aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/Kconfig109
-rw-r--r--arch/arm/boot/dts/Makefile9
-rw-r--r--arch/arm/boot/dts/clcd-panels.dtsi52
-rw-r--r--arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts159
-rw-r--r--arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts165
-rw-r--r--arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts177
-rw-r--r--arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts171
-rw-r--r--arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts183
-rw-r--r--arch/arm/boot/dts/rtsm_ve-motherboard.dtsi224
-rw-r--r--arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts244
-rw-r--r--arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts358
-rw-r--r--arch/arm/boot/dts/vexpress-v2m-rs1.dtsi1
-rw-r--r--arch/arm/boot/dts/vexpress-v2m.dtsi1
-rw-r--r--arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts4
-rw-r--r--arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts168
-rw-r--r--arch/arm/boot/dts/vexpress-v2p-ca5s.dts4
-rw-r--r--arch/arm/boot/dts/vexpress-v2p-ca9.dts4
-rw-r--r--arch/arm/common/Makefile4
-rw-r--r--arch/arm/common/bL_switcher.c864
-rw-r--r--arch/arm/common/bL_switcher_dummy_if.c71
-rw-r--r--arch/arm/common/mcpm_entry.c12
-rw-r--r--arch/arm/common/mcpm_head.S16
-rw-r--r--arch/arm/include/asm/arch_timer.h2
-rw-r--r--arch/arm/include/asm/bL_switcher.h83
-rw-r--r--arch/arm/include/asm/cp15.h14
-rw-r--r--arch/arm/include/asm/hardirq.h2
-rw-r--r--arch/arm/include/asm/mach/arch.h5
-rw-r--r--arch/arm/include/asm/mcpm.h8
-rw-r--r--arch/arm/include/asm/pmu.h12
-rw-r--r--arch/arm/include/asm/psci.h21
-rw-r--r--arch/arm/include/asm/smp.h2
-rw-r--r--arch/arm/include/asm/topology.h34
-rw-r--r--arch/arm/kernel/Makefile5
-rw-r--r--arch/arm/kernel/head.S1
-rw-r--r--arch/arm/kernel/hw_breakpoint.c3
-rw-r--r--arch/arm/kernel/perf_event.c19
-rw-r--r--arch/arm/kernel/perf_event_cpu.c117
-rw-r--r--arch/arm/kernel/perf_event_v7.c57
-rw-r--r--arch/arm/kernel/psci.c49
-rw-r--r--arch/arm/kernel/psci_smp.c84
-rw-r--r--arch/arm/kernel/setup.c22
-rw-r--r--arch/arm/kernel/sleep.S32
-rw-r--r--arch/arm/kernel/smp.c23
-rw-r--r--arch/arm/kernel/topology.c135
-rw-r--r--arch/arm/mach-exynos/mach-exynos5-dt.c26
-rw-r--r--arch/arm/mach-vexpress/Kconfig20
-rw-r--r--arch/arm/mach-vexpress/Makefile8
-rw-r--r--arch/arm/mach-vexpress/core.h2
-rw-r--r--arch/arm/mach-vexpress/dcscb.c260
-rw-r--r--arch/arm/mach-vexpress/dcscb_setup.S38
-rw-r--r--arch/arm/mach-vexpress/include/mach/tc2.h10
-rw-r--r--arch/arm/mach-vexpress/platsmp.c20
-rw-r--r--arch/arm/mach-vexpress/tc2_pm.c271
-rw-r--r--arch/arm/mach-vexpress/tc2_pm_psci.c173
-rw-r--r--arch/arm/mach-vexpress/tc2_pm_setup.S68
-rw-r--r--arch/arm/mach-vexpress/v2m.c29
-rw-r--r--arch/arm/mach-virt/Makefile1
-rw-r--r--arch/arm/mach-virt/platsmp.c50
-rw-r--r--arch/arm/mach-virt/virt.c3
-rw-r--r--arch/arm/mm/fault.c13
-rw-r--r--arch/arm/plat-versatile/headsmp.S2
61 files changed, 4603 insertions, 121 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 18a9f5ef643..0460846b8a1 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1494,6 +1494,90 @@ config SCHED_SMT
MultiThreading at a cost of slightly increased overhead in some
places. If unsure say N here.
+config DISABLE_CPU_SCHED_DOMAIN_BALANCE
+ bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing"
+ help
+ Disables scheduler load-balancing at CPU sched domain level.
+
+config SCHED_HMP
+ bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+ depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+ help
+ Experimental scheduler optimizations for heterogeneous platforms.
+ Attempts to introspectively select task affinity to optimize power
+ and performance. Basic support for multiple (>2) cpu types is in place,
+ but it has only been tested with two types of cpus.
+ There is currently no support for migration of task groups, hence
+ !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+ between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+
+config SCHED_HMP_PRIO_FILTER
+ bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+ depends on SCHED_HMP
+ help
+ Enables task priority based HMP migration filter. Any task with
+ a NICE value above the threshold will always be on low-power cpus
+ with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+ int "NICE priority threshold"
+ default 5
+ depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+ string "HMP scheduler fast CPU mask"
+ depends on SCHED_HMP
+ help
+ Leave empty to use device tree information.
+ Specify the cpuids of the fast CPUs in the system as a list string,
+ e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+ string "HMP scheduler slow CPU mask"
+ depends on SCHED_HMP
+ help
+ Leave empty to use device tree information.
+ Specify the cpuids of the slow CPUs in the system as a list string,
+ e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+ bool "Allows changing the load tracking scale through sysfs"
+ depends on SCHED_HMP
+ help
+ When turned on, this option exports the thresholds and load average
+ period value for the load tracking patches through sysfs.
+ The values can be modified to change the rate of load accumulation
+ and the thresholds used for HMP migration.
+ The load_avg_period_ms is the time in ms to reach a load average of
+ 0.5 for an idle task of 0 load average ratio that start a busy loop.
+ The up_threshold and down_threshold is the value to go to a faster
+ CPU or to go back to a slower cpu.
+ The {up,down}_threshold are devided by 1024 before being compared
+ to the load average.
+ For examples, with load_avg_period_ms = 128 and up_threshold = 512,
+ a running task with a load of 0 will be migrated to a bigger CPU after
+ 128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+ up_threshold is 0.5.
+ This patch has the same behavior as changing the Y of the load
+ average computation to
+ (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+ but it remove intermadiate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+ bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+ depends on HMP_VARIABLE_SCALE && CPU_FREQ
+ help
+ Scales the current load contribution in line with the frequency
+ of the CPU that the task was executed on.
+ In this version, we use a simple linear scale derived from the
+ maximum frequency reported by CPUFreq.
+ Restricting tracked load to be scaled by the CPU's frequency
+ represents the consumption of possible compute capacity
+ (rather than consumption of actual instantaneous capacity as
+ normal) and allows the HMP migration's simple threshold
+ migration strategy to interact more predictably with CPUFreq's
+ asynchronous compute capacity changes.
+
config HAVE_ARM_SCU
bool
help
@@ -1521,6 +1605,31 @@ config MCPM
for (multi-)cluster based systems, such as big.LITTLE based
systems.
+config BIG_LITTLE
+ bool "big.LITTLE support (Experimental)"
+ depends on CPU_V7 && SMP
+ select MCPM
+ help
+ This option enables support for the big.LITTLE architecture.
+
+config BL_SWITCHER
+ bool "big.LITTLE switcher support"
+ depends on BIG_LITTLE && MCPM && HOTPLUG_CPU
+ select CPU_PM
+ select ARM_CPU_SUSPEND
+ help
+ The big.LITTLE "switcher" provides the core functionality to
+ transparently handle transition between a cluster of A15's
+ and a cluster of A7's in a big.LITTLE system.
+
+config BL_SWITCHER_DUMMY_IF
+ tristate "Simple big.LITTLE switcher user interface"
+ depends on BL_SWITCHER && DEBUG_KERNEL
+ help
+ This is a simple and dummy char dev interface to control
+ the big.LITTLE switcher core code. It is meant for
+ debugging purposes only.
+
choice
prompt "Memory split"
default VMSPLIT_3G
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index f0895c581a8..00baf9f5766 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -202,7 +202,14 @@ dtb-$(CONFIG_ARCH_VERSATILE) += versatile-ab.dtb \
dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \
vexpress-v2p-ca9.dtb \
vexpress-v2p-ca15-tc1.dtb \
- vexpress-v2p-ca15_a7.dtb
+ vexpress-v2p-ca15_a7.dtb \
+ rtsm_ve-cortex_a9x2.dtb \
+ rtsm_ve-cortex_a9x4.dtb \
+ rtsm_ve-cortex_a15x1.dtb \
+ rtsm_ve-cortex_a15x2.dtb \
+ rtsm_ve-cortex_a15x4.dtb \
+ rtsm_ve-v2p-ca15x1-ca7x1.dtb \
+ rtsm_ve-v2p-ca15x4-ca7x4.dtb
dtb-$(CONFIG_ARCH_VIRT) += xenvm-4.2.dtb
dtb-$(CONFIG_ARCH_VT8500) += vt8500-bv07.dtb \
wm8505-ref.dtb \
diff --git a/arch/arm/boot/dts/clcd-panels.dtsi b/arch/arm/boot/dts/clcd-panels.dtsi
new file mode 100644
index 00000000000..0b0ff6ead4b
--- /dev/null
+++ b/arch/arm/boot/dts/clcd-panels.dtsi
@@ -0,0 +1,52 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ */
+
+/ {
+ panels {
+ panel@0 {
+ compatible = "panel";
+ mode = "VGA";
+ refresh = <60>;
+ xres = <640>;
+ yres = <480>;
+ pixclock = <39721>;
+ left_margin = <40>;
+ right_margin = <24>;
+ upper_margin = <32>;
+ lower_margin = <11>;
+ hsync_len = <96>;
+ vsync_len = <2>;
+ sync = <0>;
+ vmode = "FB_VMODE_NONINTERLACED";
+
+ tim2 = "TIM2_BCD", "TIM2_IPC";
+ cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+ caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+ bpp = <16>;
+ };
+
+ panel@1 {
+ compatible = "panel";
+ mode = "XVGA";
+ refresh = <60>;
+ xres = <1024>;
+ yres = <768>;
+ pixclock = <15748>;
+ left_margin = <152>;
+ right_margin = <48>;
+ upper_margin = <23>;
+ lower_margin = <3>;
+ hsync_len = <104>;
+ vsync_len = <4>;
+ sync = <0>;
+ vmode = "FB_VMODE_NONINTERLACED";
+
+ tim2 = "TIM2_BCD", "TIM2_IPC";
+ cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+ caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+ bpp = <16>;
+ };
+ };
+};
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
new file mode 100644
index 00000000000..c9eee916aa7
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
@@ -0,0 +1,159 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x1CT
+ *
+ * RTSM_VE_Cortex_A15x1.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA15x1";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x1", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
new file mode 100644
index 00000000000..853a166e3c3
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
@@ -0,0 +1,165 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x2CT
+ *
+ * RTSM_VE_Cortex_A15x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA15x2";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x2", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
new file mode 100644
index 00000000000..c1947a3a5c8
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
@@ -0,0 +1,177 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ *
+ * RTSM_VE_Cortex_A15x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA15x4";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x4", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ };
+
+ cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <2>;
+ };
+
+ cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <3>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
new file mode 100644
index 00000000000..fca6b2f7967
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
@@ -0,0 +1,171 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx2CT
+ *
+ * RTSM_VE_Cortex_A9x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA9x2";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a9x2", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <1>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0x80000000 0x80000000>;
+ };
+
+ scu@2c000000 {
+ compatible = "arm,cortex-a9-scu";
+ reg = <0x2c000000 0x58>;
+ };
+
+ timer@2c000600 {
+ compatible = "arm,cortex-a9-twd-timer";
+ reg = <0x2c000600 0x20>;
+ interrupts = <1 13 0xf04>;
+ };
+
+ watchdog@2c000620 {
+ compatible = "arm,cortex-a9-twd-wdt";
+ reg = <0x2c000620 0x20>;
+ interrupts = <1 14 0xf04>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0x2c001000 0x1000>,
+ <0x2c000100 0x100>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0x08000000 0x04000000>,
+ <1 0 0x14000000 0x04000000>,
+ <2 0 0x18000000 0x04000000>,
+ <3 0 0x1c000000 0x04000000>,
+ <4 0 0x0c000000 0x04000000>,
+ <5 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
new file mode 100644
index 00000000000..fd8a6ed97a0
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
@@ -0,0 +1,183 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx4CT
+ *
+ * RTSM_VE_Cortex_A9x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA9x4";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a9x4", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <1>;
+ };
+
+ cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <2>;
+ };
+
+ cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <3>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0x80000000 0x80000000>;
+ };
+
+ scu@2c000000 {
+ compatible = "arm,cortex-a9-scu";
+ reg = <0x2c000000 0x58>;
+ };
+
+ timer@2c000600 {
+ compatible = "arm,cortex-a9-twd-timer";
+ reg = <0x2c000600 0x20>;
+ interrupts = <1 13 0xf04>;
+ };
+
+ watchdog@2c000620 {
+ compatible = "arm,cortex-a9-twd-wdt";
+ reg = <0x2c000620 0x20>;
+ interrupts = <1 14 0xf04>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0x2c001000 0x1000>,
+ <0x2c000100 0x100>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0x08000000 0x04000000>,
+ <1 0 0x14000000 0x04000000>,
+ <2 0 0x18000000 0x04000000>,
+ <3 0 0x1c000000 0x04000000>,
+ <4 0 0x0c000000 0x04000000>,
+ <5 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
new file mode 100644
index 00000000000..6d125662612
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
@@ -0,0 +1,224 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * Motherboard component
+ *
+ * VEMotherBoard.lisa
+ */
+
+ motherboard {
+ compatible = "arm,vexpress,v2m-p1", "simple-bus";
+ arm,hbi = <0x190>;
+ arm,vexpress,site = <0>;
+ arm,v2m-memory-map = "rs1";
+ #address-cells = <2>; /* SMB chipselect number and offset */
+ #size-cells = <1>;
+ #interrupt-cells = <1>;
+ ranges;
+
+ flash@0,00000000 {
+ compatible = "arm,vexpress-flash", "cfi-flash";
+ reg = <0 0x00000000 0x04000000>,
+ <4 0x00000000 0x04000000>;
+ bank-width = <4>;
+ };
+
+ vram@2,00000000 {
+ compatible = "arm,vexpress-vram";
+ reg = <2 0x00000000 0x00800000>;
+ };
+
+ ethernet@2,02000000 {
+ compatible = "smsc,lan91c111";
+ reg = <2 0x02000000 0x10000>;
+ interrupts = <15>;
+ };
+
+ iofpga@3,00000000 {
+ compatible = "arm,amba-bus", "simple-bus";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <0 3 0 0x200000>;
+
+ v2m_sysreg: sysreg@010000 {
+ compatible = "arm,vexpress-sysreg";
+ reg = <0x010000 0x1000>;
+ gpio-controller;
+ #gpio-cells = <2>;
+ };
+
+ v2m_sysctl: sysctl@020000 {
+ compatible = "arm,sp810", "arm,primecell";
+ reg = <0x020000 0x1000>;
+ clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&smbclk>;
+ clock-names = "refclk", "timclk", "apb_pclk";
+ #clock-cells = <1>;
+ clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+ };
+
+ aaci@040000 {
+ compatible = "arm,pl041", "arm,primecell";
+ reg = <0x040000 0x1000>;
+ interrupts = <11>;
+ clocks = <&smbclk>;
+ clock-names = "apb_pclk";
+ };
+
+ mmci@050000 {
+ compatible = "arm,pl180", "arm,primecell";
+ reg = <0x050000 0x1000>;
+ interrupts = <9 10>;
+ cd-gpios = <&v2m_sysreg 0 0>;
+ wp-gpios = <&v2m_sysreg 1 0>;
+ max-frequency = <12000000>;
+ vmmc-supply = <&v2m_fixed_3v3>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "mclk", "apb_pclk";
+ };
+
+ kmi@060000 {
+ compatible = "arm,pl050", "arm,primecell";
+ reg = <0x060000 0x1000>;
+ interrupts = <12>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "KMIREFCLK", "apb_pclk";
+ };
+
+ kmi@070000 {
+ compatible = "arm,pl050", "arm,primecell";
+ reg = <0x070000 0x1000>;
+ interrupts = <13>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "KMIREFCLK", "apb_pclk";
+ };
+
+ v2m_serial0: uart@090000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x090000 0x1000>;
+ interrupts = <5>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "uartclk", "apb_pclk";
+ };
+
+ v2m_serial1: uart@0a0000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x0a0000 0x1000>;
