: 5
     items:
       - description: secure timer irq
       - description: non-secure timer irq
       - description: virtual timer irq
       - description: hypervisor timer irq
+      - description: hypervisor virtual timer irq
+
+  interrupt-names:
+    oneOf:
+      - minItems: 2
+        items:
+          - const: phys
+          - const: virt
+          - const: hyp-phys
+          - const: hyp-virt
+      - minItems: 3
+        items:
+          - const: sec-phys
+          - const: phys
+          - const: virt
+          - const: hyp-phys
+          - const: hyp-virt
 
   clock-frequency:
     description: The frequency of the main counter, in Hz. Should be present

Documentation/devicetree/bindings/vendor-prefixes.yaml

···
     description: Anvo-Systems Dresden GmbH
   "^apm,.*":
     description: Applied Micro Circuits Corporation (APM)
+  "^apple,.*":
+    description: Apple Inc.
   "^aptina,.*":
     description: Aptina Imaging
   "^arasan,.*":

Documentation/driver-api/device-io.rst

···
 outs() functions copy bytes, words or longs to the given
 port.
 
+__iomem pointer tokens
+======================
+
+The data type for an MMIO address is an ``__iomem`` qualified pointer, such as
+``void __iomem *reg``. On most architectures it is a regular pointer that
+points to a virtual memory address and can be offset or dereferenced, but in
+portable code, it must only be passed from and to functions that explicitly
+operated on an ``__iomem`` token, in particular the ioremap() and
+readl()/writel() functions. The 'sparse' semantic code checker can be used to
+verify that this is done correctly.
+
+While on most architectures, ioremap() creates a page table entry for an
+uncached virtual address pointing to the physical MMIO address, some
+architectures require special instructions for MMIO, and the ``__iomem`` pointer
+just encodes the physical address or an offsettable cookie that is interpreted
+by readl()/writel().
+
+Differences between I/O access functions
+========================================
+
+readq(), readl(), readw(), readb(), writeq(), writel(), writew(), writeb()
+
+  These are the most generic accessors, providing serialization against other
+  MMIO accesses and DMA accesses as well as fixed endianness for accessing
+  little-endian PCI devices and on-chip peripherals. Portable device drivers
+  should generally use these for any access to ``__iomem`` pointers.
+
+  Note that posted writes are not strictly ordered against a spinlock, see
+  Documentation/driver-api/io_ordering.rst.
+
+readq_relaxed(), readl_relaxed(), readw_relaxed(), readb_relaxed(),
+writeq_relaxed(), writel_relaxed(), writew_relaxed(), writeb_relaxed()
+
+  On architectures that require an expensive barrier for serializing against
+  DMA, these "relaxed" versions of the MMIO accessors only serialize against
+  each other, but contain a less expensive barrier operation. A device driver
+  might use these in a particularly performance sensitive fast path, with a
+  comment that explains why the usage in a specific location is safe without
+  the extra barriers.
+
+  See memory-barriers.txt for a more detailed discussion on the precise ordering
+  guarantees of the non-relaxed and relaxed versions.
+
+ioread64(), ioread32(), ioread16(), ioread8(),
+iowrite64(), iowrite32(), iowrite16(), iowrite8()
+
+  These are an alternative to the normal readl()/writel() functions, with almost
+  identical behavior, but they can also operate on ``__iomem`` tokens returned
+  for mapping PCI I/O space with pci_iomap() or ioport_map(). On architectures
+  that require special instructions for I/O port access, this adds a small
+  overhead for an indirect function call implemented in lib/iomap.c, while on
+  other architectures, these are simply aliases.
+
+ioread64be(), ioread32be(), ioread16be()
+iowrite64be(), iowrite32be(), iowrite16be()
+
+  These behave in the same way as the ioread32()/iowrite32() family, but with
+  reversed byte order, for accessing devices with big-endian MMIO registers.
+  Device drivers that can operate on either big-endian or little-endian
+  registers may have to implement a custom wrapper function that picks one or
+  the other depending on which device was found.
+
+  Note: On some architectures, the normal readl()/writel() functions
+  traditionally assume that devices are the same endianness as the CPU, while
+  using a hardware byte-reverse on the PCI bus when running a big-endian kernel.
+  Drivers that use readl()/writel() this way are generally not portable, but
+  tend to be limited to a particular SoC.
+
+hi_lo_readq(), lo_hi_readq(), hi_lo_readq_relaxed(), lo_hi_readq_relaxed(),
+ioread64_lo_hi(), ioread64_hi_lo(), ioread64be_lo_hi(), ioread64be_hi_lo(),
+hi_lo_writeq(), lo_hi_writeq(), hi_lo_writeq_relaxed(), lo_hi_writeq_relaxed(),
+iowrite64_lo_hi(), iowrite64_hi_lo(), iowrite64be_lo_hi(), iowrite64be_hi_lo()
+
+  Some device drivers have 64-bit registers that cannot be accessed atomically
+  on 32-bit architectures but allow two consecutive 32-bit accesses instead.
+  Since it depends on the particular device which of the two halves has to be
+  accessed first, a helper is provided for each combination of 64-bit accessors
+  with either low/high or high/low word ordering. A device driver must include
+  either <linux/io-64-nonatomic-lo-hi.h> or <linux/io-64-nonatomic-hi-lo.h> to
+  get the function definitions along with helpers that redirect the normal
+  readq()/writeq() to them on architectures that do not provide 64-bit access
+  natively.
+
+__raw_readq(), __raw_readl(), __raw_readw(), __raw_readb(),
+__raw_writeq(), __raw_writel(), __raw_writew(), __raw_writeb()
+
+  These are low-level MMIO accessors without barriers or byteorder changes and
+  architecture specific behavior. Accesses are usually atomic in the sense that
+  a four-byte __raw_readl() does not get split into individual byte loads, but
+  multiple consecutive accesses can be combined on the bus. In portable code, it
+  is only safe to use these to access memory behind a device bus but not MMIO
+  registers, as there are no ordering guarantees with regard to other MMIO
+  accesses or even spinlocks. The byte order is generally the same as for normal
+  memory, so unlike the other functions, these can be used to copy data between
+  kernel memory and device memory.
+
+inl(), inw(), inb(), outl(), outw(), outb()
+
+  PCI I/O port resources traditionally require separate helpers as they are
+  implemented using special instructions on the x86 architecture. On most other
+  architectures, these are mapped to readl()/writel() style accessors
+  internally, usually pointing to a fixed area in virtual memory. Instead of an
+  ``__iomem`` pointer, the address is a 32-bit integer token to identify a port
+  number. PCI requires I/O port access to be non-posted, meaning that an outb()
+  must complete before the following code executes, while a normal writeb() may
+  still be in progress. On architectures that correctly implement this, I/O port
+  access is therefore ordered against spinlocks. Many non-x86 PCI host bridge
+  implementations and CPU architectures however fail to implement non-posted I/O
+  space on PCI, so they can end up being posted on such hardware.
+
+  In some architectures, the I/O port number space has a 1:1 mapping to
+  ``__iomem`` pointers, but this is not recommended and device drivers should
+  not rely on that for portability. Similarly, an I/O port number as described
+  in a PCI base address register may not correspond to the port number as seen
+  by a device driver. Portable drivers need to read the port number for the
+  resource provided by the kernel.
+
+  There are no direct 64-bit I/O port accessors, but pci_iomap() in combination
+  with ioread64/iowrite64 can be used instead.
+
+inl_p(), inw_p(), inb_p(), outl_p(), outw_p(), outb_p()
+
+  On ISA devices that require specific timing, the _p versions of the I/O
+  accessors add a small delay. On architectures that do not have ISA buses,
+  these are aliases to the normal inb/outb helpers.
+
+readsq, readsl, readsw, readsb
+writesq, writesl, writesw, writesb
+ioread64_rep, ioread32_rep, ioread16_rep, ioread8_rep
+iowrite64_rep, iowrite32_rep, iowrite16_rep, iowrite8_rep
+insl, insw, insb, outsl, outsw, outsb
+
+  These are helpers that access the same address multiple times, usually to copy
+  data between kernel memory byte stream and a FIFO buffer. Unlike the normal
+  MMIO accessors, these do not perform a byteswap on big-endian kernels, so the
+  first byte in the FIFO register corresponds to the first byte in the memory
+  buffer regardless of the architecture.
+
+Device memory mapping modes
+===========================
+
+Some architectures support multiple modes for mapping device memory.
+ioremap_*() variants provide a common abstraction around these
+architecture-specific modes, with a shared set of semantics.
+
+ioremap() is the most common mapping type, and is applicable to typical device
+memory (e.g. I/O registers). Other modes can offer weaker or stronger
+guarantees, if supported by the architecture. From most to least common, they
+are as follows:
+
+ioremap()
+---------
+
+The default mode, suitable for most memory-mapped devices, e.g. control
+registers. Memory mapped using ioremap() has the following characteristics:
+
+* Uncached - CPU-side caches are bypassed, and all reads and writes are handled
+  directly by the device
+* No speculative operations - the CPU may not issue a read or write to this
+  memory, unless the instruction that does so has been reached in committed
+  program flow.
+* No reordering - The CPU may not reorder accesses to this memory mapping with
+  respect to each other. On some architectures, this relies on barriers in
+  readl_relaxed()/writel_relaxed().
+* No repetition - The CPU may not issue multiple reads or writes for a single
+  program instruction.
+* No write-combining - Each I/O operation results in one discrete read or write
+  being issued to the device, and multiple writes are not combined into larger
+  writes. This may or may not be enforced when using __raw I/O accessors or
+  pointer dereferences.
+* Non-executable - The CPU is not allowed to speculate instruction execution
+  from this memory (it probably goes without saying, but you're also not
+  allowed to jump into device memory).
+
+On many platforms and buses (e.g. PCI), writes issued through ioremap()
+mappings are posted, which means that the CPU does not wait for the write to
+actually reach the target device before retiring the write instruction.
+
+On many platforms, I/O accesses must be aligned with respect to the access
+size; failure to do so will result in an exception or unpredictable results.
+
+ioremap_wc()
+------------
+
+Maps I/O memory as normal memory with write combining. Unlike ioremap(),
+
+* The CPU may speculatively issue reads from the device that the program
+  didn't actually execute, and may choose to basically read whatever it wants.
+* The CPU may reorder operations as long as the result is consistent from the
+  program's point of view.
+* The CPU may write to the same location multiple times, even when the program
+  issued a single write.
+* The CPU may combine several writes into a single larger write.
+
+This mode is typically used for video framebuffers, where it can increase
+performance of writes. It can also be used for other blocks of memory in
+devices (e.g. buffers or shared memory), but care must be taken as accesses are
+not guaranteed to be ordered with respect to normal ioremap() MMIO register
+accesses without explicit barriers.
+
+On a PCI bus, it is usually safe to use ioremap_wc() on MMIO areas marked as
+``IORESOURCE_PREFETCH``, but it may not be used on those without the flag.
+For on-chip devices, there is no corresponding flag, but a driver can use
+ioremap_wc() on a device that is known to be safe.
+
+ioremap_wt()
+------------
+
+Maps I/O memory as normal memory with write-through caching. Like ioremap_wc(),
+but also,
+
+* The CPU may cache writes issued to and reads from the device, and serve reads
+  from that cache.
+
+This mode is sometimes used for video framebuffers, where drivers still expect
+writes to reach the device in a timely manner (and not be stuck in the CPU
+cache), but reads may be served from the cache for efficiency. However, it is
+rarely useful these days, as framebuffer drivers usually perform writes only,
+for which ioremap_wc() is more efficient (as it doesn't needlessly trash the
+cache). Most drivers should not use this.
+
+ioremap_np()
+------------
+
+Like ioremap(), but explicitly requests non-posted write semantics. On some
+architectures and buses, ioremap() mappings have posted write semantics, which
+means that writes can appear to "complete" from the point of view of the
+CPU before the written data actually arrives at the target device. Writes are
+still ordered with respect to other writes and reads from the same device, but
+due to the posted write semantics, this is not the case with respect to other
+devices. ioremap_np() explicitly requests non-posted semantics, which means
+that the write instruction will not appear to complete until the device has
+received (and to some platform-specific extent acknowledged) the written data.
+
+This mapping mode primarily exists to cater for platforms with bus fabrics that
+require this particular mapping mode to work correctly. These platforms set the
+``IORESOURCE_MEM_NONPOSTED`` flag for a resource that requires ioremap_np()
+semantics and portable drivers should use an abstraction that automatically
+selects it where appropriate (see the `Higher-level ioremap abstractions`_
+section below).
+
+The bare ioremap_np() is only available on some architectures; on others, it
+always returns NULL. Drivers should not normally use it, unless they are
+platform-specific or they derive benefit from non-posted writes where
+supported, and can fall back to ioremap() otherwise. The normal approach to
+ensure posted write completion is to do a dummy read after a write as
+explained in `Accessing the device`_, which works with ioremap() on all
+platforms.
+
+ioremap_np() should never be used for PCI drivers. PCI memory space writes are
+always posted, even on architectures that otherwise implement ioremap_np().
+Using ioremap_np() for PCI BARs will at best result in posted write semantics,
+and at worst result in complete breakage.
+
+Note that non-posted write semantics are orthogonal to CPU-side ordering
+guarantees. A CPU may still choose to issue other reads or writes before a
+non-posted write instruction retires. See the previous section on MMIO access
+functions for details on the CPU side of things.
+
+ioremap_uc()
+------------
+
+ioremap_uc() behaves like ioremap() except that on the x86 architecture without
+'PAT' mode, it marks memory as uncached even when the MTRR has designated
+it as cacheable, see Documentation/x86/pat.rst.
+
+Portable drivers should avoid the use of ioremap_uc().
+
+ioremap_cache()
+---------------
+
+ioremap_cache() effectively maps I/O memory as normal RAM. CPU write-back
+caches can be used, and the CPU is free to treat the device as if it were a
+block of RAM. This should never be used for device memory which has side
+effects of any kind, or which does not return the data previously written on
+read.
+
+It should also not be used for actual RAM, as the returned pointer is an
+``__iomem`` token. memremap() can be used for mapping normal RAM that is outside
+of the linear kernel memory area to a regular pointer.
+
+Portable drivers should avoid the use of ioremap_cache().
+
+Architecture example
+--------------------
+
+Here is how the above modes map to memory attribute settings on the ARM64
+architecture:
+
++------------------------+--------------------------------------------+
+| API                    | Memory region type and cacheability        |
++------------------------+--------------------------------------------+
+| ioremap_np()           | Device-nGnRnE                              |
++------------------------+--------------------------------------------+
+| ioremap()              | Device-nGnRE                               |
++------------------------+--------------------------------------------+
+| ioremap_uc()           | (not implemented)                          |
++------------------------+--------------------------------------------+
+| ioremap_wc()           | Normal-Non Cacheable                       |
++------------------------+--------------------------------------------+
+| ioremap_wt()           | (not implemented; fallback to ioremap)     |
++------------------------+--------------------------------------------+
+| ioremap_cache()        | Normal-Write-Back Cacheable                |
++------------------------+--------------------------------------------+
+
+Higher-level ioremap abstractions
+=================================
+
+Instead of using the above raw ioremap() modes, drivers are encouraged to use
+higher-level APIs. These APIs may implement platform-specific logic to
+automatically choose an appropriate ioremap mode on any given bus, allowing for
+a platform-agnostic driver to work on those platforms without any special
+cases. At the time of this writing, the following ioremap() wrappers have such
+logic:
+
+devm_ioremap_resource()
+
+  Can automatically select ioremap_np() over ioremap() according to platform
+  requirements, if the ``IORESOURCE_MEM_NONPOSTED`` flag is set on the struct
+  resource. Uses devres to automatically unmap the resource when the driver
+  probe() function fails or a device in unbound from its driver.
+
+  Documented in Documentation/driver-api/driver-model/devres.rst.
+
+of_address_to_resource()
+
+  Automatically sets the ``IORESOURCE_MEM_NONPOSTED`` flag for platforms that
+  require non-posted writes for certain buses (see the nonposted-mmio and
+  posted-mmio device tree properties).
+
+of_iomap()
+
+  Maps the resource described in a ``reg`` property in the device tree, doing
+  all required translations. Automatically selects ioremap_np() according to
+  platform requirements, as above.
+
+pci_ioremap_bar(), pci_ioremap_wc_bar()
+
+  Maps the resource described in a PCI base address without having to extract
+  the physical address first.
+
+pci_iomap(), pci_iomap_wc()
+
+  Like pci_ioremap_bar()/pci_ioremap_bar(), but also works on I/O space when
+  used together with ioread32()/iowrite32() and similar accessors
+
+pcim_iomap()
+
+  Like pci_iomap(), but uses devres to automatically unmap the resource when
+  the driver probe() function fails or a device in unbound from its driver
+
+  Documented in Documentation/driver-api/driver-model/devres.rst.
+
+Not using these wrappers may make drivers unusable on certain platforms with
+stricter rules for mapping I/O memory.
+
 Public Functions Provided
 =========================
 

