Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 - eBPF JIT compiler for arm64
 - CPU suspend backend for PSCI (firmware interface) with standard idle
   states defined in DT (generic idle driver to be merged via a
   different tree)
 - Support for CONFIG_DEBUG_SET_MODULE_RONX
 - Support for unmapped cpu-release-addr (outside kernel linear mapping)
 - set_arch_dma_coherent_ops() implemented and bus notifiers removed
 - EFI_STUB improvements when base of DRAM is occupied
 - Typos in KGDB macros
 - Clean-up to (partially) allow kernel building with LLVM
 - Other clean-ups (extern keyword, phys_addr_t usage)

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (51 commits)
  arm64: Remove unneeded extern keyword
  ARM64: make of_device_ids const
  arm64: Use phys_addr_t type for physical address
  aarch64: filter $x from kallsyms
  arm64: Use DMA_ERROR_CODE to denote failed allocation
  arm64: Fix typos in KGDB macros
  arm64: insn: Add return statements after BUG_ON()
  arm64: debug: don't re-enable debug exceptions on return from el1_dbg
  Revert "arm64: dmi: Add SMBIOS/DMI support"
  arm64: Implement set_arch_dma_coherent_ops() to replace bus notifiers
  of: amba: use of_dma_configure for AMBA devices
  arm64: dmi: Add SMBIOS/DMI support
  arm64: Correct ftrace calls to aarch64_insn_gen_branch_imm()
  arm64:mm: initialize max_mapnr using function set_max_mapnr
  setup: Move unmask of async interrupts after possible earlycon setup
  arm64: LLVMLinux: Fix inline arm64 assembly for use with clang
  arm64: pageattr: Correctly adjust unaligned start addresses
  net: bpf: arm64: fix module memory leak when JIT image build fails
  arm64: add PSCI CPU_SUSPEND based cpu_suspend support
  arm64: kernel: introduce cpu_init_idle CPU operation
  ...

Documentation/devicetree/bindings/arm/cpus.txt

@@ -219,6 +219,12 @@ nodes to be present and contain the properties described below.
 		Value type: <phandle>
 		Definition: Specifies the ACC[2] node associated with this CPU.
 
+	- cpu-idle-states
+		Usage: Optional
+		Value type: <prop-encoded-array>
+		Definition:
+			# List of phandles to idle state nodes supported
+			  by this cpu [3].
 
 Example 1 (dual-cluster big.LITTLE system 32-bit):
 
@@ -415,3 +421,5 @@ cpus {
 --
 [1] arm/msm/qcom,saw2.txt
 [2] arm/msm/qcom,kpss-acc.txt
+[3] ARM Linux kernel documentation - idle states bindings
+    Documentation/devicetree/bindings/arm/idle-states.txt

Documentation/devicetree/bindings/arm/idle-states.txt

@@ -0,0 +1,679 @@
+==========================================
+ARM idle states binding description
+==========================================
+
+==========================================
+1 - Introduction
+==========================================
+
+ARM systems contain HW capable of managing power consumption dynamically,
+where cores can be put in different low-power states (ranging from simple
+wfi to power gating) according to OS PM policies. The CPU states representing
+the range of dynamic idle states that a processor can enter at run-time, can be
+specified through device tree bindings representing the parameters required
+to enter/exit specific idle states on a given processor.
+
+According to the Server Base System Architecture document (SBSA, [3]), the
+power states an ARM CPU can be put into are identified by the following list:
+
+- Running
+- Idle_standby
+- Idle_retention
+- Sleep
+- Off
+
+The power states described in the SBSA document define the basic CPU states on
+top of which ARM platforms implement power management schemes that allow an OS
+PM implementation to put the processor in different idle states (which include
+states listed above; "off" state is not an idle state since it does not have
+wake-up capabilities, hence it is not considered in this document).
+
+Idle state parameters (eg entry latency) are platform specific and need to be
+characterized with bindings that provide the required information to OS PM
+code so that it can build the required tables and use them at runtime.
+
+The device tree binding definition for ARM idle states is the subject of this
+document.
+
+===========================================
+2 - idle-states definitions
+===========================================
+
+Idle states are characterized for a specific system through a set of
+timing and energy related properties, that underline the HW behaviour
+triggered upon idle states entry and exit.
+
+The following diagram depicts the CPU execution phases and related timing
+properties required to enter and exit an idle state:
+
+..__[EXEC]__|__[PREP]__|__[ENTRY]__|__[IDLE]__|__[EXIT]__|__[EXEC]__..
+	    |          |           |          |          |
+
+	    |<------ entry ------->|
+	    |       latency        |
+					      |<- exit ->|
+					      |  latency |
+	    |<-------- min-residency -------->|
+		       |<-------  wakeup-latency ------->|
+
+		Diagram 1: CPU idle state execution phases
+
+EXEC:	Normal CPU execution.
+
+PREP:	Preparation phase before committing the hardware to idle mode
+	like cache flushing. This is abortable on pending wake-up
+	event conditions. The abort latency is assumed to be negligible
+	(i.e. less than the ENTRY + EXIT duration). If aborted, CPU
+	goes back to EXEC. This phase is optional. If not abortable,
+	this should be included in the ENTRY phase instead.
+
+ENTRY:	The hardware is committed to idle mode. This period must run
+	to completion up to IDLE before anything else can happen.
+
+IDLE:	This is the actual energy-saving idle period. This may last
+	between 0 and infinite time, until a wake-up event occurs.
+
+EXIT:	Period during which the CPU is brought back to operational
+	mode (EXEC).
+
+entry-latency: Worst case latency required to enter the idle state. The
+exit-latency may be guaranteed only after entry-latency has passed.
+
+min-residency: Minimum period, including preparation and entry, for a given
+idle state to be worthwhile energywise.
+
+wakeup-latency: Maximum delay between the signaling of a wake-up event and the
+CPU being able to execute normal code again. If not specified, this is assumed
+to be entry-latency + exit-latency.
+
+These timing parameters can be used by an OS in different circumstances.
+
+An idle CPU requires the expected min-residency time to select the most
+appropriate idle state based on the expected expiry time of the next IRQ
+(ie wake-up) that causes the CPU to return to the EXEC phase.
+
+An operating system scheduler may need to compute the shortest wake-up delay
+for CPUs in the system by detecting how long will it take to get a CPU out
+of an idle state, eg:
+
+wakeup-delay = exit-latency + max(entry-latency - (now - entry-timestamp), 0)
+
+In other words, the scheduler can make its scheduling decision by selecting
+(eg waking-up) the CPU with the shortest wake-up latency.
+The wake-up latency must take into account the entry latency if that period
+has not expired. The abortable nature of the PREP period can be ignored
+if it cannot be relied upon (e.g. the PREP deadline may occur much sooner than
+the worst case since it depends on the CPU operating conditions, ie caches
+state).
+
+An OS has to reliably probe the wakeup-latency since some devices can enforce
+latency constraints guarantees to work properly, so the OS has to detect the
+worst case wake-up latency it can incur if a CPU is allowed to enter an
+idle state, and possibly to prevent that to guarantee reliable device
+functioning.
+
+The min-residency time parameter deserves further explanation since it is
+expressed in time units but must factor in energy consumption coefficients.
+
+The energy consumption of a cpu when it enters a power state can be roughly
+characterised by the following graph:
+
+               |
+               |
+               |
+           e   |
+           n   |                                      /---
+           e   |                               /------
+           r   |                        /------
+           g   |                  /-----
+           y   |           /------
+               |       ----
+               |      /|
+               |     / |
+               |    /  |
+               |   /   |
+               |  /    |
+               | /     |
+               |/      |
+          -----|-------+----------------------------------
+              0|       1                              time(ms)
+
+		Graph 1: Energy vs time example
+
+The graph is split in two parts delimited by time 1ms on the X-axis.
+The graph curve with X-axis values = { x | 0 < x < 1ms } has a steep slope
+and denotes the energy costs incurred whilst entering and leaving the idle
+state.
+The graph curve in the area delimited by X-axis values = {x | x > 1ms } has
+shallower slope and essentially represents the energy consumption of the idle
+state.
+
+min-residency is defined for a given idle state as the minimum expected
+residency time for a state (inclusive of preparation and entry) after
+which choosing that state become the most energy efficient option. A good
+way to visualise this, is by taking the same graph above and comparing some
+states energy consumptions plots.
+
+For sake of simplicity, let's consider a system with two idle states IDLE1,
+and IDLE2:
+
+          |
+          |
+          |
+          |                                                  /-- IDLE1
+       e  |                                              /---
+       n  |                                         /----
+       e  |                                     /---
+       r  |                                /-----/--------- IDLE2
+       g  |                    /-------/---------
+       y  |        ------------    /---|
+          |       /           /----    |
+          |      /        /---         |
+          |     /    /----             |
+          |    / /---                  |
+          |   ---                      |
+          |  /                         |
+          | /                          |
+          |/                           |                  time
+       ---/----------------------------+------------------------
+          |IDLE1-energy < IDLE2-energy | IDLE2-energy < IDLE1-energy
+                                       |
+                                IDLE2-min-residency
+
+		Graph 2: idle states min-residency example
+
+In graph 2 above, that takes into account idle states entry/exit energy
+costs, it is clear that if the idle state residency time (ie time till next
+wake-up IRQ) is less than IDLE2-min-residency, IDLE1 is the better idle state
+choice energywise.
+
+This is mainly down to the fact that IDLE1 entry/exit energy costs are lower
+than IDLE2.
+
+However, the lower power consumption (ie shallower energy curve slope) of idle
+state IDLE2 implies that after a suitable time, IDLE2 becomes more energy
+efficient.
+
+The time at which IDLE2 becomes more energy efficient than IDLE1 (and other
+shallower states in a system with multiple idle states) is defined
+IDLE2-min-residency and corresponds to the time when energy consumption of
+IDLE1 and IDLE2 states breaks even.
+
+The definitions provided in this section underpin the idle states
+properties specification that is the subject of the following sections.
+
+===========================================
+3 - idle-states node
+===========================================
+
+ARM processor idle states are defined within the idle-states node, which is
+a direct child of the cpus node [1] and provides a container where the
+processor idle states, defined as device tree nodes, are listed.
+
+- idle-states node
+
+	Usage: Optional - On ARM systems, it is a container of processor idle
+			  states nodes. If the system does not provide CPU
+			  power management capabilities or the processor just
+			  supports idle_standby an idle-states node is not
+			  required.
+
+	Description: idle-states node is a container node, where its
+		     subnodes describe the CPU idle states.
+
+	Node name must be "idle-states".
+
+	The idle-states node's parent node must be the cpus node.
+
+	The idle-states node's child nodes can be:
+
+	- one or more state nodes
+
+	Any other configuration is considered invalid.
+
+	An idle-states node defines the following properties:
+
+	- entry-method
+		Value type: <stringlist>
+		Usage and definition depend on ARM architecture version.
+			# On ARM v8 64-bit this property is required and must
+			  be one of:
+			   - "psci" (see bindings in [2])
+			# On ARM 32-bit systems this property is optional
+
+The nodes describing the idle states (state) can only be defined within the
+idle-states node, any other configuration is considered invalid and therefore
+must be ignored.
+
+===========================================
+4 - state node
+===========================================
+
+A state node represents an idle state description and must be defined as
+follows:
+
+- state node
+
+	Description: must be child of the idle-states node
+
+	The state node name shall follow standard device tree naming
+	rules ([5], 2.2.1 "Node names"), in particular state nodes which
+	are siblings within a single common parent must be given a unique name.
+
+	The idle state entered by executing the wfi instruction (idle_standby
+	SBSA,[3][4]) is considered standard on all ARM platforms and therefore
+	must not be listed.
+
+	With the definitions provided above, the following list represents
+	the valid properties for a state node:
+
+	- compatible
+		Usage: Required
+		Value type: <stringlist>
+		Definition: Must be "arm,idle-state".
+
+	- local-timer-stop
+		Usage: See definition
+		Value type: <none>
+		Definition: if present the CPU local timer control logic is
+			    lost on state entry, otherwise it is retained.
+
+	- entry-latency-us
+		Usage: Required
+		Value type: <prop-encoded-array>
+		Definition: u32 value representing worst case latency in
+			    microseconds required to enter the idle state.
+			    The exit-latency-us duration may be guaranteed
+			    only after entry-latency-us has passed.
+
+	- exit-latency-us
+		Usage: Required
+		Value type: <prop-encoded-array>
+		Definition: u32 value representing worst case latency
+			    in microseconds required to exit the idle state.
+
+	- min-residency-us
+		Usage: Required
+		Value type: <prop-encoded-array>
+		Definition: u32 value representing minimum residency duration
+			    in microseconds, inclusive of preparation and
+			    entry, for this idle state to be considered
+			    worthwhile energy wise (refer to section 2 of
+			    this document for a complete description).
+
+	- wakeup-latency-us:
+		Usage: Optional
+		Value type: <prop-encoded-array>
+		Definition: u32 value representing maximum delay between the
+			    signaling of a wake-up event and the CPU being
+			    able to execute normal code again. If omitted,
+			    this is assumed to be equal to:
+
+				entry-latency-us + exit-latency-us
+
+			    It is important to supply this value on systems
+			    where the duration of PREP phase (see diagram 1,
+			    section 2) is non-neglibigle.
+			    In such systems entry-latency-us + exit-latency-us
+			    will exceed wakeup-latency-us by this duration.
+
+	In addition to the properties listed above, a state node may require
+	additional properties specifics to the entry-method defined in the
+	idle-states node, please refer to the entry-method bindings
+	documentation for properties definitions.
+
+===========================================
+4 - Examples
+===========================================
+
+Example 1 (ARM 64-bit, 16-cpu system, PSCI enable-method):
+
+cpus {
+	#size-cells = <0>;
+	#address-cells = <2>;
+
+	CPU0: cpu@0 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x0 0x0>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU1: cpu@1 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x0 0x1>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU2: cpu@100 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x0 0x100>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU3: cpu@101 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x0 0x101>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU4: cpu@10000 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x0 0x10000>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU5: cpu@10001 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x0 0x10001>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU6: cpu@10100 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x0 0x10100>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU7: cpu@10101 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a57";
+		reg = <0x0 0x10101>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU8: cpu@100000000 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x1 0x0>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU9: cpu@100000001 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x1 0x1>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU10: cpu@100000100 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x1 0x100>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU11: cpu@100000101 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x1 0x101>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU12: cpu@100010000 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x1 0x10000>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU13: cpu@100010001 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x1 0x10001>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU14: cpu@100010100 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x1 0x10100>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU15: cpu@100010101 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a53";
+		reg = <0x1 0x10101>;
+		enable-method = "psci";
+		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+	};
+
+	idle-states {
+		entry-method = "arm,psci";
+
+		CPU_RETENTION_0_0: cpu-retention-0-0 {
+			compatible = "arm,idle-state";
+			arm,psci-suspend-param = <0x0010000>;
+			entry-latency-us = <20>;
+			exit-latency-us = <40>;
+			min-residency-us = <80>;
+		};
+
+		CLUSTER_RETENTION_0: cluster-retention-0 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			arm,psci-suspend-param = <0x1010000>;
+			entry-latency-us = <50>;
+			exit-latency-us = <100>;
+			min-residency-us = <250>;
+			wakeup-latency-us = <130>;
+		};
+
+		CPU_SLEEP_0_0: cpu-sleep-0-0 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			arm,psci-suspend-param = <0x0010000>;
+			entry-latency-us = <250>;
+			exit-latency-us = <500>;
+			min-residency-us = <950>;
+		};
+
+		CLUSTER_SLEEP_0: cluster-sleep-0 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			arm,psci-suspend-param = <0x1010000>;
+			entry-latency-us = <600>;
+			exit-latency-us = <1100>;
+			min-residency-us = <2700>;
+			wakeup-latency-us = <1500>;
+		};
+
+		CPU_RETENTION_1_0: cpu-retention-1-0 {
+			compatible = "arm,idle-state";
+			arm,psci-suspend-param = <0x0010000>;
+			entry-latency-us = <20>;
+			exit-latency-us = <40>;
+			min-residency-us = <90>;
+		};
+
+		CLUSTER_RETENTION_1: cluster-retention-1 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			arm,psci-suspend-param = <0x1010000>;
+			entry-latency-us = <50>;
+			exit-latency-us = <100>;
+			min-residency-us = <270>;
+			wakeup-latency-us = <100>;
+		};
+
+		CPU_SLEEP_1_0: cpu-sleep-1-0 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			arm,psci-suspend-param = <0x0010000>;
+			entry-latency-us = <70>;
+			exit-latency-us = <100>;
+			min-residency-us = <300>;
+			wakeup-latency-us = <150>;
+		};
+
+		CLUSTER_SLEEP_1: cluster-sleep-1 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			arm,psci-suspend-param = <0x1010000>;
+			entry-latency-us = <500>;
+			exit-latency-us = <1200>;
+			min-residency-us = <3500>;
+			wakeup-latency-us = <1300>;
+		};
+	};
+
+};
+
+Example 2 (ARM 32-bit, 8-cpu system, two clusters):
+
+cpus {
+	#size-cells = <0>;
+	#address-cells = <1>;
+
+	CPU0: cpu@0 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <0x0>;
+		cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU1: cpu@1 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <0x1>;
+		cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU2: cpu@2 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <0x2>;
+		cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU3: cpu@3 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <0x3>;
+		cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>;
+	};
+
+	CPU4: cpu@100 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a7";
+		reg = <0x100>;
+		cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU5: cpu@101 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a7";
+		reg = <0x101>;
+		cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU6: cpu@102 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a7";
+		reg = <0x102>;
+		cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>;
+	};
+
+	CPU7: cpu@103 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a7";
+		reg = <0x103>;
+		cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>;
+	};
+
+	idle-states {
+		CPU_SLEEP_0_0: cpu-sleep-0-0 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			entry-latency-us = <200>;
+			exit-latency-us = <100>;
+			min-residency-us = <400>;
+			wakeup-latency-us = <250>;
+		};
+
+		CLUSTER_SLEEP_0: cluster-sleep-0 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			entry-latency-us = <500>;
+			exit-latency-us = <1500>;
+			min-residency-us = <2500>;
+			wakeup-latency-us = <1700>;
+		};
+
+		CPU_SLEEP_1_0: cpu-sleep-1-0 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			entry-latency-us = <300>;
+			exit-latency-us = <500>;
+			min-residency-us = <900>;
+			wakeup-latency-us = <600>;
+		};
+
+		CLUSTER_SLEEP_1: cluster-sleep-1 {
+			compatible = "arm,idle-state";
+			local-timer-stop;
+			entry-latency-us = <800>;
+			exit-latency-us = <2000>;
+			min-residency-us = <6500>;
+			wakeup-latency-us = <2300>;
+		};
+	};
+
+};
+
+===========================================
+5 - References
+===========================================
+
+[1] ARM Linux Kernel documentation - CPUs bindings
+    Documentation/devicetree/bindings/arm/cpus.txt
+
+[2] ARM Linux Kernel documentation - PSCI bindings
+    Documentation/devicetree/bindings/arm/psci.txt
+
+[3] ARM Server Base System Architecture (SBSA)
+    http://infocenter.arm.com/help/index.jsp
+
+[4] ARM Architecture Reference Manuals
+    http://infocenter.arm.com/help/index.jsp
+
+[5] ePAPR standard
+    https://www.power.org/documentation/epapr-version-1-1/

