diff options
Diffstat (limited to 'arch/arm')
144 files changed, 2407 insertions, 924 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 13b739469c5..00bdfdbdd4a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -58,6 +58,7 @@ config ARM select CLONE_BACKWARDS select OLD_SIGSUSPEND3 select OLD_SIGACTION + select HAVE_CONTEXT_TRACKING help The ARM series is a line of low-power-consumption RISC chip designs licensed by ARM Ltd and targeted at embedded applications and @@ -1183,9 +1184,9 @@ config ARM_NR_BANKS default 8 config IWMMXT - bool "Enable iWMMXt support" + bool "Enable iWMMXt support" if !CPU_PJ4 depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4 - default y if PXA27x || PXA3xx || ARCH_MMP + default y if PXA27x || PXA3xx || ARCH_MMP || CPU_PJ4 help Enable support for iWMMXt context switching at run time if running on a CPU that supports it. @@ -1439,6 +1440,16 @@ config ARM_ERRATA_775420 to deadlock. This workaround puts DSB before executing ISB if an abort may occur on cache maintenance. +config ARM_ERRATA_798181 + bool "ARM errata: TLBI/DSB failure on Cortex-A15" + depends on CPU_V7 && SMP + help + On Cortex-A15 (r0p0..r3p2) the TLBI*IS/DSB operations are not + adequately shooting down all use of the old entries. This + option enables the Linux kernel workaround for this erratum + which sends an IPI to the CPUs that are running the same ASID + as the one being invalidated. + endmenu source "arch/arm/common/Kconfig" @@ -1596,6 +1607,14 @@ config HAVE_ARM_TWD help This options enables support for the ARM timer and watchdog unit +config MCPM + bool "Multi-Cluster Power Management" + depends on CPU_V7 && SMP + help + This option provides the common power management infrastructure + for (multi-)cluster based systems, such as big.LITTLE based + systems. + choice prompt "Memory split" default VMSPLIT_3G @@ -1683,8 +1702,9 @@ config SCHED_HRTICK def_bool HIGH_RES_TIMERS config THUMB2_KERNEL - bool "Compile the kernel in Thumb-2 mode" + bool "Compile the kernel in Thumb-2 mode" if !CPU_THUMBONLY depends on CPU_V7 && !CPU_V6 && !CPU_V6K + default y if CPU_THUMBONLY select AEABI select ARM_ASM_UNIFIED select ARM_UNWIND diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index ecfcdba2d17..791fbeba40c 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -495,6 +495,7 @@ config DEBUG_IMX_UART_PORT DEBUG_IMX53_UART || \ DEBUG_IMX6Q_UART default 1 + depends on ARCH_MXC help Choose UART port on which kernel low-level debug messages should be output. @@ -601,6 +602,17 @@ config DEBUG_LL_INCLUDE default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1 default "mach/debug-macro.S" +config DEBUG_UNCOMPRESS + bool + default y if ARCH_MULTIPLATFORM && DEBUG_LL && \ + !DEBUG_OMAP2PLUS_UART && \ + !DEBUG_TEGRA_UART + +config UNCOMPRESS_INCLUDE + string + default "debug/uncompress.h" if ARCH_MULTIPLATFORM + default "mach/uncompress.h" + config EARLY_PRINTK bool "Early printk" depends on DEBUG_LL diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index afed28e37ea..3580d57ea21 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -24,6 +24,9 @@ endif AFLAGS_head.o += -DTEXT_OFFSET=$(TEXT_OFFSET) HEAD = head.o OBJS += misc.o decompress.o +ifeq ($(CONFIG_DEBUG_UNCOMPRESS),y) +OBJS += debug.o +endif FONTC = $(srctree)/drivers/video/console/font_acorn_8x8.c # string library code (-Os is enforced to keep it much smaller) diff --git a/arch/arm/boot/compressed/debug.S b/arch/arm/boot/compressed/debug.S new file mode 100644 index 00000000000..6e8382d5b7a --- /dev/null +++ b/arch/arm/boot/compressed/debug.S @@ -0,0 +1,12 @@ +#include <linux/linkage.h> +#include <asm/assembler.h> + +#include CONFIG_DEBUG_LL_INCLUDE + +ENTRY(putc) + addruart r1, r2, r3 + waituart r3, r1 + senduart r0, r1 + busyuart r3, r1 + mov pc, lr +ENDPROC(putc) diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c index df899834d84..31bd43b8209 100644 --- a/arch/arm/boot/compressed/misc.c +++ b/arch/arm/boot/compressed/misc.c @@ -25,13 +25,7 @@ unsigned int __machine_arch_type; static void putstr(const char *ptr); extern void error(char *x); -#ifdef CONFIG_ARCH_MULTIPLATFORM -static inline void putc(int c) {} -static inline void flush(void) {} -static inline void arch_decomp_setup(void) {} -#else -#include <mach/uncompress.h> -#endif +#include CONFIG_UNCOMPRESS_INCLUDE #ifdef CONFIG_DEBUG_ICEDCC diff --git a/arch/arm/boot/dts/armada-370-mirabox.dts b/arch/arm/boot/dts/armada-370-mirabox.dts index dd0c57dd9f3..3234875824d 100644 --- a/arch/arm/boot/dts/armada-370-mirabox.dts +++ b/arch/arm/boot/dts/armada-370-mirabox.dts @@ -54,7 +54,7 @@ }; mvsdio@d00d4000 { - pinctrl-0 = <&sdio_pins2>; + pinctrl-0 = <&sdio_pins3>; pinctrl-names = "default"; status = "okay"; /* diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi index 8188d138020..a195debb67d 100644 --- a/arch/arm/boot/dts/armada-370.dtsi +++ b/arch/arm/boot/dts/armada-370.dtsi @@ -59,6 +59,12 @@ "mpp50", "mpp51", "mpp52"; marvell,function = "sd0"; }; + + sdio_pins3: sdio-pins3 { + marvell,pins = "mpp48", "mpp49", "mpp50", + "mpp51", "mpp52", "mpp53"; + marvell,function = "sd0"; + }; }; gpio0: gpio@d0018100 { diff --git a/arch/arm/boot/dts/dbx5x0.dtsi b/arch/arm/boot/dts/dbx5x0.dtsi index 9de93096601..aaa63d0a809 100644 --- a/arch/arm/boot/dts/dbx5x0.dtsi +++ b/arch/arm/boot/dts/dbx5x0.dtsi @@ -191,8 +191,8 @@ prcmu: prcmu@80157000 { compatible = "stericsson,db8500-prcmu"; - reg = <0x80157000 0x1000>; - reg-names = "prcmu"; + reg = <0x80157000 0x1000>, <0x801b0000 0x8000>, <0x801b8000 0x1000>; + reg-names = "prcmu", "prcmu-tcpm", "prcmu-tcdm"; interrupts = <0 47 0x4>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/imx28-m28evk.dts b/arch/arm/boot/dts/imx28-m28evk.dts index 6ce3d17c3a2..fd36e1cca10 100644 --- a/arch/arm/boot/dts/imx28-m28evk.dts +++ b/arch/arm/boot/dts/imx28-m28evk.dts @@ -152,7 +152,6 @@ i2c0: i2c@80058000 { pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins_a>; - clock-frequency = <400000>; status = "okay"; sgtl5000: codec@0a { diff --git a/arch/arm/boot/dts/imx28-sps1.dts b/arch/arm/boot/dts/imx28-sps1.dts index e6cde8aa7ff..6c6a5442800 100644 --- a/arch/arm/boot/dts/imx28-sps1.dts +++ b/arch/arm/boot/dts/imx28-sps1.dts @@ -70,7 +70,6 @@ i2c0: i2c@80058000 { pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins_a>; - clock-frequency = <400000>; status = "okay"; rtc: rtc@51 { diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 06ec460b458..281a223591f 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -91,6 +91,7 @@ compatible = "arm,cortex-a9-twd-timer"; reg = <0x00a00600 0x20>; interrupts = <1 13 0xf01>; + clocks = <&clks 15>; }; L2: l2-cache@00a02000 { diff --git a/arch/arm/boot/dts/kirkwood-goflexnet.dts b/arch/arm/boot/dts/kirkwood-goflexnet.dts index bd83b8fc7c8..c3573be7b92 100644 --- a/arch/arm/boot/dts/kirkwood-goflexnet.dts +++ b/arch/arm/boot/dts/kirkwood-goflexnet.dts @@ -77,6 +77,7 @@ }; nand@3000000 { + chip-delay = <40>; status = "okay"; partition@0 { diff --git a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts index 93c3afbef9e..3694e94f6e9 100644 --- a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts +++ b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts @@ -96,11 +96,11 @@ marvell,function = "gpio"; }; pmx_led_rebuild_brt_ctrl_1: pmx-led-rebuild-brt-ctrl-1 { - marvell,pins = "mpp44"; + marvell,pins = "mpp46"; marvell,function = "gpio"; }; pmx_led_rebuild_brt_ctrl_2: pmx-led-rebuild-brt-ctrl-2 { - marvell,pins = "mpp45"; + marvell,pins = "mpp47"; marvell,function = "gpio"; }; @@ -157,14 +157,14 @@ gpios = <&gpio0 16 0>; linux,default-trigger = "default-on"; }; - health_led1 { + rebuild_led { + label = "status:white:rebuild_led"; + gpios = <&gpio1 4 0>; + }; + health_led { label = "status:red:health_led"; gpios = <&gpio1 5 0>; }; - health_led2 { - label = "status:white:health_led"; - gpios = <&gpio1 4 0>; - }; backup_led { label = "status:blue:backup_led"; gpios = <&gpio0 15 0>; diff --git a/arch/arm/boot/dts/orion5x.dtsi b/arch/arm/boot/dts/orion5x.dtsi index 8aad00f81ed..f7bec3b1ba3 100644 --- a/arch/arm/boot/dts/orion5x.dtsi +++ b/arch/arm/boot/dts/orion5x.dtsi @@ -13,6 +13,9 @@ compatible = "marvell,orion5x"; interrupt-parent = <&intc>; + aliases { + gpio0 = &gpio0; + }; intc: interrupt-controller { compatible = "marvell,orion-intc", "marvell,intc"; interrupt-controller; @@ -32,7 +35,9 @@ #gpio-cells = <2>; gpio-controller; reg = <0x10100 0x40>; - ngpio = <32>; + ngpios = <32>; + interrupt-controller; + #interrupt-cells = <2>; interrupts = <6>, <7>, <8>, <9>; }; @@ -91,7 +96,7 @@ reg = <0x90000 0x10000>, <0xf2200000 0x800>; reg-names = "regs", "sram"; - interrupts = <22>; + interrupts = <28>; status = "okay"; }; }; diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi index 48d00a099ce..3d3f64d2111 100644 --- a/arch/arm/boot/dts/tegra20.dtsi +++ b/arch/arm/boot/dts/tegra20.dtsi @@ -385,7 +385,7 @@ spi@7000d800 { compatible = "nvidia,tegra20-slink"; - reg = <0x7000d480 0x200>; + reg = <0x7000d800 0x200>; interrupts = <0 83 0x04>; nvidia,dma-request-selector = <&apbdma 17>; #address-cells = <1>; diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi index 9d87a3ffe99..dbf46c27256 100644 --- a/arch/arm/boot/dts/tegra30.dtsi +++ b/arch/arm/boot/dts/tegra30.dtsi @@ -372,7 +372,7 @@ spi@7000d800 { compatible = "nvidia,tegra30-slink", "nvidia,tegra20-slink"; - reg = <0x7000d480 0x200>; + reg = <0x7000d800 0x200>; interrupts = <0 83 0x04>; nvidia,dma-request-selector = <&apbdma 17>; #address-cells = <1>; diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile index dc8dd0de5c0..53e68b16319 100644 --- a/arch/arm/common/Makefile +++ b/arch/arm/common/Makefile @@ -11,3 +11,6 @@ obj-$(CONFIG_SHARP_PARAM) += sharpsl_param.o 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 +AFLAGS_mcpm_head.o := -march=armv7-a +AFLAGS_vlock.o := -march=armv7-a diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c new file mode 100644 index 00000000000..370236dd1a0 --- /dev/null +++ b/arch/arm/common/mcpm_entry.c @@ -0,0 +1,263 @@ +/* + * arch/arm/common/mcpm_entry.c -- entry point for multi-cluster PM + * + * Created by: Nicolas Pitre, March 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/kernel.h> +#include <linux/init.h> +#include <linux/irqflags.h> + +#include <asm/mcpm.h> +#include <asm/cacheflush.h> +#include <asm/idmap.h> +#include <asm/cputype.h> + +extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER]; + +void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr) +{ + unsigned long val = ptr ? virt_to_phys(ptr) : 0; + mcpm_entry_vectors[cluster][cpu] = val; + sync_cache_w(&mcpm_entry_vectors[cluster][cpu]); +} + +static const struct mcpm_platform_ops *platform_ops; + +int __init mcpm_platform_register(const struct mcpm_platform_ops *ops) +{ + if (platform_ops) + return -EBUSY; + platform_ops = ops; + return 0; +} + +int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster) +{ + if (!platform_ops) + return -EUNATCH; /* try not to shadow power_up errors */ + might_sleep(); + return platform_ops->power_up(cpu, cluster); +} + +typedef void (*phys_reset_t)(unsigned long); + +void mcpm_cpu_power_down(void) +{ + phys_reset_t phys_reset; + + BUG_ON(!platform_ops); + BUG_ON(!irqs_disabled()); + + /* + * Do this before calling into the power_down method, + * as it might not always be safe to do afterwards. + */ + setup_mm_for_reboot(); + + platform_ops->power_down(); + + /* + * It is possible for a power_up request to happen concurrently + * with a power_down request for the same CPU. In this case the + * power_down method might not be able to actually enter a + * powered down state with the WFI instruction if the power_up + * method has removed the required reset condition. The + * power_down method is then allowed to return. We must perform + * a re-entry in the kernel as if the power_up method just had + * deasserted reset on the CPU. + * + * To simplify race issues, the platform specific implementation + * must accommodate for the possibility of unordered calls to + * power_down and power_up with a usage count. Therefore, if a + * call to power_up is issued for a CPU that is not down, then + * the next call to power_down must not attempt a full shutdown + * but only do the minimum (normally disabling L1 cache and CPU + * coherency) and return just as if a concurrent power_up request + * had happened as described above. + */ + + phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset); + phys_reset(virt_to_phys(mcpm_entry_point)); + + /* should never get here */ + BUG(); +} + +void mcpm_cpu_suspend(u64 expected_residency) +{ + phys_reset_t phys_reset; + + BUG_ON(!platform_ops); + BUG_ON(!irqs_disabled()); + + /* Very similar to mcpm_cpu_power_down() */ + setup_mm_for_reboot(); + platform_ops->suspend(expected_residency); + phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset); + phys_reset(virt_to_phys(mcpm_entry_point)); + BUG(); +} + +int mcpm_cpu_powered_up(void) +{ + if (!platform_ops) + return -EUNATCH; + if (platform_ops->powered_up) + platform_ops->powered_up(); + return 0; +} + +struct sync_struct mcpm_sync; + +/* + * __mcpm_cpu_going_down: Indicates that the cpu is being torn down. + * This must be called at the point of committing to teardown of a CPU. + * The CPU cache (SCTRL.C bit) is expected to still be active. + */ +void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster) +{ + mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_GOING_DOWN; + sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu); +} + +/* + * __mcpm_cpu_down: Indicates that cpu teardown is complete and that the + * cluster can be torn down without disrupting this CPU. + * To avoid deadlocks, this must be called before a CPU is powered down. + * The CPU cache (SCTRL.C bit) is expected to be off. + * However L2 cache might or might not be active. + */ +void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster) +{ + dmb(); + mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_DOWN; + sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu); + dsb_sev(); +} + +/* + * __mcpm_outbound_leave_critical: Leave the cluster teardown critical section. + * @state: the final state of the cluster: + * CLUSTER_UP: no destructive teardown was done and the cluster has been + * restored to the previous state (CPU cache still active); or + * CLUSTER_DOWN: the cluster has been torn-down, ready for power-off + * (CPU cache disabled, L2 cache either enabled or disabled). + */ +void __mcpm_outbound_leave_critical(unsigned int cluster, int state) +{ + dmb(); + mcpm_sync.clusters[cluster].cluster = state; + sync_cache_w(&mcpm_sync.clusters[cluster].cluster); + dsb_sev(); +} + +/* + * __mcpm_outbound_enter_critical: Enter the cluster teardown critical section. + * This function should be called by the last man, after local CPU teardown + * is complete. CPU cache expected to be active. + * + * Returns: + * false: the critical section was not entered because an inbound CPU was + * observed, or the cluster is already being set up; + * true: the critical section was entered: it is now safe to tear down the + * cluster. + */ +bool __mcpm_outbound_enter_critical(unsigned int cpu, unsigned int cluster) +{ + unsigned int i; + struct mcpm_sync_struct *c = &mcpm_sync.clusters[cluster]; + + /* Warn inbound CPUs that the cluster is being torn down: */ + c->cluster = CLUSTER_GOING_DOWN; + sync_cache_w(&c->cluster); + + /* Back out if the inbound cluster is already in the critical region: */ + sync_cache_r(&c->inbound); + if (c->inbound == INBOUND_COMING_UP) + goto abort; + + /* + * Wait for all CPUs to get out of the GOING_DOWN state, so that local + * teardown is complete on each CPU before tearing down the cluster. + * + * If any CPU has been woken up again from the DOWN state, then we + * shouldn't be taking the cluster down at all: abort in that case. + */ + sync_cache_r(&c->cpus); + for (i = 0; i < MAX_CPUS_PER_CLUSTER; i++) { + int cpustate; + + if (i == cpu) + continue; + + while (1) { + cpustate = c->cpus[i].cpu; + if (cpustate != CPU_GOING_DOWN) + break; + + wfe(); + sync_cache_r(&c->cpus[i].cpu); + } + + switch (cpustate) { + case CPU_DOWN: + continue; + + default: + goto abort; + } + } + + return true; + +abort: + __mcpm_outbound_leave_critical(cluster, CLUSTER_UP); + return false; +} + +int __mcpm_cluster_state(unsigned int cluster) +{ + sync_cache_r(&mcpm_sync.clusters[cluster].cluster); + return mcpm_sync.clusters[cluster].cluster; +} + +extern unsigned long mcpm_power_up_setup_phys; + +int __init mcpm_sync_init( + void (*power_up_setup)(unsigned int affinity_level)) +{ + unsigned int i, j, mpidr, this_cluster; + + BUILD_BUG_ON(MCPM_SYNC_CLUSTER_SIZE * MAX_NR_CLUSTERS != sizeof mcpm_sync); + BUG_ON((unsigned long)&mcpm_sync & (__CACHE_WRITEBACK_GRANULE - 1)); + + /* + * Set initial CPU and cluster states. + * Only one cluster is assumed to be active at this point. + */ + for (i = 0; i < MAX_NR_CLUSTERS; i++) { + mcpm_sync.clusters[i].cluster = CLUSTER_DOWN; + mcpm_sync.clusters[i].inbound = INBOUND_NOT_COMING_UP; + for (j = 0; j < MAX_CPUS_PER_CLUSTER; j++) + mcpm_sync.clusters[i].cpus[j].cpu = CPU_DOWN; + } + mpidr = read_cpuid_mpidr(); + this_cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + for_each_online_cpu(i) + mcpm_sync.clusters[this_cluster].cpus[i].cpu = CPU_UP; + mcpm_sync.clusters[this_cluster].cluster = CLUSTER_UP; + sync_cache_w(&mcpm_sync); + + if (power_up_setup) { + mcpm_power_up_setup_phys = virt_to_phys(power_up_setup); + sync_cache_w(&mcpm_power_up_setup_phys); + } + + return 0; +} diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S new file mode 100644 index 00000000000..8178705c4b2 --- /dev/null +++ b/arch/arm/common/mcpm_head.S @@ -0,0 +1,219 @@ +/* + * arch/arm/common/mcpm_head.S -- kernel entry point for multi-cluster PM + * + * Created by: Nicolas Pitre, March 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. + * + * + * Refer to Documentation/arm/cluster-pm-race-avoidance.txt + * for details of the synchronisation algorithms used here. + */ + +#include <linux/linkage.h> +#include <asm/mcpm.h> + +#include "vlock.h" + +.if MCPM_SYNC_CLUSTER_CPUS +.error "cpus must be the first member of struct mcpm_sync_struct" +.endif + + .macro pr_dbg string +#if defined(CONFIG_DEBUG_LL) && defined(DEBUG) + b 1901f +1902: .asciz "CPU" +1903: .asciz " cluster" +1904: .asciz ": \string" + .align +1901: adr r0, 1902b + bl printascii + mov r0, r9 + bl printhex8 + adr r0, 1903b + bl printascii + mov r0, r10 + bl printhex8 + adr r0, 1904b + bl printascii +#endif + .endm + + .arm + .align + +ENTRY(mcpm_entry_point) + + THUMB( adr r12, BSYM(1f) ) + THUMB( bx r12 ) + THUMB( .thumb ) +1: + mrc p15, 0, r0, c0, c0, 5 @ MPIDR + ubfx r9, r0, #0, #8 @ r9 = cpu + ubfx r10, r0, #8, #8 @ r10 = cluster + mov r3, #MAX_CPUS_PER_CLUSTER + mla r4, r3, r10, r9 @ r4 = canonical CPU index + cmp r4, #(MAX_CPUS_PER_CLUSTER * MAX_NR_CLUSTERS) + blo 2f + + /* We didn't expect this CPU. Try to cheaply make it quiet. */ +1: wfi + wfe + b 1b + +2: pr_dbg "kernel mcpm_entry_point\n" + + /* + * MMU is off so we need to get to various variables in a + * position independent way. + */ + adr r5, 3f + ldmia r5, {r6, r7, r8, r11} + 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 + + mov r0, #MCPM_SYNC_CLUSTER_SIZE + mla r8, r0, r10, r8 @ r8 = sync cluster base + + @ Signal that this CPU is coming UP: + mov r0, #CPU_COMING_UP + mov r5, #MCPM_SYNC_CPU_SIZE + mla r5, r9, r5, r8 @ r5 = sync cpu address + strb r0, [r5] + + @ At this point, the cluster cannot unexpectedly enter the GOING_DOWN + @ state, because there is at least one active CPU (this CPU). + + mov r0, #VLOCK_SIZE + mla r11, r0, r10, r11 @ r11 = cluster first man lock + mov r0, r11 + mov r1, r9 @ cpu + bl vlock_trylock @ implies DMB + + cmp r0, #0 @ failed to get the lock? + bne mcpm_setup_wait @ wait for cluster setup if so + + ldrb r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER] + cmp r0, #CLUSTER_UP @ cluster already up? + bne mcpm_setup @ if not, set up the cluster + + @ Otherwise, release the first man lock and skip setup: + mov r0, r11 + bl vlock_unlock + b mcpm_setup_complete + +mcpm_setup: + @ Control dependency implies strb not observable before previous ldrb. + + @ Signal that the cluster is being brought up: + mov r0, #INBOUND_COMING_UP + strb r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND] + dmb + + @ Any CPU trying to take the cluster into CLUSTER_GOING_DOWN from this + @ point onwards will observe INBOUND_COMING_UP and abort. + + @ Wait for any previously-pending cluster teardown operations to abort + @ or complete: +mcpm_teardown_wait: + ldrb r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER] + cmp r0, #CLUSTER_GOING_DOWN + bne first_man_setup + wfe + b mcpm_teardown_wait + +first_man_setup: + dmb + + @ If the outbound gave up before teardown started, skip cluster setup: + + cmp r0, #CLUSTER_UP + beq mcpm_setup_leave + + @ power_up_setup is now responsible for setting up the cluster: + + cmp r7, #0 + mov r0, #1 @ second (cluster) affinity level + blxne r7 @ Call power_up_setup if defined + dmb + + mov r0, #CLUSTER_UP + strb r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER] + dmb + +mcpm_setup_leave: + @ Leave the cluster setup critical section: + + mov r0, #INBOUND_NOT_COMING_UP + strb r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND] + dsb + sev + + mov r0, r11 + bl vlock_unlock @ implies DMB + b mcpm_setup_complete + + @ In the contended case, non-first men wait here for cluster setup + @ to complete: +mcpm_setup_wait: + ldrb r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER] + cmp r0, #CLUSTER_UP + wfene + bne mcpm_setup_wait + dmb + +mcpm_setup_complete: + @ If a platform-specific CPU setup hook is needed, it is + @ called from here. + + cmp r7, #0 + mov r0, #0 @ first (CPU) affinity level + blxne r7 @ Call power_up_setup if defined + dmb + + @ Mark the CPU as up: + + mov r0, #CPU_UP + strb r0, [r5] + + @ Observability order of CPU_UP and opening of the gate does not matter. + +mcpm_entry_gated: + ldr r5, [r6, r4, lsl #2] @ r5 = CPU entry vector + cmp r5, #0 + wfeeq + beq mcpm_entry_gated + dmb + + pr_dbg "released\n" + bx r5 + + .align 2 + +3: .word mcpm_entry_vectors - . + .word mcpm_power_up_setup_phys - 3b + .word mcpm_sync - 3b + .word first_man_locks - 3b + +ENDPROC(mcpm_entry_point) + + .bss + + .align CACHE_WRITEBACK_ORDER + .type first_man_locks, #object +first_man_locks: + .space VLOCK_SIZE * MAX_NR_CLUSTERS + .align CACHE_WRITEBACK_ORDER + + .type mcpm_entry_vectors, #object +ENTRY(mcpm_entry_vectors) + .space 4 * 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/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c new file mode 100644 index 00000000000..52b88d81b7b --- /dev/null +++ b/arch/arm/common/mcpm_platsmp.c @@ -0,0 +1,92 @@ +/* + * linux/arch/arm/mach-vexpress/mcpm_platsmp.c + * + * Created by: Nicolas Pitre, November 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. + * + * Code to handle secondary CPU bringup and hotplug for the cluster power API. + */ + +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/spinlock.h> + +#include <linux/irqchip/arm-gic.h> + +#include <asm/mcpm.h> +#include <asm/smp.h> +#include <asm/smp_plat.h> + +static void __init simple_smp_init_cpus(void) +{ +} + +static int __cpuinit mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle) +{ + unsigned int mpidr, pcpu, pcluster, ret; + extern void secondary_startup(void); + + mpidr = cpu_logical_map(cpu); + pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + pr_debug("%s: logical CPU %d is physical CPU %d cluster %d\n", + __func__, cpu, pcpu, pcluster); + + mcpm_set_entry_vector(pcpu, pcluster, NULL); + ret = mcpm_cpu_power_up(pcpu, pcluster); + if (ret) + return ret; + mcpm_set_entry_vector(pcpu, pcluster, secondary_startup); + arch_send_wakeup_ipi_mask(cpumask_of(cpu)); + dsb_sev(); + return 0; +} + +static void __cpuinit mcpm_secondary_init(unsigned int cpu) +{ + mcpm_cpu_powered_up(); + gic_secondary_init(0); +} + +#ifdef CONFIG_HOTPLUG_CPU + +static int mcpm_cpu_disable(unsigned int cpu) +{ + /* + * We assume all CPUs may be shut down. + * This would be the hook to use for eventual Secure + * OS migration requests as described in the PSCI spec. + */ + return 0; +} + +static void mcpm_cpu_die(unsigned int cpu) +{ + unsigned int mpidr, pcpu, pcluster; + mpidr = read_cpuid_mpidr(); + pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + mcpm_set_entry_vector(pcpu, pcluster, NULL); + mcpm_cpu_power_down(); +} + +#endif + +static struct smp_operations __initdata mcpm_smp_ops = { + .smp_init_cpus = simple_smp_init_cpus, + .smp_boot_secondary = mcpm_boot_secondary, + .smp_secondary_init = mcpm_secondary_init, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = mcpm_cpu_disable, + .cpu_die = mcpm_cpu_die, +#endif +}; + +void __init mcpm_smp_set_ops(void) +{ + smp_set_ops(&mcpm_smp_ops); +} diff --git a/arch/arm/common/vlock.S b/arch/arm/common/vlock.S new file mode 100644 index 00000000000..ff198583f68 --- /dev/null +++ b/arch/arm/common/vlock.S @@ -0,0 +1,108 @@ +/* + * vlock.S - simple voting lock implementation for ARM + * + * Created by: Dave Martin, 2012-08-16 + * 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. + * + * 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. + * + * + * This algorithm is described in more detail in + * Documentation/arm/vlocks.txt. + */ + +#include <linux/linkage.h> +#include "vlock.h" + +/* Select different code if voting flags can fit in a single word. */ +#if VLOCK_VOTING_SIZE > 4 +#define FEW(x...) +#define MANY(x...) x +#else +#define FEW(x...) x +#define MANY(x...) +#endif + +@ voting lock for first-man coordination + +.macro voting_begin rbase:req, rcpu:req, rscratch:req + mov \rscratch, #1 + strb \rscratch, [\rbase, \rcpu] + dmb +.endm + +.macro voting_end rbase:req, rcpu:req, rscratch:req + dmb + mov \rscratch, #0 + strb \rscratch, [\rbase, \rcpu] + dsb + sev +.endm + +/* + * The vlock structure must reside in Strongly-Ordered or Device memory. + * This implementation deliberately eliminates most of the barriers which + * would be required for other memory types, and assumes that independent + * writes to neighbouring locations within a cacheline do not interfere + * with one another. + */ + +@ r0: lock structure base +@ r1: CPU ID (0-based index within cluster) +ENTRY(vlock_trylock) + add r1, r1, #VLOCK_VOTING_OFFSET + + voting_begin r0, r1, r2 + + ldrb r2, [r0, #VLOCK_OWNER_OFFSET] @ check whether lock is held + cmp r2, #VLOCK_OWNER_NONE + bne trylock_fail @ fail if so + + @ Control dependency implies strb not observable before previous ldrb. + + strb r1, [r0, #VLOCK_OWNER_OFFSET] @ submit my vote + + voting_end r0, r1, r2 @ implies DMB + + @ Wait for the current round of voting to finish: + + MANY( mov r3, #VLOCK_VOTING_OFFSET ) +0: + MANY( ldr r2, [r0, r3] ) + FEW( ldr r2, [r0, #VLOCK_VOTING_OFFSET] ) + cmp r2, #0 + wfene + bne 0b + MANY( add r3, r3, #4 ) + MANY( cmp r3, #VLOCK_VOTING_OFFSET + VLOCK_VOTING_SIZE ) + MANY( bne 0b ) + + @ Check who won: + + dmb + ldrb r2, [r0, #VLOCK_OWNER_OFFSET] + eor r0, r1, r2 @ zero if I won, else nonzero + bx lr + +trylock_fail: + voting_end r0, r1, r2 + mov r0, #1 @ nonzero indicates that I lost + bx lr +ENDPROC(vlock_trylock) + +@ r0: lock structure base +ENTRY(vlock_unlock) + dmb + mov r1, #VLOCK_OWNER_NONE + strb r1, [r0, #VLOCK_OWNER_OFFSET] + dsb + sev + bx lr +ENDPROC(vlock_unlock) diff --git a/arch/arm/common/vlock.h b/arch/arm/common/vlock.h new file mode 100644 index 00000000000..3b441475a59 --- /dev/null +++ b/arch/arm/common/vlock.h @@ -0,0 +1,29 @@ +/* + * vlock.h - simple voting lock implementation + * + * Created by: Dave Martin, 2012-08-16 + * 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. + * + * 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. + */ + +#ifndef __VLOCK_H +#define __VLOCK_H + +#include <asm/mcpm.h> + +/* Offsets and sizes are rounded to a word (4 bytes) */ +#define VLOCK_OWNER_OFFSET 0 +#define VLOCK_VOTING_OFFSET 4 +#define VLOCK_VOTING_SIZE ((MAX_CPUS_PER_CLUSTER + 3) / 4 * 4) +#define VLOCK_SIZE (VLOCK_VOTING_OFFSET + VLOCK_VOTING_SIZE) +#define VLOCK_OWNER_NONE 0 + +#endif /* ! __VLOCK_H */ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index c79f61faa3a..da1c77d3932 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -243,6 +243,29 @@ typedef struct { #define ATOMIC64_INIT(i) { (i) } +#ifdef CONFIG_ARM_LPAE +static inline u64 atomic64_read(const atomic64_t *v) +{ + u64 result; + + __asm__ __volatile__("@ atomic64_read\n" +" ldrd %0, %H0, [%1]" + : "=&r" (result) + : "r" (&v->counter), "Qo" (v->counter) + ); + + return result; +} + +static inline void atomic64_set(atomic64_t *v, u64 i) +{ + __asm__ __volatile__("@ atomic64_set\n" +" strd %2, %H2, [%1]" + : "=Qo" (v->counter) + : "r" (&v->counter), "r" (i) + ); +} +#else static inline u64 atomic64_read(const atomic64_t *v) { u64 result; @@ -269,6 +292,7 @@ static inline void atomic64_set(atomic64_t *v, u64 i) : "r" (&v->counter), "r" (i) : "cc"); } +#endif static inline void atomic64_add(u64 i, atomic64_t *v) { diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index e1489c54cd1..bff71388e72 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -363,4 +363,79 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) flush_cache_all(); } +/* + * Memory synchronization helpers for mixed cached vs non cached accesses. + * + * Some synchronization algorithms have to set states in memory with the + * cache enabled or disabled depending on the code path. It is crucial + * to always ensure proper cache maintenance to update main memory right + * away in that case. + * + * Any cached write must be followed by a cache clean operation. + * Any cached read must be preceded by a cache invalidate operation. + * Yet, in the read case, a cache flush i.e. atomic clean+invalidate + * operation is needed to avoid discarding possible concurrent writes to the + * accessed memory. + * + * Also, in order to prevent a cached writer from interfering with an + * adjacent non-cached writer, each state variable must be located to + * a separate cache line. + */ + +/* + * This needs to be >= the max cache writeback size of all + * supported platforms included in the current kernel configuration. + * This is used to align state variables to their own cache lines. + */ +#define __CACHE_WRITEBACK_ORDER 6 /* guessed from existing platforms */ +#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER) + +/* + * There is no __cpuc_clean_dcache_area but we use it anyway for + * code intent clarity, and alias it to __cpuc_flush_dcache_area. + */ +#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area + +/* + * Ensure preceding writes to *p by this CPU are visible to + * subsequent reads by other CPUs: + */ +static inline void __sync_cache_range_w(volatile void *p, size_t size) +{ + char *_p = (char *)p; + + __cpuc_clean_dcache_area(_p, size); + outer_clean_range(__pa(_p), __pa(_p + size)); +} + +/* + * Ensure preceding writes to *p by other CPUs are visible to + * subsequent reads by this CPU. We must be careful not to + * discard data simultaneously written by another CPU, hence the + * usage of flush rather than invalidate operations. + */ +static inline void __sync_cache_range_r(volatile void *p, size_t size) +{ + char *_p = (char *)p; + +#ifdef CONFIG_OUTER_CACHE + if (outer_cache.flush_range) { + /* + * Ensure dirty data migrated from other CPUs into our cache + * are cleaned out safely before the outer cache is cleaned: + */ + __cpuc_clean_dcache_area(_p, size); + + /* Clean and invalidate stale data for *p from outer ... */ + outer_flush_range(__pa(_p), __pa(_p + size)); + } +#endif + + /* ... and inner cache: */ + __cpuc_flush_dcache_area(_p, size); +} + +#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr)) +#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr)) + #endif diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h index 5ef4d8015a6..1f3262e99d8 100644 --- a/arch/arm/include/asm/cp15.h +++ b/arch/arm/include/asm/cp15.h @@ -42,6 +42,8 @@ #define vectors_high() (0) #endif +#ifdef CONFIG_CPU_CP15 + extern unsigned long cr_no_alignment; /* defined in entry-armv.S */ extern unsigned long cr_alignment; /* defined in entry-armv.S */ @@ -82,6 +84,18 @@ static inline void set_copro_access(unsigned int val) isb(); } -#endif +#else /* ifdef CONFIG_CPU_CP15 */ + +/* + * cr_alignment and cr_no_alignment are tightly coupled to cp15 (at least in the + * minds of the developers). Yielding 0 for machines without a cp15 (and making + * it read-only) is fine for most cases and saves quite some #ifdeffery. + */ +#define cr_no_alignment UL(0) +#define cr_alignment UL(0) + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + +#endif /* ifndef __ASSEMBLY__ */ #endif diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index ad41ec2471e..7652712d1d1 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -38,6 +38,24 @@ #define MPIDR_AFFINITY_LEVEL(mpidr, level) \ ((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK) +#define ARM_CPU_IMP_ARM 0x41 +#define ARM_CPU_IMP_INTEL 0x69 + +#define ARM_CPU_PART_ARM1136 0xB360 +#define ARM_CPU_PART_ARM1156 0xB560 +#define ARM_CPU_PART_ARM1176 0xB760 +#define ARM_CPU_PART_ARM11MPCORE 0xB020 +#define ARM_CPU_PART_CORTEX_A8 0xC080 +#define ARM_CPU_PART_CORTEX_A9 0xC090 +#define ARM_CPU_PART_CORTEX_A5 0xC050 +#define ARM_CPU_PART_CORTEX_A15 0xC0F0 +#define ARM_CPU_PART_CORTEX_A7 0xC070 + +#define ARM_CPU_XSCALE_ARCH_MASK 0xe000 +#define ARM_CPU_XSCALE_ARCH_V1 0x2000 +#define ARM_CPU_XSCALE_ARCH_V2 0x4000 +#define ARM_CPU_XSCALE_ARCH_V3 0x6000 + extern unsigned int processor_id; #ifdef CONFIG_CPU_CP15 @@ -50,6 +68,7 @@ extern unsigned int processor_id; : "cc"); \ __val; \ }) + #define read_cpuid_ext(ext_reg) \ ({ \ unsigned int __val; \ @@ -59,29 +78,24 @@ extern unsigned int processor_id; : "cc"); \ __val; \ }) -#else -#define read_cpuid(reg) (processor_id) -#define read_cpuid_ext(reg) 0 -#endif -#define ARM_CPU_IMP_ARM 0x41 -#define ARM_CPU_IMP_INTEL 0x69 +#else /* ifdef CONFIG_CPU_CP15 */ -#define ARM_CPU_PART_ARM1136 0xB360 -#define ARM_CPU_PART_ARM1156 0xB560 -#define ARM_CPU_PART_ARM1176 0xB760 -#define ARM_CPU_PART_ARM11MPCORE 0xB020 -#define ARM_CPU_PART_CORTEX_A8 0xC080 -#define ARM_CPU_PART_CORTEX_A9 0xC090 -#define ARM_CPU_PART_CORTEX_A5 0xC050 -#define ARM_CPU_PART_CORTEX_A15 0xC0F0 -#define ARM_CPU_PART_CORTEX_A7 0xC070 +/* + * read_cpuid and read_cpuid_ext should only ever be called on machines that + * have cp15 so warn on other usages. + */ +#define read_cpuid(reg) \ + ({ \ + WARN_ON_ONCE(1); \ + 0; \ + }) -#define ARM_CPU_XSCALE_ARCH_MASK 0xe000 -#define ARM_CPU_XSCALE_ARCH_V1 0x2000 -#define ARM_CPU_XSCALE_ARCH_V2 0x4000 -#define ARM_CPU_XSCALE_ARCH_V3 0x6000 +#define read_cpuid_ext(reg) read_cpuid(reg) + +#endif /* ifdef CONFIG_CPU_CP15 / else */ +#ifdef CONFIG_CPU_CP15 /* * The CPU ID never changes at run time, so we might as well tell the * compiler that it's constant. Use this function to read the CPU ID @@ -92,6 +106,15 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void) return read_cpuid(CPUID_ID); } +#else /* ifdef CONFIG_CPU_CP15 */ + +static inline unsigned int __attribute_const__ read_cpuid_id(void) +{ + return processor_id; +} + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + static inline unsigned int __attribute_const__ read_cpuid_implementor(void) { return (read_cpuid_id() & 0xFF000000) >> 24; diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h index 720799fd3a8..dff714d886d 100644 --- a/arch/arm/include/asm/delay.h +++ b/arch/arm/include/asm/delay.h @@ -24,7 +24,7 @@ extern struct arm_delay_ops { void (*delay)(unsigned long); void (*const_udelay)(unsigned long); void (*udelay)(unsigned long); - bool const_clock; + unsigned long ticks_per_jiffy; } arm_delay_ops; #define __delay(n) arm_delay_ops.delay(n) diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h index cca9f15704e..ea289e1435e 100644 --- a/arch/arm/include/asm/glue-cache.h +++ b/arch/arm/include/asm/glue-cache.h @@ -19,14 +19,6 @@ #undef _CACHE #undef MULTI_CACHE -#if defined(CONFIG_CPU_CACHE_V3) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE v3 -# endif -#endif - #if defined(CONFIG_CPU_CACHE_V4) # ifdef _CACHE # define MULTI_CACHE 1 diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h index 8cacbcda76d..b6e9f2c108b 100644 --- a/arch/arm/include/asm/glue-df.h +++ b/arch/arm/include/asm/glue-df.h @@ -18,12 +18,12 @@ * ================ * * We have the following to choose from: - * arm6 - ARM6 style * arm7 - ARM7 style * v4_early - ARMv4 without Thumb early abort handler * v4t_late - ARMv4 with Thumb late abort handler * v4t_early - ARMv4 with Thumb early abort handler - * v5tej_early - ARMv5 with Thumb and Java early abort handler + * v5t_early - ARMv5 with Thumb early abort handler + * v5tj_early - ARMv5 with Thumb and Java early abort handler * xscale - ARMv5 with Thumb with Xscale extensions * v6_early - ARMv6 generic early abort handler * v7_early - ARMv7 generic early abort handler @@ -39,19 +39,19 @@ # endif #endif -#ifdef CONFIG_CPU_ABRT_LV4T +#ifdef CONFIG_CPU_ABRT_EV4 # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v4t_late_abort +# define CPU_DABORT_HANDLER v4_early_abort # endif #endif -#ifdef CONFIG_CPU_ABRT_EV4 +#ifdef CONFIG_CPU_ABRT_LV4T # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v4_early_abort +# define CPU_DABORT_HANDLER v4t_late_abort # endif #endif @@ -63,19 +63,19 @@ # endif #endif -#ifdef CONFIG_CPU_ABRT_EV5TJ +#ifdef CONFIG_CPU_ABRT_EV5T # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v5tj_early_abort +# define CPU_DABORT_HANDLER v5t_early_abort # endif #endif -#ifdef CONFIG_CPU_ABRT_EV5T +#ifdef CONFIG_CPU_ABRT_EV5TJ # ifdef CPU_DABORT_HANDLER # define MULTI_DABORT 1 # else -# define CPU_DABORT_HANDLER v5t_early_abort +# define CPU_DABORT_HANDLER v5tj_early_abort # endif #endif diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h index 02fe2fbe247..ed94b1a366a 100644 --- a/arch/arm/include/asm/hardware/iop3xx.h +++ b/arch/arm/include/asm/hardware/iop3xx.h @@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void); * IOP3XX processor registers */ #define IOP3XX_PERIPHERAL_PHYS_BASE 0xffffe000 -#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfeffe000 +#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfedfe000 #define IOP3XX_PERIPHERAL_SIZE 0x00002000 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\ IOP3XX_PERIPHERAL_SIZE - 1) diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h index 8c5e828f484..91b99abe7a9 100644 --- a/arch/arm/include/asm/highmem.h +++ b/arch/arm/include/asm/highmem.h @@ -41,6 +41,13 @@ extern void kunmap_high(struct page *page); #endif #endif +/* + * Needed to be able to broadcast the TLB invalidation for kmap. + */ +#ifdef CONFIG_ARM_ERRATA_798181 +#undef ARCH_NEEDS_KMAP_HIGH_GET +#endif + #ifdef ARCH_NEEDS_KMAP_HIGH_GET extern void *kmap_high_get(struct page *page); #else diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 7c3d813e15d..124623e5ef1 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -211,4 +211,8 @@ #define HSR_HVC_IMM_MASK ((1UL << 16) - 1) +#define HSR_DABT_S1PTW (1U << 7) +#define HSR_DABT_CM (1U << 8) +#define HSR_DABT_EA (1U << 9) + #endif /* __ARM_KVM_ARM_H__ */ diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index e4956f4e23e..18d50322a9e 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -75,7 +75,7 @@ extern char __kvm_hyp_code_end[]; extern void __kvm_tlb_flush_vmid(struct kvm *kvm); extern void __kvm_flush_vm_context(void); -extern void __kvm_tlb_flush_vmid(struct kvm *kvm); +extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); #endif diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index fd611996bfb..82b4babead2 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -22,11 +22,12 @@ #include <linux/kvm_host.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> +#include <asm/kvm_arm.h> -u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); -u32 *vcpu_spsr(struct kvm_vcpu *vcpu); +unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); +unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu); -int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run); +bool kvm_condition_valid(struct kvm_vcpu *vcpu); void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr); void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); @@ -37,14 +38,14 @@ static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu) return 1; } -static inline u32 *vcpu_pc(struct kvm_vcpu *vcpu) +static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu) { - return (u32 *)&vcpu->arch.regs.usr_regs.ARM_pc; + return &vcpu->arch.regs.usr_regs.ARM_pc; } -static inline u32 *vcpu_cpsr(struct kvm_vcpu *vcpu) +static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu) { - return (u32 *)&vcpu->arch.regs.usr_regs.ARM_cpsr; + return &vcpu->arch.regs.usr_regs.ARM_cpsr; } static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) @@ -69,4 +70,96 @@ static inline bool kvm_vcpu_reg_is_pc(struct kvm_vcpu *vcpu, int reg) return reg == 15; } +static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hsr; +} + +static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hxfar; +} + +static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu) +{ + return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8; +} + +static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.fault.hyp_pc; +} + +static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_ISV; +} + +static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_WNR; +} + +static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_SSE; +} + +static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu) +{ + return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT; +} + +static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_EA; +} + +static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; +} + +/* Get Access Size from a data abort */ +static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu) +{ + switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) { + case 0: + return 1; + case 1: + return 2; + case 2: + return 4; + default: + kvm_err("Hardware is weird: SAS 0b11 is reserved\n"); + return -EFAULT; + } +} + +/* This one is not specific to Data Abort */ +static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_IL; +} + +static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT; +} + +static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT; +} + +static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE; +} + +static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; +} + #endif /* __ARM_KVM_EMULATE_H__ */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index d1736a53b12..0c4e643d939 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -80,6 +80,15 @@ struct kvm_mmu_memory_cache { void *objects[KVM_NR_MEM_OBJS]; }; +struct kvm_vcpu_fault_info { + u32 hsr; /* Hyp Syndrome Register */ + u32 hxfar; /* Hyp Data/Inst. Fault Address Register */ + u32 hpfar; /* Hyp IPA Fault Address Register */ + u32 hyp_pc; /* PC when exception was taken from Hyp mode */ +}; + +typedef struct vfp_hard_struct kvm_kernel_vfp_t; + struct kvm_vcpu_arch { struct kvm_regs regs; @@ -93,13 +102,11 @@ struct kvm_vcpu_arch { u32 midr; /* Exception Information */ - u32 hsr; /* Hyp Syndrome Register */ - u32 hxfar; /* Hyp Data/Inst Fault Address Register */ - u32 hpfar; /* Hyp IPA Fault Address Register */ + struct kvm_vcpu_fault_info fault; /* Floating point registers (VFP and Advanced SIMD/NEON) */ - struct vfp_hard_struct vfp_guest; - struct vfp_hard_struct *vfp_host; + kvm_kernel_vfp_t vfp_guest; + kvm_kernel_vfp_t *vfp_host; /* VGIC state */ struct vgic_cpu vgic_cpu; @@ -122,9 +129,6 @@ struct kvm_vcpu_arch { /* Interrupt related fields */ u32 irq_lines; /* IRQ and FIQ levels */ - /* Hyp exception information */ - u32 hyp_pc; /* PC when exception was taken from Hyp mode */ - /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; @@ -181,4 +185,26 @@ struct kvm_one_reg; int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); +int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, + int exception_index); + +static inline void __cpu_init_hyp_mode(unsigned long long pgd_ptr, + unsigned long hyp_stack_ptr, + unsigned long vector_ptr) +{ + unsigned long pgd_low, pgd_high; + + pgd_low = (pgd_ptr & ((1ULL << 32) - 1)); + pgd_high = (pgd_ptr >> 32ULL); + + /* + * Call initialization code, and switch to the full blown + * HYP code. The init code doesn't need to preserve these registers as + * r1-r3 and r12 are already callee save according to the AAPCS. + * Note that we slightly misuse the prototype by casing the pgd_low to + * a void *. + */ + kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr); +} + #endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 