diff options
Diffstat (limited to 'arch')
311 files changed, 5485 insertions, 1523 deletions
diff --git a/arch/alpha/Makefile b/arch/alpha/Makefile index 4759fe751aa..2cc3cc519c5 100644 --- a/arch/alpha/Makefile +++ b/arch/alpha/Makefile @@ -12,7 +12,7 @@ NM := $(NM) -B LDFLAGS_vmlinux := -static -N #-relax CHECKFLAGS += -D__alpha__ -m64 -cflags-y := -pipe -mno-fp-regs -ffixed-8 -msmall-data +cflags-y := -pipe -mno-fp-regs -ffixed-8 cflags-y += $(call cc-option, -fno-jump-tables) cpuflags-$(CONFIG_ALPHA_EV4) := -mcpu=ev4 diff --git a/arch/alpha/include/asm/floppy.h b/arch/alpha/include/asm/floppy.h index 46cefbd50e7..bae97eb19d2 100644 --- a/arch/alpha/include/asm/floppy.h +++ b/arch/alpha/include/asm/floppy.h @@ -26,7 +26,7 @@ #define fd_disable_irq() disable_irq(FLOPPY_IRQ) #define fd_cacheflush(addr,size) /* nothing */ #define fd_request_irq() request_irq(FLOPPY_IRQ, floppy_interrupt,\ - IRQF_DISABLED, "floppy", NULL) + 0, "floppy", NULL) #define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) #ifdef CONFIG_PCI diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 2872accd221..7b2be251c30 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -117,13 +117,6 @@ handle_irq(int irq) return; } - /* - * From here we must proceed with IPL_MAX. Note that we do not - * explicitly enable interrupts afterwards - some MILO PALcode - * (namely LX164 one) seems to have severe problems with RTI - * at IPL 0. - */ - local_irq_disable(); irq_enter(); generic_handle_irq_desc(irq, desc); irq_exit(); diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 772ddfdb71a..f433fc11877 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -45,6 +45,14 @@ do_entInt(unsigned long type, unsigned long vector, unsigned long la_ptr, struct pt_regs *regs) { struct pt_regs *old_regs; + + /* + * Disable interrupts during IRQ handling. + * Note that there is no matching local_irq_enable() due to + * severe problems with RTI at IPL0 and some MILO PALcode + * (namely LX164). + */ + local_irq_disable(); switch (type) { case 0: #ifdef CONFIG_SMP @@ -62,7 +70,6 @@ do_entInt(unsigned long type, unsigned long vector, { long cpu; - local_irq_disable(); smp_percpu_timer_interrupt(regs); cpu = smp_processor_id(); if (cpu != boot_cpuid) { @@ -222,7 +229,6 @@ process_mcheck_info(unsigned long vector, unsigned long la_ptr, struct irqaction timer_irqaction = { .handler = timer_interrupt, - .flags = IRQF_DISABLED, .name = "timer", }; diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 4d4c046f708..1383f8601a9 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -188,6 +188,10 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr) extern void free_reserved_mem(void *, void *); extern void pcibios_claim_one_bus(struct pci_bus *); +static struct resource irongate_io = { + .name = "Irongate PCI IO", + .flags = IORESOURCE_IO, +}; static struct resource irongate_mem = { .name = "Irongate PCI MEM", .flags = IORESOURCE_MEM, @@ -209,6 +213,7 @@ nautilus_init_pci(void) irongate = pci_get_bus_and_slot(0, 0); bus->self = irongate; + bus->resource[0] = &irongate_io; bus->resource[1] = &irongate_mem; pci_bus_size_bridges(bus); diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c index 5cf4a481b8c..a53cf03f49d 100644 --- a/arch/alpha/kernel/sys_titan.c +++ b/arch/alpha/kernel/sys_titan.c @@ -280,15 +280,15 @@ titan_late_init(void) * all reported to the kernel as machine checks, so the handler * is a nop so it can be called to count the individual events. */ - titan_request_irq(63+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(63+16, titan_intr_nop, 0, "CChip Error", NULL); - titan_request_irq(62+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(62+16, titan_intr_nop, 0, "PChip 0 H_Error", NULL); - titan_request_irq(61+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(61+16, titan_intr_nop, 0, "PChip 1 H_Error", NULL); - titan_request_irq(60+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(60+16, titan_intr_nop, 0, "PChip 0 C_Error", NULL); - titan_request_irq(59+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(59+16, titan_intr_nop, 0, "PChip 1 C_Error", NULL); /* @@ -348,9 +348,9 @@ privateer_init_pci(void) * Hook a couple of extra err interrupts that the * common titan code won't. */ - titan_request_irq(53+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(53+16, titan_intr_nop, 0, "NMI", NULL); - titan_request_irq(50+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(50+16, titan_intr_nop, 0, "Temperature Warning", NULL); /* diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h index 31f77aec082..45b8e0cea17 100644 --- a/arch/arc/include/asm/dma-mapping.h +++ b/arch/arc/include/asm/dma-mapping.h @@ -126,7 +126,7 @@ dma_map_sg(struct device *dev, struct scatterlist *sg, int i; for_each_sg(sg, s, nents, i) - sg->dma_address = dma_map_page(dev, sg_page(s), s->offset, + s->dma_address = dma_map_page(dev, sg_page(s), s->offset, s->length, dir); return nents; diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h index f4c8d36ebec..a2628285768 100644 --- a/arch/arc/include/asm/elf.h +++ b/arch/arc/include/asm/elf.h @@ -72,7 +72,4 @@ extern int elf_check_arch(const struct elf32_hdr *); */ #define ELF_PLATFORM (NULL) -#define SET_PERSONALITY(ex) \ - set_personality(PER_LINUX | (current->personality & (~PER_MASK))) - #endif diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index 23daa326fc9..eb2ae53187d 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -415,7 +415,7 @@ *-------------------------------------------------------------*/ .macro SAVE_ALL_EXCEPTION marker - st \marker, [sp, 8] + st \marker, [sp, 8] /* orig_r8 */ st r0, [sp, 4] /* orig_r0, needed only for sys calls */ /* Restore r9 used to code the early prologue */ diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h index ccd84806b62..eac07166820 100644 --- a/arch/arc/include/asm/irqflags.h +++ b/arch/arc/include/asm/irqflags.h @@ -39,7 +39,7 @@ static inline long arch_local_irq_save(void) " flag.nz %0 \n" : "=r"(temp), "=r"(flags) : "n"((STATUS_E1_MASK | STATUS_E2_MASK)) - : "cc"); + : "memory", "cc"); return flags; } @@ -53,7 +53,8 @@ static inline void arch_local_irq_restore(unsigned long flags) __asm__ __volatile__( " flag %0 \n" : - : "r"(flags)); + : "r"(flags) + : "memory"); } /* @@ -73,7 +74,8 @@ static inline void arch_local_irq_disable(void) " and %0, %0, %1 \n" " flag %0 \n" : "=&r"(temp) - : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))); + : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK)) + : "memory"); } /* @@ -85,7 +87,9 @@ static inline long arch_local_save_flags(void) __asm__ __volatile__( " lr %0, [status32] \n" - : "=&r"(temp)); + : "=&r"(temp) + : + : "memory"); return temp; } diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h index f3c4934f0ca..4930957ca3d 100644 --- a/arch/arc/include/asm/kgdb.h +++ b/arch/arc/include/asm/kgdb.h @@ -13,7 +13,7 @@ #ifdef CONFIG_KGDB -#include <asm/user.h> +#include <asm/ptrace.h> /* to ensure compatibility with Linux 2.6.35, we don't implement the get/set * register API yet */ @@ -53,9 +53,7 @@ enum arc700_linux_regnums { }; #else -static inline void kgdb_trap(struct pt_regs *regs, int param) -{ -} +#define kgdb_trap(regs, param) #endif #endif /* __ARC_KGDB_H__ */ diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 8ae783d20a8..6179de7e07c 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -123,7 +123,7 @@ static inline long regs_return_value(struct pt_regs *regs) #define orig_r8_IS_SCALL 0x0001 #define orig_r8_IS_SCALL_RESTARTED 0x0002 #define orig_r8_IS_BRKPT 0x0004 -#define orig_r8_IS_EXCPN 0x0004 +#define orig_r8_IS_EXCPN 0x0008 #define orig_r8_IS_IRQ1 0x0010 #define orig_r8_IS_IRQ2 0x0020 diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h index e53a5340ba4..dd785befe7f 100644 --- a/arch/arc/include/asm/syscalls.h +++ b/arch/arc/include/asm/syscalls.h @@ -16,8 +16,6 @@ #include <linux/types.h> int sys_clone_wrapper(int, int, int, int, int); -int sys_fork_wrapper(void); -int sys_vfork_wrapper(void); int sys_cacheflush(uint32_t, uint32_t uint32_t); int sys_arc_settls(void *); int sys_arc_gettls(void); diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h index 6afa4f70207..30333cec0fe 100644 --- a/arch/arc/include/uapi/asm/ptrace.h +++ b/arch/arc/include/uapi/asm/ptrace.h @@ -28,14 +28,14 @@ */ struct user_regs_struct { - struct scratch { + struct { long pad; long bta, lp_start, lp_end, lp_count; long status32, ret, blink, fp, gp; long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; long sp; } scratch; - struct callee { + struct { long pad; long r25, r24, r23, r22, r21, r20; long r19, r18, r17, r16, r15, r14, r13; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index ef6800ba2f0..91eeab81f52 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -452,7 +452,7 @@ tracesys: ; using ERET won't work since next-PC has already committed lr r12, [efa] GET_CURR_TASK_FIELD_PTR TASK_THREAD, r11 - st r12, [r11, THREAD_FAULT_ADDR] + st r12, [r11, THREAD_FAULT_ADDR] ; thread.fault_address ; PRE Sys Call Ptrace hook mov r0, sp ; pt_regs needed @@ -792,31 +792,6 @@ ARC_EXIT ret_from_fork ;################### Special Sys Call Wrappers ########################## -; TBD: call do_fork directly from here -ARC_ENTRY sys_fork_wrapper - SAVE_CALLEE_SAVED_USER - bl @sys_fork - DISCARD_CALLEE_SAVED_USER - - GET_CURR_THR_INFO_FLAGS r10 - btst r10, TIF_SYSCALL_TRACE - bnz tracesys_exit - - b ret_from_system_call -ARC_EXIT sys_fork_wrapper - -ARC_ENTRY sys_vfork_wrapper - SAVE_CALLEE_SAVED_USER - bl @sys_vfork - DISCARD_CALLEE_SAVED_USER - - GET_CURR_THR_INFO_FLAGS r10 - btst r10, TIF_SYSCALL_TRACE - bnz tracesys_exit - - b ret_from_system_call -ARC_EXIT sys_vfork_wrapper - ARC_ENTRY sys_clone_wrapper SAVE_CALLEE_SAVED_USER bl @sys_clone diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c index 2888ba5be47..52bdc83c149 100644 --- a/arch/arc/kernel/kgdb.c +++ b/arch/arc/kernel/kgdb.c @@ -9,6 +9,7 @@ */ #include <linux/kgdb.h> +#include <linux/sched.h> #include <asm/disasm.h> #include <asm/cacheflush.h> diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index dc0f968dae0..2d95ac07df7 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -232,10 +232,8 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) n += scnprintf(buf + n, len - n, "\n"); -#ifdef _ASM_GENERIC_UNISTD_H n += scnprintf(buf + n, len - n, - "OS ABI [v2]\t: asm-generic/{unistd,stat,fcntl}\n"); -#endif + "OS ABI [v3]\t: no-legacy-syscalls\n"); return buf; } diff --git a/arch/arc/kernel/sys.c b/arch/arc/kernel/sys.c index f6bdd07583f..9d6c1ca26af 100644 --- a/arch/arc/kernel/sys.c +++ b/arch/arc/kernel/sys.c @@ -6,8 +6,6 @@ #include <asm/syscalls.h> #define sys_clone sys_clone_wrapper -#define sys_fork sys_fork_wrapper -#define sys_vfork sys_vfork_wrapper #undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 74538c6a97f..49edb6bea6b 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -49,7 +49,6 @@ config ARM select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 - select VIRT_TO_BUS select KTIME_SCALAR select PERF_USE_VMALLOC select RTC_LIB @@ -743,6 +742,7 @@ config ARCH_RPC select NEED_MACH_IO_H select NEED_MACH_MEMORY_H select NO_IOPORT + select VIRT_TO_BUS help On the Acorn Risc-PC, Linux can support the internal IDE disk and CD-ROM interface, serial and parallel port, and the floppy drive. @@ -878,6 +878,7 @@ config ARCH_SHARK select ISA_DMA select NEED_MACH_MEMORY_H select PCI + select VIRT_TO_BUS select ZONE_DMA help Support for the StrongARM based Digital DNARD machine, also known @@ -1005,12 +1006,12 @@ config ARCH_MULTI_V4_V5 bool config ARCH_MULTI_V6 - bool "ARMv6 based platforms (ARM11, Scorpion, ...)" + bool "ARMv6 based platforms (ARM11)" select ARCH_MULTI_V6_V7 select CPU_V6 config ARCH_MULTI_V7 - bool "ARMv7 based platforms (Cortex-A, PJ4, Krait)" + bool "ARMv7 based platforms (Cortex-A, PJ4, Scorpion, Krait)" default y select ARCH_MULTI_V6_V7 select ARCH_VEXPRESS @@ -1182,9 +1183,9 @@ 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. @@ -1438,6 +1439,16 @@ 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" @@ -1461,10 +1472,6 @@ config ISA_DMA bool select ISA_DMA_API -config ARCH_NO_VIRT_TO_BUS - def_bool y - depends on !ARCH_RPC && !ARCH_NETWINDER && !ARCH_SHARK - # Select ISA DMA interface config ISA_DMA_API bool @@ -1581,6 +1588,91 @@ config SCHED_SMT MultiThreading at a cost of slightly increased overhead in some places. If unsure say N here. +config DISABLE_CPU_SCHED_DOMAIN_BALANCE + bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing" + help + Disables scheduler load-balancing at CPU sched domain level. + +config SCHED_HMP + bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling" + depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP + help + Experimental scheduler optimizations for heterogeneous platforms. + Attempts to introspectively select task affinity to optimize power + and performance. Basic support for multiple (>2) cpu types is in place, + but it has only been tested with two types of cpus. + There is currently no support for migration of task groups, hence + !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled + between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE). + +config SCHED_HMP_PRIO_FILTER + bool "(EXPERIMENTAL) Filter HMP migrations by task priority" + depends on SCHED_HMP + default y + help + Enables task priority based HMP migration filter. Any task with + a NICE value above the threshold will always be on low-power cpus + with less compute capacity. + +config SCHED_HMP_PRIO_FILTER_VAL + int "NICE priority threshold" + default 5 + depends on SCHED_HMP_PRIO_FILTER + +config HMP_FAST_CPU_MASK + string "HMP scheduler fast CPU mask" + depends on SCHED_HMP + help + Leave empty to use device tree information. + Specify the cpuids of the fast CPUs in the system as a list string, + e.g. cpuid 0+1 should be specified as 0-1. + +config HMP_SLOW_CPU_MASK + string "HMP scheduler slow CPU mask" + depends on SCHED_HMP + help + Leave empty to use device tree information. + Specify the cpuids of the slow CPUs in the system as a list string, + e.g. cpuid 0+1 should be specified as 0-1. + +config HMP_VARIABLE_SCALE + bool "Allows changing the load tracking scale through sysfs" + depends on SCHED_HMP + help + When turned on, this option exports the thresholds and load average + period value for the load tracking patches through sysfs. + The values can be modified to change the rate of load accumulation + and the thresholds used for HMP migration. + The load_avg_period_ms is the time in ms to reach a load average of + 0.5 for an idle task of 0 load average ratio that start a busy loop. + The up_threshold and down_threshold is the value to go to a faster + CPU or to go back to a slower cpu. + The {up,down}_threshold are devided by 1024 before being compared + to the load average. + For examples, with load_avg_period_ms = 128 and up_threshold = 512, + a running task with a load of 0 will be migrated to a bigger CPU after + 128ms, because after 128ms its load_avg_ratio is 0.5 and the real + up_threshold is 0.5. + This patch has the same behavior as changing the Y of the load + average computation to + (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms) + but it remove intermadiate overflows in computation. + +config HMP_FREQUENCY_INVARIANT_SCALE + bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP" + depends on HMP_VARIABLE_SCALE && CPU_FREQ + help + Scales the current load contribution in line with the frequency + of the CPU that the task was executed on. + In this version, we use a simple linear scale derived from the + maximum frequency reported by CPUFreq. + Restricting tracked load to be scaled by the CPU's frequency + represents the consumption of possible compute capacity + (rather than consumption of actual instantaneous capacity as + normal) and allows the HMP migration's simple threshold + migration strategy to interact more predictably with CPUFreq's + asynchronous compute capacity changes. + config HAVE_ARM_SCU bool help diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index ecfcdba2d17..9b31f4311ea 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. diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 9c6255884cb..2fc92bf10cc 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -169,7 +169,14 @@ dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \ vexpress-v2p-ca9.dtb \ vexpress-v2p-ca15-tc1.dtb \ vexpress-v2p-ca15_a7.dtb \ - xenvm-4.2.dtb + xenvm-4.2.dtb \ + rtsm_ve-cortex_a9x2.dtb \ + rtsm_ve-cortex_a9x4.dtb \ + rtsm_ve-cortex_a15x1.dtb \ + rtsm_ve-cortex_a15x2.dtb \ + rtsm_ve-cortex_a15x4.dtb \ + rtsm_ve-v2p-ca15x1-ca7x1.dtb \ + rtsm_ve-v2p-ca15x4-ca7x4.dtb dtb-$(CONFIG_ARCH_VT8500) += vt8500-bv07.dtb \ wm8505-ref.dtb \ wm8650-mid.dtb \ 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/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index aa98e641931..a98c0d50fbb 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -238,8 +238,32 @@ nand { pinctrl_nand: nand-0 { atmel,pins = - <3 4 0x0 0x1 /* PD5 gpio RDY pin pull_up */ - 3 5 0x0 0x1>; /* PD4 gpio enable pin pull_up */ + <3 0 0x1 0x0 /* PD0 periph A Read Enable */ + 3 1 0x1 0x0 /* PD1 periph A Write Enable */ + 3 2 0x1 0x0 /* PD2 periph A Address Latch Enable */ + 3 3 0x1 0x0 /* PD3 periph A Command Latch Enable */ + 3 4 0x0 0x1 /* PD4 gpio Chip Enable pin pull_up */ + 3 5 0x0 0x1 /* PD5 gpio RDY/BUSY pin pull_up */ + 3 6 0x1 0x0 /* PD6 periph A Data bit 0 */ + 3 7 0x1 0x0 /* PD7 periph A Data bit 1 */ + 3 8 0x1 0x0 /* PD8 periph A Data bit 2 */ + 3 9 0x1 0x0 /* PD9 periph A Data bit 3 */ + 3 10 0x1 0x0 /* PD10 periph A Data bit 4 */ + 3 11 0x1 0x0 /* PD11 periph A Data bit 5 */ + 3 12 0x1 0x0 /* PD12 periph A Data bit 6 */ + 3 13 0x1 0x0>; /* PD13 periph A Data bit 7 */ + }; + + pinctrl_nand_16bits: nand_16bits-0 { + atmel,pins = + <3 14 0x1 0x0 /* PD14 periph A Data bit 8 */ + 3 15 0x1 0x0 /* PD15 periph A Data bit 9 */ + 3 16 0x1 0x0 /* PD16 periph A Data bit 10 */ + 3 17 0x1 0x0 /* PD17 periph A Data bit 11 */ + 3 18 0x1 0x0 /* PD18 periph A Data bit 12 */ + 3 19 0x1 0x0 /* PD19 periph A Data bit 13 */ + 3 20 0x1 0x0 /* PD20 periph A Data bit 14 */ + 3 21 0x1 0x0>; /* PD21 periph A Data bit 15 */ }; }; diff --git a/arch/arm/boot/dts/clcd-panels.dtsi b/arch/arm/boot/dts/clcd-panels.dtsi new file mode 100644 index 00000000000..0b0ff6ead4b --- /dev/null +++ b/arch/arm/boot/dts/clcd-panels.dtsi @@ -0,0 +1,52 @@ +/* + * ARM Ltd. Versatile Express + * + */ + +/ { + panels { + panel@0 { + compatible = "panel"; + mode = "VGA"; + refresh = <60>; + xres = <640>; + yres = <480>; + pixclock = <39721>; + left_margin = <40>; + right_margin = <24>; + upper_margin = <32>; + lower_margin = <11>; + hsync_len = <96>; + vsync_len = <2>; + sync = <0>; + vmode = "FB_VMODE_NONINTERLACED"; + + tim2 = "TIM2_BCD", "TIM2_IPC"; + cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)"; + caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888"; + bpp = <16>; + }; + + panel@1 { + compatible = "panel"; + mode = "XVGA"; + refresh = <60>; + xres = <1024>; + yres = <768>; + pixclock = <15748>; + left_margin = <152>; + right_margin = <48>; + upper_margin = <23>; + lower_margin = <3>; + hsync_len = <104>; + vsync_len = <4>; + sync = <0>; + vmode = "FB_VMODE_NONINTERLACED"; + + tim2 = "TIM2_BCD", "TIM2_IPC"; + cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)"; + caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888"; + bpp = <16>; + }; + }; +}; diff --git a/arch/arm/boot/dts/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/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi index e1347fceb5b..1a62bcf18aa 100644 --- a/arch/arm/boot/dts/exynos4.dtsi +++ b/arch/arm/boot/dts/exynos4.dtsi @@ -275,18 +275,27 @@ compatible = "arm,pl330", "arm,primecell"; reg = <0x12680000 0x1000>; interrupts = <0 35 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; pdma1: pdma@12690000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x12690000 0x1000>; interrupts = <0 36 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; mdma1: mdma@12850000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x12850000 0x1000>; interrupts = <0 34 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <1>; }; }; }; diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi index 5f3562ad674..9a99755920c 100644 --- a/arch/arm/boot/dts/exynos5440.dtsi +++ b/arch/arm/boot/dts/exynos5440.dtsi @@ -142,12 +142,18 @@ compatible = "arm,pl330", "arm,primecell"; reg = <0x120000 0x1000>; interrupts = <0 34 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; pdma1: pdma@121B0000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x121000 0x1000>; interrupts = <0 35 0>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; }; 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/rtsm_ve-cortex_a15x1.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts new file mode 100644 index 00000000000..c9eee916aa7 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts @@ -0,0 +1,159 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x1CT + * + * RTSM_VE_Cortex_A15x1.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA15x1"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x1", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts new file mode 100644 index 00000000000..853a166e3c3 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts @@ -0,0 +1,165 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x2CT + * + * RTSM_VE_Cortex_A15x2.