+ interrupts = <6>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "uartclk", "apb_pclk";
+ };
+
+ v2m_serial2: uart@0b0000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x0b0000 0x1000>;
+ interrupts = <7>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "uartclk", "apb_pclk";
+ };
+
+ v2m_serial3: uart@0c0000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x0c0000 0x1000>;
+ interrupts = <8>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "uartclk", "apb_pclk";
+ };
+
+ wdt@0f0000 {
+ compatible = "arm,sp805", "arm,primecell";
+ reg = <0x0f0000 0x1000>;
+ interrupts = <0>;
+ clocks = <&v2m_refclk32khz>, <&smbclk>;
+ clock-names = "wdogclk", "apb_pclk";
+ };
+
+ v2m_timer01: timer@110000 {
+ compatible = "arm,sp804", "arm,primecell";
+ reg = <0x110000 0x1000>;
+ interrupts = <2>;
+ clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&smbclk>;
+ clock-names = "timclken1", "timclken2", "apb_pclk";
+ };
+
+ v2m_timer23: timer@120000 {
+ compatible = "arm,sp804", "arm,primecell";
+ reg = <0x120000 0x1000>;
+ interrupts = <3>;
+ clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&smbclk>;
+ clock-names = "timclken1", "timclken2", "apb_pclk";
+ };
+
+ rtc@170000 {
+ compatible = "arm,pl031", "arm,primecell";
+ reg = <0x170000 0x1000>;
+ interrupts = <4>;
+ clocks = <&smbclk>;
+ clock-names = "apb_pclk";
+ };
+
+ clcd@1f0000 {
+ compatible = "arm,pl111", "arm,primecell";
+ reg = <0x1f0000 0x1000>;
+ interrupts = <14>;
+ clocks = <&v2m_oscclk1>, <&smbclk>;
+ clock-names = "v2m:oscclk1", "apb_pclk";
+ mode = "VGA";
+ use_dma = <0>;
+ framebuffer = <0x18000000 0x00180000>;
+ };
+ };
+
+ v2m_fixed_3v3: fixedregulator@0 {
+ compatible = "regulator-fixed";
+ regulator-name = "3V3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
+
+ v2m_clk24mhz: clk24mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <24000000>;
+ clock-output-names = "v2m:clk24mhz";
+ };
+
+ v2m_refclk1mhz: refclk1mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <1000000>;
+ clock-output-names = "v2m:refclk1mhz";
+ };
+
+ v2m_refclk32khz: refclk32khz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <32768>;
+ clock-output-names = "v2m:refclk32khz";
+ };
+
+ mcc {
+ compatible = "simple-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ v2m_oscclk1: osc@1 {
+ /* CLCD clock */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <23750000 63500000>;
+ #clock-cells = <0>;
+ clock-output-names = "v2m:oscclk1";
+ };
+
+ muxfpga@0 {
+ compatible = "arm,vexpress-muxfpga";
+ arm,vexpress-sysreg,func = <7 0>;
+ };
+
+ shutdown@0 {
+ compatible = "arm,vexpress-shutdown";
+ arm,vexpress-sysreg,func = <8 0>;
+ };
+ };
+ };
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
new file mode 100644
index 00000000000..fe8cf5dc857
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
@@ -0,0 +1,244 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x1_A7x1.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+ model = "RTSM_VE_CortexA15x1-A7x1";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x1_a7x1", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ clusters {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cluster0: cluster@0 {
+ reg = <0>;
+// freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core0: core@0 {
+ reg = <0>;
+ };
+
+ };
+ };
+
+ cluster1: cluster@1 {
+ reg = <1>;
+// freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core1: core@0 {
+ reg = <0>;
+ };
+
+ };
+ };
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ cluster = <&cluster0>;
+ core = <&core0>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x100>;
+ cluster = <&cluster1>;
+ core = <&core1>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ cci@2c090000 {
+ compatible = "arm,cci-400", "arm,cci";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0 0x2c090000 0 0x1000>;
+ ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+ cci_control1: slave-if@4000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x4000 0x1000>;
+ };
+
+ cci_control2: slave-if@5000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x5000 0x1000>;
+ };
+ };
+
+ dcscb@60000000 {
+ compatible = "arm,rtsm,dcscb";
+ reg = <0 0x60000000 0 0x1000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+
+ gic-cpuif@0 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <0>;
+ cpu = <&cpu0>;
+ };
+ gic-cpuif@1 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <1>;
+ cpu = <&cpu1>;
+ };
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
new file mode 100644
index 00000000000..f715285131d
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
@@ -0,0 +1,358 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x4_A7x4.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+ model = "RTSM_VE_CortexA15x4-A7x4";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x4_a7x4", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ clusters {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cluster0: cluster@0 {
+ reg = <0>;
+// freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core0: core@0 {
+ reg = <0>;
+ };
+
+ core1: core@1 {
+ reg = <1>;
+ };
+
+ core2: core@2 {
+ reg = <2>;
+ };
+
+ core3: core@3 {
+ reg = <3>;
+ };
+
+ };
+ };
+
+ cluster1: cluster@1 {
+ reg = <1>;
+// freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core4: core@0 {
+ reg = <0>;
+ };
+
+ core5: core@1 {
+ reg = <1>;
+ };
+
+ core6: core@2 {
+ reg = <2>;
+ };
+
+ core7: core@3 {
+ reg = <3>;
+ };
+
+ };
+ };
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ cluster = <&cluster0>;
+ core = <&core0>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ cluster = <&cluster0>;
+ core = <&core1>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu2: cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <2>;
+ cluster = <&cluster0>;
+ core = <&core2>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu3: cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <3>;
+ cluster = <&cluster0>;
+ core = <&core3>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu4: cpu@4 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x100>;
+ cluster = <&cluster1>;
+ core = <&core4>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+
+ cpu5: cpu@5 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x101>;
+ cluster = <&cluster1>;
+ core = <&core5>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+
+ cpu6: cpu@6 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x102>;
+ cluster = <&cluster1>;
+ core = <&core6>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+
+ cpu7: cpu@7 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x103>;
+ cluster = <&cluster1>;
+ core = <&core7>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ cci@2c090000 {
+ compatible = "arm,cci-400", "arm,cci";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0 0x2c090000 0 0x1000>;
+ ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+ cci_control1: slave-if@4000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x4000 0x1000>;
+ };
+
+ cci_control2: slave-if@5000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x5000 0x1000>;
+ };
+ };
+
+ dcscb@60000000 {
+ compatible = "arm,rtsm,dcscb";
+ reg = <0 0x60000000 0 0x1000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+
+ gic-cpuif@0 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <0>;
+ cpu = <&cpu0>;
+ };
+ gic-cpuif@1 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <1>;
+ cpu = <&cpu1>;
+ };
+ gic-cpuif@2 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <2>;
+ cpu = <&cpu2>;
+ };
+ gic-cpuif@3 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <3>;
+ cpu = <&cpu3>;
+ };
+ gic-cpuif@4 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <4>;
+ cpu = <&cpu4>;
+ };
+ gic-cpuif@5 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <5>;
+ cpu = <&cpu5>;
+ };
+ gic-cpuif@6 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <6>;
+ cpu = <&cpu6>;
+ };
+ gic-cpuif@7 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <7>;
+ cpu = <&cpu7>;
+ };
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index ac870fb3fa0..9584232ee6b 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -228,6 +228,7 @@
};
clcd@1f0000 {
+ status = "disabled";
compatible = "arm,pl111", "arm,primecell";
reg = <0x1f0000 0x1000>;
interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi
index f1420368355..6593398c11a 100644
--- a/arch/arm/boot/dts/vexpress-v2m.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m.dtsi
@@ -227,6 +227,7 @@
};
clcd@1f000 {
+ status = "disabled";
compatible = "arm,pl111", "arm,primecell";
reg = <0x1f000 0x1000>;
interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
index 9420053acc1..cc6a8c0cfe3 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
@@ -9,6 +9,8 @@
/dts-v1/;
+/memreserve/ 0xbf000000 0x01000000;
+
/ {
model = "V2P-CA15";
arm,hbi = <0x237>;
@@ -57,6 +59,8 @@
interrupts = <0 85 4>;
clocks = <&oscclk5>;
clock-names = "pxlclk";
+ mode = "1024x768-16@60";
+ framebuffer = <0 0xff000000 0 0x01000000>;
};
memory-controller@2b0a0000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index d2803be4e1a..f1dc620c5c4 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -9,11 +9,13 @@
/dts-v1/;
+/memreserve/ 0xff000000 0x01000000;
+
/ {
model = "V2P-CA15_CA7";
arm,hbi = <0x249>;
arm,vexpress,site = <0xf>;
- compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress";
+ compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress", "arm,generic";
interrupt-parent = <&gic>;
#address-cells = <2>;
#size-cells = <2>;
@@ -29,44 +31,106 @@
i2c1 = &v2m_i2c_pcie;
};
- cpus {
+ clusters {
#address-cells = <1>;
#size-cells = <0>;
- cpu0: cpu@0 {
- device_type = "cpu";
- compatible = "arm,cortex-a15";
+ cluster0: cluster@0 {
reg = <0>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core0: core@0 {
+ reg = <0>;
+ };
+
+ core1: core@1 {
+ reg = <1>;
+ };
+
+ };
};
- cpu1: cpu@1 {
- device_type = "cpu";
- compatible = "arm,cortex-a15";
+ cluster1: cluster@1 {
reg = <1>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core2: core@0 {
+ reg = <0>;
+ };
+
+ core3: core@1 {
+ reg = <1>;
+ };
+
+ core4: core@2 {
+ reg = <2>;
+ };
+ };
};
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
cpu2: cpu@2 {
device_type = "cpu";
compatible = "arm,cortex-a7";
reg = <0x100>;
+ cluster = <&cluster1>;
+ core = <&core2>;
+ clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
};
cpu3: cpu@3 {
device_type = "cpu";
compatible = "arm,cortex-a7";
reg = <0x101>;
+ cluster = <&cluster1>;
+ core = <&core3>;
+ clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
};
cpu4: cpu@4 {
device_type = "cpu";
compatible = "arm,cortex-a7";
reg = <0x102>;
+ cluster = <&cluster1>;
+ core = <&core4>;
+ clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ cluster = <&cluster0>;
+ core = <&core0>;
+ clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ cluster = <&cluster0>;
+ core = <&core1>;
+ clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
};
};
memory@80000000 {
device_type = "memory";
- reg = <0 0x80000000 0 0x40000000>;
+ reg = <0 0x80000000 0 0x80000000>;
};
wdt@2a490000 {
@@ -81,6 +145,8 @@
compatible = "arm,hdlcd";
reg = <0 0x2b000000 0 0x1000>;
interrupts = <0 85 4>;
+ mode = "1024x768-16@60";
+ framebuffer = <0 0xff000000 0 0x01000000>;
clocks = <&oscclk5>;
clock-names = "pxlclk";
};
@@ -102,6 +168,64 @@
<0 0x2c004000 0 0x2000>,
<0 0x2c006000 0 0x2000>;
interrupts = <1 9 0xf04>;
+
+ gic-cpuif@0 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <0>;
+ cpu = <&cpu0>;
+ };
+ gic-cpuif@1 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <1>;
+ cpu = <&cpu1>;
+ };
+ gic-cpuif@2 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <2>;
+ cpu = <&cpu2>;
+ };
+
+ gic-cpuif@3 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <3>;
+ cpu = <&cpu3>;
+ };
+
+ gic-cpuif@4 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <4>;
+ cpu = <&cpu4>;
+ };
+ };
+
+ cci@2c090000 {
+ compatible = "arm,cci-400";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0 0x2c090000 0 0x1000>;
+ ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+ cci_control1: slave-if@4000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x4000 0x1000>;
+ };
+
+ cci_control2: slave-if@5000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x5000 0x1000>;
+ };
+ };
+
+ cci-pmu@2c099000 {
+ compatible = "arm,cci-400-pmu";
+ reg = <0 0x2c099000 0 0x6000>;
+ interrupts = <0 101 4>,
+ <0 102 4>,
+ <0 103 4>,
+ <0 104 4>,
+ <0 105 4>;
};
memory-controller@7ffd0000 {
@@ -125,6 +249,12 @@
clock-names = "apb_pclk";
};
+ spc@7fff0000 {
+ compatible = "arm,vexpress-spc,v2p-ca15_a7","arm,vexpress-spc";
+ reg = <0 0x7fff0000 0 0x1000>;
+ interrupts = <0 95 4>;
+ };
+
timer {
compatible = "arm,armv7-timer";
interrupts = <1 13 0xf08>,
@@ -133,12 +263,21 @@
<1 10 0xf08>;
};
- pmu {
+ pmu_a15 {
compatible = "arm,cortex-a15-pmu";
+ cluster = <&cluster0>;
interrupts = <0 68 4>,
<0 69 4>;
};
+ pmu_a7 {
+ compatible = "arm,cortex-a7-pmu";
+ cluster = <&cluster1>;
+ interrupts = <0 128 4>,
+ <0 129 4>,
+ <0 130 4>;
+ };
+
oscclk6a: oscclk6a {
/* Reference 24MHz clock */
compatible = "fixed-clock";
@@ -147,6 +286,15 @@
clock-output-names = "oscclk6a";
};
+ psci {
+ compatible = "arm,psci";
+ method = "smc";
+ cpu_suspend = <0x80100001>;
+ cpu_off = <0x80100002>;
+ cpu_on = <0x80100003>;
+ migrate = <0x80100004>;
+ };
+
dcc {
compatible = "arm,vexpress,config-bus";
arm,vexpress,config-bridge = <&v2m_sysreg>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
index c544a550459..cf633ed6a1b 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
@@ -9,6 +9,8 @@
/dts-v1/;
+/memreserve/ 0xbf000000 0x01000000;
+
/ {
model = "V2P-CA5s";
arm,hbi = <0x225>;
@@ -59,6 +61,8 @@
interrupts = <0 85 4>;
clocks = <&oscclk3>;
clock-names = "pxlclk";
+ mode = "640x480-16@60";
+ framebuffer = <0xbf000000 0x01000000>;
};
memory-controller@2a150000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
index 62d9b225dcc..f83706bd3f9 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
@@ -9,6 +9,8 @@
/dts-v1/;
+/include/ "clcd-panels.dtsi"
+
/ {
model = "V2P-CA9";
arm,hbi = <0x191>;
@@ -73,6 +75,8 @@
interrupts = <0 44 4>;
clocks = <&oscclk1>, <&oscclk2>;
clock-names = "clcdclk", "apb_pclk";
+ mode = "XVGA";
+ use_dma = <1>;
};
memory-controller@100e0000 {
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 48434cbe3e8..462cd580fc2 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -14,5 +14,9 @@ obj-$(CONFIG_SHARP_SCOOP) += scoop.o
obj-$(CONFIG_PCI_HOST_ITE8152) += it8152.o
obj-$(CONFIG_ARM_TIMER_SP804) += timer-sp.o
obj-$(CONFIG_MCPM) += mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
+obj-$(CONFIG_BL_SWITCHER) += bL_switcher.o
+obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o
+
AFLAGS_mcpm_head.o := -march=armv7-a
AFLAGS_vlock.o := -march=armv7-a
+CFLAGS_REMOVE_mcpm_entry.o = -pg
diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
new file mode 100644
index 00000000000..8fee70dfb30
--- /dev/null
+++ b/arch/arm/common/bL_switcher.c
@@ -0,0 +1,864 @@
+/*
+ * arch/arm/common/bL_switcher.c -- big.LITTLE cluster switcher core driver
+ *
+ * Created by: Nicolas Pitre, March 2012
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * 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/atomic.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/cpu_pm.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/kthread.h>
+#include <linux/wait.h>
+#include <linux/time.h>
+#include <linux/clockchips.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/notifier.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/moduleparam.h>
+
+#include <asm/smp_plat.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/suspend.h>
+#include <asm/mcpm.h>
+#include <asm/bL_switcher.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power_cpu_migrate.h>
+
+
+/*
+ * Use our own MPIDR accessors as the generic ones in asm/cputype.h have
+ * __attribute_const__ and we don't want the compiler to assume any
+ * constness here as the value _does_ change along some code paths.