421a20b3487..970f3b5fa10 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -19,6 +19,18 @@ #ifndef __ARM_KVM_MMU_H__ #define __ARM_KVM_MMU_H__ +#include <asm/cacheflush.h> +#include <asm/pgalloc.h> +#include <asm/idmap.h> + +/* + * We directly use the kernel VA for the HYP, as we can directly share + * the mapping (HTTBR "covers" TTBR1). + */ +#define HYP_PAGE_OFFSET_MASK (~0UL) +#define HYP_PAGE_OFFSET PAGE_OFFSET +#define KERN_TO_HYP(kva) (kva) + int create_hyp_mappings(void *from, void *to); int create_hyp_io_mappings(void *from, void *to, phys_addr_t); void free_hyp_pmds(void); @@ -36,6 +48,16 @@ phys_addr_t kvm_mmu_get_httbr(void); int kvm_mmu_init(void); void kvm_clear_hyp_idmap(void); +static inline void kvm_set_pte(pte_t *pte, pte_t new_pte) +{ + pte_val(*pte) = new_pte; + /* + * flush_pmd_entry just takes a void pointer and cleans the necessary + * cache entries, so we can reuse the function for ptes. + */ + flush_pmd_entry(pte); +} + static inline bool kvm_is_write_fault(unsigned long hsr) { unsigned long hsr_ec = hsr >> HSR_EC_SHIFT; @@ -47,4 +69,49 @@ static inline bool kvm_is_write_fault(unsigned long hsr) return true; } +static inline void kvm_clean_pgd(pgd_t *pgd) +{ + clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t)); +} + +static inline void kvm_clean_pmd_entry(pmd_t *pmd) +{ + clean_pmd_entry(pmd); +} + +static inline void kvm_clean_pte(pte_t *pte) +{ + clean_pte_table(pte); +} + +static inline void kvm_set_s2pte_writable(pte_t *pte) +{ + pte_val(*pte) |= L_PTE_S2_RDWR; +} + +struct kvm; + +static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn) +{ + /* + * If we are going to insert an instruction page and the icache is + * either VIPT or PIPT, there is a potential problem where the host + * (or another VM) may have used the same page as this guest, and we + * read incorrect data from the icache. If we're using a PIPT cache, + * we can invalidate just that page, but if we are using a VIPT cache + * we need to invalidate the entire icache - damn shame - as written + * in the ARM ARM (DDI 0406C.b - Page B3-1393). + * + * VIVT caches are tagged using both the ASID and the VMID and doesn't + * need any kind of flushing (DDI 0406C.b - Page B3-1392). + */ + if (icache_is_pipt()) { + unsigned long hva = gfn_to_hva(kvm, gfn); + __cpuc_coherent_user_range(hva, hva + PAGE_SIZE); + } else if (!icache_is_vivt_asid_tagged()) { + /* any kind of VIPT cache */ + __flush_icache_all(); + } +} + #endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/include/asm/kvm_vgic.h b/arch/arm/include/asm/kvm_vgic.h index ab97207d9cd..343744e4809 100644 --- a/arch/arm/include/asm/kvm_vgic.h +++ b/arch/arm/include/asm/kvm_vgic.h @@ -21,7 +21,6 @@ #include <linux/kernel.h> #include <linux/kvm.h> -#include <linux/kvm_host.h> #include <linux/irqreturn.h> #include <linux/spinlock.h> #include <linux/types.h> diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h index 5cf2e979b4b..7d2c3c84380 100644 --- a/arch/arm/include/asm/mach/pci.h +++ b/arch/arm/include/asm/mach/pci.h @@ -30,6 +30,11 @@ struct hw_pci { void (*postinit)(void); u8 (*swizzle)(struct pci_dev *dev, u8 *pin); int (*map_irq)(const struct pci_dev *dev, u8 slot, u8 pin); + resource_size_t (*align_resource)(struct pci_dev *dev, + const struct resource *res, + resource_size_t start, + resource_size_t size, + resource_size_t align); }; /* @@ -51,6 +56,12 @@ struct pci_sys_data { u8 (*swizzle)(struct pci_dev *, u8 *); /* IRQ mapping */ int (*map_irq)(const struct pci_dev *, u8, u8); + /* Resource alignement requirements */ + resource_size_t (*align_resource)(struct pci_dev *dev, + const struct resource *res, + resource_size_t start, + resource_size_t size, + resource_size_t align); void *private_data; /* platform controller private data */ }; diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h new file mode 100644 index 00000000000..0f7b7620e9a --- /dev/null +++ b/arch/arm/include/asm/mcpm.h @@ -0,0 +1,209 @@ +/* + * arch/arm/include/asm/mcpm.h + * + * Created by: Nicolas Pitre, April 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. + */ + +#ifndef MCPM_H +#define MCPM_H + +/* + * Maximum number of possible clusters / CPUs per cluster. + * + * This should be sufficient for quite a while, while keeping the + * (assembly) code simpler. When this starts to grow then we'll have + * to consider dynamic allocation. + */ +#define MAX_CPUS_PER_CLUSTER 4 +#define MAX_NR_CLUSTERS 2 + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> +#include <asm/cacheflush.h> + +/* + * Platform specific code should use this symbol to set up secondary + * entry location for processors to use when released from reset. + */ +extern void mcpm_entry_point(void); + +/* + * This is used to indicate where the given CPU from given cluster should + * branch once it is ready to re-enter the kernel using ptr, or NULL if it + * should be gated. A gated CPU is held in a WFE loop until its vector + * becomes non NULL. + */ +void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr); + +/* + * CPU/cluster power operations API for higher subsystems to use. + */ + +/** + * mcpm_cpu_power_up - make given CPU in given cluster runable + * + * @cpu: CPU number within given cluster + * @cluster: cluster number for the CPU + * + * The identified CPU is brought out of reset. If the cluster was powered + * down then it is brought up as well, taking care not to let the other CPUs + * in the cluster run, and ensuring appropriate cluster setup. + * + * Caller must ensure the appropriate entry vector is initialized with + * mcpm_set_entry_vector() prior to calling this. + * + * This must be called in a sleepable context. However, the implementation + * is strongly encouraged to return early and let the operation happen + * asynchronously, especially when significant delays are expected. + * + * If the operation cannot be performed then an error code is returned. + */ +int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster); + +/** + * mcpm_cpu_power_down - power the calling CPU down + * + * The calling CPU is powered down. + * + * If this CPU is found to be the "last man standing" in the cluster + * then the cluster is prepared for power-down too. + * + * This must be called with interrupts disabled. + * + * This does not return. Re-entry in the kernel is expected via + * mcpm_entry_point. + */ +void mcpm_cpu_power_down(void); + +/** + * mcpm_cpu_suspend - bring the calling CPU in a suspended state + * + * @expected_residency: duration in microseconds the CPU is expected + * to remain suspended, or 0 if unknown/infinity. + * + * The calling CPU is suspended. The expected residency argument is used + * as a hint by the platform specific backend to implement the appropriate + * sleep state level according to the knowledge it has on wake-up latency + * for the given hardware. + * + * If this CPU is found to be the "last man standing" in the cluster + * then the cluster may be prepared for power-down too, if the expected + * residency makes it worthwhile. + * + * This must be called with interrupts disabled. + * + * This does not return. Re-entry in the kernel is expected via + * mcpm_entry_point. + */ +void mcpm_cpu_suspend(u64 expected_residency); + +/** + * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up + * + * This lets the platform specific backend code perform needed housekeeping + * work. This must be called by the newly activated CPU as soon as it is + * fully operational in kernel space, before it enables interrupts. + * + * If the operation cannot be performed then an error code is returned. + */ +int mcpm_cpu_powered_up(void); + +/* + * Platform specific methods used in the implementation of the above API. + */ +struct mcpm_platform_ops { + int (*power_up)(unsigned int cpu, unsigned int cluster); + void (*power_down)(void); + void (*suspend)(u64); + void (*powered_up)(void); +}; + +/** + * mcpm_platform_register - register platform specific power methods + * + * @ops: mcpm_platform_ops structure to register + * + * An error is returned if the registration has been done previously. + */ +int __init mcpm_platform_register(const struct mcpm_platform_ops *ops); + +/* Synchronisation structures for coordinating safe cluster setup/teardown: */ + +/* + * When modifying this structure, make sure you update the MCPM_SYNC_ defines + * to match. + */ +struct mcpm_sync_struct { + /* individual CPU states */ + struct { + s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE); + } cpus[MAX_CPUS_PER_CLUSTER]; + + /* cluster state */ + s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE); + + /* inbound-side state */ + s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE); +}; + +struct sync_struct { + struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS]; +}; + +extern unsigned long sync_phys; /* physical address of *mcpm_sync */ + +void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster); +void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster); +void __mcpm_outbound_leave_critical(unsigned int cluster, int state); +bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster); +int __mcpm_cluster_state(unsigned int cluster); + +int __init mcpm_sync_init( + void (*power_up_setup)(unsigned int affinity_level)); + +void __init mcpm_smp_set_ops(void); + +#else + +/* + * asm-offsets.h causes trouble when included in .c files, and cacheflush.h + * cannot be included in asm files. Let's work around the conflict like this. + */ +#include <asm/asm-offsets.h> +#define __CACHE_WRITEBACK_GRANULE CACHE_WRITEBACK_GRANULE + +#endif /* ! __ASSEMBLY__ */ + +/* Definitions for mcpm_sync_struct */ +#define CPU_DOWN 0x11 +#define CPU_COMING_UP 0x12 +#define CPU_UP 0x13 +#define CPU_GOING_DOWN 0x14 + +#define CLUSTER_DOWN 0x21 +#define CLUSTER_UP 0x22 +#define CLUSTER_GOING_DOWN 0x23 + +#define INBOUND_NOT_COMING_UP 0x31 +#define INBOUND_COMING_UP 0x32 + +/* + * Offsets for the mcpm_sync_struct members, for use in asm. + * We don't want to make them global to the kernel via asm-offsets.c. + */ +#define MCPM_SYNC_CLUSTER_CPUS 0 +#define MCPM_SYNC_CPU_SIZE __CACHE_WRITEBACK_GRANULE +#define MCPM_SYNC_CLUSTER_CLUSTER \ + (MCPM_SYNC_CLUSTER_CPUS + MCPM_SYNC_CPU_SIZE * MAX_CPUS_PER_CLUSTER) +#define MCPM_SYNC_CLUSTER_INBOUND \ + (MCPM_SYNC_CLUSTER_CLUSTER + __CACHE_WRITEBACK_GRANULE) +#define MCPM_SYNC_CLUSTER_SIZE \ + (MCPM_SYNC_CLUSTER_INBOUND + __CACHE_WRITEBACK_GRANULE) + +#endif diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index 863a6611323..a7b85e0d0cc 100644 --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -27,6 +27,8 @@ void __check_vmalloc_seq(struct mm_struct *mm); void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk); #define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) +DECLARE_PER_CPU(atomic64_t, active_asids); + #else /* !CONFIG_CPU_HAS_ASID */ #ifdef CONFIG_MMU diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 6ef8afd1b64..86b8fe398b9 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -111,7 +111,7 @@ #define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 2) << 6) /* HAP[2:1] */ +#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ /* * Hyp-mode PL2 PTE definitions for LPAE. diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 80d6fc4dbe4..9bcd262a900 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -61,6 +61,15 @@ extern void __pgd_error(const char *file, int line, pgd_t); #define FIRST_USER_ADDRESS PAGE_SIZE /* + * Use TASK_SIZE as the ceiling argument for free_pgtables() and + * free_pgd_range() to avoid freeing the modules pmd when LPAE is enabled (pmd + * page shared between user and kernel). + */ +#ifdef CONFIG_ARM_LPAE +#define USER_PGTABLES_CEILING TASK_SIZE +#endif + +/* * The pgprot_* and protection_map entries will be fixed up in runtime * to include the cachable and bufferable bits based on memory policy, * as well as any architecture dependent bits like global/ASID and SMP diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index cddda1f41f0..1995d1a8406 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -152,6 +152,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define TIF_SYSCALL_AUDIT 9 #define TIF_SYSCALL_TRACEPOINT 10 #define TIF_SECCOMP 11 /* seccomp syscall filtering active */ +#define TIF_NOHZ 12 /* in adaptive nohz mode */ #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 20 diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 4db8c8820f0..a3625d141c1 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -14,7 +14,6 @@ #include <asm/glue.h> -#define TLB_V3_PAGE (1 << 0) #define TLB_V4_U_PAGE (1 << 1) #define TLB_V4_D_PAGE (1 << 2) #define TLB_V4_I_PAGE (1 << 3) @@ -22,7 +21,6 @@ #define TLB_V6_D_PAGE (1 << 5) #define TLB_V6_I_PAGE (1 << 6) -#define TLB_V3_FULL (1 << 8) #define TLB_V4_U_FULL (1 << 9) #define TLB_V4_D_FULL (1 << 10) #define TLB_V4_I_FULL (1 << 11) @@ -52,7 +50,6 @@ * ============= * * We have the following to choose from: - * v3 - ARMv3 * v4 - ARMv4 without write buffer * v4wb - ARMv4 with write buffer without I TLB flush entry instruction * v4wbi - ARMv4 with write buffer with I TLB flush entry instruction @@ -169,7 +166,7 @@ # define v6wbi_always_flags (-1UL) #endif -#define v7wbi_tlb_flags_smp (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ +#define v7wbi_tlb_flags_smp (TLB_WB | TLB_BARRIER | \ TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | \ TLB_V7_UIS_ASID | TLB_V7_UIS_BP) #define v7wbi_tlb_flags_up (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ @@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero); @@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { + if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero); @@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && + if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { - tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr); @@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr); @@ -450,6 +443,21 @@ static inline void local_flush_bp_all(void) isb(); } +#ifdef CONFIG_ARM_ERRATA_798181 +static inline void dummy_flush_tlb_a15_erratum(void) +{ + /* + * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0. + */ + asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); + dsb(); +} +#else +static inline void dummy_flush_tlb_a15_erratum(void) +{ +} +#endif + /* * flush_pmd_entry * diff --git a/arch/arm/include/debug/uncompress.h b/arch/arm/include/debug/uncompress.h new file mode 100644 index 00000000000..0e2949b0fae --- /dev/null +++ b/arch/arm/include/debug/uncompress.h @@ -0,0 +1,7 @@ +#ifdef CONFIG_DEBUG_UNCOMPRESS +extern void putc(int c); +#else +static inline void putc(int c) {} +#endif +static inline void flush(void) {} +static inline void arch_decomp_setup(void) {} diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 023bfeb367b..c1ee007523d 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -53,12 +53,12 @@ #define KVM_ARM_FIQ_spsr fiq_regs[7] struct kvm_regs { - struct pt_regs usr_regs;/* R0_usr - R14_usr, PC, CPSR */ - __u32 svc_regs[3]; /* SP_svc, LR_svc, SPSR_svc */ - __u32 abt_regs[3]; /* SP_abt, LR_abt, SPSR_abt */ - __u32 und_regs[3]; /* SP_und, LR_und, SPSR_und */ - __u32 irq_regs[3]; /* SP_irq, LR_irq, SPSR_irq */ - __u32 fiq_regs[8]; /* R8_fiq - R14_fiq, SPSR_fiq */ + struct pt_regs usr_regs; /* R0_usr - R14_usr, PC, CPSR */ + unsigned long svc_regs[3]; /* SP_svc, LR_svc, SPSR_svc */ + unsigned long abt_regs[3]; /* SP_abt, LR_abt, SPSR_abt */ + unsigned long und_regs[3]; /* SP_und, LR_und, SPSR_und */ + unsigned long irq_regs[3]; /* SP_irq, LR_irq, SPSR_irq */ + unsigned long fiq_regs[8]; /* R8_fiq - R14_fiq, SPSR_fiq */ }; /* Supported Processor Types */ diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 923eec7105c..a53efa99369 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -149,6 +149,10 @@ int main(void) DEFINE(DMA_BIDIRECTIONAL, DMA_BIDIRECTIONAL); DEFINE(DMA_TO_DEVICE, DMA_TO_DEVICE); DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE); + BLANK(); + DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER); + DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE); + BLANK(); #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); DEFINE(VCPU_MIDR, offsetof(struct kvm_vcpu, arch.midr)); @@ -165,10 +169,10 @@ int main(void) DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc)); DEFINE(VCPU_CPSR, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr)); DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines)); - DEFINE(VCPU_HSR, offsetof(struct kvm_vcpu, arch.hsr)); - DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.hxfar)); - DEFINE(VCPU_HPFAR, offsetof(struct kvm_vcpu, arch.hpfar)); - DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.hyp_pc)); + DEFINE(VCPU_HSR, offsetof(struct kvm_vcpu, arch.fault.hsr)); + DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.fault.hxfar)); + DEFINE(VCPU_HPFAR, offsetof(struct kvm_vcpu, arch.fault.hpfar)); + DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.fault.hyp_pc)); #ifdef CONFIG_KVM_ARM_VGIC DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); DEFINE(VGIC_CPU_HCR, offsetof(struct vgic_cpu, vgic_hcr)); diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index a1f73b502ef..b2ed73c4548 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -462,6 +462,7 @@ static void pcibios_init_hw(struct hw_pci *hw, struct list_head *head) sys->busnr = busnr; sys->swizzle = hw->swizzle; sys->map_irq = hw->map_irq; + sys->align_resource = hw->align_resource; INIT_LIST_HEAD(&sys->resources); if (hw->private_data) @@ -574,6 +575,8 @@ char * __init pcibios_setup(char *str) resource_size_t pcibios_align_resource(void *data, const struct resource *res, resource_size_t size, resource_size_t align) { + struct pci_dev *dev = data; + struct pci_sys_data *sys = dev->sysdata; resource_size_t start = res->start; if (res->flags & IORESOURCE_IO && start & 0x300) @@ -581,6 +584,9 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, start = (start + align - 1) & ~(align - 1); + if (sys->align_resource) + return sys->align_resource(dev, res, start, size, align); + return start; } diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 0f82098c9bf..c66ca7e4ee9 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -192,18 +192,6 @@ __dabt_svc: svc_entry mov r2, sp dabt_helper - - @ - @ IRQs off again before pulling preserved data off the stack - @ - disable_irq_notrace - -#ifdef CONFIG_TRACE_IRQFLAGS - tst r5, #PSR_I_BIT - bleq trace_hardirqs_on - tst r5, #PSR_I_BIT - blne trace_hardirqs_off -#endif svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__dabt_svc) @@ -223,12 +211,7 @@ __irq_svc: blne svc_preempt #endif -#ifdef CONFIG_TRACE_IRQFLAGS - @ The parent context IRQs must have been enabled to get here in - @ the first place, so there's no point checking the PSR I bit. - bl trace_hardirqs_on -#endif - svc_exit r5 @ return from exception + svc_exit r5, irq = 1 @ return from exception UNWIND(.fnend ) ENDPROC(__irq_svc) @@ -295,22 +278,8 @@ __und_svc_fault: mov r0, sp @ struct pt_regs *regs bl __und_fault - @ - @ IRQs off again before pulling preserved data off the stack - @ __und_svc_finish: - disable_irq_notrace - - @ - @ restore SPSR and restart the instruction - @ ldr r5, [sp, #S_PSR] @ Get SVC cpsr -#ifdef CONFIG_TRACE_IRQFLAGS - tst r5, #PSR_I_BIT - bleq trace_hardirqs_on - tst r5, #PSR_I_BIT - blne trace_hardirqs_off -#endif svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__und_svc) @@ -320,18 +289,6 @@ __pabt_svc: svc_entry mov r2, sp @ regs pabt_helper - - @ - @ IRQs off again before pulling preserved data off the stack - @ - disable_irq_notrace - -#ifdef CONFIG_TRACE_IRQFLAGS - tst r5, #PSR_I_BIT - bleq trace_hardirqs_on - tst r5, #PSR_I_BIT - blne trace_hardirqs_off -#endif svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__pabt_svc) @@ -396,6 +353,7 @@ ENDPROC(__pabt_svc) #ifdef CONFIG_IRQSOFF_TRACER bl trace_hardirqs_off #endif + ct_user_exit save = 0 .endm .macro kuser_cmpxchg_check diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 3248cde504e..bc5bc0a9713 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -35,12 +35,11 @@ ret_fast_syscall: ldr r1, [tsk, #TI_FLAGS] tst r1, #_TIF_WORK_MASK bne fast_work_pending -#if defined(CONFIG_IRQSOFF_TRACER) asm_trace_hardirqs_on -#endif /* perform architecture specific actions before user return */ arch_ret_to_user r1, lr + ct_user_enter restore_user_regs fast = 1, offset = S_OFF UNWIND(.fnend ) @@ -71,11 +70,11 @@ ENTRY(ret_to_user_from_irq) tst r1, #_TIF_WORK_MASK bne work_pending no_work_pending: -#if defined(CONFIG_IRQSOFF_TRACER) asm_trace_hardirqs_on -#endif + /* perform architecture specific actions before user return */ arch_ret_to_user r1, lr + ct_user_enter save = 0 restore_user_regs fast = 0, offset = 0 ENDPROC(ret_to_user_from_irq) @@ -276,7 +275,13 @@ ENDPROC(ftrace_graph_caller_old) */ .macro mcount_enter +/* + * This pad compensates for the push {lr} at the call site. Note that we are + * unable to unwind through a function which does not otherwise save its lr. + */ + UNWIND(.pad #4) stmdb sp!, {r0-r3, lr} + UNWIND(.save {r0-r3, lr}) .endm .macro mcount_get_lr reg @@ -289,6 +294,7 @@ ENDPROC(ftrace_graph_caller_old) .endm ENTRY(__gnu_mcount_nc) +UNWIND(.fnstart) #ifdef CONFIG_DYNAMIC_FTRACE mov ip, lr ldmia sp!, {lr} @@ -296,17 +302,22 @@ ENTRY(__gnu_mcount_nc) #else __mcount #endif +UNWIND(.fnend) ENDPROC(__gnu_mcount_nc) #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(ftrace_caller) +UNWIND(.fnstart) __ftrace_caller +UNWIND(.fnend) ENDPROC(ftrace_caller) #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) +UNWIND(.fnstart) __ftrace_graph_caller +UNWIND(.fnend) ENDPROC(ftrace_graph_caller) #endif @@ -394,6 +405,7 @@ ENTRY(vector_swi) mcr p15, 0, ip, c1, c0 @ update control register #endif enable_irq + ct_user_exit get_thread_info tsk adr tbl, sys_call_table @ load syscall table pointer diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 9a8531eadd3..160f3376ba6 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -74,7 +74,24 @@ .endm #ifndef CONFIG_THUMB2_KERNEL - .macro svc_exit, rpsr + .macro svc_exit, rpsr, irq = 0 + .if \irq != 0 + @ IRQs already off +#ifdef CONFIG_TRACE_IRQFLAGS + @ The parent context IRQs must have been enabled to get here in + @ the first place, so there's no point checking the PSR I bit. + bl trace_hardirqs_on +#endif + .else + @ IRQs