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA15x2"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x2", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <1>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts new file mode 100644 index 00000000000..c1947a3a5c8 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts @@ -0,0 +1,177 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x4CT + * + * RTSM_VE_Cortex_A15x4.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA15x4"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x4", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <1>; + }; + + cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <2>; + }; + + cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <3>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts new file mode 100644 index 00000000000..fca6b2f7967 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts @@ -0,0 +1,171 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA9MPx2CT + * + * RTSM_VE_Cortex_A9x2.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA9x2"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a9x2", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <1>; + #size-cells = <1>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <1>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x80000000>; + }; + + scu@2c000000 { + compatible = "arm,cortex-a9-scu"; + reg = <0x2c000000 0x58>; + }; + + timer@2c000600 { + compatible = "arm,cortex-a9-twd-timer"; + reg = <0x2c000600 0x20>; + interrupts = <1 13 0xf04>; + }; + + watchdog@2c000620 { + compatible = "arm,cortex-a9-twd-wdt"; + reg = <0x2c000620 0x20>; + interrupts = <1 14 0xf04>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0x2c001000 0x1000>, + <0x2c000100 0x100>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0x08000000 0x04000000>, + <1 0 0x14000000 0x04000000>, + <2 0 0x18000000 0x04000000>, + <3 0 0x1c000000 0x04000000>, + <4 0 0x0c000000 0x04000000>, + <5 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts new file mode 100644 index 00000000000..fd8a6ed97a0 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts @@ -0,0 +1,183 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA9MPx4CT + * + * RTSM_VE_Cortex_A9x4.lisa + */ + +/dts-v1/; + +/ { + model = "RTSM_VE_CortexA9x4"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a9x4", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <1>; + #size-cells = <1>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <1>; + }; + + cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <2>; + }; + + cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a9"; + reg = <3>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x80000000>; + }; + + scu@2c000000 { + compatible = "arm,cortex-a9-scu"; + reg = <0x2c000000 0x58>; + }; + + timer@2c000600 { + compatible = "arm,cortex-a9-twd-timer"; + reg = <0x2c000600 0x20>; + interrupts = <1 13 0xf04>; + }; + + watchdog@2c000620 { + compatible = "arm,cortex-a9-twd-wdt"; + reg = <0x2c000620 0x20>; + interrupts = <1 14 0xf04>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0x2c001000 0x1000>, + <0x2c000100 0x100>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0x08000000 0x04000000>, + <1 0 0x14000000 0x04000000>, + <2 0 0x18000000 0x04000000>, + <3 0 0x1c000000 0x04000000>, + <4 0 0x0c000000 0x04000000>, + <5 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi new file mode 100644 index 00000000000..6d125662612 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi @@ -0,0 +1,224 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * Motherboard component + * + * VEMotherBoard.lisa + */ + + motherboard { + compatible = "arm,vexpress,v2m-p1", "simple-bus"; + arm,hbi = <0x190>; + arm,vexpress,site = <0>; + arm,v2m-memory-map = "rs1"; + #address-cells = <2>; /* SMB chipselect number and offset */ + #size-cells = <1>; + #interrupt-cells = <1>; + ranges; + + flash@0,00000000 { + compatible = "arm,vexpress-flash", "cfi-flash"; + reg = <0 0x00000000 0x04000000>, + <4 0x00000000 0x04000000>; + bank-width = <4>; + }; + + vram@2,00000000 { + compatible = "arm,vexpress-vram"; + reg = <2 0x00000000 0x00800000>; + }; + + ethernet@2,02000000 { + compatible = "smsc,lan91c111"; + reg = <2 0x02000000 0x10000>; + interrupts = <15>; + }; + + iofpga@3,00000000 { + compatible = "arm,amba-bus", "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 3 0 0x200000>; + + v2m_sysreg: sysreg@010000 { + compatible = "arm,vexpress-sysreg"; + reg = <0x010000 0x1000>; + gpio-controller; + #gpio-cells = <2>; + }; + + v2m_sysctl: sysctl@020000 { + compatible = "arm,sp810", "arm,primecell"; + reg = <0x020000 0x1000>; + clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&smbclk>; + clock-names = "refclk", "timclk", "apb_pclk"; + #clock-cells = <1>; + clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3"; + }; + + aaci@040000 { + compatible = "arm,pl041", "arm,primecell"; + reg = <0x040000 0x1000>; + interrupts = <11>; + clocks = <&smbclk>; + clock-names = "apb_pclk"; + }; + + mmci@050000 { + compatible = "arm,pl180", "arm,primecell"; + reg = <0x050000 0x1000>; + interrupts = <9 10>; + cd-gpios = <&v2m_sysreg 0 0>; + wp-gpios = <&v2m_sysreg 1 0>; + max-frequency = <12000000>; + vmmc-supply = <&v2m_fixed_3v3>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "mclk", "apb_pclk"; + }; + + kmi@060000 { + compatible = "arm,pl050", "arm,primecell"; + reg = <0x060000 0x1000>; + interrupts = <12>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "KMIREFCLK", "apb_pclk"; + }; + + kmi@070000 { + compatible = "arm,pl050", "arm,primecell"; + reg = <0x070000 0x1000>; + interrupts = <13>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "KMIREFCLK", "apb_pclk"; + }; + + v2m_serial0: uart@090000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x090000 0x1000>; + interrupts = <5>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "uartclk", "apb_pclk"; + }; + + v2m_serial1: uart@0a0000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0a0000 0x1000>; + interrupts = <6>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "uartclk", "apb_pclk"; + }; + + v2m_serial2: uart@0b0000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0b0000 0x1000>; + interrupts = <7>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "uartclk", "apb_pclk"; + }; + + v2m_serial3: uart@0c0000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0c0000 0x1000>; + interrupts = <8>; + clocks = <&v2m_clk24mhz>, <&smbclk>; + clock-names = "uartclk", "apb_pclk"; + }; + + wdt@0f0000 { + compatible = "arm,sp805", "arm,primecell"; + reg = <0x0f0000 0x1000>; + interrupts = <0>; + clocks = <&v2m_refclk32khz>, <&smbclk>; + clock-names = "wdogclk", "apb_pclk"; + }; + + v2m_timer01: timer@110000 { + compatible = "arm,sp804", "arm,primecell"; + reg = <0x110000 0x1000>; + interrupts = <2>; + clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&smbclk>; + clock-names = "timclken1", "timclken2", "apb_pclk"; + }; + + v2m_timer23: timer@120000 { + compatible = "arm,sp804", "arm,primecell"; + reg = <0x120000 0x1000>; + interrupts = <3>; + clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&smbclk>; + clock-names = "timclken1", "timclken2", "apb_pclk"; + }; + + rtc@170000 { + compatible = "arm,pl031", "arm,primecell"; + reg = <0x170000 0x1000>; + interrupts = <4>; + clocks = <&smbclk>; + clock-names = "apb_pclk"; + }; + + clcd@1f0000 { + compatible = "arm,pl111", "arm,primecell"; + reg = <0x1f0000 0x1000>; + interrupts = <14>; + clocks = <&v2m_oscclk1>, <&smbclk>; + clock-names = "v2m:oscclk1", "apb_pclk"; + mode = "VGA"; + use_dma = <0>; + framebuffer = <0x18000000 0x00180000>; + }; + }; + + v2m_fixed_3v3: fixedregulator@0 { + compatible = "regulator-fixed"; + regulator-name = "3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + v2m_clk24mhz: clk24mhz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <24000000>; + clock-output-names = "v2m:clk24mhz"; + }; + + v2m_refclk1mhz: refclk1mhz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <1000000>; + clock-output-names = "v2m:refclk1mhz"; + }; + + v2m_refclk32khz: refclk32khz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <32768>; + clock-output-names = "v2m:refclk32khz"; + }; + + mcc { + compatible = "simple-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + v2m_oscclk1: osc@1 { + /* CLCD clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <23750000 63500000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk1"; + }; + + muxfpga@0 { + compatible = "arm,vexpress-muxfpga"; + arm,vexpress-sysreg,func = <7 0>; + }; + + shutdown@0 { + compatible = "arm,vexpress-shutdown"; + arm,vexpress-sysreg,func = <8 0>; + }; + }; + }; diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts new file mode 100644 index 00000000000..55d4f5ce019 --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts @@ -0,0 +1,227 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x4CT + * ARMCortexA7x4CT + * RTSM_VE_Cortex_A15x1_A7x1.lisa + */ + +/dts-v1/; + +/memreserve/ 0xff000000 0x01000000; + +/ { + model = "RTSM_VE_CortexA15x1-A7x1"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x1_a7x1", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + clusters { + #address-cells = <1>; + #size-cells = <0>; + + cluster0: cluster@0 { + reg = <0>; +// freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core0: core@0 { + reg = <0>; + }; + + }; + }; + + cluster1: cluster@1 { + reg = <1>; +// freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core1: core@0 { + reg = <0>; + }; + + }; + }; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + cluster = <&cluster0>; + core = <&core0>; +// clock-frequency = <1000000000>; + }; + + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x100>; + cluster = <&cluster1>; + core = <&core1>; +// clock-frequency = <800000000>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + cci@2c090000 { + compatible = "arm,cci"; + reg = <0 0x2c090000 0 0x8000>; + }; + + dcscb@60000000 { + compatible = "arm,rtsm,dcscb"; + reg = <0 0x60000000 0 0x1000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + + gic-cpuif@0 { + compatible = "arm,gic-cpuif"; + cpuif-id = <0>; + cpu = <&cpu0>; + }; + gic-cpuif@1 { + compatible = "arm,gic-cpuif"; + cpuif-id = <1>; + cpu = <&cpu1>; + }; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts new file mode 100644 index 00000000000..a2d4441568a --- /dev/null +++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts @@ -0,0 +1,335 @@ +/* + * ARM Ltd. Fast Models + * + * Versatile Express (VE) system model + * ARMCortexA15x4CT + * ARMCortexA7x4CT + * RTSM_VE_Cortex_A15x4_A7x4.lisa + */ + +/dts-v1/; + +/memreserve/ 0xff000000 0x01000000; + +/ { + model = "RTSM_VE_CortexA15x4-A7x4"; + arm,vexpress,site = <0xf>; + compatible = "arm,rtsm_ve,cortex_a15x4_a7x4", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + }; + + clusters { + #address-cells = <1>; + #size-cells = <0>; + + cluster0: cluster@0 { + reg = <0>; +// freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core0: core@0 { + reg = <0>; + }; + + core1: core@1 { + reg = <1>; + }; + + core2: core@2 { + reg = <2>; + }; + + core3: core@3 { + reg = <3>; + }; + + }; + }; + + cluster1: cluster@1 { + reg = <1>; +// freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core4: core@0 { + reg = <0>; + }; + + core5: core@1 { + reg = <1>; + }; + + core6: core@2 { + reg = <2>; + }; + + core7: core@3 { + reg = <3>; + }; + + }; + }; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <0>; + cluster = <&cluster0>; + core = <&core0>; +// clock-frequency = <1000000000>; + }; + + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <1>; + cluster = <&cluster0>; + core = <&core1>; +// clock-frequency = <1000000000>; + }; + + cpu2: cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <2>; + cluster = <&cluster0>; + core = <&core2>; +// clock-frequency = <1000000000>; + }; + + cpu3: cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a15"; + reg = <3>; + cluster = <&cluster0>; + core = <&core3>; +// clock-frequency = <1000000000>; + }; + + cpu4: cpu@4 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x100>; + cluster = <&cluster1>; + core = <&core4>; +// clock-frequency = <800000000>; + }; + + cpu5: cpu@5 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x101>; + cluster = <&cluster1>; + core = <&core5>; +// clock-frequency = <800000000>; + }; + + cpu6: cpu@6 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x102>; + cluster = <&cluster1>; + core = <&core6>; +// clock-frequency = <800000000>; + }; + + cpu7: cpu@7 { + device_type = "cpu"; + compatible = "arm,cortex-a7"; + reg = <0x103>; + cluster = <&cluster1>; + core = <&core7>; +// clock-frequency = <800000000>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; + }; + + cci@2c090000 { + compatible = "arm,cci"; + reg = <0 0x2c090000 0 0x8000>; + }; + + dcscb@60000000 { + compatible = "arm,rtsm,dcscb"; + reg = <0 0x60000000 0 0x1000>; + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x1000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = <1 9 0xf04>; + + gic-cpuif@0 { + compatible = "arm,gic-cpuif"; + cpuif-id = <0>; + cpu = <&cpu0>; + }; + gic-cpuif@1 { + compatible = "arm,gic-cpuif"; + cpuif-id = <1>; + cpu = <&cpu1>; + }; + gic-cpuif@2 { + compatible = "arm,gic-cpuif"; + cpuif-id = <2>; + cpu = <&cpu2>; + }; + gic-cpuif@3 { + compatible = "arm,gic-cpuif"; + cpuif-id = <3>; + cpu = <&cpu3>; + }; + gic-cpuif@4 { + compatible = "arm,gic-cpuif"; + cpuif-id = <4>; + cpu = <&cpu4>; + }; + gic-cpuif@5 { + compatible = "arm,gic-cpuif"; + cpuif-id = <5>; + cpu = <&cpu5>; + }; + gic-cpuif@6 { + compatible = "arm,gic-cpuif"; + cpuif-id = <6>; + cpu = <&cpu6>; + }; + gic-cpuif@7 { + compatible = "arm,gic-cpuif"; + cpuif-id = <7>; + cpu = <&cpu7>; + }; + }; + + timer { + compatible = "arm,armv7-timer"; + interrupts = <1 13 0xf08>, + <1 14 0xf08>, + <1 11 0xf08>, + <1 10 0xf08>; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + osc@0 { + /* ACLK clock to the AXI master port on the test chip */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <30000000 50000000>; + #clock-cells = <0>; + clock-output-names = "extsaxiclk"; + }; + + oscclk1: osc@1 { + /* Reference clock for the CLCD */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <10000000 80000000>; + #clock-cells = <0>; + clock-output-names = "clcdclk"; + }; + + smbclk: oscclk2: osc@2 { + /* Reference clock for the test chip internal PLLs */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <33000000 100000000>; + #clock-cells = <0>; + clock-output-names = "tcrefclk"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic 0 0 4>, + <0 0 1 &gic 0 1 4>, + <0 0 2 &gic 0 2 4>, + <0 0 3 &gic 0 3 4>, + <0 0 4 &gic 0 4 4>, + <0 0 5 &gic 0 5 4>, + <0 0 6 &gic 0 6 4>, + <0 0 7 &gic 0 7 4>, + <0 0 8 &gic 0 8 4>, + <0 0 9 &gic 0 9 4>, + <0 0 10 &gic 0 10 4>, + <0 0 11 &gic 0 11 4>, + <0 0 12 &gic 0 12 4>, + <0 0 13 &gic 0 13 4>, + <0 0 14 &gic 0 14 4>, + <0 0 15 &gic 0 15 4>, + <0 0 16 &gic 0 16 4>, + <0 0 17 &gic 0 17 4>, + <0 0 18 &gic 0 18 4>, + <0 0 19 &gic 0 19 4>, + <0 0 20 &gic 0 20 4>, + <0 0 21 &gic 0 21 4>, + <0 0 22 &gic 0 22 4>, + <0 0 23 &gic 0 23 4>, + <0 0 24 &gic 0 24 4>, + <0 0 25 &gic 0 25 4>, + <0 0 26 &gic 0 26 4>, + <0 0 27 &gic 0 27 4>, + <0 0 28 &gic 0 28 4>, + <0 0 29 &gic 0 29 4>, + <0 0 30 &gic 0 30 4>, + <0 0 31 &gic 0 31 4>, + <0 0 32 &gic 0 32 4>, + <0 0 33 &gic 0 33 4>, + <0 0 34 &gic 0 34 4>, + <0 0 35 &gic 0 35 4>, + <0 0 36 &gic 0 36 4>, + <0 0 37 &gic 0 37 4>, + <0 0 38 &gic 0 38 4>, + <0 0 39 &gic 0 39 4>, + <0 0 40 &gic 0 40 4>, + <0 0 41 &gic 0 41 4>, + <0 0 42 &gic 0 42 4>; + + /include/ "rtsm_ve-motherboard.dtsi" + }; +}; + +/include/ "clcd-panels.dtsi" diff --git a/arch/arm/boot/dts/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/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi index ac870fb3fa0..9584232ee6b 100644 --- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi @@ -228,6 +228,7 @@ }; clcd@1f0000 { + status = "disabled"; compatible = "arm,pl111", "arm,primecell"; reg = <0x1f0000 0x1000>; interrupts = <14>; diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi index f1420368355..6593398c11a 100644 --- a/arch/arm/boot/dts/vexpress-v2m.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m.dtsi @@ -227,6 +227,7 @@ }; clcd@1f000 { + status = "disabled"; compatible = "arm,pl111", "arm,primecell"; reg = <0x1f000 0x1000>; interrupts = <14>; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts index 73187173117..cc6a8c0cfe3 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts @@ -9,6 +9,8 @@ /dts-v1/; +/memreserve/ 0xbf000000 0x01000000; + / { model = "V2P-CA15"; arm,hbi = <0x237>; @@ -57,6 +59,8 @@ interrupts = <0 85 4>; clocks = <&oscclk5>; clock-names = "pxlclk"; + mode = "1024x768-16@60"; + framebuffer = <0 0xff000000 0 0x01000000>; }; memory-controller@2b0a0000 { @@ -117,7 +121,7 @@ }; pmu { - compatible = "arm,cortex-a15-pmu", "arm,cortex-a9-pmu"; + compatible = "arm,cortex-a15-pmu"; interrupts = <0 68 4>, <0 69 4>; }; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts index dfe371ec274..b37fdd8c146 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts @@ -9,11 +9,13 @@ /dts-v1/; +/memreserve/ 0xff000000 0x01000000; + / { model = "V2P-CA15_CA7"; arm,hbi = <0x249>; arm,vexpress,site = <0xf>; - compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress"; + compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress", "arm,generic"; interrupt-parent = <&gic>; #address-cells = <2>; #size-cells = <2>; @@ -29,6 +31,48 @@ i2c1 = &v2m_i2c_pcie; }; + clusters { + #address-cells = <1>; + #size-cells = <0>; + + cluster0: cluster@0 { + reg = <0>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core0: core@0 { + reg = <0>; + }; + + core1: core@1 { + reg = <1>; + }; + + }; + }; + + cluster1: cluster@1 { + reg = <1>; + cores { + #address-cells = <1>; + #size-cells = <0>; + + core2: core@0 { + reg = <0>; + }; + + core3: core@1 { + reg = <1>; + }; + + core4: core@2 { + reg = <2>; + }; + }; + }; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -37,36 +81,51 @@ device_type = "cpu"; compatible = "arm,cortex-a15"; reg = <0>; + cluster = <&cluster0>; + core = <&core0>; + clock-frequency = <1000000000>; }; cpu1: cpu@1 { device_type = "cpu"; compatible = "arm,cortex-a15"; reg = <1>; + cluster = <&cluster0>; + core = <&core1>; + clock-frequency = <1000000000>; }; cpu2: cpu@2 { device_type = "cpu"; compatible = "arm,cortex-a7"; reg = <0x100>; + cluster = <&cluster1>; + core = <&core2>; + clock-frequency = <800000000>; }; cpu3: cpu@3 { device_type = "cpu"; compatible = "arm,cortex-a7"; reg = <0x101>; + cluster = <&cluster1>; + core = <&core3>; + clock-frequency = <800000000>; }; cpu4: cpu@4 { device_type = "cpu"; compatible = "arm,cortex-a7"; reg = <0x102>; + cluster = <&cluster1>; + core = <&core4>; + clock-frequency = <800000000>; }; }; memory@80000000 { device_type = "memory"; - reg = <0 0x80000000 0 0x40000000>; + reg = <0 0x80000000 0 0x80000000>; }; wdt@2a490000 { @@ -81,6 +140,8 @@ compatible = "arm,hdlcd"; reg = <0 0x2b000000 0 0x1000>; interrupts = <0 85 4>; + mode = "1024x768-16@60"; + framebuffer = <0 0xff000000 0 0x01000000>; clocks = <&oscclk5>; clock-names = "pxlclk"; }; @@ -102,6 +163,44 @@ <0 0x2c004000 0 0x2000>, <0 0x2c006000 0 0x2000>; interrupts = <1 9 0xf04>; + + gic-cpuif@0 { + compatible = "arm,gic-cpuif"; + cpuif-id = <0>; + cpu = <&cpu0>; + }; + gic-cpuif@1 { + compatible = "arm,gic-cpuif"; + cpuif-id = <1>; + cpu = <&cpu1>; + }; + gic-cpuif@2 { + compatible = "arm,gic-cpuif"; + cpuif-id = <2>; + cpu = <&cpu2>; + }; + + gic-cpuif@3 { + compatible = "arm,gic-cpuif"; + cpuif-id = <3>; + cpu = <&cpu3>; + }; + + gic-cpuif@4 { + compatible = "arm,gic-cpuif"; + cpuif-id = <4>; + cpu = <&cpu4>; + }; + }; + + cci@2c090000 { + compatible = "arm,cci"; + reg = <0 0x2c090000 0 0x10000>; + interrupts = <0 101 4>, + <0 102 4>, + <0 103 4>, + <0 104 4>, + <0 105 4>; }; memory-controller@7ffd0000 { @@ -125,6 +224,12 @@ clock-names = "apb_pclk"; }; + spc@7fff0000 { + compatible = "arm,spc"; + reg = <0 0x7fff0000 0 0x1000>; + interrupts = <0 95 4>; + }; + timer { compatible = "arm,armv7-timer"; interrupts = <1 13 0xf08>, @@ -133,12 +238,21 @@ <1 10 0xf08>; }; - pmu { - compatible = "arm,cortex-a15-pmu", "arm,cortex-a9-pmu"; + pmu_a15 { + compatible = "arm,cortex-a15-pmu"; + cluster = <&cluster0>; interrupts = <0 68 4>, <0 69 4>; }; + pmu_a7 { + compatible = "arm,cortex-a7-pmu"; + cluster = <&cluster1>; + interrupts = <0 128 4>, + <0 129 4>, + <0 130 4>; + }; + oscclk6a: oscclk6a { /* Reference 24MHz clock */ compatible = "fixed-clock"; @@ -147,6 +261,15 @@ clock-output-names = "oscclk6a"; }; + psci { + compatible = "arm,psci"; + method = "smc"; + cpu_suspend = <0x80100001>; + cpu_off = <0x80100002>; + cpu_on = <0x80100003>; + migrate = <0x80100004>; + }; + dcc { compatible = "arm,vexpress,config-bus"; arm,vexpress,config-bridge = <&v2m_sysreg>; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts index 6328cbc71d3..cf633ed6a1b 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts @@ -9,6 +9,8 @@ /dts-v1/; +/memreserve/ 0xbf000000 0x01000000; + / { model = "V2P-CA5s"; arm,hbi = <0x225>; @@ -59,6 +61,8 @@ interrupts = <0 85 4>; clocks = <&oscclk3>; clock-names = "pxlclk"; + mode = "640x480-16@60"; + framebuffer = <0xbf000000 0x01000000>; }; memory-controller@2a150000 { @@ -111,7 +115,7 @@ }; pmu { - compatible = "arm,cortex-a5-pmu", "arm,cortex-a9-pmu"; + compatible = "arm,cortex-a5-pmu"; interrupts = <0 68 4>, <0 69 4>; }; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts index 1420bb14d95..663fa5927e7 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts @@ -9,6 +9,8 @@ /dts-v1/; +/include/ "clcd-panels.dtsi" + / { model = "V2P-CA9"; arm,hbi = <0x191>; @@ -73,6 +75,8 @@ interrupts = <0 44 4>; clocks = <&oscclk1>, <&oscclk2>; clock-names = "clcdclk", "apb_pclk"; + mode = "XVGA"; + use_dma = <1>; }; memory-controller@100e0000 { diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile index d35f28ad8a8..d412ff0b15a 100644 --- a/arch/arm/common/Makefile +++ b/arch/arm/common/Makefile @@ -12,6 +12,7 @@ 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 +CFLAGS_REMOVE_mcpm_entry.o = -pg AFLAGS_mcpm_head.o := -march=armv7-a AFLAGS_vlock.o := -march=armv7-a obj-$(CONFIG_BL_SWITCHER) += bL_switcher.o diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c index 52b88d81b7b..3caed0db698 100644 --- a/arch/arm/common/mcpm_platsmp.c +++ b/arch/arm/common/mcpm_platsmp.c @@ -15,8 +15,6 @@ #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> @@ -49,7 +47,6 @@ static int __cpuinit mcpm_boot_secondary(unsigned int cpu, struct task_struct *i static void __cpuinit mcpm_secondary_init(unsigned int cpu) { mcpm_cpu_powered_up(); - gic_secondary_init(0); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h index 1f3262e99d8..cedd3721318 100644 --- a/arch/arm/include/asm/cp15.h +++ b/arch/arm/include/asm/cp15.h @@ -61,6 +61,20 @@ static inline void set_cr(unsigned int val) isb(); } +static inline unsigned int get_auxcr(void) +{ + unsigned int val; + asm("mrc p15, 0, %0, c1, c0, 1 @ get AUXCR" : "=r" (val)); + return val; +} + +static inline void set_auxcr(unsigned int val) +{ + asm volatile("mcr p15, 0, %0, c1, c0, 1 @ set AUXCR" + : : "r" (val)); + isb(); +} + #ifndef CONFIG_SMP extern void adjust_cr(unsigned long mask, unsigned long set); #endif diff --git a/arch/arm/include/asm/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/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/irq.h b/arch/arm/include/asm/irq.h index 35c21c375d8..53c15dec7af 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -30,6 +30,11 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *); void handle_IRQ(unsigned int, struct pt_regs *); void init_IRQ(void); +#ifdef CONFIG_MULTI_IRQ_HANDLER +extern void (*handle_arch_irq)(struct pt_regs *); +extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); +#endif + #endif #endif diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 308ad7d6f98..75bf07910b8 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -8,6 +8,8 @@ * published by the Free Software Foundation. */ +#include <linux/types.h> + #ifndef __ASSEMBLY__ struct tag; @@ -16,8 +18,10 @@ struct pt_regs; struct smp_operations; #ifdef CONFIG_SMP #define smp_ops(ops) (&(ops)) +#define smp_init_ops(ops) (&(ops)) #else #define smp_ops(ops) (struct smp_operations *)NULL +#define smp_init_ops(ops) (bool (*)(void))NULL #endif struct machine_desc { @@ -41,6 +45,7 @@ struct machine_desc { unsigned char reserve_lp2 :1; /* never has lp2 */ char restart_mode; /* default restart mode */ struct smp_operations *smp; /* SMP operations */ + bool (*smp_init)(void); void (*fixup)(struct tag *, char **, struct meminfo *); void (*reserve)(void);/* reserve mem blocks */ diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h index 18c88302333..2092ee1e130 100644 --- a/arch/arm/include/asm/mach/irq.h +++ b/arch/arm/include/asm/mach/irq.h @@ -20,11 +20,6 @@ struct seq_file; extern void init_FIQ(int); extern int show_fiq_list(struct seq_file *, int); -#ifdef CONFIG_MULTI_IRQ_HANDLER -extern void (*handle_arch_irq)(struct pt_regs *); -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); -#endif - /* * This is for easy migration, but should be changed in the source */ @@ -35,35 +30,4 @@ do { \ raw_spin_unlock(&desc->lock); \ } while(0) -#ifndef __ASSEMBLY__ -/* - * Entry/exit functions for chained handlers where the primary IRQ chip - * may implement either fasteoi or level-trigger flow control. - */ -static inline void chained_irq_enter(struct irq_chip *chip, - struct irq_desc *desc) -{ - /* FastEOI controllers require no action on entry. */ - if (chip->irq_eoi) - return; - - if (chip->irq_mask_ack) { - chip->irq_mask_ack(&desc->irq_data); - } else { - chip->irq_mask(&desc->irq_data); - if (chip->irq_ack) - chip->irq_ack(&desc->irq_data); - } -} - -static inline void chained_irq_exit(struct irq_chip *chip, - struct irq_desc *desc) -{ - if (chip->irq_eoi) - chip->irq_eoi(&desc->irq_data); - else - chip->irq_unmask(&desc->irq_data); -} -#endif - #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/pmu.h b/arch/arm/include/asm/pmu.h index f24edad26c7..0cd7824ca76 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -62,9 +62,19 @@ struct pmu_hw_events { raw_spinlock_t pmu_lock; }; +struct cpupmu_regs { + u32 pmc; + u32 pmcntenset; + u32 pmuseren; + u32 pmintenset; + u32 pmxevttype[8]; + u32 pmxevtcnt[8]; +}; + struct arm_pmu { struct pmu pmu; cpumask_t active_irqs; + cpumask_t valid_cpus; char *name; irqreturn_t (*handle_irq)(int irq_num, void *dev); void (*enable)(struct perf_event *event); @@ -81,6 +91,8 @@ struct arm_pmu { int (*request_irq)(struct arm_pmu *, irq_handler_t handler); void (*free_irq)(struct arm_pmu *); int (*map_event)(struct perf_event *event); + void (*save_regs)(struct arm_pmu *, struct cpupmu_regs *); + void (*restore_regs)(struct arm_pmu *, struct cpupmu_regs *); int num_events; atomic_t active_events; struct mutex reserve_mutex; diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h index ce0dbe7c162..a079cbee427 100644 --- a/arch/arm/include/asm/psci.h +++ b/arch/arm/include/asm/psci.h @@ -16,6 +16,10 @@ #define PSCI_POWER_STATE_TYPE_STANDBY 0 #define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 +#define PSCI_POWER_STATE_AFFINITY_LEVEL0 0 +#define PSCI_POWER_STATE_AFFINITY_LEVEL1 1 +#define PSCI_POWER_STATE_AFFINITY_LEVEL2 2 +#define PSCI_POWER_STATE_AFFINITY_LEVEL3 3 struct psci_power_state { u16 id; @@ -33,4 +37,12 @@ struct psci_operations { extern struct psci_operations psci_ops; +#ifdef CONFIG_ARM_PSCI +extern int __init psci_probe(void); +#else +static inline int psci_probe(void) +{ + return -ENODEV; +} +#endif #endif /* __ASM_ARM_PSCI_H */ diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 4db8c8820f0..ab865e65a84 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 @@ -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/asm/topology.h b/arch/arm/include/asm/topology.h index 58b8b84adcd..983fa7c153a 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -26,11 +26,45 @@ extern struct cputopo_arm cpu_topology[NR_CPUS]; void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); +int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask); + +#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE +/* Common values for CPUs */ +#ifndef SD_CPU_INIT +#define SD_CPU_INIT (struct sched_domain) { \ + .min_interval = 1, \ + .max_interval = 4, \ + .busy_factor = 64, \ + .imbalance_pct = 125, \ + .cache_nice_tries = 1, \ + .busy_idx = 2, \ + .idle_idx = 1, \ + .newidle_idx = 0, \ + .wake_idx = 0, \ + .forkexec_idx = 0, \ + \ + .flags = 0*SD_LOAD_BALANCE \ + | 1*SD_BALANCE_NEWIDLE \ + | 1*SD_BALANCE_EXEC \ + | 1*SD_BALANCE_FORK \ + | 0*SD_BALANCE_WAKE \ + | 1*SD_WAKE_AFFINE \ + | 0*SD_SHARE_CPUPOWER \ + | 0*SD_SHARE_PKG_RESOURCES \ + | 0*SD_SERIALIZE \ + , \ + .last_balance = jiffies, \ + .balance_interval = 1, \ +} +#endif +#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */ #else static inline void init_cpu_topology(void) { } static inline void store_cpu_topology(unsigned int cpuid) { } +static inline int cluster_to_logical_mask(unsigned int socket_id, + cpumask_t *cluster_mask) { return -EINVAL; } #endif diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 3248cde504e..fefd7f97143 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -276,7 +276,13 @@ 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 +295,7 @@ ENDPROC(ftrace_graph_caller_old) .endm ENTRY(__gnu_mcount_nc) +UNWIND(.fnstart) #ifdef CONFIG_DYNAMIC_FTRACE mov ip, lr ldmia sp!, {lr} @@ -296,17 +303,22 @@ 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 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..1b803117ed9 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; } @@ -1043,13 +1043,14 @@ 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, }; static void __init pm_init(void) { - cpu_pm_register_notifier(&dbg_cpu_pm_nb); + if (has_ossr) + cpu_pm_register_notifier(&dbg_cpu_pm_nb); } #else static inline void pm_init(void) diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 146157dfe27..d847c622a7b 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -12,6 +12,7 @@ */ #define pr_fmt(fmt) "hw perfevents: " fmt +#include <linux/cpumask.h> #include <linux/kernel.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> @@ -81,6 +82,9 @@ armpmu_map_event(struct perf_event *event, return armpmu_map_cache_event(cache_map, config); case PERF_TYPE_RAW: return armpmu_map_raw_event(raw_event_mask, config); + default: + if (event->attr.type >= PERF_TYPE_MAX) + return armpmu_map_raw_event(raw_event_mask, config); } return -ENOENT; @@ -158,6 +162,8 @@ armpmu_stop(struct perf_event *event, int flags) struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; /* * ARM pmu always has to update the counter, so ignore * PERF_EF_UPDATE, see comments in armpmu_start(). @@ -174,6 +180,8 @@ static void armpmu_start(struct perf_event *event, int flags) struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; /* * ARM pmu always has to reprogram the period, so ignore * PERF_EF_RELOAD, see the comment below. @@ -201,6 +209,9 @@ armpmu_del(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return; + armpmu_stop(event, PERF_EF_UPDATE); hw_events->events[idx] = NULL; clear_bit(idx, hw_events->used_mask); @@ -217,6 +228,10 @@ armpmu_add(struct perf_event *event, int flags) int idx; int err = 0; + /* An event following a process won't be stopped earlier */ + if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus)) + return 0; + perf_pmu_disable(event->pmu); /* If we don't have a space for the counter then finish early. */ @@ -253,7 +268,10 @@ 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; @@ -413,6 +431,10 @@ static int armpmu_event_init(struct perf_event *event) int err = 0; atomic_t *active_events = &armpmu->active_events; + if (event->cpu != -1 && + !cpumask_test_cpu(event->cpu, &armpmu->valid_cpus)) + return -ENOENT; + /* does not support taken branch sampling */ if (has_branch_stack(event)) return -EOPNOTSUPP; diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 1f2740e3dbc..0b48a38e3cf 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -19,6 +19,7 @@ #define pr_fmt(fmt) "CPU PMU: " fmt #include <linux/bitmap.h> +#include <linux/cpu_pm.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/of.h> @@ -31,33 +32,36 @@ #include <asm/pmu.h> /* Set at runtime when we know what CPU type we are. */ -static struct arm_pmu *cpu_pmu; +static DEFINE_PER_CPU(struct arm_pmu *, cpu_pmu); static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events); static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask); static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events); +static DEFINE_PER_CPU(struct cpupmu_regs, cpu_pmu_regs); + /* * Despite the names, these two functions are CPU-specific and are used * by the OProfile/perf code. */ const char *perf_pmu_name(void) { - if (!cpu_pmu) + struct arm_pmu *pmu = per_cpu(cpu_pmu, 0); + if (!pmu) return NULL; - return cpu_pmu->name; + return pmu->name; } EXPORT_SYMBOL_GPL(perf_pmu_name); int perf_num_counters(void) { - int max_events = 0; + struct arm_pmu *pmu = per_cpu(cpu_pmu, 0); - if (cpu_pmu != NULL) - max_events = cpu_pmu->num_events; + if (!pmu) + return 0; - return max_events; + return pmu->num_events; } EXPORT_SYMBOL_GPL(perf_num_counters); @@ -75,11 +79,13 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu) { int i, irq, irqs; struct platform_device *pmu_device = cpu_pmu->plat_device; + int cpu = -1; irqs = min(pmu_device->num_resources, num_possible_cpus()); for (i = 0; i < irqs; ++i) { - if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs)) + cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus); + if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs)) continue; irq = platform_get_irq(pmu_device, i); if (irq >= 0) @@ -91,6 +97,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) { int i, err, irq, irqs; struct platform_device *pmu_device = cpu_pmu->plat_device; + int cpu = -1; if (!pmu_device) return -ENODEV; @@ -103,6 +110,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) for (i = 0; i < irqs; ++i) { err = 0; + cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus); irq = platform_get_irq(pmu_device, i); if (irq < 0) continue; @@ -112,7 +120,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) * assume that we're running on a uniprocessor machine and * continue. Otherwise, continue without this interrupt. */ - if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) { + if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) { pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n", irq, i); continue; @@ -126,7 +134,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) return err; } - cpumask_set_cpu(i, &cpu_pmu->active_irqs); + cpumask_set_cpu(cpu, &cpu_pmu->active_irqs); } return 0; @@ -135,7 +143,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) static void cpu_pmu_init(struct arm_pmu *cpu_pmu) { int cpu; - for_each_possible_cpu(cpu) { + for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) { struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu); events->events = per_cpu(hw_events, cpu); events->used_mask = per_cpu(used_mask, cpu); @@ -148,7 +156,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu) /* Ensure the PMU has sane values out of reset. */ if (cpu_pmu->reset) - on_each_cpu(cpu_pmu->reset, cpu_pmu, 1); + on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1); } /* @@ -160,21 +168,46 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu) static int __cpuinit cpu_pmu_notify(struct notifier_block *b, unsigned long action, void *hcpu) { + struct arm_pmu *pmu = per_cpu(cpu_pmu, (long)hcpu); + if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING) return NOTIFY_DONE; - if (cpu_pmu && cpu_pmu->reset) - cpu_pmu->reset(cpu_pmu); + if (pmu && pmu->reset) + pmu->reset(pmu); else return NOTIFY_DONE; return NOTIFY_OK; } +static int cpu_pmu_pm_notify(struct notifier_block *b, + unsigned long action, void *hcpu) +{ + int cpu = smp_processor_id(); + struct arm_pmu *pmu = per_cpu(cpu_pmu, cpu); + struct cpupmu_regs *pmuregs = &per_cpu(cpu_pmu_regs, cpu); + + if (!pmu) + return NOTIFY_DONE; + + if (action == CPU_PM_ENTER && pmu->save_regs) { + pmu->save_regs(pmu, pmuregs); + } else if (action == CPU_PM_EXIT && pmu->restore_regs) { + pmu->restore_regs(pmu, pmuregs); + } + + return NOTIFY_OK; +} + static struct notifier_block __cpuinitdata cpu_pmu_hotplug_notifier = { .notifier_call = cpu_pmu_notify, }; +static struct notifier_block __cpuinitdata cpu_pmu_pm_notifier = { + .notifier_call = cpu_pmu_pm_notify, +}; + /* * PMU platform driver and devicetree bindings. */ @@ -246,6 +279,9 @@ static int probe_current_pmu(struct arm_pmu *pmu) } } + /* assume PMU support all the CPUs in this case */ + cpumask_setall(&pmu->valid_cpus); + put_cpu(); return ret; } @@ -253,15 +289,10 @@ static int probe_current_pmu(struct arm_pmu *pmu) static int cpu_pmu_device_probe(struct platform_device *pdev) { const struct of_device_id *of_id; - int (*init_fn)(struct arm_pmu *); struct device_node *node = pdev->dev.of_node; struct arm_pmu *pmu; - int ret = -ENODEV; - - if (cpu_pmu) { - pr_info("attempt to register multiple PMU devices!"); - return -ENOSPC; - } + int ret = 0; + int cpu; pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL); if (!pmu) { @@ -270,8 +301,28 @@ static int cpu_pmu_device_probe(struct platform_device *pdev) } if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) { - init_fn = of_id->data; - ret = init_fn(pmu); + smp_call_func_t init_fn = (smp_call_func_t)of_id->data; + struct device_node *ncluster; + int cluster = -1; + cpumask_t sibling_mask; + + ncluster = of_parse_phandle(node, "cluster", 0); + if (ncluster) { + int len; + const u32 *hwid; + hwid = of_get_property(ncluster, "reg", &len); + if (hwid && len == 4) + cluster = be32_to_cpup(hwid); + } + /* set sibling mask to all cpu mask if socket is not specified */ + if (cluster == -1 || + cluster_to_logical_mask(cluster, &sibling_mask)) + cpumask_setall(&sibling_mask); + + smp_call_function_any(&sibling_mask, init_fn, pmu, 1); + + /* now set the valid_cpus after init */ + cpumask_copy(&pmu->valid_cpus, &sibling_mask); } else { ret = probe_current_pmu(pmu); } @@ -281,10 +332,12 @@ static int cpu_pmu_device_probe(struct platform_device *pdev) goto out_free; } - cpu_pmu = pmu; - cpu_pmu->plat_device = pdev; - cpu_pmu_init(cpu_pmu); - ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW); + for_each_cpu_mask(cpu, pmu->valid_cpus) + per_cpu(cpu_pmu, cpu) = pmu; + + pmu->plat_device = pdev; + cpu_pmu_init(pmu); + ret = armpmu_register(pmu, -1); if (!ret) return 0; @@ -313,9 +366,17 @@ static int __init register_pmu_driver(void) if (err) return err; + err = cpu_pm_register_notifier(&cpu_pmu_pm_notifier); + if (err) { + unregister_cpu_notifier(&cpu_pmu_hotplug_notifier); + return err; + } + err = platform_driver_register(&cpu_pmu_driver); - if (err) + if (err) { + cpu_pm_unregister_notifier(&cpu_pmu_pm_notifier); unregister_cpu_notifier(&cpu_pmu_hotplug_notifier); + } return err; } diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 039cffb053a..654db5030c3 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -950,6 +950,51 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu) } #endif +static void armv7pmu_save_regs(struct arm_pmu *cpu_pmu, + struct cpupmu_regs *regs) +{ + unsigned int cnt; + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (regs->pmc)); + if (!(regs->pmc & ARMV7_PMNC_E)) + return; + + asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (regs->pmcntenset)); + asm volatile("mrc p15, 0, %0, c9, c14, 0" : "=r" (regs->pmuseren)); + asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (regs->pmintenset)); + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (regs->pmxevtcnt[0])); + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) { + armv7_pmnc_select_counter(cnt); + asm volatile("mrc p15, 0, %0, c9, c13, 1" + : "=r"(regs->pmxevttype[cnt])); + asm volatile("mrc p15, 0, %0, c9, c13, 2" + : "=r"(regs->pmxevtcnt[cnt])); + } + return; +} + +static void armv7pmu_restore_regs(struct arm_pmu *cpu_pmu, + struct cpupmu_regs *regs) +{ + unsigned int cnt; + if (!(regs->pmc & ARMV7_PMNC_E)) + return; + + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (regs->pmcntenset)); + asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r" (regs->pmuseren)); + asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (regs->pmintenset)); + asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (regs->pmxevtcnt[0])); + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) { + armv7_pmnc_select_counter(cnt); + asm volatile("mcr p15, 0, %0, c9, c13, 1" + : : "r"(regs->pmxevttype[cnt])); + asm volatile("mcr p15, 0, %0, c9, c13, 2" + : : "r"(regs->pmxevtcnt[cnt])); + } + asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (regs->pmc)); +} + static void armv7pmu_enable_event(struct perf_event *event) { unsigned long flags; @@ -1223,6 +1268,8 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->start = armv7pmu_start; cpu_pmu->stop = armv7pmu_stop; cpu_pmu->reset = armv7pmu_reset; + cpu_pmu->save_regs = armv7pmu_save_regs; + cpu_pmu->restore_regs = armv7pmu_restore_regs; cpu_pmu->max_period = (1LLU << 32) - 1; }; @@ -1240,7 +1287,7 @@ static u32 armv7_read_num_pmnc_events(void) static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A8"; + cpu_pmu->name = "ARMv7_Cortex_A8"; cpu_pmu->map_event = armv7_a8_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1249,7 +1296,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A9"; + cpu_pmu->name = "ARMv7_Cortex_A9"; cpu_pmu->map_event = armv7_a9_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1258,7 +1305,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A5"; + cpu_pmu->name = "ARMv7_Cortex_A5"; cpu_pmu->map_event = armv7_a5_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); return 0; @@ -1267,7 +1314,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A15"; + cpu_pmu->name = "ARMv7_Cortex_A15"; cpu_pmu->map_event = armv7_a15_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); cpu_pmu->set_event_filter = armv7pmu_set_event_filter; @@ -1277,7 +1324,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu) { armv7pmu_init(cpu_pmu); - cpu_pmu->name = "ARMv7 Cortex-A7"; + cpu_pmu->name = "ARMv7_Cortex_A7"; cpu_pmu->map_event = armv7_a7_map_event; cpu_pmu->num_events = armv7_read_num_pmnc_events(); cpu_pmu->set_event_filter = armv7pmu_set_event_filter; diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c index 36531643cc2..1180801468d 100644 --- a/arch/arm/kernel/psci.c +++ b/arch/arm/kernel/psci.