+ */
+
+static int read_mpidr(void)
+{
+ unsigned int id;
+ asm volatile ("mrc\tp15, 0, %0, c0, c0, 5" : "=r" (id));
+ return id & MPIDR_HWID_BITMASK;
+}
+
+/*
+ * Get a global nanosecond time stamp for tracing.
+ */
+static s64 get_ns(void)
+{
+ struct timespec ts;
+ getnstimeofday(&ts);
+ return timespec_to_ns(&ts);
+}
+
+/*
+ * bL switcher core code.
+ */
+
+static void bL_do_switch(void *_arg)
+{
+ unsigned ib_mpidr, ib_cpu, ib_cluster;
+ long volatile handshake, **handshake_ptr = _arg;
+
+ pr_debug("%s\n", __func__);
+
+ ib_mpidr = cpu_logical_map(smp_processor_id());
+ ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0);
+ ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1);
+
+ /* Advertise our handshake location */
+ if (handshake_ptr) {
+ handshake = 0;
+ *handshake_ptr = &handshake;
+ } else
+ handshake = -1;
+
+ /*
+ * Our state has been saved at this point. Let's release our
+ * inbound CPU.
+ */
+ mcpm_set_entry_vector(ib_cpu, ib_cluster, cpu_resume);
+ sev();
+
+ /*
+ * From this point, we must assume that our counterpart CPU might
+ * have taken over in its parallel world already, as if execution
+ * just returned from cpu_suspend(). It is therefore important to
+ * be very careful not to make any change the other guy is not
+ * expecting. This is why we need stack isolation.
+ *
+ * Fancy under cover tasks could be performed here. For now
+ * we have none.
+ */
+
+ /*
+ * Let's wait until our inbound is alive.
+ */
+ while (!handshake) {
+ wfe();
+ smp_mb();
+ }
+
+ /* Let's put ourself down. */
+ mcpm_cpu_power_down();
+
+ /* should never get here */
+ BUG();
+}
+
+/*
+ * Stack isolation. To ensure 'current' remains valid, we just use another
+ * piece of our thread's stack space which should be fairly lightly used.
+ * The selected area starts just above the thread_info structure located
+ * at the very bottom of the stack, aligned to a cache line, and indexed
+ * with the cluster number.
+ */
+#define STACK_SIZE 512
+extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
+static int bL_switchpoint(unsigned long _arg)
+{
+ unsigned int mpidr = read_mpidr();
+ unsigned int clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+ void *stack = current_thread_info() + 1;
+ stack = PTR_ALIGN(stack, L1_CACHE_BYTES);
+ stack += clusterid * STACK_SIZE + STACK_SIZE;
+ call_with_stack(bL_do_switch, (void *)_arg, stack);
+ BUG();
+}
+
+/*
+ * Generic switcher interface
+ */
+
+static unsigned int bL_gic_id[MAX_CPUS_PER_CLUSTER][MAX_NR_CLUSTERS];
+static int bL_switcher_cpu_pairing[NR_CPUS];
+
+/*
+ * bL_switch_to - Switch to a specific cluster for the current CPU
+ * @new_cluster_id: the ID of the cluster to switch to.
+ *
+ * This function must be called on the CPU to be switched.
+ * Returns 0 on success, else a negative status code.
+ */
+static int bL_switch_to(unsigned int new_cluster_id)
+{
+ unsigned int mpidr, this_cpu, that_cpu;
+ unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster;
+ struct completion inbound_alive;
+ struct tick_device *tdev;
+ enum clock_event_mode tdev_mode;
+ long volatile *handshake_ptr;
+ int ipi_nr, ret;
+
+ this_cpu = smp_processor_id();
+ ob_mpidr = read_mpidr();
+ ob_cpu = MPIDR_AFFINITY_LEVEL(ob_mpidr, 0);
+ ob_cluster = MPIDR_AFFINITY_LEVEL(ob_mpidr, 1);
+ BUG_ON(cpu_logical_map(this_cpu) != ob_mpidr);
+
+ if (new_cluster_id == ob_cluster)
+ return 0;
+
+ that_cpu = bL_switcher_cpu_pairing[this_cpu];
+ ib_mpidr = cpu_logical_map(that_cpu);
+ ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0);
+ ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1);
+
+ pr_debug("before switch: CPU %d MPIDR %#x -> %#x\n",
+ this_cpu, ob_mpidr, ib_mpidr);
+
+ this_cpu = smp_processor_id();
+
+ /* Close the gate for our entry vectors */
+ mcpm_set_entry_vector(ob_cpu, ob_cluster, NULL);
+ mcpm_set_entry_vector(ib_cpu, ib_cluster, NULL);
+
+ /* Install our "inbound alive" notifier. */
+ init_completion(&inbound_alive);
+ ipi_nr = register_ipi_completion(&inbound_alive, this_cpu);
+ ipi_nr |= ((1 << 16) << bL_gic_id[ob_cpu][ob_cluster]);
+ mcpm_set_early_poke(ib_cpu, ib_cluster, gic_get_sgir_physaddr(), ipi_nr);
+
+ /*
+ * Let's wake up the inbound CPU now in case it requires some delay
+ * to come online, but leave it gated in our entry vector code.
+ */
+ ret = mcpm_cpu_power_up(ib_cpu, ib_cluster);
+ if (ret) {
+ pr_err("%s: mcpm_cpu_power_up() returned %d\n", __func__, ret);
+ return ret;
+ }
+
+ /*
+ * Raise a SGI on the inbound CPU to make sure it doesn't stall
+ * in a possible WFI, such as in bL_power_down().
+ */
+ gic_send_sgi(bL_gic_id[ib_cpu][ib_cluster], 0);
+
+ /*
+ * Wait for the inbound to come up. This allows for other
+ * tasks to be scheduled in the mean time.
+ */
+ wait_for_completion(&inbound_alive);
+ mcpm_set_early_poke(ib_cpu, ib_cluster, 0, 0);
+
+ /*
+ * From this point we are entering the switch critical zone
+ * and can't sleep/schedule anymore.
+ */
+ local_irq_disable();
+ local_fiq_disable();
+ trace_cpu_migrate_begin(get_ns(), ob_mpidr);
+
+ /* redirect GIC's SGIs to our counterpart */
+ gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]);
+
+ tdev = tick_get_device(this_cpu);
+ if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu)))
+ tdev = NULL;
+ if (tdev) {
+ tdev_mode = tdev->evtdev->mode;
+ clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
+ }
+
+ ret = cpu_pm_enter();
+
+ /* we can not tolerate errors at this point */
+ if (ret)
+ panic("%s: cpu_pm_enter() returned %d\n", __func__, ret);
+
+ /*
+ * Swap the physical CPUs in the logical map for this logical CPU.
+ * This must be flushed to RAM as the resume code
+ * needs to access it while the caches are still disabled.
+ */
+ cpu_logical_map(this_cpu) = ib_mpidr;
+ cpu_logical_map(that_cpu) = ob_mpidr;
+ sync_cache_w(&cpu_logical_map(this_cpu));
+
+ /* Let's do the actual CPU switch. */
+ ret = cpu_suspend((unsigned long)&handshake_ptr, bL_switchpoint);
+ if (ret > 0)
+ panic("%s: cpu_suspend() returned %d\n", __func__, ret);
+
+ /* We are executing on the inbound CPU at this point */
+ mpidr = read_mpidr();
+ pr_debug("after switch: CPU %d MPIDR %#x\n", this_cpu, mpidr);
+ BUG_ON(mpidr != ib_mpidr);
+
+ mcpm_cpu_powered_up();
+
+ ret = cpu_pm_exit();
+
+ if (tdev) {
+ clockevents_set_mode(tdev->evtdev, tdev_mode);
+ clockevents_program_event(tdev->evtdev,
+ tdev->evtdev->next_event, 1);
+ }
+
+ trace_cpu_migrate_finish(get_ns(), ib_mpidr);
+ local_fiq_enable();
+ local_irq_enable();
+
+ *handshake_ptr = 1;
+ dsb_sev();
+
+ if (ret)
+ pr_err("%s exiting with error %d\n", __func__, ret);
+ return ret;
+}
+
+struct bL_thread {
+ spinlock_t lock;
+ struct task_struct *task;
+ wait_queue_head_t wq;
+ int wanted_cluster;
+ struct completion started;
+ bL_switch_completion_handler completer;
+ void *completer_cookie;
+};
+
+static struct bL_thread bL_threads[NR_CPUS];
+
+static int bL_switcher_thread(void *arg)
+{
+ struct bL_thread *t = arg;
+ struct sched_param param = { .sched_priority = 1 };
+ int cluster;
+ bL_switch_completion_handler completer;
+ void *completer_cookie;
+
+ sched_setscheduler_nocheck(current, SCHED_FIFO, &param);
+ complete(&t->started);
+
+ do {
+ if (signal_pending(current))
+ flush_signals(current);
+ wait_event_interruptible(t->wq,
+ t->wanted_cluster != -1 ||
+ kthread_should_stop());
+
+ spin_lock(&t->lock);
+ cluster = t->wanted_cluster;
+ completer = t->completer;
+ completer_cookie = t->completer_cookie;
+ t->wanted_cluster = -1;
+ t->completer = NULL;
+ spin_unlock(&t->lock);
+
+ if (cluster != -1) {
+ bL_switch_to(cluster);
+
+ if (completer)
+ completer(completer_cookie);
+ }
+ } while (!kthread_should_stop());
+
+ return 0;
+}
+
+static struct task_struct * bL_switcher_thread_create(int cpu, void *arg)
+{
+ struct task_struct *task;
+
+ task = kthread_create_on_node(bL_switcher_thread, arg,
+ cpu_to_node(cpu), "kswitcher_%d", cpu);
+ if (!IS_ERR(task)) {
+ kthread_bind(task, cpu);
+ wake_up_process(task);
+ } else
+ pr_err("%s failed for CPU %d\n", __func__, cpu);
+ return task;
+}
+
+/*
+ * bL_switch_request_cb - Switch to a specific cluster for the given CPU,
+ * with completion notification via a callback
+ *
+ * @cpu: the CPU to switch
+ * @new_cluster_id: the ID of the cluster to switch to.
+ * @completer: switch completion callback. if non-NULL,
+ * @completer(@completer_cookie) will be called on completion of
+ * the switch, in non-atomic context.
+ * @completer_cookie: opaque context argument for @completer.
+ *
+ * This function causes a cluster switch on the given CPU by waking up
+ * the appropriate switcher thread. This function may or may not return
+ * before the switch has occurred.
+ *
+ * If a @completer callback function is supplied, it will be called when
+ * the switch is complete. This can be used to determine asynchronously
+ * when the switch is complete, regardless of when bL_switch_request()
+ * returns. When @completer is supplied, no new switch request is permitted
+ * for the affected CPU until after the switch is complete, and @completer
+ * has returned.
+ */
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+ bL_switch_completion_handler completer,
+ void *completer_cookie)
+{
+ struct bL_thread *t;
+
+ if (cpu >= ARRAY_SIZE(bL_threads)) {
+ pr_err("%s: cpu %d out of bounds\n", __func__, cpu);
+ return -EINVAL;
+ }
+
+ t = &bL_threads[cpu];
+
+ if (IS_ERR(t->task))
+ return PTR_ERR(t->task);
+ if (!t->task)
+ return -ESRCH;
+
+ spin_lock(&t->lock);
+ if (t->completer) {
+ spin_unlock(&t->lock);
+ return -EBUSY;
+ }
+ t->completer = completer;
+ t->completer_cookie = completer_cookie;
+ t->wanted_cluster = new_cluster_id;
+ spin_unlock(&t->lock);
+ wake_up(&t->wq);
+ return 0;
+}
+
+EXPORT_SYMBOL_GPL(bL_switch_request_cb);
+
+/*
+ * Detach an outstanding switch request.
+ *
+ * The switcher will continue with the switch request in the background,
+ * but the completer function will not be called.
+ *
+ * This may be necessary if the completer is in a kernel module which is
+ * about to be unloaded.
+ */
+void bL_switch_request_detach(unsigned int cpu,
+ bL_switch_completion_handler completer)
+{
+ struct bL_thread *t;
+
+ if (cpu >= ARRAY_SIZE(bL_threads)) {
+ pr_err("%s: cpu %d out of bounds\n", __func__, cpu);
+ return;
+ }
+
+ t = &bL_threads[cpu];
+
+ if (IS_ERR(t->task) || !t->task)
+ return;
+
+ spin_lock(&t->lock);
+ if (t->completer == completer)
+ t->completer = NULL;
+ spin_unlock(&t->lock);
+}
+
+EXPORT_SYMBOL_GPL(bL_switch_request_detach);
+
+/*
+ * Activation and configuration code.
+ */
+
+static DEFINE_MUTEX(bL_switcher_activation_lock);
+static BLOCKING_NOTIFIER_HEAD(bL_activation_notifier);
+static unsigned int bL_switcher_active;
+static unsigned int bL_switcher_cpu_original_cluster[NR_CPUS];
+static cpumask_t bL_switcher_removed_logical_cpus;
+
+int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&bL_activation_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_register_notifier);
+
+int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&bL_activation_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_unregister_notifier);
+
+static int bL_activation_notify(unsigned long val)
+{
+ int ret;
+
+ ret = blocking_notifier_call_chain(&bL_activation_notifier, val, NULL);
+ if (ret & NOTIFY_STOP_MASK)
+ pr_err("%s: notifier chain failed with status 0x%x\n",
+ __func__, ret);
+ return notifier_to_errno(ret);
+}
+
+static void bL_switcher_restore_cpus(void)
+{
+ int i;
+
+ for_each_cpu(i, &bL_switcher_removed_logical_cpus)
+ cpu_up(i);
+}
+
+static int bL_switcher_halve_cpus(void)
+{
+ int i, j, cluster_0, gic_id, ret;
+ unsigned int cpu, cluster, mask;
+ cpumask_t available_cpus;
+
+ /* First pass to validate what we have */
+ mask = 0;
+ for_each_online_cpu(i) {
+ cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0);
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+ if (cluster >= 2) {
+ pr_err("%s: only dual cluster systems are supported\n", __func__);
+ return -EINVAL;
+ }
+ if (WARN_ON(cpu >= MAX_CPUS_PER_CLUSTER))
+ return -EINVAL;
+ mask |= (1 << cluster);
+ }
+ if (mask != 3) {
+ pr_err("%s: no CPU pairing possible\n", __func__);
+ return -EINVAL;
+ }
+
+ /*
+ * Now let's do the pairing. We match each CPU with another CPU
+ * from a different cluster. To get a uniform scheduling behavior
+ * without fiddling with CPU topology and compute capacity data,
+ * we'll use logical CPUs initially belonging to the same cluster.
+ */
+ memset(bL_switcher_cpu_pairing, -1, sizeof(bL_switcher_cpu_pairing));
+ cpumask_copy(&available_cpus, cpu_online_mask);
+ cluster_0 = -1;
+ for_each_cpu(i, &available_cpus) {
+ int match = -1;
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+ if (cluster_0 == -1)
+ cluster_0 = cluster;
+ if (cluster != cluster_0)
+ continue;
+ cpumask_clear_cpu(i, &available_cpus);
+ for_each_cpu(j, &available_cpus) {
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(j), 1);
+ /*
+ * Let's remember the last match to create "odd"
+ * pairing on purpose in order for other code not
+ * to assume any relation between physical and
+ * logical CPU numbers.
+ */
+ if (cluster != cluster_0)
+ match = j;
+ }
+ if (match != -1) {
+ bL_switcher_cpu_pairing[i] = match;
+ cpumask_clear_cpu(match, &available_cpus);
+ pr_info("CPU%d paired with CPU%d\n", i, match);
+ }
+ }
+
+ /*
+ * Now we disable the unwanted CPUs i.e. everything that has no
+ * pairing information (that includes the pairing counterparts).