off again before pulling preserved data off the stack + disable_irq_notrace +#ifdef CONFIG_TRACE_IRQFLAGS + tst \rpsr, #PSR_I_BIT + bleq trace_hardirqs_on + tst \rpsr, #PSR_I_BIT + blne trace_hardirqs_off +#endif + .endif msr spsr_cxsf, \rpsr #if defined(CONFIG_CPU_V6) ldr r0, [sp] @@ -120,7 +137,24 @@ mov pc, \reg .endm #else /* CONFIG_THUMB2_KERNEL */ - .macro svc_exit, rpsr + .macro svc_exit, rpsr, irq = 0 + .if \irq != 0 + @ IRQs already off +#ifdef CONFIG_TRACE_IRQFLAGS + @ The parent context IRQs must have been enabled to get here in + @ the first place, so there's no point checking the PSR I bit. + bl trace_hardirqs_on +#endif + .else + @ IRQs off again before pulling preserved data off the stack + disable_irq_notrace +#ifdef CONFIG_TRACE_IRQFLAGS + tst \rpsr, #PSR_I_BIT + bleq trace_hardirqs_on + tst \rpsr, #PSR_I_BIT + blne trace_hardirqs_off +#endif + .endif ldr lr, [sp, #S_SP] @ top of the stack ldrd r0, r1, [sp, #S_LR] @ calling lr and pc clrex @ clear the exclusive monitor @@ -164,6 +198,34 @@ #endif /* !CONFIG_THUMB2_KERNEL */ /* + * Context tracking subsystem. Used to instrument transitions + * between user and kernel mode. + */ + .macro ct_user_exit, save = 1 +#ifdef CONFIG_CONTEXT_TRACKING + .if \save + stmdb sp!, {r0-r3, ip, lr} + bl user_exit + ldmia sp!, {r0-r3, ip, lr} + .else + bl user_exit + .endif +#endif + .endm + + .macro ct_user_enter, save = 1 +#ifdef CONFIG_CONTEXT_TRACKING + .if \save + stmdb sp!, {r0-r3, ip, lr} + bl user_enter + ldmia sp!, {r0-r3, ip, lr} + .else + bl user_enter + .endif +#endif + .endm + +/* * These are the registers used in the syscall handler, and allow us to * have in theory up to 7 arguments to a function - r0 to r6. * diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index 854bd22380d..5b391a689b4 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -98,8 +98,9 @@ __mmap_switched: str r9, [r4] @ Save processor ID str r1, [r5] @ Save machine type str r2, [r6] @ Save atags pointer - bic r4, r0, #CR_A @ Clear 'A' bit - stmia r7, {r0, r4} @ Save control register values + cmp r7, #0 + bicne r4, r0, #CR_A @ Clear 'A' bit + stmneia r7, {r0, r4} @ Save control register values b start_kernel ENDPROC(__mmap_switched) @@ -113,7 +114,11 @@ __mmap_switched_data: .long processor_id @ r4 .long __machine_arch_type @ r5 .long __atags_pointer @ r6 +#ifdef CONFIG_CPU_CP15 .long cr_alignment @ r7 +#else + .long 0 @ r7 +#endif .long init_thread_union + THREAD_START_SP @ sp .size __mmap_switched_data, . - __mmap_switched_data diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index 2c228a07e58..6a2e09c952c 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -32,15 +32,21 @@ * numbers for r1. * */ - .arm __HEAD + +#ifdef CONFIG_CPU_THUMBONLY + .thumb +ENTRY(stext) +#else + .arm ENTRY(stext) THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM. THUMB( bx r9 ) @ If this is a Thumb-2 kernel, THUMB( .thumb ) @ switch to Thumb now. THUMB(1: ) +#endif setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode @ and irqs disabled diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index e0eb9a1cae7..8bac553fe21 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -267,7 +267,7 @@ __create_page_tables: addne r6, r6, #1 << SECTION_SHIFT strne r6, [r3] -#if defined(CONFIG_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8) +#if defined(CONFIG_ARM_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8) sub r4, r4, #4 @ Fixup page table pointer @ for 64-bit descriptors #endif diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 96093b75ab9..1fd749ee4a1 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -966,7 +966,7 @@ static void reset_ctrl_regs(void *unused) } if (err) { - pr_warning("CPU %d debug is powered down!\n", cpu); + pr_warn_once("CPU %d debug is powered down!\n", cpu); cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu)); return; } @@ -987,7 +987,7 @@ clear_vcr: isb(); if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) { - pr_warning("CPU %d failed to disable vector catch\n", cpu); + pr_warn_once("CPU %d failed to disable vector catch\n", cpu); return; } @@ -1007,7 +1007,7 @@ clear_vcr: } if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) { - pr_warning("CPU %d failed to clear debug register pairs\n", cpu); + pr_warn_once("CPU %d failed to clear debug register pairs\n", cpu); return; } @@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = { +static struct notifier_block dbg_cpu_pm_nb = { .notifier_call = dbg_cpu_pm_notify, }; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 146157dfe27..8c3094d0f7b 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events, struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu *leader_pmu = event->group_leader->pmu; - if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) + if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) + return 1; + + if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) return 1; return armpmu->get_event_idx(hw_events, event) >= 0; diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c index 8085417555d..fafedd86885 100644 --- a/arch/arm/kernel/return_address.c +++ b/arch/arm/kernel/return_address.c @@ -26,7 +26,7 @@ static int save_return_addr(struct stackframe *frame, void *d) struct return_address_data *data = d; if (!data->level) { - data->addr = (void *)frame->lr; + data->addr = (void *)frame->pc; return 1; } else { @@ -41,7 +41,8 @@ void *return_address(unsigned int level) struct stackframe frame; register unsigned long current_sp asm ("sp"); - data.level = level + 1; + data.level = level + 2; + data.addr = NULL; frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_sp; diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c index bd6f56b9ec2..59d2adb764a 100644 --- a/arch/arm/kernel/sched_clock.c +++ b/arch/arm/kernel/sched_clock.c @@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void) static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; -static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) +static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) { return (cyc * mult) >> shift; } -static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask) +static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask) { u64 epoch_ns; u32 epoch_cyc; diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 3f6cbb2e3ed..728007c4a2b 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -56,7 +56,6 @@ #include <asm/virt.h> #include "atags.h" -#include "tcm.h" #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE) @@ -291,10 +290,10 @@ static int cpu_has_aliasing_icache(unsigned int arch) static void __init cacheid_init(void) { - unsigned int cachetype = read_cpuid_cachetype(); unsigned int arch = cpu_architecture(); if (arch >= CPU_ARCH_ARMv6) { + unsigned int cachetype = read_cpuid_cachetype(); if ((cachetype & (7 << 29)) == 4 << 29) { /* ARMv7 register format */ arch = CPU_ARCH_ARMv7; @@ -353,6 +352,23 @@ void __init early_print(const char *str, ...) printk("%s", buf); } +static void __init cpuid_init_hwcaps(void) +{ + unsigned int divide_instrs; + + if (cpu_architecture() < CPU_ARCH_ARMv7) + return; + + divide_instrs = (read_cpuid_ext(CPUID_EXT_ISAR0) & 0x0f000000) >> 24; + + switch (divide_instrs) { + case 2: + elf_hwcap |= HWCAP_IDIVA; + case 1: + elf_hwcap |= HWCAP_IDIVT; + } +} + static void __init feat_v6_fixup(void) { int id = read_cpuid_id(); @@ -373,7 +389,7 @@ static void __init feat_v6_fixup(void) * * cpu_init sets up the per-CPU stacks. */ -void cpu_init(void) +void notrace cpu_init(void) { unsigned int cpu = smp_processor_id(); struct stack *stk = &stacks[cpu]; @@ -483,8 +499,11 @@ static void __init setup_processor(void) snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c", list->elf_name, ENDIANNESS); elf_hwcap = list->elf_hwcap; + + cpuid_init_hwcaps(); + #ifndef CONFIG_ARM_THUMB - elf_hwcap &= ~HWCAP_THUMB; + elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT); #endif feat_v6_fixup(); @@ -524,7 +543,7 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) size -= start & ~PAGE_MASK; bank->start = PAGE_ALIGN(start); -#ifndef CONFIG_LPAE +#ifndef CONFIG_ARM_LPAE if (bank->start + size < bank->start) { printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in " "32-bit physical address space\n", (long long)start); @@ -778,8 +797,6 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); - tcm_init(); - #ifdef CONFIG_MULTI_IRQ_HANDLER handle_arch_irq = mdesc->handle_irq; #endif diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 79078edbb9b..4231034b812 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -211,6 +211,13 @@ void __cpuinit __cpu_die(unsigned int cpu) } printk(KERN_NOTICE "CPU%u: shutdown\n", cpu); + /* + * platform_cpu_kill() is generally expected to do the powering off + * and/or cutting of clocks to the dying CPU. Optionally, this may + * be done by the CPU which is dying in preference to supporting + * this call, but that means there is _no_ synchronisation between + * the requesting CPU and the dying CPU actually losing power. + */ if (!platform_cpu_kill(cpu)) printk("CPU%u: unable to kill\n", cpu); } @@ -230,14 +237,41 @@ void __ref cpu_die(void) idle_task_exit(); local_irq_disable(); - mb(); - /* Tell __cpu_die() that this CPU is now safe to dispose of */ + /* + * Flush the data out of the L1 cache for this CPU. This must be + * before the completion to ensure that data is safely written out + * before platform_cpu_kill() gets called - which may disable + * *this* CPU and power down its cache. + */ + flush_cache_louis(); + + /* + * Tell __cpu_die() that this CPU is now safe to dispose of. Once + * this returns, power and/or clocks can be removed at any point + * from this CPU and its cache by platform_cpu_kill(). + */ RCU_NONIDLE(complete(&cpu_died)); /* - * actual CPU shutdown procedure is at least platform (if not - * CPU) specific. + * Ensure that the cache lines associated with that completion are + * written out. This covers the case where _this_ CPU is doing the + * powering down, to ensure that the completion is visible to the + * CPU waiting for this one. + */ + flush_cache_louis(); + + /* + * The actual CPU shutdown procedure is at least platform (if not + * CPU) specific. This may remove power, or it may simply spin. + * + * Platforms are generally expected *NOT* to return from this call, + * although there are some which do because they have no way to + * power down the CPU. These platforms are the _only_ reason we + * have a return path which uses the fragment of assembly below. + * + * The return path should not be used for platforms which can + * power off the CPU. */ if (smp_ops.cpu_die) smp_ops.cpu_die(cpu); @@ -673,9 +707,6 @@ static int cpufreq_callback(struct notifier_block *nb, if (freq->flags & CPUFREQ_CONST_LOOPS) return NOTIFY_OK; - if (arm_delay_ops.const_clock) - return NOTIFY_OK; - if (!per_cpu(l_p_j_ref, cpu)) { per_cpu(l_p_j_ref, cpu) = per_cpu(cpu_data, cpu).loops_per_jiffy; diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 45eac87ed66..5bc1a63284e 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -41,7 +41,7 @@ void scu_enable(void __iomem *scu_base) #ifdef CONFIG_ARM_ERRATA_764369 /* Cortex-A9 only */ - if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) { + if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) { scu_ctrl = __raw_readl(scu_base + 0x30); if (!(scu_ctrl & 1)) __raw_writel(scu_ctrl | 0x1, scu_base + 0x30); diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index bd030053139..9a52a07aa40 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -12,6 +12,7 @@ #include <asm/smp_plat.h> #include <asm/tlbflush.h> +#include <asm/mmu_context.h> /**********************************************************************/ @@ -69,12 +70,73 @@ static inline void ipi_flush_bp_all(void *ignored) local_flush_bp_all(); } +#ifdef CONFIG_ARM_ERRATA_798181 +static int erratum_a15_798181(void) +{ + unsigned int midr = read_cpuid_id(); + + /* Cortex-A15 r0p0..r3p2 affected */ + if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2) + return 0; + return 1; +} +#else +static int erratum_a15_798181(void) +{ + return 0; +} +#endif + +static void ipi_flush_tlb_a15_erratum(void *arg) +{ + dmb(); +} + +static void broadcast_tlb_a15_erratum(void) +{ + if (!erratum_a15_798181()) + return; + + dummy_flush_tlb_a15_erratum(); + smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1); +} + +static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) +{ + int cpu, this_cpu; + cpumask_t mask = { CPU_BITS_NONE }; + + if (!erratum_a15_798181()) + return; + + dummy_flush_tlb_a15_erratum(); + this_cpu = get_cpu(); + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + /* + * We only need to send an IPI if the other CPUs are running + * the same ASID as the one being invalidated. There is no + * need for locking around the active_asids check since the + * switch_mm() function has at least one dmb() (as required by + * this workaround) in case a context switch happens on + * another CPU after the condition below. + */ + if (atomic64_read(&mm->context.id) == + atomic64_read(&per_cpu(active_asids, cpu))) + cpumask_set_cpu(cpu, &mask); + } + smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1); + put_cpu(); +} + void flush_tlb_all(void) { if (tlb_ops_need_broadcast()) on_each_cpu(ipi_flush_tlb_all, NULL, 1); else local_flush_tlb_all(); + broadcast_tlb_a15_erratum(); } void flush_tlb_mm(struct mm_struct *mm) @@ -83,6 +145,7 @@ void flush_tlb_mm(struct mm_struct *mm) on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1); else local_flush_tlb_mm(mm); + broadcast_tlb_mm_a15_erratum(mm); } void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) @@ -95,6 +158,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) &ta, 1); } else local_flush_tlb_page(vma, uaddr); + broadcast_tlb_mm_a15_erratum(vma->vm_mm); } void flush_tlb_kernel_page(unsigned long kaddr) @@ -105,6 +169,7 @@ void flush_tlb_kernel_page(unsigned long kaddr) on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1); } else local_flush_tlb_kernel_page(kaddr); + broadcast_tlb_a15_erratum(); } void flush_tlb_range(struct vm_area_struct *vma, @@ -119,6 +184,7 @@ void flush_tlb_range(struct vm_area_struct *vma, &ta, 1); } else local_flush_tlb_range(vma, start, end); + broadcast_tlb_mm_a15_erratum(vma->vm_mm); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) @@ -130,6 +196,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1); } else local_flush_tlb_kernel_range(start, end); + broadcast_tlb_a15_erratum(); } void flush_bp_all(void) diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c index 30ae6bb4a31..f50f19e5c13 100644 --- a/arch/arm/kernel/tcm.c +++ b/arch/arm/kernel/tcm.c @@ -17,7 +17,6 @@ #include <asm/mach/map.h> #include <asm/memory.h> #include <asm/system_info.h> -#include "tcm.h" static struct gen_pool *tcm_pool; static bool dtcm_present; diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index fc96ce6f235..8dc5e76cb78 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -17,7 +17,7 @@ AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) kvm-arm-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) obj-y += kvm-arm.o init.o interrupts.o -obj-y += arm.o guest.o mmu.o emulate.o reset.o +obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o obj-y += coproc.o coproc_a15.o mmio.o psci.o obj-$(CONFIG_KVM_ARM_VGIC) += vgic.o obj-$(CONFIG_KVM_ARM_TIMER) += arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 5a936988eb2..a0dfc2a53f9 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -30,11 +30,9 @@ #define CREATE_TRACE_POINTS #include "trace.h" -#include <asm/unified.h> #include <asm/uaccess.h> #include <asm/ptrace.h> #include <asm/mman.h> -#include <asm/cputype.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> #include <asm/virt.h> @@ -44,14 +42,13 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> #include <asm/kvm_psci.h> -#include <asm/opcodes.h> #ifdef REQUIRES_VIRT __asm__(".arch_extension virt"); #endif static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); -static struct vfp_hard_struct __percpu *kvm_host_vfp_state; +static kvm_kernel_vfp_t __percpu *kvm_host_vfp_state; static unsigned long hyp_default_vectors; /* Per-CPU variable containing the currently running vcpu. */ @@ -201,6 +198,7 @@ int kvm_dev_ioctl_check_extension(long ext) break; case KVM_CAP_ARM_SET_DEVICE_ADDR: r = 1; + break; case KVM_CAP_NR_VCPUS: r = num_online_cpus(); break; @@ -303,22 +301,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) return 0; } -int __attribute_const__ kvm_target_cpu(void) -{ - unsigned long implementor = read_cpuid_implementor(); - unsigned long part_number = read_cpuid_part_number(); - - if (implementor != ARM_CPU_IMP_ARM) - return -EINVAL; - - switch (part_number) { - case ARM_CPU_PART_CORTEX_A15: - return KVM_ARM_TARGET_CORTEX_A15; - default: - return -EINVAL; - } -} - int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { int ret; @@ -481,163 +463,6 @@ static void update_vttbr(struct kvm *kvm) spin_unlock(&kvm_vmid_lock); } -static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* SVC called from Hyp mode should never get here */ - kvm_debug("SVC called from Hyp mode shouldn't go here\n"); - BUG(); - return -EINVAL; /* Squash warning */ -} - -static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), - vcpu->arch.hsr & HSR_HVC_IMM_MASK); - - if (kvm_psci_call(vcpu)) - return 1; - - kvm_inject_undefined(vcpu); - return 1; -} - -static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - if (kvm_psci_call(vcpu)) - return 1; - - kvm_inject_undefined(vcpu); - return 1; -} - -static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* The hypervisor should never cause aborts */ - kvm_err("Prefetch Abort taken from Hyp mode at %#08x (HSR: %#08x)\n", - vcpu->arch.hxfar, vcpu->arch.hsr); - return -EFAULT; -} - -static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - /* This is either an error in the ws. code or an external abort */ - kvm_err("Data Abort taken from Hyp mode at %#08x (HSR: %#08x)\n", - vcpu->arch.hxfar, vcpu->arch.hsr); - return -EFAULT; -} - -typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); -static exit_handle_fn arm_exit_handlers[] = { - [HSR_EC_WFI] = kvm_handle_wfi, - [HSR_EC_CP15_32] = kvm_handle_cp15_32, - [HSR_EC_CP15_64] = kvm_handle_cp15_64, - [HSR_EC_CP14_MR] = kvm_handle_cp14_access, - [HSR_EC_CP14_LS] = kvm_handle_cp14_load_store, - [HSR_EC_CP14_64] = kvm_handle_cp14_access, - [HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access, - [HSR_EC_CP10_ID] = kvm_handle_cp10_id, - [HSR_EC_SVC_HYP] = handle_svc_hyp, - [HSR_EC_HVC] = handle_hvc, - [HSR_EC_SMC] = handle_smc, - [HSR_EC_IABT] = kvm_handle_guest_abort, - [HSR_EC_IABT_HYP] = handle_pabt_hyp, - [HSR_EC_DABT] = kvm_handle_guest_abort, - [HSR_EC_DABT_HYP] = handle_dabt_hyp, -}; - -/* - * A conditional instruction is allowed to trap, even though it - * wouldn't be executed. So let's re-implement the hardware, in - * software! - */ -static bool kvm_condition_valid(struct kvm_vcpu *vcpu) -{ - unsigned long cpsr, cond, insn; - - /* - * Exception Code 0 can only happen if we set HCR.TGE to 1, to - * catch undefined instructions, and then we won't get past - * the arm_exit_handlers test anyway. - */ - BUG_ON(((vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT) == 0); - - /* Top two bits non-zero? Unconditional. */ - if (vcpu->arch.hsr >> 30) - return true; - - cpsr = *vcpu_cpsr(vcpu); - - /* Is condition field valid? */ - if ((vcpu->arch.hsr & HSR_CV) >> HSR_CV_SHIFT) - cond = (vcpu->arch.hsr & HSR_COND) >> HSR_COND_SHIFT; - else { - /* This can happen in Thumb mode: examine IT state. */ - unsigned long it; - - it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); - - /* it == 0 => unconditional. */ - if (it == 0) - return true; - - /* The cond for this insn works out as the top 4 bits. */ - cond = (it >> 4); - } - - /* Shift makes it look like an ARM-mode instruction */ - insn = cond << 28; - return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL; -} - -/* - * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on - * proper exit to QEMU. - */ -static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, - int exception_index) -{ - unsigned long hsr_ec; - - switch (exception_index) { - case ARM_EXCEPTION_IRQ: - return 1; - case ARM_EXCEPTION_UNDEFINED: - kvm_err("Undefined exception in Hyp mode at: %#08x\n", - vcpu->arch.hyp_pc); - BUG(); - panic("KVM: Hypervisor undefined exception!