Documentation/driver-api/driver-model/devres.rst

···
   devm_ioremap()
   devm_ioremap_uc()
   devm_ioremap_wc()
+  devm_ioremap_np()
   devm_ioremap_resource() : checks resource, requests memory region, ioremaps
   devm_ioremap_resource_wc()
   devm_platform_ioremap_resource() : calls devm_ioremap_resource() for platform device

MAINTAINERS

···
 F:	arch/arm64/boot/dts/amazon/
 F:	drivers/*/*alpine*
 
+ARM/APPLE MACHINE SUPPORT
+M:	Hector Martin <[e-mail]>
+L:	[e-mail] (moderated for non-subscribers)
+S:	Maintained
+W:	https://asahilinux.org
+B:	https://github.com/AsahiLinux/linux/issues
+C:	irc://chat.freenode.net/asahi-dev
+T:	git https://github.com/AsahiLinux/linux.git
+F:	Documentation/devicetree/bindings/arm/apple.yaml
+F:	Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml
+F:	arch/arm64/boot/dts/apple/
+F:	drivers/irqchip/irq-apple-aic.c
+F:	include/dt-bindings/interrupt-controller/apple-aic.h
+
 ARM/ARTPEC MACHINE SUPPORT
 M:	Jesper Nilsson <[e-mail]>
 M:	Lars Persson <[e-mail]>

arch/arm64/Kconfig.platforms

···
 	  This enables support for the Annapurna Labs Alpine
 	  Soc family.
 