Documentation/devicetree/bindings/arm/psci.txt

@@ -50,6 +50,16 @@ Main node optional properties:
 
  - migrate       : Function ID for MIGRATE operation
 
+Device tree nodes that require usage of PSCI CPU_SUSPEND function (ie idle
+state nodes, as per bindings in [1]) must specify the following properties:
+
+- arm,psci-suspend-param
+		Usage: Required for state nodes[1] if the corresponding
+                       idle-states node entry-method property is set
+                       to "psci".
+		Value type: <u32>
+		Definition: power_state parameter to pass to the PSCI
+			    suspend call.
 
 Example:
 
@@ -64,7 +74,6 @@ Case 1: PSCI v0.1 only.
 		migrate		= <0x95c10003>;
 	};
 
-
 Case 2: PSCI v0.2 only
 
 	psci {
@@ -88,3 +97,6 @@ Case 3: PSCI v0.2 and PSCI v0.1.
 
 		...
 	};
+
+[1] Kernel documentation - ARM idle states bindings
+    Documentation/devicetree/bindings/arm/idle-states.txt

Documentation/networking/filter.txt

@@ -462,9 +462,9 @@ JIT compiler
 ------------
 
 The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, PowerPC,
-ARM, MIPS and s390 and can be enabled through CONFIG_BPF_JIT. The JIT compiler
-is transparently invoked for each attached filter from user space or for
-internal kernel users if it has been previously enabled by root:
+ARM, ARM64, MIPS and s390 and can be enabled through CONFIG_BPF_JIT. The JIT
+compiler is transparently invoked for each attached filter from user space
+or for internal kernel users if it has been previously enabled by root:
 
   echo 1 > /proc/sys/net/core/bpf_jit_enable
 

arch/arm64/Kconfig

@@ -35,6 +35,7 @@ config ARM64
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_BPF_JIT
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_BUGVERBOSE
@@ -252,11 +253,11 @@ config SCHED_SMT
 	  places. If unsure say N here.
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-32)"
-	range 2 32
+	int "Maximum number of CPUs (2-64)"
+	range 2 64
 	depends on SMP
 	# These have to remain sorted largest to smallest
-	default "8"
+	default "64"
 
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"

arch/arm64/Kconfig.debug

@@ -43,4 +43,15 @@ config ARM64_RANDOMIZE_TEXT_OFFSET
 	  of TEXT_OFFSET and platforms must not require a specific
 	  value.
 
+config DEBUG_SET_MODULE_RONX
+        bool "Set loadable kernel module data as NX and text as RO"
+        depends on MODULES
+        help
+          This option helps catch unintended modifications to loadable
+          kernel module's text and read-only data. It also prevents execution
+          of module data. Such protection may interfere with run-time code
+          patching and dynamic kernel tracing - and they might also protect
+          against certain classes of kernel exploits.
+          If in doubt, say "N".
+
 endmenu

arch/arm64/Makefile

@@ -47,6 +47,7 @@ endif
 export	TEXT_OFFSET GZFLAGS
 
 core-y		+= arch/arm64/kernel/ arch/arm64/mm/
+core-$(CONFIG_NET) += arch/arm64/net/
 core-$(CONFIG_KVM) += arch/arm64/kvm/
 core-$(CONFIG_XEN) += arch/arm64/xen/
 core-$(CONFIG_CRYPTO) += arch/arm64/crypto/

arch/arm64/include/asm/cacheflush.h

@@ -148,4 +148,8 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
 }
 
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
 #endif

arch/arm64/include/asm/cachetype.h

@@ -39,6 +39,26 @@
 
 extern unsigned long __icache_flags;
 
+#define CCSIDR_EL1_LINESIZE_MASK	0x7
+#define CCSIDR_EL1_LINESIZE(x)		((x) & CCSIDR_EL1_LINESIZE_MASK)
+
+#define CCSIDR_EL1_NUMSETS_SHIFT	13
+#define CCSIDR_EL1_NUMSETS_MASK		(0x7fff << CCSIDR_EL1_NUMSETS_SHIFT)
+#define CCSIDR_EL1_NUMSETS(x) \
+	(((x) & CCSIDR_EL1_NUMSETS_MASK) >> CCSIDR_EL1_NUMSETS_SHIFT)
+
+extern u64 __attribute_const__ icache_get_ccsidr(void);
+
+static inline int icache_get_linesize(void)
+{
+	return 16 << CCSIDR_EL1_LINESIZE(icache_get_ccsidr());
+}
+
+static inline int icache_get_numsets(void)
+{
+	return 1 + CCSIDR_EL1_NUMSETS(icache_get_ccsidr());
+}
+
 /*
  * Whilst the D-side always behaves as PIPT on AArch64, aliasing is
  * permitted in the I-cache.

arch/arm64/include/asm/cpu_ops.h

@@ -28,6 +28,8 @@ struct device_node;
  *		enable-method property.
  * @cpu_init:	Reads any data necessary for a specific enable-method from the
  *		devicetree, for a given cpu node and proposed logical id.
+ * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
+ *		devicetree, for a given cpu node and proposed logical id.
  * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
  *		mechanism for doing so, tests whether it is possible to boot
  *		the given CPU.
@@ -47,6 +49,7 @@ struct device_node;
 struct cpu_operations {
 	const char	*name;
 	int		(*cpu_init)(struct device_node *, unsigned int);
+	int		(*cpu_init_idle)(struct device_node *, unsigned int);
 	int		(*cpu_prepare)(unsigned int);
 	int		(*cpu_boot)(unsigned int);
 	void		(*cpu_postboot)(void);
@@ -61,7 +64,7 @@ struct cpu_operations {
 };
 
 extern const struct cpu_operations *cpu_ops[NR_CPUS];
-extern int __init cpu_read_ops(struct device_node *dn, int cpu);
-extern void __init cpu_read_bootcpu_ops(void);
+int __init cpu_read_ops(struct device_node *dn, int cpu);
+void __init cpu_read_bootcpu_ops(void);
 
 #endif /* ifndef __ASM_CPU_OPS_H */

arch/arm64/include/asm/cpuidle.h

@@ -0,0 +1,13 @@
+#ifndef __ASM_CPUIDLE_H
+#define __ASM_CPUIDLE_H
+
+#ifdef CONFIG_CPU_IDLE
+extern int cpu_init_idle(unsigned int cpu);
+#else
+static inline int cpu_init_idle(unsigned int cpu)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif

arch/arm64/include/asm/debug-monitors.h

@@ -48,11 +48,13 @@
 /*
  * #imm16 values used for BRK instruction generation
  * Allowed values for kgbd are 0x400 - 0x7ff
+ * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
  * 0x401: for compile time BRK instruction
  */
-#define KGDB_DYN_DGB_BRK_IMM		0x400
-#define KDBG_COMPILED_DBG_BRK_IMM	0x401
+#define FAULT_BRK_IMM			0x100
+#define KGDB_DYN_DBG_BRK_IMM		0x400
+#define KGDB_COMPILED_DBG_BRK_IMM	0x401
 
 /*
  * BRK instruction encoding
@@ -60,25 +62,31 @@
  */
 #define AARCH64_BREAK_MON	0xd4200000
 
+/*
+ * BRK instruction for provoking a fault on purpose
+ * Unlike kgdb, #imm16 value with unallocated handler is used for faulting.
+ */
+#define AARCH64_BREAK_FAULT	(AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5))
+
 /*
  * Extract byte from BRK instruction
  */
-#define KGDB_DYN_DGB_BRK_INS_BYTE(x) \
+#define KGDB_DYN_DBG_BRK_INS_BYTE(x) \
 	((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
 
 /*
  * Extract byte from BRK #imm16
  */
-#define KGBD_DYN_DGB_BRK_IMM_BYTE(x) \
-	(((((KGDB_DYN_DGB_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
+#define KGBD_DYN_DBG_BRK_IMM_BYTE(x) \
+	(((((KGDB_DYN_DBG_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
 
-#define KGDB_DYN_DGB_BRK_BYTE(x) \
-	(KGDB_DYN_DGB_BRK_INS_BYTE(x) | KGBD_DYN_DGB_BRK_IMM_BYTE(x))
+#define KGDB_DYN_DBG_BRK_BYTE(x) \
+	(KGDB_DYN_DBG_BRK_INS_BYTE(x) | KGBD_DYN_DBG_BRK_IMM_BYTE(x))
 
-#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DGB_BRK_BYTE(0)
-#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DGB_BRK_BYTE(1)
-#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DGB_BRK_BYTE(2)
-#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DGB_BRK_BYTE(3)
+#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DBG_BRK_BYTE(0)
+#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DBG_BRK_BYTE(1)
+#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DBG_BRK_BYTE(2)
+#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DBG_BRK_BYTE(3)
 
 #define CACHE_FLUSH_IS_SAFE		1
 

arch/arm64/include/asm/dma-mapping.h

@@ -52,6 +52,13 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 	dev->archdata.dma_ops = ops;
 }
 
+static inline int set_arch_dma_coherent_ops(struct device *dev)
+{
+	set_dma_ops(dev, &coherent_swiotlb_dma_ops);
+	return 0;
+}
+#define set_arch_dma_coherent_ops	set_arch_dma_coherent_ops
+
 #include <asm-generic/dma-mapping-common.h>
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)

arch/arm64/include/asm/insn.h

@@ -2,6 +2,8 @@
  * Copyright (C) 2013 Huawei Ltd.
  * Author: Jiang Liu <liuj97@gmail.com>
  *
+ * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.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.
@@ -64,12 +66,155 @@ enum aarch64_insn_imm_type {
 	AARCH64_INSN_IMM_14,
 	AARCH64_INSN_IMM_12,
 	AARCH64_INSN_IMM_9,
+	AARCH64_INSN_IMM_7,
+	AARCH64_INSN_IMM_6,
+	AARCH64_INSN_IMM_S,
+	AARCH64_INSN_IMM_R,
 	AARCH64_INSN_IMM_MAX
 };
 