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/of.h> +#include <linux/string.h> #include <asm/compiler.h> #include <asm/errno.h> @@ -26,6 +27,11 @@ struct psci_operations psci_ops; +/* Type of psci support. Currently can only be enabled or disabled */ +#define PSCI_SUP_DISABLED 0 +#define PSCI_SUP_ENABLED 1 + +static unsigned int psci; static int (*invoke_psci_fn)(u32, u32, u32, u32); enum psci_function { @@ -42,6 +48,7 @@ static u32 psci_function_id[PSCI_FN_MAX]; #define PSCI_RET_EOPNOTSUPP -1 #define PSCI_RET_EINVAL -2 #define PSCI_RET_EPERM -3 +#define PSCI_RET_EALREADYON -4 static int psci_to_linux_errno(int errno) { @@ -54,6 +61,8 @@ static int psci_to_linux_errno(int errno) return -EINVAL; case PSCI_RET_EPERM: return -EPERM; + case PSCI_RET_EALREADYON: + return -EAGAIN; }; return -EINVAL; @@ -164,6 +173,9 @@ static int __init psci_init(void) const char *method; u32 id; + if (psci == PSCI_SUP_DISABLED) + return 0; + np = of_find_matching_node(NULL, psci_of_match); if (!np) return 0; @@ -209,3 +221,33 @@ out_put_node: return 0; } early_initcall(psci_init); + +int __init psci_probe(void) +{ + struct device_node *np; + int ret = -ENODEV; + + if (psci == PSCI_SUP_ENABLED) { + np = of_find_matching_node(NULL, psci_of_match); + if (np) + ret = 0; + } + + of_node_put(np); + return ret; +} + +static int __init early_psci(char *val) +{ + int ret = 0; + + if (strcmp(val, "enable") == 0) + psci = PSCI_SUP_ENABLED; + else if (strcmp(val, "disable") == 0) + psci = PSCI_SUP_DISABLED; + else + ret = -EINVAL; + + return ret; +} +early_param("psci", early_psci); 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 1cc9e179641..7c9fd36be1d 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) @@ -261,6 +260,19 @@ static int cpu_has_aliasing_icache(unsigned int arch) int aliasing_icache; unsigned int id_reg, num_sets, line_size; +#ifdef CONFIG_BIG_LITTLE + /* + * We expect a combination of Cortex-A15 and Cortex-A7 cores. + * A7 = VIPT aliasing I-cache + * A15 = PIPT (non-aliasing) I-cache + * To cater for this discrepancy, let's assume aliasing I-cache + * all the time. This means unneeded extra work on the A15 but + * only ptrace is affected which is not performance critical. + */ + if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0) + return 1; +#endif + /* PIPT caches never alias. */ if (icache_is_pipt()) return 0; @@ -353,6 +365,23 @@ 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 +402,7 @@ 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 +512,11 @@ 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 +556,7 @@ 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); @@ -768,7 +800,10 @@ void __init setup_arch(char **cmdline_p) arm_dt_init_cpu_maps(); #ifdef CONFIG_SMP if (is_smp()) { - smp_set_ops(mdesc->smp); + if (!mdesc->smp_init || !mdesc->smp_init()) { + if(mdesc->smp) + smp_set_ops(mdesc->smp); + } smp_init_cpus(); } #endif @@ -778,8 +813,6 @@ 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/sleep.S b/arch/arm/kernel/sleep.S index 987dcf33415..b5c1e636ed8 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -4,6 +4,7 @@ #include <asm/assembler.h> #include <asm/glue-cache.h> #include <asm/glue-proc.h> +#include "entry-header.S" .text /* @@ -30,9 +31,8 @@ ENTRY(__cpu_suspend) mov r2, r5 @ virtual SP ldr r3, =sleep_save_sp #ifdef CONFIG_SMP - ALT_SMP(mrc p15, 0, lr, c0, c0, 5) - ALT_UP(mov lr, #0) - and lr, lr, #15 + get_thread_info r5 + ldr lr, [r5, #TI_CPU] @ cpu logical index add r3, r3, lr, lsl #2 #endif bl __cpu_suspend_save @@ -82,10 +82,13 @@ ENDPROC(cpu_resume_after_mmu) .align ENTRY(cpu_resume) #ifdef CONFIG_SMP + mov r1, #0 @ fall-back logical index for UP + ALT_SMP(mrc p15, 0, r0, c0, c0, 5) + ALT_UP_B(1f) + bic r0, #0xff000000 + bl cpu_logical_index @ return logical index in r1 +1: adr r0, sleep_save_sp - ALT_SMP(mrc p15, 0, r1, c0, c0, 5) - ALT_UP(mov r1, #0) - and r1, r1, #15 ldr r0, [r0, r1, lsl #2] @ stack phys addr #else ldr r0, sleep_save_sp @ stack phys addr @@ -102,3 +105,20 @@ sleep_save_sp: .rept CONFIG_NR_CPUS .long 0 @ preserve stack phys ptr here .endr + +#ifdef CONFIG_SMP +cpu_logical_index: + adr r3, cpu_map_ptr + ldr r2, [r3] + add r3, r3, r2 @ virt_to_phys(__cpu_logical_map) + mov r1, #0 +1: + ldr r2, [r3, r1, lsl #2] + cmp r2, r0 + moveq pc, lr + add r1, r1, #1 + b 1b + +cpu_map_ptr: + .long __cpu_logical_map - . +#endif diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 668c8863ab4..f40fb0dcb3b 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -694,9 +694,6 @@ 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_tlb.c b/arch/arm/kernel/smp_tlb.c index bd030053139..e82e1d24877 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 +70,72 @@ 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_many(cpu_online_mask, ipi_flush_tlb_a15_erratum, + NULL, 1); +} + +static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) +{ + int cpu; + cpumask_t mask = { CPU_BITS_NONE }; + + if (!erratum_a15_798181()) + return; + + dummy_flush_tlb_a15_erratum(); + for_each_online_cpu(cpu) { + if (cpu == smp_processor_id()) + 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); +} + 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 +144,7 @@ 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 +157,7 @@ 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 +168,7 @@ 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 +183,7 @@ 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 +195,7 @@ 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/kernel/topology.c b/arch/arm/kernel/topology.c index 79282ebcd93..8df74d630ca 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -13,6 +13,7 @@ #include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/percpu.h> #include <linux/node.h> @@ -22,6 +23,7 @@ #include <linux/slab.h> #include <asm/cputype.h> +#include <asm/smp_plat.h> #include <asm/topology.h> /* @@ -200,6 +202,7 @@ static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {} * cpu topology table */ struct cputopo_arm cpu_topology[NR_CPUS]; +EXPORT_SYMBOL_GPL(cpu_topology); const struct cpumask *cpu_coregroup_mask(int cpu) { @@ -287,6 +290,137 @@ void store_cpu_topology(unsigned int cpuid) cpu_topology[cpuid].socket_id, mpidr); } + +#ifdef CONFIG_SCHED_HMP + +static const char * const little_cores[] = { + "arm,cortex-a7", + NULL, +}; + +static bool is_little_cpu(struct device_node *cn) +{ + const char * const *lc; + for (lc = little_cores; *lc; lc++) + if (of_device_is_compatible(cn, *lc)) + return true; + return false; +} + +void __init arch_get_fast_and_slow_cpus(struct cpumask *fast, + struct cpumask *slow) +{ + struct device_node *cn = NULL; + int cpu; + + cpumask_clear(fast); + cpumask_clear(slow); + + /* + * Use the config options if they are given. This helps testing + * HMP scheduling on systems without a big.LITTLE architecture. + */ + if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) { + if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast)) + WARN(1, "Failed to parse HMP fast cpu mask!\n"); + if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow)) + WARN(1, "Failed to parse HMP slow cpu mask!\n"); + return; + } + + /* + * Else, parse device tree for little cores. + */ + while ((cn = of_find_node_by_type(cn, "cpu"))) { + + const u32 *mpidr; + int len; + + mpidr = of_get_property(cn, "reg", &len); + if (!mpidr || len != 4) { + pr_err("* %s missing reg property\n", cn->full_name); + continue; + } + + cpu = get_logical_index(be32_to_cpup(mpidr)); + if (cpu == -EINVAL) { + pr_err("couldn't get logical index for mpidr %x\n", + be32_to_cpup(mpidr)); + break; + } + + if (is_little_cpu(cn)) + cpumask_set_cpu(cpu, slow); + else + cpumask_set_cpu(cpu, fast); + } + + if (!cpumask_empty(fast) && !cpumask_empty(slow)) + return; + + /* + * We didn't find both big and little cores so let's call all cores + * fast as this will keep the system running, with all cores being + * treated equal. + */ + cpumask_setall(fast); + cpumask_clear(slow); +} + +void __init arch_get_hmp_domains(struct list_head *hmp_domains_list) +{ + struct cpumask hmp_fast_cpu_mask; + struct cpumask hmp_slow_cpu_mask; + struct hmp_domain *domain; + + arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask); + + /* + * Initialize hmp_domains + * Must be ordered with respect to compute capacity. + * Fastest domain at head of list. + */ + if(!cpumask_empty(&hmp_slow_cpu_mask)) { + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->cpus, &hmp_slow_cpu_mask); + list_add(&domain->hmp_domains, hmp_domains_list); + } + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->cpus, &hmp_fast_cpu_mask); + list_add(&domain->hmp_domains, hmp_domains_list); +} +#endif /* CONFIG_SCHED_HMP */ + + +/* + * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster + * @socket_id: cluster HW identifier + * @cluster_mask: the cpumask location to be initialized, modified by the + * function only if return value == 0 + * + * Return: + * + * 0 on success + * -EINVAL if cluster_mask is NULL or there is no record matching socket_id + */ +int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask) +{ + int cpu; + + if (!cluster_mask) + return -EINVAL; + + for_each_online_cpu(cpu) + if (socket_id == topology_physical_package_id(cpu)) { + cpumask_copy(cluster_mask, topology_core_cpumask(cpu)); + return 0; + } + + return -EINVAL; +} + /* * init_cpu_topology is called at boot when only one cpu is running * which prevent simultaneous write access to cpu_topology array diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index c10a45fa73f..a0dfc2a53f9 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -198,6 +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; diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 94eee8befc8..8eea97be1ed 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -79,11 +79,11 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, 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); diff --git a/arch/arm/kvm/vgic.c b/arch/arm/kvm/vgic.c index 161d5c15f0f..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) 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-at91/gpio.c b/arch/arm/mach-at91/gpio.c index c5d7e1e9d75..a5afcf76550 100644 --- a/arch/arm/mach-at91/gpio.c +++ b/arch/arm/mach-at91/gpio.c @@ -22,10 +22,9 @@ #include <linux/module.h> #include <linux/io.h> #include <linux/irqdomain.h> +#include <linux/irqchip/chained_irq.h> #include <linux/of_address.h> -#include <asm/mach/irq.h> - #include <mach/hardware.h> #include <mach/at91_pio.h> diff --git a/arch/arm/mach-at91/include/mach/gpio.h b/arch/arm/mach-at91/include/mach/gpio.h index eed465ab0dd..5fc23771c15 100644 --- a/arch/arm/mach-at91/include/mach/gpio.h +++ b/arch/arm/mach-at91/include/mach/gpio.h @@ -209,6 +209,14 @@ extern int at91_get_gpio_value(unsigned pin); extern void at91_gpio_suspend(void); extern void at91_gpio_resume(void); +#ifdef CONFIG_PINCTRL_AT91 +extern void at91_pinctrl_gpio_suspend(void); +extern void at91_pinctrl_gpio_resume(void); +#else +static inline void at91_pinctrl_gpio_suspend(void) {} +static inline void at91_pinctrl_gpio_resume(void) {} +#endif + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm/mach-at91/irq.c b/arch/arm/mach-at91/irq.c index 8e210262aee..e0ca5917102 100644 --- a/arch/arm/mach-at91/irq.c +++ b/arch/arm/mach-at91/irq.c @@ -92,23 +92,21 @@ static int at91_aic_set_wake(struct irq_data *d, unsigned value) void at91_irq_suspend(void) { - int i = 0, bit; + int bit = -1; if (has_aic5()) { /* disable enabled irqs */ - while ((bit = find_next_bit(backups, n_irqs, i)) < n_irqs) { + while ((bit = find_next_bit(backups, n_irqs, bit + 1)) < n_irqs) { at91_aic_write(AT91_AIC5_SSR, bit & AT91_AIC5_INTSEL_MSK); at91_aic_write(AT91_AIC5_IDCR, 1); - i = bit; } /* enable wakeup irqs */ - i = 0; - while ((bit = find_next_bit(wakeups, n_irqs, i)) < n_irqs) { + bit = -1; + while ((bit = find_next_bit(wakeups, n_irqs, bit + 1)) < n_irqs) { at91_aic_write(AT91_AIC5_SSR, bit & AT91_AIC5_INTSEL_MSK); at91_aic_write(AT91_AIC5_IECR, 1); - i = bit; } } else { at91_aic_write(AT91_AIC_IDCR, *backups); @@ -118,23 +116,21 @@ void at91_irq_suspend(void) void at91_irq_resume(void) { - int i = 0, bit; + int bit = -1; if (has_aic5()) { /* disable wakeup irqs */ - while ((bit = find_next_bit(wakeups, n_irqs, i)) < n_irqs) { + while ((bit = find_next_bit(wakeups, n_irqs, bit + 1)) < n_irqs) { at91_aic_write(AT91_AIC5_SSR, bit & AT91_AIC5_INTSEL_MSK); at91_aic_write(AT91_AIC5_IDCR, 1); - i = bit; } /* enable irqs disabled for suspend */ - i = 0; - while ((bit = find_next_bit(backups, n_irqs, i)) < n_irqs) { + bit = -1; + while ((bit = find_next_bit(backups, n_irqs, bit + 1)) < n_irqs) { at91_aic_write(AT91_AIC5_SSR, bit & AT91_AIC5_INTSEL_MSK); at91_aic_write(AT91_AIC5_IECR, 1); - i = bit; } } else { at91_aic_write(AT91_AIC_IDCR, *wakeups); diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index adb6db888a1..73f1f250403 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -201,7 +201,10 @@ extern u32 at91_slow_clock_sz; static int at91_pm_enter(suspend_state_t state) { - at91_gpio_suspend(); + if (of_have_populated_dt()) + at91_pinctrl_gpio_suspend(); + else + at91_gpio_suspend(); at91_irq_suspend(); pr_debug("AT91: PM - wake mask %08x, pm state %d\n", @@ -286,7 +289,10 @@ static int at91_pm_enter(suspend_state_t state) error: target_state = PM_SUSPEND_ON; at91_irq_resume(); - at91_gpio_resume(); + if (of_have_populated_dt()) + at91_pinctrl_gpio_resume(); + else + at91_gpio_resume(); return 0; } 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-davinci/dma.c b/arch/arm/mach-davinci/dma.c index a685e9706b7..45b7c71d9cc 100644 --- a/arch/arm/mach-davinci/dma.c +++ b/arch/arm/mach-davinci/dma.c @@ -743,6 +743,9 @@ EXPORT_SYMBOL(edma_free_channel); */ int edma_alloc_slot(unsigned ctlr, int slot) { + if (!edma_cc[ctlr]) + return -EINVAL; + if (slot >= 0) slot = EDMA_CHAN_SLOT(slot); 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/common.c b/arch/arm/mach-exynos/common.c index d63d399c7ba..7bc0f9aa8b3 100644 --- a/arch/arm/mach-exynos/common.c +++ b/arch/arm/mach-exynos/common.c @@ -26,6 +26,7 @@ #include <linux/irqchip.h> #include <linux/of_address.h> #include <linux/irqchip/arm-gic.h> +#include <linux/irqchip/chained_irq.h> #include <asm/proc-fns.h> #include <asm/exception.h> diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c index 60f7c5be057..95e04bd5813 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -20,7 +20,6 @@ #include <linux/jiffies.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -76,13 +75,6 @@ static DEFINE_SPINLOCK(boot_lock); static void __cpuinit exynos_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig index abda5a18a66..0f2111a1131 100644 --- a/arch/arm/mach-footbridge/Kconfig +++ b/arch/arm/mach-footbridge/Kconfig @@ -67,6 +67,7 @@ config ARCH_NETWINDER select ISA select ISA_DMA select PCI + select VIRT_TO_BUS help Say Y here if you intend to run this kernel on the Rebel.COM NetWinder. Information about this machine can be found at: diff --git a/arch/arm/mach-highbank/hotplug.c b/arch/arm/mach-highbank/hotplug.c index f30c5284339..890cae23c12 100644 --- a/arch/arm/mach-highbank/hotplug.c +++ b/arch/arm/mach-highbank/hotplug.c @@ -28,13 +28,11 @@ 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-highbank/platsmp.c b/arch/arm/mach-highbank/platsmp.c index 8797a700172..a984573e0d0 100644 --- a/arch/arm/mach-highbank/platsmp.c +++ b/arch/arm/mach-highbank/platsmp.c @@ -17,7 +17,6 @@ #include <linux/init.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <asm/smp_scu.h> @@ -25,11 +24,6 @@ extern void secondary_startup(void); -static void __cpuinit highbank_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - static int __cpuinit highbank_boot_secondary(unsigned int cpu, struct task_struct *idle) { highbank_set_cpu_jump(cpu, secondary_startup); @@ -67,7 +61,6 @@ static void __init highbank_smp_prepare_cpus(unsigned int max_cpus) struct smp_operations highbank_smp_ops __initdata = { .smp_init_cpus = highbank_smp_init_cpus, .smp_prepare_cpus = highbank_smp_prepare_cpus, - .smp_secondary_init = highbank_secondary_init, .smp_boot_secondary = highbank_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_die = highbank_cpu_die, diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c index 74e3a34d78b..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]); @@ -264,6 +265,8 @@ int __init mx35_clocks_init(void) clk_prepare_enable(clk[gpio3_gate]); 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..361a253e2b6 100644 --- a/arch/arm/mach-imx/hotplug.c +++ b/arch/arm/mach-imx/hotplug.c @@ -46,11 +46,23 @@ 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/imx25-dt.c b/arch/arm/mach-imx/imx25-dt.c index 03b65e5ea54..82348391582 100644 --- a/arch/arm/mach-imx/imx25-dt.c +++ b/arch/arm/mach-imx/imx25-dt.c @@ -27,6 +27,11 @@ static const char * const imx25_dt_board_compat[] __initconst = { NULL }; +static void __init imx25_timer_init(void) +{ + mx25_clocks_init_dt(); +} + DT_MACHINE_START(IMX25_DT, "Freescale i.MX25 (Device Tree Support)") .map_io = mx25_map_io, .init_early = imx25_init_early, diff --git a/arch/arm/mach-imx/platsmp.c b/arch/arm/mach-imx/platsmp.c index 7c0b03f67b0..77e9a25ed0f 100644 --- a/arch/arm/mach-imx/platsmp.c +++ b/arch/arm/mach-imx/platsmp.c @@ -12,7 +12,6 @@ #include <linux/init.h> #include <linux/smp.h> -#include <linux/irqchip/arm-gic.h> #include <asm/page.h> #include <asm/smp_scu.h> #include <asm/mach/map.h> @@ -52,16 +51,6 @@ void imx_scu_standby_enable(void) writel_relaxed(val, scu_base); } -static void __cpuinit imx_secondary_init(unsigned int cpu) -{ - /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); -} - static int __cpuinit imx_boot_secondary(unsigned int cpu, struct task_struct *idle) { imx_set_cpu_jump(cpu, v7_secondary_startup); @@ -96,7 +85,6 @@ static void __init imx_smp_prepare_cpus(unsigned int max_cpus) struct smp_operations imx_smp_ops __initdata = { .smp_init_cpus = imx_smp_init_cpus, .smp_prepare_cpus = imx_smp_prepare_cpus, - .smp_secondary_init = imx_secondary_init, .smp_boot_secondary = imx_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_die = imx_cpu_die, 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-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c index d1e2d595e79..f62b68d926f 100644 --- a/arch/arm/mach-mmp/gplugd.c +++ b/arch/arm/mach-mmp/gplugd.c @@ -9,6 +9,7 @@ */ #include <linux/init.h> +#include <linux/platform_device.h> #include <linux/gpio.h> #include <asm/mach/arch.h> diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c index 42932865416..00cdb0a5dac 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -15,7 +15,6 @@ #include <linux/jiffies.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/cputype.h> @@ -42,13 +41,6 @@ static inline int get_core_count(void) static void __cpuinit msm_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ 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/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-smp.c b/arch/arm/mach-omap2/omap-smp.c index 7f5626d8fd3..f0897732a96 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -67,13 +67,6 @@ static void __cpuinit omap4_secondary_init(unsigned int cpu) 4, 0, 0, 0, 0, 0); /* - * If any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * Synchronise with the boot thread. */ spin_lock(&boot_lock); 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..eaba9dc91a0 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -2719,7 +2719,17 @@ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { .name = "ocp2scp_usb_phy", .class = &omap44xx_ocp2scp_hwmod_class, .clkdm_name = "l3_init_clkdm", - .main_clk = "func_48m_fclk", + /* + * ocp2scp_usb_phy_phy_48m is provided by the OMAP4 PRCM IP + * block as an "optional clock," and normally should never be + * specified as the main_clk for an OMAP IP block. However it + * turns out that this clock is actually the main clock for + * the ocp2scp_usb_phy IP block: + * http://lists.infradead.org/pipermail/linux-arm-kernel/2012-September/119943.html + * So listing ocp2scp_usb_phy_phy_48m as a main_clk here seems + * to be the best workaround. + */ + .main_clk = "ocp2scp_usb_phy_phy_48m", .prcm = { .omap4 = { .clkctrl_offs = OMAP4_CM_L3INIT_USBPHYOCP2SCP_CLKCTRL_OFFSET, 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/platsmp.c b/arch/arm/mach-prima2/platsmp.c index 4b788310f6a..c7c92e78f0c 100644 --- a/arch/arm/mach-prima2/platsmp.c +++ b/arch/arm/mach-prima2/platsmp.c @@ -11,7 +11,6 @@ #include <linux/delay.h> #include <linux/of.h> #include <linux/of_address.h> -#include <linux/irqchip/arm-gic.h> #include <asm/page.h> #include <asm/mach/map.h> #include <asm/smp_plat.h> @@ -49,13 +48,6 @@ void __init sirfsoc_map_scu(void) static void __cpuinit sirfsoc_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ 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..6b0b6047785 100644 --- a/arch/arm/mach-s3c24xx/irq.c +++ b/arch/arm/mach-s3c24xx/irq.c @@ -25,6 +25,7 @@ #include <linux/ioport.h> #include <linux/device.h> #include <linux/irqdomain.h> +#include <linux/irqchip/chained_irq.h> #include <asm/mach/irq.h> @@ -500,7 +501,7 @@ 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-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c index fcdf52dbcc4..f051f53e35b 100644 --- a/arch/arm/mach-s5pv210/clock.c +++ b/arch/arm/mach-s5pv210/clock.c @@ -214,11 +214,6 @@ static struct clk clk_pcmcdclk2 = { .name = "pcmcdclk", }; -static struct clk dummy_apb_pclk = { - .name = "apb_pclk", - .id = -1, -}; - static struct clk *clkset_vpllsrc_list[] = { [0] = &clk_fin_vpll, [1] = &clk_sclk_hdmi27m, @@ -305,18 +300,6 @@ static struct clk_ops clk_fout_apll_ops = { static struct clk init_clocks_off[] = { { - .name = "dma", - .devname = "dma-pl330.0", - .parent = &clk_hclk_psys.clk, - .enable = s5pv210_clk_ip0_ctrl, - .ctrlbit = (1 << 3), - }, { - .name = "dma", - .devname = "dma-pl330.1", - .parent = &clk_hclk_psys.clk, - .enable = s5pv210_clk_ip0_ctrl, - .ctrlbit = (1 << 4), - }, { .name = "rot", .parent = &clk_hclk_dsys.clk, .enable = s5pv210_clk_ip0_ctrl, @@ -573,6 +556,20 @@ static struct clk clk_hsmmc3 = { .ctrlbit = (1<<19), }; +static struct clk clk_pdma0 = { + .name = "pdma0", + .parent = &clk_hclk_psys.clk, + .enable = s5pv210_clk_ip0_ctrl, + .ctrlbit = (1 << 3), +}; + +static struct clk clk_pdma1 = { + .name = "pdma1", + .parent = &clk_hclk_psys.clk, + .enable = s5pv210_clk_ip0_ctrl, + .ctrlbit = (1 << 4), +}; + static struct clk *clkset_uart_list[] = { [6] = &clk_mout_mpll.clk, [7] = &clk_mout_epll.clk, @@ -1075,6 +1072,8 @@ static struct clk *clk_cdev[] = { &clk_hsmmc1, &clk_hsmmc2, &clk_hsmmc3, + &clk_pdma0, + &clk_pdma1, }; /* Clock initialisation code */ @@ -1333,6 +1332,8 @@ static struct clk_lookup s5pv210_clk_lookup[] = { CLKDEV_INIT(NULL, "spi_busclk0", &clk_p), CLKDEV_INIT("s5pv210-spi.0", "spi_busclk1", &clk_sclk_spi0.clk), CLKDEV_INIT("s5pv210-spi.1", "spi_busclk1", &clk_sclk_spi1.clk), + CLKDEV_INIT("dma-pl330.0", "apb_pclk", &clk_pdma0), + CLKDEV_INIT("dma-pl330.1", "apb_pclk", &clk_pdma1), }; void __init s5pv210_register_clocks(void) @@ -1361,6 +1362,5 @@ void __init s5pv210_register_clocks(void) for (ptr = 0; ptr < ARRAY_SIZE(clk_cdev); ptr++) s3c_disable_clocks(clk_cdev[ptr], 1); - s3c24xx_register_clock(&dummy_apb_pclk); s3c_pwmclk_init(); } diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c index 3a38f7b34b9..e373de44a8b 100644 --- a/arch/arm/mach-s5pv210/mach-goni.c +++ b/arch/arm/mach-s5pv210/mach-goni.c @@ -845,7 +845,7 @@ static struct fimc_source_info goni_camera_sensors[] = { .mux_id = 0, .flags = V4L2_MBUS_PCLK_SAMPLE_FALLING | V4L2_MBUS_VSYNC_ACTIVE_LOW, - .bus_type = FIMC_BUS_TYPE_ITU_601, + .fimc_bus_type = FIMC_BUS_TYPE_ITU_601, .board_info = &noon010pc30_board_info, .i2c_bus_num = 0, .clk_frequency = 16000000UL, diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c index cdcb799e802..fec49ebc359 100644 --- a/arch/arm/mach-shmobile/board-marzen.c +++ b/arch/arm/mach-shmobile/board-marzen.c @@ -32,6 +32,7 @@ #include <linux/smsc911x.h> #include <linux/spi/spi.h> #include <linux/spi/sh_hspi.h> +#include <linux/mmc/host.h> #include <linux/mmc/sh_mobile_sdhi.h> #include <linux/mfd/tmio.h> #include <linux/usb/otg.h> diff --git a/arch/arm/mach-shmobile/smp-emev2.c b/arch/arm/mach-shmobile/smp-emev2.c index 953eb1f9388..384e27dd360 100644 --- a/arch/arm/mach-shmobile/smp-emev2.c +++ b/arch/arm/mach-shmobile/smp-emev2.c @@ -23,7 +23,6 @@ #include <linux/spinlock.h> #include <linux/io.h> #include <linux/delay.h> -#include <linux/irqchip/arm-gic.h> #include <mach/common.h> #include <mach/emev2.h> #include <asm/smp_plat.h> @@ -85,11 +84,6 @@ static int __maybe_unused emev2_cpu_kill(unsigned int cpu) } -static void __cpuinit emev2_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - static int __cpuinit emev2_boot_secondary(unsigned int cpu, struct task_struct *idle) { cpu = cpu_logical_map(cpu); @@ -124,7 +118,6 @@ static void __init emev2_smp_init_cpus(void) struct smp_operations emev2_smp_ops __initdata = { .smp_init_cpus = emev2_smp_init_cpus, .smp_prepare_cpus = emev2_smp_prepare_cpus, - .smp_secondary_init = emev2_secondary_init, .smp_boot_secondary = emev2_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_kill = emev2_cpu_kill, diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c index 3a4acf23edc..994906560ed 100644 --- a/arch/arm/mach-shmobile/smp-r8a7779.c +++ b/arch/arm/mach-shmobile/smp-r8a7779.c @@ -23,7 +23,6 @@ #include <linux/spinlock.h> #include <linux/io.h> #include <linux/delay.h> -#include <linux/irqchip/arm-gic.h> #include <mach/common.h> #include <mach/r8a7779.h> #include <asm/smp_plat.h> @@ -132,11 +131,6 @@ static int __maybe_unused r8a7779_cpu_kill(unsigned int cpu) } -static void __cpuinit r8a7779_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - static int __cpuinit r8a7779_boot_secondary(unsigned int cpu, struct task_struct *idle) { struct r8a7779_pm_ch *ch = NULL; @@ -186,7 +180,6 @@ static void __init r8a7779_smp_init_cpus(void) struct smp_operations r8a7779_smp_ops __initdata = { .smp_init_cpus = r8a7779_smp_init_cpus, .smp_prepare_cpus = r8a7779_smp_prepare_cpus, - .smp_secondary_init = r8a7779_secondary_init, .smp_boot_secondary = r8a7779_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_kill = r8a7779_cpu_kill, diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c index acb46a94ccd..d0f9aca2247 100644 --- a/arch/arm/mach-shmobile/smp-sh73a0.c +++ b/arch/arm/mach-shmobile/smp-sh73a0.c @@ -23,7 +23,6 @@ #include <linux/spinlock.h> #include <linux/io.h> #include <linux/delay.h> -#include <linux/irqchip/arm-gic.h> #include <mach/common.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -59,11 +58,6 @@ static unsigned int __init sh73a0_get_core_count(void) return scu_get_core_count(scu_base); } -static void __cpuinit sh73a0_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - static int __cpuinit sh73a0_boot_secondary(unsigned int cpu, struct task_struct *idle) { cpu = cpu_logical_map(cpu); @@ -138,7 +132,6 @@ static void sh73a0_cpu_die(unsigned int cpu) struct smp_operations sh73a0_smp_ops __initdata = { .smp_init_cpus = sh73a0_smp_init_cpus, .smp_prepare_cpus = sh73a0_smp_prepare_cpus, - .smp_secondary_init = sh73a0_secondary_init, .smp_boot_secondary = sh73a0_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_kill = sh73a0_cpu_kill, diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c index 84c60fa8daa..ca14d1d5ac7 100644 --- a/arch/arm/mach-socfpga/platsmp.c +++ b/arch/arm/mach-socfpga/platsmp.c @@ -22,7 +22,6 @@ #include <linux/io.h> #include <linux/of.h> #include <linux/of_address.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_scu.h> @@ -33,16 +32,6 @@ extern void __iomem *sys_manager_base_addr; extern void __iomem *rst_manager_base_addr; -static void __cpuinit socfpga_secondary_init(unsigned int cpu) -{ - /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); -} - static int __cpuinit socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) { int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; @@ -109,7 +98,6 @@ static void socfpga_cpu_die(unsigned int cpu) struct smp_operations socfpga_smp_ops __initdata = { .smp_init_cpus = socfpga_smp_init_cpus, .smp_prepare_cpus = socfpga_smp_prepare_cpus, - .smp_secondary_init = socfpga_secondary_init, .smp_boot_secondary = socfpga_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU .cpu_die = socfpga_cpu_die, diff --git a/arch/arm/mach-spear13xx/platsmp.c b/arch/arm/mach-spear13xx/platsmp.c index af4ade61cd9..551c69c9a22 100644 --- a/arch/arm/mach-spear13xx/platsmp.c +++ b/arch/arm/mach-spear13xx/platsmp.c @@ -15,7 +15,6 @@ #include <linux/jiffies.h> #include <linux/io.h> #include <linux/smp.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_scu.h> #include <mach/spear.h> @@ -28,13 +27,6 @@ static void __iomem *scu_base = IOMEM(VA_SCU_BASE); static void __cpuinit spear13xx_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c index 2c6b3d55213..9348d3c496a 100644 --- a/arch/arm/mach-tegra/platsmp.c +++ b/arch/arm/mach-tegra/platsmp.c @@ -18,7 +18,6 @@ #include <linux/jiffies.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <linux/clk/tegra.h> #include <asm/cacheflush.h> @@ -44,13 +43,6 @@ static cpumask_t tegra_cpu_init_mask; static void __cpuinit tegra_secondary_init(unsigned int cpu) { - /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - cpumask_set_cpu(cpu, &tegra_cpu_init_mask); } 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/platsmp.c b/arch/arm/mach-ux500/platsmp.c index 18f7af339dc..152b1309b9a 100644 --- a/arch/arm/mach-ux500/platsmp.c +++ b/arch/arm/mach-ux500/platsmp.c @@ -16,7 +16,6 @@ #include <linux/device.h> #include <linux/smp.h> #include <linux/io.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -58,13 +57,6 @@ static DEFINE_SPINLOCK(boot_lock); static void __cpuinit ux500_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig index 52d315b792c..7b2ebc29ce3 100644 --- a/arch/arm/mach-vexpress/Kconfig +++ b/arch/arm/mach-vexpress/Kconfig @@ -1,5 +1,6 @@ config ARCH_VEXPRESS bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7 + select ARCH_HAS_CPUFREQ select ARCH_REQUIRE_GPIOLIB select ARM_AMBA select ARM_GIC @@ -52,4 +53,21 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA config ARCH_VEXPRESS_CA9X4 bool "Versatile Express Cortex-A9x4 tile" +config ARCH_VEXPRESS_DCSCB + bool "Dual Cluster System Control Block (DCSCB) support" + depends on MCPM + select ARM_CCI + help + Support for the Dual Cluster System Configuration Block (DCSCB). + This is needed to provide CPU and cluster power management + on RTSM. + +config ARCH_VEXPRESS_TC2 + bool "TC2 cluster management" + depends on MCPM + select ARM_SPC + select ARM_CCI + help + Support for CPU and cluster power management on TC2. + endmenu diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile index 80b64971fbd..b4117dbfe85 100644 --- a/arch/arm/mach-vexpress/Makefile +++ b/arch/arm/mach-vexpress/Makefile @@ -6,5 +6,13 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \ obj-y := v2m.o reset.o obj-$(CONFIG_ARCH_VEXPRESS_CA9X4) += ct-ca9x4.o +obj-$(CONFIG_ARCH_VEXPRESS_DCSCB) += dcscb.o dcscb_setup.o +CFLAGS_REMOVE_dcscb.o = -pg +obj-$(CONFIG_ARCH_VEXPRESS_TC2) += tc2_pm.o tc2_pm_setup.o +CFLAGS_REMOVE_tc2_pm.o = -pg +ifeq ($(CONFIG_ARCH_VEXPRESS_TC2),y) +obj-$(CONFIG_ARM_PSCI) += tc2_pm_psci.o +CFLAGS_REMOVE_tc2_pm_psci.o = -pg +endif obj-$(CONFIG_SMP) += platsmp.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o diff --git a/arch/arm/mach-vexpress/core.h b/arch/arm/mach-vexpress/core.h index f134cd4a85f..bde4374ab6d 100644 --- a/arch/arm/mach-vexpress/core.h +++ b/arch/arm/mach-vexpress/core.h @@ -6,6 +6,8 @@ void vexpress_dt_smp_map_io(void); +bool vexpress_smp_init_ops(void); + extern struct smp_operations vexpress_smp_ops; extern void vexpress_cpu_die(unsigned int cpu); diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c new file mode 100644 index 00000000000..0dc3caca227 --- /dev/null +++ b/arch/arm/mach-vexpress/dcscb.c @@ -0,0 +1,256 @@ +/* + * arch/arm/mach-vexpress/dcscb.c - Dual Cluster System Configuration Block + * + * Created by: Nicolas Pitre, May 2012 + * Copyright: (C) 2012-2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/io.h> +#include <linux/spinlock.h> +#include <linux/errno.h> +#include <linux/of_address.h> +#include <linux/vexpress.h> +#include <linux/arm-cci.h> + +#include <asm/mcpm.h> +#include <asm/proc-fns.h> +#include <asm/cacheflush.h> +#include <asm/cputype.h> +#include <asm/cp15.h> +#include <asm/psci.h> + + +#define RST_HOLD0 0x0 +#define RST_HOLD1 0x4 +#define SYS_SWRESET 0x8 +#define RST_STAT0 0xc +#define RST_STAT1 0x10 +#define EAG_CFG_R 0x20 +#define EAG_CFG_W 0x24 +#define KFC_CFG_R 0x28 +#define KFC_CFG_W 0x2c +#define DCS_CFG_R 0x30 + +/* + * We can't use regular spinlocks. In the switcher case, it is possible + * for an outbound CPU to call power_down() after its inbound counterpart + * is already live using the same logical CPU number which trips lockdep + * debugging. + */ +static arch_spinlock_t dcscb_lock = __ARCH_SPIN_LOCK_UNLOCKED; + +static void __iomem *dcscb_base; +static int dcscb_use_count[4][2]; +static int dcscb_mcpm_cpu_mask[2]; + +static int dcscb_power_up(unsigned int cpu, unsigned int cluster) +{ + unsigned int rst_hold, cpumask = (1 << cpu); + unsigned int mcpm_mask = dcscb_mcpm_cpu_mask[cluster]; + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + if (cpu >= 4 || cluster >= 2) + return -EINVAL; + + /* + * Since this is called with IRQs enabled, and no arch_spin_lock_irq + * variant exists, we need to disable IRQs manually here. + */ + local_irq_disable(); + arch_spin_lock(&dcscb_lock); + + dcscb_use_count[cpu][cluster]++; + if (dcscb_use_count[cpu][cluster] == 1) { + rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4); + if (rst_hold & (1 << 8)) { + /* remove cluster reset and add individual CPU's reset */ + rst_hold &= ~(1 << 8); + rst_hold |= mcpm_mask; + } + rst_hold &= ~(cpumask | (cpumask << 4)); + writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4); + } else if (dcscb_use_count[cpu][cluster] != 2) { + /* + * The only possible values are: + * 0 = CPU down + * 1 = CPU (still) up + * 2 = CPU requested to be up before it had a chance + * to actually make itself down. + * Any other value is a bug. + */ + BUG(); + } + + arch_spin_unlock(&dcscb_lock); + local_irq_enable(); + + return 0; +} + +static void dcscb_power_down(void) +{ + unsigned int mpidr, cpu, cluster, rst_hold, cpumask, mcpm_mask; + bool last_man = false, skip_wfi = false; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + cpumask = (1 << cpu); + mcpm_mask = dcscb_mcpm_cpu_mask[cluster]; + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cpu >= 4 || cluster >= 2); + + __mcpm_cpu_going_down(cpu, cluster); + + arch_spin_lock(&dcscb_lock); + BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP); + dcscb_use_count[cpu][cluster]--; + if (dcscb_use_count[cpu][cluster] == 0) { + rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4); + rst_hold |= cpumask; + if (((rst_hold | (rst_hold >> 4)) & mcpm_mask) == mcpm_mask) { + rst_hold |= (1 << 8); + last_man = true; + } + writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4); + } else if (dcscb_use_count[cpu][cluster] == 1) { + /* + * A power_up request went ahead of us. + * Even if we do not want to shut this CPU down, + * the caller expects a certain state as if the WFI + * was aborted. So let's continue with cache cleaning. + */ + skip_wfi = true; + } else + BUG(); + + if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) { + arch_spin_unlock(&dcscb_lock); + + /* + * Flush all cache levels for this cluster. + * + * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need + * a preliminary flush here for those CPUs. At least, that's + * the theory -- without the extra flush, Linux explodes on + * RTSM (maybe not needed anymore, to be investigated). + */ + flush_cache_all(); + set_cr(get_cr() & ~CR_C); + flush_cache_all(); + + /* + * This is a harmless no-op. On platforms with a real + * outer cache this might either be needed or not, + * depending on where the outer cache sits. + */ + outer_flush_all(); + + /* Disable local coherency by clearing the ACTLR "SMP" bit: */ + set_auxcr(get_auxcr() & ~(1 << 6)); + + /* + * Disable cluster-level coherency by masking + * incoming snoops and DVM messages: + */ + disable_cci(cluster); + + __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN); + } else { + arch_spin_unlock(&dcscb_lock); + + /* + * Flush the local CPU cache. + * + * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need + * a preliminary flush here for those CPUs. At least, that's + * the theory -- without the extra flush, Linux explodes on + * RTSM (maybe not needed anymore, to be investigated). + */ + flush_cache_louis(); + set_cr(get_cr() & ~CR_C); + flush_cache_louis(); + + /* Disable local coherency by clearing the ACTLR "SMP" bit: */ + set_auxcr(get_auxcr() & ~(1 << 6)); + } + + __mcpm_cpu_down(cpu, cluster); + + /* Now we are prepared for power-down, do it: */ + if (!skip_wfi) { + dsb(); + wfi(); + } + + /* Not dead at this point? Let our caller cope. */ +} + +static const struct mcpm_platform_ops dcscb_power_ops = { + .power_up = dcscb_power_up, + .power_down = dcscb_power_down, +}; + +static void __init dcscb_usage_count_init(void) +{ + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cpu >= 4 || cluster >= 2); + dcscb_use_count[cpu][cluster] = 1; +} + +extern void dcscb_power_up_setup(unsigned int affinity_level); + +static int __init dcscb_init(void) +{ + struct device_node *node; + unsigned int cfg; + int ret; + + ret = psci_probe(); + if (!ret) { + pr_debug("psci found. Aborting native init\n"); + return -ENODEV; + } + + node = of_find_compatible_node(NULL, NULL, "arm,rtsm,dcscb"); + if (!node) + return -ENODEV; + dcscb_base= of_iomap(node, 0); + if (!dcscb_base) + return -EADDRNOTAVAIL; + cfg = readl_relaxed(dcscb_base + DCS_CFG_R); + dcscb_mcpm_cpu_mask[0] = (1 << (((cfg >> 16) >> (0 << 2)) & 0xf)) - 1; + dcscb_mcpm_cpu_mask[1] = (1 << (((cfg >> 16) >> (1 << 2)) & 0xf)) - 1; + dcscb_usage_count_init(); + + ret = mcpm_platform_register(&dcscb_power_ops); + if (!ret) + ret = mcpm_sync_init(dcscb_power_up_setup); + if (ret) { + iounmap(dcscb_base); + return ret; + } + + /* + * Future entries into the kernel can now go + * through the cluster entry vectors. + */ + vexpress_flags_set(virt_to_phys(mcpm_entry_point)); + + return 0; +} + +early_initcall(dcscb_init); diff --git a/arch/arm/mach-vexpress/dcscb_setup.S b/arch/arm/mach-vexpress/dcscb_setup.S new file mode 100644 index 00000000000..93bd13f458a --- /dev/null +++ b/arch/arm/mach-vexpress/dcscb_setup.S @@ -0,0 +1,80 @@ +/* + * arch/arm/include/asm/dcscb_setup.S + * + * Created by: Dave Martin, 2012-06-22 + * Copyright: (C) 2012-2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + + +#include <linux/linkage.h> +#include <asm/mcpm.h> + + +#define SLAVE_SNOOPCTL_OFFSET 0 +#define SNOOPCTL_SNOOP_ENABLE (1 << 0) +#define SNOOPCTL_DVM_ENABLE (1 << 1) + +#define CCI_STATUS_OFFSET 0xc +#define STATUS_CHANGE_PENDING (1 << 0) + +#define CCI_SLAVE_OFFSET(n) (0x1000 + 0x1000 * (n)) + +#define RTSM_CCI_PHYS_BASE 0x2c090000 +#define RTSM_CCI_SLAVE_A15 3 +#define RTSM_CCI_SLAVE_A7 4 + +#define RTSM_CCI_A15_OFFSET CCI_SLAVE_OFFSET(RTSM_CCI_SLAVE_A15) +#define RTSM_CCI_A7_OFFSET CCI_SLAVE_OFFSET(RTSM_CCI_SLAVE_A7) + + +ENTRY(dcscb_power_up_setup) + + cmp r0, #0 @ check affinity level + beq 2f + +/* + * Enable cluster-level coherency, in preparation for turning on the MMU. + * The ACTLR SMP bit does not need to be set here, because cpu_resume() + * already restores that. + */ + + mrc p15, 0, r0, c0, c0, 5 @ MPIDR + ubfx r0, r0, #8, #4 @ cluster + + @ A15/A7 may not require explicit L2 invalidation on reset, dependent + @ on hardware integration desicions. + @ For now, this code assumes that L2 is either already invalidated, or + @ invalidation is not required. + + ldr r3, =RTSM_CCI_PHYS_BASE + RTSM_CCI_A15_OFFSET + cmp r0, #0 @ A15 cluster? + addne r3, r3, #RTSM_CCI_A7_OFFSET - RTSM_CCI_A15_OFFSET + + @ r3 now points to the correct CCI slave register block + + ldr r0, [r3, #SLAVE_SNOOPCTL_OFFSET] + orr r0, r0, #SNOOPCTL_SNOOP_ENABLE | SNOOPCTL_DVM_ENABLE + str r0, [r3, #SLAVE_SNOOPCTL_OFFSET] @ enable CCI snoops + + @ Wait for snoop control change to complete: + + ldr r3, =RTSM_CCI_PHYS_BASE + +1: ldr r0, [r3, #CCI_STATUS_OFFSET] + tst r0, #STATUS_CHANGE_PENDING + bne 1b + + dsb @ Synchronise side-effects of enabling CCI + + bx lr + +2: @ Implementation-specific local CPU setup operations should go here, + @ if any. In this case, there is nothing to do. + + bx lr + +ENDPROC(dcscb_power_up_setup) diff --git a/arch/arm/mach-vexpress/include/mach/tc2.h b/arch/arm/mach-vexpress/include/mach/tc2.h new file mode 100644 index 00000000000..d3b5a2225a0 --- /dev/null +++ b/arch/arm/mach-vexpress/include/mach/tc2.h @@ -0,0 +1,10 @@ +#ifndef __MACH_TC2_H +#define __MACH_TC2_H + +/* + * cpu and cluster limits + */ +#define TC2_MAX_CPUS 3 +#define TC2_MAX_CLUSTERS 2 + +#endif diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c index dc1ace55d55..21368ba6ca2 100644 --- a/arch/arm/mach-vexpress/platsmp.c +++ b/arch/arm/mach-vexpress/platsmp.c @@ -12,9 +12,11 @@ #include <linux/errno.h> #include <linux/smp.h> #include <linux/io.h> +#include <linux/of.h> #include <linux/of_fdt.h> #include <linux/vexpress.h> +#include <asm/mcpm.h> #include <asm/smp_scu.h> #include <asm/mach/map.h> @@ -203,3 +205,14 @@ struct smp_operations __initdata vexpress_smp_ops = { .cpu_die = vexpress_cpu_die, #endif }; + +bool __init vexpress_smp_init_ops(void) +{ +#ifdef CONFIG_MCPM + if(of_find_compatible_node(NULL, NULL, "arm,cci")) { + mcpm_smp_set_ops(); + return true; + } +#endif + return false; +} diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c new file mode 100644 index 00000000000..f2e9959fb26 --- /dev/null +++ b/arch/arm/mach-vexpress/tc2_pm.c @@ -0,0 +1,271 @@ +/* + * arch/arm/mach-vexpress/tc2_pm.c - TC2 power management support + * + * Created by: Nicolas Pitre, October 2012 + * Copyright: (C) 2012 Linaro Limited + * + * Some portions of this file were originally written by Achin Gupta + * Copyright: (C) 2012 ARM Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/errno.h> +#include <linux/irqchip/arm-gic.h> + +#include <asm/mcpm.h> +#include <asm/proc-fns.h> +#include <asm/cacheflush.h> +#include <asm/cputype.h> +#include <asm/cp15.h> +#include <asm/psci.h> + +#include <mach/motherboard.h> +#include <mach/tc2.h> + +#include <linux/vexpress.h> +#include <linux/arm-cci.h> + +/* + * We can't use regular spinlocks. In the switcher case, it is possible + * for an outbound CPU to call power_down() after its inbound counterpart + * is already live using the same logical CPU number which trips lockdep + * debugging. + */ +static arch_spinlock_t tc2_pm_lock = __ARCH_SPIN_LOCK_UNLOCKED; + +static int tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS]; + +static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster) +{ + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + if (cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)) + return -EINVAL; + + /* + * Since this is called with IRQs enabled, and no arch_spin_lock_irq + * variant exists, we need to disable IRQs manually here. + */ + local_irq_disable(); + arch_spin_lock(&tc2_pm_lock); + + if (!tc2_pm_use_count[0][cluster] && + !tc2_pm_use_count[1][cluster] && + !tc2_pm_use_count[2][cluster]) + vexpress_spc_powerdown_enable(cluster, 0); + + tc2_pm_use_count[cpu][cluster]++; + if (tc2_pm_use_count[cpu][cluster] == 1) { + vexpress_spc_write_bxaddr_reg(cluster, cpu, + virt_to_phys(mcpm_entry_point)); + vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1); + } else if (tc2_pm_use_count[cpu][cluster] != 2) { + /* + * The only possible values are: + * 0 = CPU down + * 1 = CPU (still) up + * 2 = CPU requested to be up before it had a chance + * to actually make itself down. + * Any other value is a bug. + */ + BUG(); + } + + arch_spin_unlock(&tc2_pm_lock); + local_irq_enable(); + + return 0; +} + +static void tc2_pm_down(u64 residency) +{ + unsigned int mpidr, cpu, cluster; + bool last_man = false, skip_wfi = false; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)); + + __mcpm_cpu_going_down(cpu, cluster); + + arch_spin_lock(&tc2_pm_lock); + BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP); + tc2_pm_use_count[cpu][cluster]--; + if (tc2_pm_use_count[cpu][cluster] == 0) { + vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1); + if (!tc2_pm_use_count[0][cluster] && + !tc2_pm_use_count[1][cluster] && + !tc2_pm_use_count[2][cluster] && + (!residency || residency > 5000)) { + vexpress_spc_powerdown_enable(cluster, 1); + vexpress_spc_set_global_wakeup_intr(1); + last_man = true; + } + } else if (tc2_pm_use_count[cpu][cluster] == 1) { + /* + * A power_up request went ahead of us. + * Even if we do not want to shut this CPU down, + * the caller expects a certain state as if the WFI + * was aborted. So let's continue with cache cleaning. + */ + skip_wfi = true; + } else + BUG(); + + gic_cpu_if_down(); + + if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) { + arch_spin_unlock(&tc2_pm_lock); + + set_cr(get_cr() & ~CR_C); + flush_cache_all(); + asm volatile ("clrex"); + set_auxcr(get_auxcr() & ~(1 << 6)); + + disable_cci(cluster); + + /* + * Ensure that both C & I bits are disabled in the SCTLR + * before disabling ACE snoops. This ensures that no + * coherency traffic will originate from this cpu after + * ACE snoops are turned off. + */ + cpu_proc_fin(); + + __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN); + } else { + /* + * If last man then undo any setup done previously. + */ + if (last_man) { + vexpress_spc_powerdown_enable(cluster, 0); + vexpress_spc_set_global_wakeup_intr(0); + } + + arch_spin_unlock(&tc2_pm_lock); + + set_cr(get_cr() & ~CR_C); + flush_cache_louis(); + asm volatile ("clrex"); + set_auxcr(get_auxcr() & ~(1 << 6)); + } + + __mcpm_cpu_down(cpu, cluster); + + /* Now we are prepared for power-down, do it: */ + if (!skip_wfi) + wfi(); + + /* Not dead at this point? Let our caller cope. */ +} + +static void tc2_pm_power_down(void) +{ + tc2_pm_down(0); +} + +static void tc2_pm_suspend(u64 residency) +{ + extern void tc2_resume(void); + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + vexpress_spc_write_bxaddr_reg(cluster, cpu, + virt_to_phys(tc2_resume)); + + tc2_pm_down(residency); +} + +static void tc2_pm_powered_up(void) +{ + unsigned int mpidr, cpu, cluster; + unsigned long flags; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)); + + local_irq_save(flags); + arch_spin_lock(&tc2_pm_lock); + + if (!tc2_pm_use_count[0][cluster] && + !tc2_pm_use_count[1][cluster] && + !tc2_pm_use_count[2][cluster]) { + vexpress_spc_powerdown_enable(cluster, 0); + vexpress_spc_set_global_wakeup_intr(0); + } + + if (!tc2_pm_use_count[cpu][cluster]) + tc2_pm_use_count[cpu][cluster] = 1; + + vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 0); + vexpress_spc_write_bxaddr_reg(cluster, cpu, 0); + + arch_spin_unlock(&tc2_pm_lock); + local_irq_restore(flags); +} + +static const struct mcpm_platform_ops tc2_pm_power_ops = { + .power_up = tc2_pm_power_up, + .power_down = tc2_pm_power_down, + .suspend = tc2_pm_suspend, + .powered_up = tc2_pm_powered_up, +}; + +static void __init tc2_pm_usage_count_init(void) +{ + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)); + + tc2_pm_use_count[cpu][cluster] = 1; +} + +extern void tc2_pm_power_up_setup(unsigned int affinity_level); + +static int __init tc2_pm_init(void) +{ + int ret; + + ret = psci_probe(); + if (!ret) { + pr_debug("psci found. Aborting native init\n"); + return -ENODEV; + } + + if (!vexpress_spc_check_loaded()) + return -ENODEV; + + tc2_pm_usage_count_init(); + + ret = mcpm_platform_register(&tc2_pm_power_ops); + if (!ret) + ret = mcpm_sync_init(tc2_pm_power_up_setup); + if (!ret) + pr_info("TC2 power management initialized\n"); + return ret; +} + +early_initcall(tc2_pm_init); diff --git a/arch/arm/mach-vexpress/tc2_pm_psci.c b/arch/arm/mach-vexpress/tc2_pm_psci.c new file mode 100644 index 00000000000..5a5e4f56849 --- /dev/null +++ b/arch/arm/mach-vexpress/tc2_pm_psci.c @@ -0,0 +1,168 @@ +/* + * arch/arm/mach-vexpress/tc2_pm_psci.c - TC2 PSCI support + * + * Created by: Achin Gupta, December 2012 + * Copyright: (C) 2012 ARM Limited + * + * Some portions of this file were originally written by Nicolas Pitre + * Copyright: (C) 2012 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/errno.h> + +#include <asm/mcpm.h> +#include <asm/proc-fns.h> +#include <asm/cacheflush.h> +#include <asm/psci.h> +#include <asm/atomic.h> +#include <asm/cputype.h> +#include <asm/cp15.h> + +#include <mach/motherboard.h> +#include <mach/tc2.h> + +#include <linux/vexpress.h> + +/* + * Platform specific state id understood by the firmware and used to + * program the power controller + */ +#define PSCI_POWER_STATE_ID 0 + +static atomic_t tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS]; + +static int tc2_pm_psci_power_up(unsigned int cpu, unsigned int cluster) +{ + unsigned int mpidr = (cluster << 8) | cpu; + int ret = 0; + + BUG_ON(!psci_ops.cpu_on); + + switch (atomic_inc_return(&tc2_pm_use_count[cpu][cluster])) { + case 1: + /* + * This is a request to power up a cpu that linux thinks has + * been powered down. Retries are needed if the firmware has + * seen the power down request as yet. + */ + do + ret = psci_ops.cpu_on(mpidr, + virt_to_phys(mcpm_entry_point)); + while (ret == -EAGAIN); + + return ret; + case 2: + /* This power up request has overtaken a power down request */ + return ret; + default: + /* Any other value is a bug */ + BUG(); + } +} + +static void tc2_pm_psci_power_down(void) +{ + struct psci_power_state power_state; + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + BUG_ON(!psci_ops.cpu_off); + + switch (atomic_dec_return(&tc2_pm_use_count[cpu][cluster])) { + case 1: + /* + * Overtaken by a power up. Flush caches, exit coherency, + * return & fake a reset + */ + set_cr(get_cr() & ~CR_C); + + flush_cache_louis(); + + asm volatile ("clrex"); + set_auxcr(get_auxcr() & ~(1 << 6)); + + return; + case 0: + /* A normal request to possibly power down the cluster */ + power_state.id = PSCI_POWER_STATE_ID; + power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN; + power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1; + + psci_ops.cpu_off(power_state); + + /* On success this function never returns */ + default: + /* Any other value is a bug */ + BUG(); + } +} + +static void tc2_pm_psci_suspend(u64 unused) +{ + struct psci_power_state power_state; + + BUG_ON(!psci_ops.cpu_suspend); + + /* On TC2 always attempt to power down the cluster */ + power_state.id = PSCI_POWER_STATE_ID; + power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN; + power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1; + + psci_ops.cpu_suspend(power_state, virt_to_phys(mcpm_entry_point)); + + /* On success this function never returns */ + BUG(); +} + +static const struct mcpm_platform_ops tc2_pm_power_ops = { + .power_up = tc2_pm_psci_power_up, + .power_down = tc2_pm_psci_power_down, + .suspend = tc2_pm_psci_suspend, +}; + +static void __init tc2_pm_usage_count_init(void) +{ + unsigned int mpidr, cpu, cluster; + + mpidr = read_cpuid_mpidr(); + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + + pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); + BUG_ON(cluster >= TC2_MAX_CLUSTERS || + cpu >= vexpress_spc_get_nb_cpus(cluster)); + + atomic_set(&tc2_pm_use_count[cpu][cluster], 1); +} + +static int __init tc2_pm_psci_init(void) +{ + int ret; + + ret = psci_probe(); + if (ret) { + pr_debug("psci not found. Aborting psci init\n"); + return -ENODEV; + } + + tc2_pm_usage_count_init(); + + ret = mcpm_platform_register(&tc2_pm_power_ops); + if (!ret) + ret = mcpm_sync_init(NULL); + if (!ret) + pr_info("TC2 power management initialized\n"); + return ret; +} + +early_initcall(tc2_pm_psci_init); diff --git a/arch/arm/mach-vexpress/tc2_pm_setup.S b/arch/arm/mach-vexpress/tc2_pm_setup.S new file mode 100644 index 00000000000..4728f83731a --- /dev/null +++ b/arch/arm/mach-vexpress/tc2_pm_setup.S @@ -0,0 +1,102 @@ +/* + * arch/arm/include/asm/tc2_pm_setup.S + * + * Created by: Nicolas Pitre, October 2012 + ( (based on dcscb_setup.S by Dave Martin) + * Copyright: (C) 2012 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + + +#include <linux/linkage.h> +#include <asm/mcpm.h> + + +#define SPC_PHYS_BASE 0x7FFF0000 +#define SPC_WAKE_INT_STAT 0xb2c + +#define SNOOP_CTL_A15 0x404 +#define SNOOP_CTL_A7 0x504 + +#define A15_SNOOP_MASK (0x3 << 7) +#define A7_SNOOP_MASK (0x1 << 13) + +#define A15_BX_ADDR0 0xB68 + + +#define CCI_PHYS_BASE 0x2c090000 + +#define SLAVE_SNOOPCTL_OFFSET 0 +#define SNOOPCTL_SNOOP_ENABLE (1 << 0) +#define SNOOPCTL_DVM_ENABLE (1 << 1) + +#define CCI_STATUS_OFFSET 0xc +#define STATUS_CHANGE_PENDING (1 << 0) + +#define CCI_SLAVE_OFFSET(n) (0x1000 + 0x1000 * (n)) +#define CCI_SLAVE_A15 3 +#define CCI_SLAVE_A7 4 +#define CCI_A15_OFFSET CCI_SLAVE_OFFSET(CCI_SLAVE_A15) +#define CCI_A7_OFFSET CCI_SLAVE_OFFSET(CCI_SLAVE_A7) + + +ENTRY(tc2_resume) + mrc p15, 0, r0, c0, c0, 5 + ubfx r1, r0, #0, #4 @ r1 = cpu + ubfx r2, r0, #8, #4 @ r2 = cluster + add r1, r1, r2, lsl #2 @ r1 = index of CPU in WAKE_INT_STAT + ldr r3, =SPC_PHYS_BASE + SPC_WAKE_INT_STAT + ldr r3, [r3] + lsr r3, r1 + tst r3, #1 + wfieq @ if no pending IRQ reenters wfi + b mcpm_entry_point +ENDPROC(tc2_resume) + +/* + * Enable cluster-level coherency, in preparation for turning on the MMU. + * The ACTLR SMP bit does not need to be set here, because cpu_resume() + * already restores that. + */ + +ENTRY(tc2_pm_power_up_setup) + + cmp r0, #0 + beq 2f + + @ Enable CCI snoops + mrc p15, 0, r0, c0, c0, 5 @ MPIDR + ubfx r0, r0, #8, #4 @ cluster + ldr r3, =CCI_PHYS_BASE + CCI_A15_OFFSET + cmp r0, #0 @ A15 cluster? + addne r3, r3, #CCI_A7_OFFSET - CCI_A15_OFFSET + + @ r3 now points to the correct CCI slave register block + ldr r0, [r3, #SLAVE_SNOOPCTL_OFFSET] + orr r0, r0, #SNOOPCTL_SNOOP_ENABLE | SNOOPCTL_DVM_ENABLE + str r0, [r3, #SLAVE_SNOOPCTL_OFFSET] @ enable CCI snoops + + @ Wait for snoop control change to complete: + ldr r3, =CCI_PHYS_BASE +1: ldr r0, [r3, #CCI_STATUS_OFFSET] + tst r0, #STATUS_CHANGE_PENDING + bne 1b + + bx lr + +2: @ Clear the BX addr register + ldr r3, =SPC_PHYS_BASE + A15_BX_ADDR0 + mrc p15, 0, r0, c0, c0, 5 @ MPIDR + ubfx r1, r0, #8, #4 @ cluster + ubfx r0, r0, #0, #4 @ cpu + add r3, r3, r1, lsl #4 + mov r1, #0 + str r1, [r3, r0, lsl #2] + dsb + + bx lr + +ENDPROC(tc2_pm_power_up_setup) diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 915683cb67d..772b7a179dd 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -8,6 +8,7 @@ #include <linux/smp.h> #include <linux/init.h> #include <linux/irqchip.h> +#include <linux/memblock.h> #include <linux/of_address.h> #include <linux/of_fdt.h> #include <linux/of_irq.h> @@ -377,6 +378,31 @@ MACHINE_START(VEXPRESS, "ARM-Versatile Express") .restart = vexpress_restart, MACHINE_END +static void __init v2m_dt_hdlcd_init(void) +{ + struct device_node *node; + int len, na, ns; + const __be32 *prop; + phys_addr_t fb_base, fb_size; + + node = of_find_compatible_node(NULL, NULL, "arm,hdlcd"); + if (!node) + return; + + na = of_n_addr_cells(node); + ns = of_n_size_cells(node); + + prop = of_get_property(node, "framebuffer", &len); + if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop))) + return; + + fb_base = of_read_number(prop, na); + fb_size = of_read_number(prop + na, ns); + + if (WARN_ON(memblock_remove(fb_base, fb_size))) + return; +}; + static struct map_desc v2m_rs1_io_desc __initdata = { .virtual = V2M_PERIPH, .pfn = __phys_to_pfn(0x1c000000), @@ -427,6 +453,8 @@ void __init v2m_dt_init_early(void) pr_warning("vexpress: DT HBI (%x) is not matching " "hardware (%x)!\n", dt_hbi, hbi); } + + v2m_dt_hdlcd_init(); } static void __init v2m_dt_timer_init(void) @@ -476,6 +504,7 @@ static const char * const v2m_dt_match[] __initconst = { DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express") .dt_compat = v2m_dt_match, .smp = smp_ops(vexpress_smp_ops), + .smp_init = smp_init_ops(vexpress_smp_init_ops), .map_io = v2m_dt_map_io, .init_early = v2m_dt_init_early, .init_irq = irqchip_init, diff --git a/arch/arm/mach-virt/platsmp.c b/arch/arm/mach-virt/platsmp.c index 8badaabe70a..f4143f5bfa5 100644 --- a/arch/arm/mach-virt/platsmp.c +++ b/arch/arm/mach-virt/platsmp.c @@ -21,8 +21,6 @@ #include <linux/smp.h> #include <linux/of.h> -#include <linux/irqchip/arm-gic.h> - #include <asm/psci.h> #include <asm/smp_plat.h> @@ -45,14 +43,8 @@ static int __cpuinit virt_boot_secondary(unsigned int cpu, return -ENODEV; } -static void __cpuinit virt_secondary_init(unsigned int cpu) -{ - gic_secondary_init(0); -} - struct smp_operations __initdata virt_smp_ops = { .smp_init_cpus = virt_smp_init_cpus, .smp_prepare_cpus = virt_smp_prepare_cpus, - .smp_secondary_init = virt_secondary_init, .smp_boot_secondary = virt_boot_secondary, }; diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index cb812a13e29..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 @@ -476,9 +476,6 @@ config CPU_PABRT_V7 bool # The cache model -config CPU_CACHE_V3 - bool - config CPU_CACHE_V4 bool 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/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/fault.c b/arch/arm/mm/fault.c index 5dbf13f954f..e207aa5f846 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -446,8 +446,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr, if (pud_none(*pud_k)) goto bad_area; - if (!pud_present(*pud)) + if (!pud_present(*pud)) { set_pud(pud, *pud_k); + /* + * There is a small window during free_pgtables() where the + * user *pud entry is 0 but the TLB has not been invalidated + * and we get a level 2 (pmd) translation fault caused by the + * intermediate TLB caching of the old level 1 (pud) entry. + */ + flush_tlb_kernel_page(addr); + } pmd = pmd_offset(pud, addr); pmd_k = pmd_offset(pud_k, addr); @@ -470,8 +478,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, #endif if (pmd_none(pmd_k[index])) goto bad_area; + if (!pmd_present(pmd[index])) + copy_pmd(pmd, pmd_k); - copy_pmd(pmd, pmd_k); return 0; bad_area: diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index c6d45c87540..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 @@ -615,39 +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, @@ -658,7 +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); } @@ -1273,6 +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..5c07ee4fe3e 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -138,7 +138,7 @@ 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..2f76880060d 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -110,7 +110,9 @@ 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 + mrc p15, 0, r3, c0, c1, 7 @ read ID_MMFR3 + tst r3, #0xf << 20 @ check the coherent walk bits + mcreq p15, 0, r0, c7, c10, 1 @ clean D-cache to PoU #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..2098e026632 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -73,7 +73,9 @@ 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 + mrc p15, 0, r3, c0, c1, 7 @ read ID_MMFR3 + tst r3, #0xf << 20 @ check the coherent walk bits + mcreq p15, 0, r0, c7, c10, 1 @ clean D-cache to PoU #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..f584d3f5b37 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -420,7 +420,7 @@ __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 +430,25 @@ __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 diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 6828ef6ce80..a0bd8a755bd 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -576,7 +576,7 @@ load_ind: /* x = ((*(frame + k)) & 0xf) << 2; */ ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL; /* the interpreter should deal with the negative K */ - if (k < 0) + if ((int)k < 0) return -1; /* offset in r1: we might have to take the slow path */ emit_mov_i(r_off, k, ctx); diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c index f980cf3d2ba..5d205e74e49 100644 --- a/arch/arm/plat-samsung/irq-vic-timer.c +++ b/arch/arm/plat-samsung/irq-vic-timer.c @@ -16,6 +16,7 @@ #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> #include <linux/io.h> #include <mach/map.h> @@ -23,8 +24,6 @@ #include <plat/irq-vic-timer.h> #include <plat/regs-timer.h> -#include <asm/mach/irq.h> - static void s3c_irq_demux_vic_timer(unsigned int irq, struct irq_desc *desc) { struct irq_chip *chip = irq_get_chip(irq); diff --git a/arch/arm/plat-samsung/s5p-irq-gpioint.c b/arch/arm/plat-samsung/s5p-irq-gpioint.c index bae56131a50..fafdb059043 100644 --- a/arch/arm/plat-samsung/s5p-irq-gpioint.c +++ b/arch/arm/plat-samsung/s5p-irq-gpioint.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> #include <linux/io.h> #include <linux/gpio.h> #include <linux/slab.h> @@ -22,8 +23,6 @@ #include <plat/gpio-core.h> #include <plat/gpio-cfg.h> -#include <asm/mach/irq.h> - #define GPIO_BASE(chip) ((void __iomem *)((unsigned long)((chip)->base) & 0xFFFFF000u)) #define CON_OFFSET 0x700 diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c index f2ac1556177..1e1b2d76974 100644 --- a/arch/arm/plat-versatile/platsmp.c +++ b/arch/arm/plat-versatile/platsmp.c @@ -14,7 +14,6 @@ #include <linux/device.h> #include <linux/jiffies.h> #include <linux/smp.h> -#include <linux/irqchip/arm-gic.h> #include <asm/cacheflush.h> #include <asm/smp_plat.h> @@ -37,13 +36,6 @@ static DEFINE_SPINLOCK(boot_lock); void __cpuinit versatile_secondary_init(unsigned int cpu) { /* - * if any interrupts are already enabled for the primary - * core (e.g. timer irq), then they will not have been enabled - * for us: do so - */ - gic_secondary_init(0); - - /* * let the primary processor know we're out of the * pen, then head off into the C entry point */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index fd70a68387e..9b6d19f7407 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -9,7 +9,6 @@ config ARM64 select CLONE_BACKWARDS select COMMON_CLK select GENERIC_CLOCKEVENTS - select GENERIC_HARDIRQS_NO_DEPRECATED select GENERIC_IOMAP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index 51493430f14..1a6bfe954d4 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -6,17 +6,6 @@ config FRAME_POINTER bool default y -config DEBUG_ERRORS - bool "Verbose kernel error messages" - depends on DEBUG_KERNEL - help - This option controls verbose debugging information which can be - printed when the kernel detects an internal error. This debugging - information is useful to kernel hackers when tracking down problems, - but mostly meaningless to other people. It's safe to say Y unless - you are concerned with the code size or don't want to see these - messages. - config DEBUG_STACK_USAGE bool "Enable stack utilization instrumentation" depends on DEBUG_KERNEL diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 9212c7880da..09bef29f3a0 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -82,4 +82,3 @@ CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_INFO=y # CONFIG_FTRACE is not set CONFIG_ATOMIC64_SELFTEST=y -CONFIG_DEBUG_ERRORS=y diff --git a/arch/arm64/include/asm/ucontext.h b/arch/arm64/include/asm/ucontext.h index bde96072089..42e04c87742 100644 --- a/arch/arm64/include/asm/ucontext.h +++ b/arch/arm64/include/asm/ucontext.h @@ -22,7 +22,7 @@ struct ucontext { stack_t uc_stack; sigset_t uc_sigmask; /* glibc uses a 1024-bit sigset_t */ - __u8 __unused[(1024 - sizeof(sigset_t)) / 8]; + __u8 __unused[1024 / 8 - sizeof(sigset_t)]; /* last for future expansion */ struct sigcontext uc_mcontext; }; diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index cef3925eaf6..aa3e948f788 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -40,7 +40,9 @@ EXPORT_SYMBOL(__copy_to_user); EXPORT_SYMBOL(__clear_user); /* bitops */ +#ifdef CONFIG_SMP EXPORT_SYMBOL(__atomic_hash); +#endif /* physical memory */ EXPORT_SYMBOL(memstart_addr); diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 7f4f3673f2b..e393174fe85 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -549,7 +549,6 @@ int compat_setup_rt_frame(int usig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs) { struct compat_rt_sigframe __user *frame; - compat_stack_t stack; int err = 0; frame = compat_get_sigframe(ka, regs, sizeof(*frame)); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 224b44ab534..70b8cd4021c 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -261,7 +261,7 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt, void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt) { unsigned long size, mask; - bool page64k = IS_ENABLED(ARM64_64K_PAGES); + bool page64k = IS_ENABLED(CONFIG_ARM64_64K_PAGES); pgd_t *pgd; pud_t *pud; pmd_t *pmd; diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h index cf60d0a9f17..fc6483f83cc 100644 --- a/arch/avr32/include/asm/io.h +++ b/arch/avr32/include/asm/io.h @@ -165,6 +165,10 @@ BUILDIO_IOPORT(l, u32) #define readw_be __raw_readw #define readl_be __raw_readl +#define writeb_relaxed writeb +#define writew_relaxed writew +#define writel_relaxed writel + #define writeb_be __raw_writeb #define writew_be __raw_writew #define writel_be __raw_writel diff --git a/arch/c6x/include/asm/irqflags.h b/arch/c6x/include/asm/irqflags.h index cf78e09e18c..2c71d5634ec 100644 --- a/arch/c6x/include/asm/irqflags.h +++ b/arch/c6x/include/asm/irqflags.h @@ -27,7 +27,7 @@ static inline unsigned long arch_local_save_flags(void) /* set interrupt enabled status */ static inline void arch_local_irq_restore(unsigned long flags) { - asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags)); + asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags) : "memory"); } /* unconditionally enable interrupts */ diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index 