+ */
+ cpumask_clear(&bL_switcher_removed_logical_cpus);
+ for_each_online_cpu(i) {
+ cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0);
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+
+ /* Let's take note of the GIC ID for this CPU */
+ gic_id = gic_get_cpu_id(i);
+ if (gic_id < 0) {
+ pr_err("%s: bad GIC ID for CPU %d\n", __func__, i);
+ bL_switcher_restore_cpus();
+ return -EINVAL;
+ }
+ bL_gic_id[cpu][cluster] = gic_id;
+ pr_info("GIC ID for CPU %u cluster %u is %u\n",
+ cpu, cluster, gic_id);
+
+ if (bL_switcher_cpu_pairing[i] != -1) {
+ bL_switcher_cpu_original_cluster[i] = cluster;
+ continue;
+ }
+
+ ret = cpu_down(i);
+ if (ret) {
+ bL_switcher_restore_cpus();
+ return ret;
+ }
+ cpumask_set_cpu(i, &bL_switcher_removed_logical_cpus);
+ }
+
+ return 0;
+}
+
+/* Determine the logical CPU a given physical CPU is grouped on. */
+int bL_switcher_get_logical_index(u32 mpidr)
+{
+ int cpu;
+
+ if (!bL_switcher_active)
+ return -EUNATCH;
+
+ mpidr &= MPIDR_HWID_BITMASK;
+ for_each_online_cpu(cpu) {
+ int pairing = bL_switcher_cpu_pairing[cpu];
+ if (pairing == -1)
+ continue;
+ if ((mpidr == cpu_logical_map(cpu)) ||
+ (mpidr == cpu_logical_map(pairing)))
+ return cpu;
+ }
+ return -EINVAL;
+}
+
+static void bL_switcher_trace_trigger_cpu(void *__always_unused info)
+{
+ trace_cpu_migrate_current(get_ns(), read_mpidr());
+}
+
+int bL_switcher_trace_trigger(void)
+{
+ int ret;
+
+ preempt_disable();
+
+ bL_switcher_trace_trigger_cpu(NULL);
+ ret = smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true);
+
+ preempt_enable();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(bL_switcher_trace_trigger);
+
+static int bL_switcher_enable(void)
+{
+ int cpu, ret;
+
+ mutex_lock(&bL_switcher_activation_lock);
+ cpu_hotplug_driver_lock();
+ if (bL_switcher_active) {
+ cpu_hotplug_driver_unlock();
+ mutex_unlock(&bL_switcher_activation_lock);
+ return 0;
+ }
+
+ pr_info("big.LITTLE switcher initializing\n");
+
+ ret = bL_activation_notify(BL_NOTIFY_PRE_ENABLE);
+ if (ret)
+ goto error;
+
+ ret = bL_switcher_halve_cpus();
+ if (ret)
+ goto error;
+
+ bL_switcher_trace_trigger();
+
+ for_each_online_cpu(cpu) {
+ struct bL_thread *t = &bL_threads[cpu];
+ spin_lock_init(&t->lock);
+ init_waitqueue_head(&t->wq);
+ init_completion(&t->started);
+ t->wanted_cluster = -1;
+ t->task = bL_switcher_thread_create(cpu, t);
+ }
+
+ bL_switcher_active = 1;
+ bL_activation_notify(BL_NOTIFY_POST_ENABLE);
+ pr_info("big.LITTLE switcher initialized\n");
+ goto out;
+
+error:
+ pr_warning("big.LITTLE switcher initialization failed\n");
+ bL_activation_notify(BL_NOTIFY_POST_DISABLE);
+
+out:
+ cpu_hotplug_driver_unlock();
+ mutex_unlock(&bL_switcher_activation_lock);
+ return ret;
+}
+
+#ifdef CONFIG_SYSFS
+
+static void bL_switcher_disable(void)
+{
+ unsigned int cpu, cluster;
+ struct bL_thread *t;
+ struct task_struct *task;
+
+ mutex_lock(&bL_switcher_activation_lock);
+ cpu_hotplug_driver_lock();
+
+ if (!bL_switcher_active)
+ goto out;
+
+ if (bL_activation_notify(BL_NOTIFY_PRE_DISABLE) != 0) {
+ bL_activation_notify(BL_NOTIFY_POST_ENABLE);
+ goto out;
+ }
+
+ bL_switcher_active = 0;
+
+ /*
+ * To deactivate the switcher, we must shut down the switcher
+ * threads to prevent any other requests from being accepted.
+ * Then, if the final cluster for given logical CPU is not the
+ * same as the original one, we'll recreate a switcher thread
+ * just for the purpose of switching the CPU back without any
+ * possibility for interference from external requests.
+ */
+ for_each_online_cpu(cpu) {
+ t = &bL_threads[cpu];
+ task = t->task;
+ t->task = NULL;
+ if (!task || IS_ERR(task))
+ continue;
+ kthread_stop(task);
+ /* no more switch may happen on this CPU at this point */
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+ if (cluster == bL_switcher_cpu_original_cluster[cpu])
+ continue;
+ init_completion(&t->started);
+ t->wanted_cluster = bL_switcher_cpu_original_cluster[cpu];
+ task = bL_switcher_thread_create(cpu, t);
+ if (!IS_ERR(task)) {
+ wait_for_completion(&t->started);
+ kthread_stop(task);
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+ if (cluster == bL_switcher_cpu_original_cluster[cpu])
+ continue;
+ }
+ /* If execution gets here, we're in trouble. */
+ pr_crit("%s: unable to restore original cluster for CPU %d\n",
+ __func__, cpu);
+ pr_crit("%s: CPU %d can't be restored\n",
+ __func__, bL_switcher_cpu_pairing[cpu]);
+ cpumask_clear_cpu(bL_switcher_cpu_pairing[cpu],
+ &bL_switcher_removed_logical_cpus);
+ }
+
+ bL_switcher_restore_cpus();
+ bL_switcher_trace_trigger();
+
+ bL_activation_notify(BL_NOTIFY_POST_DISABLE);
+
+out:
+ cpu_hotplug_driver_unlock();
+ mutex_unlock(&bL_switcher_activation_lock);
+}
+
+static ssize_t bL_switcher_active_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%u\n", bL_switcher_active);
+}
+
+static ssize_t bL_switcher_active_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ int ret;
+
+ switch (buf[0]) {
+ case '0':
+ bL_switcher_disable();
+ ret = 0;
+ break;
+ case '1':
+ ret = bL_switcher_enable();
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ return (ret >= 0) ? count : ret;
+}
+
+static ssize_t bL_switcher_trace_trigger_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ int ret = bL_switcher_trace_trigger();
+
+ return ret ? ret : count;
+}
+
+static struct kobj_attribute bL_switcher_active_attr =
+ __ATTR(active, 0644, bL_switcher_active_show, bL_switcher_active_store);
+
+static struct kobj_attribute bL_switcher_trace_trigger_attr =
+ __ATTR(trace_trigger, 0200, NULL, bL_switcher_trace_trigger_store);
+
+static struct attribute *bL_switcher_attrs[] = {
+ &bL_switcher_active_attr.attr,
+ &bL_switcher_trace_trigger_attr.attr,
+ NULL,
+};
+
+static struct attribute_group bL_switcher_attr_group = {
+ .attrs = bL_switcher_attrs,
+};
+
+static struct kobject *bL_switcher_kobj;
+
+static int __init bL_switcher_sysfs_init(void)
+{
+ int ret;
+
+ bL_switcher_kobj = kobject_create_and_add("bL_switcher", kernel_kobj);
+ if (!bL_switcher_kobj)
+ return -ENOMEM;
+ ret = sysfs_create_group(bL_switcher_kobj, &bL_switcher_attr_group);
+ if (ret)
+ kobject_put(bL_switcher_kobj);
+ return ret;
+}
+
+#endif /* CONFIG_SYSFS */
+
+bool bL_switcher_get_enabled(void)
+{
+ mutex_lock(&bL_switcher_activation_lock);
+
+ return bL_switcher_active;
+}
+EXPORT_SYMBOL_GPL(bL_switcher_get_enabled);
+
+void bL_switcher_put_enabled(void)
+{
+ mutex_unlock(&bL_switcher_activation_lock);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_put_enabled);
+
+/*
+ * Veto any CPU hotplug operation while the switcher is active.
+ * We're just not ready to deal with that given the trickery involved.
+ */
+static int bL_switcher_hotplug_callback(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_DOWN_PREPARE:
+ if (bL_switcher_active)
+ return NOTIFY_BAD;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block bL_switcher_hotplug_notifier =
+ { &bL_switcher_hotplug_callback, NULL, 0 };
+
+#ifdef CONFIG_SCHED_HMP
+static bool no_bL_switcher = true;
+#else
+static bool no_bL_switcher;
+#endif
+core_param(no_bL_switcher, no_bL_switcher, bool, 0644);
+
+static int __init bL_switcher_init(void)
+{
+ int ret;
+
+ if (MAX_NR_CLUSTERS != 2) {
+ pr_err("%s: only dual cluster systems are supported\n", __func__);
+ return -EINVAL;
+ }
+
+ register_cpu_notifier(&bL_switcher_hotplug_notifier);
+
+ if (!no_bL_switcher) {
+ ret = bL_switcher_enable();
+ if (ret)
+ return ret;
+ }
+
+#ifdef CONFIG_SYSFS
+ ret = bL_switcher_sysfs_init();
+ if (ret)
+ pr_err("%s: unable to create sysfs entry\n", __func__);
+#endif
+
+ return 0;
+}
+
+late_initcall(bL_switcher_init);
diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c
new file mode 100644
index 00000000000..5e2dd197e72
--- /dev/null
+++ b/arch/arm/common/bL_switcher_dummy_if.c
@@ -0,0 +1,71 @@
+/*
+ * arch/arm/common/bL_switcher_dummy_if.c -- b.L switcher dummy interface
+ *
+ * Created by: Nicolas Pitre, November 2012
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * Dummy interface to user space for debugging purpose only.
+ *
+ * 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/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <asm/uaccess.h>
+#include <asm/bL_switcher.h>
+
+static ssize_t bL_switcher_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *pos)
+{
+ unsigned char val[3];
+ unsigned int cpu, cluster;
+ int ret;
+
+ pr_debug("%s\n", __func__);
+
+ if (len < 3)
+ return -EINVAL;
+
+ if (copy_from_user(val, buf, 3))
+ return -EFAULT;
+
+ /* format: <cpu#>,<cluster#> */
+ if (val[0] < '0' || val[0] > '4' ||
+ val[1] != ',' ||
+ val[2] < '0' || val[2] > '1')
+ return -EINVAL;
+
+ cpu = val[0] - '0';
+ cluster = val[2] - '0';
+ ret = bL_switch_request(cpu, cluster);
+
+ return ret ? : len;
+}
+
+static const struct file_operations bL_switcher_fops = {
+ .write = bL_switcher_write,
+ .owner = THIS_MODULE,
+};
+
+static struct miscdevice bL_switcher_device = {
+ MISC_DYNAMIC_MINOR,
+ "b.L_switcher",
+ &bL_switcher_fops
+};
+
+static int __init bL_switcher_dummy_if_init(void)
+{
+ return misc_register(&bL_switcher_device);
+}
+
+static void __exit bL_switcher_dummy_if_exit(void)
+{
+ misc_deregister(&bL_switcher_device);
+}
+
+module_init(bL_switcher_dummy_if_init);
+module_exit(bL_switcher_dummy_if_exit);
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 370236dd1a0..4a2b32fd53a 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -27,6 +27,18 @@ void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr)
sync_cache_w(&mcpm_entry_vectors[cluster][cpu]);
}
+extern unsigned long mcpm_entry_early_pokes[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER][2];
+
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+ unsigned long poke_phys_addr, unsigned long poke_val)
+{
+ unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0];
+ poke[0] = poke_phys_addr;
+ poke[1] = poke_val;
+ __cpuc_flush_dcache_area((void *)poke, 8);
+ outer_clean_range(__pa(poke), __pa(poke + 2));
+}
+
static const struct mcpm_platform_ops *platform_ops;
int __init mcpm_platform_register(const struct mcpm_platform_ops *ops)
diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S
index 8178705c4b2..057e9c5a9e1 100644
--- a/arch/arm/common/mcpm_head.S
+++ b/arch/arm/common/mcpm_head.S
@@ -71,12 +71,19 @@ ENTRY(mcpm_entry_point)
* position independent way.
*/
adr r5, 3f
- ldmia r5, {r6, r7, r8, r11}
+ ldmia r5, {r0, r6, r7, r8, r11}
+ add r0, r5, r0 @ r0 = mcpm_entry_early_pokes
add r6, r5, r6 @ r6 = mcpm_entry_vectors
ldr r7, [r5, r7] @ r7 = mcpm_power_up_setup_phys
add r8, r5, r8 @ r8 = mcpm_sync
add r11, r5, r11 @ r11 = first_man_locks
+ @ Perform an early poke, if any
+ add r0, r0, r4, lsl #3
+ ldmia r0, {r0, r1}
+ teq r0, #0
+ strne r1, [r0]
+
mov r0, #MCPM_SYNC_CLUSTER_SIZE
mla r8, r0, r10, r8 @ r8 = sync cluster base
@@ -195,7 +202,8 @@ mcpm_entry_gated:
.align 2
-3: .word mcpm_entry_vectors - .
+3: .word mcpm_entry_early_pokes - .
+ .word mcpm_entry_vectors - 3b
.word mcpm_power_up_setup_phys - 3b
.word mcpm_sync - 3b
.word first_man_locks - 3b
@@ -214,6 +222,10 @@ first_man_locks:
ENTRY(mcpm_entry_vectors)
.space 4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
+ .type mcpm_entry_early_pokes, #object
+ENTRY(mcpm_entry_early_pokes)
+ .space 8 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
+
.type mcpm_power_up_setup_phys, #object
ENTRY(mcpm_power_up_setup_phys)
.space 4 @ set by mcpm_sync_init()
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 7c1bfc0aea0..4928cdacedf 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -105,7 +105,7 @@ static inline void __cpuinit arch_counter_set_user_access(void)
asm volatile("mrc p15, 0, %0, c14, c1, 0" : "=r" (cntkctl));
/* disable user access to everything */
- cntkctl &= ~((3 << 8) | (7 << 0));
+ cntkctl &= ~((3 << 8) | (3 << 0));
asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
}
diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h
new file mode 100644
index 00000000000..482383b45c9
--- /dev/null
+++ b/arch/arm/include/asm/bL_switcher.h
@@ -0,0 +1,83 @@
+/*
+ * arch/arm/include/asm/bL_switcher.h
+ *
+ * Created by: Nicolas Pitre, April 2012
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+ bL_switch_completion_handler completer,
+ void *completer_cookie);
+static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
+{
+ return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL);
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE 0
+#define BL_NOTIFY_POST_ENABLE 1
+#define BL_NOTIFY_PRE_DISABLE 2
+#define BL_NOTIFY_POST_DISABLE 3
+
+#ifdef CONFIG_BL_SWITCHER
+
+void bL_switch_request_detach(unsigned int cpu,
+ bL_switch_completion_handler completer);
+
+int bL_switcher_register_notifier(struct notifier_block *nb);
+int bL_switcher_unregister_notifier(struct notifier_block *nb);
+
+/*
+ * Use these functions to temporarily prevent enabling/disabling of
+ * the switcher.
+ * bL_switcher_get_enabled() returns true if the switcher is currently
+ * enabled. Each call to bL_switcher_get_enabled() must be followed
+ * by a call to bL_switcher_put_enabled(). These functions are not
+ * recursive.
+ */
+bool bL_switcher_get_enabled(void);
+void bL_switcher_put_enabled(void);
+
+int bL_switcher_trace_trigger(void);
+int bL_switcher_get_logical_index(u32 mpidr);
+
+#else
+static void bL_switch_request_detach(unsigned int cpu,
+ bL_switch_completion_handler completer) { }
+
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+#endif /* CONFIG_BL_SWITCHER */
+
+#endif
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 1f3262e99d8..cedd3721318 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -61,6 +61,20 @@ static inline void set_cr(unsigned int val)
isb();
}
+static inline unsigned int get_auxcr(void)
+{
+ unsigned int val;
+ asm("mrc p15, 0, %0, c1, c0, 1 @ get AUXCR" : "=r" (val));
+ return val;
+}
+
+static inline void set_auxcr(unsigned int val)
+{
+ asm volatile("mcr p15, 0, %0, c1, c0, 1 @ set AUXCR"
+ : : "r" (val));
+ isb();
+}
+
#ifndef CONFIG_SMP
extern void adjust_cr(unsigned long mask, unsigned long set);
#endif
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 2740c2a2df6..3d7351c844a 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
#include <linux/threads.h>
#include <asm/irq.h>
-#define NR_IPI 6
+#define NR_IPI 7
typedef struct {
unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 308ad7d6f98..75bf07910b8 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -8,6 +8,8 @@
* published by the Free Software Foundation.