+enum aarch64_insn_register_type {
+	AARCH64_INSN_REGTYPE_RT,
+	AARCH64_INSN_REGTYPE_RN,
+	AARCH64_INSN_REGTYPE_RT2,
+	AARCH64_INSN_REGTYPE_RM,
+	AARCH64_INSN_REGTYPE_RD,
+	AARCH64_INSN_REGTYPE_RA,
+};
+
+enum aarch64_insn_register {
+	AARCH64_INSN_REG_0  = 0,
+	AARCH64_INSN_REG_1  = 1,
+	AARCH64_INSN_REG_2  = 2,
+	AARCH64_INSN_REG_3  = 3,
+	AARCH64_INSN_REG_4  = 4,
+	AARCH64_INSN_REG_5  = 5,
+	AARCH64_INSN_REG_6  = 6,
+	AARCH64_INSN_REG_7  = 7,
+	AARCH64_INSN_REG_8  = 8,
+	AARCH64_INSN_REG_9  = 9,
+	AARCH64_INSN_REG_10 = 10,
+	AARCH64_INSN_REG_11 = 11,
+	AARCH64_INSN_REG_12 = 12,
+	AARCH64_INSN_REG_13 = 13,
+	AARCH64_INSN_REG_14 = 14,
+	AARCH64_INSN_REG_15 = 15,
+	AARCH64_INSN_REG_16 = 16,
+	AARCH64_INSN_REG_17 = 17,
+	AARCH64_INSN_REG_18 = 18,
+	AARCH64_INSN_REG_19 = 19,
+	AARCH64_INSN_REG_20 = 20,
+	AARCH64_INSN_REG_21 = 21,
+	AARCH64_INSN_REG_22 = 22,
+	AARCH64_INSN_REG_23 = 23,
+	AARCH64_INSN_REG_24 = 24,
+	AARCH64_INSN_REG_25 = 25,
+	AARCH64_INSN_REG_26 = 26,
+	AARCH64_INSN_REG_27 = 27,
+	AARCH64_INSN_REG_28 = 28,
+	AARCH64_INSN_REG_29 = 29,
+	AARCH64_INSN_REG_FP = 29, /* Frame pointer */
+	AARCH64_INSN_REG_30 = 30,
+	AARCH64_INSN_REG_LR = 30, /* Link register */
+	AARCH64_INSN_REG_ZR = 31, /* Zero: as source register */
+	AARCH64_INSN_REG_SP = 31  /* Stack pointer: as load/store base reg */
+};
+
+enum aarch64_insn_variant {
+	AARCH64_INSN_VARIANT_32BIT,
+	AARCH64_INSN_VARIANT_64BIT
+};
+
+enum aarch64_insn_condition {
+	AARCH64_INSN_COND_EQ = 0x0, /* == */
+	AARCH64_INSN_COND_NE = 0x1, /* != */
+	AARCH64_INSN_COND_CS = 0x2, /* unsigned >= */
+	AARCH64_INSN_COND_CC = 0x3, /* unsigned < */
+	AARCH64_INSN_COND_MI = 0x4, /* < 0 */
+	AARCH64_INSN_COND_PL = 0x5, /* >= 0 */
+	AARCH64_INSN_COND_VS = 0x6, /* overflow */
+	AARCH64_INSN_COND_VC = 0x7, /* no overflow */
+	AARCH64_INSN_COND_HI = 0x8, /* unsigned > */
+	AARCH64_INSN_COND_LS = 0x9, /* unsigned <= */
+	AARCH64_INSN_COND_GE = 0xa, /* signed >= */
+	AARCH64_INSN_COND_LT = 0xb, /* signed < */
+	AARCH64_INSN_COND_GT = 0xc, /* signed > */
+	AARCH64_INSN_COND_LE = 0xd, /* signed <= */
+	AARCH64_INSN_COND_AL = 0xe, /* always */
+};
+
 enum aarch64_insn_branch_type {
 	AARCH64_INSN_BRANCH_NOLINK,
 	AARCH64_INSN_BRANCH_LINK,
+	AARCH64_INSN_BRANCH_RETURN,
+	AARCH64_INSN_BRANCH_COMP_ZERO,
+	AARCH64_INSN_BRANCH_COMP_NONZERO,
+};
+
+enum aarch64_insn_size_type {
+	AARCH64_INSN_SIZE_8,
+	AARCH64_INSN_SIZE_16,
+	AARCH64_INSN_SIZE_32,
+	AARCH64_INSN_SIZE_64,
+};
+
+enum aarch64_insn_ldst_type {
+	AARCH64_INSN_LDST_LOAD_REG_OFFSET,
+	AARCH64_INSN_LDST_STORE_REG_OFFSET,
+	AARCH64_INSN_LDST_LOAD_PAIR_PRE_INDEX,
+	AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
+	AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+};
+
+enum aarch64_insn_adsb_type {
+	AARCH64_INSN_ADSB_ADD,
+	AARCH64_INSN_ADSB_SUB,
+	AARCH64_INSN_ADSB_ADD_SETFLAGS,
+	AARCH64_INSN_ADSB_SUB_SETFLAGS
+};
+
+enum aarch64_insn_movewide_type {
+	AARCH64_INSN_MOVEWIDE_ZERO,
+	AARCH64_INSN_MOVEWIDE_KEEP,
+	AARCH64_INSN_MOVEWIDE_INVERSE
+};
+
+enum aarch64_insn_bitfield_type {
+	AARCH64_INSN_BITFIELD_MOVE,
+	AARCH64_INSN_BITFIELD_MOVE_UNSIGNED,
+	AARCH64_INSN_BITFIELD_MOVE_SIGNED
+};
+
+enum aarch64_insn_data1_type {
+	AARCH64_INSN_DATA1_REVERSE_16,
+	AARCH64_INSN_DATA1_REVERSE_32,
+	AARCH64_INSN_DATA1_REVERSE_64,
+};
+
+enum aarch64_insn_data2_type {
+	AARCH64_INSN_DATA2_UDIV,
+	AARCH64_INSN_DATA2_SDIV,
+	AARCH64_INSN_DATA2_LSLV,
+	AARCH64_INSN_DATA2_LSRV,
+	AARCH64_INSN_DATA2_ASRV,
+	AARCH64_INSN_DATA2_RORV,
+};
+
+enum aarch64_insn_data3_type {
+	AARCH64_INSN_DATA3_MADD,
+	AARCH64_INSN_DATA3_MSUB,
+};
+
+enum aarch64_insn_logic_type {
+	AARCH64_INSN_LOGIC_AND,
+	AARCH64_INSN_LOGIC_BIC,
+	AARCH64_INSN_LOGIC_ORR,
+	AARCH64_INSN_LOGIC_ORN,
+	AARCH64_INSN_LOGIC_EOR,
+	AARCH64_INSN_LOGIC_EON,
+	AARCH64_INSN_LOGIC_AND_SETFLAGS,
+	AARCH64_INSN_LOGIC_BIC_SETFLAGS
 };
 
 #define	__AARCH64_INSN_FUNCS(abbr, mask, val)	\
@@ -78,13 +223,58 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
 static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
 { return (val); }
 
+__AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
+__AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
+__AARCH64_INSN_FUNCS(stp_post,	0x7FC00000, 0x28800000)
+__AARCH64_INSN_FUNCS(ldp_post,	0x7FC00000, 0x28C00000)
+__AARCH64_INSN_FUNCS(stp_pre,	0x7FC00000, 0x29800000)
+__AARCH64_INSN_FUNCS(ldp_pre,	0x7FC00000, 0x29C00000)
+__AARCH64_INSN_FUNCS(add_imm,	0x7F000000, 0x11000000)
+__AARCH64_INSN_FUNCS(adds_imm,	0x7F000000, 0x31000000)
+__AARCH64_INSN_FUNCS(sub_imm,	0x7F000000, 0x51000000)
+__AARCH64_INSN_FUNCS(subs_imm,	0x7F000000, 0x71000000)
+__AARCH64_INSN_FUNCS(movn,	0x7F800000, 0x12800000)
+__AARCH64_INSN_FUNCS(sbfm,	0x7F800000, 0x13000000)
+__AARCH64_INSN_FUNCS(bfm,	0x7F800000, 0x33000000)
+__AARCH64_INSN_FUNCS(movz,	0x7F800000, 0x52800000)
+__AARCH64_INSN_FUNCS(ubfm,	0x7F800000, 0x53000000)
+__AARCH64_INSN_FUNCS(movk,	0x7F800000, 0x72800000)
+__AARCH64_INSN_FUNCS(add,	0x7F200000, 0x0B000000)
+__AARCH64_INSN_FUNCS(adds,	0x7F200000, 0x2B000000)
+__AARCH64_INSN_FUNCS(sub,	0x7F200000, 0x4B000000)
+__AARCH64_INSN_FUNCS(subs,	0x7F200000, 0x6B000000)
+__AARCH64_INSN_FUNCS(madd,	0x7FE08000, 0x1B000000)
+__AARCH64_INSN_FUNCS(msub,	0x7FE08000, 0x1B008000)
+__AARCH64_INSN_FUNCS(udiv,	0x7FE0FC00, 0x1AC00800)
+__AARCH64_INSN_FUNCS(sdiv,	0x7FE0FC00, 0x1AC00C00)
+__AARCH64_INSN_FUNCS(lslv,	0x7FE0FC00, 0x1AC02000)
+__AARCH64_INSN_FUNCS(lsrv,	0x7FE0FC00, 0x1AC02400)
+__AARCH64_INSN_FUNCS(asrv,	0x7FE0FC00, 0x1AC02800)
+__AARCH64_INSN_FUNCS(rorv,	0x7FE0FC00, 0x1AC02C00)
+__AARCH64_INSN_FUNCS(rev16,	0x7FFFFC00, 0x5AC00400)
+__AARCH64_INSN_FUNCS(rev32,	0x7FFFFC00, 0x5AC00800)
+__AARCH64_INSN_FUNCS(rev64,	0x7FFFFC00, 0x5AC00C00)
+__AARCH64_INSN_FUNCS(and,	0x7F200000, 0x0A000000)
+__AARCH64_INSN_FUNCS(bic,	0x7F200000, 0x0A200000)
+__AARCH64_INSN_FUNCS(orr,	0x7F200000, 0x2A000000)
+__AARCH64_INSN_FUNCS(orn,	0x7F200000, 0x2A200000)
+__AARCH64_INSN_FUNCS(eor,	0x7F200000, 0x4A000000)
+__AARCH64_INSN_FUNCS(eon,	0x7F200000, 0x4A200000)
+__AARCH64_INSN_FUNCS(ands,	0x7F200000, 0x6A000000)
+__AARCH64_INSN_FUNCS(bics,	0x7F200000, 0x6A200000)
 __AARCH64_INSN_FUNCS(b,		0xFC000000, 0x14000000)
 __AARCH64_INSN_FUNCS(bl,	0xFC000000, 0x94000000)
+__AARCH64_INSN_FUNCS(cbz,	0xFE000000, 0x34000000)
+__AARCH64_INSN_FUNCS(cbnz,	0xFE000000, 0x35000000)
+__AARCH64_INSN_FUNCS(bcond,	0xFF000010, 0x54000000)
 __AARCH64_INSN_FUNCS(svc,	0xFFE0001F, 0xD4000001)
 __AARCH64_INSN_FUNCS(hvc,	0xFFE0001F, 0xD4000002)
 __AARCH64_INSN_FUNCS(smc,	0xFFE0001F, 0xD4000003)
 __AARCH64_INSN_FUNCS(brk,	0xFFE0001F, 0xD4200000)
 __AARCH64_INSN_FUNCS(hint,	0xFFFFF01F, 0xD503201F)
+__AARCH64_INSN_FUNCS(br,	0xFFFFFC1F, 0xD61F0000)
+__AARCH64_INSN_FUNCS(blr,	0xFFFFFC1F, 0xD63F0000)
+__AARCH64_INSN_FUNCS(ret,	0xFFFFFC1F, 0xD65F0000)
 
 #undef	__AARCH64_INSN_FUNCS
 
@@ -97,8 +287,67 @@ u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 				  u32 insn, u64 imm);
 u32 aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
 				enum aarch64_insn_branch_type type);
+u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_register reg,
+				     enum aarch64_insn_variant variant,
+				     enum aarch64_insn_branch_type type);
+u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_condition cond);
 u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_op op);
 u32 aarch64_insn_gen_nop(void);
+u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
+				enum aarch64_insn_branch_type type);
+u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
+				    enum aarch64_insn_register base,
+				    enum aarch64_insn_register offset,
+				    enum aarch64_insn_size_type size,
+				    enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
+				     enum aarch64_insn_register reg2,
+				     enum aarch64_insn_register base,
+				     int offset,
+				     enum aarch64_insn_variant variant,
+				     enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
+				 enum aarch64_insn_register src,
+				 int imm, enum aarch64_insn_variant variant,
+				 enum aarch64_insn_adsb_type type);
+u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      int immr, int imms,
+			      enum aarch64_insn_variant variant,
+			      enum aarch64_insn_bitfield_type type);
+u32 aarch64_insn_gen_movewide(enum aarch64_insn_register dst,
+			      int imm, int shift,
+			      enum aarch64_insn_variant variant,
+			      enum aarch64_insn_movewide_type type);
+u32 aarch64_insn_gen_add_sub_shifted_reg(enum aarch64_insn_register dst,
+					 enum aarch64_insn_register src,
+					 enum aarch64_insn_register reg,
+					 int shift,
+					 enum aarch64_insn_variant variant,
+					 enum aarch64_insn_adsb_type type);
+u32 aarch64_insn_gen_data1(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data1_type type);
+u32 aarch64_insn_gen_data2(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_register reg,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data2_type type);
+u32 aarch64_insn_gen_data3(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_register reg1,
+			   enum aarch64_insn_register reg2,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data3_type type);
+u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
+					 enum aarch64_insn_register src,
+					 enum aarch64_insn_register reg,
+					 int shift,
+					 enum aarch64_insn_variant variant,
+					 enum aarch64_insn_logic_type type);
 
 bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
 

arch/arm64/include/asm/io.h

@@ -243,7 +243,7 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
  * (PHYS_OFFSET and PHYS_MASK taken into account).
  */
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
-extern int valid_phys_addr_range(unsigned long addr, size_t size);
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
 extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
 
 extern int devmem_is_allowed(unsigned long pfn);

arch/arm64/include/asm/kgdb.h

@@ -29,7 +29,7 @@
 
 static inline void arch_kgdb_breakpoint(void)
 {
-	asm ("brk %0" : : "I" (KDBG_COMPILED_DBG_BRK_IMM));
+	asm ("brk %0" : : "I" (KGDB_COMPILED_DBG_BRK_IMM));
 }
 
 extern void kgdb_handle_bus_error(void);

arch/arm64/include/asm/percpu.h

@@ -26,13 +26,13 @@ static inline void set_my_cpu_offset(unsigned long off)
 static inline unsigned long __my_cpu_offset(void)
 {
 	unsigned long off;
-	register unsigned long *sp asm ("sp");
 
 	/*
 	 * We want to allow caching the value, so avoid using volatile and
 	 * instead use a fake stack read to hazard against barrier().
 	 */
-	asm("mrs %0, tpidr_el1" : "=r" (off) : "Q" (*sp));
+	asm("mrs %0, tpidr_el1" : "=r" (off) :
+		"Q" (*(const unsigned long *)current_stack_pointer));
 
 	return off;
 }

arch/arm64/include/asm/pgtable.h

@@ -149,46 +149,51 @@ extern struct page *empty_zero_page;
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
-static inline pte_t pte_wrprotect(pte_t pte)
+static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
 {
-	pte_val(pte) &= ~PTE_WRITE;
+	pte_val(pte) &= ~pgprot_val(prot);
 	return pte;
 }
 
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
 {
-	pte_val(pte) |= PTE_WRITE;
+	pte_val(pte) |= pgprot_val(prot);
 	return pte;
 }
 
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_WRITE));
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_WRITE));
+}
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	pte_val(pte) &= ~PTE_DIRTY;
-	return pte;
+	return clear_pte_bit(pte, __pgprot(PTE_DIRTY));
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	pte_val(pte) |= PTE_DIRTY;
-	return pte;
+	return set_pte_bit(pte, __pgprot(PTE_DIRTY));
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-	pte_val(pte) &= ~PTE_AF;
-	return pte;
+	return clear_pte_bit(pte, __pgprot(PTE_AF));
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
 {
-	pte_val(pte) |= PTE_AF;
-	return pte;
+	return set_pte_bit(pte, __pgprot(PTE_AF));
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
 {
-	pte_val(pte) |= PTE_SPECIAL;
-	return pte;
+	return set_pte_bit(pte, __pgprot(PTE_SPECIAL));
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pte)

arch/arm64/include/asm/proc-fns.h

@@ -32,6 +32,8 @@ extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+void cpu_soft_restart(phys_addr_t cpu_reset,
+		unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 

arch/arm64/include/asm/suspend.h

@@ -21,6 +21,7 @@ struct sleep_save_sp {
 	phys_addr_t save_ptr_stash_phys;
 };
 
+extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
 extern void cpu_resume(void);
 extern int cpu_suspend(unsigned long);
 

arch/arm64/include/asm/thread_info.h

@@ -68,6 +68,11 @@ struct thread_info {
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 
+/*
+ * how to get the current stack pointer from C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
 /*
  * how to get the thread information struct from C
  */
@@ -75,8 +80,8 @@ static inline struct thread_info *current_thread_info(void) __attribute_const__;
 
 static inline struct thread_info *current_thread_info(void)
 {
-	register unsigned long sp asm ("sp");
-	return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
+	return (struct thread_info *)
+		(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
 #define thread_saved_pc(tsk)	\

arch/arm64/kernel/Makefile

@@ -26,6 +26,7 @@ arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)	+= sleep.o suspend.o
+arm64-obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o

arch/arm64/kernel/cpuidle.c

@@ -0,0 +1,31 @@
+/*
+ * ARM64 CPU idle arch support
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.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.
+ */
+
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+#include <asm/cpuidle.h>
+#include <asm/cpu_ops.h>
+
+int cpu_init_idle(unsigned int cpu)
+{
+	int ret = -EOPNOTSUPP;
+	struct device_node *cpu_node = of_cpu_device_node_get(cpu);
+
+	if (!cpu_node)
+		return -ENODEV;
+
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle)
+		ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu);
+
+	of_node_put(cpu_node);
+	return ret;
+}

arch/arm64/kernel/cpuinfo.c

@@ -20,8 +20,10 @@
 #include <asm/cputype.h>
 
 #include <linux/bitops.h>
+#include <linux/bug.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/preempt.h>
 #include <linux/printk.h>
 #include <linux/smp.h>
 