\n"); - case ARM_EXCEPTION_DATA_ABORT: - case ARM_EXCEPTION_PREF_ABORT: - case ARM_EXCEPTION_HVC: - hsr_ec = (vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT; - - if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) - || !arm_exit_handlers[hsr_ec]) { - kvm_err("Unkown exception class: %#08lx, " - "hsr: %#08x\n", hsr_ec, - (unsigned int)vcpu->arch.hsr); - BUG(); - } - - /* - * See ARM ARM B1.14.1: "Hyp traps on instructions - * that fail their condition code check" - */ - if (!kvm_condition_valid(vcpu)) { - bool is_wide = vcpu->arch.hsr & HSR_IL; - kvm_skip_instr(vcpu, is_wide); - return 1; - } - - return arm_exit_handlers[hsr_ec](vcpu, run); - default: - kvm_pr_unimpl("Unsupported exception type: %d", - exception_index); - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - return 0; - } -} - static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) { if (likely(vcpu->arch.has_run_once)) @@ -972,7 +797,6 @@ long kvm_arch_vm_ioctl(struct file *filp, static void cpu_init_hyp_mode(void *vector) { unsigned long long pgd_ptr; - unsigned long pgd_low, pgd_high; unsigned long hyp_stack_ptr; unsigned long stack_page; unsigned long vector_ptr; @@ -981,20 +805,11 @@ static void cpu_init_hyp_mode(void *vector) __hyp_set_vectors((unsigned long)vector); pgd_ptr = (unsigned long long)kvm_mmu_get_httbr(); - pgd_low = (pgd_ptr & ((1ULL << 32) - 1)); - pgd_high = (pgd_ptr >> 32ULL); stack_page = __get_cpu_var(kvm_arm_hyp_stack_page); hyp_stack_ptr = stack_page + PAGE_SIZE; vector_ptr = (unsigned long)__kvm_hyp_vector; - /* - * Call initialization code, and switch to the full blown - * HYP code. The init code doesn't need to preserve these registers as - * r1-r3 and r12 are already callee save according to the AAPCS. - * Note that we slightly misuse the prototype by casing the pgd_low to - * a void *. - */ - kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr); + __cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr); } /** @@ -1077,7 +892,7 @@ static int init_hyp_mode(void) /* * Map the host VFP structures */ - kvm_host_vfp_state = alloc_percpu(struct vfp_hard_struct); + kvm_host_vfp_state = alloc_percpu(kvm_kernel_vfp_t); if (!kvm_host_vfp_state) { err = -ENOMEM; kvm_err("Cannot allocate host VFP state\n"); @@ -1085,7 +900,7 @@ static int init_hyp_mode(void) } for_each_possible_cpu(cpu) { - struct vfp_hard_struct *vfp; + kvm_kernel_vfp_t *vfp; vfp = per_cpu_ptr(kvm_host_vfp_state, cpu); err = create_hyp_mappings(vfp, vfp + 1); diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 4ea9a982269..8eea97be1ed 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -76,14 +76,14 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, const struct coproc_params *p, const struct coproc_reg *r) { - u32 val; + unsigned long val; int cpu; - cpu = get_cpu(); - if (!p->is_write) return read_from_write_only(vcpu, p); + cpu = get_cpu(); + cpumask_setall(&vcpu->arch.require_dcache_flush); cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); @@ -293,12 +293,12 @@ static int emulate_cp15(struct kvm_vcpu *vcpu, if (likely(r->access(vcpu, params, r))) { /* Skip instruction, since it was emulated */ - kvm_skip_instr(vcpu, (vcpu->arch.hsr >> 25) & 1); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 1; } /* If access function fails, it should complain. */ } else { - kvm_err("Unsupported guest CP15 access at: %08x\n", + kvm_err("Unsupported guest CP15 access at: %08lx\n", *vcpu_pc(vcpu)); print_cp_instr(params); } @@ -315,14 +315,14 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct coproc_params params; - params.CRm = (vcpu->arch.hsr >> 1) & 0xf; - params.Rt1 = (vcpu->arch.hsr >> 5) & 0xf; - params.is_write = ((vcpu->arch.hsr & 1) == 0); + params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; + params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; + params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); params.is_64bit = true; - params.Op1 = (vcpu->arch.hsr >> 16) & 0xf; + params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf; params.Op2 = 0; - params.Rt2 = (vcpu->arch.hsr >> 10) & 0xf; + params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; params.CRn = 0; return emulate_cp15(vcpu, ¶ms); @@ -347,14 +347,14 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct coproc_params params; - params.CRm = (vcpu->arch.hsr >> 1) & 0xf; - params.Rt1 = (vcpu->arch.hsr >> 5) & 0xf; - params.is_write = ((vcpu->arch.hsr & 1) == 0); + params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf; + params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf; + params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0); params.is_64bit = false; - params.CRn = (vcpu->arch.hsr >> 10) & 0xf; - params.Op1 = (vcpu->arch.hsr >> 14) & 0x7; - params.Op2 = (vcpu->arch.hsr >> 17) & 0x7; + params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf; + params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 14) & 0x7; + params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7; params.Rt2 = 0; return emulate_cp15(vcpu, ¶ms); diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h index 992adfafa2f..b7301d3e479 100644 --- a/arch/arm/kvm/coproc.h +++ b/arch/arm/kvm/coproc.h @@ -84,7 +84,7 @@ static inline bool read_zero(struct kvm_vcpu *vcpu, static inline bool write_to_read_only(struct kvm_vcpu *vcpu, const struct coproc_params *params) { - kvm_debug("CP15 write to read-only register at: %08x\n", + kvm_debug("CP15 write to read-only register at: %08lx\n", *vcpu_pc(vcpu)); print_cp_instr(params); return false; @@ -93,7 +93,7 @@ static inline bool write_to_read_only(struct kvm_vcpu *vcpu, static inline bool read_from_write_only(struct kvm_vcpu *vcpu, const struct coproc_params *params) { - kvm_debug("CP15 read to write-only register at: %08x\n", + kvm_debug("CP15 read to write-only register at: %08lx\n", *vcpu_pc(vcpu)); print_cp_instr(params); return false; diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c index d61450ac666..bdede9e7da5 100644 --- a/arch/arm/kvm/emulate.c +++ b/arch/arm/kvm/emulate.c @@ -20,6 +20,7 @@ #include <linux/kvm_host.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> +#include <asm/opcodes.h> #include <trace/events/kvm.h> #include "trace.h" @@ -109,10 +110,10 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = { * Return a pointer to the register number valid in the current mode of * the virtual CPU. */ -u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) +unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) { - u32 *reg_array = (u32 *)&vcpu->arch.regs; - u32 mode = *vcpu_cpsr(vcpu) & MODE_MASK; + unsigned long *reg_array = (unsigned long *)&vcpu->arch.regs; + unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; switch (mode) { case USR_MODE...SVC_MODE: @@ -141,9 +142,9 @@ u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num) /* * Return the SPSR for the current mode of the virtual CPU. */ -u32 *vcpu_spsr(struct kvm_vcpu *vcpu) +unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu) { - u32 mode = *vcpu_cpsr(vcpu) & MODE_MASK; + unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK; switch (mode) { case SVC_MODE: return &vcpu->arch.regs.KVM_ARM_SVC_spsr; @@ -160,20 +161,48 @@ u32 *vcpu_spsr(struct kvm_vcpu *vcpu) } } -/** - * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest - * @vcpu: the vcpu pointer - * @run: the kvm_run structure pointer - * - * Simply sets the wait_for_interrupts flag on the vcpu structure, which will - * halt execution of world-switches and schedule other host processes until - * there is an incoming IRQ or FIQ to the VM. +/* + * A conditional instruction is allowed to trap, even though it + * wouldn't be executed. So let's re-implement the hardware, in + * software! */ -int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) +bool kvm_condition_valid(struct kvm_vcpu *vcpu) { - trace_kvm_wfi(*vcpu_pc(vcpu)); - kvm_vcpu_block(vcpu); - return 1; + unsigned long cpsr, cond, insn; + + /* + * Exception Code 0 can only happen if we set HCR.TGE to 1, to + * catch undefined instructions, and then we won't get past + * the arm_exit_handlers test anyway. + */ + BUG_ON(!kvm_vcpu_trap_get_class(vcpu)); + + /* Top two bits non-zero? Unconditional. */ + if (kvm_vcpu_get_hsr(vcpu) >> 30) + return true; + + cpsr = *vcpu_cpsr(vcpu); + + /* Is condition field valid? */ + if ((kvm_vcpu_get_hsr(vcpu) & HSR_CV) >> HSR_CV_SHIFT) + cond = (kvm_vcpu_get_hsr(vcpu) & HSR_COND) >> HSR_COND_SHIFT; + else { + /* This can happen in Thumb mode: examine IT state. */ + unsigned long it; + + it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); + + /* it == 0 => unconditional. */ + if (it == 0) + return true; + + /* The cond for this insn works out as the top 4 bits. */ + cond = (it >> 4); + } + + /* Shift makes it look like an ARM-mode instruction */ + insn = cond << 28; + return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL; } /** @@ -257,9 +286,9 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu) */ void kvm_inject_undefined(struct kvm_vcpu *vcpu) { - u32 new_lr_value; - u32 new_spsr_value; - u32 cpsr = *vcpu_cpsr(vcpu); + unsigned long new_lr_value; + unsigned long new_spsr_value; + unsigned long cpsr = *vcpu_cpsr(vcpu); u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; bool is_thumb = (cpsr & PSR_T_BIT); u32 vect_offset = 4; @@ -291,9 +320,9 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu) */ static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr) { - u32 new_lr_value; - u32 new_spsr_value; - u32 cpsr = *vcpu_cpsr(vcpu); + unsigned long new_lr_value; + unsigned long new_spsr_value; + unsigned long cpsr = *vcpu_cpsr(vcpu); u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; bool is_thumb = (cpsr & PSR_T_BIT); u32 vect_offset; diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 2339d9609d3..152d0361218 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -22,6 +22,7 @@ #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/fs.h> +#include <asm/cputype.h> #include <asm/uaccess.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> @@ -180,6 +181,22 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return -EINVAL; } +int __attribute_const__ kvm_target_cpu(void) +{ + unsigned long implementor = read_cpuid_implementor(); + unsigned long part_number = read_cpuid_part_number(); + + if (implementor != ARM_CPU_IMP_ARM) + return -EINVAL; + + switch (part_number) { + case ARM_CPU_PART_CORTEX_A15: + return KVM_ARM_TARGET_CORTEX_A15; + default: + return -EINVAL; + } +} + int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c new file mode 100644 index 00000000000..26ad17310a1 --- /dev/null +++ b/arch/arm/kvm/handle_exit.c @@ -0,0 +1,164 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.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, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_coproc.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_psci.h> +#include <trace/events/kvm.h> + +#include "trace.h" + +#include "trace.h" + +typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); + +static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* SVC called from Hyp mode should never get here */ + kvm_debug("SVC called from Hyp mode shouldn't go here\n"); + BUG(); + return -EINVAL; /* Squash warning */ +} + +static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), + kvm_vcpu_hvc_get_imm(vcpu)); + + if (kvm_psci_call(vcpu)) + return 1; + + kvm_inject_undefined(vcpu); + return 1; +} + +static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + if (kvm_psci_call(vcpu)) + return 1; + + kvm_inject_undefined(vcpu); + return 1; +} + +static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* The hypervisor should never cause aborts */ + kvm_err("Prefetch Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n", + kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu)); + return -EFAULT; +} + +static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* This is either an error in the ws. code or an external abort */ + kvm_err("Data Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n", + kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu)); + return -EFAULT; +} + +/** + * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest + * @vcpu: the vcpu pointer + * @run: the kvm_run structure pointer + * + * Simply sets the wait_for_interrupts flag on the vcpu structure, which will + * halt execution of world-switches and schedule other host processes until + * there is an incoming IRQ or FIQ to the VM. + */ +static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + trace_kvm_wfi(*vcpu_pc(vcpu)); + kvm_vcpu_block(vcpu); + return 1; +} + +static exit_handle_fn arm_exit_handlers[] = { + [HSR_EC_WFI] = kvm_handle_wfi, + [HSR_EC_CP15_32] = kvm_handle_cp15_32, + [HSR_EC_CP15_64] = kvm_handle_cp15_64, + [HSR_EC_CP14_MR] = kvm_handle_cp14_access, + [HSR_EC_CP14_LS] = kvm_handle_cp14_load_store, + [HSR_EC_CP14_64] = kvm_handle_cp14_access, + [HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access, + [HSR_EC_CP10_ID] = kvm_handle_cp10_id, + [HSR_EC_SVC_HYP] = handle_svc_hyp, + [HSR_EC_HVC] = handle_hvc, + [HSR_EC_SMC] = handle_smc, + [HSR_EC_IABT] = kvm_handle_guest_abort, + [HSR_EC_IABT_HYP] = handle_pabt_hyp, + [HSR_EC_DABT] = kvm_handle_guest_abort, + [HSR_EC_DABT_HYP] = handle_dabt_hyp, +}; + +static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) +{ + u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); + + if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) || + !arm_exit_handlers[hsr_ec]) { + kvm_err("Unkown exception class: hsr: %#08x\n", + (unsigned int)kvm_vcpu_get_hsr(vcpu)); + BUG(); + } + + return arm_exit_handlers[hsr_ec]; +} + +/* + * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on + * proper exit to userspace. + */ +int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, + int exception_index) +{ + exit_handle_fn exit_handler; + + switch (exception_index) { + case ARM_EXCEPTION_IRQ: + return 1; + case ARM_EXCEPTION_UNDEFINED: + kvm_err("Undefined exception in Hyp mode at: %#08lx\n", + kvm_vcpu_get_hyp_pc(vcpu)); + BUG(); + panic("KVM: Hypervisor undefined exception!\n"); + case ARM_EXCEPTION_DATA_ABORT: + case ARM_EXCEPTION_PREF_ABORT: + case ARM_EXCEPTION_HVC: + /* + * See ARM ARM B1.14.1: "Hyp traps on instructions + * that fail their condition code check" + */ + if (!kvm_condition_valid(vcpu)) { + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; + } + + exit_handler = kvm_get_exit_handler(vcpu); + + return exit_handler(vcpu, run); + default: + kvm_pr_unimpl("Unsupported exception type: %d", + exception_index); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return 0; + } +} diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 8ca87ab0919..f7793df62f5 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -35,15 +35,18 @@ __kvm_hyp_code_start: /******************************************************************** * Flush per-VMID TLBs * - * void __kvm_tlb_flush_vmid(struct kvm *kvm); + * void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); * * We rely on the hardware to broadcast the TLB invalidation to all CPUs * inside the inner-shareable domain (which is the case for all v7 * implementations). If we come across a non-IS SMP implementation, we'll * have to use an IPI based mechanism. Until then, we stick to the simple * hardware assisted version. + * + * As v7 does not support flushing per IPA, just nuke the whole TLB + * instead, ignoring the ipa value. */ -ENTRY(__kvm_tlb_flush_vmid) +ENTRY(__kvm_tlb_flush_vmid_ipa) push {r2, r3} add r0, r0, #KVM_VTTBR @@ -60,7 +63,7 @@ ENTRY(__kvm_tlb_flush_vmid) pop {r2, r3} bx lr -ENDPROC(__kvm_tlb_flush_vmid) +ENDPROC(__kvm_tlb_flush_vmid_ipa) /******************************************************************** * Flush TLBs and instruction caches of all CPUs inside the inner-shareable @@ -235,9 +238,9 @@ ENTRY(kvm_call_hyp) * instruction is issued since all traps are disabled when running the host * kernel as per the Hyp-mode initialization at boot time. * - * HVC instructions cause a trap to the vector page + offset 0x18 (see hyp_hvc + * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc * below) when the HVC instruction is called from SVC mode (i.e. a guest or the - * host kernel) and they cause a trap to the vector page + offset 0xc when HVC + * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC * instructions are called from within Hyp-mode. * * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode): diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 98a870ff1a5..72a12f2171b 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -33,16 +33,16 @@ */ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) { - __u32 *dest; + unsigned long *dest; unsigned int len; int mask; if (!run->mmio.is_write) { dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt); - memset(dest, 0, sizeof(int)); + *dest = 0; len = run->mmio.len; - if (len > 4) + if (len > sizeof(unsigned long)) return -EINVAL; memcpy(dest, run->mmio.data, len); @@ -50,7 +50,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, *((u64 *)run->mmio.data)); - if (vcpu->arch.mmio_decode.sign_extend && len < 4) { + if (vcpu->arch.mmio_decode.sign_extend && + len < sizeof(unsigned long)) { mask = 1U << ((len * 8) - 1); *dest = (*dest ^ mask) - mask; } @@ -65,40 +66,29 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long rt, len; bool is_write, sign_extend; - if ((vcpu->arch.hsr >> 8) & 1) { + if (kvm_vcpu_dabt_isextabt(vcpu)) { /* cache operation on I/O addr, tell guest unsupported */ - kvm_inject_dabt(vcpu, vcpu->arch.hxfar); + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 1; } - if ((vcpu->arch.hsr >> 7) & 1) { + if (kvm_vcpu_dabt_iss1tw(vcpu)) { /* page table accesses IO mem: tell guest to fix its TTBR */ - kvm_inject_dabt(vcpu, vcpu->arch.hxfar); + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 1; } - switch ((vcpu->arch.hsr >> 22) & 0x3) { - case 0: - len = 1; - break; - case 1: - len = 2; - break; - case 2: - len = 4; - break; - default: - kvm_err("Hardware is weird: SAS 0b11 is reserved\n"); - return -EFAULT; - } + len = kvm_vcpu_dabt_get_as(vcpu); + if (unlikely(len < 0)) + return len; - is_write = vcpu->arch.hsr & HSR_WNR; - sign_extend = vcpu->arch.hsr & HSR_SSE; - rt = (vcpu->arch.hsr & HSR_SRT_MASK) >> HSR_SRT_SHIFT; + is_write = kvm_vcpu_dabt_iswrite(vcpu); + sign_extend = kvm_vcpu_dabt_issext(vcpu); + rt = kvm_vcpu_dabt_get_rd(vcpu); if (kvm_vcpu_reg_is_pc(vcpu, rt)) { /* IO memory trying to read/write pc */ - kvm_inject_pabt(vcpu, vcpu->arch.hxfar); + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 1; } @@ -112,7 +102,7 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * The MMIO instruction is emulated and should not be re-executed * in the guest. */ - kvm_skip_instr(vcpu, (vcpu->arch.hsr >> 25) & 1); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 0; } @@ -130,7 +120,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, * space do its magic. */ - if (vcpu->arch.hsr & HSR_ISV) { + if (kvm_vcpu_dabt_isvalid(vcpu)) { ret = decode_hsr(vcpu, fault_ipa, &mmio); if (ret) return ret; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 99e07c7dd74..2f12e405640 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -20,7 +20,6 @@ #include <linux/kvm_host.h> #include <linux/io.h> #include <trace/events/kvm.h> -#include <asm/idmap.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/kvm_arm.h> @@ -28,8 +27,6 @@ #include <asm/kvm_mmio.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> -#include <asm/mach/map.h> -#include <trace/events/kvm.h> #include "trace.h" @@ -37,19 +34,9 @@ extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; static DEFINE_MUTEX(kvm_hyp_pgd_mutex); -static void kvm_tlb_flush_vmid(struct kvm *kvm) +static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { - kvm_call_hyp(__kvm_tlb_flush_vmid, kvm); -} - -static void kvm_set_pte(pte_t *pte, pte_t new_pte) -{ - pte_val(*pte) = new_pte; - /* - * flush_pmd_entry just takes a void pointer and cleans the necessary - * cache entries, so we can reuse the function for ptes. - */ - flush_pmd_entry(pte); + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); } static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, @@ -98,33 +85,42 @@ static void free_ptes(pmd_t *pmd, unsigned long addr) } } +static void free_hyp_pgd_entry(unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + unsigned long hyp_addr = KERN_TO_HYP(addr); + + pgd = hyp_pgd + pgd_index(hyp_addr); + pud = pud_offset(pgd, hyp_addr); + + if (pud_none(*pud)) + return; + BUG_ON(pud_bad(*pud)); + + pmd = pmd_offset(pud, hyp_addr); + free_ptes(pmd, addr); + pmd_free(NULL, pmd); + pud_clear(pud); +} + /** * free_hyp_pmds - free a Hyp-mode level-2 tables and child level-3 tables * * Assumes this is a page table used strictly in Hyp-mode and therefore contains - * only mappings in the kernel memory area, which is above PAGE_OFFSET. + * either mappings in the kernel memory area (above PAGE_OFFSET), or + * device mappings in the vmalloc range (from VMALLOC_START to VMALLOC_END). */ void free_hyp_pmds(void) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; unsigned long addr; mutex_lock(&kvm_hyp_pgd_mutex); - for (addr = PAGE_OFFSET; addr != 0; addr += PGDIR_SIZE) { - pgd = hyp_pgd + pgd_index(addr); - pud = pud_offset(pgd, addr); - - if (pud_none(*pud)) - continue; - BUG_ON(pud_bad(*pud)); - - pmd = pmd_offset(pud, addr); - free_ptes(pmd, addr); - pmd_free(NULL, pmd); - pud_clear(pud); - } + for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE) + free_hyp_pgd_entry(addr); + for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE) + free_hyp_pgd_entry(addr); mutex_unlock(&kvm_hyp_pgd_mutex); } @@ -136,7 +132,9 @@ static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start, struct page *page; for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) { - pte = pte_offset_kernel(pmd, addr); + unsigned long hyp_addr = KERN_TO_HYP(addr); + + pte = pte_offset_kernel(pmd, hyp_addr); BUG_ON(!virt_addr_valid(addr)); page = virt_to_page(addr); kvm_set_pte(pte, mk_pte(page, PAGE_HYP)); @@ -151,7 +149,9 @@ static void create_hyp_io_pte_mappings(pmd_t *pmd, unsigned long start, unsigned long addr; for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) { - pte = pte_offset_kernel(pmd, addr); + unsigned long hyp_addr = KERN_TO_HYP(addr); + + pte = pte_offset_kernel(pmd, hyp_addr); BUG_ON(pfn_valid(*pfn_base)); kvm_set_pte(pte, pfn_pte(*pfn_base, PAGE_HYP_DEVICE)); (*pfn_base)++; @@ -166,12 +166,13 @@ static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start, unsigned long addr, next; for (addr = start; addr < end; addr = next) { - pmd = pmd_offset(pud, addr); + unsigned long hyp_addr = KERN_TO_HYP(addr); + pmd = pmd_offset(pud, hyp_addr); BUG_ON(pmd_sect(*pmd)); if (pmd_none(*pmd)) { - pte = pte_alloc_one_kernel(NULL, addr); + pte = pte_alloc_one_kernel(NULL, hyp_addr); if (!pte) { kvm_err("Cannot allocate Hyp pte\n"); return -ENOMEM; @@ -206,17 +207,23 @@ static int __create_hyp_mappings(void *from, void *to, unsigned long *pfn_base) unsigned long addr, next; int err = 0; - BUG_ON(start > end); - if (start < PAGE_OFFSET) + if (start >= end) + return -EINVAL; + /* Check for a valid kernel memory mapping */ + if (!pfn_base && (!virt_addr_valid(from) || !virt_addr_valid(to - 1))) + return -EINVAL; + /* Check for a valid kernel IO mapping */ + if (pfn_base && (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1))) return -EINVAL; mutex_lock(&kvm_hyp_pgd_mutex); for (addr = start; addr < end; addr = next) { - pgd = hyp_pgd + pgd_index(addr); - pud = pud_offset(pgd, addr); + unsigned long hyp_addr = KERN_TO_HYP(addr); + pgd = hyp_pgd + pgd_index(hyp_addr); + pud = pud_offset(pgd, hyp_addr); if (pud_none_or_clear_bad(pud)) { - pmd = pmd_alloc_one(NULL, addr); + pmd = pmd_alloc_one(NULL, hyp_addr); if (!pmd) { kvm_err("Cannot allocate Hyp pmd\n"); err = -ENOMEM; @@ -236,12 +243,13 @@ out: } /** - * create_hyp_mappings - map a kernel virtual address range in Hyp mode + * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range * @to: The virtual kernel end address of the range (exclusive) * - * The same virtual address as the kernel virtual address is also used in - * Hyp-mode mapping to the same underlying physical pages. + * The same virtual address as the kernel virtual address is also used + * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying + * physical pages. * * Note: Wrapping around zero in the "to" address is not supported. */ @@ -251,10 +259,13 @@ int create_hyp_mappings(void *from, void *to) } /** - * create_hyp_io_mappings - map a physical IO range in Hyp mode - * @from: The virtual HYP start address of the range - * @to: The virtual HYP end address of the range (exclusive) + * create_hyp_io_mappings - duplicate a kernel IO mapping into Hyp mode + * @from: The kernel start VA of the range + * @to: The kernel end VA of the range (exclusive) * @addr: The physical start address which gets mapped + * + * The resulting HYP VA is the same as the kernel VA, modulo + * HYP_PAGE_OFFSET. */ int create_hyp_io_mappings(void *from, void *to, phys_addr_t addr) { @@ -290,7 +301,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) VM_BUG_ON((unsigned long)pgd & (S2_PGD_SIZE - 1)); memset(pgd, 0, PTRS_PER_S2_PGD * sizeof(pgd_t)); - clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t)); + kvm_clean_pgd(pgd); kvm->arch.pgd = pgd; return 0; @@ -422,22 +433,22 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, return 0; /* ignore calls from kvm_set_spte_hva */ pmd = mmu_memory_cache_alloc(cache); pud_populate(NULL, pud, pmd); - pmd += pmd_index(addr); get_page(virt_to_page(pud)); - } else - pmd = pmd_offset(pud, addr); + } + + pmd = pmd_offset(pud, addr); /* Create 2nd stage page table mapping - Level 2 */ if (pmd_none(*pmd)) { if (!cache) return 0; /* ignore calls from kvm_set_spte_hva */ pte = mmu_memory_cache_alloc(cache); - clean_pte_table(pte); + kvm_clean_pte(pte); pmd_populate_kernel(NULL, pmd, pte); - pte += pte_index(addr); get_page(virt_to_page(pmd)); - } else - pte = pte_offset_kernel(pmd, addr); + } + + pte = pte_offset_kernel(pmd, addr); if (iomap && pte_present(*pte)) return -EFAULT; @@ -446,7 +457,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, old_pte = *pte; kvm_set_pte(pte, *new_pte); if (pte_present(old_pte)) - kvm_tlb_flush_vmid(kvm); + kvm_tlb_flush_vmid_ipa(kvm, addr); else get_page(virt_to_page(pte)); @@ -473,7 +484,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, pfn = __phys_to_pfn(pa); for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) { - pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE | L_PTE_S2_RDWR); + pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE); + kvm_set_s2pte_writable(&pte); ret = mmu_topup_memory_cache(&cache, 2, 2); if (ret) @@ -492,29 +504,6 @@ out: return ret; } -static void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn) -{ - /* - * If we are going to insert an instruction page and the icache is - * either VIPT or PIPT, there is a potential problem where the host - * (or another VM) may have used the same page as this guest, and we - * read incorrect data from the icache. If we're using a PIPT cache, - * we can invalidate just that page, but if we are using a VIPT cache - * we need to invalidate the entire icache - damn shame - as written - * in the ARM ARM (DDI 0406C.b - Page B3-1393). - * - * VIVT caches are tagged using both the ASID and the VMID and doesn't - * need any kind of flushing (DDI 0406C.b - Page B3-1392). - */ - if (icache_is_pipt()) { - unsigned long hva = gfn_to_hva(kvm, gfn); - __cpuc_coherent_user_range(hva, hva + PAGE_SIZE); - } else if (!icache_is_vivt_asid_tagged()) { - /* any kind of VIPT cache */ - __flush_icache_all(); - } -} - static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, gfn_t gfn, struct kvm_memory_slot *memslot, unsigned long fault_status) @@ -526,7 +515,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long mmu_seq; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; - write_fault = kvm_is_write_fault(vcpu->arch.hsr); + write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu)); if (fault_status == FSC_PERM && !write_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; @@ -560,7 +549,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; if (writable) { - pte_val(new_pte) |= L_PTE_S2_RDWR; + kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn); } stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte, false); @@ -585,7 +574,6 @@ out_unlock: */ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) { - unsigned long hsr_ec; unsigned long fault_status; phys_addr_t fault_ipa; struct kvm_memory_slot *memslot; @@ -593,18 +581,17 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) gfn_t gfn; int ret, idx; - hsr_ec = vcpu->arch.hsr >> HSR_EC_SHIFT; - is_iabt = (hsr_ec == HSR_EC_IABT); - fault_ipa = ((phys_addr_t)vcpu->arch.hpfar & HPFAR_MASK) << 8; + is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); - trace_kvm_guest_fault(*vcpu_pc(vcpu), vcpu->arch.hsr, - vcpu->arch.hxfar, fault_ipa); + trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu), + kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ - fault_status = (vcpu->arch.hsr & HSR_FSC_TYPE); + fault_status = kvm_vcpu_trap_get_fault(vcpu); if (fault_status != FSC_FAULT && fault_status != FSC_PERM) { - kvm_err("Unsupported fault status: EC=%#lx DFCS=%#lx\n", - hsr_ec, fault_status); + kvm_err("Unsupported fault status: EC=%#x DFCS=%#lx\n", + kvm_vcpu_trap_get_class(vcpu), fault_status); return -EFAULT; } @@ -614,7 +601,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) if (!kvm_is_visible_gfn(vcpu->kvm, gfn)) { if (is_iabt) { /* Prefetch Abort on I/O address */ - kvm_inject_pabt(vcpu, vcpu->arch.hxfar); + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); ret = 1; goto out_unlock; } @@ -626,8 +613,13 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) goto out_unlock; } - /* Adjust page offset */ - fault_ipa |= vcpu->arch.hxfar & ~PAGE_MASK; + /* + * The IPA is reported as [MAX:12], so we need to + * complement it with the bottom 12 bits from the + * faulting VA. This is always 12 bits, irrespective + * of the page size. + */ + fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1); ret = io_mem_abort(vcpu, run, fault_ipa); goto out_unlock; } @@ -682,7 +674,7 @@ static void handle_hva_to_gpa(struct kvm *kvm, static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) { unmap_stage2_range(kvm, gpa, PAGE_SIZE); - kvm_tlb_flush_vmid(kvm); + kvm_tlb_flush_vmid_ipa(kvm, gpa); } int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) @@ -776,7 +768,7 @@ void kvm_clear_hyp_idmap(void) pmd = pmd_offset(pud, addr); pud_clear(pud); - clean_pmd_entry(pmd); + kvm_clean_pmd_entry(pmd); pmd_free(NULL, (pmd_t *)((unsigned long)pmd & PAGE_MASK)); } while (pgd++, addr = next, addr < end); } diff --git a/arch/arm/kvm/vgic.c b/arch/arm/kvm/vgic.c index c9a17316e9f..17c5ac7d10e 100644 --- a/arch/arm/kvm/vgic.c +++ b/arch/arm/kvm/vgic.c @@ -883,8 +883,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) lr, irq, vgic_cpu->vgic_lr[lr]); BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT; - - goto out; + return true; } /* Try to use another LR for this interrupt */ @@ -898,7 +897,6 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) vgic_cpu->vgic_irq_lr_map[irq] = lr; set_bit(lr, vgic_cpu->lr_used); -out: if (!vgic_irq_is_edge(vcpu, irq)) vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI; @@ -1018,21 +1016,6 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr); - /* - * We do not need to take the distributor lock here, since the only - * action we perform is clearing the irq_active_bit for an EOIed - * level interrupt. There is a potential race with - * the queuing of an interrupt in __kvm_vgic_flush_hwstate(), where we - * check if the interrupt is already active. Two possibilities: - * - * - The queuing is occurring on the same vcpu: cannot happen, - * as we're already in the context of this vcpu, and - * executing the handler - * - The interrupt has been migrated to another vcpu, and we - * ignore this interrupt for this run. Big deal. It is still - * pending though, and will get considered when this vcpu - * exits. - */ if (vgic_cpu->vgic_misr & GICH_MISR_EOI) { /* * Some level interrupts have been EOIed. Clear their @@ -1054,6 +1037,13 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) } else { vgic_cpu_irq_clear(vcpu, irq); } + + /* + * Despite being EOIed, the LR may not have + * been marked as empty. + */ + set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr); + vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT; } } @@ -1064,9 +1054,8 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) } /* - * Sync back the VGIC state after a guest run. We do not really touch - * the distributor here (the irq_pending_on_cpu bit is safe to set), - * so there is no need for taking its lock. + * Sync back the VGIC state after a guest run. The distributor lock is + * needed so we don't get preempted in the middle of the state processing. */ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { @@ -1112,10 +1101,14 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + if (!irqchip_in_kernel(vcpu->kvm)) return; + spin_lock(&dist->lock); __kvm_vgic_sync_hwstate(vcpu); + spin_unlock(&dist->lock); } int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) @@ -1484,7 +1477,7 @@ int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr) if (addr & ~KVM_PHYS_MASK) return -E2BIG; - if (addr & ~PAGE_MASK) + if (addr & (SZ_4K - 1)) return -EINVAL; mutex_lock(&kvm->lock); diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c index 6b93f6a1a3c..64dbfa57204 100644 --- a/arch/arm/lib/delay.c +++ b/arch/arm/lib/delay.c @@ -58,7 +58,7 @@ static void __timer_delay(unsigned long cycles) static void __timer_const_udelay(unsigned long xloops) { unsigned long long loops = xloops; - loops *= loops_per_jiffy; + loops *= arm_delay_ops.ticks_per_jiffy; __timer_delay(loops >> UDELAY_SHIFT); } @@ -73,11 +73,13 @@ void __init register_current_timer_delay(const struct delay_timer *timer) pr_info("Switching to timer-based delay loop\n"); delay_timer = timer; lpj_fine = timer->freq / HZ; - loops_per_jiffy = lpj_fine; + + /* cpufreq may scale loops_per_jiffy, so keep a private copy */ + arm_delay_ops.ticks_per_jiffy = lpj_fine; arm_delay_ops.delay = __timer_delay; arm_delay_ops.const_udelay = __timer_const_udelay; arm_delay_ops.udelay = __timer_udelay; - arm_delay_ops.const_clock = true; + delay_calibrated = true; } else { pr_info("Ignoring duplicate/late registration of read_current_timer delay\n"); diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c index e698f26cc0c..52e4bb5cf12 100644 --- a/arch/arm/mach-cns3xxx/core.c +++ b/arch/arm/mach-cns3xxx/core.c @@ -22,19 +22,9 @@ static struct map_desc cns3xxx_io_desc[] __initdata = { { - .virtual = CNS3XXX_TC11MP_TWD_BASE_VIRT, - .pfn = __phys_to_pfn(CNS3XXX_TC11MP_TWD_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT, - .pfn = __phys_to_pfn(CNS3XXX_TC11MP_GIC_CPU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT, - .pfn = __phys_to_pfn(CNS3XXX_TC11MP_GIC_DIST_BASE), - .length = SZ_4K, + .virtual = CNS3XXX_TC11MP_SCU_BASE_VIRT, + .pfn = __phys_to_pfn(CNS3XXX_TC11MP_SCU_BASE), + .length = SZ_8K, .type = MT_DEVICE, }, { .virtual = CNS3XXX_TIMER1_2_3_BASE_VIRT, diff --git a/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h b/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h index 191c8e57f28..b1021aafa48 100644 --- a/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h +++ b/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h @@ -94,10 +94,10 @@ #define RTC_INTR_STS_OFFSET 0x34 #define CNS3XXX_MISC_BASE 0x76000000 /* Misc Control */ -#define CNS3XXX_MISC_BASE_VIRT 0xFFF07000 /* Misc Control */ +#define CNS3XXX_MISC_BASE_VIRT 0xFB000000 /* Misc Control */ #define CNS3XXX_PM_BASE 0x77000000 /* Power Management Control */ -#define CNS3XXX_PM_BASE_VIRT 0xFFF08000 +#define CNS3XXX_PM_BASE_VIRT 0xFB001000 #define PM_CLK_GATE_OFFSET 0x00 #define PM_SOFT_RST_OFFSET 0x04 @@ -109,7 +109,7 @@ #define PM_PLL_HM_PD_OFFSET 0x1C #define CNS3XXX_UART0_BASE 0x78000000 /* UART 0 */ -#define CNS3XXX_UART0_BASE_VIRT 0xFFF09000 +#define CNS3XXX_UART0_BASE_VIRT 0xFB002000 #define CNS3XXX_UART1_BASE 0x78400000 /* UART 1 */ #define CNS3XXX_UART1_BASE_VIRT 0xFFF0A000 @@ -130,7 +130,7 @@ #define CNS3XXX_I2S_BASE_VIRT 0xFFF10000 #define CNS3XXX_TIMER1_2_3_BASE 0x7C800000 /* Timer */ -#define CNS3XXX_TIMER1_2_3_BASE_VIRT 0xFFF10800 +#define CNS3XXX_TIMER1_2_3_BASE_VIRT 0xFB003000 #define TIMER1_COUNTER_OFFSET 0x00 #define TIMER1_AUTO_RELOAD_OFFSET 0x04 @@ -227,16 +227,16 @@ * Testchip peripheral and fpga gic regions */ #define CNS3XXX_TC11MP_SCU_BASE 0x90000000 /* IRQ, Test chip */ -#define CNS3XXX_TC11MP_SCU_BASE_VIRT 0xFF000000 +#define CNS3XXX_TC11MP_SCU_BASE_VIRT 0xFB004000 #define CNS3XXX_TC11MP_GIC_CPU_BASE 0x90000100 /* Test chip interrupt controller CPU interface */ -#define CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT 0xFF000100 +#define CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x100) #define CNS3XXX_TC11MP_TWD_BASE 0x90000600 -#define CNS3XXX_TC11MP_TWD_BASE_VIRT 0xFF000600 +#define CNS3XXX_TC11MP_TWD_BASE_VIRT (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x600) #define CNS3XXX_TC11MP_GIC_DIST_BASE 0x90001000 /* Test chip interrupt controller distributor */ -#define CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT 0xFF001000 +#define CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x1000) #define CNS3XXX_TC11MP_L220_BASE 0x92002000 /* L220 registers */ #define CNS3XXX_TC11MP_L220_BASE_VIRT 0xFF002000 diff --git a/arch/arm/mach-ep93xx/include/mach/uncompress.h b/arch/arm/mach-ep93xx/include/mach/uncompress.h index d2afb4dd82a..b5cc77d2380 100644 --- a/arch/arm/mach-ep93xx/include/mach/uncompress.h +++ b/arch/arm/mach-ep93xx/include/mach/uncompress.h @@ -47,9 +47,13 @@ static void __raw_writel(unsigned int value, unsigned int ptr) static inline void putc(int c) { - /* Transmit fifo not full? */ - while (__raw_readb(PHYS_UART_FLAG) & UART_FLAG_TXFF) - ; + int i; + + for (i = 0; i < 10000; i++) { + /* Transmit fifo not full? */ + if (!(__raw_readb(PHYS_UART_FLAG) & UART_FLAG_TXFF)) + break; + } __raw_writeb(c, PHYS_UART_DATA); } diff --git a/arch/arm/mach-exynos/hotplug.c b/arch/arm/mach-exynos/hotplug.c index c3f825b2794..af90cfa2f82 100644 --- a/arch/arm/mach-exynos/hotplug.c +++ b/arch/arm/mach-exynos/hotplug.c @@ -28,7 +28,6 @@ static inline void cpu_enter_lowpower_a9(void) { unsigned int v; - flush_cache_all(); asm volatile( " mcr p15, 0, %1, c7, c5, 0\n" " mcr p15, 0, %1, c7, c10, 4\n" diff --git a/arch/arm/mach-highbank/hotplug.c b/arch/arm/mach-highbank/hotplug.c index f30c5284339..a019e4e86e5 100644 --- a/arch/arm/mach-highbank/hotplug.c +++ b/arch/arm/mach-highbank/hotplug.c @@ -14,7 +14,6 @@ * this program. If not, see <http://www.gnu.org/licenses/>. */ #include <linux/kernel.h> - #include <asm/cacheflush.h> #include "core.h" @@ -28,13 +27,11 @@ extern void secondary_startup(void); */ void __ref highbank_cpu_die(unsigned int cpu) { - flush_cache_all(); - highbank_set_cpu_jump(cpu, phys_to_virt(0)); - highbank_set_core_pwr(); - cpu_do_idle(); + flush_cache_louis(); + highbank_set_core_pwr(); - /* We should never return from idle */ - panic("highbank: cpu %d unexpectedly exit from shutdown\n", cpu); + while (1) + cpu_do_idle(); } diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c index e13a8fa5e62..2193c834f55 100644 --- a/arch/arm/mach-imx/clk-imx35.c +++ b/arch/arm/mach-imx/clk-imx35.c @@ -257,6 +257,7 @@ int __init mx35_clocks_init(void) clk_register_clkdev(clk[wdog_gate], NULL, "imx2-wdt.0"); clk_register_clkdev(clk[nfc_div], NULL, "imx25-nand.0"); clk_register_clkdev(clk[csi_gate], NULL, "mx3-camera.0"); + clk_register_clkdev(clk[admux_gate], "audmux", NULL); clk_prepare_enable(clk[spba_gate]); clk_prepare_enable(clk[gpio1_gate]); @@ -265,6 +266,7 @@ int __init mx35_clocks_init(void) clk_prepare_enable(clk[iim_gate]); clk_prepare_enable(clk[emi_gate]); clk_prepare_enable(clk[max_gate]); + clk_prepare_enable(clk[iomuxc_gate]); /* * SCC is needed to boot via mmc after a watchdog reset. The clock code diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 2f9ff93a4e6..d38e54f5b6d 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -115,7 +115,7 @@ static const char *gpu2d_core_sels[] = { "axi", "pll3_usb_otg", "pll2_pfd0_352m" static const char *gpu3d_core_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd2_396m", }; static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd9_720m", }; static const char *ipu_sels[] = { "mmdc_ch0_axi", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", }; -static const char *ldb_di_sels[] = { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_pfd1_540m", }; +static const char *ldb_di_sels[] = { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", }; static const char *ipu_di_pre_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd1_540m", }; static const char *ipu1_di0_sels[] = { "ipu1_di0_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", }; static const char *ipu1_di1_sels[] = { "ipu1_di1_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", }; @@ -443,7 +443,6 @@ int __init mx6q_clocks_init(void) clk_register_clkdev(clk[gpt_ipg], "ipg", "imx-gpt.0"); clk_register_clkdev(clk[gpt_ipg_per], "per", "imx-gpt.0"); - clk_register_clkdev(clk[twd], NULL, "smp_twd"); clk_register_clkdev(clk[cko1_sel], "cko1_sel", NULL); clk_register_clkdev(clk[ahb], "ahb", NULL); clk_register_clkdev(clk[cko1], "cko1", NULL); diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 5a800bfcec5..5bf4a97ab24 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -110,6 +110,8 @@ void tzic_handle_irq(struct pt_regs *); extern void imx_enable_cpu(int cpu, bool enable); extern void imx_set_cpu_jump(int cpu, void *jump_addr); +extern u32 imx_get_cpu_arg(int cpu); +extern void imx_set_cpu_arg(int cpu, u32 arg); extern void v7_cpu_resume(void); extern u32 *pl310_get_save_ptr(void); #ifdef CONFIG_SMP diff --git a/arch/arm/mach-imx/hotplug.c b/arch/arm/mach-imx/hotplug.c index 7bc5fe15dda..5e91112dcbe 100644 --- a/arch/arm/mach-imx/hotplug.c +++ b/arch/arm/mach-imx/hotplug.c @@ -11,7 +11,6 @@ */ #include <linux/errno.h> -#include <asm/cacheflush.h> #include <asm/cp15.h> #include "common.h" @@ -20,7 +19,6 @@ static inline void cpu_enter_lowpower(void) { unsigned int v; - flush_cache_all(); asm volatile( "mcr p15, 0, %1, c7, c5, 0\n" " mcr p15, 0, %1, c7, c10, 4\n" @@ -46,11 +44,23 @@ static inline void cpu_enter_lowpower(void) void imx_cpu_die(unsigned int cpu) { cpu_enter_lowpower(); + /* + * We use the cpu jumping argument register to sync with + * imx_cpu_kill() which is running on cpu0 and waiting for + * the register being cleared to kill the cpu. + */ + imx_set_cpu_arg(cpu, ~0); cpu_do_idle(); } int imx_cpu_kill(unsigned int cpu) { + unsigned long timeout = jiffies + msecs_to_jiffies(50); + + while (imx_get_cpu_arg(cpu) == 0) + if (time_after(jiffies, timeout)) + return 0; imx_enable_cpu(cpu, false); + imx_set_cpu_arg(cpu, 0); return 1; } diff --git a/arch/arm/mach-imx/src.c b/arch/arm/mach-imx/src.c index e15f1555c59..09a742f8c7a 100644 --- a/arch/arm/mach-imx/src.c +++ b/arch/arm/mach-imx/src.c @@ -43,6 +43,18 @@ void imx_set_cpu_jump(int cpu, void *jump_addr) src_base + SRC_GPR1 + cpu * 8); } +u32 imx_get_cpu_arg(int cpu) +{ + cpu = cpu_logical_map(cpu); + return readl_relaxed(src_base + SRC_GPR1 + cpu * 8 + 4); +} + +void imx_set_cpu_arg(int cpu, u32 arg) +{ + cpu = cpu_logical_map(cpu); + writel_relaxed(arg, src_base + SRC_GPR1 + cpu * 8 + 4); +} + void imx_src_prepare_restart(void) { u32 val; diff --git a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c index f655b2637b0..e5f70415905 100644 --- a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c +++ b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c @@ -20,10 +20,15 @@ static struct mv643xx_eth_platform_data iomega_ix2_200_ge00_data = { .duplex = DUPLEX_FULL, }; +static struct mv643xx_eth_platform_data iomega_ix2_200_ge01_data = { + .phy_addr = MV643XX_ETH_PHY_ADDR(11), +}; + void __init iomega_ix2_200_init(void) { /* * Basic setup. Needs to be called early. */ - kirkwood_ge01_init(&iomega_ix2_200_ge00_data); + kirkwood_ge00_init(&iomega_ix2_200_ge00_data); + kirkwood_ge01_init(&iomega_ix2_200_ge01_data); } diff --git a/arch/arm/mach-kirkwood/guruplug-setup.c b/arch/arm/mach-kirkwood/guruplug-setup.c index 1c6e736cbbf..08dd739aa70 100644 --- a/arch/arm/mach-kirkwood/guruplug-setup.c +++ b/arch/arm/mach-kirkwood/guruplug-setup.c @@ -53,6 +53,8 @@ static struct mv_sata_platform_data guruplug_sata_data = { static struct mvsdio_platform_data guruplug_mvsdio_data = { /* unfortunately the CD signal has not been connected */ + .gpio_card_detect = -1, + .gpio_write_protect = -1, }; static struct gpio_led guruplug_led_pins[] = { diff --git a/arch/arm/mach-kirkwood/openrd-setup.c b/arch/arm/mach-kirkwood/openrd-setup.c index 8ddd69fdc93..6a6eb548307 100644 --- a/arch/arm/mach-kirkwood/openrd-setup.c +++ b/arch/arm/mach-kirkwood/openrd-setup.c @@ -55,6 +55,7 @@ static struct mv_sata_platform_data openrd_sata_data = { static struct mvsdio_platform_data openrd_mvsdio_data = { .gpio_card_detect = 29, /* MPP29 used as SD card detect */ + .gpio_write_protect = -1, }; static unsigned int openrd_mpp_config[] __initdata = { diff --git a/arch/arm/mach-kirkwood/rd88f6281-setup.c b/arch/arm/mach-kirkwood/rd88f6281-setup.c index c7d93b48926..d24223166e0 100644 --- a/arch/arm/mach-kirkwood/rd88f6281-setup.c +++ b/arch/arm/mach-kirkwood/rd88f6281-setup.c @@ -69,6 +69,7 @@ static struct mv_sata_platform_data rd88f6281_sata_data = { static struct mvsdio_platform_data rd88f6281_mvsdio_data = { .gpio_card_detect = 28, + .gpio_write_protect = -1, }; static unsigned int rd88f6281_mpp_config[] __initdata = { diff --git a/arch/arm/mach-msm/hotplug.c b/arch/arm/mach-msm/hotplug.c index 750446feb44..326a87261f9 100644 --- a/arch/arm/mach-msm/hotplug.c +++ b/arch/arm/mach-msm/hotplug.c @@ -10,16 +10,12 @@ #include <linux/errno.h> #include <linux/smp.h> -#include <asm/cacheflush.h> #include <asm/smp_plat.h> #include "common.h" static inline void cpu_enter_lowpower(void) { - /* Just flush the cache. Changing the coherency is not yet - * available on msm. */ - flush_cache_all(); } static inline void cpu_leave_lowpower(void) diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c index 2969027f02f..f9fd77e8f1f 100644 --- a/arch/arm/mach-msm/timer.c +++ b/arch/arm/mach-msm/timer.c @@ -62,7 +62,10 @@ static int msm_timer_set_next_event(unsigned long cycles, { u32 ctrl = readl_relaxed(event_base + TIMER_ENABLE); - writel_relaxed(0, event_base + TIMER_CLEAR); + ctrl &= ~TIMER_ENABLE_EN; + writel_relaxed(ctrl, event_base + TIMER_ENABLE); + + writel_relaxed(ctrl, event_base + TIMER_CLEAR); writel_relaxed(cycles, event_base + TIMER_MATCH_VAL); writel_relaxed(ctrl | TIMER_ENABLE_EN, event_base + TIMER_ENABLE); return 0; diff --git a/arch/arm/mach-mvebu/irq-armada-370-xp.c b/arch/arm/mach-mvebu/irq-armada-370-xp.c index 274ff58271d..d5970f5a1e8 100644 --- a/arch/arm/mach-mvebu/irq-armada-370-xp.c +++ b/arch/arm/mach-mvebu/irq-armada-370-xp.c @@ -44,6 +44,8 @@ #define ARMADA_370_XP_MAX_PER_CPU_IRQS (28) +#define ARMADA_370_XP_TIMER0_PER_CPU_IRQ (5) + #define ACTIVE_DOORBELLS (8) static DEFINE_RAW_SPINLOCK(irq_controller_lock); @@ -59,36 +61,26 @@ static struct irq_domain *armada_370_xp_mpic_domain; */ static void armada_370_xp_irq_mask(struct irq_data *d) { -#ifdef CONFIG_SMP irq_hw_number_t hwirq = irqd_to_hwirq(d); - if (hwirq > ARMADA_370_XP_MAX_PER_CPU_IRQS) + if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) writel(hwirq, main_int_base + ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS); else writel(hwirq, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS); -#else - writel(irqd_to_hwirq(d), - per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS); -#endif } static void armada_370_xp_irq_unmask(struct irq_data *d) { -#ifdef CONFIG_SMP irq_hw_number_t hwirq = irqd_to_hwirq(d); - if (hwirq > ARMADA_370_XP_MAX_PER_CPU_IRQS) + if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) writel(hwirq, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); else writel(hwirq, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); -#else - writel(irqd_to_hwirq(d), - per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); -#endif } #ifdef CONFIG_SMP @@ -144,10 +136,14 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h, unsigned int virq, irq_hw_number_t hw) { armada_370_xp_irq_mask(irq_get_irq_data(virq)); - writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); + if (hw != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) + writel(hw, per_cpu_int_base + + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + else + writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); irq_set_status_flags(virq, IRQ_LEVEL); - if (hw < ARMADA_370_XP_MAX_PER_CPU_IRQS) { + if (hw == ARMADA_370_XP_TIMER0_PER_CPU_IRQ) { irq_set_percpu_devid(virq); irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip, handle_percpu_devid_irq); diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c index 3218f1f2c0e..e7b781d3788 100644 --- a/arch/arm/mach-mxs/mach-mxs.c +++ b/arch/arm/mach-mxs/mach-mxs.c @@ -41,8 +41,6 @@ static struct fb_videomode mx23evk_video_modes[] = { .lower_margin = 4, .hsync_len = 1, .vsync_len = 1, - .sync = FB_SYNC_DATA_ENABLE_HIGH_ACT | - FB_SYNC_DOTCLK_FAILING_ACT, }, }; @@ -59,8 +57,6 @@ static struct fb_videomode mx28evk_video_modes[] = { .lower_margin = 10, .hsync_len = 10, .vsync_len = 10, - .sync = FB_SYNC_DATA_ENABLE_HIGH_ACT | - FB_SYNC_DOTCLK_FAILING_ACT, }, }; @@ -77,7 +73,6 @@ static struct fb_videomode m28evk_video_modes[] = { .lower_margin = 45, .hsync_len = 1, .vsync_len = 1, - .sync = FB_SYNC_DATA_ENABLE_HIGH_ACT, }, }; @@ -94,9 +89,7 @@ static struct fb_videomode apx4devkit_video_modes[] = { .lower_margin = 13, .hsync_len = 48, .vsync_len = 3, - .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT | - FB_SYNC_DATA_ENABLE_HIGH_ACT | - FB_SYNC_DOTCLK_FAILING_ACT, + .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, }, }; @@ -113,9 +106,7 @@ static struct fb_videomode apf28dev_video_modes[] = { .lower_margin = 0x15, .hsync_len = 64, .vsync_len = 4, - .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT | - FB_SYNC_DATA_ENABLE_HIGH_ACT | - FB_SYNC_DOTCLK_FAILING_ACT, + .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, }, }; @@ -132,7 +123,6 @@ static struct fb_videomode cfa10049_video_modes[] = { .lower_margin = 2, .hsync_len = 15, .vsync_len = 15, - .sync = FB_SYNC_DATA_ENABLE_HIGH_ACT }, }; @@ -259,6 +249,8 @@ static void __init imx23_evk_init(void) mxsfb_pdata.mode_count = ARRAY_SIZE(mx23evk_video_modes); mxsfb_pdata.default_bpp = 32; mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT; + mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT | + MXSFB_SYNC_DOTCLK_FAILING_ACT; } static inline void enable_clk_enet_out(void) @@ -278,6 +270,8 @@ static void __init imx28_evk_init(void) mxsfb_pdata.mode_count = ARRAY_SIZE(mx28evk_video_modes); mxsfb_pdata.default_bpp = 32; mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT; + mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT | + MXSFB_SYNC_DOTCLK_FAILING_ACT; mxs_saif_clkmux_select(MXS_DIGCTL_SAIF_CLKMUX_EXTMSTR0); } @@ -297,6 +291,7 @@ static void __init m28evk_init(void) mxsfb_pdata.mode_count = ARRAY_SIZE(m28evk_video_modes); mxsfb_pdata.default_bpp = 16; mxsfb_pdata.ld_intf_width = STMLCDIF_18BIT; + mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT; } static void __init sc_sps1_init(void) @@ -322,6 +317,8 @@ static void __init apx4devkit_init(void) mxsfb_pdata.mode_count = ARRAY_SIZE(apx4devkit_video_modes); mxsfb_pdata.default_bpp = 32; mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT; + mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT | + MXSFB_SYNC_DOTCLK_FAILING_ACT; } #define ENET0_MDC__GPIO_4_0 MXS_GPIO_NR(4, 0) @@ -407,6 +404,7 @@ static void __init cfa10049_init(void) mxsfb_pdata.mode_count = ARRAY_SIZE(cfa10049_video_modes); mxsfb_pdata.default_bpp = 32; mxsfb_pdata.ld_intf_width = STMLCDIF_18BIT; + mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT; } static void __init cfa10037_init(void) @@ -423,6 +421,8 @@ static void __init apf28_init(void) mxsfb_pdata.mode_count = ARRAY_SIZE(apf28dev_video_modes); mxsfb_pdata.default_bpp = 16; mxsfb_pdata.ld_intf_width = STMLCDIF_16BIT; + mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT | + MXSFB_SYNC_DOTCLK_FAILING_ACT; } static void __init mxs_machine_init(void) diff --git a/arch/arm/mach-omap1/clock_data.c b/arch/arm/mach-omap1/clock_data.c index cb7c6ae2e3f..6c4f766365a 100644 --- a/arch/arm/mach-omap1/clock_data.c +++ b/arch/arm/mach-omap1/clock_data.c @@ -543,15 +543,6 @@ static struct clk usb_dc_ck = { /* Direct from ULPD, no parent */ .rate = 48000000, .enable_reg = OMAP1_IO_ADDRESS(SOFT_REQ_REG), - .enable_bit = USB_REQ_EN_SHIFT, -}; - -static struct clk usb_dc_ck7xx = { - .name = "usb_dc_ck", - .ops = &clkops_generic, - /* Direct from ULPD, no parent */ - .rate = 48000000, - .enable_reg = OMAP1_IO_ADDRESS(SOFT_REQ_REG), .enable_bit = SOFT_USB_OTG_DPLL_REQ_SHIFT, }; @@ -727,8 +718,7 @@ static struct omap_clk omap_clks[] = { CLK(NULL, "usb_clko", &usb_clko, CK_16XX | CK_1510 | CK_310), CLK(NULL, "usb_hhc_ck", &usb_hhc_ck1510, CK_1510 | CK_310), CLK(NULL, "usb_hhc_ck", &usb_hhc_ck16xx, CK_16XX), - CLK(NULL, "usb_dc_ck", &usb_dc_ck, CK_16XX), - CLK(NULL, "usb_dc_ck", &usb_dc_ck7xx, CK_7XX), + CLK(NULL, "usb_dc_ck", &usb_dc_ck, CK_16XX | CK_7XX), CLK(NULL, "mclk", &mclk_1510, CK_1510 | CK_310), CLK(NULL, "mclk", &mclk_16xx, CK_16XX), CLK(NULL, "bclk", &bclk_1510, CK_1510 | CK_310), diff --git a/arch/arm/mach-omap2/cclock44xx_data.c b/arch/arm/mach-omap2/cclock44xx_data.c index 3d58f335f17..0c6834ae1fc 100644 --- a/arch/arm/mach-omap2/cclock44xx_data.c +++ b/arch/arm/mach-omap2/cclock44xx_data.c @@ -52,6 +52,13 @@ */ #define OMAP4_DPLL_ABE_DEFFREQ 98304000 +/* + * OMAP4 USB DPLL default frequency. In OMAP4430 TRM version V, section + * "3.6.3.9.5 DPLL_USB Preferred Settings" shows that the preferred + * locked frequency for the USB DPLL is 960MHz. + */ +#define OMAP4_DPLL_USB_DEFFREQ 960000000 + /* Root clocks */ DEFINE_CLK_FIXED_RATE(extalt_clkin_ck, CLK_IS_ROOT, 59000000, 0x0); @@ -1011,6 +1018,10 @@ DEFINE_CLK_OMAP_MUX(hsmmc2_fclk, "l3_init_clkdm", hsmmc1_fclk_sel, OMAP4430_CM_L3INIT_MMC2_CLKCTRL, OMAP4430_CLKSEL_MASK, hsmmc1_fclk_parents, func_dmic_abe_gfclk_ops); +DEFINE_CLK_GATE(ocp2scp_usb_phy_phy_48m, "func_48m_fclk", &func_48m_fclk, 0x0, + OMAP4430_CM_L3INIT_USBPHYOCP2SCP_CLKCTRL, + OMAP4430_OPTFCLKEN_PHY_48M_SHIFT, 0x0, NULL); + DEFINE_CLK_GATE(sha2md5_fck, "l3_div_ck", &l3_div_ck, 0x0, OMAP4430_CM_L4SEC_SHA2MD51_CLKCTRL, OMAP4430_MODULEMODE_SWCTRL_SHIFT, 0x0, NULL); @@ -1538,6 +1549,7 @@ static struct omap_clk omap44xx_clks[] = { CLK(NULL, "per_mcbsp4_gfclk", &per_mcbsp4_gfclk, CK_443X), CLK(NULL, "hsmmc1_fclk", &hsmmc1_fclk, CK_443X), CLK(NULL, "hsmmc2_fclk", &hsmmc2_fclk, CK_443X), + CLK(NULL, "ocp2scp_usb_phy_phy_48m", &ocp2scp_usb_phy_phy_48m, CK_443X), CLK(NULL, "sha2md5_fck", &sha2md5_fck, CK_443X), CLK(NULL, "slimbus1_fclk_1", &slimbus1_fclk_1, CK_443X), CLK(NULL, "slimbus1_fclk_0", &slimbus1_fclk_0, CK_443X), @@ -1705,5 +1717,13 @@ int __init omap4xxx_clk_init(void) if (rc) pr_err("%s: failed to configure ABE DPLL!\n", __func__); + /* + * Lock USB DPLL on OMAP4 devices so that the L3INIT power + * domain can transition to retention state when not in use. + */ + rc = clk_set_rate(&dpll_usb_ck, OMAP4_DPLL_USB_DEFFREQ); + if (rc) + pr_err("%s: failed to configure USB DPLL!\n", __func__); + return 0; } diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h index 40f4a03d728..d6ba13e1c54 100644 --- a/arch/arm/mach-omap2/common.h +++ b/arch/arm/mach-omap2/common.h @@ -293,5 +293,8 @@ extern void omap_reserve(void); struct omap_hwmod; extern int omap_dss_reset(struct omap_hwmod *); +/* SoC specific clock initializer */ +extern int (*omap_clk_init)(void); + #endif /* __ASSEMBLER__ */ #endif /* __ARCH_ARM_MACH_OMAP2PLUS_COMMON_H */ diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 8a68f1ec66b..577298ed5a4 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -300,7 +300,7 @@ void __init omap3xxx_check_revision(void) * If the processor type is Cortex-A8 and the revision is 0x0 * it means its Cortex r0p0 which is 3430 ES1.0. */ - cpuid = read_cpuid(CPUID_ID); + cpuid = read_cpuid_id(); if ((((cpuid >> 4) & 0xfff) == 0xc08) && ((cpuid & 0xf) == 0x0)) { omap_revision = OMAP3430_REV_ES1_0; cpu_rev = "1.0"; @@ -460,7 +460,7 @@ void __init omap4xxx_check_revision(void) * Use ARM register to detect the correct ES version */ if (!rev && (hawkeye != 0xb94e) && (hawkeye != 0xb975)) { - idcode = read_cpuid(CPUID_ID); + idcode = read_cpuid_id(); rev = (idcode & 0xf) - 1; } diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 2c3fdd65387..5c445ca1e27 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -55,6 +55,12 @@ #include "prm44xx.h" /* + * omap_clk_init: points to a function that does the SoC-specific + * clock initializations + */ +int (*omap_clk_init)(void); + +/* * The machine specific code may provide the extra mapping besides the * default mapping provided here. */ @@ -397,7 +403,7 @@ void __init omap2420_init_early(void) omap242x_clockdomains_init(); omap2420_hwmod_init(); omap_hwmod_init_postsetup(); - omap2420_clk_init(); + omap_clk_init = omap2420_clk_init; } void __init omap2420_init_late(void) @@ -427,7 +433,7 @@ void __init omap2430_init_early(void) omap243x_clockdomains_init(); omap2430_hwmod_init(); omap_hwmod_init_postsetup(); - omap2430_clk_init(); + omap_clk_init = omap2430_clk_init; } void __init omap2430_init_late(void) @@ -462,7 +468,7 @@ void __init omap3_init_early(void) omap3xxx_clockdomains_init(); omap3xxx_hwmod_init(); omap_hwmod_init_postsetup(); - omap3xxx_clk_init(); + omap_clk_init = omap3xxx_clk_init; } void __init omap3430_init_early(void) @@ -500,7 +506,7 @@ void __init ti81xx_init_early(void) omap3xxx_clockdomains_init(); omap3xxx_hwmod_init(); omap_hwmod_init_postsetup(); - omap3xxx_clk_init(); + omap_clk_init = omap3xxx_clk_init; } void __init omap3_init_late(void) @@ -568,7 +574,7 @@ void __init am33xx_init_early(void) am33xx_clockdomains_init(); am33xx_hwmod_init(); omap_hwmod_init_postsetup(); - am33xx_clk_init(); + omap_clk_init = am33xx_clk_init; } #endif @@ -593,7 +599,7 @@ void __init omap4430_init_early(void) omap44xx_clockdomains_init(); omap44xx_hwmod_init(); omap_hwmod_init_postsetup(); - omap4xxx_clk_init(); + omap_clk_init = omap4xxx_clk_init; } void __init omap4430_init_late(void) diff --git a/arch/arm/mach-omap2/omap-hotplug.c b/arch/arm/mach-omap2/omap-hotplug.c index e712d1725a8..ceb30a59bf2 100644 --- a/arch/arm/mach-omap2/omap-hotplug.c +++ b/arch/arm/mach-omap2/omap-hotplug.c @@ -35,9 +35,6 @@ void __ref omap4_cpu_die(unsigned int cpu) unsigned int boot_cpu = 0; void __iomem *base = omap_get_wakeupgen_base(); - flush_cache_all(); - dsb(); - /* * we're ready for shutdown now, so do it */ diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index d9727218dd0..7f5626d8fd3 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -209,7 +209,7 @@ static void __init omap4_smp_init_cpus(void) unsigned int i = 0, ncores = 1, cpu_id; /* Use ARM cpuid check here, as SoC detection will not work so early */ - cpu_id = read_cpuid(CPUID_ID) & CPU_MASK; + cpu_id = read_cpuid_id() & CPU_MASK; if (cpu_id == CPU_CORTEX_A9) { /* * Currently we can't call ioremap here because diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index c2c798c08c2..a202a478510 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1368,7 +1368,9 @@ static void _enable_sysc(struct omap_hwmod *oh) } if (sf & SYSC_HAS_MIDLEMODE) { - if (oh->flags & HWMOD_SWSUP_MSTANDBY) { + if (oh->flags & HWMOD_FORCE_MSTANDBY) { + idlemode = HWMOD_IDLEMODE_FORCE; + } else if (oh->flags & HWMOD_SWSUP_MSTANDBY) { idlemode = HWMOD_IDLEMODE_NO; } else { if (sf & SYSC_HAS_ENAWAKEUP) @@ -1440,7 +1442,8 @@ static void _idle_sysc(struct omap_hwmod *oh) } if (sf & SYSC_HAS_MIDLEMODE) { - if (oh->flags & HWMOD_SWSUP_MSTANDBY) { + if ((oh->flags & HWMOD_SWSUP_MSTANDBY) || + (oh->flags & HWMOD_FORCE_MSTANDBY)) { idlemode = HWMOD_IDLEMODE_FORCE; } else { if (sf & SYSC_HAS_ENAWAKEUP) diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index d43d9b608ed..d5dc935f606 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -427,8 +427,8 @@ struct omap_hwmod_omap4_prcm { * * HWMOD_SWSUP_SIDLE: omap_hwmod code should manually bring module in and out * of idle, rather than relying on module smart-idle - * HWMOD_SWSUP_MSTDBY: omap_hwmod code should manually bring module in and out - * of standby, rather than relying on module smart-standby + * HWMOD_SWSUP_MSTANDBY: omap_hwmod code should manually bring module in and + * out of standby, rather than relying on module smart-standby * HWMOD_INIT_NO_RESET: don't reset this module at boot - important for * SDRAM controller, etc. XXX probably belongs outside the main hwmod file * XXX Should be HWMOD_SETUP_NO_RESET @@ -459,6 +459,10 @@ struct omap_hwmod_omap4_prcm { * correctly, or this is being abused to deal with some PM latency * issues -- but we're currently suffering from a shortage of * folks who are able to track these issues down properly. + * HWMOD_FORCE_MSTANDBY: Always keep MIDLEMODE bits cleared so that device + * is kept in force-standby mode. Failing to do so causes PM problems + * with musb on OMAP3630 at least. Note that musb has a dedicated register + * to control MSTANDBY signal when MIDLEMODE is set to force-standby. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -471,6 +475,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_16BIT_REG (1 << 8) #define HWMOD_EXT_OPT_MAIN_CLK (1 << 9) #define HWMOD_BLOCK_WFI (1 << 10) +#define HWMOD_FORCE_MSTANDBY (1 << 11) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index ac7e03ec952..5112d04e7b7 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -1707,9 +1707,14 @@ static struct omap_hwmod omap3xxx_usbhsotg_hwmod = { * Erratum ID: i479 idle_req / idle_ack mechanism potentially * broken when autoidle is enabled * workaround is to disable the autoidle bit at module level. + * + * Enabling the device in any other MIDLEMODE setting but force-idle + * causes core_pwrdm not enter idle states at least on OMAP3630. + * Note that musb has OTG_FORCESTDBY register that controls MSTANDBY + * signal when MIDLEMODE is set to force-idle. */ .flags = HWMOD_NO_OCP_AUTOIDLE | HWMOD_SWSUP_SIDLE - | HWMOD_SWSUP_MSTANDBY, + | HWMOD_FORCE_MSTANDBY, }; /* usb_otg_hs */ diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c index 0e47d2e1687..9e0576569e0 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -2714,6 +2714,10 @@ static struct omap_ocp2scp_dev ocp2scp_dev_attr[] = { { } }; +static struct omap_hwmod_opt_clk ocp2scp_usb_phy_opt_clks[] = { + { .role = "48mhz", .clk = "ocp2scp_usb_phy_phy_48m" }, +}; + /* ocp2scp_usb_phy */ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { .name = "ocp2scp_usb_phy", @@ -2728,6 +2732,8 @@ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { }, }, .dev_attr = ocp2scp_dev_attr, + .opt_clks = ocp2scp_usb_phy_opt_clks, + .opt_clks_cnt = ARRAY_SIZE(ocp2scp_usb_phy_opt_clks), }; /* diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 2bdd4cf17a8..f62b509ed08 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -547,6 +547,8 @@ static inline void __init realtime_counter_init(void) clksrc_nr, clksrc_src) \ void __init omap##name##_gptimer_timer_init(void) \ { \ + if (omap_clk_init) \ + omap_clk_init(); \ omap_dmtimer_init(); \ omap2_gp_clockevent_init((clkev_nr), clkev_src, clkev_prop); \ omap2_gptimer_clocksource_init((clksrc_nr), clksrc_src); \ @@ -556,6 +558,8 @@ void __init omap##name##_gptimer_timer_init(void) \ clksrc_nr, clksrc_src) \ void __init omap##name##_sync32k_timer_init(void) \ { \ + if (omap_clk_init) \ + omap_clk_init(); \ omap_dmtimer_init(); \ omap2_gp_clockevent_init((clkev_nr), clkev_src, clkev_prop); \ /* Enable the use of clocksource="gp_timer" kernel parameter */ \ diff --git a/arch/arm/mach-prima2/hotplug.c b/arch/arm/mach-prima2/hotplug.c index f4b17cbabab..0ab2f8bae28 100644 --- a/arch/arm/mach-prima2/hotplug.c +++ b/arch/arm/mach-prima2/hotplug.c @@ -10,13 +10,10 @@ #include <linux/errno.h> #include <linux/smp.h> -#include <asm/cacheflush.h> #include <asm/smp_plat.h> static inline void platform_do_lowpower(unsigned int cpu) { - flush_cache_all(); - /* we put the platform to just WFI */ for (;;) { __asm__ __volatile__("dsb\n\t" "wfi\n\t" diff --git a/arch/arm/mach-realview/hotplug.c b/arch/arm/mach-realview/hotplug.c index 53818e5cd3a..ac22dd41b13 100644 --- a/arch/arm/mach-realview/hotplug.c +++ b/arch/arm/mach-realview/hotplug.c @@ -12,7 +12,6 @@ #include <linux/errno.h> #include <linux/smp.h> -#include <asm/cacheflush.h> #include <asm/cp15.h> #include <asm/smp_plat.h> @@ -20,7 +19,6 @@ static inline void cpu_enter_lowpower(void) { unsigned int v; - flush_cache_all(); asm volatile( " mcr p15, 0, %1, c7, c5, 0\n" " mcr p15, 0, %1, c7, c10, 4\n" diff --git a/arch/arm/mach-s3c24xx/include/mach/irqs.h b/arch/arm/mach-s3c24xx/include/mach/irqs.h index b7a9f4d469e..1e73f5fa865 100644 --- a/arch/arm/mach-s3c24xx/include/mach/irqs.h +++ b/arch/arm/mach-s3c24xx/include/mach/irqs.h @@ -188,10 +188,8 @@ #if defined(CONFIG_CPU_S3C2416) #define NR_IRQS (IRQ_S3C2416_I2S1 + 1) -#elif defined(CONFIG_CPU_S3C2443) -#define NR_IRQS (IRQ_S3C2443_AC97+1) #else -#define NR_IRQS (IRQ_S3C2440_AC97+1) +#define NR_IRQS (IRQ_S3C2443_AC97 + 1) #endif /* compatibility define. */ diff --git a/arch/arm/mach-s3c24xx/irq.c b/arch/arm/mach-s3c24xx/irq.c index cb9f5e011e7..d8ba9bee4c7 100644 --- a/arch/arm/mach-s3c24xx/irq.c +++ b/arch/arm/mach-s3c24xx/irq.c @@ -500,7 +500,7 @@ struct s3c_irq_intc *s3c24xx_init_intc(struct device_node *np, base = (void *)0xfd000000; intc->reg_mask = base + 0xa4; - intc->reg_pending = base + 0x08; + intc->reg_pending = base + 0xa8; irq_num = 20; irq_start = S3C2410_IRQ(32); irq_offset = 4; diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c index acb46a94ccd..2f1ef1bc805 100644 --- a/arch/arm/mach-shmobile/smp-sh73a0.c +++ b/arch/arm/mach-shmobile/smp-sh73a0.c @@ -119,14 +119,6 @@ static int sh73a0_cpu_kill(unsigned int cpu) static void sh73a0_cpu_die(unsigned int cpu) { - /* - * The ARM MPcore does not issue a cache coherency request for the L1 - * cache when powering off single CPUs. We must take care of this and - * further caches. - */ - dsb(); - flush_cache_all(); - /* Set power off mode. This takes the CPU out of the MP cluster */ scu_power_mode(scu_base_addr(), SCU_PM_POWEROFF); diff --git a/arch/arm/mach-spear13xx/hotplug.c b/arch/arm/mach-spear13xx/hotplug.c index a7d2dd11a4f..d97749c642c 100644 --- a/arch/arm/mach-spear13xx/hotplug.c +++ b/arch/arm/mach-spear13xx/hotplug.c @@ -13,7 +13,6 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/smp.h> -#include <asm/cacheflush.h> #include <asm/cp15.h> #include <asm/smp_plat.h> @@ -21,7 +20,6 @@ static inline void cpu_enter_lowpower(void) { unsigned int v; - flush_cache_all(); asm volatile( " mcr p15, 0, %1, c7, c5, 0\n" " dsb\n" diff --git a/arch/arm/mach-tegra/common.h b/arch/arm/mach-tegra/common.h index 32f8eb3fe34..5900cc44f78 100644 --- a/arch/arm/mach-tegra/common.h +++ b/arch/arm/mach-tegra/common.h @@ -2,4 +2,3 @@ extern struct smp_operations tegra_smp_ops; extern int tegra_cpu_kill(unsigned int cpu); extern void tegra_cpu_die(unsigned int cpu); -extern int tegra_cpu_disable(unsigned int cpu); diff --git a/arch/arm/mach-tegra/hotplug.c b/arch/arm/mach-tegra/hotplug.c index a599f6e36de..e8323bc9577 100644 --- a/arch/arm/mach-tegra/hotplug.c +++ b/arch/arm/mach-tegra/hotplug.c @@ -12,7 +12,6 @@ #include <linux/smp.h> #include <linux/clk/tegra.h> -#include <asm/cacheflush.h> #include <asm/smp_plat.h> #include "sleep.h" @@ -47,15 +46,6 @@ void __ref tegra_cpu_die(unsigned int cpu) BUG(); } -int tegra_cpu_disable(unsigned int cpu) -{ - /* - * we don't allow CPU 0 to be shutdown (it is still too special - * e.g. clock tick interrupts) - */ - return cpu == 0 ? -EPERM : 0; -} - #ifdef CONFIG_ARCH_TEGRA_2x_SOC extern void tegra20_hotplug_shutdown(void); void __init tegra20_hotplug_init(void) diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c index 2c6b3d55213..ec33ec86aad 100644 --- a/arch/arm/mach-tegra/platsmp.c +++ b/arch/arm/mach-tegra/platsmp.c @@ -192,6 +192,5 @@ struct smp_operations tegra_smp_ops __initdata = { #ifdef CONFIG_HOTPLUG_CPU .cpu_kill = tegra_cpu_kill, .cpu_die = tegra_cpu_die, - .cpu_disable = tegra_cpu_disable, #endif }; diff --git a/arch/arm/mach-ux500/board-mop500-sdi.c b/arch/arm/mach-ux500/board-mop500-sdi.c index 051b62c2710..7f2cb6c5e2c 100644 --- a/arch/arm/mach-ux500/board-mop500-sdi.c +++ b/arch/arm/mach-ux500/board-mop500-sdi.c @@ -81,7 +81,6 @@ static struct stedma40_chan_cfg mop500_sdi0_dma_cfg_tx = { #endif struct