*/
+#include <linux/types.h>
+
#ifndef __ASSEMBLY__
struct tag;
@@ -16,8 +18,10 @@ struct pt_regs;
struct smp_operations;
#ifdef CONFIG_SMP
#define smp_ops(ops) (&(ops))
+#define smp_init_ops(ops) (&(ops))
#else
#define smp_ops(ops) (struct smp_operations *)NULL
+#define smp_init_ops(ops) (bool (*)(void))NULL
#endif
struct machine_desc {
@@ -41,6 +45,7 @@ struct machine_desc {
unsigned char reserve_lp2 :1; /* never has lp2 */
char restart_mode; /* default restart mode */
struct smp_operations *smp; /* SMP operations */
+ bool (*smp_init)(void);
void (*fixup)(struct tag *, char **,
struct meminfo *);
void (*reserve)(void);/* reserve mem blocks */
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 0f7b7620e9a..7626a7fd493 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -42,6 +42,14 @@ extern void mcpm_entry_point(void);
void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
/*
+ * This sets an early poke i.e a value to be poked into some address
+ * from very early assembly code before the CPU is ungated. The
+ * address must be physical, and if 0 then nothing will happen.
+ */
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+ unsigned long poke_phys_addr, unsigned long poke_val);
+
+/*
* CPU/cluster power operations API for higher subsystems to use.
*/
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index f24edad26c7..0cd7824ca76 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -62,9 +62,19 @@ struct pmu_hw_events {
raw_spinlock_t pmu_lock;
};
+struct cpupmu_regs {
+ u32 pmc;
+ u32 pmcntenset;
+ u32 pmuseren;
+ u32 pmintenset;
+ u32 pmxevttype[8];
+ u32 pmxevtcnt[8];
+};
+
struct arm_pmu {
struct pmu pmu;
cpumask_t active_irqs;
+ cpumask_t valid_cpus;
char *name;
irqreturn_t (*handle_irq)(int irq_num, void *dev);
void (*enable)(struct perf_event *event);
@@ -81,6 +91,8 @@ struct arm_pmu {
int (*request_irq)(struct arm_pmu *, irq_handler_t handler);
void (*free_irq)(struct arm_pmu *);
int (*map_event)(struct perf_event *event);
+ void (*save_regs)(struct arm_pmu *, struct cpupmu_regs *);
+ void (*restore_regs)(struct arm_pmu *, struct cpupmu_regs *);
int num_events;
atomic_t active_events;
struct mutex reserve_mutex;
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index ce0dbe7c162..f0a8627c9f1 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -16,6 +16,10 @@
#define PSCI_POWER_STATE_TYPE_STANDBY 0
#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL0 0
+#define PSCI_POWER_STATE_AFFINITY_LEVEL1 1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL2 2
+#define PSCI_POWER_STATE_AFFINITY_LEVEL3 3
struct psci_power_state {
u16 id;
@@ -32,5 +36,22 @@ struct psci_operations {
};
extern struct psci_operations psci_ops;
+extern struct smp_operations psci_smp_ops;
+#ifdef CONFIG_ARM_PSCI
+void psci_init(void);
+bool psci_smp_available(void);
+#else
+static inline void psci_init(void) { }
+static inline bool psci_smp_available(void) { return false; }
+#endif
+
+#ifdef CONFIG_ARM_PSCI
+extern int __init psci_probe(void);
+#else
+static inline int psci_probe(void)
+{
+ return -ENODEV;
+}
+#endif
#endif /* __ASM_ARM_PSCI_H */
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index d3a22bebe6c..610ccf33f5e 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -81,6 +81,8 @@ extern void arch_send_call_function_single_ipi(int cpu);
extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
+extern int register_ipi_completion(struct completion *completion, int cpu);
+
struct smp_operations {
#ifdef CONFIG_SMP
/*
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 58b8b84adcd..983fa7c153a 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -26,11 +26,45 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
const struct cpumask *cpu_coregroup_mask(int cpu);
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask);
+
+#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE
+/* Common values for CPUs */
+#ifndef SD_CPU_INIT
+#define SD_CPU_INIT (struct sched_domain) { \
+ .min_interval = 1, \
+ .max_interval = 4, \
+ .busy_factor = 64, \
+ .imbalance_pct = 125, \
+ .cache_nice_tries = 1, \
+ .busy_idx = 2, \
+ .idle_idx = 1, \
+ .newidle_idx = 0, \
+ .wake_idx = 0, \
+ .forkexec_idx = 0, \
+ \
+ .flags = 0*SD_LOAD_BALANCE \
+ | 1*SD_BALANCE_NEWIDLE \
+ | 1*SD_BALANCE_EXEC \
+ | 1*SD_BALANCE_FORK \
+ | 0*SD_BALANCE_WAKE \
+ | 1*SD_WAKE_AFFINE \
+ | 0*SD_SHARE_CPUPOWER \
+ | 0*SD_SHARE_PKG_RESOURCES \
+ | 0*SD_SERIALIZE \
+ , \
+ .last_balance = jiffies, \
+ .balance_interval = 1, \
+}
+#endif
+#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */
#else
static inline void init_cpu_topology(void) { }
static inline void store_cpu_topology(unsigned int cpuid) { }
+static inline int cluster_to_logical_mask(unsigned int socket_id,
+ cpumask_t *cluster_mask) { return -EINVAL; }
#endif
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5f3338eacad..dd9d90ab65d 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -82,6 +82,9 @@ obj-$(CONFIG_DEBUG_LL) += debug.o
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o
-obj-$(CONFIG_ARM_PSCI) += psci.o
+ifeq ($(CONFIG_ARM_PSCI),y)
+obj-y += psci.o
+obj-$(CONFIG_SMP) += psci_smp.o
+endif
extra-y := $(head-y) vmlinux.lds
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 8bac553fe21..2725c87fade 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -342,7 +342,6 @@ __turn_mmu_on_loc:
.long __turn_mmu_on_end
#if defined(CONFIG_SMP)
- __CPUINIT
ENTRY(secondary_startup)
/*
* Common entry point for secondary CPUs.
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 1fd749ee4a1..1b803117ed9 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -1049,7 +1049,8 @@ static struct notifier_block dbg_cpu_pm_nb = {
static void __init pm_init(void)
{
- cpu_pm_register_notifier(&dbg_cpu_pm_nb);
+ if (has_ossr)
+ cpu_pm_register_notifier(&dbg_cpu_pm_nb);
}
#else
static inline void pm_init(void)
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index e19edc6f2d1..3a9d627cab6 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,6 +12,7 @@
*/
#define pr_fmt(fmt) "hw perfevents: " fmt
+#include <linux/cpumask.h>
#include <linux/kernel.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
@@ -86,6 +87,9 @@ armpmu_map_event(struct perf_event *event,
return armpmu_map_cache_event(cache_map, config);
case PERF_TYPE_RAW:
return armpmu_map_raw_event(raw_event_mask, config);
+ default:
+ if (event->attr.type >= PERF_TYPE_MAX)
+ return armpmu_map_raw_event(raw_event_mask, config);
}
return -ENOENT;
@@ -163,6 +167,8 @@ armpmu_stop(struct perf_event *event, int flags)
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
+ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+ return;
/*
* ARM pmu always has to update the counter, so ignore
* PERF_EF_UPDATE, see comments in armpmu_start().
@@ -179,6 +185,8 @@ static void armpmu_start(struct perf_event *event, int flags)
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
+ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+ return;
/*
* ARM pmu always has to reprogram the period, so ignore
* PERF_EF_RELOAD, see the comment below.
@@ -206,6 +214,9 @@ armpmu_del(struct perf_event *event, int flags)
struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx;
+ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+ return;
+
armpmu_stop(event, PERF_EF_UPDATE);
hw_events->events[idx] = NULL;
clear_bit(idx, hw_events->used_mask);
@@ -222,6 +233,10 @@ armpmu_add(struct perf_event *event, int flags)
int idx;
int err = 0;
+ /* An event following a process won't be stopped earlier */
+ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+ return 0;
+
perf_pmu_disable(event->pmu);
/* If we don't have a space for the counter then finish early. */
@@ -424,6 +439,10 @@ static int armpmu_event_init(struct perf_event *event)
int err = 0;
atomic_t *active_events = &armpmu->active_events;
+ if (event->cpu != -1 &&
+ !cpumask_test_cpu(event->cpu, &armpmu->valid_cpus))
+ return -ENOENT;
+
/* does not support taken branch sampling */
if (has_branch_stack(event))
return -EOPNOTSUPP;
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 1f2740e3dbc..0b48a38e3cf 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -19,6 +19,7 @@
#define pr_fmt(fmt) "CPU PMU: " fmt
#include <linux/bitmap.h>
+#include <linux/cpu_pm.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/of.h>
@@ -31,33 +32,36 @@
#include <asm/pmu.h>
/* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
+static DEFINE_PER_CPU(struct arm_pmu *, cpu_pmu);
static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
+static DEFINE_PER_CPU(struct cpupmu_regs, cpu_pmu_regs);
+
/*
* Despite the names, these two functions are CPU-specific and are used
* by the OProfile/perf code.
*/
const char *perf_pmu_name(void)
{
- if (!cpu_pmu)
+ struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
+ if (!pmu)
return NULL;
- return cpu_pmu->name;
+ return pmu->name;
}
EXPORT_SYMBOL_GPL(perf_pmu_name);
int perf_num_counters(void)
{
- int max_events = 0;
+ struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
- if (cpu_pmu != NULL)
- max_events = cpu_pmu->num_events;
+ if (!pmu)
+ return 0;
- return max_events;
+ return pmu->num_events;
}
EXPORT_SYMBOL_GPL(perf_num_counters);
@@ -75,11 +79,13 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
{
int i, irq, irqs;
struct platform_device *pmu_device = cpu_pmu->plat_device;
+ int cpu = -1;
irqs = min(pmu_device->num_resources, num_possible_cpus());
for (i = 0; i < irqs; ++i) {
- if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+ cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
+ if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
continue;
irq = platform_get_irq(pmu_device, i);
if (irq >= 0)
@@ -91,6 +97,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
{
int i, err, irq, irqs;
struct platform_device *pmu_device = cpu_pmu->plat_device;
+ int cpu = -1;
if (!pmu_device)
return -ENODEV;
@@ -103,6 +110,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
for (i = 0; i < irqs; ++i) {
err = 0;
+ cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
irq = platform_get_irq(pmu_device, i);
if (irq < 0)
continue;
@@ -112,7 +120,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
* assume that we're running on a uniprocessor machine and
* continue. Otherwise, continue without this interrupt.
*/
- if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+ if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
irq, i);
continue;
@@ -126,7 +134,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
return err;
}
- cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+ cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
}
return 0;
@@ -135,7 +143,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
{
int cpu;
- for_each_possible_cpu(cpu) {
+ for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) {
struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
events->events = per_cpu(hw_events, cpu);
events->used_mask = per_cpu(used_mask, cpu);
@@ -148,7 +156,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
/* Ensure the PMU has sane values out of reset. */
if (cpu_pmu->reset)
- on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
+ on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1);
}
/*
@@ -160,21 +168,46 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
static int __cpuinit cpu_pmu_notify(struct notifier_block *b,
unsigned long action, void *hcpu)
{
+ struct arm_pmu *pmu = per_cpu(cpu_pmu, (long)hcpu);
+
if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
return NOTIFY_DONE;
- if (cpu_pmu && cpu_pmu->reset)
- cpu_pmu->reset(cpu_pmu);
+ if (pmu && pmu->reset)
+ pmu->reset(pmu);
else
return NOTIFY_DONE;
return NOTIFY_OK;
}
+static int cpu_pmu_pm_notify(struct notifier_block *b,
+ unsigned long action, void *hcpu)
+{
+ int cpu = smp_processor_id();
+ struct arm_pmu *pmu = per_cpu(cpu_pmu, cpu);
+ struct cpupmu_regs *pmuregs = &per_cpu(cpu_pmu_regs, cpu);
+
+ if (!pmu)
+ return NOTIFY_DONE;
+
+ if (action == CPU_PM_ENTER && pmu->save_regs) {
+ pmu->save_regs(pmu, pmuregs);
+ } else if (action == CPU_PM_EXIT && pmu->restore_regs) {
+ pmu->restore_regs(pmu, pmuregs);
+ }
+
+ return NOTIFY_OK;
+}
+
static struct notifier_block __cpuinitdata cpu_pmu_hotplug_notifier = {
.notifier_call = cpu_pmu_notify,
};
+static struct notifier_block __cpuinitdata cpu_pmu_pm_notifier = {
+ .notifier_call = cpu_pmu_pm_notify,
+};
+
/*
* PMU platform driver and devicetree bindings.