@@ -47,8 +49,18 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
 	unsigned int cpu = smp_processor_id();
 	u32 l1ip = CTR_L1IP(info->reg_ctr);
 
-	if (l1ip != ICACHE_POLICY_PIPT)
-		set_bit(ICACHEF_ALIASING, &__icache_flags);
+	if (l1ip != ICACHE_POLICY_PIPT) {
+		/*
+		 * VIPT caches are non-aliasing if the VA always equals the PA
+		 * in all bit positions that are covered by the index. This is
+		 * the case if the size of a way (# of sets * line size) does
+		 * not exceed PAGE_SIZE.
+		 */
+		u32 waysize = icache_get_numsets() * icache_get_linesize();
+
+		if (l1ip != ICACHE_POLICY_VIPT || waysize > PAGE_SIZE)
+			set_bit(ICACHEF_ALIASING, &__icache_flags);
+	}
 	if (l1ip == ICACHE_POLICY_AIVIVT)
 		set_bit(ICACHEF_AIVIVT, &__icache_flags);
 
@@ -190,3 +202,15 @@ void __init cpuinfo_store_boot_cpu(void)
 
 	boot_cpu_data = *info;
 }
+
+u64 __attribute_const__ icache_get_ccsidr(void)
+{
+	u64 ccsidr;
+
+	WARN_ON(preemptible());
+
+	/* Select L1 I-cache and read its size ID register */
+	asm("msr csselr_el1, %1; isb; mrs %0, ccsidr_el1"
+	    : "=r"(ccsidr) : "r"(1L));
+	return ccsidr;
+}

arch/arm64/kernel/efi-stub.c

@@ -28,20 +28,16 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 	kernel_size = _edata - _text;
 	if (*image_addr != (dram_base + TEXT_OFFSET)) {
 		kernel_memsize = kernel_size + (_end - _edata);
-		status = efi_relocate_kernel(sys_table, image_addr,
-					     kernel_size, kernel_memsize,
-					     dram_base + TEXT_OFFSET,
-					     PAGE_SIZE);
+		status = efi_low_alloc(sys_table, kernel_memsize + TEXT_OFFSET,
+				       SZ_2M, reserve_addr);
 		if (status != EFI_SUCCESS) {
 			pr_efi_err(sys_table, "Failed to relocate kernel\n");
 			return status;
 		}
-		if (*image_addr != (dram_base + TEXT_OFFSET)) {
-			pr_efi_err(sys_table, "Failed to alloc kernel memory\n");
-			efi_free(sys_table, kernel_memsize, *image_addr);
-			return EFI_LOAD_ERROR;
-		}
-		*image_size = kernel_memsize;
+		memcpy((void *)*reserve_addr + TEXT_OFFSET, (void *)*image_addr,
+		       kernel_size);
+		*image_addr = *reserve_addr + TEXT_OFFSET;
+		*reserve_size = kernel_memsize + TEXT_OFFSET;
 	}
 
 

arch/arm64/kernel/entry.S

@@ -324,7 +324,6 @@ el1_dbg:
 	mrs	x0, far_el1
 	mov	x2, sp				// struct pt_regs
 	bl	do_debug_exception
-	enable_dbg
 	kernel_exit 1
 el1_inv:
 	// TODO: add support for undefined instructions in kernel mode

arch/arm64/kernel/ftrace.c

@@ -58,7 +58,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	u32 new;
 
 	pc = (unsigned long)&ftrace_call;
-	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func, true);
+	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func,
+					  AARCH64_INSN_BRANCH_LINK);
 
 	return ftrace_modify_code(pc, 0, new, false);
 }
@@ -72,7 +73,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	u32 old, new;
 
 	old = aarch64_insn_gen_nop();
-	new = aarch64_insn_gen_branch_imm(pc, addr, true);
+	new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
 
 	return ftrace_modify_code(pc, old, new, true);
 }
@@ -86,7 +87,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	unsigned long pc = rec->ip;
 	u32 old, new;
 
-	old = aarch64_insn_gen_branch_imm(pc, addr, true);
+	old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
 	new = aarch64_insn_gen_nop();
 
 	return ftrace_modify_code(pc, old, new, true);
@@ -154,7 +155,8 @@ static int ftrace_modify_graph_caller(bool enable)
 	u32 branch, nop;
 
 	branch = aarch64_insn_gen_branch_imm(pc,
-			(unsigned long)ftrace_graph_caller, false);
+					     (unsigned long)ftrace_graph_caller,
+					     AARCH64_INSN_BRANCH_LINK);
 	nop = aarch64_insn_gen_nop();
 
 	if (enable)

arch/arm64/kernel/head.S

@@ -151,7 +151,7 @@ optional_header:
 	.short	0x20b				// PE32+ format
 	.byte	0x02				// MajorLinkerVersion
 	.byte	0x14				// MinorLinkerVersion
-	.long	_edata - stext			// SizeOfCode
+	.long	_end - stext			// SizeOfCode
 	.long	0				// SizeOfInitializedData
 	.long	0				// SizeOfUninitializedData
 	.long	efi_stub_entry - efi_head	// AddressOfEntryPoint
@@ -169,7 +169,7 @@ extra_header_fields:
 	.short	0				// MinorSubsystemVersion
 	.long	0				// Win32VersionValue
 
-	.long	_edata - efi_head		// SizeOfImage
+	.long	_end - efi_head			// SizeOfImage
 
 	// Everything before the kernel image is considered part of the header
 	.long	stext - efi_head		// SizeOfHeaders
@@ -216,7 +216,7 @@ section_table:
 	.byte	0
 	.byte	0
 	.byte	0        		// end of 0 padding of section name
-	.long	_edata - stext		// VirtualSize
+	.long	_end - stext		// VirtualSize
 	.long	stext - efi_head	// VirtualAddress
 	.long	_edata - stext		// SizeOfRawData
 	.long	stext - efi_head	// PointerToRawData

arch/arm64/kernel/insn.c

@@ -2,6 +2,8 @@
  * Copyright (C) 2013 Huawei Ltd.
  * Author: Jiang Liu <liuj97@gmail.com>
  *
+ * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.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.
@@ -20,9 +22,14 @@
 #include <linux/smp.h>
 #include <linux/stop_machine.h>
 #include <linux/uaccess.h>
+
 #include <asm/cacheflush.h>
+#include <asm/debug-monitors.h>
 #include <asm/insn.h>
 
+#define AARCH64_INSN_SF_BIT	BIT(31)
+#define AARCH64_INSN_N_BIT	BIT(22)
+
 static int aarch64_insn_encoding_class[] = {
 	AARCH64_INSN_CLS_UNKNOWN,
 	AARCH64_INSN_CLS_UNKNOWN,
@@ -251,6 +258,19 @@ u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 		mask = BIT(9) - 1;
 		shift = 12;
 		break;
+	case AARCH64_INSN_IMM_7:
+		mask = BIT(7) - 1;
+		shift = 15;
+		break;
+	case AARCH64_INSN_IMM_6:
+	case AARCH64_INSN_IMM_S:
+		mask = BIT(6) - 1;
+		shift = 10;
+		break;
+	case AARCH64_INSN_IMM_R:
+		mask = BIT(6) - 1;
+		shift = 16;
+		break;
 	default:
 		pr_err("aarch64_insn_encode_immediate: unknown immediate encoding %d\n",
 			type);
@@ -264,10 +284,76 @@ u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 	return insn;
 }
 
-u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
-					  enum aarch64_insn_branch_type type)
+static u32 aarch64_insn_encode_register(enum aarch64_insn_register_type type,
+					u32 insn,
+					enum aarch64_insn_register reg)
+{
+	int shift;
+
+	if (reg < AARCH64_INSN_REG_0 || reg > AARCH64_INSN_REG_SP) {
+		pr_err("%s: unknown register encoding %d\n", __func__, reg);
+		return 0;
+	}
+
+	switch (type) {
+	case AARCH64_INSN_REGTYPE_RT:
+	case AARCH64_INSN_REGTYPE_RD:
+		shift = 0;
+		break;
+	case AARCH64_INSN_REGTYPE_RN:
+		shift = 5;
+		break;
+	case AARCH64_INSN_REGTYPE_RT2:
+	case AARCH64_INSN_REGTYPE_RA:
+		shift = 10;
+		break;
+	case AARCH64_INSN_REGTYPE_RM:
+		shift = 16;
+		break;
+	default:
+		pr_err("%s: unknown register type encoding %d\n", __func__,
+		       type);
+		return 0;
+	}
+
+	insn &= ~(GENMASK(4, 0) << shift);
+	insn |= reg << shift;
+
+	return insn;
+}
+
+static u32 aarch64_insn_encode_ldst_size(enum aarch64_insn_size_type type,
+					 u32 insn)
+{
+	u32 size;
+
+	switch (type) {
+	case AARCH64_INSN_SIZE_8:
+		size = 0;
+		break;
+	case AARCH64_INSN_SIZE_16:
+		size = 1;
+		break;
+	case AARCH64_INSN_SIZE_32:
+		size = 2;
+		break;
+	case AARCH64_INSN_SIZE_64:
+		size = 3;
+		break;
+	default:
+		pr_err("%s: unknown size encoding %d\n", __func__, type);
+		return 0;
+	}
+
+	insn &= ~GENMASK(31, 30);
+	insn |= size << 30;
+
+	return insn;
+}
+
+static inline long branch_imm_common(unsigned long pc, unsigned long addr,
+				     long range)
 {
-	u32 insn;
 	long offset;
 
 	/*
@@ -276,23 +362,97 @@ u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
 	 */
 	BUG_ON((pc & 0x3) || (addr & 0x3));
 
+	offset = ((long)addr - (long)pc);
+	BUG_ON(offset < -range || offset >= range);
+
+	return offset;
+}
+
+u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
+					  enum aarch64_insn_branch_type type)
+{
+	u32 insn;
+	long offset;
+
 	/*
 	 * B/BL support [-128M, 128M) offset
 	 * ARM64 virtual address arrangement guarantees all kernel and module
 	 * texts are within +/-128M.
 	 */
-	offset = ((long)addr - (long)pc);
-	BUG_ON(offset < -SZ_128M || offset >= SZ_128M);
+	offset = branch_imm_common(pc, addr, SZ_128M);
 
-	if (type == AARCH64_INSN_BRANCH_LINK)
+	switch (type) {
+	case AARCH64_INSN_BRANCH_LINK:
 		insn = aarch64_insn_get_bl_value();
-	else
+		break;
+	case AARCH64_INSN_BRANCH_NOLINK:
 		insn = aarch64_insn_get_b_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
 
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn,
 					     offset >> 2);
 }
 
+u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_register reg,
+				     enum aarch64_insn_variant variant,
+				     enum aarch64_insn_branch_type type)
+{
+	u32 insn;
+	long offset;
+
+	offset = branch_imm_common(pc, addr, SZ_1M);
+
+	switch (type) {
+	case AARCH64_INSN_BRANCH_COMP_ZERO:
+		insn = aarch64_insn_get_cbz_value();
+		break;
+	case AARCH64_INSN_BRANCH_COMP_NONZERO:
+		insn = aarch64_insn_get_cbnz_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+					     offset >> 2);
+}
+
+u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_condition cond)
+{
+	u32 insn;
+	long offset;
+
+	offset = branch_imm_common(pc, addr, SZ_1M);
+
+	insn = aarch64_insn_get_bcond_value();
+
+	BUG_ON(cond < AARCH64_INSN_COND_EQ || cond > AARCH64_INSN_COND_AL);
+	insn |= cond;
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+					     offset >> 2);
+}
+
 u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_op op)
 {
 	return aarch64_insn_get_hint_value() | op;
@@ -302,3 +462,500 @@ u32 __kprobes aarch64_insn_gen_nop(void)
 {
 	return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP);
 }
+
+u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
+				enum aarch64_insn_branch_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_BRANCH_NOLINK:
+		insn = aarch64_insn_get_br_value();
+		break;
+	case AARCH64_INSN_BRANCH_LINK:
+		insn = aarch64_insn_get_blr_value();
+		break;
+	case AARCH64_INSN_BRANCH_RETURN:
+		insn = aarch64_insn_get_ret_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, reg);
+}
+
+u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
+				    enum aarch64_insn_register base,
+				    enum aarch64_insn_register offset,
+				    enum aarch64_insn_size_type size,
+				    enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_REG_OFFSET:
+		insn = aarch64_insn_get_ldr_reg_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_REG_OFFSET:
+		insn = aarch64_insn_get_str_reg_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn,
+					    offset);
+}
+
+u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
+				     enum aarch64_insn_register reg2,
+				     enum aarch64_insn_register base,
+				     int offset,
+				     enum aarch64_insn_variant variant,
+				     enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+	int shift;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_PAIR_PRE_INDEX:
+		insn = aarch64_insn_get_ldp_pre_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX:
+		insn = aarch64_insn_get_stp_pre_value();
+		break;
+	case AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX:
+		insn = aarch64_insn_get_ldp_post_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX:
+		insn = aarch64_insn_get_stp_post_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		/* offset must be multiples of 4 in the range [-256, 252] */
+		BUG_ON(offset & 0x3);
+		BUG_ON(offset < -256 || offset > 252);
+		shift = 2;
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		/* offset must be multiples of 8 in the range [-512, 504] */
+		BUG_ON(offset & 0x7);
+		BUG_ON(offset < -512 || offset > 504);
+		shift = 3;
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    reg1);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT2, insn,
+					    reg2);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_7, insn,
+					     offset >> shift);
+}
+
+u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
+				 enum aarch64_insn_register src,
+				 int imm, enum aarch64_insn_variant variant,
+				 enum aarch64_insn_adsb_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_ADSB_ADD:
+		insn = aarch64_insn_get_add_imm_value();
+		break;
+	case AARCH64_INSN_ADSB_SUB:
+		insn = aarch64_insn_get_sub_imm_value();
+		break;
+	case AARCH64_INSN_ADSB_ADD_SETFLAGS:
+		insn = aarch64_insn_get_adds_imm_value();
+		break;
+	case AARCH64_INSN_ADSB_SUB_SETFLAGS:
+		insn = aarch64_insn_get_subs_imm_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	BUG_ON(imm & ~(SZ_4K - 1));
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, imm);
+}
+
+u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      int immr, int imms,
+			      enum aarch64_insn_variant variant,
+			      enum aarch64_insn_bitfield_type type)
+{
+	u32 insn;
+	u32 mask;
+
+	switch (type) {
+	case AARCH64_INSN_BITFIELD_MOVE:
+		insn = aarch64_insn_get_bfm_value();
+		break;
+	case AARCH64_INSN_BITFIELD_MOVE_UNSIGNED:
+		insn = aarch64_insn_get_ubfm_value();
+		break;
+	case AARCH64_INSN_BITFIELD_MOVE_SIGNED:
+		insn = aarch64_insn_get_sbfm_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		mask = GENMASK(4, 0);
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT | AARCH64_INSN_N_BIT;
+		mask = GENMASK(5, 0);
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	BUG_ON(immr & ~mask);
+	BUG_ON(imms & ~mask);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_R, insn, immr);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, imms);
+}
+
+u32 aarch64_insn_gen_movewide(enum aarch64_insn_register dst,
+			      int imm, int shift,
+			      enum aarch64_insn_variant variant,
+			      enum aarch64_insn_movewide_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_MOVEWIDE_ZERO:
+		insn = aarch64_insn_get_movz_value();
+		break;
+	case AARCH64_INSN_MOVEWIDE_KEEP:
+		insn = aarch64_insn_get_movk_value();
+		break;
+	case AARCH64_INSN_MOVEWIDE_INVERSE:
+		insn = aarch64_insn_get_movn_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	BUG_ON(imm & ~(SZ_64K - 1));
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		BUG_ON(shift != 0 && shift != 16);
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		BUG_ON(shift != 0 && shift != 16 && shift != 32 &&
+		       shift != 48);
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn |= (shift >> 4) << 21;
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm);
+}
+
+u32 aarch64_insn_gen_add_sub_shifted_reg(enum aarch64_insn_register dst,
+					 enum aarch64_insn_register src,
+					 enum aarch64_insn_register reg,
+					 int shift,
+					 enum aarch64_insn_variant variant,
+					 enum aarch64_insn_adsb_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_ADSB_ADD:
+		insn = aarch64_insn_get_add_value();
+		break;
+	case AARCH64_INSN_ADSB_SUB:
+		insn = aarch64_insn_get_sub_value();
+		break;
+	case AARCH64_INSN_ADSB_ADD_SETFLAGS:
+		insn = aarch64_insn_get_adds_value();
+		break;
+	case AARCH64_INSN_ADSB_SUB_SETFLAGS:
+		insn = aarch64_insn_get_subs_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		BUG_ON(shift & ~(SZ_32 - 1));
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		BUG_ON(shift & ~(SZ_64 - 1));
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
+}
+
+u32 aarch64_insn_gen_data1(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data1_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_DATA1_REVERSE_16:
+		insn = aarch64_insn_get_rev16_value();
+		break;
+	case AARCH64_INSN_DATA1_REVERSE_32:
+		insn = aarch64_insn_get_rev32_value();
+		break;
+	case AARCH64_INSN_DATA1_REVERSE_64:
+		BUG_ON(variant != AARCH64_INSN_VARIANT_64BIT);
+		insn = aarch64_insn_get_rev64_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+}
+
+u32 aarch64_insn_gen_data2(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_register reg,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data2_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_DATA2_UDIV:
+		insn = aarch64_insn_get_udiv_value();
+		break;
+	case AARCH64_INSN_DATA2_SDIV:
+		insn = aarch64_insn_get_sdiv_value();
+		break;
+	case AARCH64_INSN_DATA2_LSLV:
+		insn = aarch64_insn_get_lslv_value();
+		break;
+	case AARCH64_INSN_DATA2_LSRV:
+		insn = aarch64_insn_get_lsrv_value();
+		break;
+	case AARCH64_INSN_DATA2_ASRV:
+		insn = aarch64_insn_get_asrv_value();
+		break;
+	case AARCH64_INSN_DATA2_RORV:
+		insn = aarch64_insn_get_rorv_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg);
+}
+
+u32 aarch64_insn_gen_data3(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_register reg1,
+			   enum aarch64_insn_register reg2,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data3_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_DATA3_MADD:
+		insn = aarch64_insn_get_madd_value();
+		break;
+	case AARCH64_INSN_DATA3_MSUB:
+		insn = aarch64_insn_get_msub_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RA, insn, src);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    reg1);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn,
+					    reg2);
+}
+
+u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
+					 enum aarch64_insn_register src,
+					 enum aarch64_insn_register reg,
+					 int shift,
+					 enum aarch64_insn_variant variant,
+					 enum aarch64_insn_logic_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LOGIC_AND:
+		insn = aarch64_insn_get_and_value();
+		break;
+	case AARCH64_INSN_LOGIC_BIC:
+		insn = aarch64_insn_get_bic_value();
+		break;
+	case AARCH64_INSN_LOGIC_ORR:
+		insn = aarch64_insn_get_orr_value();
+		break;
+	case AARCH64_INSN_LOGIC_ORN:
+		insn = aarch64_insn_get_orn_value();
+		break;
+	case AARCH64_INSN_LOGIC_EOR:
+		insn = aarch64_insn_get_eor_value();
+		break;
+	case AARCH64_INSN_LOGIC_EON:
+		insn = aarch64_insn_get_eon_value();
+		break;
+	case AARCH64_INSN_LOGIC_AND_SETFLAGS:
+		insn = aarch64_insn_get_ands_value();
+		break;
+	case AARCH64_INSN_LOGIC_BIC_SETFLAGS:
+		insn = aarch64_insn_get_bics_value();
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		BUG_ON(shift & ~(SZ_32 - 1));
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		BUG_ON(shift & ~(SZ_64 - 1));
+		break;
+	default:
+		BUG_ON(1);
+		return AARCH64_BREAK_FAULT;
+	}
+
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
+}