mmci_platform_data mop500_sdi0_data = { - .ios_handler = mop500_sdi0_ios_handler, .ocr_mask = MMC_VDD_29_30, .f_max = 50000000, .capabilities = MMC_CAP_4_BIT_DATA | diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index b03457881c4..87d2d7b38ce 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/platform_device.h> +#include <linux/clk.h> #include <linux/io.h> #include <linux/i2c.h> #include <linux/platform_data/i2c-nomadik.h> @@ -439,6 +440,15 @@ static void mop500_prox_deactivate(struct device *dev) regulator_put(prox_regulator); } +void mop500_snowball_ethernet_clock_enable(void) +{ + struct clk *clk; + + clk = clk_get_sys("fsmc", NULL); + if (!IS_ERR(clk)) + clk_prepare_enable(clk); +} + static struct cryp_platform_data u8500_cryp1_platform_data = { .mem_to_engine = { .dir = STEDMA40_MEM_TO_PERIPH, @@ -683,6 +693,8 @@ static void __init snowball_init_machine(void) mop500_audio_init(parent); mop500_uart_init(parent); + mop500_snowball_ethernet_clock_enable(); + /* This board has full regulator constraints */ regulator_has_full_constraints(); } diff --git a/arch/arm/mach-ux500/board-mop500.h b/arch/arm/mach-ux500/board-mop500.h index eaa605f5d90..d38951be70d 100644 --- a/arch/arm/mach-ux500/board-mop500.h +++ b/arch/arm/mach-ux500/board-mop500.h @@ -104,6 +104,7 @@ void __init mop500_pinmaps_init(void); void __init snowball_pinmaps_init(void); void __init hrefv60_pinmaps_init(void); void mop500_audio_init(struct device *parent); +void mop500_snowball_ethernet_clock_enable(void); int __init mop500_uib_init(void); void mop500_uib_i2c_add(int busnum, struct i2c_board_info *info, diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 19235cf7bbe..f1a58184437 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -312,9 +312,10 @@ static void __init u8500_init_machine(void) /* Pinmaps must be in place before devices register */ if (of_machine_is_compatible("st-ericsson,mop500")) mop500_pinmaps_init(); - else if (of_machine_is_compatible("calaosystems,snowball-a9500")) + else if (of_machine_is_compatible("calaosystems,snowball-a9500")) { snowball_pinmaps_init(); - else if (of_machine_is_compatible("st-ericsson,hrefv60+")) + mop500_snowball_ethernet_clock_enable(); + } else if (of_machine_is_compatible("st-ericsson,hrefv60+")) hrefv60_pinmaps_init(); else if (of_machine_is_compatible("st-ericsson,ccu9540")) {} /* TODO: Add pinmaps for ccu9540 board. */ diff --git a/arch/arm/mach-ux500/hotplug.c b/arch/arm/mach-ux500/hotplug.c index 2f6af259015..1c55a55dd89 100644 --- a/arch/arm/mach-ux500/hotplug.c +++ b/arch/arm/mach-ux500/hotplug.c @@ -12,7 +12,6 @@ #include <linux/errno.h> #include <linux/smp.h> -#include <asm/cacheflush.h> #include <asm/smp_plat.h> #include <mach/setup.h> @@ -24,8 +23,6 @@ */ void __ref ux500_cpu_die(unsigned int cpu) { - flush_cache_all(); - /* directly enter low power state, skipping secure registers */ for (;;) { __asm__ __volatile__("dsb\n\t" "wfi\n\t" diff --git a/arch/arm/mach-vexpress/hotplug.c b/arch/arm/mach-vexpress/hotplug.c index a141b98d84f..f0ce6b8f5e7 100644 --- a/arch/arm/mach-vexpress/hotplug.c +++ b/arch/arm/mach-vexpress/hotplug.c @@ -12,7 +12,6 @@ #include <linux/errno.h> #include <linux/smp.h> -#include <asm/cacheflush.h> #include <asm/smp_plat.h> #include <asm/cp15.h> @@ -20,7 +19,6 @@ static inline void cpu_enter_lowpower(void) { unsigned int v; - flush_cache_all(); asm volatile( "mcr p15, 0, %1, c7, c5, 0\n" " mcr p15, 0, %1, c7, c10, 4\n" diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 025d1732873..35955b54944 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -43,7 +43,7 @@ config CPU_ARM740T depends on !MMU select CPU_32v4T select CPU_ABRT_LV4T - select CPU_CACHE_V3 # although the core is v4t + select CPU_CACHE_V4 select CPU_CP15_MPU select CPU_PABRT_LEGACY help @@ -397,6 +397,13 @@ config CPU_V7 select CPU_PABRT_V7 select CPU_TLB_V7 if MMU +config CPU_THUMBONLY + bool + # There are no CPUs available with MMU that don't implement an ARM ISA: + depends on !MMU + help + Select this if your CPU doesn't support the 32 bit ARM instructions. + # Figure out what processor architecture version we should be using. # This defines the compiler instruction set which depends on the machine type. config CPU_32v3 @@ -469,9 +476,6 @@ config CPU_PABRT_V7 bool # The cache model -config CPU_CACHE_V3 - bool - config CPU_CACHE_V4 bool @@ -608,7 +612,7 @@ config ARCH_DMA_ADDR_T_64BIT bool config ARM_THUMB - bool "Support Thumb user binaries" + bool "Support Thumb user binaries" if !CPU_THUMBONLY depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON default y help diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 4e333fa2756..9e51be96f63 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY) += pabort-legacy.o obj-$(CONFIG_CPU_PABRT_V6) += pabort-v6.o obj-$(CONFIG_CPU_PABRT_V7) += pabort-v7.o -obj-$(CONFIG_CPU_CACHE_V3) += cache-v3.o obj-$(CONFIG_CPU_CACHE_V4) += cache-v4.o obj-$(CONFIG_CPU_CACHE_V4WT) += cache-v4wt.o obj-$(CONFIG_CPU_CACHE_V4WB) += cache-v4wb.o diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index db26e2e543f..6f4585b8907 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -961,12 +961,14 @@ static int __init alignment_init(void) return -ENOMEM; #endif +#ifdef CONFIG_CPU_CP15 if (cpu_is_v6_unaligned()) { cr_alignment &= ~CR_A; cr_no_alignment &= ~CR_A; set_cr(cr_alignment); ai_usermode = safe_usermode(ai_usermode, false); } +#endif hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN, "alignment exception"); diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index dd3d59122cc..48bc3c0a87c 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; + outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index c2f37390308..c465faca51b 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -299,7 +299,7 @@ static void l2x0_unlock(u32 cache_id) int lockregs; int i; - switch (cache_id) { + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: lockregs = 8; break; @@ -333,15 +333,14 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) if (cache_id_part_number_from_dt) cache_id = cache_id_part_number_from_dt; else - cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID) - & L2X0_CACHE_ID_PART_MASK; + cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); aux &= aux_mask; aux |= aux_val; /* Determine the number of ways */ - switch (cache_id) { + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: if (aux & (1 << 16)) ways = 16; @@ -725,7 +724,6 @@ static const struct l2x0_of_data pl310_data = { .flush_all = l2x0_flush_all, .inv_all = l2x0_inv_all, .disable = l2x0_disable, - .set_debug = pl310_set_debug, }, }; @@ -814,9 +812,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) data->save(); of_init = true; - l2x0_init(l2x0_base, aux_val, aux_mask); - memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache)); + l2x0_init(l2x0_base, aux_val, aux_mask); return 0; } diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S deleted file mode 100644 index 8a3fadece8d..00000000000 --- a/arch/arm/mm/cache-v3.S +++ /dev/null @@ -1,137 +0,0 @@ -/* - * linux/arch/arm/mm/cache-v3.S - * - * Copyright (C) 1997-2002 Russell king - * - * 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 <linux/init.h> -#include <asm/page.h> -#include "proc-macros.S" - -/* - * flush_icache_all() - * - * Unconditionally clean and invalidate the entire icache. - */ -ENTRY(v3_flush_icache_all) - mov pc, lr -ENDPROC(v3_flush_icache_all) - -/* - * flush_user_cache_all() - * - * Invalidate all cache entries in a particular address - * space. - * - * - mm - mm_struct describing address space - */ -ENTRY(v3_flush_user_cache_all) - /* FALLTHROUGH */ -/* - * flush_kern_cache_all() - * - * Clean and invalidate the entire cache. - */ -ENTRY(v3_flush_kern_cache_all) - /* FALLTHROUGH */ - -/* - * flush_user_cache_range(start, end, flags) - * - * Invalidate a range of cache entries in the specified - * address space. - * - * - start - start address (may not be aligned) - * - end - end address (exclusive, may not be aligned) - * - flags - vma_area_struct flags describing address space - */ -ENTRY(v3_flush_user_cache_range) - mov ip, #0 - mcreq p15, 0, ip, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * coherent_kern_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_kern_range) - /* FALLTHROUGH */ - -/* - * coherent_user_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_user_range) - mov r0, #0 - mov pc, lr - -/* - * flush_kern_dcache_area(void *page, size_t size) - * - * Ensure no D cache aliasing occurs, either with itself or - * the I cache - * - * - addr - kernel address - * - size - region size - */ -ENTRY(v3_flush_kern_dcache_area) - /* FALLTHROUGH */ - -/* - * dma_flush_range(start, end) - * - * Clean and invalidate the specified virtual address range. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_dma_flush_range) - mov r0, #0 - mcr p15, 0, r0, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * dma_unmap_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_unmap_area) - teq r2, #DMA_TO_DEVICE - bne v3_dma_flush_range - /* FALLTHROUGH */ - -/* - * dma_map_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_map_area) - mov pc, lr -ENDPROC(v3_dma_unmap_area) -ENDPROC(v3_dma_map_area) - - .globl v3_flush_kern_cache_louis - .equ v3_flush_kern_cache_louis, v3_flush_kern_cache_all - - __INITDATA - - @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S) - define_cache_functions v3 diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index 43e5d77be67..a7ba68f59f0 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all) ENTRY(v4_flush_user_cache_range) #ifdef CONFIG_CPU_CP15 mov ip, #0 - mcreq p15, 0, ip, c7, c7, 0 @ flush ID cache + mcr p15, 0, ip, c7, c7, 0 @ flush ID cache mov pc, lr #else /* FALLTHROUGH */ diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index a5a4b2bc42b..2ac37372ef5 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -48,7 +48,7 @@ static DEFINE_RAW_SPINLOCK(cpu_asid_lock); static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION); static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS); -static DEFINE_PER_CPU(atomic64_t, active_asids); +DEFINE_PER_CPU(atomic64_t, active_asids); static DEFINE_PER_CPU(u64, reserved_asids); static cpumask_t tlb_flush_pending; @@ -215,6 +215,7 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) { local_flush_bp_all(); local_flush_tlb_all(); + dummy_flush_tlb_a15_erratum(); } atomic64_set(&per_cpu(active_asids, cpu), asid); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e9db6b4bf65..ef3e0f3aac9 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -823,16 +823,17 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, if (PageHighMem(page)) { if (len + offset > PAGE_SIZE) len = PAGE_SIZE - offset; - vaddr = kmap_high_get(page); - if (vaddr) { - vaddr += offset; - op(vaddr, len, dir); - kunmap_high(page); - } else if (cache_is_vipt()) { - /* unmapped pages might still be cached */ + + if (cache_is_vipt_nonaliasing()) { vaddr = kmap_atomic(page); op(vaddr + offset, len, dir); kunmap_atomic(vaddr); + } else { + vaddr = kmap_high_get(page); + if (vaddr) { + op(vaddr + offset, len, dir); + kunmap_high(page); + } } } else { vaddr = page_address(page) + offset; diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 1c8f7f56417..0d473cce501 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -170,15 +170,18 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) if (!PageHighMem(page)) { __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); } else { - void *addr = kmap_high_get(page); - if (addr) { - __cpuc_flush_dcache_area(addr, PAGE_SIZE); - kunmap_high(page); - } else if (cache_is_vipt()) { - /* unmapped pages might still be cached */ + void *addr; + + if (cache_is_vipt_nonaliasing()) { addr = kmap_atomic(page); __cpuc_flush_dcache_area(addr, PAGE_SIZE); kunmap_atomic(addr); + } else { + addr = kmap_high_get(page); + if (addr) { + __cpuc_flush_dcache_area(addr, PAGE_SIZE); + kunmap_high(page); + } } } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e95a996ab78..e0d8565671a 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -34,6 +34,7 @@ #include <asm/mach/pci.h> #include "mm.h" +#include "tcm.h" /* * empty_zero_page is a special page that is used for @@ -112,6 +113,7 @@ static struct cachepolicy cache_policies[] __initdata = { } }; +#ifdef CONFIG_CPU_CP15 /* * These are useful for identifying cache coherency * problems by allowing the cache or the cache and @@ -210,6 +212,22 @@ void adjust_cr(unsigned long mask, unsigned long set) } #endif +#else /* ifdef CONFIG_CPU_CP15 */ + +static int __init early_cachepolicy(char *p) +{ + pr_warning("cachepolicy kernel parameter not supported without cp15\n"); +} +early_param("cachepolicy", early_cachepolicy); + +static int __init noalign_setup(char *__unused) +{ + pr_warning("noalign kernel parameter not supported without cp15\n"); +} +__setup("noalign", noalign_setup); + +#endif /* ifdef CONFIG_CPU_CP15 / else */ + #define PROT_PTE_DEVICE L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE @@ -598,39 +616,60 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, } while (pte++, addr += PAGE_SIZE, addr != end); } -static void __init alloc_init_section(pud_t *pud, unsigned long addr, - unsigned long end, phys_addr_t phys, - const struct mem_type *type) +static void __init map_init_section(pmd_t *pmd, unsigned long addr, + unsigned long end, phys_addr_t phys, + const struct mem_type *type) { - pmd_t *pmd = pmd_offset(pud, addr); - +#ifndef CONFIG_ARM_LPAE /* - * Try a section mapping - end, addr and phys must all be aligned - * to a section boundary. Note that PMDs refer to the individual - * L1 entries, whereas PGDs refer to a group of L1 entries making - * up one logical pointer to an L2 table. + * In classic MMU format, puds and pmds are folded in to + * the pgds. pmd_offset gives the PGD entry. PGDs refer to a + * group of L1 entries making up one logical pointer to + * an L2 table (2MB), where as PMDs refer to the individual + * L1 entries (1MB). Hence increment to get the correct + * offset for odd 1MB sections. + * (See arch/arm/include/asm/pgtable-2level.h) */ - if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) { - pmd_t *p = pmd; - -#ifndef CONFIG_ARM_LPAE - if (addr & SECTION_SIZE) - pmd++; + if (addr & SECTION_SIZE) + pmd++; #endif + do { + *pmd = __pmd(phys | type->prot_sect); + phys += SECTION_SIZE; + } while (pmd++, addr += SECTION_SIZE, addr != end); - do { - *pmd = __pmd(phys | type->prot_sect); - phys += SECTION_SIZE; - } while (pmd++, addr += SECTION_SIZE, addr != end); + flush_pmd_entry(pmd); +} - flush_pmd_entry(p); - } else { +static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, + unsigned long end, phys_addr_t phys, + const struct mem_type *type) +{ + pmd_t *pmd = pmd_offset(pud, addr); + unsigned long next; + + do { /* - * No need to loop; pte's aren't interested in the - * individual L1 entries. + * With LPAE, we must loop over to map + * all the pmds for the given range. */ - alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type); - } + next = pmd_addr_end(addr, end); + + /* + * Try a section mapping - addr, next and phys must all be + * aligned to a section boundary. + */ + if (type->prot_sect && + ((addr | next | phys) & ~SECTION_MASK) == 0) { + map_init_section(pmd, addr, next, phys, type); + } else { + alloc_init_pte(pmd, addr, next, + __phys_to_pfn(phys), type); + } + + phys += next - addr; + + } while (pmd++, addr = next, addr != end); } static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, @@ -641,7 +680,7 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, do { next = pud_addr_end(addr, end); - alloc_init_section(pud, addr, next, phys, type); + alloc_init_pmd(pud, addr, next, phys, type); phys += next - addr; } while (pud++, addr = next, addr != end); } @@ -1256,6 +1295,7 @@ void __init paging_init(struct machine_desc *mdesc) dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); + tcm_init(); top_pmd = pmd_off_k(0xffff0000); diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index dc5de5d53f2..fde2d2a794c 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -77,24 +77,27 @@ __arm740_setup: mcr p15, 0, r0, c6, c0 @ set area 0, default ldr r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM - ldr r1, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit mcr p15, 0, r0, c6, c1 @ set area 1, RAM ldr r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH - ldr r1, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) + cmp r3, #0 + moveq r0, #0 + beq 2f + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit - mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH +2: mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH mov r0, #0x06 mcr p15, 0, r0, c2, c0 @ Region 1&2 cacheable @@ -137,13 +140,14 @@ __arm740_proc_info: .long 0x41807400 .long 0xfffffff0 .long 0 + .long 0 b __arm740_setup .long cpu_arch_name .long cpu_elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT + .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT .long cpu_arm740_name .long arm740_processor_functions .long 0 .long 0 - .long v3_cache_fns @ cache model + .long v4_cache_fns @ cache model .size __arm740_proc_info, . - __arm740_proc_info diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 2c3b9421ab5..2556cf1c2da 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size .equ cpu_arm920_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm920_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index f1803f7e297..344c8a548cc 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size .equ cpu_arm926_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm926_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 82f9cdc751d..0b60dd3d742 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext) .globl cpu_mohawk_suspend_size .equ cpu_mohawk_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_mohawk_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 3aa0da11fd8..d92dfd08142 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext) .globl cpu_sa1100_suspend_size .equ cpu_sa1100_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_sa1100_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c index 3e6210b4d6d..054b491ff76 100644 --- a/arch/arm/mm/proc-syms.c +++ b/arch/arm/mm/proc-syms.c @@ -17,7 +17,9 @@ #ifndef MULTI_CPU EXPORT_SYMBOL(cpu_dcache_clean_area); +#ifdef CONFIG_MMU EXPORT_SYMBOL(cpu_set_pte_ext); +#endif #else EXPORT_SYMBOL(processor); #endif diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index bcaaa8de932..919405e20b8 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -80,12 +80,10 @@ ENTRY(cpu_v6_do_idle) mov pc, lr ENTRY(cpu_v6_dcache_clean_area) -#ifndef TLB_CAN_READ_FROM_L1_CACHE 1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry add r0, r0, #D_CACHE_LINE_SIZE subs r1, r1, #D_CACHE_LINE_SIZE bhi 1b -#endif mov pc, lr /* @@ -138,7 +136,7 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size .equ cpu_v6_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v6_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index 78f520bc0e9..9704097c450 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -110,7 +110,8 @@ ENTRY(cpu_v7_set_pte_ext) ARM( str r3, [r0, #2048]! ) THUMB( add r0, r0, #2048 ) THUMB( str r3, [r0] ) - mcr p15, 0, r0, c7, c10, 1 @ flush_pte + ALT_SMP(mov pc,lr) + ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif mov pc, lr ENDPROC(cpu_v7_set_pte_ext) diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 6ffd78c0f9a..363027e811d 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -73,7 +73,8 @@ ENTRY(cpu_v7_set_pte_ext) tst r3, #1 << (55 - 32) @ L_PTE_DIRTY orreq r2, #L_PTE_RDONLY 1: strd r2, r3, [r0] - mcr p15, 0, r0, c7, c10, 1 @ flush_pte + ALT_SMP(mov pc, lr) + ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif mov pc, lr ENDPROC(cpu_v7_set_pte_ext) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 3a3c015f8d5..2c73a7301ff 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -75,14 +75,14 @@ ENTRY(cpu_v7_do_idle) ENDPROC(cpu_v7_do_idle) ENTRY(cpu_v7_dcache_clean_area) -#ifndef TLB_CAN_READ_FROM_L1_CACHE + ALT_SMP(mov pc, lr) @ MP extensions imply L1 PTW + ALT_UP(W(nop)) dcache_line_size r2, r3 1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry add r0, r0, r2 subs r1, r1, r2 bhi 1b dsb -#endif mov pc, lr ENDPROC(cpu_v7_dcache_clean_area) @@ -402,6 +402,8 @@ __v7_ca9mp_proc_info: __v7_proc __v7_ca9mp_setup .size __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info +#endif /* CONFIG_ARM_LPAE */ + /* * Marvell PJ4B processor. */ @@ -411,7 +413,6 @@ __v7_pj4b_proc_info: .long 0xfffffff0 __v7_proc __v7_pj4b_setup .size __v7_pj4b_proc_info, . - __v7_pj4b_proc_info -#endif /* CONFIG_ARM_LPAE */ /* * ARM Ltd. Cortex A7 processor. @@ -420,7 +421,7 @@ __v7_pj4b_proc_info: __v7_ca7mp_proc_info: .long 0x410fc070 .long 0xff0ffff0 - __v7_proc __v7_ca7mp_setup, hwcaps = HWCAP_IDIV + __v7_proc __v7_ca7mp_setup .size __v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info /* @@ -430,10 +431,25 @@ __v7_ca7mp_proc_info: __v7_ca15mp_proc_info: .long 0x410fc0f0 .long 0xff0ffff0 - __v7_proc __v7_ca15mp_setup, hwcaps = HWCAP_IDIV + __v7_proc __v7_ca15mp_setup .size __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info /* + * Qualcomm Inc. Krait processors. + */ + .type __krait_proc_info, #object +__krait_proc_info: + .long 0x510f0400 @ Required ID value + .long 0xff0ffc00 @ Mask for ID + /* + * Some Krait processors don't indicate support for SDIV and UDIV + * instructions in the ARM instruction set, even though they actually + * do support them. + */ + __v7_proc __v7_setup, hwcaps = HWCAP_IDIV + .size __krait_proc_info, . - __krait_proc_info + + /* * Match any ARMv7 processor core. */ .type __v7_proc_info, #object diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index eb93d6487f3..e8efd83b6f2 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .globl cpu_xsc3_suspend_size .equ cpu_xsc3_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xsc3_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 25510361aa1..e766f889bfd 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext) .globl cpu_xscale_suspend_size .equ cpu_xscale_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xscale_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/kernel/tcm.h b/arch/arm/mm/tcm.h index 8015ad434a4..8015ad434a4 100644 --- a/arch/arm/kernel/tcm.h +++ b/arch/arm/mm/tcm.h |