*/
@@ -246,6 +279,9 @@ static int probe_current_pmu(struct arm_pmu *pmu)
}
}
+ /* assume PMU support all the CPUs in this case */
+ cpumask_setall(&pmu->valid_cpus);
+
put_cpu();
return ret;
}
@@ -253,15 +289,10 @@ static int probe_current_pmu(struct arm_pmu *pmu)
static int cpu_pmu_device_probe(struct platform_device *pdev)
{
const struct of_device_id *of_id;
- int (*init_fn)(struct arm_pmu *);
struct device_node *node = pdev->dev.of_node;
struct arm_pmu *pmu;
- int ret = -ENODEV;
-
- if (cpu_pmu) {
- pr_info("attempt to register multiple PMU devices!");
- return -ENOSPC;
- }
+ int ret = 0;
+ int cpu;
pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
if (!pmu) {
@@ -270,8 +301,28 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
}
if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
- init_fn = of_id->data;
- ret = init_fn(pmu);
+ smp_call_func_t init_fn = (smp_call_func_t)of_id->data;
+ struct device_node *ncluster;
+ int cluster = -1;
+ cpumask_t sibling_mask;
+
+ ncluster = of_parse_phandle(node, "cluster", 0);
+ if (ncluster) {
+ int len;
+ const u32 *hwid;
+ hwid = of_get_property(ncluster, "reg", &len);
+ if (hwid && len == 4)
+ cluster = be32_to_cpup(hwid);
+ }
+ /* set sibling mask to all cpu mask if socket is not specified */
+ if (cluster == -1 ||
+ cluster_to_logical_mask(cluster, &sibling_mask))
+ cpumask_setall(&sibling_mask);
+
+ smp_call_function_any(&sibling_mask, init_fn, pmu, 1);
+
+ /* now set the valid_cpus after init */
+ cpumask_copy(&pmu->valid_cpus, &sibling_mask);
} else {
ret = probe_current_pmu(pmu);
}
@@ -281,10 +332,12 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
goto out_free;
}
- cpu_pmu = pmu;
- cpu_pmu->plat_device = pdev;
- cpu_pmu_init(cpu_pmu);
- ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
+ for_each_cpu_mask(cpu, pmu->valid_cpus)
+ per_cpu(cpu_pmu, cpu) = pmu;
+
+ pmu->plat_device = pdev;
+ cpu_pmu_init(pmu);
+ ret = armpmu_register(pmu, -1);
if (!ret)
return 0;
@@ -313,9 +366,17 @@ static int __init register_pmu_driver(void)
if (err)
return err;
+ err = cpu_pm_register_notifier(&cpu_pmu_pm_notifier);
+ if (err) {
+ unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+ return err;
+ }
+
err = platform_driver_register(&cpu_pmu_driver);
- if (err)
+ if (err) {
+ cpu_pm_unregister_notifier(&cpu_pmu_pm_notifier);
unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+ }
return err;
}
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 039cffb053a..654db5030c3 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -950,6 +950,51 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu)
}
#endif
+static void armv7pmu_save_regs(struct arm_pmu *cpu_pmu,
+ struct cpupmu_regs *regs)
+{
+ unsigned int cnt;
+ asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (regs->pmc));
+ if (!(regs->pmc & ARMV7_PMNC_E))
+ return;
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (regs->pmcntenset));
+ asm volatile("mrc p15, 0, %0, c9, c14, 0" : "=r" (regs->pmuseren));
+ asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (regs->pmintenset));
+ asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (regs->pmxevtcnt[0]));
+ for (cnt = ARMV7_IDX_COUNTER0;
+ cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+ armv7_pmnc_select_counter(cnt);
+ asm volatile("mrc p15, 0, %0, c9, c13, 1"
+ : "=r"(regs->pmxevttype[cnt]));
+ asm volatile("mrc p15, 0, %0, c9, c13, 2"
+ : "=r"(regs->pmxevtcnt[cnt]));
+ }
+ return;
+}
+
+static void armv7pmu_restore_regs(struct arm_pmu *cpu_pmu,
+ struct cpupmu_regs *regs)
+{
+ unsigned int cnt;
+ if (!(regs->pmc & ARMV7_PMNC_E))
+ return;
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (regs->pmcntenset));
+ asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r" (regs->pmuseren));
+ asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (regs->pmintenset));
+ asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (regs->pmxevtcnt[0]));
+ for (cnt = ARMV7_IDX_COUNTER0;
+ cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+ armv7_pmnc_select_counter(cnt);
+ asm volatile("mcr p15, 0, %0, c9, c13, 1"
+ : : "r"(regs->pmxevttype[cnt]));
+ asm volatile("mcr p15, 0, %0, c9, c13, 2"
+ : : "r"(regs->pmxevtcnt[cnt]));
+ }
+ asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (regs->pmc));
+}
+
static void armv7pmu_enable_event(struct perf_event *event)
{
unsigned long flags;
@@ -1223,6 +1268,8 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->start = armv7pmu_start;
cpu_pmu->stop = armv7pmu_stop;
cpu_pmu->reset = armv7pmu_reset;
+ cpu_pmu->save_regs = armv7pmu_save_regs;
+ cpu_pmu->restore_regs = armv7pmu_restore_regs;
cpu_pmu->max_period = (1LLU << 32) - 1;
};
@@ -1240,7 +1287,7 @@ static u32 armv7_read_num_pmnc_events(void)
static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A8";
+ cpu_pmu->name = "ARMv7_Cortex_A8";
cpu_pmu->map_event = armv7_a8_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
return 0;
@@ -1249,7 +1296,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A9";
+ cpu_pmu->name = "ARMv7_Cortex_A9";
cpu_pmu->map_event = armv7_a9_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
return 0;
@@ -1258,7 +1305,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A5";
+ cpu_pmu->name = "ARMv7_Cortex_A5";
cpu_pmu->map_event = armv7_a5_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
return 0;
@@ -1267,7 +1314,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A15";
+ cpu_pmu->name = "ARMv7_Cortex_A15";
cpu_pmu->map_event = armv7_a15_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1277,7 +1324,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A7";
+ cpu_pmu->name = "ARMv7_Cortex_A7";
cpu_pmu->map_event = armv7_a7_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index 36531643cc2..0daf4f25228 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -17,6 +17,7 @@
#include <linux/init.h>
#include <linux/of.h>
+#include <linux/string.h>
#include <asm/compiler.h>
#include <asm/errno.h>
@@ -26,6 +27,11 @@
struct psci_operations psci_ops;
+/* Type of psci support. Currently can only be enabled or disabled */
+#define PSCI_SUP_DISABLED 0
+#define PSCI_SUP_ENABLED 1
+
+static unsigned int psci;
static int (*invoke_psci_fn)(u32, u32, u32, u32);
enum psci_function {
@@ -42,6 +48,7 @@ static u32 psci_function_id[PSCI_FN_MAX];
#define PSCI_RET_EOPNOTSUPP -1
#define PSCI_RET_EINVAL -2
#define PSCI_RET_EPERM -3
+#define PSCI_RET_EALREADYON -4
static int psci_to_linux_errno(int errno)
{
@@ -54,6 +61,8 @@ static int psci_to_linux_errno(int errno)
return -EINVAL;
case PSCI_RET_EPERM:
return -EPERM;
+ case PSCI_RET_EALREADYON:
+ return -EAGAIN;
};
return -EINVAL;
@@ -158,15 +167,18 @@ static const struct of_device_id psci_of_match[] __initconst = {
{},
};
-static int __init psci_init(void)
+void __init psci_init(void)
{
struct device_node *np;
const char *method;
u32 id;
+ if (psci == PSCI_SUP_DISABLED)
+ return;
+
np = of_find_matching_node(NULL, psci_of_match);
if (!np)
- return 0;
+ return;
pr_info("probing function IDs from device-tree\n");
@@ -206,6 +218,35 @@ static int __init psci_init(void)
out_put_node:
of_node_put(np);
- return 0;
+ return;
+}
+
+int __init psci_probe(void)
+{
+ struct device_node *np;
+ int ret = -ENODEV;
+
+ if (psci == PSCI_SUP_ENABLED) {
+ np = of_find_matching_node(NULL, psci_of_match);
+ if (np)
+ ret = 0;
+ }
+
+ of_node_put(np);
+ return ret;
+}
+
+static int __init early_psci(char *val)
+{
+ int ret = 0;
+
+ if (strcmp(val, "enable") == 0)
+ psci = PSCI_SUP_ENABLED;
+ else if (strcmp(val, "disable") == 0)
+ psci = PSCI_SUP_DISABLED;
+ else
+ ret = -EINVAL;
+
+ return ret;
}
-early_initcall(psci_init);
+early_param("psci", early_psci);
diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c
new file mode 100644
index 00000000000..23a11424c56
--- /dev/null
+++ b/arch/arm/kernel/psci_smp.c
@@ -0,0 +1,84 @@
+/*
+ * 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.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/init.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/smp.h>
+#include <linux/of.h>
+
+#include <asm/psci.h>
+#include <asm/smp_plat.h>
+
+/*
+ * psci_smp assumes that the following is true about PSCI:
+ *
+ * cpu_suspend Suspend the execution on a CPU
+ * @state we don't currently describe affinity levels, so just pass 0.
+ * @entry_point the first instruction to be executed on return
+ * returns 0 success, < 0 on failure
+ *
+ * cpu_off Power down a CPU
+ * @state we don't currently describe affinity levels, so just pass 0.
+ * no return on successful call
+ *
+ * cpu_on Power up a CPU
+ * @cpuid cpuid of target CPU, as from MPIDR
+ * @entry_point the first instruction to be executed on return
+ * returns 0 success, < 0 on failure
+ *
+ * migrate Migrate the context to a different CPU
+ * @cpuid cpuid of target CPU, as from MPIDR
+ * returns 0 success, < 0 on failure
+ *
+ */
+
+extern void secondary_startup(void);
+
+static int __cpuinit psci_boot_secondary(unsigned int cpu,
+ struct task_struct *idle)
+{
+ if (psci_ops.cpu_on)
+ return psci_ops.cpu_on(cpu_logical_map(cpu),
+ __pa(secondary_startup));
+ return -ENODEV;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void __ref psci_cpu_die(unsigned int cpu)
+{
+ const struct psci_power_state ps = {
+ .type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
+ };
+
+ if (psci_ops.cpu_off)
+ psci_ops.cpu_off(ps);
+
+ /* We should never return */
+ panic("psci: cpu %d failed to shutdown\n", cpu);
+}
+#else
+#define psci_cpu_die NULL
+#endif
+
+bool __init psci_smp_available(void)
+{
+ /* is cpu_on available at least? */
+ return (psci_ops.cpu_on != NULL);
+}
+
+struct smp_operations __initdata psci_smp_ops = {
+ .smp_boot_secondary = psci_boot_secondary,
+ .cpu_die = psci_cpu_die,
+};
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b4b1d397592..6002fe06b12 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -37,6 +37,7 @@
#include <asm/cputype.h>
#include <asm/elf.h>
#include <asm/procinfo.h>
+#include <asm/psci.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
@@ -261,6 +262,19 @@ static int cpu_has_aliasing_icache(unsigned int arch)
int aliasing_icache;
unsigned int id_reg, num_sets, line_size;
+#ifdef CONFIG_BIG_LITTLE
+ /*
+ * We expect a combination of Cortex-A15 and Cortex-A7 cores.
+ * A7 = VIPT aliasing I-cache
+ * A15 = PIPT (non-aliasing) I-cache
+ * To cater for this discrepancy, let's assume aliasing I-cache
+ * all the time. This means unneeded extra work on the A15 but
+ * only ptrace is affected which is not performance critical.
+ */
+ if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0)
+ return 1;
+#endif
+
/* PIPT caches never alias. */
if (icache_is_pipt())
return 0;
@@ -796,9 +810,15 @@ void __init setup_arch(char **cmdline_p)
unflatten_device_tree();
arm_dt_init_cpu_maps();
+ psci_init();
#ifdef CONFIG_SMP
if (is_smp()) {
- smp_set_ops(mdesc->smp);
+ if (!mdesc->smp_init || !mdesc->smp_init()) {
+ if (psci_smp_available())
+ smp_set_ops(&psci_smp_ops);
+ else if (mdesc->smp)
+ smp_set_ops(mdesc->smp);
+ }
smp_init_cpus();
}
#endif
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 987dcf33415..b5c1e636ed8 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -4,6 +4,7 @@
#include <asm/assembler.h>
#include <asm/glue-cache.h>
#include <asm/glue-proc.h>
+#include "entry-header.S"
.text
/*
@@ -30,9 +31,8 @@ ENTRY(__cpu_suspend)
mov r2, r5 @ virtual SP
ldr r3, =sleep_save_sp
#ifdef CONFIG_SMP
- ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
- ALT_UP(mov lr, #0)
- and lr, lr, #15
+ get_thread_info r5
+ ldr lr, [r5, #TI_CPU] @ cpu logical index
add r3, r3, lr, lsl #2
#endif
bl __cpu_suspend_save
@@ -82,10 +82,13 @@ ENDPROC(cpu_resume_after_mmu)
.align
ENTRY(cpu_resume)
#ifdef CONFIG_SMP
+ mov r1, #0 @ fall-back logical index for UP
+ ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
+ ALT_UP_B(1f)
+ bic r0, #0xff000000
+ bl cpu_logical_index @ return logical index in r1
+1:
adr r0, sleep_save_sp
- ALT_SMP(mrc p15, 0, r1, c0, c0, 5)
- ALT_UP(mov r1, #0)
- and r1, r1, #15
ldr r0, [r0, r1, lsl #2] @ stack phys addr
#else
ldr r0, sleep_save_sp @ stack phys addr
@@ -102,3 +105,20 @@ sleep_save_sp:
.rept CONFIG_NR_CPUS
.long 0 @ preserve stack phys ptr here
.endr
+
+#ifdef CONFIG_SMP
+cpu_logical_index:
+ adr r3, cpu_map_ptr
+ ldr r2, [r3]
+ add r3, r3, r2 @ virt_to_phys(__cpu_logical_map)
+ mov r1, #0
+1:
+ ldr r2, [r3, r1, lsl #2]
+ cmp r2, r0
+ moveq pc, lr
+ add r1, r1, #1
+ b 1b
+
+cpu_map_ptr:
+ .long __cpu_logical_map - .
+#endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 5919eb451bb..46e8ab384e6 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -57,7 +57,7 @@ struct secondary_data secondary_data;
* control for which core is the next to come out of the secondary
* boot "holding pen"
*/
-volatile int __cpuinitdata pen_release = -1;
+volatile int pen_release = -1;
enum ipi_msg_type {
IPI_WAKEUP,
@@ -66,6 +66,7 @@ enum ipi_msg_type {
IPI_CALL_FUNC,
IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
+ IPI_COMPLETION,
};
static DECLARE_COMPLETION(cpu_running);
@@ -463,6 +464,7 @@ static const char *ipi_types[NR_IPI] = {
S(IPI_CALL_FUNC, "Function call interrupts"),
S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
S(IPI_CPU_STOP, "CPU stop interrupts"),
+ S(IPI_COMPLETION, "completion interrupts"),
};
void show_ipi_list(struct seq_file *p, int prec)
@@ -588,6 +590,19 @@ static void ipi_cpu_stop(unsigned int cpu)
cpu_relax();
}
+static DEFINE_PER_CPU(struct completion *, cpu_completion);
+
+int register_ipi_completion(struct completion *completion, int cpu)
+{
+ per_cpu(cpu_completion, cpu) = completion;
+ return IPI_COMPLETION;
+}
+
+static void ipi_complete(unsigned int cpu)
+{
+ complete(per_cpu(cpu_completion, cpu));
+}
+
/*
* Main handler for inter-processor interrupts
*/
@@ -638,6 +653,12 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
irq_exit();
break;
+ case IPI_COMPLETION:
+ irq_enter();
+ ipi_complete(cpu);
+ irq_exit();
+ break;
+
default:
printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
cpu, ipinr);
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index c5a59546a25..677da58d9e8 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -23,6 +23,7 @@
#include <linux/slab.h>
#include <asm/cputype.h>
+#include <asm/smp_plat.h>
#include <asm/topology.h>
/*
@@ -289,6 +290,140 @@ void store_cpu_topology(unsigned int cpuid)
cpu_topology[cpuid].socket_id, mpidr);
}
+
+#ifdef CONFIG_SCHED_HMP
+
+static const char * const little_cores[] = {
+ "arm,cortex-a7",
+ NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+ const char * const *lc;
+ for (lc = little_cores; *lc; lc++)
+ if (of_device_is_compatible(cn, *lc))
+ return true;
+ return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+ struct cpumask *slow)
+{
+ struct device_node *cn = NULL;
+ int cpu;
+
+ cpumask_clear(fast);
+ cpumask_clear(slow);
+
+ /*
+ * Use the config options if they are given. This helps testing
+ * HMP scheduling on systems without a big.LITTLE architecture.
+ */
+ if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+ if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+ WARN(1, "Failed to parse HMP fast cpu mask!\n");
+ if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+ WARN(1, "Failed to parse HMP slow cpu mask!\n");
+ return;
+ }
+
+ /*
+ * Else, parse device tree for little cores.
+ */
+ while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+ const u32 *mpidr;
+ int len;
+
+ mpidr = of_get_property(cn, "reg", &len);
+ if (!mpidr || len != 4) {
+ pr_err("* %s missing reg property\n", cn->full_name);
+ continue;
+ }
+
+ cpu = get_logical_index(be32_to_cpup(mpidr));
+ if (cpu == -EINVAL) {
+ pr_err("couldn't get logical index for mpidr %x\n",
+ be32_to_cpup(mpidr));
+ break;
+ }
+
+ if (is_little_cpu(cn))
+ cpumask_set_cpu(cpu, slow);
+ else
+ cpumask_set_cpu(cpu, fast);
+ }
+
+ if (!cpumask_empty(fast) && !cpumask_empty(slow))
+ return;
+
+ /*
+ * We didn't find both big and little cores so let's call all cores
+ * fast as this will keep the system running, with all cores being
+ * treated equal.
+ */
+ cpumask_setall(fast);
+ cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+ struct cpumask hmp_fast_cpu_mask;
+ struct hmp_domain *domain;
+
+ arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+ /*
+ * Initialize hmp_domains
+ * Must be ordered with respect to compute capacity.
+ * Fastest domain at head of list.