arch/arm64/kernel/kgdb.c

@@ -235,13 +235,13 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 
 static struct break_hook kgdb_brkpt_hook = {
 	.esr_mask	= 0xffffffff,
-	.esr_val	= DBG_ESR_VAL_BRK(KGDB_DYN_DGB_BRK_IMM),
+	.esr_val	= DBG_ESR_VAL_BRK(KGDB_DYN_DBG_BRK_IMM),
 	.fn		= kgdb_brk_fn
 };
 
 static struct break_hook kgdb_compiled_brkpt_hook = {
 	.esr_mask	= 0xffffffff,
-	.esr_val	= DBG_ESR_VAL_BRK(KDBG_COMPILED_DBG_BRK_IMM),
+	.esr_val	= DBG_ESR_VAL_BRK(KGDB_COMPILED_DBG_BRK_IMM),
 	.fn		= kgdb_compiled_brk_fn
 };
 

arch/arm64/kernel/perf_event.c

@@ -1276,7 +1276,7 @@ arch_initcall(cpu_pmu_reset);
 /*
  * PMU platform driver and devicetree bindings.
  */
-static struct of_device_id armpmu_of_device_ids[] = {
+static const struct of_device_id armpmu_of_device_ids[] = {
 	{.compatible = "arm,armv8-pmuv3"},
 	{},
 };

arch/arm64/kernel/process.c

@@ -57,36 +57,10 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
-static void setup_restart(void)
-{
-	/*
-	 * Tell the mm system that we are going to reboot -
-	 * we may need it to insert some 1:1 mappings so that
-	 * soft boot works.
-	 */
-	setup_mm_for_reboot();
-
-	/* Clean and invalidate caches */
-	flush_cache_all();
-
-	/* Turn D-cache off */
-	cpu_cache_off();
-
-	/* Push out any further dirty data, and ensure cache is empty */
-	flush_cache_all();
-}
-
 void soft_restart(unsigned long addr)
 {
-	typedef void (*phys_reset_t)(unsigned long);
-	phys_reset_t phys_reset;
-
-	setup_restart();
-
-	/* Switch to the identity mapping */
-	phys_reset = (phys_reset_t)virt_to_phys(cpu_reset);
-	phys_reset(addr);
-
+	setup_mm_for_reboot();
+	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
 	/* Should never get here */
 	BUG();
 }

arch/arm64/kernel/psci.c

@@ -21,6 +21,7 @@
 #include <linux/reboot.h>
 #include <linux/pm.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 #include <uapi/linux/psci.h>
 
 #include <asm/compiler.h>
@@ -28,6 +29,7 @@
 #include <asm/errno.h>
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
+#include <asm/suspend.h>
 #include <asm/system_misc.h>
 
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
@@ -65,6 +67,8 @@ enum psci_function {
 	PSCI_FN_MAX,
 };
 
+static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state);
+
 static u32 psci_function_id[PSCI_FN_MAX];
 
 static int psci_to_linux_errno(int errno)
@@ -93,6 +97,18 @@ static u32 psci_power_state_pack(struct psci_power_state state)
 		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
 }
 
+static void psci_power_state_unpack(u32 power_state,
+				    struct psci_power_state *state)
+{
+	state->id = (power_state & PSCI_0_2_POWER_STATE_ID_MASK) >>
+			PSCI_0_2_POWER_STATE_ID_SHIFT;
+	state->type = (power_state & PSCI_0_2_POWER_STATE_TYPE_MASK) >>
+			PSCI_0_2_POWER_STATE_TYPE_SHIFT;
+	state->affinity_level =
+			(power_state & PSCI_0_2_POWER_STATE_AFFL_MASK) >>
+			PSCI_0_2_POWER_STATE_AFFL_SHIFT;
+}
+
 /*
  * The following two functions are invoked via the invoke_psci_fn pointer
  * and will not be inlined, allowing us to piggyback on the AAPCS.
@@ -199,6 +215,63 @@ static int psci_migrate_info_type(void)
 	return err;
 }
 
+static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
+						 unsigned int cpu)
+{
+	int i, ret, count = 0;
+	struct psci_power_state *psci_states;
+	struct device_node *state_node;
+
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	/* Count idle states */
+	while ((state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
+					      count))) {
+		count++;
+		of_node_put(state_node);
+	}
+
+	if (!count)
+		return -ENODEV;
+
+	psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL);
+	if (!psci_states)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		u32 psci_power_state;
+
+		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
+
+		ret = of_property_read_u32(state_node,
+					   "arm,psci-suspend-param",
+					   &psci_power_state);
+		if (ret) {
+			pr_warn(" * %s missing arm,psci-suspend-param property\n",
+				state_node->full_name);
+			of_node_put(state_node);
+			goto free_mem;
+		}
+
+		of_node_put(state_node);
+		pr_debug("psci-power-state %#x index %d\n", psci_power_state,
+							    i);
+		psci_power_state_unpack(psci_power_state, &psci_states[i]);
+	}
+	/* Idle states parsed correctly, initialize per-cpu pointer */
+	per_cpu(psci_power_state, cpu) = psci_states;
+	return 0;
+
+free_mem:
+	kfree(psci_states);
+	return ret;
+}
+
 static int get_set_conduit_method(struct device_node *np)
 {
 	const char *method;
@@ -436,8 +509,39 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 #endif
 #endif
 
+static int psci_suspend_finisher(unsigned long index)
+{
+	struct psci_power_state *state = __get_cpu_var(psci_power_state);
+
+	return psci_ops.cpu_suspend(state[index - 1],
+				    virt_to_phys(cpu_resume));
+}
+
+static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index)
+{
+	int ret;
+	struct psci_power_state *state = __get_cpu_var(psci_power_state);
+	/*
+	 * idle state index 0 corresponds to wfi, should never be called
+	 * from the cpu_suspend operations
+	 */
+	if (WARN_ON_ONCE(!index))
+		return -EINVAL;
+
+	if (state->type == PSCI_POWER_STATE_TYPE_STANDBY)
+		ret = psci_ops.cpu_suspend(state[index - 1], 0);
+	else
+		ret = __cpu_suspend(index, psci_suspend_finisher);
+
+	return ret;
+}
+
 const struct cpu_operations cpu_psci_ops = {
 	.name		= "psci",
+#ifdef CONFIG_CPU_IDLE
+	.cpu_init_idle	= cpu_psci_cpu_init_idle,
+	.cpu_suspend	= cpu_psci_cpu_suspend,
+#endif
 #ifdef CONFIG_SMP
 	.cpu_init	= cpu_psci_cpu_init,
 	.cpu_prepare	= cpu_psci_cpu_prepare,

arch/arm64/kernel/return_address.c

@@ -36,13 +36,12 @@ void *return_address(unsigned int level)
 {
 	struct return_address_data data;
 	struct stackframe frame;
-	register unsigned long current_sp asm ("sp");
 
 	data.level = level + 2;
 	data.addr = NULL;
 
 	frame.fp = (unsigned long)__builtin_frame_address(0);
-	frame.sp = current_sp;
+	frame.sp = current_stack_pointer;
 	frame.pc = (unsigned long)return_address; /* dummy */
 
 	walk_stackframe(&frame, save_return_addr, &data);

arch/arm64/kernel/setup.c

@@ -365,11 +365,6 @@ u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
 {
-	/*
-	 * Unmask asynchronous aborts early to catch possible system errors.
-	 */
-	local_async_enable();
-
 	setup_processor();
 
 	setup_machine_fdt(__fdt_pointer);
@@ -385,6 +380,12 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+	/*
+	 *  Unmask asynchronous aborts after bringing up possible earlycon.
+	 * (Report possible System Errors once we can report this occurred)
+	 */
+	local_async_enable();
+
 	efi_init();
 	arm64_memblock_init();
 

arch/arm64/kernel/sleep.S

@@ -49,28 +49,39 @@
 	orr	\dst, \dst, \mask		// dst|=(aff3>>rs3)
 	.endm
 /*
- * Save CPU state for a suspend.  This saves callee registers, and allocates
- * space on the kernel stack to save the CPU specific registers + some
- * other data for resume.
+ * Save CPU state for a suspend and execute the suspend finisher.
+ * On success it will return 0 through cpu_resume - ie through a CPU
+ * soft/hard reboot from the reset vector.
+ * On failure it returns the suspend finisher return value or force
+ * -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher
+ * is not allowed to return, if it does this must be considered failure).
+ * It saves callee registers, and allocates space on the kernel stack
+ * to save the CPU specific registers + some other data for resume.
  *
  *  x0 = suspend finisher argument
+ *  x1 = suspend finisher function pointer
  */
-ENTRY(__cpu_suspend)
+ENTRY(__cpu_suspend_enter)
 	stp	x29, lr, [sp, #-96]!
 	stp	x19, x20, [sp,#16]
 	stp	x21, x22, [sp,#32]
 	stp	x23, x24, [sp,#48]
 	stp	x25, x26, [sp,#64]
 	stp	x27, x28, [sp,#80]
+	/*
+	 * Stash suspend finisher and its argument in x20 and x19
+	 */
+	mov	x19, x0
+	mov	x20, x1
 	mov	x2, sp
 	sub	sp, sp, #CPU_SUSPEND_SZ	// allocate cpu_suspend_ctx
-	mov	x1, sp
+	mov	x0, sp
 	/*
-	 * x1 now points to struct cpu_suspend_ctx allocated on the stack
+	 * x0 now points to struct cpu_suspend_ctx allocated on the stack
 	 */
-	str	x2, [x1, #CPU_CTX_SP]
-	ldr	x2, =sleep_save_sp
-	ldr	x2, [x2, #SLEEP_SAVE_SP_VIRT]
+	str	x2, [x0, #CPU_CTX_SP]
+	ldr	x1, =sleep_save_sp
+	ldr	x1, [x1, #SLEEP_SAVE_SP_VIRT]
 #ifdef CONFIG_SMP
 	mrs	x7, mpidr_el1
 	ldr	x9, =mpidr_hash
@@ -82,11 +93,21 @@ ENTRY(__cpu_suspend)
 	ldp	w3, w4, [x9, #MPIDR_HASH_SHIFTS]
 	ldp	w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
-	add	x2, x2, x8, lsl #3
+	add	x1, x1, x8, lsl #3
 #endif
-	bl	__cpu_suspend_finisher
+	bl	__cpu_suspend_save
+	/*
+	 * Grab suspend finisher in x20 and its argument in x19
+	 */
+	mov	x0, x19
+	mov	x1, x20
+	/*
+	 * We are ready for power down, fire off the suspend finisher
+	 * in x1, with argument in x0
+	 */
+	blr	x1
         /*
-	 * Never gets here, unless suspend fails.
+	 * Never gets here, unless suspend finisher fails.
 	 * Successful cpu_suspend should return from cpu_resume, returning
 	 * through this code path is considered an error
 	 * If the return value is set to 0 force x0 = -EOPNOTSUPP
@@ -103,7 +124,7 @@ ENTRY(__cpu_suspend)
 	ldp	x27, x28, [sp, #80]
 	ldp	x29, lr, [sp], #96
 	ret
-ENDPROC(__cpu_suspend)
+ENDPROC(__cpu_suspend_enter)
 	.ltorg
 
 /*

arch/arm64/kernel/smp_spin_table.c

@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
+#include <linux/types.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
@@ -65,12 +66,21 @@ static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
 
 static int smp_spin_table_cpu_prepare(unsigned int cpu)
 {
-	void **release_addr;
+	__le64 __iomem *release_addr;
 
 	if (!cpu_release_addr[cpu])
 		return -ENODEV;
 
-	release_addr = __va(cpu_release_addr[cpu]);
+	/*
+	 * The cpu-release-addr may or may not be inside the linear mapping.
+	 * As ioremap_cache will either give us a new mapping or reuse the
+	 * existing linear mapping, we can use it to cover both cases. In
+	 * either case the memory will be MT_NORMAL.
+	 */
+	release_addr = ioremap_cache(cpu_release_addr[cpu],
+				     sizeof(*release_addr));
+	if (!release_addr)
+		return -ENOMEM;
 