+config ARCH_APPLE
+	bool "Apple Silicon SoC family"
+	select APPLE_AIC
+	help
+	  This enables support for Apple's in-house ARM SoC family, starting
+	  with the Apple M1.
+
 config ARCH_BCM2835
 	bool "Broadcom BCM2835 family"
 	select TIMER_OF

arch/arm64/boot/dts/Makefile

···
 subdir-y += amd
 subdir-y += amlogic
 subdir-y += apm
+subdir-y += apple
 subdir-y += arm
 subdir-y += bitmain
 subdir-y += broadcom

arch/arm64/boot/dts/apple/Makefile

···
+# SPDX-License-Identifier: GPL-2.0
+dtb-$(CONFIG_ARCH_APPLE) += t8103-j274.dtb

arch/arm64/boot/dts/apple/t8103-j274.dts

···
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple Mac mini (M1, 2020)
+ *
+ * target-type: J274
+ *
+ * Copyright The Asahi Linux Contributors
+ */
+
+/dts-v1/;
+
+#include "t8103.dtsi"
+
+/ {
+	compatible = "apple,j274", "apple,t8103", "apple,arm-platform";
+	model = "Apple Mac mini (M1, 2020)";
+
+	aliases {
+		serial0 = &serial0;
+	};
+
+	chosen {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		stdout-path = "serial0";
+
+		framebuffer0: framebuffer@0 {
+			compatible = "apple,simple-framebuffer", "simple-framebuffer";
+			reg = <0 0 0 0>; /* To be filled by loader */
+			/* Format properties will be added by loader */
+			status = "disabled";
+		};
+	};
+
+	memory@800000000 {
+		device_type = "memory";
+		reg = <0x8 0 0x2 0>; /* To be filled by loader */
+	};
+};
+
+&serial0 {
+	status = "okay";
+};

arch/arm64/boot/dts/apple/t8103.dtsi

···
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T8103 "M1" SoC
+ *
+ * Other names: H13G, "Tonga"
+ *
+ * Copyright The Asahi Linux Contributors
+ */
+
+#include <dt-bindings/interrupt-controller/apple-aic.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	compatible = "apple,t8103", "apple,arm-platform";
+
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "apple,icestorm";
+			device_type = "cpu";
+			reg = <0x0 0x0>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+		};
+
+		cpu1: cpu@1 {
+			compatible = "apple,icestorm";
+			device_type = "cpu";
+			reg = <0x0 0x1>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+		};
+
+		cpu2: cpu@2 {
+			compatible = "apple,icestorm";
+			device_type = "cpu";
+			reg = <0x0 0x2>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+		};
+
+		cpu3: cpu@3 {
+			compatible = "apple,icestorm";
+			device_type = "cpu";
+			reg = <0x0 0x3>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+		};
+
+		cpu4: cpu@10100 {
+			compatible = "apple,firestorm";
+			device_type = "cpu";
+			reg = <0x0 0x10100>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+		};
+
+		cpu5: cpu@10101 {
+			compatible = "apple,firestorm";
+			device_type = "cpu";
+			reg = <0x0 0x10101>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+		};
+
+		cpu6: cpu@10102 {
+			compatible = "apple,firestorm";
+			device_type = "cpu";
+			reg = <0x0 0x10102>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+		};
+
+		cpu7: cpu@10103 {
+			compatible = "apple,firestorm";
+			device_type = "cpu";
+			reg = <0x0 0x10103>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&aic>;
+		interrupt-names = "phys", "virt", "hyp-phys", "hyp-virt";
+		interrupts = <AIC_FIQ AIC_TMR_GUEST_PHYS IRQ_TYPE_LEVEL_HIGH>,
+			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>,
+			     <AIC_FIQ AIC_TMR_HV_PHYS IRQ_TYPE_LEVEL_HIGH>,
+			     <AIC_FIQ AIC_TMR_HV_VIRT IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	clk24: clock-24m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "clk24";
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		ranges;
+		nonposted-mmio;
+
+		serial0: serial@235200000 {
+			compatible = "apple,s5l-uart";
+			reg = <0x2 0x35200000 0x0 0x1000>;
+			reg-io-width = <4>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 605 IRQ_TYPE_LEVEL_HIGH>;
+			/*
+			 * TODO: figure out the clocking properly, there may
+			 * be a third selectable clock.
+			 */
+			clocks = <&clk24>, <&clk24>;
+			clock-names = "uart", "clk_uart_baud0";
+			status = "disabled";
+		};
+
+		aic: interrupt-controller@23b100000 {
+			compatible = "apple,t8103-aic", "apple,aic";
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			reg = <0x2 0x3b100000 0x0 0x8000>;
+		};
+	};
+};

arch/arm64/configs/defconfig

···
 CONFIG_ARCH_N5X=y
 CONFIG_ARCH_SUNXI=y
 CONFIG_ARCH_ALPINE=y
+CONFIG_ARCH_APPLE=y
 CONFIG_ARCH_BCM2835=y
 CONFIG_ARCH_BCM4908=y
 CONFIG_ARCH_BCM_IPROC=y

arch/arm64/include/asm/cputype.h

···
 #define ARM_CPU_IMP_NVIDIA		0x4E
 #define ARM_CPU_IMP_FUJITSU		0x46
 #define ARM_CPU_IMP_HISI		0x48
+#define ARM_CPU_IMP_APPLE		0x61
 
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
···
 
 #define HISI_CPU_PART_TSV110		0xD01
 
+#define APPLE_CPU_PART_M1_ICESTORM	0x022
+#define APPLE_CPU_PART_M1_FIRESTORM	0x023
+
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
···
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
+#define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
+#define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX

arch/arm64/include/asm/io.h

···
 
 #define ioremap(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
-
-/*
- * PCI configuration space mapping function.
- *
- * The PCI specification disallows posted write configuration transactions.
- * Add an arch specific pci_remap_cfgspace() definition that is implemented
- * through nGnRnE device memory attribute as recommended by the ARM v8
- * Architecture reference manual Issue A.k B2.8.2 "Device memory".
- */
-#define pci_remap_cfgspace(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
+#define ioremap_np(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
 
 /*
  * io{read,write}{16,32,64}be() macros

arch/arm64/include/asm/sysreg.h

···
 #define TRFCR_ELx_ExTRE			BIT(1)
 #define TRFCR_ELx_E0TRE			BIT(0)
 
+
+/* GIC Hypervisor interface registers */
+/* ICH_MISR_EL2 bit definitions */
+#define ICH_MISR_EOI		(1 << 0)
+#define ICH_MISR_U		(1 << 1)
+
+/* ICH_LR*_EL2 bit definitions */
+#define ICH_LR_VIRTUAL_ID_MASK	((1ULL << 32) - 1)
+
+#define ICH_LR_EOI		(1ULL << 41)
+#define ICH_LR_GROUP		(1ULL << 60)
+#define ICH_LR_HW		(1ULL << 61)
+#define ICH_LR_STATE		(3ULL << 62)
+#define ICH_LR_PENDING_BIT	(1ULL << 62)
+#define ICH_LR_ACTIVE_BIT	(1ULL << 63)
+#define ICH_LR_PHYS_ID_SHIFT	32
+#define ICH_LR_PHYS_ID_MASK	(0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
+#define ICH_LR_PRIORITY_SHIFT	48
+#define ICH_LR_PRIORITY_MASK	(0xffULL << ICH_LR_PRIORITY_SHIFT)
+
+/* ICH_HCR_EL2 bit definitions */
+#define ICH_HCR_EN		(1 << 0)
+#define ICH_HCR_UIE		(1 << 1)
+#define ICH_HCR_NPIE		(1 << 3)
+#define ICH_HCR_TC		(1 << 10)
+#define ICH_HCR_TALL0		(1 << 11)
+#define ICH_HCR_TALL1		(1 << 12)
+#define ICH_HCR_EOIcount_SHIFT	27
+#define ICH_HCR_EOIcount_MASK	(0x1f << ICH_HCR_EOIcount_SHIFT)
+
+/* ICH_VMCR_EL2 bit definitions */
+#define ICH_VMCR_ACK_CTL_SHIFT	2
+#define ICH_VMCR_ACK_CTL_MASK	(1 << ICH_VMCR_ACK_CTL_SHIFT)
+#define ICH_VMCR_FIQ_EN_SHIFT	3
+#define ICH_VMCR_FIQ_EN_MASK	(1 << ICH_VMCR_FIQ_EN_SHIFT)
+#define ICH_VMCR_CBPR_SHIFT	4
+#define ICH_VMCR_CBPR_MASK	(1 << ICH_VMCR_CBPR_SHIFT)
+#define ICH_VMCR_EOIM_SHIFT	9
+#define ICH_VMCR_EOIM_MASK	(1 << ICH_VMCR_EOIM_SHIFT)
+#define ICH_VMCR_BPR1_SHIFT	18
+#define ICH_VMCR_BPR1_MASK	(7 << ICH_VMCR_BPR1_SHIFT)
+#define ICH_VMCR_BPR0_SHIFT	21
+#define ICH_VMCR_BPR0_MASK	(7 << ICH_VMCR_BPR0_SHIFT)
+#define ICH_VMCR_PMR_SHIFT	24
+#define ICH_VMCR_PMR_MASK	(0xffUL << ICH_VMCR_PMR_SHIFT)
+#define ICH_VMCR_ENG0_SHIFT	0
+#define ICH_VMCR_ENG0_MASK	(1 << ICH_VMCR_ENG0_SHIFT)
+#define ICH_VMCR_ENG1_SHIFT	1
+#define ICH_VMCR_ENG1_MASK	(1 << ICH_VMCR_ENG1_SHIFT)
+
+/* ICH_VTR_EL2 bit definitions */
+#define ICH_VTR_PRI_BITS_SHIFT	29
+#define ICH_VTR_PRI_BITS_MASK	(7 << ICH_VTR_PRI_BITS_SHIFT)
+#define ICH_VTR_ID_BITS_SHIFT	23
+#define ICH_VTR_ID_BITS_MASK	(7 << ICH_VTR_ID_BITS_SHIFT)
+#define ICH_VTR_SEIS_SHIFT	22
+#define ICH_VTR_SEIS_MASK	(1 << ICH_VTR_SEIS_SHIFT)
+#define ICH_VTR_A3V_SHIFT	21
+#define ICH_VTR_A3V_MASK	(1 << ICH_VTR_A3V_SHIFT)
+
 #ifdef __ASSEMBLY__
 
 	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30

arch/sparc/include/asm/io_64.h

···
 #define ioremap_uc(X,Y)			ioremap((X),(Y))
 #define ioremap_wc(X,Y)			ioremap((X),(Y))
 #define ioremap_wt(X,Y)			ioremap((X),(Y))
+static inline void __iomem *ioremap_np(unsigned long offset, unsigned long size)
+{
+	return NULL;
+}
 
 static inline void iounmap(volatile void __iomem *addr)
 {

drivers/clocksource/arm_arch_timer.c

···
 u32 arch_timer_rate1 __ro_after_init;
 static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI] __ro_after_init;
 