77597e5ea60..79521d5499f 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -849,17 +849,6 @@ static palinfo_entry_t palinfo_entries[]={ #define NR_PALINFO_ENTRIES (int) ARRAY_SIZE(palinfo_entries) -/* - * this array is used to keep track of the proc entries we create. This is - * required in the module mode when we need to remove all entries. The procfs code - * does not do recursion of deletion - * - * Notes: - * - +1 accounts for the cpuN directory entry in /proc/pal - */ -#define NR_PALINFO_PROC_ENTRIES (NR_CPUS*(NR_PALINFO_ENTRIES+1)) - -static struct proc_dir_entry *palinfo_proc_entries[NR_PALINFO_PROC_ENTRIES]; static struct proc_dir_entry *palinfo_dir; /* @@ -971,60 +960,32 @@ palinfo_read_entry(char *page, char **start, off_t off, int count, int *eof, voi static void __cpuinit create_palinfo_proc_entries(unsigned int cpu) { -# define CPUSTR "cpu%d" - pal_func_cpu_u_t f; - struct proc_dir_entry **pdir; struct proc_dir_entry *cpu_dir; int j; - char cpustr[sizeof(CPUSTR)]; - - - /* - * we keep track of created entries in a depth-first order for - * cleanup purposes. Each entry is stored into palinfo_proc_entries - */ - sprintf(cpustr,CPUSTR, cpu); + char cpustr[3+4+1]; /* cpu numbers are up to 4095 on itanic */ + sprintf(cpustr, "cpu%d", cpu); cpu_dir = proc_mkdir(cpustr, palinfo_dir); + if (!cpu_dir) + return; f.req_cpu = cpu; - /* - * Compute the location to store per cpu entries - * We dont store the top level entry in this list, but - * remove it finally after removing all cpu entries. - */ - pdir = &palinfo_proc_entries[cpu*(NR_PALINFO_ENTRIES+1)]; - *pdir++ = cpu_dir; for (j=0; j < NR_PALINFO_ENTRIES; j++) { f.func_id = j; - *pdir = create_proc_read_entry( - palinfo_entries[j].name, 0, cpu_dir, - palinfo_read_entry, (void *)f.value); - pdir++; + create_proc_read_entry( + palinfo_entries[j].name, 0, cpu_dir, + palinfo_read_entry, (void *)f.value); } } static void remove_palinfo_proc_entries(unsigned int hcpu) { - int j; - struct proc_dir_entry *cpu_dir, **pdir; - - pdir = &palinfo_proc_entries[hcpu*(NR_PALINFO_ENTRIES+1)]; - cpu_dir = *pdir; - *pdir++=NULL; - for (j=0; j < (NR_PALINFO_ENTRIES); j++) { - if ((*pdir)) { - remove_proc_entry ((*pdir)->name, cpu_dir); - *pdir ++= NULL; - } - } - - if (cpu_dir) { - remove_proc_entry(cpu_dir->name, palinfo_dir); - } + char cpustr[3+4+1]; /* cpu numbers are up to 4095 on itanic */ + sprintf(cpustr, "cpu%d", hcpu); + remove_proc_subtree(cpustr, palinfo_dir); } static int __cpuinit palinfo_cpu_callback(struct notifier_block *nfb, @@ -1058,6 +1019,8 @@ palinfo_init(void) printk(KERN_INFO "PAL Information Facility v%s\n", PALINFO_VERSION); palinfo_dir = proc_mkdir("pal", NULL); + if (!palinfo_dir) + return -ENOMEM; /* Create palinfo dirs in /proc for all online cpus */ for_each_online_cpu(i) { @@ -1073,22 +1036,8 @@ palinfo_init(void) static void __exit palinfo_exit(void) { - int i = 0; - - /* remove all nodes: depth first pass. Could optimize this */ - for_each_online_cpu(i) { - remove_palinfo_proc_entries(i); - } - - /* - * Remove the top level entry finally - */ - remove_proc_entry(palinfo_dir->name, NULL); - - /* - * Unregister from cpu notifier callbacks - */ unregister_hotcpu_notifier(&palinfo_cpu_notifier); + remove_proc_subtree("pal", NULL); } module_init(palinfo_init); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index e34f565f595..6f7dc8b7b35 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -291,7 +291,6 @@ cpu_idle (void) } if (!need_resched()) { - void (*idle)(void); #ifdef CONFIG_SMP min_xtp(); #endif @@ -299,9 +298,7 @@ cpu_idle (void) if (mark_idle) (*mark_idle)(1); - if (!idle) - idle = default_idle; - (*idle)(); + default_idle(); if (mark_idle) (*mark_idle)(0); #ifdef CONFIG_SMP diff --git a/arch/m68k/include/asm/gpio.h b/arch/m68k/include/asm/gpio.h index 4395ffc51fd..8cc83431805 100644 --- a/arch/m68k/include/asm/gpio.h +++ b/arch/m68k/include/asm/gpio.h @@ -86,4 +86,24 @@ static inline int gpio_cansleep(unsigned gpio) return gpio < MCFGPIO_PIN_MAX ? 0 : __gpio_cansleep(gpio); } +static inline int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) +{ + int err; + + err = gpio_request(gpio, label); + if (err) + return err; + + if (flags & GPIOF_DIR_IN) + err = gpio_direction_input(gpio); + else + err = gpio_direction_output(gpio, + (flags & GPIOF_INIT_HIGH) ? 1 : 0); + + if (err) + gpio_free(gpio); + + return err; +} + #endif diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index cd2e21ff562..51244bf9727 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -18,7 +18,7 @@ config MIPS select HAVE_KRETPROBES select HAVE_DEBUG_KMEMLEAK select ARCH_BINFMT_ELF_RANDOMIZE_PIE - select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT select RTC_LIB if !MACH_LOONGSON select GENERIC_ATOMIC64 if !64BIT select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE @@ -657,7 +657,7 @@ config SNI_RM bool "SNI RM200/300/400" select FW_ARC if CPU_LITTLE_ENDIAN select FW_ARC32 if CPU_LITTLE_ENDIAN - select SNIPROM if CPU_BIG_ENDIAN + select FW_SNIPROM if CPU_BIG_ENDIAN select ARCH_MAY_HAVE_PC_FDC select BOOT_ELF32 select CEVT_R4K @@ -1144,7 +1144,7 @@ config DEFAULT_SGI_PARTITION config FW_ARC32 bool -config SNIPROM +config FW_SNIPROM bool config BOOT_ELF32 @@ -1493,7 +1493,6 @@ config CPU_XLP select CPU_SUPPORTS_32BIT_KERNEL select CPU_SUPPORTS_64BIT_KERNEL select CPU_SUPPORTS_HIGHMEM - select CPU_HAS_LLSC select WEAK_ORDERING select WEAK_REORDERING_BEYOND_LLSC select CPU_HAS_PREFETCH diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index ed1949c2950..9aa7d44898e 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -745,10 +745,7 @@ void __init board_prom_init(void) strcpy(cfe_version, "unknown"); printk(KERN_INFO PFX "CFE version: %s\n", cfe_version); - if (bcm63xx_nvram_init(boot_addr + BCM963XX_NVRAM_OFFSET)) { - printk(KERN_ERR PFX "invalid nvram checksum\n"); - return; - } + bcm63xx_nvram_init(boot_addr + BCM963XX_NVRAM_OFFSET); board_name = bcm63xx_nvram_get_name(); /* find board by name */ diff --git a/arch/mips/bcm63xx/nvram.c b/arch/mips/bcm63xx/nvram.c index 62061168083..a4b8864f930 100644 --- a/arch/mips/bcm63xx/nvram.c +++ b/arch/mips/bcm63xx/nvram.c @@ -38,7 +38,7 @@ struct bcm963xx_nvram { static struct bcm963xx_nvram nvram; static int mac_addr_used; -int __init bcm63xx_nvram_init(void *addr) +void __init bcm63xx_nvram_init(void *addr) { unsigned int check_len; u32 crc, expected_crc; @@ -60,9 +60,8 @@ int __init bcm63xx_nvram_init(void *addr) crc = crc32_le(~0, (u8 *)&nvram, check_len); if (crc != expected_crc) - return -EINVAL; - - return 0; + pr_warn("nvram checksum failed, contents may be invalid (expected %08x, got %08x)\n", + expected_crc, crc); } u8 *bcm63xx_nvram_get_name(void) diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c index 314231be788..35e18e98beb 100644 --- a/arch/mips/bcm63xx/setup.c +++ b/arch/mips/bcm63xx/setup.c @@ -157,4 +157,4 @@ int __init bcm63xx_register_devices(void) return board_register_devices(); } -device_initcall(bcm63xx_register_devices); +arch_initcall(bcm63xx_register_devices); diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index c594a3d4f74..b0baa299f89 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -174,7 +174,10 @@ static int octeon_kexec_prepare(struct kimage *image) static void octeon_generic_shutdown(void) { - int cpu, i; + int i; +#ifdef CONFIG_SMP + int cpu; +#endif struct cvmx_bootmem_desc *bootmem_desc; void *named_block_array_ptr; diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h index 62d6a3b4d3b..4e0b6bc1165 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h @@ -9,10 +9,8 @@ * * Initialized the local nvram copy from the target address and checks * its checksum. - * - * Returns 0 on success. */ -int __init bcm63xx_nvram_init(void *nvram); +void bcm63xx_nvram_init(void *nvram); /** * bcm63xx_nvram_get_name() - returns the board name according to nvram diff --git a/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h b/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h index d9c82841903..193c0912d38 100644 --- a/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h @@ -28,11 +28,7 @@ /* #define cpu_has_prefetch ? */ #define cpu_has_mcheck 1 /* #define cpu_has_ejtag ? */ -#ifdef CONFIG_CPU_HAS_LLSC #define cpu_has_llsc 1 -#else -#define cpu_has_llsc 0 -#endif /* #define cpu_has_vtag_icache ? */ /* #define cpu_has_dc_aliases ? */ /* #define cpu_has_ic_fills_f_dc ? */ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 12b70c25906..0da44d422f5 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -1166,7 +1166,10 @@ do { \ unsigned int __dspctl; \ \ __asm__ __volatile__( \ + " .set push \n" \ + " .set dsp \n" \ " rddsp %0, %x1 \n" \ + " .set pop \n" \ : "=r" (__dspctl) \ : "i" (mask)); \ __dspctl; \ @@ -1175,30 +1178,198 @@ do { \ #define wrdsp(val, mask) \ do { \ __asm__ __volatile__( \ + " .set push \n" \ + " .set dsp \n" \ " wrdsp %0, %x1 \n" \ + " .set pop \n" \ : \ : "r" (val), "i" (mask)); \ } while (0) -#define mflo0() ({ long mflo0; __asm__("mflo %0, $ac0" : "=r" (mflo0)); mflo0;}) -#define mflo1() ({ long mflo1; __asm__("mflo %0, $ac1" : "=r" (mflo1)); mflo1;}) -#define mflo2() ({ long mflo2; __asm__("mflo %0, $ac2" : "=r" (mflo2)); mflo2;}) -#define mflo3() ({ long mflo3; __asm__("mflo %0, $ac3" : "=r" (mflo3)); mflo3;}) - -#define mfhi0() ({ long mfhi0; __asm__("mfhi %0, $ac0" : "=r" (mfhi0)); mfhi0;}) -#define mfhi1() ({ long mfhi1; __asm__("mfhi %0, $ac1" : "=r" (mfhi1)); mfhi1;}) -#define mfhi2() ({ long mfhi2; __asm__("mfhi %0, $ac2" : "=r" (mfhi2)); mfhi2;}) -#define mfhi3() ({ long mfhi3; __asm__("mfhi %0, $ac3" : "=r" (mfhi3)); mfhi3;}) - -#define mtlo0(x) __asm__("mtlo %0, $ac0" ::"r" (x)) -#define mtlo1(x) __asm__("mtlo %0, $ac1" ::"r" (x)) -#define mtlo2(x) __asm__("mtlo %0, $ac2" ::"r" (x)) -#define mtlo3(x) __asm__("mtlo %0, $ac3" ::"r" (x)) - -#define mthi0(x) __asm__("mthi %0, $ac0" ::"r" (x)) -#define mthi1(x) __asm__("mthi %0, $ac1" ::"r" (x)) -#define mthi2(x) __asm__("mthi %0, $ac2" ::"r" (x)) -#define mthi3(x) __asm__("mthi %0, $ac3" ::"r" (x)) +#define mflo0() \ +({ \ + long mflo0; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mflo %0, $ac0 \n" \ + " .set pop \n" \ + : "=r" (mflo0)); \ + mflo0; \ +}) + +#define mflo1() \ +({ \ + long mflo1; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mflo %0, $ac1 \n" \ + " .set pop \n" \ + : "=r" (mflo1)); \ + mflo1; \ +}) + +#define mflo2() \ +({ \ + long mflo2; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mflo %0, $ac2 \n" \ + " .set pop \n" \ + : "=r" (mflo2)); \ + mflo2; \ +}) + +#define mflo3() \ +({ \ + long mflo3; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mflo %0, $ac3 \n" \ + " .set pop \n" \ + : "=r" (mflo3)); \ + mflo3; \ +}) + +#define mfhi0() \ +({ \ + long mfhi0; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mfhi %0, $ac0 \n" \ + " .set pop \n" \ + : "=r" (mfhi0)); \ + mfhi0; \ +}) + +#define mfhi1() \ +({ \ + long mfhi1; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mfhi %0, $ac1 \n" \ + " .set pop \n" \ + : "=r" (mfhi1)); \ + mfhi1; \ +}) + +#define mfhi2() \ +({ \ + long mfhi2; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mfhi %0, $ac2 \n" \ + " .set pop \n" \ + : "=r" (mfhi2)); \ + mfhi2; \ +}) + +#define mfhi3() \ +({ \ + long mfhi3; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mfhi %0, $ac3 \n" \ + " .set pop \n" \ + : "=r" (mfhi3)); \ + mfhi3; \ +}) + + +#define mtlo0(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mtlo %0, $ac0 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mtlo1(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mtlo %0, $ac1 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mtlo2(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mtlo %0, $ac2 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mtlo3(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mtlo %0, $ac3 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mthi0(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mthi %0, $ac0 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mthi1(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mthi %0, $ac1 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mthi2(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mthi %0, $ac2 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mthi3(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mthi %0, $ac3 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) #else diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 99fc547af9d..eab99e536b5 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -31,7 +31,7 @@ #define PAGE_SHIFT 16 #endif #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) +#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1)) #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT #define HPAGE_SHIFT (PAGE_SHIFT + PAGE_SHIFT - 3) diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h index 197f6367c20..8efe5a9e2c3 100644 --- a/arch/mips/include/asm/signal.h +++ b/arch/mips/include/asm/signal.h @@ -21,6 +21,6 @@ #include <asm/sigcontext.h> #include <asm/siginfo.h> -#define __ARCH_HAS_ODD_SIGACTION +#define __ARCH_HAS_IRIX_SIGACTION #endif /* _ASM_SIGNAL_H */ diff --git a/arch/mips/include/uapi/asm/signal.h b/arch/mips/include/uapi/asm/signal.h index d6b18b4d0f3..addb9f556b7 100644 --- a/arch/mips/include/uapi/asm/signal.h +++ b/arch/mips/include/uapi/asm/signal.h @@ -72,6 +72,12 @@ typedef unsigned long old_sigset_t; /* at least 32 bits */ * * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single * Unix names RESETHAND and NODEFER respectively. + * + * SA_RESTORER used to be defined as 0x04000000 but only the O32 ABI ever + * supported its use and no libc was using it, so the entire sa-restorer + * functionality was removed with lmo commit 39bffc12c3580ab for 2.5.48 + * retaining only the SA_RESTORER definition as a reminder to avoid + * accidental reuse of the mask bit. */ #define SA_ONSTACK 0x08000000 #define SA_RESETHAND 0x80000000 @@ -84,8 +90,6 @@ typedef unsigned long old_sigset_t; /* at least 32 bits */ #define SA_NOMASK SA_NODEFER #define SA_ONESHOT SA_RESETHAND -#define SA_RESTORER 0x04000000 /* Only for o32 */ - #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index f81d98f6184..de75fb50562 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -100,29 +100,16 @@ obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_mipsxx.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o # -# DSP ASE supported for MIPS32 or MIPS64 Release 2 cores only. It is safe -# to enable DSP assembler support here even if the MIPS Release 2 CPU we -# are targetting does not support DSP because all code-paths making use of -# it properly check that the running CPU *actually does* support these -# instructions. +# DSP ASE supported for MIPS32 or MIPS64 Release 2 cores only. It is not +# safe to unconditionnaly use the assembler -mdsp / -mdspr2 switches +# here because the compiler may use DSP ASE instructions (such as lwx) in +# code paths where we cannot check that the CPU we are running on supports it. +# Proper abstraction using HAVE_AS_DSP and macros is done in +# arch/mips/include/asm/mipsregs.h. # ifeq ($(CONFIG_CPU_MIPSR2), y) CFLAGS_DSP = -DHAVE_AS_DSP -# -# Check if assembler supports DSP ASE -# -ifeq ($(call cc-option-yn,-mdsp), y) -CFLAGS_DSP += -mdsp -endif - -# -# Check if assembler supports DSP ASE Rev2 -# -ifeq ($(call cc-option-yn,-mdspr2), y) -CFLAGS_DSP += -mdspr2 -endif - CFLAGS_signal.o = $(CFLAGS_DSP) CFLAGS_signal32.o = $(CFLAGS_DSP) CFLAGS_process.o = $(CFLAGS_DSP) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6bfccc227a9..5fe66a0c322 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -580,6 +580,9 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) c->tlbsize = 48; break; case PRID_IMP_VR41XX: + set_isa(c, MIPS_CPU_ISA_III); + c->options = R4K_OPTS; + c->tlbsize = 32; switch (c->processor_id & 0xf0) { case PRID_REV_VR4111: c->cputype = CPU_VR4111; @@ -604,6 +607,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) __cpu_name[cpu] = "NEC VR4131"; } else { c->cputype = CPU_VR4133; + c->options |= MIPS_CPU_LLSC; __cpu_name[cpu] = "NEC VR4133"; } break; @@ -613,9 +617,6 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) __cpu_name[cpu] = "NEC Vr41xx"; break; } - set_isa(c, MIPS_CPU_ISA_III); - c->options = R4K_OPTS; - c->tlbsize = 32; break; case PRID_IMP_R4300: c->cputype = CPU_R4300; @@ -1226,10 +1227,8 @@ __cpuinit void cpu_probe(void) if (c->options & MIPS_CPU_FPU) { c->fpu_id = cpu_get_fpu_id(); - if (c->isa_level == MIPS_CPU_ISA_M32R1 || - c->isa_level == MIPS_CPU_ISA_M32R2 || - c->isa_level == MIPS_CPU_ISA_M64R1 || - c->isa_level == MIPS_CPU_ISA_M64R2) { + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 | + MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) { if (c->fpu_id & MIPS_FPIR_3D) c->ases |= MIPS_ASE_MIPS3D; } diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 8eeee1c860c..db9655f0889 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -171,7 +171,7 @@ SYSCALL_DEFINE6(32_ipc, u32, call, long, first, long, second, long, third, err = compat_sys_shmctl(first, second, compat_ptr(ptr)); break; default: - err = -EINVAL; + err = -ENOSYS; break; } diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index 16586767335..33d067148e6 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -46,10 +46,9 @@ PTR_L a5, PT_R9(sp) PTR_L a6, PT_R10(sp) PTR_L a7, PT_R11(sp) -#else - PTR_ADDIU sp, PT_SIZE #endif -.endm + PTR_ADDIU sp, PT_SIZE + .endm .macro RETURN_BACK jr ra @@ -68,7 +67,11 @@ NESTED(ftrace_caller, PT_SIZE, ra) .globl _mcount _mcount: b ftrace_stub - addiu sp,sp,8 +#ifdef CONFIG_32BIT + addiu sp,sp,8 +#else + nop +#endif /* When tracing is activated, it calls ftrace_caller+8 (aka here) */ lw t1, function_trace_stop diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 135c4aadccb..7a54f74b781 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -67,7 +67,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has_mips_r) { seq_printf(m, "isa\t\t\t:"); if (cpu_has_mips_1) - seq_printf(m, "%s", "mips1"); + seq_printf(m, "%s", " mips1"); if (cpu_has_mips_2) seq_printf(m, "%s", " mips2"); if (cpu_has_mips_3) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index a200b5bdbb8..c3abb88170f 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1571,7 +1571,7 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu) #ifdef CONFIG_64BIT status_set |= ST0_FR|ST0_KX|ST0_SX|ST0_UX; #endif - if (current_cpu_data.isa_level == MIPS_CPU_ISA_IV) + if (current_cpu_data.isa_level & MIPS_CPU_ISA_IV) status_set |= ST0_XX; if (cpu_has_dsp) status_set |= ST0_MX; diff --git a/arch/mips/lib/bitops.c b/arch/mips/lib/bitops.c index 81f1dcfdcab..a64daee740e 100644 --- a/arch/mips/lib/bitops.c +++ b/arch/mips/lib/bitops.c @@ -90,12 +90,12 @@ int __mips_test_and_set_bit(unsigned long nr, unsigned bit = nr & SZLONG_MASK; unsigned long mask; unsigned long flags; - unsigned long res; + int res; a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); - res = (mask & *a); + res = (mask & *a) != 0; *a |= mask; raw_local_irq_restore(flags); return res; @@ -116,12 +116,12 @@ int __mips_test_and_set_bit_lock(unsigned long nr, unsigned bit = nr & SZLONG_MASK; unsigned long mask; unsigned long flags; - unsigned long res; + int res; a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); - res = (mask & *a); + res = (mask & *a) != 0; *a |= mask; raw_local_irq_restore(flags); return res; @@ -141,12 +141,12 @@ int __mips_test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) unsigned bit = nr & SZLONG_MASK; unsigned long mask; unsigned long flags; - unsigned long res; + int res; a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); - res = (mask & *a); + res = (mask & *a) != 0; *a &= ~mask; raw_local_irq_restore(flags); return res; @@ -166,12 +166,12 @@ int __mips_test_and_change_bit(unsigned long nr, volatile unsigned long *addr) unsigned bit = nr & SZLONG_MASK; unsigned long mask; unsigned long flags; - unsigned long res; + int res; a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); - res = (mask & *a); + res = (mask & *a) != 0; *a ^= mask; raw_local_irq_restore(flags); return res; diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S index 507147aebd4..a6adffbb4e5 100644 --- a/arch/mips/lib/csum_partial.S +++ b/arch/mips/lib/csum_partial.S @@ -270,7 +270,7 @@ LEAF(csum_partial) #endif /* odd buffer alignment? */ -#ifdef CPU_MIPSR2 +#ifdef CONFIG_CPU_MIPSR2 wsbh v1, sum movn sum, v1, t7 #else @@ -670,7 +670,7 @@ EXC( sb t0, NBYTES-2(dst), .Ls_exc) addu sum, v1 #endif -#ifdef CPU_MIPSR2 +#ifdef CONFIG_CPU_MIPSR2 wsbh v1, sum movn sum, v1, odd #else diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index ecca559b8d7..2078915eacb 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1247,10 +1247,8 @@ static void __cpuinit setup_scache(void) return; default: - if (c->isa_level == MIPS_CPU_ISA_M32R1 || - c->isa_level == MIPS_CPU_ISA_M32R2 || - c->isa_level == MIPS_CPU_ISA_M64R1 || - c->isa_level == MIPS_CPU_ISA_M64R2) { + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 | + MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) { #ifdef CONFIG_MIPS_CPU_SCACHE if (mips_sc_init ()) { scache_size = c->scache.ways * c->scache.sets * c->scache.linesz; diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 93d937b4b1b..df96da7e939 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -98,10 +98,8 @@ static inline int __init mips_sc_probe(void) c->scache.flags |= MIPS_CACHE_NOT_PRESENT; /* Ignore anything but MIPSxx processors */ - if (c->isa_level != MIPS_CPU_ISA_M32R1 && - c->isa_level != MIPS_CPU_ISA_M32R2 && - c->isa_level != MIPS_CPU_ISA_M64R1 && - c->isa_level != MIPS_CPU_ISA_M64R2) + if (!