 	/*
 	 * We write the release address as LE regardless of the native
@@ -79,15 +89,17 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 	 * boot-loader's endianess before jumping. This is mandated by
 	 * the boot protocol.
 	 */
-	release_addr[0] = (void *) cpu_to_le64(__pa(secondary_holding_pen));
-
-	__flush_dcache_area(release_addr, sizeof(release_addr[0]));
+	writeq_relaxed(__pa(secondary_holding_pen), release_addr);
+	__flush_dcache_area((__force void *)release_addr,
+			    sizeof(*release_addr));
 
 	/*
 	 * Send an event to wake up the secondary CPU.
 	 */
 	sev();
 
+	iounmap(release_addr);
+
 	return 0;
 }
 

arch/arm64/kernel/stacktrace.c

@@ -111,10 +111,9 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		frame.sp = thread_saved_sp(tsk);
 		frame.pc = thread_saved_pc(tsk);
 	} else {
-		register unsigned long current_sp asm("sp");
 		data.no_sched_functions = 0;
 		frame.fp = (unsigned long)__builtin_frame_address(0);
-		frame.sp = current_sp;
+		frame.sp = current_stack_pointer;
 		frame.pc = (unsigned long)save_stack_trace_tsk;
 	}
 

arch/arm64/kernel/suspend.c

@@ -9,22 +9,19 @@
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-extern int __cpu_suspend(unsigned long);
+extern int __cpu_suspend_enter(unsigned long arg, int (*fn)(unsigned long));
 /*
- * This is called by __cpu_suspend() to save the state, and do whatever
+ * This is called by __cpu_suspend_enter() to save the state, and do whatever
  * flushing is required to ensure that when the CPU goes to sleep we have
  * the necessary data available when the caches are not searched.
  *
- * @arg: Argument to pass to suspend operations
- * @ptr: CPU context virtual address
- * @save_ptr: address of the location where the context physical address
- *            must be saved
+ * ptr: CPU context virtual address
+ * save_ptr: address of the location where the context physical address
+ *           must be saved
  */
-int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
-			   phys_addr_t *save_ptr)
+void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr,
+				phys_addr_t *save_ptr)
 {
-	int cpu = smp_processor_id();
-
 	*save_ptr = virt_to_phys(ptr);
 
 	cpu_do_suspend(ptr);
@@ -35,8 +32,6 @@ int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
 	 */
 	__flush_dcache_area(ptr, sizeof(*ptr));
 	__flush_dcache_area(save_ptr, sizeof(*save_ptr));
-
-	return cpu_ops[cpu]->cpu_suspend(arg);
 }
 
 /*
@@ -56,15 +51,15 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 }
 
 /**
- * cpu_suspend
+ * cpu_suspend() - function to enter a low-power state
+ * @arg: argument to pass to CPU suspend operations
  *
- * @arg: argument to pass to the finisher function
+ * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
+ * operations back-end error code otherwise.
  */
 int cpu_suspend(unsigned long arg)
 {
-	struct mm_struct *mm = current->active_mm;
-	int ret, cpu = smp_processor_id();
-	unsigned long flags;
+	int cpu = smp_processor_id();
 
 	/*
 	 * If cpu_ops have not been registered or suspend
@@ -72,6 +67,21 @@ int cpu_suspend(unsigned long arg)
 	 */
 	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
 		return -EOPNOTSUPP;
+	return cpu_ops[cpu]->cpu_suspend(arg);
+}
+
+/*
+ * __cpu_suspend
+ *
+ * arg: argument to pass to the finisher function
+ * fn: finisher function pointer
+ *
+ */
+int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret;
+	unsigned long flags;
 
 	/*
 	 * From this point debug exceptions are disabled to prevent
@@ -86,7 +96,7 @@ int cpu_suspend(unsigned long arg)
 	 * page tables, so that the thread address space is properly
 	 * set-up on function return.
 	 */
-	ret = __cpu_suspend(arg);
+	ret = __cpu_suspend_enter(arg, fn);
 	if (ret == 0) {
 		cpu_switch_mm(mm->pgd, mm);
 		flush_tlb_all();
@@ -95,7 +105,7 @@ int cpu_suspend(unsigned long arg)
 		 * Restore per-cpu offset before any kernel
 		 * subsystem relying on it has a chance to run.
 		 */
-		set_my_cpu_offset(per_cpu_offset(cpu));
+		set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 
 		/*
 		 * Restore HW breakpoint registers to sane values

arch/arm64/kernel/traps.c

@@ -132,7 +132,6 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
-	const register unsigned long current_sp asm ("sp");
 
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
@@ -145,7 +144,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		frame.pc = regs->pc;
 	} else if (tsk == current) {
 		frame.fp = (unsigned long)__builtin_frame_address(0);
-		frame.sp = current_sp;
+		frame.sp = current_stack_pointer;
 		frame.pc = (unsigned long)dump_backtrace;
 	} else {
 		/*

arch/arm64/mm/Makefile

@@ -1,5 +1,5 @@
 obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   cache.o copypage.o flush.o \
 				   ioremap.o mmap.o pgd.o mmu.o \
-				   context.o proc.o
+				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o

arch/arm64/mm/dma-mapping.c

@@ -22,11 +22,8 @@
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
-#include <linux/amba/bus.h>
 
 #include <asm/cacheflush.h>
 
@@ -125,7 +122,7 @@ static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
 no_map:
 	__dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
 no_mem:
-	*dma_handle = ~0;
+	*dma_handle = DMA_ERROR_CODE;
 	return NULL;
 }
 
@@ -308,40 +305,12 @@ struct dma_map_ops coherent_swiotlb_dma_ops = {
 };
 EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
 
-static int dma_bus_notifier(struct notifier_block *nb,
-			    unsigned long event, void *_dev)
-{
-	struct device *dev = _dev;
-
-	if (event != BUS_NOTIFY_ADD_DEVICE)
-		return NOTIFY_DONE;
-
-	if (of_property_read_bool(dev->of_node, "dma-coherent"))
-		set_dma_ops(dev, &coherent_swiotlb_dma_ops);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block platform_bus_nb = {
-	.notifier_call = dma_bus_notifier,
-};
-
-static struct notifier_block amba_bus_nb = {
-	.notifier_call = dma_bus_notifier,
-};
-
 extern int swiotlb_late_init_with_default_size(size_t default_size);
 
 static int __init swiotlb_late_init(void)
 {
 	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
 
-	/*
-	 * These must be registered before of_platform_populate().
-	 */
-	bus_register_notifier(&platform_bus_type, &platform_bus_nb);
-	bus_register_notifier(&amba_bustype, &amba_bus_nb);
-
 	dma_ops = &noncoherent_swiotlb_dma_ops;
 
 	return swiotlb_late_init_with_default_size(swiotlb_size);

arch/arm64/mm/init.c

@@ -255,7 +255,7 @@ static void __init free_unused_memmap(void)
  */
 void __init mem_init(void)
 {
-	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
+	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 	free_unused_memmap();

arch/arm64/mm/mmap.c

@@ -102,7 +102,7 @@ EXPORT_SYMBOL_GPL(arch_pick_mmap_layout);
  * You really shouldn't be using read() or write() on /dev/mem.  This might go
  * away in the future.
  */
-int valid_phys_addr_range(unsigned long addr, size_t size)
+int valid_phys_addr_range(phys_addr_t addr, size_t size)
 {
 	if (addr < PHYS_OFFSET)
 		return 0;

arch/arm64/mm/mmu.c

@@ -94,7 +94,7 @@ static int __init early_cachepolicy(char *p)
 	 */
 	asm volatile(
 	"	mrs	%0, mair_el1\n"
-	"	bfi	%0, %1, #%2, #8\n"
+	"	bfi	%0, %1, %2, #8\n"
 	"	msr	mair_el1, %0\n"
 	"	isb\n"
 	: "=&r" (tmp)

arch/arm64/mm/pageattr.c

@@ -0,0 +1,97 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. 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 and
+ * only 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.
+ */
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+struct page_change_data {
+	pgprot_t set_mask;
+	pgprot_t clear_mask;
+};
+
+static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
+			void *data)
+{
+	struct page_change_data *cdata = data;
+	pte_t pte = *ptep;
+
+	pte = clear_pte_bit(pte, cdata->clear_mask);
+	pte = set_pte_bit(pte, cdata->set_mask);
+
+	set_pte(ptep, pte);
+	return 0;
+}
+
+static int change_memory_common(unsigned long addr, int numpages,
+				pgprot_t set_mask, pgprot_t clear_mask)
+{
+	unsigned long start = addr;
+	unsigned long size = PAGE_SIZE*numpages;
+	unsigned long end = start + size;
+	int ret;
+	struct page_change_data data;
+
+	if (!IS_ALIGNED(addr, PAGE_SIZE)) {
+		start &= PAGE_MASK;
+		end = start + size;
+		WARN_ON_ONCE(1);
+	}
+
+	if (!is_module_address(start) || !is_module_address(end - 1))
+		return -EINVAL;
+
+	data.set_mask = set_mask;
+	data.clear_mask = clear_mask;
+
+	ret = apply_to_page_range(&init_mm, start, size, change_page_range,
+					&data);
+
+	flush_tlb_kernel_range(start, end);
+	return ret;
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+	return change_memory_common(addr, numpages,
+					__pgprot(PTE_RDONLY),
+					__pgprot(PTE_WRITE));
+}
+EXPORT_SYMBOL_GPL(set_memory_ro);
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+	return change_memory_common(addr, numpages,
+					__pgprot(PTE_WRITE),
+					__pgprot(PTE_RDONLY));
+}
+EXPORT_SYMBOL_GPL(set_memory_rw);
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+	return change_memory_common(addr, numpages,
+					__pgprot(PTE_PXN),
+					__pgprot(0));
+}
+EXPORT_SYMBOL_GPL(set_memory_nx);
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+	return change_memory_common(addr, numpages,
+					__pgprot(0),
+					__pgprot(PTE_PXN));
+}
+EXPORT_SYMBOL_GPL(set_memory_x);

arch/arm64/mm/proc.S

@@ -76,6 +76,21 @@ ENTRY(cpu_reset)
 	ret	x0
 ENDPROC(cpu_reset)
 
+ENTRY(cpu_soft_restart)
+	/* Save address of cpu_reset() and reset address */
+	mov	x19, x0
+	mov	x20, x1
+
+	/* Turn D-cache off */
+	bl	cpu_cache_off
+
+	/* Push out all dirty data, and ensure cache is empty */
+	bl	flush_cache_all
+
+	mov	x0, x20
+	ret	x19
+ENDPROC(cpu_soft_restart)
+
 /*
  *	cpu_do_idle()
  *

arch/arm64/net/Makefile

@@ -0,0 +1,4 @@
+#
+# ARM64 networking code
+#
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o