+static const char *arch_timer_ppi_names[ARCH_TIMER_MAX_TIMER_PPI] = {
+	[ARCH_TIMER_PHYS_SECURE_PPI]	= "sec-phys",
+	[ARCH_TIMER_PHYS_NONSECURE_PPI]	= "phys",
+	[ARCH_TIMER_VIRT_PPI]		= "virt",
+	[ARCH_TIMER_HYP_PPI]		= "hyp-phys",
+	[ARCH_TIMER_HYP_VIRT_PPI]	= "hyp-virt",
+};
+
 static struct clock_event_device __percpu *arch_timer_evt;
 
 static enum arch_timer_ppi_nr arch_timer_uses_ppi __ro_after_init = ARCH_TIMER_VIRT_PPI;
···
 
 static int __init arch_timer_of_init(struct device_node *np)
 {
-	int i, ret;
+	int i, irq, ret;
 	u32 rate;
+	bool has_names;
 
 	if (arch_timers_present & ARCH_TIMER_TYPE_CP15) {
 		pr_warn("multiple nodes in dt, skipping\n");
···
 	}
 
 	arch_timers_present |= ARCH_TIMER_TYPE_CP15;
-	for (i = ARCH_TIMER_PHYS_SECURE_PPI; i < ARCH_TIMER_MAX_TIMER_PPI; i++)
-		arch_timer_ppi[i] = irq_of_parse_and_map(np, i);
+
+	has_names = of_property_read_bool(np, "interrupt-names");
+
+	for (i = ARCH_TIMER_PHYS_SECURE_PPI; i < ARCH_TIMER_MAX_TIMER_PPI; i++) {
+		if (has_names)
+			irq = of_irq_get_byname(np, arch_timer_ppi_names[i]);
+		else
+			irq = of_irq_get(np, i);
+		if (irq > 0)
+			arch_timer_ppi[i] = irq;
+	}
 
 	arch_timer_populate_kvm_info();
 

drivers/irqchip/Kconfig

···
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
 
+config APPLE_AIC
+	bool "Apple Interrupt Controller (AIC)"
+	depends on ARM64
+	default ARCH_APPLE
+	help
+	  Support for the Apple Interrupt Controller found on Apple Silicon SoCs,
+	  such as the M1.
+
 endmenu

drivers/irqchip/Makefile

···
 obj-$(CONFIG_MACH_REALTEK_RTL)		+= irq-realtek-rtl.o
 obj-$(CONFIG_WPCM450_AIC)		+= irq-wpcm450-aic.o
 obj-$(CONFIG_IRQ_IDT3243X)		+= irq-idt3243x.o
+obj-$(CONFIG_APPLE_AIC)			+= irq-apple-aic.o