+ */
+ if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+ domain = (struct hmp_domain *)
+ kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+ cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+ cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+ list_add(&domain->hmp_domains, hmp_domains_list);
+ }
+ domain = (struct hmp_domain *)
+ kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+ cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+ cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+ list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
+
+/*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id: cluster HW identifier
+ * @cluster_mask: the cpumask location to be initialized, modified by the
+ * function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+ int cpu;
+
+ if (!cluster_mask)
+ return -EINVAL;
+
+ for_each_online_cpu(cpu)
+ if (socket_id == topology_physical_package_id(cpu)) {
+ cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
/*
* init_cpu_topology is called at boot when only one cpu is running
* which prevent simultaneous write access to cpu_topology array
diff --git a/arch/arm/mach-exynos/mach-exynos5-dt.c b/arch/arm/mach-exynos/mach-exynos5-dt.c
index 753b94f3fca..d88234e14f9 100644
--- a/arch/arm/mach-exynos/mach-exynos5-dt.c
+++ b/arch/arm/mach-exynos/mach-exynos5-dt.c
@@ -14,6 +14,7 @@
#include <linux/memblock.h>
#include <linux/io.h>
#include <linux/clocksource.h>
+#include <linux/dma-mapping.h>
#include <asm/mach/arch.h>
#include <mach/regs-pmu.h>
@@ -23,11 +24,31 @@
#include "common.h"
+static u64 dma_mask64 = DMA_BIT_MASK(64);
+
static void __init exynos5_dt_map_io(void)
{
exynos_init_io(NULL, 0);
}
+static int exynos5250_platform_notifier(struct notifier_block *nb,
+ unsigned long event, void *__dev)
+{
+ struct device *dev = __dev;
+
+ if (event != BUS_NOTIFY_ADD_DEVICE)
+ return NOTIFY_DONE;
+
+ dev->dma_mask = &dma_mask64;
+ dev->coherent_dma_mask = DMA_BIT_MASK(64);
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block exynos5250_platform_nb = {
+ .notifier_call = exynos5250_platform_notifier,
+};
+
static void __init exynos5_dt_machine_init(void)
{
struct device_node *i2c_np;
@@ -52,6 +73,11 @@ static void __init exynos5_dt_machine_init(void)
}
}
+ if (config_enabled(CONFIG_ARM_LPAE) &&
+ of_machine_is_compatible("samsung,exynos5250"))
+ bus_register_notifier(&platform_bus_type,
+ &exynos5250_platform_nb);
+
of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
}
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 5907e10c37f..dd3d5975a5c 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -1,5 +1,7 @@
config ARCH_VEXPRESS
bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7
+ select ARCH_HAS_CPUFREQ
+ select ARCH_HAS_OPP
select ARCH_REQUIRE_GPIOLIB
select ARM_AMBA
select ARM_GIC
@@ -56,5 +58,23 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
config ARCH_VEXPRESS_CA9X4
bool "Versatile Express Cortex-A9x4 tile"
+ select ARM_ERRATA_643719
+
+config ARCH_VEXPRESS_DCSCB
+ bool "Dual Cluster System Control Block (DCSCB) support"
+ depends on MCPM
+ select ARM_CCI
+ help
+ Support for the Dual Cluster System Configuration Block (DCSCB).
+ This is needed to provide CPU and cluster power management
+ on RTSM implementing big.LITTLE.
+
+config ARCH_VEXPRESS_TC2
+ bool "TC2 cluster management"
+ depends on MCPM
+ select VEXPRESS_SPC
+ select ARM_CCI
+ help
+ Support for CPU and cluster power management on TC2.
endmenu
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 42703e8b4d3..14193dc7e6e 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -6,5 +6,13 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
obj-y := v2m.o
obj-$(CONFIG_ARCH_VEXPRESS_CA9X4) += ct-ca9x4.o
+obj-$(CONFIG_ARCH_VEXPRESS_DCSCB) += dcscb.o dcscb_setup.o
+CFLAGS_REMOVE_dcscb.o = -pg
+obj-$(CONFIG_ARCH_VEXPRESS_TC2) += tc2_pm.o tc2_pm_setup.o
+CFLAGS_REMOVE_tc2_pm.o = -pg
+ifeq ($(CONFIG_ARCH_VEXPRESS_TC2),y)
+obj-$(CONFIG_ARM_PSCI) += tc2_pm_psci.o
+CFLAGS_REMOVE_tc2_pm_psci.o = -pg
+endif
obj-$(CONFIG_SMP) += platsmp.o
obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o
diff --git a/arch/arm/mach-vexpress/core.h b/arch/arm/mach-vexpress/core.h
index f134cd4a85f..bde4374ab6d 100644
--- a/arch/arm/mach-vexpress/core.h
+++ b/arch/arm/mach-vexpress/core.h
@@ -6,6 +6,8 @@
void vexpress_dt_smp_map_io(void);
+bool vexpress_smp_init_ops(void);
+
extern struct smp_operations vexpress_smp_ops;
extern void vexpress_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
new file mode 100644
index 00000000000..948aec0890f
--- /dev/null
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -0,0 +1,260 @@
+/*
+ * arch/arm/mach-vexpress/dcscb.c - Dual Cluster System Configuration Block
+ *
+ * Created by: Nicolas Pitre, May 2012
+ * Copyright: (C) 2012-2013 Linaro Limited
+ *
+ * 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/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/of_address.h>
+#include <linux/vexpress.h>
+#include <linux/arm-cci.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+#include <asm/psci.h>
+
+
+#define RST_HOLD0 0x0
+#define RST_HOLD1 0x4
+#define SYS_SWRESET 0x8
+#define RST_STAT0 0xc
+#define RST_STAT1 0x10
+#define EAG_CFG_R 0x20
+#define EAG_CFG_W 0x24
+#define KFC_CFG_R 0x28
+#define KFC_CFG_W 0x2c
+#define DCS_CFG_R 0x30
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() while its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t dcscb_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static void __iomem *dcscb_base;
+static int dcscb_use_count[4][2];
+static int dcscb_allcpus_mask[2];
+
+static int dcscb_power_up(unsigned int cpu, unsigned int cluster)
+{
+ unsigned int rst_hold, cpumask = (1 << cpu);
+ unsigned int all_mask = dcscb_allcpus_mask[cluster];
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ if (cpu >= 4 || cluster >= 2)
+ return -EINVAL;
+
+ /*
+ * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+ * variant exists, we need to disable IRQs manually here.
+ */
+ local_irq_disable();
+ arch_spin_lock(&dcscb_lock);
+
+ dcscb_use_count[cpu][cluster]++;
+ if (dcscb_use_count[cpu][cluster] == 1) {
+ rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+ if (rst_hold & (1 << 8)) {
+ /* remove cluster reset and add individual CPU's reset */
+ rst_hold &= ~(1 << 8);
+ rst_hold |= all_mask;
+ }
+ rst_hold &= ~(cpumask | (cpumask << 4));
+ writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+ } else if (dcscb_use_count[cpu][cluster] != 2) {
+ /*
+ * The only possible values are:
+ * 0 = CPU down
+ * 1 = CPU (still) up
+ * 2 = CPU requested to be up before it had a chance
+ * to actually make itself down.
+ * Any other value is a bug.
+ */
+ BUG();
+ }
+
+ arch_spin_unlock(&dcscb_lock);
+ local_irq_enable();
+
+ return 0;
+}
+
+static void dcscb_power_down(void)
+{
+ unsigned int mpidr, cpu, cluster, rst_hold, cpumask, all_mask;
+ bool last_man = false, skip_wfi = false;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+ cpumask = (1 << cpu);
+ all_mask = dcscb_allcpus_mask[cluster];
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cpu >= 4 || cluster >= 2);
+
+ __mcpm_cpu_going_down(cpu, cluster);
+
+ arch_spin_lock(&dcscb_lock);
+ BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+ dcscb_use_count[cpu][cluster]--;
+ if (dcscb_use_count[cpu][cluster] == 0) {
+ rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+ rst_hold |= cpumask;
+ if (((rst_hold | (rst_hold >> 4)) & all_mask) == all_mask) {
+ rst_hold |= (1 << 8);
+ last_man = true;
+ }
+ writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+ } else if (dcscb_use_count[cpu][cluster] == 1) {
+ /*
+ * A power_up request went ahead of us.
+ * Even if we do not want to shut this CPU down,
+ * the caller expects a certain state as if the WFI
+ * was aborted. So let's continue with cache cleaning.
+ */
+ skip_wfi = true;
+ } else
+ BUG();
+
+ if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+ arch_spin_unlock(&dcscb_lock);
+
+ /*
+ * Flush all cache levels for this cluster.
+ *
+ * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
+ * a preliminary flush here for those CPUs. At least, that's
+ * the theory -- without the extra flush, Linux explodes on
+ * RTSM (to be investigated).
+ */
+ flush_cache_all();
+ set_cr(get_cr() & ~CR_C);
+ flush_cache_all();
+
+ /*
+ * This is a harmless no-op. On platforms with a real
+ * outer cache this might either be needed or not,
+ * depending on where the outer cache sits.
+ */
+ outer_flush_all();
+
+ /* Disable local coherency by clearing the ACTLR "SMP" bit: */
+ set_auxcr(get_auxcr() & ~(1 << 6));
+
+ /*
+ * Disable cluster-level coherency by masking
+ * incoming snoops and DVM messages:
+ */
+ cci_disable_port_by_cpu(mpidr);
+
+ __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+ } else {
+ arch_spin_unlock(&dcscb_lock);
+
+ /*
+ * Flush the local CPU cache.
+ *
+ * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
+ * a preliminary flush here for those CPUs. At least, that's
+ * the theory -- without the extra flush, Linux explodes on
+ * RTSM (to be investigated).
+ */
+ flush_cache_louis();
+ set_cr(get_cr() & ~CR_C);
+ flush_cache_louis();
+
+ /* Disable local coherency by clearing the ACTLR "SMP" bit: */
+ set_auxcr(get_auxcr() & ~(1 << 6));
+ }
+
+ __mcpm_cpu_down(cpu, cluster);
+
+ /* Now we are prepared for power-down, do it: */
+ dsb();
+ if (!skip_wfi)
+ wfi();
+
+ /* Not dead at this point? Let our caller cope. */
+}
+
+static const struct mcpm_platform_ops dcscb_power_ops = {
+ .power_up = dcscb_power_up,
+ .power_down = dcscb_power_down,
+};
+
+static void __init dcscb_usage_count_init(void)
+{
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cpu >= 4 || cluster >= 2);
+ dcscb_use_count[cpu][cluster] = 1;
+}
+
+extern void dcscb_power_up_setup(unsigned int affinity_level);
+
+static int __init dcscb_init(void)
+{
+ struct device_node *node;
+ unsigned int cfg;
+ int ret;
+
+ ret = psci_probe();
+ if (!ret) {
+ pr_debug("psci found. Aborting native init\n");
+ return -ENODEV;
+ }
+
+ if (!cci_probed())
+ return -ENODEV;
+
+ node = of_find_compatible_node(NULL, NULL, "arm,rtsm,dcscb");
+ if (!node)
+ return -ENODEV;
+ dcscb_base = of_iomap(node, 0);
+ if (!dcscb_base)
+ return -EADDRNOTAVAIL;
+ cfg = readl_relaxed(dcscb_base + DCS_CFG_R);
+ dcscb_allcpus_mask[0] = (1 << (((cfg >> 16) >> (0 << 2)) & 0xf)) - 1;
+ dcscb_allcpus_mask[1] = (1 << (((cfg >> 16) >> (1 << 2)) & 0xf)) - 1;
+ dcscb_usage_count_init();
+
+ ret = mcpm_platform_register(&dcscb_power_ops);
+ if (!ret)
+ ret = mcpm_sync_init(dcscb_power_up_setup);
+ if (ret) {
+ iounmap(dcscb_base);
+ return ret;
+ }
+
+ pr_info("VExpress DCSCB support installed\n");
+
+ /*
+ * Future entries into the kernel can now go
+ * through the cluster entry vectors.
+ */
+ vexpress_flags_set(virt_to_phys(mcpm_entry_point));
+
+ return 0;
+}
+
+early_initcall(dcscb_init);
diff --git a/arch/arm/mach-vexpress/dcscb_setup.S b/arch/arm/mach-vexpress/dcscb_setup.S
new file mode 100644
index 00000000000..4bb7fbe0f62
--- /dev/null
+++ b/arch/arm/mach-vexpress/dcscb_setup.S
@@ -0,0 +1,38 @@
+/*
+ * arch/arm/include/asm/dcscb_setup.S
+ *
+ * Created by: Dave Martin, 2012-06-22
+ * Copyright: (C) 2012-2013 Linaro Limited
+ *
+ * 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/linkage.h>
+
+
+ENTRY(dcscb_power_up_setup)
+
+ cmp r0, #0 @ check affinity level
+ beq 2f
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ * The ACTLR SMP bit does not need to be set here, because cpu_resume()
+ * already restores that.
+ *
+ * A15/A7 may not require explicit L2 invalidation on reset, dependent
+ * on hardware integration decisions.
+ * For now, this code assumes that L2 is either already invalidated,
+ * or invalidation is not required.
+ */
+
+ b cci_enable_port_for_self
+
+2: @ Implementation-specific local CPU setup operations should go here,
+ @ if any. In this case, there is nothing to do.
+
+ bx lr
+
+ENDPROC(dcscb_power_up_setup)
diff --git a/arch/arm/mach-vexpress/include/mach/tc2.h b/arch/arm/mach-vexpress/include/mach/tc2.h
new file mode 100644
index 00000000000..d3b5a2225a0
--- /dev/null
+++ b/arch/arm/mach-vexpress/include/mach/tc2.h
@@ -0,0 +1,10 @@
+#ifndef __MACH_TC2_H
+#define __MACH_TC2_H
+
+/*
+ * cpu and cluster limits
+ */
+#define TC2_MAX_CPUS 3
+#define TC2_MAX_CLUSTERS 2
+
+#endif
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index dc1ace55d55..993c9ae5dc5 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -12,9 +12,11 @@
#include <linux/errno.h>
#include <linux/smp.h>
#include <linux/io.h>
+#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/vexpress.h>
+#include <asm/mcpm.h>
#include <asm/smp_scu.h>
#include <asm/mach/map.h>
@@ -203,3 +205,21 @@ struct smp_operations __initdata vexpress_smp_ops = {
.cpu_die = vexpress_cpu_die,
#endif
};
+
+bool __init vexpress_smp_init_ops(void)
+{
+#ifdef CONFIG_MCPM
+ /*
+ * The best way to detect a multi-cluster configuration at the moment
+ * is to look for the presence of a CCI in the system.
+ * Override the default vexpress_smp_ops if so.
+ */
+ struct device_node *node;
+ node = of_find_compatible_node(NULL, NULL, "arm,cci-400");
+ if (node && of_device_is_available(node)) {
+ mcpm_smp_set_ops();
+ return true;
+ }
+#endif
+ return false;
+}
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
new file mode 100644
index 00000000000..9c742edb7ae
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -0,0 +1,271 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm.c - TC2 power management support
+ *
+ * Created by: Nicolas Pitre, October 2012
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * Some portions of this file were originally written by Achin Gupta
+ * Copyright: (C) 2012 ARM Limited
+ *
+ * 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/init.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+#include <asm/psci.h>
+
+#include <mach/motherboard.h>
+#include <mach/tc2.h>
+
+#include <linux/vexpress.h>
+#include <linux/arm-cci.h>
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() after its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t tc2_pm_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static int tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS];
+
+static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster)
+{
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ if (cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster))
+ return -EINVAL;
+
+ /*
+ * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+ * variant exists, we need to disable IRQs manually here.
+ */
+ local_irq_disable();
+ arch_spin_lock(&tc2_pm_lock);
+
+ if (!tc2_pm_use_count[0][cluster] &&
+ !tc2_pm_use_count[1][cluster] &&
+ !tc2_pm_use_count[2][cluster])
+ vexpress_spc_powerdown_enable(cluster, 0);
+
+ tc2_pm_use_count[cpu][cluster]++;
+ if (tc2_pm_use_count[cpu][cluster] == 1) {
+ vexpress_spc_write_resume_reg(cluster, cpu,
+ virt_to_phys(mcpm_entry_point));
+ vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1);
+ } else if (tc2_pm_use_count[cpu][cluster] != 2) {
+ /*
+ * The only possible values are:
+ * 0 = CPU down
+ * 1 = CPU (still) up
+ * 2 = CPU requested to be up before it had a chance
+ * to actually make itself down.
+ * Any other value is a bug.
+ */
+ BUG();
+ }
+
+ arch_spin_unlock(&tc2_pm_lock);
+ local_irq_enable();
+
+ return 0;
+}
+
+static void tc2_pm_down(u64 residency)
+{
+ unsigned int mpidr, cpu, cluster;
+ bool last_man = false, skip_wfi = false;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+ __mcpm_cpu_going_down(cpu, cluster);
+
+ arch_spin_lock(&tc2_pm_lock);
+ BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+ tc2_pm_use_count[cpu][cluster]--;
+ if (tc2_pm_use_count[cpu][cluster] == 0) {
+ vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1);
+ if (!tc2_pm_use_count[0][cluster] &&
+ !tc2_pm_use_count[1][cluster] &&
+ !tc2_pm_use_count[2][cluster] &&
+ (!residency || residency > 5000)) {
+ vexpress_spc_powerdown_enable(cluster, 1);
+ vexpress_spc_set_global_wakeup_intr(1);
+ last_man = true;
+ }
+ } else if (tc2_pm_use_count[cpu][cluster] == 1) {
+ /*
+ * A power_up request went ahead of us.