arch/arm64/net/bpf_jit.h

@@ -0,0 +1,169 @@
+/*
+ * BPF JIT compiler for ARM64
+ *
+ * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.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/>.
+ */
+#ifndef _BPF_JIT_H
+#define _BPF_JIT_H
+
+#include <asm/insn.h>
+
+/* 5-bit Register Operand */
+#define A64_R(x)	AARCH64_INSN_REG_##x
+#define A64_FP		AARCH64_INSN_REG_FP
+#define A64_LR		AARCH64_INSN_REG_LR
+#define A64_ZR		AARCH64_INSN_REG_ZR
+#define A64_SP		AARCH64_INSN_REG_SP
+
+#define A64_VARIANT(sf) \
+	((sf) ? AARCH64_INSN_VARIANT_64BIT : AARCH64_INSN_VARIANT_32BIT)
+
+/* Compare & branch (immediate) */
+#define A64_COMP_BRANCH(sf, Rt, offset, type) \
+	aarch64_insn_gen_comp_branch_imm(0, offset, Rt, A64_VARIANT(sf), \
+		AARCH64_INSN_BRANCH_COMP_##type)
+#define A64_CBZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, ZERO)
+
+/* Conditional branch (immediate) */
+#define A64_COND_BRANCH(cond, offset) \
+	aarch64_insn_gen_cond_branch_imm(0, offset, cond)
+#define A64_COND_EQ	AARCH64_INSN_COND_EQ /* == */
+#define A64_COND_NE	AARCH64_INSN_COND_NE /* != */
+#define A64_COND_CS	AARCH64_INSN_COND_CS /* unsigned >= */
+#define A64_COND_HI	AARCH64_INSN_COND_HI /* unsigned > */
+#define A64_COND_GE	AARCH64_INSN_COND_GE /* signed >= */
+#define A64_COND_GT	AARCH64_INSN_COND_GT /* signed > */
+#define A64_B_(cond, imm19) A64_COND_BRANCH(cond, (imm19) << 2)
+
+/* Unconditional branch (immediate) */
+#define A64_BRANCH(offset, type) aarch64_insn_gen_branch_imm(0, offset, \
+	AARCH64_INSN_BRANCH_##type)
+#define A64_B(imm26)  A64_BRANCH((imm26) << 2, NOLINK)
+#define A64_BL(imm26) A64_BRANCH((imm26) << 2, LINK)
+
+/* Unconditional branch (register) */
+#define A64_BLR(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_LINK)
+#define A64_RET(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_RETURN)
+
+/* Load/store register (register offset) */
+#define A64_LS_REG(Rt, Rn, Rm, size, type) \
+	aarch64_insn_gen_load_store_reg(Rt, Rn, Rm, \
+		AARCH64_INSN_SIZE_##size, \
+		AARCH64_INSN_LDST_##type##_REG_OFFSET)
+#define A64_STRB(Wt, Xn, Xm)  A64_LS_REG(Wt, Xn, Xm, 8, STORE)
+#define A64_LDRB(Wt, Xn, Xm)  A64_LS_REG(Wt, Xn, Xm, 8, LOAD)
+#define A64_STRH(Wt, Xn, Xm)  A64_LS_REG(Wt, Xn, Xm, 16, STORE)
+#define A64_LDRH(Wt, Xn, Xm)  A64_LS_REG(Wt, Xn, Xm, 16, LOAD)
+#define A64_STR32(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 32, STORE)
+#define A64_LDR32(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 32, LOAD)
+#define A64_STR64(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 64, STORE)
+#define A64_LDR64(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 64, LOAD)
+
+/* Load/store register pair */
+#define A64_LS_PAIR(Rt, Rt2, Rn, offset, ls, type) \
+	aarch64_insn_gen_load_store_pair(Rt, Rt2, Rn, offset, \
+		AARCH64_INSN_VARIANT_64BIT, \
+		AARCH64_INSN_LDST_##ls##_PAIR_##type)
+/* Rn -= 16; Rn[0] = Rt; Rn[8] = Rt2; */
+#define A64_PUSH(Rt, Rt2, Rn) A64_LS_PAIR(Rt, Rt2, Rn, -16, STORE, PRE_INDEX)
+/* Rt = Rn[0]; Rt2 = Rn[8]; Rn += 16; */
+#define A64_POP(Rt, Rt2, Rn)  A64_LS_PAIR(Rt, Rt2, Rn, 16, LOAD, POST_INDEX)
+
+/* Add/subtract (immediate) */
+#define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \
+	aarch64_insn_gen_add_sub_imm(Rd, Rn, imm12, \
+		A64_VARIANT(sf), AARCH64_INSN_ADSB_##type)
+/* Rd = Rn OP imm12 */
+#define A64_ADD_I(sf, Rd, Rn, imm12) A64_ADDSUB_IMM(sf, Rd, Rn, imm12, ADD)
+#define A64_SUB_I(sf, Rd, Rn, imm12) A64_ADDSUB_IMM(sf, Rd, Rn, imm12, SUB)
+/* Rd = Rn */
+#define A64_MOV(sf, Rd, Rn) A64_ADD_I(sf, Rd, Rn, 0)
+
+/* Bitfield move */
+#define A64_BITFIELD(sf, Rd, Rn, immr, imms, type) \
+	aarch64_insn_gen_bitfield(Rd, Rn, immr, imms, \
+		A64_VARIANT(sf), AARCH64_INSN_BITFIELD_MOVE_##type)
+/* Signed, with sign replication to left and zeros to right */
+#define A64_SBFM(sf, Rd, Rn, ir, is) A64_BITFIELD(sf, Rd, Rn, ir, is, SIGNED)
+/* Unsigned, with zeros to left and right */
+#define A64_UBFM(sf, Rd, Rn, ir, is) A64_BITFIELD(sf, Rd, Rn, ir, is, UNSIGNED)
+
+/* Rd = Rn << shift */
+#define A64_LSL(sf, Rd, Rn, shift) ({	\
+	int sz = (sf) ? 64 : 32;	\
+	A64_UBFM(sf, Rd, Rn, (unsigned)-(shift) % sz, sz - 1 - (shift)); \
+})
+/* Rd = Rn >> shift */
+#define A64_LSR(sf, Rd, Rn, shift) A64_UBFM(sf, Rd, Rn, shift, (sf) ? 63 : 31)
+/* Rd = Rn >> shift; signed */
+#define A64_ASR(sf, Rd, Rn, shift) A64_SBFM(sf, Rd, Rn, shift, (sf) ? 63 : 31)
+
+/* Move wide (immediate) */
+#define A64_MOVEW(sf, Rd, imm16, shift, type) \
+	aarch64_insn_gen_movewide(Rd, imm16, shift, \
+		A64_VARIANT(sf), AARCH64_INSN_MOVEWIDE_##type)
+/* Rd = Zeros (for MOVZ);
+ * Rd |= imm16 << shift (where shift is {0, 16, 32, 48});
+ * Rd = ~Rd; (for MOVN); */
+#define A64_MOVN(sf, Rd, imm16, shift) A64_MOVEW(sf, Rd, imm16, shift, INVERSE)
+#define A64_MOVZ(sf, Rd, imm16, shift) A64_MOVEW(sf, Rd, imm16, shift, ZERO)
+#define A64_MOVK(sf, Rd, imm16, shift) A64_MOVEW(sf, Rd, imm16, shift, KEEP)
+
+/* Add/subtract (shifted register) */
+#define A64_ADDSUB_SREG(sf, Rd, Rn, Rm, type) \
+	aarch64_insn_gen_add_sub_shifted_reg(Rd, Rn, Rm, 0, \
+		A64_VARIANT(sf), AARCH64_INSN_ADSB_##type)
+/* Rd = Rn OP Rm */
+#define A64_ADD(sf, Rd, Rn, Rm)  A64_ADDSUB_SREG(sf, Rd, Rn, Rm, ADD)
+#define A64_SUB(sf, Rd, Rn, Rm)  A64_ADDSUB_SREG(sf, Rd, Rn, Rm, SUB)
+#define A64_SUBS(sf, Rd, Rn, Rm) A64_ADDSUB_SREG(sf, Rd, Rn, Rm, SUB_SETFLAGS)
+/* Rd = -Rm */
+#define A64_NEG(sf, Rd, Rm) A64_SUB(sf, Rd, A64_ZR, Rm)
+/* Rn - Rm; set condition flags */
+#define A64_CMP(sf, Rn, Rm) A64_SUBS(sf, A64_ZR, Rn, Rm)
+
+/* Data-processing (1 source) */
+#define A64_DATA1(sf, Rd, Rn, type) aarch64_insn_gen_data1(Rd, Rn, \
+	A64_VARIANT(sf), AARCH64_INSN_DATA1_##type)
+/* Rd = BSWAPx(Rn) */
+#define A64_REV16(sf, Rd, Rn) A64_DATA1(sf, Rd, Rn, REVERSE_16)
+#define A64_REV32(sf, Rd, Rn) A64_DATA1(sf, Rd, Rn, REVERSE_32)
+#define A64_REV64(Rd, Rn)     A64_DATA1(1, Rd, Rn, REVERSE_64)
+
+/* Data-processing (2 source) */
+/* Rd = Rn OP Rm */
+#define A64_UDIV(sf, Rd, Rn, Rm) aarch64_insn_gen_data2(Rd, Rn, Rm, \
+	A64_VARIANT(sf), AARCH64_INSN_DATA2_UDIV)
+
+/* Data-processing (3 source) */
+/* Rd = Ra + Rn * Rm */
+#define A64_MADD(sf, Rd, Ra, Rn, Rm) aarch64_insn_gen_data3(Rd, Ra, Rn, Rm, \
+	A64_VARIANT(sf), AARCH64_INSN_DATA3_MADD)
+/* Rd = Rn * Rm */
+#define A64_MUL(sf, Rd, Rn, Rm) A64_MADD(sf, Rd, A64_ZR, Rn, Rm)
+
+/* Logical (shifted register) */
+#define A64_LOGIC_SREG(sf, Rd, Rn, Rm, type) \
+	aarch64_insn_gen_logical_shifted_reg(Rd, Rn, Rm, 0, \
+		A64_VARIANT(sf), AARCH64_INSN_LOGIC_##type)
+/* Rd = Rn OP Rm */
+#define A64_AND(sf, Rd, Rn, Rm)  A64_LOGIC_SREG(sf, Rd, Rn, Rm, AND)
+#define A64_ORR(sf, Rd, Rn, Rm)  A64_LOGIC_SREG(sf, Rd, Rn, Rm, ORR)
+#define A64_EOR(sf, Rd, Rn, Rm)  A64_LOGIC_SREG(sf, Rd, Rn, Rm, EOR)
+#define A64_ANDS(sf, Rd, Rn, Rm) A64_LOGIC_SREG(sf, Rd, Rn, Rm, AND_SETFLAGS)
+/* Rn & Rm; set condition flags */
+#define A64_TST(sf, Rn, Rm) A64_ANDS(sf, A64_ZR, Rn, Rm)
+
+#endif /* _BPF_JIT_H */