drivers/irqchip/irq-apple-aic.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright The Asahi Linux Contributors
+ *
+ * Based on irq-lpc32xx:
+ *   Copyright 2015-2016 Vladimir Zapolskiy <[e-mail]>
+ * Based on irq-bcm2836:
+ *   Copyright 2015 Broadcom
+ */
+
+/*
+ * AIC is a fairly simple interrupt controller with the following features:
+ *
+ * - 896 level-triggered hardware IRQs
+ *   - Single mask bit per IRQ
+ *   - Per-IRQ affinity setting
+ *   - Automatic masking on event delivery (auto-ack)
+ *   - Software triggering (ORed with hw line)
+ * - 2 per-CPU IPIs (meant as "self" and "other", but they are
+ *   interchangeable if not symmetric)
+ * - Automatic prioritization (single event/ack register per CPU, lower IRQs =
+ *   higher priority)
+ * - Automatic masking on ack
+ * - Default "this CPU" register view and explicit per-CPU views
+ *
+ * In addition, this driver also handles FIQs, as these are routed to the same
+ * IRQ vector. These are used for Fast IPIs (TODO), the ARMv8 timer IRQs, and
+ * performance counters (TODO).
+ *
+ * Implementation notes:
+ *
+ * - This driver creates two IRQ domains, one for HW IRQs and internal FIQs,
+ *   and one for IPIs.
+ * - Since Linux needs more than 2 IPIs, we implement a software IRQ controller
+ *   and funnel all IPIs into one per-CPU IPI (the second "self" IPI is unused).
+ * - FIQ hwirq numbers are assigned after true hwirqs, and are per-cpu.
+ * - DT bindings use 3-cell form (like GIC):
+ *   - <0 nr flags> - hwirq #nr
+ *   - <1 nr flags> - FIQ #nr
+ *     - nr=0  Physical HV timer
+ *     - nr=1  Virtual HV timer
+ *     - nr=2  Physical guest timer
+ *     - nr=3  Virtual guest timer
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/bits.h>
+#include <linux/bitfield.h>
+#include <linux/cpuhotplug.h>
+#include <linux/io.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/limits.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <asm/exception.h>
+#include <asm/sysreg.h>
+#include <asm/virt.h>
+
+#include <dt-bindings/interrupt-controller/apple-aic.h>
+
+/*
+ * AIC registers (MMIO)
+ */
+
+#define AIC_INFO		0x0004
+#define AIC_INFO_NR_HW		GENMASK(15, 0)
+
+#define AIC_CONFIG		0x0010
+
+#define AIC_WHOAMI		0x2000
+#define AIC_EVENT		0x2004
+#define AIC_EVENT_TYPE		GENMASK(31, 16)
+#define AIC_EVENT_NUM		GENMASK(15, 0)
+
+#define AIC_EVENT_TYPE_HW	1
+#define AIC_EVENT_TYPE_IPI	4
+#define AIC_EVENT_IPI_OTHER	1
+#define AIC_EVENT_IPI_SELF	2
+
+#define AIC_IPI_SEND		0x2008
+#define AIC_IPI_ACK		0x200c
+#define AIC_IPI_MASK_SET	0x2024
+#define AIC_IPI_MASK_CLR	0x2028
+
+#define AIC_IPI_SEND_CPU(cpu)	BIT(cpu)
+
+#define AIC_IPI_OTHER		BIT(0)
+#define AIC_IPI_SELF		BIT(31)
+
+#define AIC_TARGET_CPU		0x3000
+#define AIC_SW_SET		0x4000
+#define AIC_SW_CLR		0x4080
+#define AIC_MASK_SET		0x4100
+#define AIC_MASK_CLR		0x4180
+
+#define AIC_CPU_IPI_SET(cpu)	(0x5008 + ((cpu) << 7))
+#define AIC_CPU_IPI_CLR(cpu)	(0x500c + ((cpu) << 7))
+#define AIC_CPU_IPI_MASK_SET(cpu) (0x5024 + ((cpu) << 7))
+#define AIC_CPU_IPI_MASK_CLR(cpu) (0x5028 + ((cpu) << 7))
+
+#define MASK_REG(x)		(4 * ((x) >> 5))
+#define MASK_BIT(x)		BIT((x) & GENMASK(4, 0))
+
+/*
+ * IMP-DEF sysregs that control FIQ sources
+ * Note: sysreg-based IPIs are not supported yet.
+ */
+
+/* Core PMC control register */
+#define SYS_IMP_APL_PMCR0_EL1		sys_reg(3, 1, 15, 0, 0)
+#define PMCR0_IMODE			GENMASK(10, 8)
+#define PMCR0_IMODE_OFF			0
+#define PMCR0_IMODE_PMI			1
+#define PMCR0_IMODE_AIC			2
+#define PMCR0_IMODE_HALT		3
+#define PMCR0_IMODE_FIQ			4
+#define PMCR0_IACT			BIT(11)
+
+/* IPI request registers */
+#define SYS_IMP_APL_IPI_RR_LOCAL_EL1	sys_reg(3, 5, 15, 0, 0)
+#define SYS_IMP_APL_IPI_RR_GLOBAL_EL1	sys_reg(3, 5, 15, 0, 1)
+#define IPI_RR_CPU			GENMASK(7, 0)
+/* Cluster only used for the GLOBAL register */
+#define IPI_RR_CLUSTER			GENMASK(23, 16)
+#define IPI_RR_TYPE			GENMASK(29, 28)
+#define IPI_RR_IMMEDIATE		0
+#define IPI_RR_RETRACT			1
+#define IPI_RR_DEFERRED			2
+#define IPI_RR_NOWAKE			3
+
+/* IPI status register */
+#define SYS_IMP_APL_IPI_SR_EL1		sys_reg(3, 5, 15, 1, 1)
+#define IPI_SR_PENDING			BIT(0)
+
+/* Guest timer FIQ enable register */
+#define SYS_IMP_APL_VM_TMR_FIQ_ENA_EL2	sys_reg(3, 5, 15, 1, 3)
+#define VM_TMR_FIQ_ENABLE_V		BIT(0)
+#define VM_TMR_FIQ_ENABLE_P		BIT(1)
+
+/* Deferred IPI countdown register */
+#define SYS_IMP_APL_IPI_CR_EL1		sys_reg(3, 5, 15, 3, 1)
+
+/* Uncore PMC control register */
+#define SYS_IMP_APL_UPMCR0_EL1		sys_reg(3, 7, 15, 0, 4)
+#define UPMCR0_IMODE			GENMASK(18, 16)
+#define UPMCR0_IMODE_OFF		0
+#define UPMCR0_IMODE_AIC		2
+#define UPMCR0_IMODE_HALT		3
+#define UPMCR0_IMODE_FIQ		4
+
+/* Uncore PMC status register */
+#define SYS_IMP_APL_UPMSR_EL1		sys_reg(3, 7, 15, 6, 4)
+#define UPMSR_IACT			BIT(0)
+
+#define AIC_NR_FIQ		4
+#define AIC_NR_SWIPI		32
+
+/*
+ * FIQ hwirq index definitions: FIQ sources use the DT binding defines
+ * directly, except that timers are special. At the irqchip level, the
+ * two timer types are represented by their access method: _EL0 registers
+ * or _EL02 registers. In the DT binding, the timers are represented
+ * by their purpose (HV or guest). This mapping is for when the kernel is
+ * running at EL2 (with VHE). When the kernel is running at EL1, the
+ * mapping differs and aic_irq_domain_translate() performs the remapping.
+ */
+
+#define AIC_TMR_EL0_PHYS	AIC_TMR_HV_PHYS
+#define AIC_TMR_EL0_VIRT	AIC_TMR_HV_VIRT
+#define AIC_TMR_EL02_PHYS	AIC_TMR_GUEST_PHYS
+#define AIC_TMR_EL02_VIRT	AIC_TMR_GUEST_VIRT
+
+struct aic_irq_chip {
+	void __iomem *base;
+	struct irq_domain *hw_domain;
+	struct irq_domain *ipi_domain;
+	int nr_hw;
+	int ipi_hwirq;
+};
+
+static DEFINE_PER_CPU(uint32_t, aic_fiq_unmasked);
+
+static DEFINE_PER_CPU(atomic_t, aic_vipi_flag);
+static DEFINE_PER_CPU(atomic_t, aic_vipi_enable);
+
+static struct aic_irq_chip *aic_irqc;
+
+static void aic_handle_ipi(struct pt_regs *regs);
+
+static u32 aic_ic_read(struct aic_irq_chip *ic, u32 reg)
+{
+	return readl_relaxed(ic->base + reg);
+}
+
+static void aic_ic_write(struct aic_irq_chip *ic, u32 reg, u32 val)
+{
+	writel_relaxed(val, ic->base + reg);
+}
+
+/*
+ * IRQ irqchip
+ */
+
+static void aic_irq_mask(struct irq_data *d)
+{
+	struct aic_irq_chip *ic = irq_data_get_irq_chip_data(d);
+
+	aic_ic_write(ic, AIC_MASK_SET + MASK_REG(irqd_to_hwirq(d)),
+		     MASK_BIT(irqd_to_hwirq(d)));
+}
+
+static void aic_irq_unmask(struct irq_data *d)
+{
+	struct aic_irq_chip *ic = irq_data_get_irq_chip_data(d);
+
+	aic_ic_write(ic, AIC_MASK_CLR + MASK_REG(d->hwirq),
+		     MASK_BIT(irqd_to_hwirq(d)));
+}
+
+static void aic_irq_eoi(struct irq_data *d)
+{
+	/*
+	 * Reading the interrupt reason automatically acknowledges and masks
+	 * the IRQ, so we just unmask it here if needed.
+	 */
+	if (!irqd_irq_disabled(d) && !irqd_irq_masked(d))
+		aic_irq_unmask(d);
+}
+
+static void __exception_irq_entry aic_handle_irq(struct pt_regs *regs)
+{
+	struct aic_irq_chip *ic = aic_irqc;
+	u32 event, type, irq;
+
+	do {
+		/*
+		 * We cannot use a relaxed read here, as reads from DMA buffers
+		 * need to be ordered after the IRQ fires.
+		 */
+		event = readl(ic->base + AIC_EVENT);
+		type = FIELD_GET(AIC_EVENT_TYPE, event);
+		irq = FIELD_GET(AIC_EVENT_NUM, event);
+
+		if (type == AIC_EVENT_TYPE_HW)
+			handle_domain_irq(aic_irqc->hw_domain, irq, regs);
+		else if (type == AIC_EVENT_TYPE_IPI && irq == 1)
+			aic_handle_ipi(regs);
+		else if (event != 0)
+			pr_err_ratelimited("Unknown IRQ event %d, %d\n", type, irq);
+	} while (event);
+
+	/*
+	 * vGIC maintenance interrupts end up here too, so we need to check
+	 * for them separately. This should never trigger if KVM is working
+	 * properly, because it will have already taken care of clearing it
+	 * on guest exit before this handler runs.
+	 */
+	if (is_kernel_in_hyp_mode() && (read_sysreg_s(SYS_ICH_HCR_EL2) & ICH_HCR_EN) &&
+		read_sysreg_s(SYS_ICH_MISR_EL2) != 0) {
+		pr_err_ratelimited("vGIC IRQ fired and not handled by KVM, disabling.\n");
+		sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EN, 0);
+	}
+}
+
+static int aic_irq_set_affinity(struct irq_data *d,
+				const struct cpumask *mask_val, bool force)
+{
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	struct aic_irq_chip *ic = irq_data_get_irq_chip_data(d);
+	int cpu;
+
+	if (force)
+		cpu = cpumask_first(mask_val);
+	else
+		cpu = cpumask_any_and(mask_val, cpu_online_mask);
+
+	aic_ic_write(ic, AIC_TARGET_CPU + hwirq * 4, BIT(cpu));
+	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+
+	return IRQ_SET_MASK_OK;
+}
+
+static int aic_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	/*
+	 * Some IRQs (e.g. MSIs) implicitly have edge semantics, and we don't
+	 * have a way to find out the type of any given IRQ, so just allow both.
+	 */
+	return (type == IRQ_TYPE_LEVEL_HIGH || type == IRQ_TYPE_EDGE_RISING) ? 0 : -EINVAL;
+}
+
+static struct irq_chip aic_chip = {
+	.name = "AIC",
+	.irq_mask = aic_irq_mask,
+	.irq_unmask = aic_irq_unmask,
+	.irq_eoi = aic_irq_eoi,
+	.irq_set_affinity = aic_irq_set_affinity,
+	.irq_set_type = aic_irq_set_type,
+};
+
+/*
+ * FIQ irqchip
+ */
+
+static unsigned long aic_fiq_get_idx(struct irq_data *d)
+{
+	struct aic_irq_chip *ic = irq_data_get_irq_chip_data(d);
+
+	return irqd_to_hwirq(d) - ic->nr_hw;
+}
+
+static void aic_fiq_set_mask(struct irq_data *d)
+{
+	/* Only the guest timers have real mask bits, unfortunately. */
+	switch (aic_fiq_get_idx(d)) {
+	case AIC_TMR_EL02_PHYS:
+		sysreg_clear_set_s(SYS_IMP_APL_VM_TMR_FIQ_ENA_EL2, VM_TMR_FIQ_ENABLE_P, 0);
+		isb();
+		break;
+	case AIC_TMR_EL02_VIRT:
+		sysreg_clear_set_s(SYS_IMP_APL_VM_TMR_FIQ_ENA_EL2, VM_TMR_FIQ_ENABLE_V, 0);
+		isb();
+		break;
+	default:
+		break;
+	}
+}
+
+static void aic_fiq_clear_mask(struct irq_data *d)
+{
+	switch (aic_fiq_get_idx(d)) {
+	case AIC_TMR_EL02_PHYS:
+		sysreg_clear_set_s(SYS_IMP_APL_VM_TMR_FIQ_ENA_EL2, 0, VM_TMR_FIQ_ENABLE_P);
+		isb();
+		break;
+	case AIC_TMR_EL02_VIRT:
+		sysreg_clear_set_s(SYS_IMP_APL_VM_TMR_FIQ_ENA_EL2, 0, VM_TMR_FIQ_ENABLE_V);
+		isb();
+		break;
+	default:
+		break;
+	}
+}
+
+static void aic_fiq_mask(struct irq_data *d)
+{
+	aic_fiq_set_mask(d);
+	__this_cpu_and(aic_fiq_unmasked, ~BIT(aic_fiq_get_idx(d)));
+}
+
+static void aic_fiq_unmask(struct irq_data *d)
+{
+	aic_fiq_clear_mask(d);
+	__this_cpu_or(aic_fiq_unmasked, BIT(aic_fiq_get_idx(d)));
+}
+
+static void aic_fiq_eoi(struct irq_data *d)
+{
+	/* We mask to ack (where we can), so we need to unmask at EOI. */
+	if (__this_cpu_read(aic_fiq_unmasked) & BIT(aic_fiq_get_idx(d)))
+		aic_fiq_clear_mask(d);
+}
+
+#define TIMER_FIRING(x)                                                        \
+	(((x) & (ARCH_TIMER_CTRL_ENABLE | ARCH_TIMER_CTRL_IT_MASK |            \
+		 ARCH_TIMER_CTRL_IT_STAT)) ==                                  \
+	 (ARCH_TIMER_CTRL_ENABLE | ARCH_TIMER_CTRL_IT_STAT))
+
+static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs)
+{
+	/*
+	 * It would be really nice if we had a system register that lets us get
+	 * the FIQ source state without having to peek down into sources...
+	 * but such a register does not seem to exist.
+	 *
+	 * So, we have these potential sources to test for:
+	 *  - Fast IPIs (not yet used)
+	 *  - The 4 timers (CNTP, CNTV for each of HV and guest)
+	 *  - Per-core PMCs (not yet supported)
+	 *  - Per-cluster uncore PMCs (not yet supported)
+	 *
+	 * Since not dealing with any of these results in a FIQ storm,
+	 * we check for everything here, even things we don't support yet.
+	 */
+
+	if (read_sysreg_s(SYS_IMP_APL_IPI_SR_EL1) & IPI_SR_PENDING) {
+		pr_err_ratelimited("Fast IPI fired. Acking.\n");
+		write_sysreg_s(IPI_SR_PENDING, SYS_IMP_APL_IPI_SR_EL1);
+	}
+
+	if (TIMER_FIRING(read_sysreg(cntp_ctl_el0)))
+		handle_domain_irq(aic_irqc->hw_domain,
+				  aic_irqc->nr_hw + AIC_TMR_EL0_PHYS, regs);
+
+	if (TIMER_FIRING(read_sysreg(cntv_ctl_el0)))
+		handle_domain_irq(aic_irqc->hw_domain,
+				  aic_irqc->nr_hw + AIC_TMR_EL0_VIRT, regs);
+
+	if (is_kernel_in_hyp_mode()) {
+		uint64_t enabled = read_sysreg_s(SYS_IMP_APL_VM_TMR_FIQ_ENA_EL2);
+
+		if ((enabled & VM_TMR_FIQ_ENABLE_P) &&
+		    TIMER_FIRING(read_sysreg_s(SYS_CNTP_CTL_EL02)))
+			handle_domain_irq(aic_irqc->hw_domain,
+					  aic_irqc->nr_hw + AIC_TMR_EL02_PHYS, regs);
+