+ * Even if we do not want to shut this CPU down,
+ * the caller expects a certain state as if the WFI
+ * was aborted. So let's continue with cache cleaning.
+ */
+ skip_wfi = true;
+ } else
+ BUG();
+
+ gic_cpu_if_down();
+
+ if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+ arch_spin_unlock(&tc2_pm_lock);
+
+ set_cr(get_cr() & ~CR_C);
+ flush_cache_all();
+ asm volatile ("clrex");
+ set_auxcr(get_auxcr() & ~(1 << 6));
+
+ cci_disable_port_by_cpu(mpidr);
+
+ /*
+ * Ensure that both C & I bits are disabled in the SCTLR
+ * before disabling ACE snoops. This ensures that no
+ * coherency traffic will originate from this cpu after
+ * ACE snoops are turned off.
+ */
+ cpu_proc_fin();
+
+ __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+ } else {
+ /*
+ * If last man then undo any setup done previously.
+ */
+ if (last_man) {
+ vexpress_spc_powerdown_enable(cluster, 0);
+ vexpress_spc_set_global_wakeup_intr(0);
+ }
+
+ arch_spin_unlock(&tc2_pm_lock);
+
+ set_cr(get_cr() & ~CR_C);
+ flush_cache_louis();
+ asm volatile ("clrex");
+ set_auxcr(get_auxcr() & ~(1 << 6));
+ }
+
+ __mcpm_cpu_down(cpu, cluster);
+
+ /* Now we are prepared for power-down, do it: */
+ if (!skip_wfi)
+ wfi();
+
+ /* Not dead at this point? Let our caller cope. */
+}
+
+static void tc2_pm_power_down(void)
+{
+ tc2_pm_down(0);
+}
+
+static void tc2_pm_suspend(u64 residency)
+{
+ extern void tc2_resume(void);
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+ vexpress_spc_write_resume_reg(cluster, cpu,
+ virt_to_phys(tc2_resume));
+
+ tc2_pm_down(residency);
+}
+
+static void tc2_pm_powered_up(void)
+{
+ unsigned int mpidr, cpu, cluster;
+ unsigned long flags;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+ local_irq_save(flags);
+ arch_spin_lock(&tc2_pm_lock);
+
+ if (!tc2_pm_use_count[0][cluster] &&
+ !tc2_pm_use_count[1][cluster] &&
+ !tc2_pm_use_count[2][cluster]) {
+ vexpress_spc_powerdown_enable(cluster, 0);
+ vexpress_spc_set_global_wakeup_intr(0);
+ }
+
+ if (!tc2_pm_use_count[cpu][cluster])
+ tc2_pm_use_count[cpu][cluster] = 1;
+
+ vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 0);
+ vexpress_spc_write_resume_reg(cluster, cpu, 0);
+
+ arch_spin_unlock(&tc2_pm_lock);
+ local_irq_restore(flags);
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+ .power_up = tc2_pm_power_up,
+ .power_down = tc2_pm_power_down,
+ .suspend = tc2_pm_suspend,
+ .powered_up = tc2_pm_powered_up,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+ tc2_pm_use_count[cpu][cluster] = 1;
+}
+
+extern void tc2_pm_power_up_setup(unsigned int affinity_level);
+
+static int __init tc2_pm_init(void)
+{
+ int ret;
+
+ ret = psci_probe();
+ if (!ret) {
+ pr_debug("psci found. Aborting native init\n");
+ return -ENODEV;
+ }
+
+ if (!vexpress_spc_check_loaded())
+ return -ENODEV;
+
+ tc2_pm_usage_count_init();
+
+ ret = mcpm_platform_register(&tc2_pm_power_ops);
+ if (!ret)
+ ret = mcpm_sync_init(tc2_pm_power_up_setup);
+ if (!ret)
+ pr_info("TC2 power management initialized\n");
+ return ret;
+}
+
+early_initcall(tc2_pm_init);
diff --git a/arch/arm/mach-vexpress/tc2_pm_psci.c b/arch/arm/mach-vexpress/tc2_pm_psci.c
new file mode 100644
index 00000000000..c2fdc22e4c0
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_psci.c
@@ -0,0 +1,173 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm_psci.c - TC2 PSCI support
+ *
+ * Created by: Achin Gupta, December 2012
+ * Copyright: (C) 2012 ARM Limited
+ *
+ * Some portions of this file were originally written by Nicolas Pitre
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * 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/init.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/psci.h>
+#include <asm/atomic.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+
+#include <mach/motherboard.h>
+#include <mach/tc2.h>
+
+#include <linux/vexpress.h>
+
+/*
+ * Platform specific state id understood by the firmware and used to
+ * program the power controller
+ */
+#define PSCI_POWER_STATE_ID 0
+
+static atomic_t tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS];
+
+static int tc2_pm_psci_power_up(unsigned int cpu, unsigned int cluster)
+{
+ unsigned int mpidr = (cluster << 8) | cpu;
+ int ret = 0;
+
+ BUG_ON(!psci_ops.cpu_on);
+
+ switch (atomic_inc_return(&tc2_pm_use_count[cpu][cluster])) {
+ case 1:
+ /*
+ * This is a request to power up a cpu that linux thinks has
+ * been powered down. Retries are needed if the firmware has
+ * seen the power down request as yet.
+ */
+ do
+ ret = psci_ops.cpu_on(mpidr,
+ virt_to_phys(mcpm_entry_point));
+ while (ret == -EAGAIN);
+
+ return ret;
+ case 2:
+ /* This power up request has overtaken a power down request */
+ return ret;
+ default:
+ /* Any other value is a bug */
+ BUG();
+ }
+}
+
+static void tc2_pm_psci_power_down(void)
+{
+ struct psci_power_state power_state;
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ BUG_ON(!psci_ops.cpu_off);
+
+ switch (atomic_dec_return(&tc2_pm_use_count[cpu][cluster])) {
+ case 1:
+ /*
+ * Overtaken by a power up. Flush caches, exit coherency,
+ * return & fake a reset
+ */
+ set_cr(get_cr() & ~CR_C);
+
+ flush_cache_louis();
+
+ asm volatile ("clrex");
+ set_auxcr(get_auxcr() & ~(1 << 6));
+
+ return;
+ case 0:
+ /* A normal request to possibly power down the cluster */
+ power_state.id = PSCI_POWER_STATE_ID;
+ power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+ power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+ psci_ops.cpu_off(power_state);
+
+ /* On success this function never returns */
+ default:
+ /* Any other value is a bug */
+ BUG();
+ }
+}
+
+static void tc2_pm_psci_suspend(u64 unused)
+{
+ struct psci_power_state power_state;
+
+ BUG_ON(!psci_ops.cpu_suspend);
+
+ /* On TC2 always attempt to power down the cluster */
+ power_state.id = PSCI_POWER_STATE_ID;
+ power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+ power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+ psci_ops.cpu_suspend(power_state, virt_to_phys(mcpm_entry_point));
+
+ /* On success this function never returns */
+ BUG();
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+ .power_up = tc2_pm_psci_power_up,
+ .power_down = tc2_pm_psci_power_down,
+ .suspend = tc2_pm_psci_suspend,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+ atomic_set(&tc2_pm_use_count[cpu][cluster], 1);
+}
+
+static int __init tc2_pm_psci_init(void)
+{
+ int ret;
+
+ ret = psci_probe();
+ if (ret) {
+ pr_debug("psci not found. Aborting psci init\n");
+ return -ENODEV;
+ }
+
+ if (!vexpress_spc_check_loaded()) {
+ pr_debug("spc not found. Aborting psci init\n");
+ return -ENODEV;
+ }
+
+ tc2_pm_usage_count_init();
+
+ ret = mcpm_platform_register(&tc2_pm_power_ops);
+ if (!ret)
+ ret = mcpm_sync_init(NULL);
+ if (!ret)
+ pr_info("TC2 power management initialized\n");
+ return ret;
+}
+
+early_initcall(tc2_pm_psci_init);
diff --git a/arch/arm/mach-vexpress/tc2_pm_setup.S b/arch/arm/mach-vexpress/tc2_pm_setup.S
new file mode 100644
index 00000000000..a18dafeeb0e
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_setup.S
@@ -0,0 +1,68 @@
+/*
+ * arch/arm/include/asm/tc2_pm_setup.S
+ *
+ * Created by: Nicolas Pitre, October 2012
+ ( (based on dcscb_setup.S by Dave Martin)
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * 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/linkage.h>
+#include <asm/mcpm.h>
+
+
+#define SPC_PHYS_BASE 0x7FFF0000
+#define SPC_WAKE_INT_STAT 0xb2c
+
+#define SNOOP_CTL_A15 0x404
+#define SNOOP_CTL_A7 0x504
+
+#define A15_SNOOP_MASK (0x3 << 7)
+#define A7_SNOOP_MASK (0x1 << 13)
+
+#define A15_BX_ADDR0 0xB68
+
+
+ENTRY(tc2_resume)
+ mrc p15, 0, r0, c0, c0, 5
+ ubfx r1, r0, #0, #4 @ r1 = cpu
+ ubfx r2, r0, #8, #4 @ r2 = cluster
+ add r1, r1, r2, lsl #2 @ r1 = index of CPU in WAKE_INT_STAT
+ ldr r3, =SPC_PHYS_BASE + SPC_WAKE_INT_STAT
+ ldr r3, [r3]
+ lsr r3, r1
+ tst r3, #1
+ wfieq @ if no pending IRQ reenters wfi
+ b mcpm_entry_point
+ENDPROC(tc2_resume)
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ * The ACTLR SMP bit does not need to be set here, because cpu_resume()
+ * already restores that.
+ */
+
+ENTRY(tc2_pm_power_up_setup)
+
+ cmp r0, #0
+ beq 2f
+
+ b cci_enable_port_for_self
+
+2: @ Clear the BX addr register
+ ldr r3, =SPC_PHYS_BASE + A15_BX_ADDR0
+ mrc p15, 0, r0, c0, c0, 5 @ MPIDR
+ ubfx r1, r0, #8, #4 @ cluster
+ ubfx r0, r0, #0, #4 @ cpu
+ add r3, r3, r1, lsl #4
+ mov r1, #0
+ str r1, [r3, r0, lsl #2]
+ dsb
+
+ bx lr
+
+ENDPROC(tc2_pm_power_up_setup)
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 8802030df98..057f99b62ea 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -10,6 +10,7 @@
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/irqchip.h>
+#include <linux/memblock.h>
#include <linux/of_address.h>
#include <linux/of_fdt.h>
#include <linux/of_irq.h>
@@ -373,6 +374,31 @@ MACHINE_START(VEXPRESS, "ARM-Versatile Express")
.init_machine = v2m_init,
MACHINE_END
+static void __init v2m_dt_hdlcd_init(void)
+{
+ struct device_node *node;
+ int len, na, ns;
+ const __be32 *prop;
+ phys_addr_t fb_base, fb_size;
+
+ node = of_find_compatible_node(NULL, NULL, "arm,hdlcd");
+ if (!node)
+ return;
+
+ na = of_n_addr_cells(node);
+ ns = of_n_size_cells(node);
+
+ prop = of_get_property(node, "framebuffer", &len);
+ if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+ return;
+
+ fb_base = of_read_number(prop, na);
+ fb_size = of_read_number(prop + na, ns);
+
+ if (WARN_ON(memblock_remove(fb_base, fb_size)))
+ return;
+};
+
static struct map_desc v2m_rs1_io_desc __initdata = {
.virtual = V2M_PERIPH,
.pfn = __phys_to_pfn(0x1c000000),
@@ -423,6 +449,8 @@ void __init v2m_dt_init_early(void)
pr_warning("vexpress: DT HBI (%x) is not matching "
"hardware (%x)!\n", dt_hbi, hbi);
}
+
+ v2m_dt_hdlcd_init();
}
static void __init v2m_dt_timer_init(void)
@@ -456,6 +484,7 @@ static const char * const v2m_dt_match[] __initconst = {
DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express")
.dt_compat = v2m_dt_match,
.smp = smp_ops(vexpress_smp_ops),
+ .smp_init = smp_init_ops(vexpress_smp_init_ops),
.map_io = v2m_dt_map_io,
.init_early = v2m_dt_init_early,
.init_irq = irqchip_init,
diff --git a/arch/arm/mach-virt/Makefile b/arch/arm/mach-virt/Makefile
index 042afc1f8c4..7ddbfa60227 100644
--- a/arch/arm/mach-virt/Makefile
+++ b/arch/arm/mach-virt/Makefile
@@ -3,4 +3,3 @@
#
obj-y := virt.o
-obj-$(CONFIG_SMP) += platsmp.o
diff --git a/arch/arm/mach-virt/platsmp.c b/arch/arm/mach-virt/platsmp.c
deleted file mode 100644
index f4143f5bfa5..00000000000
--- a/arch/arm/mach-virt/platsmp.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Dummy Virtual Machine - does what it says on the tin.
- *
- * Copyright (C) 2012 ARM Ltd
- * Author: Will Deacon <will.deacon@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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/of.h>
-
-#include <asm/psci.h>
-#include <asm/smp_plat.h>
-
-extern void secondary_startup(void);
-
-static void __init virt_smp_init_cpus(void)
-{
-}
-
-static void __init virt_smp_prepare_cpus(unsigned int max_cpus)
-{
-}
-
-static int __cpuinit virt_boot_secondary(unsigned int cpu,
- struct task_struct *idle)
-{
- if (psci_ops.cpu_on)
- return psci_ops.cpu_on(cpu_logical_map(cpu),
- __pa(secondary_startup));
- return -ENODEV;
-}
-
-struct smp_operations __initdata virt_smp_ops = {
- .smp_init_cpus = virt_smp_init_cpus,
- .smp_prepare_cpus = virt_smp_prepare_cpus,
- .smp_boot_secondary = virt_boot_secondary,
-};
diff --git a/arch/arm/mach-virt/virt.c b/arch/arm/mach-virt/virt.c
index 061f283f579..a67d2dd5bb6 100644
--- a/arch/arm/mach-virt/virt.c
+++ b/arch/arm/mach-virt/virt.c
@@ -36,11 +36,8 @@ static const char *virt_dt_match[] = {
NULL
};
-extern struct smp_operations virt_smp_ops;
-
DT_MACHINE_START(VIRT, "Dummy Virtual Machine")
.init_irq = irqchip_init,
.init_machine = virt_init,
- .smp = smp_ops(virt_smp_ops),
.dt_compat = virt_dt_match,
MACHINE_END
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 5dbf13f954f..e207aa5f846 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -446,8 +446,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
if (pud_none(*pud_k))
goto bad_area;
- if (!pud_present(*pud))
+ if (!pud_present(*pud)) {
set_pud(pud, *pud_k);
+ /*
+ * There is a small window during free_pgtables() where the
+ * user *pud entry is 0 but the TLB has not been invalidated
+ * and we get a level 2 (pmd) translation fault caused by the
+ * intermediate TLB caching of the old level 1 (pud) entry.
+ */
+ flush_tlb_kernel_page(addr);
+ }
pmd = pmd_offset(pud, addr);
pmd_k = pmd_offset(pud_k, addr);
@@ -470,8 +478,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
#endif
if (pmd_none(pmd_k[index]))
goto bad_area;
+ if (!pmd_present(pmd[index]))
+ copy_pmd(pmd, pmd_k);
- copy_pmd(pmd, pmd_k);
return 0;
bad_area:
diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S
index b178d44e9ea..2677bc3762d 100644
--- a/arch/arm/plat-versatile/headsmp.S
+++ b/arch/arm/plat-versatile/headsmp.S
@@ -11,8 +11,6 @@
#include <linux/linkage.h>
#include <linux/init.h>
- __INIT
-
/*
* Realview/Versatile Express specific entry point for secondary CPUs.
* This provides a "holding pen" into which all secondary cores are held