arch/arm64/net/bpf_jit_comp.c

@@ -0,0 +1,679 @@
+/*
+ * BPF JIT compiler for ARM64
+ *
+ * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.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/>.
+ */
+
+#define pr_fmt(fmt) "bpf_jit: " fmt
+
+#include <linux/filter.h>
+#include <linux/moduleloader.h>
+#include <linux/printk.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <asm/byteorder.h>
+#include <asm/cacheflush.h>
+
+#include "bpf_jit.h"
+
+int bpf_jit_enable __read_mostly;
+
+#define TMP_REG_1 (MAX_BPF_REG + 0)
+#define TMP_REG_2 (MAX_BPF_REG + 1)
+
+/* Map BPF registers to A64 registers */
+static const int bpf2a64[] = {
+	/* return value from in-kernel function, and exit value from eBPF */
+	[BPF_REG_0] = A64_R(7),
+	/* arguments from eBPF program to in-kernel function */
+	[BPF_REG_1] = A64_R(0),
+	[BPF_REG_2] = A64_R(1),
+	[BPF_REG_3] = A64_R(2),
+	[BPF_REG_4] = A64_R(3),
+	[BPF_REG_5] = A64_R(4),
+	/* callee saved registers that in-kernel function will preserve */
+	[BPF_REG_6] = A64_R(19),
+	[BPF_REG_7] = A64_R(20),
+	[BPF_REG_8] = A64_R(21),
+	[BPF_REG_9] = A64_R(22),
+	/* read-only frame pointer to access stack */
+	[BPF_REG_FP] = A64_FP,
+	/* temporary register for internal BPF JIT */
+	[TMP_REG_1] = A64_R(23),
+	[TMP_REG_2] = A64_R(24),
+};
+
+struct jit_ctx {
+	const struct bpf_prog *prog;
+	int idx;
+	int tmp_used;
+	int body_offset;
+	int *offset;
+	u32 *image;
+};
+
+static inline void emit(const u32 insn, struct jit_ctx *ctx)
+{
+	if (ctx->image != NULL)
+		ctx->image[ctx->idx] = cpu_to_le32(insn);
+
+	ctx->idx++;
+}
+
+static inline void emit_a64_mov_i64(const int reg, const u64 val,
+				    struct jit_ctx *ctx)
+{
+	u64 tmp = val;
+	int shift = 0;
+
+	emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
+	tmp >>= 16;
+	shift += 16;
+	while (tmp) {
+		if (tmp & 0xffff)
+			emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
+		tmp >>= 16;
+		shift += 16;
+	}
+}
+
+static inline void emit_a64_mov_i(const int is64, const int reg,
+				  const s32 val, struct jit_ctx *ctx)
+{
+	u16 hi = val >> 16;
+	u16 lo = val & 0xffff;
+
+	if (hi & 0x8000) {
+		if (hi == 0xffff) {
+			emit(A64_MOVN(is64, reg, (u16)~lo, 0), ctx);
+		} else {
+			emit(A64_MOVN(is64, reg, (u16)~hi, 16), ctx);
+			emit(A64_MOVK(is64, reg, lo, 0), ctx);
+		}
+	} else {
+		emit(A64_MOVZ(is64, reg, lo, 0), ctx);
+		if (hi)
+			emit(A64_MOVK(is64, reg, hi, 16), ctx);
+	}
+}
+
+static inline int bpf2a64_offset(int bpf_to, int bpf_from,
+				 const struct jit_ctx *ctx)
+{
+	int to = ctx->offset[bpf_to + 1];
+	/* -1 to account for the Branch instruction */
+	int from = ctx->offset[bpf_from + 1] - 1;
+
+	return to - from;
+}
+
+static inline int epilogue_offset(const struct jit_ctx *ctx)
+{
+	int to = ctx->offset[ctx->prog->len - 1];
+	int from = ctx->idx - ctx->body_offset;
+
+	return to - from;
+}
+
+/* Stack must be multiples of 16B */
+#define STACK_ALIGN(sz) (((sz) + 15) & ~15)
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+	const u8 r6 = bpf2a64[BPF_REG_6];
+	const u8 r7 = bpf2a64[BPF_REG_7];
+	const u8 r8 = bpf2a64[BPF_REG_8];
+	const u8 r9 = bpf2a64[BPF_REG_9];
+	const u8 fp = bpf2a64[BPF_REG_FP];
+	const u8 ra = bpf2a64[BPF_REG_A];
+	const u8 rx = bpf2a64[BPF_REG_X];
+	const u8 tmp1 = bpf2a64[TMP_REG_1];
+	const u8 tmp2 = bpf2a64[TMP_REG_2];
+	int stack_size = MAX_BPF_STACK;
+
+	stack_size += 4; /* extra for skb_copy_bits buffer */
+	stack_size = STACK_ALIGN(stack_size);
+
+	/* Save callee-saved register */
+	emit(A64_PUSH(r6, r7, A64_SP), ctx);
+	emit(A64_PUSH(r8, r9, A64_SP), ctx);
+	if (ctx->tmp_used)
+		emit(A64_PUSH(tmp1, tmp2, A64_SP), ctx);
+
+	/* Set up BPF stack */
+	emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx);
+
+	/* Set up frame pointer */
+	emit(A64_MOV(1, fp, A64_SP), ctx);
+
+	/* Clear registers A and X */
+	emit_a64_mov_i64(ra, 0, ctx);
+	emit_a64_mov_i64(rx, 0, ctx);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	const u8 r0 = bpf2a64[BPF_REG_0];
+	const u8 r6 = bpf2a64[BPF_REG_6];
+	const u8 r7 = bpf2a64[BPF_REG_7];
+	const u8 r8 = bpf2a64[BPF_REG_8];
+	const u8 r9 = bpf2a64[BPF_REG_9];
+	const u8 fp = bpf2a64[BPF_REG_FP];
+	const u8 tmp1 = bpf2a64[TMP_REG_1];
+	const u8 tmp2 = bpf2a64[TMP_REG_2];
+	int stack_size = MAX_BPF_STACK;
+
+	stack_size += 4; /* extra for skb_copy_bits buffer */
+	stack_size = STACK_ALIGN(stack_size);
+
+	/* We're done with BPF stack */
+	emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx);
+
+	/* Restore callee-saved register */
+	if (ctx->tmp_used)
+		emit(A64_POP(tmp1, tmp2, A64_SP), ctx);
+	emit(A64_POP(r8, r9, A64_SP), ctx);
+	emit(A64_POP(r6, r7, A64_SP), ctx);
+
+	/* Restore frame pointer */
+	emit(A64_MOV(1, fp, A64_SP), ctx);
+
+	/* Set return value */
+	emit(A64_MOV(1, A64_R(0), r0), ctx);
+
+	emit(A64_RET(A64_LR), ctx);
+}
+
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const u8 code = insn->code;
+	const u8 dst = bpf2a64[insn->dst_reg];
+	const u8 src = bpf2a64[insn->src_reg];
+	const u8 tmp = bpf2a64[TMP_REG_1];
+	const u8 tmp2 = bpf2a64[TMP_REG_2];
+	const s16 off = insn->off;
+	const s32 imm = insn->imm;
+	const int i = insn - ctx->prog->insnsi;
+	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
+	u8 jmp_cond;
+	s32 jmp_offset;
+
+	switch (code) {
+	/* dst = src */
+	case BPF_ALU | BPF_MOV | BPF_X:
+	case BPF_ALU64 | BPF_MOV | BPF_X:
+		emit(A64_MOV(is64, dst, src), ctx);
+		break;
+	/* dst = dst OP src */
+	case BPF_ALU | BPF_ADD | BPF_X:
+	case BPF_ALU64 | BPF_ADD | BPF_X:
+		emit(A64_ADD(is64, dst, dst, src), ctx);
+		break;
+	case BPF_ALU | BPF_SUB | BPF_X:
+	case BPF_ALU64 | BPF_SUB | BPF_X:
+		emit(A64_SUB(is64, dst, dst, src), ctx);
+		break;
+	case BPF_ALU | BPF_AND | BPF_X:
+	case BPF_ALU64 | BPF_AND | BPF_X:
+		emit(A64_AND(is64, dst, dst, src), ctx);
+		break;
+	case BPF_ALU | BPF_OR | BPF_X:
+	case BPF_ALU64 | BPF_OR | BPF_X:
+		emit(A64_ORR(is64, dst, dst, src), ctx);
+		break;
+	case BPF_ALU | BPF_XOR | BPF_X:
+	case BPF_ALU64 | BPF_XOR | BPF_X:
+		emit(A64_EOR(is64, dst, dst, src), ctx);
+		break;
+	case BPF_ALU | BPF_MUL | BPF_X:
+	case BPF_ALU64 | BPF_MUL | BPF_X:
+		emit(A64_MUL(is64, dst, dst, src), ctx);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_X:
+	case BPF_ALU64 | BPF_DIV | BPF_X:
+		emit(A64_UDIV(is64, dst, dst, src), ctx);
+		break;
+	case BPF_ALU | BPF_MOD | BPF_X:
+	case BPF_ALU64 | BPF_MOD | BPF_X:
+		ctx->tmp_used = 1;
+		emit(A64_UDIV(is64, tmp, dst, src), ctx);
+		emit(A64_MUL(is64, tmp, tmp, src), ctx);
+		emit(A64_SUB(is64, dst, dst, tmp), ctx);
+		break;
+	/* dst = -dst */
+	case BPF_ALU | BPF_NEG:
+	case BPF_ALU64 | BPF_NEG:
+		emit(A64_NEG(is64, dst, dst), ctx);
+		break;
+	/* dst = BSWAP##imm(dst) */
+	case BPF_ALU | BPF_END | BPF_FROM_LE:
+	case BPF_ALU | BPF_END | BPF_FROM_BE:
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		if (BPF_SRC(code) == BPF_FROM_BE)
+			break;
+#else /* !CONFIG_CPU_BIG_ENDIAN */
+		if (BPF_SRC(code) == BPF_FROM_LE)
+			break;
+#endif
+		switch (imm) {
+		case 16:
+			emit(A64_REV16(is64, dst, dst), ctx);
+			break;
+		case 32:
+			emit(A64_REV32(is64, dst, dst), ctx);
+			break;
+		case 64:
+			emit(A64_REV64(dst, dst), ctx);
+			break;
+		}
+		break;
+	/* dst = imm */
+	case BPF_ALU | BPF_MOV | BPF_K:
+	case BPF_ALU64 | BPF_MOV | BPF_K:
+		emit_a64_mov_i(is64, dst, imm, ctx);
+		break;
+	/* dst = dst OP imm */
+	case BPF_ALU | BPF_ADD | BPF_K:
+	case BPF_ALU64 | BPF_ADD | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_ADD(is64, dst, dst, tmp), ctx);
+		break;
+	case BPF_ALU | BPF_SUB | BPF_K:
+	case BPF_ALU64 | BPF_SUB | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_SUB(is64, dst, dst, tmp), ctx);
+		break;
+	case BPF_ALU | BPF_AND | BPF_K:
+	case BPF_ALU64 | BPF_AND | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_AND(is64, dst, dst, tmp), ctx);
+		break;
+	case BPF_ALU | BPF_OR | BPF_K:
+	case BPF_ALU64 | BPF_OR | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_ORR(is64, dst, dst, tmp), ctx);
+		break;
+	case BPF_ALU | BPF_XOR | BPF_K:
+	case BPF_ALU64 | BPF_XOR | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_EOR(is64, dst, dst, tmp), ctx);
+		break;
+	case BPF_ALU | BPF_MUL | BPF_K:
+	case BPF_ALU64 | BPF_MUL | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_MUL(is64, dst, dst, tmp), ctx);
+		break;
+	case BPF_ALU | BPF_DIV | BPF_K:
+	case BPF_ALU64 | BPF_DIV | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_UDIV(is64, dst, dst, tmp), ctx);
+		break;
+	case BPF_ALU | BPF_MOD | BPF_K:
+	case BPF_ALU64 | BPF_MOD | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(is64, tmp2, imm, ctx);
+		emit(A64_UDIV(is64, tmp, dst, tmp2), ctx);
+		emit(A64_MUL(is64, tmp, tmp, tmp2), ctx);
+		emit(A64_SUB(is64, dst, dst, tmp), ctx);
+		break;
+	case BPF_ALU | BPF_LSH | BPF_K:
+	case BPF_ALU64 | BPF_LSH | BPF_K:
+		emit(A64_LSL(is64, dst, dst, imm), ctx);
+		break;
+	case BPF_ALU | BPF_RSH | BPF_K:
+	case BPF_ALU64 | BPF_RSH | BPF_K:
+		emit(A64_LSR(is64, dst, dst, imm), ctx);
+		break;
+	case BPF_ALU | BPF_ARSH | BPF_K:
+	case BPF_ALU64 | BPF_ARSH | BPF_K:
+		emit(A64_ASR(is64, dst, dst, imm), ctx);
+		break;
+
+#define check_imm(bits, imm) do {				\
+	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
+	    (((imm) < 0) && (~(imm) >> (bits)))) {		\
+		pr_info("[%2d] imm=%d(0x%x) out of range\n",	\
+			i, imm, imm);				\
+		return -EINVAL;					\
+	}							\
+} while (0)
+#define check_imm19(imm) check_imm(19, imm)
+#define check_imm26(imm) check_imm(26, imm)
+
+	/* JUMP off */
+	case BPF_JMP | BPF_JA:
+		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		check_imm26(jmp_offset);
+		emit(A64_B(jmp_offset), ctx);
+		break;
+	/* IF (dst COND src) JUMP off */
+	case BPF_JMP | BPF_JEQ | BPF_X:
+	case BPF_JMP | BPF_JGT | BPF_X:
+	case BPF_JMP | BPF_JGE | BPF_X:
+	case BPF_JMP | BPF_JNE | BPF_X:
+	case BPF_JMP | BPF_JSGT | BPF_X:
+	case BPF_JMP | BPF_JSGE | BPF_X:
+		emit(A64_CMP(1, dst, src), ctx);
+emit_cond_jmp:
+		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		check_imm19(jmp_offset);
+		switch (BPF_OP(code)) {
+		case BPF_JEQ:
+			jmp_cond = A64_COND_EQ;
+			break;
+		case BPF_JGT:
+			jmp_cond = A64_COND_HI;
+			break;
+		case BPF_JGE:
+			jmp_cond = A64_COND_CS;
+			break;
+		case BPF_JNE:
+			jmp_cond = A64_COND_NE;
+			break;
+		case BPF_JSGT:
+			jmp_cond = A64_COND_GT;
+			break;
+		case BPF_JSGE:
+			jmp_cond = A64_COND_GE;
+			break;
+		default:
+			return -EFAULT;
+		}
+		emit(A64_B_(jmp_cond, jmp_offset), ctx);
+		break;
+	case BPF_JMP | BPF_JSET | BPF_X:
+		emit(A64_TST(1, dst, src), ctx);
+		goto emit_cond_jmp;
+	/* IF (dst COND imm) JUMP off */
+	case BPF_JMP | BPF_JEQ | BPF_K:
+	case BPF_JMP | BPF_JGT | BPF_K:
+	case BPF_JMP | BPF_JGE | BPF_K:
+	case BPF_JMP | BPF_JNE | BPF_K:
+	case BPF_JMP | BPF_JSGT | BPF_K:
+	case BPF_JMP | BPF_JSGE | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(1, tmp, imm, ctx);
+		emit(A64_CMP(1, dst, tmp), ctx);
+		goto emit_cond_jmp;
+	case BPF_JMP | BPF_JSET | BPF_K:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(1, tmp, imm, ctx);
+		emit(A64_TST(1, dst, tmp), ctx);
+		goto emit_cond_jmp;
+	/* function call */
+	case BPF_JMP | BPF_CALL:
+	{
+		const u8 r0 = bpf2a64[BPF_REG_0];
+		const u64 func = (u64)__bpf_call_base + imm;
+
+		ctx->tmp_used = 1;
+		emit_a64_mov_i64(tmp, func, ctx);
+		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
+		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
+		emit(A64_BLR(tmp), ctx);
+		emit(A64_MOV(1, r0, A64_R(0)), ctx);
+		emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
+		break;
+	}
+	/* function return */
+	case BPF_JMP | BPF_EXIT:
+		if (i == ctx->prog->len - 1)
+			break;
+		jmp_offset = epilogue_offset(ctx);
+		check_imm26(jmp_offset);
+		emit(A64_B(jmp_offset), ctx);
+		break;
+
+	/* LDX: dst = *(size *)(src + off) */
+	case BPF_LDX | BPF_MEM | BPF_W:
+	case BPF_LDX | BPF_MEM | BPF_H:
+	case BPF_LDX | BPF_MEM | BPF_B:
+	case BPF_LDX | BPF_MEM | BPF_DW:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(1, tmp, off, ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			emit(A64_LDR32(dst, src, tmp), ctx);
+			break;
+		case BPF_H:
+			emit(A64_LDRH(dst, src, tmp), ctx);
+			break;
+		case BPF_B:
+			emit(A64_LDRB(dst, src, tmp), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_LDR64(dst, src, tmp), ctx);
+			break;
+		}
+		break;
+
+	/* ST: *(size *)(dst + off) = imm */
+	case BPF_ST | BPF_MEM | BPF_W:
+	case BPF_ST | BPF_MEM | BPF_H:
+	case BPF_ST | BPF_MEM | BPF_B:
+	case BPF_ST | BPF_MEM | BPF_DW:
+		goto notyet;
+
+	/* STX: *(size *)(dst + off) = src */
+	case BPF_STX | BPF_MEM | BPF_W:
+	case BPF_STX | BPF_MEM | BPF_H:
+	case BPF_STX | BPF_MEM | BPF_B:
+	case BPF_STX | BPF_MEM | BPF_DW:
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(1, tmp, off, ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			emit(A64_STR32(src, dst, tmp), ctx);
+			break;
+		case BPF_H:
+			emit(A64_STRH(src, dst, tmp), ctx);
+			break;
+		case BPF_B:
+			emit(A64_STRB(src, dst, tmp), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_STR64(src, dst, tmp), ctx);
+			break;
+		}
+		break;
+	/* STX XADD: lock *(u32 *)(dst + off) += src */
+	case BPF_STX | BPF_XADD | BPF_W:
+	/* STX XADD: lock *(u64 *)(dst + off) += src */
+	case BPF_STX | BPF_XADD | BPF_DW:
+		goto notyet;
+
+	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
+	case BPF_LD | BPF_ABS | BPF_W:
+	case BPF_LD | BPF_ABS | BPF_H:
+	case BPF_LD | BPF_ABS | BPF_B:
+	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
+	case BPF_LD | BPF_IND | BPF_W:
+	case BPF_LD | BPF_IND | BPF_H:
+	case BPF_LD | BPF_IND | BPF_B:
+	{
+		const u8 r0 = bpf2a64[BPF_REG_0]; /* r0 = return value */
+		const u8 r6 = bpf2a64[BPF_REG_6]; /* r6 = pointer to sk_buff */
+		const u8 fp = bpf2a64[BPF_REG_FP];
+		const u8 r1 = bpf2a64[BPF_REG_1]; /* r1: struct sk_buff *skb */
+		const u8 r2 = bpf2a64[BPF_REG_2]; /* r2: int k */
+		const u8 r3 = bpf2a64[BPF_REG_3]; /* r3: unsigned int size */
+		const u8 r4 = bpf2a64[BPF_REG_4]; /* r4: void *buffer */
+		const u8 r5 = bpf2a64[BPF_REG_5]; /* r5: void *(*func)(...) */
+		int size;
+
+		emit(A64_MOV(1, r1, r6), ctx);
+		emit_a64_mov_i(0, r2, imm, ctx);
+		if (BPF_MODE(code) == BPF_IND)
+			emit(A64_ADD(0, r2, r2, src), ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			size = 4;
+			break;
+		case BPF_H:
+			size = 2;
+			break;
+		case BPF_B:
+			size = 1;
+			break;
+		default:
+			return -EINVAL;
+		}
+		emit_a64_mov_i64(r3, size, ctx);
+		emit(A64_ADD_I(1, r4, fp, MAX_BPF_STACK), ctx);
+		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
+		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
+		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
+		emit(A64_BLR(r5), ctx);
+		emit(A64_MOV(1, r0, A64_R(0)), ctx);
+		emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
+
+		jmp_offset = epilogue_offset(ctx);
+		check_imm19(jmp_offset);
+		emit(A64_CBZ(1, r0, jmp_offset), ctx);
+		emit(A64_MOV(1, r5, r0), ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			emit(A64_LDR32(r0, r5, A64_ZR), ctx);
+#ifndef CONFIG_CPU_BIG_ENDIAN
+			emit(A64_REV32(0, r0, r0), ctx);
+#endif
+			break;
+		case BPF_H:
+			emit(A64_LDRH(r0, r5, A64_ZR), ctx);
+#ifndef CONFIG_CPU_BIG_ENDIAN
+			emit(A64_REV16(0, r0, r0), ctx);
+#endif
+			break;
+		case BPF_B:
+			emit(A64_LDRB(r0, r5, A64_ZR), ctx);
+			break;
+		}
+		break;
+	}
+notyet:
+		pr_info_once("*** NOT YET: opcode %02x ***\n", code);
+		return -EFAULT;
+
+	default:
+		pr_err_once("unknown opcode %02x\n", code);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+	const struct bpf_prog *prog = ctx->prog;
+	int i;
+
+	for (i = 0; i < prog->len; i++) {
+		const struct bpf_insn *insn = &prog->insnsi[i];
+		int ret;
+
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
+
+		ret = build_insn(insn, ctx);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static inline void bpf_flush_icache(void *start, void *end)
+{
+	flush_icache_range((unsigned long)start, (unsigned long)end);
+}
+
+void bpf_jit_compile(struct bpf_prog *prog)
+{
+	/* Nothing to do here. We support Internal BPF. */
+}
+
+void bpf_int_jit_compile(struct bpf_prog *prog)
+{
+	struct jit_ctx ctx;
+	int image_size;
+
+	if (!bpf_jit_enable)
+		return;
+
+	if (!prog || !prog->len)
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.prog = prog;
+
+	ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
+	if (ctx.offset == NULL)
+		return;
+
+	/* 1. Initial fake pass to compute ctx->idx. */
+
+	/* Fake pass to fill in ctx->offset. */
+	if (build_body(&ctx))
+		goto out;
+
+	build_prologue(&ctx);
+
+	build_epilogue(&ctx);
+
+	/* Now we know the actual image size. */
+	image_size = sizeof(u32) * ctx.idx;
+	ctx.image = module_alloc(image_size);
+	if (unlikely(ctx.image == NULL))
+		goto out;
+
+	/* 2. Now, the actual pass. */
+
+	ctx.idx = 0;
+	build_prologue(&ctx);
+
+	ctx.body_offset = ctx.idx;
+	if (build_body(&ctx)) {
+		module_free(NULL, ctx.image);
+		goto out;
+	}
+
+	build_epilogue(&ctx);
+
+	/* And we're done. */
+	if (bpf_jit_enable > 1)
+		bpf_jit_dump(prog->len, image_size, 2, ctx.image);
+
+	bpf_flush_icache(ctx.image, ctx.image + ctx.idx);
+	prog->bpf_func = (void *)ctx.image;
+	prog->jited = 1;
+
+out:
+	kfree(ctx.offset);
+}
+
+void bpf_jit_free(struct bpf_prog *prog)
+{
+	if (prog->jited)
+		module_free(NULL, prog->bpf_func);
+
+	kfree(prog);
+}

drivers/of/platform.c

@@ -160,11 +160,10 @@ EXPORT_SYMBOL(of_device_alloc);
  * can use Platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE event
  * to fix up DMA configuration.
  */
-static void of_dma_configure(struct platform_device *pdev)
+static void of_dma_configure(struct device *dev)
 {
 	u64 dma_addr, paddr, size;
 	int ret;
-	struct device *dev = &pdev->dev;
 
 	/*
 	 * Set default dma-mask to 32 bit. Drivers are expected to setup
@@ -229,7 +228,7 @@ static struct platform_device *of_platform_device_create_pdata(
 	if (!dev)
 		goto err_clear_flag;
 
-	of_dma_configure(dev);
+	of_dma_configure(&dev->dev);
 	dev->dev.bus = &platform_bus_type;
 	dev->dev.platform_data = platform_data;
 
@@ -291,7 +290,6 @@ static struct amba_device *of_amba_device_create(struct device_node *node,
 	}
 
 	/* setup generic device info */
-	dev->dev.coherent_dma_mask = ~0;
 	dev->dev.of_node = of_node_get(node);
 	dev->dev.parent = parent;
 	dev->dev.platform_data = platform_data;
@@ -299,6 +297,7 @@ static struct amba_device *of_amba_device_create(struct device_node *node,
 		dev_set_name(&dev->dev, "%s", bus_id);
 	else
 		of_device_make_bus_id(&dev->dev);
+	of_dma_configure(&dev->dev);
 
 	/* Allow the HW Peripheral ID to be overridden */
 	prop = of_get_property(node, "arm,primecell-periphid", NULL);

kernel/module.c

@@ -3388,7 +3388,7 @@ static inline int is_arm_mapping_symbol(const char *str)
 {
 	if (str[0] == '.' && str[1] == 'L')
 		return true;
-	return str[0] == '$' && strchr("atd", str[1])
+	return str[0] == '$' && strchr("axtd", str[1])
 	       && (str[2] == '\0' || str[2] == '.');
 }
 

scripts/kallsyms.c

@@ -84,7 +84,7 @@ static void usage(void)
  */
 static inline int is_arm_mapping_symbol(const char *str)
 {
-	return str[0] == '$' && strchr("atd", str[1])
+	return str[0] == '$' && strchr("axtd", str[1])
 	       && (str[2] == '\0' || str[2] == '.');
 }
 

scripts/mod/modpost.c

@@ -1147,7 +1147,7 @@ static Elf_Sym *find_elf_symbol(struct elf_info *elf, Elf64_Sword addr,
 
 static inline int is_arm_mapping_symbol(const char *str)
 {
-	return str[0] == '$' && strchr("atd", str[1])
+	return str[0] == '$' && strchr("axtd", str[1])
 	       && (str[2] == '\0' || str[2] == '.');
 }