+		if ((enabled & VM_TMR_FIQ_ENABLE_V) &&
+		    TIMER_FIRING(read_sysreg_s(SYS_CNTV_CTL_EL02)))
+			handle_domain_irq(aic_irqc->hw_domain,
+					  aic_irqc->nr_hw + AIC_TMR_EL02_VIRT, regs);
+	}
+
+	if ((read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & (PMCR0_IMODE | PMCR0_IACT)) ==
+			(FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_FIQ) | PMCR0_IACT)) {
+		/*
+		 * Not supported yet, let's figure out how to handle this when
+		 * we implement these proprietary performance counters. For now,
+		 * just mask it and move on.
+		 */
+		pr_err_ratelimited("PMC FIQ fired. Masking.\n");
+		sysreg_clear_set_s(SYS_IMP_APL_PMCR0_EL1, PMCR0_IMODE | PMCR0_IACT,
+				   FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_OFF));
+	}
+
+	if (FIELD_GET(UPMCR0_IMODE, read_sysreg_s(SYS_IMP_APL_UPMCR0_EL1)) == UPMCR0_IMODE_FIQ &&
+			(read_sysreg_s(SYS_IMP_APL_UPMSR_EL1) & UPMSR_IACT)) {
+		/* Same story with uncore PMCs */
+		pr_err_ratelimited("Uncore PMC FIQ fired. Masking.\n");
+		sysreg_clear_set_s(SYS_IMP_APL_UPMCR0_EL1, UPMCR0_IMODE,
+				   FIELD_PREP(UPMCR0_IMODE, UPMCR0_IMODE_OFF));
+	}
+}
+
+static int aic_fiq_set_type(struct irq_data *d, unsigned int type)
+{
+	return (type == IRQ_TYPE_LEVEL_HIGH) ? 0 : -EINVAL;
+}
+
+static struct irq_chip fiq_chip = {
+	.name = "AIC-FIQ",
+	.irq_mask = aic_fiq_mask,
+	.irq_unmask = aic_fiq_unmask,
+	.irq_ack = aic_fiq_set_mask,
+	.irq_eoi = aic_fiq_eoi,
+	.irq_set_type = aic_fiq_set_type,
+};
+
+/*
+ * Main IRQ domain
+ */
+
+static int aic_irq_domain_map(struct irq_domain *id, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	struct aic_irq_chip *ic = id->host_data;
+
+	if (hw < ic->nr_hw) {
+		irq_domain_set_info(id, irq, hw, &aic_chip, id->host_data,
+				    handle_fasteoi_irq, NULL, NULL);
+		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(irq)));
+	} else {
+		irq_set_percpu_devid(irq);
+		irq_domain_set_info(id, irq, hw, &fiq_chip, id->host_data,
+				    handle_percpu_devid_irq, NULL, NULL);
+	}
+
+	return 0;
+}
+
+static int aic_irq_domain_translate(struct irq_domain *id,
+				    struct irq_fwspec *fwspec,
+				    unsigned long *hwirq,
+				    unsigned int *type)
+{
+	struct aic_irq_chip *ic = id->host_data;
+
+	if (fwspec->param_count != 3 || !is_of_node(fwspec->fwnode))
+		return -EINVAL;
+
+	switch (fwspec->param[0]) {
+	case AIC_IRQ:
+		if (fwspec->param[1] >= ic->nr_hw)
+			return -EINVAL;
+		*hwirq = fwspec->param[1];
+		break;
+	case AIC_FIQ:
+		if (fwspec->param[1] >= AIC_NR_FIQ)
+			return -EINVAL;
+		*hwirq = ic->nr_hw + fwspec->param[1];
+
+		/*
+		 * In EL1 the non-redirected registers are the guest's,
+		 * not EL2's, so remap the hwirqs to match.
+		 */
+		if (!is_kernel_in_hyp_mode()) {
+			switch (fwspec->param[1]) {
+			case AIC_TMR_GUEST_PHYS:
+				*hwirq = ic->nr_hw + AIC_TMR_EL0_PHYS;
+				break;
+			case AIC_TMR_GUEST_VIRT:
+				*hwirq = ic->nr_hw + AIC_TMR_EL0_VIRT;
+				break;
+			case AIC_TMR_HV_PHYS:
+			case AIC_TMR_HV_VIRT:
+				return -ENOENT;
+			default:
+				break;
+			}
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+
+	return 0;
+}
+
+static int aic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	unsigned int type = IRQ_TYPE_NONE;
+	struct irq_fwspec *fwspec = arg;
+	irq_hw_number_t hwirq;
+	int i, ret;
+
+	ret = aic_irq_domain_translate(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = aic_irq_domain_map(domain, virq + i, hwirq + i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void aic_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		struct irq_data *d = irq_domain_get_irq_data(domain, virq + i);
+
+		irq_set_handler(virq + i, NULL);
+		irq_domain_reset_irq_data(d);
+	}
+}
+
+static const struct irq_domain_ops aic_irq_domain_ops = {
+	.translate	= aic_irq_domain_translate,
+	.alloc		= aic_irq_domain_alloc,
+	.free		= aic_irq_domain_free,
+};
+
+/*
+ * IPI irqchip
+ */
+
+static void aic_ipi_mask(struct irq_data *d)
+{
+	u32 irq_bit = BIT(irqd_to_hwirq(d));
+
+	/* No specific ordering requirements needed here. */
+	atomic_andnot(irq_bit, this_cpu_ptr(&aic_vipi_enable));
+}
+
+static void aic_ipi_unmask(struct irq_data *d)
+{
+	struct aic_irq_chip *ic = irq_data_get_irq_chip_data(d);
+	u32 irq_bit = BIT(irqd_to_hwirq(d));
+
+	atomic_or(irq_bit, this_cpu_ptr(&aic_vipi_enable));
+
+	/*
+	 * The atomic_or() above must complete before the atomic_read()
+	 * below to avoid racing aic_ipi_send_mask().
+	 */
+	smp_mb__after_atomic();
+
+	/*
+	 * If a pending vIPI was unmasked, raise a HW IPI to ourselves.
+	 * No barriers needed here since this is a self-IPI.
+	 */
+	if (atomic_read(this_cpu_ptr(&aic_vipi_flag)) & irq_bit)
+		aic_ic_write(ic, AIC_IPI_SEND, AIC_IPI_SEND_CPU(smp_processor_id()));
+}
+
+static void aic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
+{
+	struct aic_irq_chip *ic = irq_data_get_irq_chip_data(d);
+	u32 irq_bit = BIT(irqd_to_hwirq(d));
+	u32 send = 0;
+	int cpu;
+	unsigned long pending;
+
+	for_each_cpu(cpu, mask) {
+		/*
+		 * This sequence is the mirror of the one in aic_ipi_unmask();
+		 * see the comment there. Additionally, release semantics
+		 * ensure that the vIPI flag set is ordered after any shared
+		 * memory accesses that precede it. This therefore also pairs
+		 * with the atomic_fetch_andnot in aic_handle_ipi().
+		 */
+		pending = atomic_fetch_or_release(irq_bit, per_cpu_ptr(&aic_vipi_flag, cpu));
+
+		/*
+		 * The atomic_fetch_or_release() above must complete before the
+		 * atomic_read() below to avoid racing aic_ipi_unmask().
+		 */
+		smp_mb__after_atomic();
+
+		if (!(pending & irq_bit) &&
+		    (atomic_read(per_cpu_ptr(&aic_vipi_enable, cpu)) & irq_bit))
+			send |= AIC_IPI_SEND_CPU(cpu);
+	}
+
+	/*
+	 * The flag writes must complete before the physical IPI is issued
+	 * to another CPU. This is implied by the control dependency on
+	 * the result of atomic_read_acquire() above, which is itself
+	 * already ordered after the vIPI flag write.
+	 */
+	if (send)
+		aic_ic_write(ic, AIC_IPI_SEND, send);
+}
+
+static struct irq_chip ipi_chip = {
+	.name = "AIC-IPI",
+	.irq_mask = aic_ipi_mask,
+	.irq_unmask = aic_ipi_unmask,
+	.ipi_send_mask = aic_ipi_send_mask,
+};
+
+/*
+ * IPI IRQ domain
+ */
+
+static void aic_handle_ipi(struct pt_regs *regs)
+{
+	int i;
+	unsigned long enabled, firing;
+
+	/*
+	 * Ack the IPI. We need to order this after the AIC event read, but
+	 * that is enforced by normal MMIO ordering guarantees.
+	 */
+	aic_ic_write(aic_irqc, AIC_IPI_ACK, AIC_IPI_OTHER);
+
+	/*
+	 * The mask read does not need to be ordered. Only we can change
+	 * our own mask anyway, so no races are possible here, as long as
+	 * we are properly in the interrupt handler (which is covered by
+	 * the barrier that is part of the top-level AIC handler's readl()).
+	 */
+	enabled = atomic_read(this_cpu_ptr(&aic_vipi_enable));
+
+	/*
+	 * Clear the IPIs we are about to handle. This pairs with the
+	 * atomic_fetch_or_release() in aic_ipi_send_mask(), and needs to be
+	 * ordered after the aic_ic_write() above (to avoid dropping vIPIs) and
+	 * before IPI handling code (to avoid races handling vIPIs before they
+	 * are signaled). The former is taken care of by the release semantics
+	 * of the write portion, while the latter is taken care of by the
+	 * acquire semantics of the read portion.
+	 */
+	firing = atomic_fetch_andnot(enabled, this_cpu_ptr(&aic_vipi_flag)) & enabled;
+
+	for_each_set_bit(i, &firing, AIC_NR_SWIPI)
+		handle_domain_irq(aic_irqc->ipi_domain, i, regs);
+
+	/*
+	 * No ordering needed here; at worst this just changes the timing of
+	 * when the next IPI will be delivered.
+	 */
+	aic_ic_write(aic_irqc, AIC_IPI_MASK_CLR, AIC_IPI_OTHER);
+}
+
+static int aic_ipi_alloc(struct irq_domain *d, unsigned int virq,
+			 unsigned int nr_irqs, void *args)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_percpu_devid(virq + i);
+		irq_domain_set_info(d, virq + i, i, &ipi_chip, d->host_data,
+				    handle_percpu_devid_irq, NULL, NULL);
+	}
+
+	return 0;
+}
+
+static void aic_ipi_free(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs)
+{
+	/* Not freeing IPIs */
+}
+
+static const struct irq_domain_ops aic_ipi_domain_ops = {
+	.alloc = aic_ipi_alloc,
+	.free = aic_ipi_free,
+};
+
+static int aic_init_smp(struct aic_irq_chip *irqc, struct device_node *node)
+{
+	struct irq_domain *ipi_domain;
+	int base_ipi;
+
+	ipi_domain = irq_domain_create_linear(irqc->hw_domain->fwnode, AIC_NR_SWIPI,
+					      &aic_ipi_domain_ops, irqc);
+	if (WARN_ON(!ipi_domain))
+		return -ENODEV;
+
+	ipi_domain->flags |= IRQ_DOMAIN_FLAG_IPI_SINGLE;
+	irq_domain_update_bus_token(ipi_domain, DOMAIN_BUS_IPI);
+
+	base_ipi = __irq_domain_alloc_irqs(ipi_domain, -1, AIC_NR_SWIPI,
+					   NUMA_NO_NODE, NULL, false, NULL);
+
+	if (WARN_ON(!base_ipi)) {
+		irq_domain_remove(ipi_domain);
+		return -ENODEV;
+	}
+
+	set_smp_ipi_range(base_ipi, AIC_NR_SWIPI);
+
+	irqc->ipi_domain = ipi_domain;
+
+	return 0;
+}
+
+static int aic_init_cpu(unsigned int cpu)
+{
+	/* Mask all hard-wired per-CPU IRQ/FIQ sources */
+
+	/* Pending Fast IPI FIQs */
+	write_sysreg_s(IPI_SR_PENDING, SYS_IMP_APL_IPI_SR_EL1);
+
+	/* Timer FIQs */
+	sysreg_clear_set(cntp_ctl_el0, 0, ARCH_TIMER_CTRL_IT_MASK);
+	sysreg_clear_set(cntv_ctl_el0, 0, ARCH_TIMER_CTRL_IT_MASK);
+
+	/* EL2-only (VHE mode) IRQ sources */
+	if (is_kernel_in_hyp_mode()) {
+		/* Guest timers */
+		sysreg_clear_set_s(SYS_IMP_APL_VM_TMR_FIQ_ENA_EL2,
+				   VM_TMR_FIQ_ENABLE_V | VM_TMR_FIQ_ENABLE_P, 0);
+
+		/* vGIC maintenance IRQ */
+		sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EN, 0);
+	}
+
+	/* PMC FIQ */
+	sysreg_clear_set_s(SYS_IMP_APL_PMCR0_EL1, PMCR0_IMODE | PMCR0_IACT,
+			   FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_OFF));
+
+	/* Uncore PMC FIQ */
+	sysreg_clear_set_s(SYS_IMP_APL_UPMCR0_EL1, UPMCR0_IMODE,
+			   FIELD_PREP(UPMCR0_IMODE, UPMCR0_IMODE_OFF));
+
+	/* Commit all of the above */
+	isb();
+
+	/*
+	 * Make sure the kernel's idea of logical CPU order is the same as AIC's
+	 * If we ever end up with a mismatch here, we will have to introduce
+	 * a mapping table similar to what other irqchip drivers do.
+	 */
+	WARN_ON(aic_ic_read(aic_irqc, AIC_WHOAMI) != smp_processor_id());
+
+	/*
+	 * Always keep IPIs unmasked at the hardware level (except auto-masking
+	 * by AIC during processing). We manage masks at the vIPI level.
+	 */
+	aic_ic_write(aic_irqc, AIC_IPI_ACK, AIC_IPI_SELF | AIC_IPI_OTHER);
+	aic_ic_write(aic_irqc, AIC_IPI_MASK_SET, AIC_IPI_SELF);
+	aic_ic_write(aic_irqc, AIC_IPI_MASK_CLR, AIC_IPI_OTHER);
+
+	/* Initialize the local mask state */
+	__this_cpu_write(aic_fiq_unmasked, 0);
+
+	return 0;
+}
+
+static int __init aic_of_ic_init(struct device_node *node, struct device_node *parent)
+{
+	int i;
+	void __iomem *regs;
+	u32 info;
+	struct aic_irq_chip *irqc;
+
+	regs = of_iomap(node, 0);
+	if (WARN_ON(!regs))
+		return -EIO;
+
+	irqc = kzalloc(sizeof(*irqc), GFP_KERNEL);
+	if (!irqc)
+		return -ENOMEM;
+
+	aic_irqc = irqc;
+	irqc->base = regs;
+
+	info = aic_ic_read(irqc, AIC_INFO);
+	irqc->nr_hw = FIELD_GET(AIC_INFO_NR_HW, info);
+
+	irqc->hw_domain = irq_domain_create_linear(of_node_to_fwnode(node),
+						   irqc->nr_hw + AIC_NR_FIQ,
+						   &aic_irq_domain_ops, irqc);
+	if (WARN_ON(!irqc->hw_domain)) {
+		iounmap(irqc->base);
+		kfree(irqc);
+		return -ENODEV;
+	}
+
+	irq_domain_update_bus_token(irqc->hw_domain, DOMAIN_BUS_WIRED);
+
+	if (aic_init_smp(irqc, node)) {
+		irq_domain_remove(irqc->hw_domain);
+		iounmap(irqc->base);
+		kfree(irqc);
+		return -ENODEV;
+	}
+
+	set_handle_irq(aic_handle_irq);
+	set_handle_fiq(aic_handle_fiq);
+
+	for (i = 0; i < BITS_TO_U32(irqc->nr_hw); i++)
+		aic_ic_write(irqc, AIC_MASK_SET + i * 4, U32_MAX);
+	for (i = 0; i < BITS_TO_U32(irqc->nr_hw); i++)
+		aic_ic_write(irqc, AIC_SW_CLR + i * 4, U32_MAX);
+	for (i = 0; i < irqc->nr_hw; i++)
+		aic_ic_write(irqc, AIC_TARGET_CPU + i * 4, 1);
+
+	if (!is_kernel_in_hyp_mode())
+		pr_info("Kernel running in EL1, mapping interrupts");
+
+	cpuhp_setup_state(CPUHP_AP_IRQ_APPLE_AIC_STARTING,
+			  "irqchip/apple-aic/ipi:starting",
+			  aic_init_cpu, NULL);
+
+	pr_info("Initialized with %d IRQs, %d FIQs, %d vIPIs\n",
+		irqc->nr_hw, AIC_NR_FIQ, AIC_NR_SWIPI);
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(apple_m1_aic, "apple,aic", aic_of_ic_init);

drivers/of/address.c

···
 static int __of_address_to_resource(struct device_node *dev,
 		const __be32 *addrp, u64 size, unsigned int flags,
 		const char *name, struct resource *r);
+static bool of_mmio_is_nonposted(struct device_node *np);
 
 /* Debug utility */
 #ifdef DEBUG
···
 		return -EINVAL;
 	memset(r, 0, sizeof(struct resource));
 
+	if (of_mmio_is_nonposted(dev))
+		flags |= IORESOURCE_MEM_NONPOSTED;
+
 	r->start = taddr;
 	r->end = taddr + size - 1;
 	r->flags = flags;
···
 	if (of_address_to_resource(np, index, &res))
 		return NULL;
 
-	return ioremap(res.start, resource_size(&res));
+	if (res.flags & IORESOURCE_MEM_NONPOSTED)
+		return ioremap_np(res.start, resource_size(&res));
+	else
+		return ioremap(res.start, resource_size(&res));
 }
 EXPORT_SYMBOL(of_iomap);
 
···
 	if (!request_mem_region(res.start, resource_size(&res), name))
 		return IOMEM_ERR_PTR(-EBUSY);
 
-	mem = ioremap(res.start, resource_size(&res));
+	if (res.flags & IORESOURCE_MEM_NONPOSTED)
+		mem = ioremap_np(res.start, resource_size(&res));
+	else
+		mem = ioremap(res.start, resource_size(&res));
+
 	if (!mem) {
 		release_mem_region(res.start, resource_size(&res));
 		return IOMEM_ERR_PTR(-ENOMEM);
···
 	return false;
 }
 EXPORT_SYMBOL_GPL(of_dma_is_coherent);
+
+/**
+ * of_mmio_is_nonposted - Check if device uses non-posted MMIO
+ * @np:	device node
+ *
+ * Returns true if the "nonposted-mmio" property was found for
+ * the device's bus.
+ *
+ * This is currently only enabled on builds that support Apple ARM devices, as
+ * an optimization.
+ */
+static bool of_mmio_is_nonposted(struct device_node *np)
+{
+	struct device_node *parent;
+	bool nonposted;
+
+	if (!IS_ENABLED(CONFIG_ARCH_APPLE))
+		return false;
+
+	parent = of_get_parent(np);
+	if (!parent)
+		return false;
+
+	nonposted = of_property_read_bool(parent, "nonposted-mmio");
+
+	of_node_put(parent);
+	return nonposted;
+}

include/asm-generic/io.h

···
  *
  * ioremap_wc() and ioremap_wt() can provide more relaxed caching attributes
  * for specific drivers if the architecture choses to implement them.  If they
- * are not implemented we fall back to plain ioremap.
+ * are not implemented we fall back to plain ioremap. Conversely, ioremap_np()
+ * can provide stricter non-posted write semantics if the architecture
+ * implements them.
  */
 #ifndef CONFIG_MMU
 #ifndef ioremap
···
 #ifndef ioremap_uc
 #define ioremap_uc ioremap_uc
 static inline void __iomem *ioremap_uc(phys_addr_t offset, size_t size)
+{
+	return NULL;
+}
+#endif
+
+/*
+ * ioremap_np needs an explicit architecture implementation, as it
+ * requests stronger semantics than regular ioremap(). Portable drivers
+ * should instead use one of the higher-level abstractions, like
+ * devm_ioremap_resource(), to choose the correct variant for any given
+ * device and bus. Portable drivers with a good reason to want non-posted
+ * write semantics should always provide an ioremap() fallback in case
+ * ioremap_np() is not available.
+ */
+#ifndef ioremap_np
+#define ioremap_np ioremap_np
+static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size)
 {
 	return NULL;
 }

include/asm-generic/iomap.h

···
 #define ioremap_wt ioremap
 #endif
 
+#ifndef ARCH_HAS_IOREMAP_NP
+/* See the comment in asm-generic/io.h about ioremap_np(). */
+#define ioremap_np ioremap_np
+static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size)
+{
+	return NULL;
+}
+#endif
+
 #ifdef CONFIG_PCI
 /* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */
 struct pci_dev;

include/clocksource/arm_arch_timer.h

···
 	ARCH_TIMER_PHYS_NONSECURE_PPI,
 	ARCH_TIMER_VIRT_PPI,
 	ARCH_TIMER_HYP_PPI,
+	ARCH_TIMER_HYP_VIRT_PPI,
 	ARCH_TIMER_MAX_TIMER_PPI
 };
 

include/dt-bindings/interrupt-controller/apple-aic.h

···
+/* SPDX-License-Identifier: GPL-2.0+ OR MIT */
+#ifndef _DT_BINDINGS_INTERRUPT_CONTROLLER_APPLE_AIC_H
+#define _DT_BINDINGS_INTERRUPT_CONTROLLER_APPLE_AIC_H
+
+#include <dt-bindings/interrupt-controller/irq.h>
+
+#define AIC_IRQ	0
+#define AIC_FIQ	1
+
+#define AIC_TMR_HV_PHYS		0
+#define AIC_TMR_HV_VIRT		1
+#define AIC_TMR_GUEST_PHYS	2
+#define AIC_TMR_GUEST_VIRT	3
+
+#endif

include/linux/cpuhotplug.h

···
 	CPUHP_AP_CPU_PM_STARTING,
 	CPUHP_AP_IRQ_GIC_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
+	CPUHP_AP_IRQ_APPLE_AIC_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_IRQ_MIPS_GIC_STARTING,

include/linux/io.h

···
 				   resource_size_t size);
 void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset,
 				   resource_size_t size);
+void __iomem *devm_ioremap_np(struct device *dev, resource_size_t offset,
+				   resource_size_t size);
 void devm_iounmap(struct device *dev, void __iomem *addr);
 int check_signature(const volatile void __iomem *io_addr,
 			const unsigned char *signature, int length);
···
 #ifdef CONFIG_PCI
 /*
  * The PCI specifications (Rev 3.0, 3.2.5 "Transaction Ordering and
- * Posting") mandate non-posted configuration transactions. There is
- * no ioremap API in the kernel that can guarantee non-posted write
- * semantics across arches so provide a default implementation for
- * mapping PCI config space that defaults to ioremap(); arches
- * should override it if they have memory mapping implementations that
- * guarantee non-posted writes semantics to make the memory mapping
- * compliant with the PCI specification.
+ * Posting") mandate non-posted configuration transactions. This default
+ * implementation attempts to use the ioremap_np() API to provide this
+ * on arches that support it, and falls back to ioremap() on those that
+ * don't. Overriding this function is deprecated; arches that properly
+ * support non-posted accesses should implement ioremap_np() instead, which
+ * this default implementation can then use to return mappings compliant with
+ * the PCI specification.
  */
 #ifndef pci_remap_cfgspace
 #define pci_remap_cfgspace pci_remap_cfgspace
 static inline void __iomem *pci_remap_cfgspace(phys_addr_t offset,
 					       size_t size)
 {
-	return ioremap(offset, size);
+	return ioremap_np(offset, size) ?: ioremap(offset, size);
 }
 #endif
 #endif

include/linux/ioport.h

···
 #define IORESOURCE_MEM_32BIT		(3<<3)
 #define IORESOURCE_MEM_SHADOWABLE	(1<<5)	/* dup: IORESOURCE_SHADOWABLE */
 #define IORESOURCE_MEM_EXPANSIONROM	(1<<6)
+#define IORESOURCE_MEM_NONPOSTED	(1<<7)
 
 /* PnP I/O specific bits (IORESOURCE_BITS) */
 #define IORESOURCE_IO_16BIT_ADDR	(1<<0)

include/linux/irqchip/arm-gic-v3.h

···
 #define ICC_SRE_EL1_DFB			(1U << 1)
 #define ICC_SRE_EL1_SRE			(1U << 0)
 
-/*
- * Hypervisor interface registers (SRE only)
- */
-#define ICH_LR_VIRTUAL_ID_MASK		((1ULL << 32) - 1)
-
-#define ICH_LR_EOI			(1ULL << 41)
-#define ICH_LR_GROUP			(1ULL << 60)
-#define ICH_LR_HW			(1ULL << 61)
-#define ICH_LR_STATE			(3ULL << 62)
-#define ICH_LR_PENDING_BIT		(1ULL << 62)
-#define ICH_LR_ACTIVE_BIT		(1ULL << 63)
-#define ICH_LR_PHYS_ID_SHIFT		32
-#define ICH_LR_PHYS_ID_MASK		(0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
-#define ICH_LR_PRIORITY_SHIFT		48
-#define ICH_LR_PRIORITY_MASK		(0xffULL << ICH_LR_PRIORITY_SHIFT)
-
 /* These are for GICv2 emulation only */
 #define GICH_LR_VIRTUALID		(0x3ffUL << 0)
 #define GICH_LR_PHYSID_CPUID_SHIFT	(10)
 #define GICH_LR_PHYSID_CPUID		(7UL << GICH_LR_PHYSID_CPUID_SHIFT)
-
-#define ICH_MISR_EOI			(1 << 0)
-#define ICH_MISR_U			(1 << 1)
-
-#define ICH_HCR_EN			(1 << 0)
-#define ICH_HCR_UIE			(1 << 1)
-#define ICH_HCR_NPIE			(1 << 3)
-#define ICH_HCR_TC			(1 << 10)
-#define ICH_HCR_TALL0			(1 << 11)
-#define ICH_HCR_TALL1			(1 << 12)
-#define ICH_HCR_EOIcount_SHIFT		27
-#define ICH_HCR_EOIcount_MASK		(0x1f << ICH_HCR_EOIcount_SHIFT)
-
-#define ICH_VMCR_ACK_CTL_SHIFT		2
-#define ICH_VMCR_ACK_CTL_MASK		(1 << ICH_VMCR_ACK_CTL_SHIFT)
-#define ICH_VMCR_FIQ_EN_SHIFT		3
-#define ICH_VMCR_FIQ_EN_MASK		(1 << ICH_VMCR_FIQ_EN_SHIFT)
-#define ICH_VMCR_CBPR_SHIFT		4
-#define ICH_VMCR_CBPR_MASK		(1 << ICH_VMCR_CBPR_SHIFT)
-#define ICH_VMCR_EOIM_SHIFT		9
-#define ICH_VMCR_EOIM_MASK		(1 << ICH_VMCR_EOIM_SHIFT)
-#define ICH_VMCR_BPR1_SHIFT		18
-#define ICH_VMCR_BPR1_MASK		(7 << ICH_VMCR_BPR1_SHIFT)
-#define ICH_VMCR_BPR0_SHIFT		21
-#define ICH_VMCR_BPR0_MASK		(7 << ICH_VMCR_BPR0_SHIFT)
-#define ICH_VMCR_PMR_SHIFT		24
-#define ICH_VMCR_PMR_MASK		(0xffUL << ICH_VMCR_PMR_SHIFT)
-#define ICH_VMCR_ENG0_SHIFT		0
-#define ICH_VMCR_ENG0_MASK		(1 << ICH_VMCR_ENG0_SHIFT)
-#define ICH_VMCR_ENG1_SHIFT		1
-#define ICH_VMCR_ENG1_MASK		(1 << ICH_VMCR_ENG1_SHIFT)
-
-#define ICH_VTR_PRI_BITS_SHIFT		29
-#define ICH_VTR_PRI_BITS_MASK		(7 << ICH_VTR_PRI_BITS_SHIFT)
-#define ICH_VTR_ID_BITS_SHIFT		23
-#define ICH_VTR_ID_BITS_MASK		(7 << ICH_VTR_ID_BITS_SHIFT)
-#define ICH_VTR_SEIS_SHIFT		22
-#define ICH_VTR_SEIS_MASK		(1 << ICH_VTR_SEIS_SHIFT)
-#define ICH_VTR_A3V_SHIFT		21
-#define ICH_VTR_A3V_MASK		(1 << ICH_VTR_A3V_SHIFT)
 
 #define ICC_IAR1_EL1_SPURIOUS		0x3ff
 

lib/devres.c

···
 	DEVM_IOREMAP = 0,
 	DEVM_IOREMAP_UC,
 	DEVM_IOREMAP_WC,
+	DEVM_IOREMAP_NP,
 };
 
 void devm_ioremap_release(struct device *dev, void *res)
···
 		break;
 	case DEVM_IOREMAP_WC:
 		addr = ioremap_wc(offset, size);
+		break;
+	case DEVM_IOREMAP_NP:
+		addr = ioremap_np(offset, size);
 		break;
 	}
 
···
 EXPORT_SYMBOL(devm_ioremap_wc);
 
 /**
+ * devm_ioremap_np - Managed ioremap_np()
+ * @dev: Generic device to remap IO address for
+ * @offset: Resource address to map
+ * @size: Size of map
+ *
+ * Managed ioremap_np().  Map is automatically unmapped on driver detach.
+ */
+void __iomem *devm_ioremap_np(struct device *dev, resource_size_t offset,
+			      resource_size_t size)
+{
+	return __devm_ioremap(dev, offset, size, DEVM_IOREMAP_NP);
+}
+EXPORT_SYMBOL(devm_ioremap_np);
+
+/**
  * devm_iounmap - Managed iounmap()
  * @dev: Generic device to unmap for
  * @addr: Address to unmap
···
 		dev_err(dev, "invalid resource\n");
 		return IOMEM_ERR_PTR(-EINVAL);
 	}
+
+	if (type == DEVM_IOREMAP && res->flags & IORESOURCE_MEM_NONPOSTED)
+		type = DEVM_IOREMAP_NP;
 
 	size = resource_size(res);