(c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 | + MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2))) return 0; /* Does this MIPS32/MIPS64 CPU have a config2 register? */ diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c index 38a80c83fd6..d1faece21b6 100644 --- a/arch/mips/pci/pci-alchemy.c +++ b/arch/mips/pci/pci-alchemy.c @@ -19,7 +19,7 @@ #include <asm/mach-au1x00/au1000.h> #include <asm/tlbmisc.h> -#ifdef CONFIG_DEBUG_PCI +#ifdef CONFIG_PCI_DEBUG #define DBG(x...) printk(KERN_DEBUG x) #else #define DBG(x...) do {} while (0) @@ -162,7 +162,7 @@ static int config_access(unsigned char access_type, struct pci_bus *bus, if (status & (1 << 29)) { *data = 0xffffffff; error = -1; - DBG("alchemy-pci: master abort on cfg access %d bus %d dev %d", + DBG("alchemy-pci: master abort on cfg access %d bus %d dev %d\n", access_type, bus->number, device); } else if ((status >> 28) & 0xf) { DBG("alchemy-pci: PCI ERR detected: dev %d, status %lx\n", diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 01d95e2f058..113e2820650 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -65,8 +65,10 @@ ifndef CONFIG_FUNCTION_TRACER endif # Use long jumps instead of long branches (needed if your linker fails to -# link a too big vmlinux executable) -cflags-$(CONFIG_MLONGCALLS) += -mlong-calls +# link a too big vmlinux executable). Not enabled for building modules. +ifdef CONFIG_MLONGCALLS +KBUILD_CFLAGS_KERNEL += -mlong-calls +endif # select which processor to optimise for cflags-$(CONFIG_PA7100) += -march=1.1 -mschedule=7100 diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 79f694f3ad9..f0e2784e7cc 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -140,7 +140,10 @@ static inline void *kmap(struct page *page) return page_address(page); } -#define kunmap(page) kunmap_parisc(page_address(page)) +static inline void kunmap(struct page *page) +{ + kunmap_parisc(page_address(page)); +} static inline void *kmap_atomic(struct page *page) { diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 7df49fad29f..1e40d7f86be 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -16,6 +16,8 @@ #include <asm/processor.h> #include <asm/cache.h> +extern spinlock_t pa_dbit_lock; + /* * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel * memory. For the return value to be meaningful, ADDR must be >= @@ -44,8 +46,11 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long); #define set_pte_at(mm, addr, ptep, pteval) \ do { \ + unsigned long flags; \ + spin_lock_irqsave(&pa_dbit_lock, flags); \ set_pte(ptep, pteval); \ purge_tlb_entries(mm, addr); \ + spin_unlock_irqrestore(&pa_dbit_lock, flags); \ } while (0) #endif /* !__ASSEMBLY__ */ @@ -435,48 +440,46 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { -#ifdef CONFIG_SMP + pte_t pte; + unsigned long flags; + if (!pte_young(*ptep)) return 0; - return test_and_clear_bit(xlate_pabit(_PAGE_ACCESSED_BIT), &pte_val(*ptep)); -#else - pte_t pte = *ptep; - if (!pte_young(pte)) + + spin_lock_irqsave(&pa_dbit_lock, flags); + pte = *ptep; + if (!pte_young(pte)) { + spin_unlock_irqrestore(&pa_dbit_lock, flags); return 0; - set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte)); + } + set_pte(ptep, pte_mkold(pte)); + purge_tlb_entries(vma->vm_mm, addr); + spin_unlock_irqrestore(&pa_dbit_lock, flags); return 1; -#endif } -extern spinlock_t pa_dbit_lock; - struct mm_struct; static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t old_pte; + unsigned long flags; - spin_lock(&pa_dbit_lock); + spin_lock_irqsave(&pa_dbit_lock, flags); old_pte = *ptep; pte_clear(mm,addr,ptep); - spin_unlock(&pa_dbit_lock); + purge_tlb_entries(mm, addr); + spin_unlock_irqrestore(&pa_dbit_lock, flags); return old_pte; } static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { -#ifdef CONFIG_SMP - unsigned long new, old; - - do { - old = pte_val(*ptep); - new = pte_val(pte_wrprotect(__pte (old))); - } while (cmpxchg((unsigned long *) ptep, old, new) != old); + unsigned long flags; + spin_lock_irqsave(&pa_dbit_lock, flags); + set_pte(ptep, pte_wrprotect(*ptep)); purge_tlb_entries(mm, addr); -#else - pte_t old_pte = *ptep; - set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); -#endif + spin_unlock_irqrestore(&pa_dbit_lock, flags); } #define pte_same(A,B) (pte_val(A) == pte_val(B)) diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 4ba2c93770f..e0a82358517 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -181,30 +181,24 @@ struct exception_data { #if !defined(CONFIG_64BIT) #define __put_kernel_asm64(__val,ptr) do { \ - u64 __val64 = (u64)(__val); \ - u32 hi = (__val64) >> 32; \ - u32 lo = (__val64) & 0xffffffff; \ __asm__ __volatile__ ( \ "\n1:\tstw %2,0(%1)" \ - "\n2:\tstw %3,4(%1)\n\t" \ + "\n2:\tstw %R2,4(%1)\n\t" \ ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\ ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\ : "=r"(__pu_err) \ - : "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \ + : "r"(ptr), "r"(__val), "0"(__pu_err) \ : "r1"); \ } while (0) #define __put_user_asm64(__val,ptr) do { \ - u64 __val64 = (u64)(__val); \ - u32 hi = (__val64) >> 32; \ - u32 lo = (__val64) & 0xffffffff; \ __asm__ __volatile__ ( \ "\n1:\tstw %2,0(%%sr3,%1)" \ - "\n2:\tstw %3,4(%%sr3,%1)\n\t" \ + "\n2:\tstw %R2,4(%%sr3,%1)\n\t" \ ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\ ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\ : "=r"(__pu_err) \ - : "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \ + : "r"(ptr), "r"(__val), "0"(__pu_err) \ : "r1"); \ } while (0) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 4b12890642e..83ded26cad0 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -421,14 +421,11 @@ void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) /* Note: purge_tlb_entries can be called at startup with no context. */ - /* Disable preemption while we play with %sr1. */ - preempt_disable(); - mtsp(mm->context, 1); purge_tlb_start(flags); + mtsp(mm->context, 1); pdtlb(addr); pitlb(addr); purge_tlb_end(flags); - preempt_enable(); } EXPORT_SYMBOL(purge_tlb_entries); diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 6795dc6c995..568b2c61ea0 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -120,11 +120,13 @@ extern void __ashrdi3(void); extern void __ashldi3(void); extern void __lshrdi3(void); extern void __muldi3(void); +extern void __ucmpdi2(void); EXPORT_SYMBOL(__ashrdi3); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__muldi3); +EXPORT_SYMBOL(__ucmpdi2); asmlinkage void * __canonicalize_funcptr_for_compare(void *); EXPORT_SYMBOL(__canonicalize_funcptr_for_compare); diff --git a/arch/parisc/lib/Makefile b/arch/parisc/lib/Makefile index 5f2e6904d14..5651536ac73 100644 --- a/arch/parisc/lib/Makefile +++ b/arch/parisc/lib/Makefile @@ -2,6 +2,7 @@ # Makefile for parisc-specific library files # -lib-y := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o +lib-y := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o \ + ucmpdi2.o obj-y := iomap.o diff --git a/arch/parisc/lib/ucmpdi2.c b/arch/parisc/lib/ucmpdi2.c new file mode 100644 index 00000000000..149c016f32c --- /dev/null +++ b/arch/parisc/lib/ucmpdi2.c @@ -0,0 +1,25 @@ +#include <linux/module.h> + +union ull_union { + unsigned long long ull; + struct { + unsigned int high; + unsigned int low; + } ui; +}; + +int __ucmpdi2(unsigned long long a, unsigned long long b) +{ + union ull_union au = {.ull = a}; + union ull_union bu = {.ull = b}; + + if (au.ui.high < bu.ui.high) + return 0; + else if (au.ui.high > bu.ui.high) + return 2; + if (au.ui.low < bu.ui.low) + return 0; + else if (au.ui.low > bu.ui.low) + return 2; + return 1; +} diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 80821512e9c..ea5bb045983 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -90,6 +90,7 @@ config GENERIC_GPIO config PPC bool default y + select BINFMT_ELF select OF select OF_EARLY_FLATTREE select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 2fdb47a19ef..b59e06f507e 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -343,17 +343,16 @@ extern void slb_set_size(u16 size); /* * VSID allocation (256MB segment) * - * We first generate a 38-bit "proto-VSID". For kernel addresses this - * is equal to the ESID | 1 << 37, for user addresses it is: - * (context << USER_ESID_BITS) | (esid & ((1U << USER_ESID_BITS) - 1) + * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated + * from mmu context id and effective segment id of the address. * - * This splits the proto-VSID into the below range - * 0 - (2^(CONTEXT_BITS + USER_ESID_BITS) - 1) : User proto-VSID range - * 2^(CONTEXT_BITS + USER_ESID_BITS) - 2^(VSID_BITS) : Kernel proto-VSID range - * - * We also have CONTEXT_BITS + USER_ESID_BITS = VSID_BITS - 1 - * That is, we assign half of the space to user processes and half - * to the kernel. + * For user processes max context id is limited to ((1ul << 19) - 5) + * for kernel space, we use the top 4 context ids to map address as below + * NOTE: each context only support 64TB now. + * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] * * The proto-VSIDs are then scrambled into real VSIDs with the * multiplicative hash: @@ -363,41 +362,49 @@ extern void slb_set_size(u16 size); * VSID_MULTIPLIER is prime, so in particular it is * co-prime to VSID_MODULUS, making this a 1:1 scrambling function. * Because the modulus is 2^n-1 we can compute it efficiently without - * a divide or extra multiply (see below). - * - * This scheme has several advantages over older methods: - * - * - We have VSIDs allocated for every kernel address - * (i.e. everything above 0xC000000000000000), except the very top - * segment, which simplifies several things. + * a divide or extra multiply (see below). The scramble function gives + * robust scattering in the hash table (at least based on some initial + * results). * - * - We allow for USER_ESID_BITS significant bits of ESID and - * CONTEXT_BITS bits of context for user addresses. - * i.e. 64T (46 bits) of address space for up to half a million contexts. + * We also consider VSID 0 special. We use VSID 0 for slb entries mapping + * bad address. This enables us to consolidate bad address handling in + * hash_page. * - * - The scramble function gives robust scattering in the hash - * table (at least based on some initial results). The previous - * method was more susceptible to pathological cases giving excessive - * hash collisions. + * We also need to avoid the last segment of the last context, because that + * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 + * because of the modulo operation in vsid scramble. But the vmemmap + * (which is what uses region 0xf) will never be close to 64TB in size + * (it's 56 bytes per page of system memory). */ +#define CONTEXT_BITS 19 +#define ESID_BITS 18 +#define ESID_BITS_1T 6 + +/* + * 256MB segment + * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments + * available for user + kernel mapping. The top 4 contexts are used for + * kernel mapping. Each segment contains 2^28 bytes. Each + * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts + * (19 == 37 + 28 - 46). + */ +#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 5) + /* * This should be computed such that protovosid * vsid_mulitplier * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus */ #define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_256M 38 +#define VSID_BITS_256M (CONTEXT_BITS + ESID_BITS) #define VSID_MODULUS_256M ((1UL<<VSID_BITS_256M)-1) #define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */ -#define VSID_BITS_1T 26 +#define VSID_BITS_1T (CONTEXT_BITS + ESID_BITS_1T) #define VSID_MODULUS_1T ((1UL<<VSID_BITS_1T)-1) -#define CONTEXT_BITS 19 -#define USER_ESID_BITS 18 -#define USER_ESID_BITS_1T 6 -#define USER_VSID_RANGE (1UL << (USER_ESID_BITS + SID_SHIFT)) +#define USER_VSID_RANGE (1UL << (ESID_BITS + SID_SHIFT)) /* * This macro generates asm code to compute the VSID scramble @@ -421,7 +428,8 @@ extern void slb_set_size(u16 size); srdi rx,rt,VSID_BITS_##size; \ clrldi rt,rt,(64-VSID_BITS_##size); \ add rt,rt,rx; /* add high and low bits */ \ - /* Now, r3 == VSID (mod 2^36-1), and lies between 0 and \ + /* NOTE: explanation based on VSID_BITS_##size = 36 \ + * Now, r3 == VSID (mod 2^36-1), and lies between 0 and \ * 2^36-1+2^28-1. That in particular means that if r3 >= \ * 2^36-1, then r3+1 has the 2^36 bit set. So, if r3+1 has \ * the bit clear, r3 already has the answer we want, if it \ @@ -513,34 +521,6 @@ typedef struct { }) #endif /* 1 */ -/* - * This is only valid for addresses >= PAGE_OFFSET - * The proto-VSID space is divided into two class - * User: 0 to 2^(CONTEXT_BITS + USER_ESID_BITS) -1 - * kernel: 2^(CONTEXT_BITS + USER_ESID_BITS) to 2^(VSID_BITS) - 1 - * - * With KERNEL_START at 0xc000000000000000, the proto vsid for - * the kernel ends up with 0xc00000000 (36 bits). With 64TB - * support we need to have kernel proto-VSID in the - * [2^37 to 2^38 - 1] range due to the increased USER_ESID_BITS. - */ -static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) -{ - unsigned long proto_vsid; - /* - * We need to make sure proto_vsid for the kernel is - * >= 2^(CONTEXT_BITS + USER_ESID_BITS[_1T]) - */ - if (ssize == MMU_SEGSIZE_256M) { - proto_vsid = ea >> SID_SHIFT; - proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS)); - return vsid_scramble(proto_vsid, 256M); - } - proto_vsid = ea >> SID_SHIFT_1T; - proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS_1T)); - return vsid_scramble(proto_vsid, 1T); -} - /* Returns the segment size indicator for a user address */ static inline int user_segment_size(unsigned long addr) { @@ -550,17 +530,41 @@ static inline int user_segment_size(unsigned long addr) return MMU_SEGSIZE_256M; } -/* This is only valid for user addresses (which are below 2^44) */ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, int ssize) { + /* + * Bad address. We return VSID 0 for that + */ + if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) + return 0; + if (ssize == MMU_SEGSIZE_256M) - return vsid_scramble((context << USER_ESID_BITS) + return vsid_scramble((context << ESID_BITS) | (ea >> SID_SHIFT), 256M); - return vsid_scramble((context << USER_ESID_BITS_1T) + return vsid_scramble((context << ESID_BITS_1T) | (ea >> SID_SHIFT_1T), 1T); } +/* + * This is only valid for addresses >= PAGE_OFFSET + * + * For kernel space, we use the top 4 context ids to map address as below + * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] + */ +static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) +{ + unsigned long context; + + /* + * kernel take the top 4 context from the available range + */ + context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1; + return get_vsid(context, ea, ssize); +} #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_MMU_HASH64_H_ */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 75a3d71b895..19599ef352b 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -275,7 +275,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 256c5bf0adb..04d69c4a5ac 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -304,7 +304,7 @@ syscall_exit_work: subi r12,r12,TI_FLAGS 4: /* Anything else left to do? */ - SET_DEFAULT_THREAD_PPR(r3, r9) /* Set thread.ppr = 3 */ + SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) beq .ret_from_except_lite @@ -657,7 +657,7 @@ resume_kernel: /* Clear _TIF_EMULATE_STACK_STORE flag */ lis r11,_TIF_EMULATE_STACK_STORE@h addi r5,r9,TI_FLAGS - ldarx r4,0,r5 +0: ldarx r4,0,r5 andc r4,r4,r11 stdcx. r4,0,r5 bne- 0b diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index f3eab8594d9..d44a571e45a 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -23,8 +23,10 @@ #include <asm/code-patching.h> #include <asm/machdep.h> +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) extern void epapr_ev_idle(void); extern u32 epapr_ev_idle_start[]; +#endif bool epapr_paravirt_enabled; @@ -47,11 +49,15 @@ static int __init epapr_paravirt_init(void) for (i = 0; i < (len / 4); i++) { patch_instruction(epapr_hypercall_start + i, insts[i]); +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) patch_instruction(epapr_ev_idle_start + i, insts[i]); +#endif } +#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64) if (of_get_property(hyper_node, "has-idle", NULL)) ppc_md.power_save = epapr_ev_idle; +#endif epapr_paravirt_enabled = true; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 87ef8f5ee5b..56bd92362ce 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1066,78 +1066,6 @@ unrecov_user_slb: #endif /* __DISABLED__ */ -/* - * r13 points to the PACA, r9 contains the saved CR, - * r12 contain the saved SRR1, SRR0 is still ready for return - * r3 has the faulting address - * r9 - r13 are saved in paca->exslb. - * r3 is saved in paca->slb_r3 - * We assume we aren't going to take any exceptions during this procedure. - */ -_GLOBAL(slb_miss_realmode) - mflr r10 -#ifdef CONFIG_RELOCATABLE - mtctr r11 -#endif - - stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ - std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ - - bl .slb_allocate_realmode - - /* All done -- return from exception. */ - - ld r10,PACA_EXSLB+EX_LR(r13) - ld r3,PACA_EXSLB+EX_R3(r13) - lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ - - mtlr r10 - - andi. r10,r12,MSR_RI /* check for unrecoverable exception */ - beq- 2f - -.machine push -.machine "power4" - mtcrf 0x80,r9 - mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ -.machine pop - - RESTORE_PPR_PACA(PACA_EXSLB, r9) - ld r9,PACA_EXSLB+EX_R9(r13) - ld r10,PACA_EXSLB+EX_R10(r13) - ld r11,PACA_EXSLB+EX_R11(r13) - ld r12,PACA_EXSLB+EX_R12(r13) - ld r13,PACA_EXSLB+EX_R13(r13) - rfid - b . /* prevent speculative execution */ - -2: mfspr r11,SPRN_SRR0 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10,unrecov_slb) - mtspr SPRN_SRR0,r10 - ld r10,PACAKMSR(r13) - mtspr SPRN_SRR1,r10 - rfid - b . - -unrecov_slb: - EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) - DISABLE_INTS - bl .save_nvgprs -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl .unrecoverable_exception - b 1b - - -#ifdef CONFIG_PPC_970_NAP -power4_fixup_nap: - andc r9,r9,r10 - std r9,TI_LOCAL_FLAGS(r11) - ld r10,_LINK(r1) /* make idle task do the */ - std r10,_NIP(r1) /* equivalent of a blr */ - blr -#endif - .align 7 .globl alignment_common alignment_common: @@ -1336,6 +1264,78 @@ _GLOBAL(opal_mc_secondary_handler) /* + * r13 points to the PACA, r9 contains the saved CR, + * r12 contain the saved SRR1, SRR0 is still ready for return + * r3 has the faulting address + * r9 - r13 are saved in paca->exslb. + * r3 is saved in paca->slb_r3 + * We assume we aren't going to take any exceptions during this procedure. + */ +_GLOBAL(slb_miss_realmode) + mflr r10 +#ifdef CONFIG_RELOCATABLE + mtctr r11 +#endif + + stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ + std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ + + bl .slb_allocate_realmode + + /* All done -- return from exception. */ + + ld r10,PACA_EXSLB+EX_LR(r13) + ld r3,PACA_EXSLB+EX_R3(r13) + lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ + + mtlr r10 + + andi. r10,r12,MSR_RI /* check for unrecoverable exception */ + beq- 2f + +.machine push +.machine "power4" + mtcrf 0x80,r9 + mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ +.machine pop + + RESTORE_PPR_PACA(PACA_EXSLB, r9) + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + rfid + b . /* prevent speculative execution */ + +2: mfspr r11,SPRN_SRR0 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10,unrecov_slb) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) + mtspr SPRN_SRR1,r10 + rfid + b . + +unrecov_slb: + EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) + DISABLE_INTS + bl .save_nvgprs +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b + + +#ifdef CONFIG_PPC_970_NAP +power4_fixup_nap: + andc r9,r9,r10 + std r9,TI_LOCAL_FLAGS(r11) + ld r10,_LINK(r1) /* make idle task do the */ + std r10,_NIP(r1) /* equivalent of a blr */ + blr +#endif + +/* * Hash table stuff */ .align 7 @@ -1452,20 +1452,36 @@ do_ste_alloc: _GLOBAL(do_stab_bolted) stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ + mfspr r11,SPRN_DAR /* ea */ + /* + * check for bad kernel/user address + * (ea & ~REGION_MASK) >= PGTABLE_RANGE + */ + rldicr. r9,r11,4,(63 - 46 - 4) + li r9,0 /* VSID = 0 for bad address */ + bne- 0f + + /* + * Calculate VSID: + * This is the kernel vsid, we take the top for context from + * the range. context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * Here we know that (ea >> 60) == 0xc + */ + lis r9,(MAX_USER_CONTEXT + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT + 1)@l + + srdi r10,r11,SID_SHIFT + rldimi r10,r9,ESID_BITS,0 /* proto vsid */ + ASM_VSID_SCRAMBLE(r10, r9, 256M) + rldic r9,r10,12,16 /* r9 = vsid << 12 */ + +0: /* Hash to the primary group */ ld r10,PACASTABVIRT(r13) - mfspr r11,SPRN_DAR - srdi r11,r11,28 + srdi r11,r11,SID_SHIFT rldimi r10,r11,7,52 /* r10 = first ste of the group */ - /* Calculate VSID */ - /* This is a kernel address, so protovsid = ESID | 1 << 37 */ - li r9,0x1 - rldimi r11,r9,(CONTEXT_BITS + USER_ESID_BITS),0 - ASM_VSID_SCRAMBLE(r11, r9, 256M) - rldic r9,r11,12,16 /* r9 = vsid << 12 */ - /* Search the primary group for a free entry */ 1: ld r11,0(r10) /* Test valid bit of the current ste */ andi. r11,r11,0x80 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59dd545fdde..16e77a81ab4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -555,10 +555,12 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) new->thread.regs->msr |= (MSR_FP | new->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(&new->thread); new->thread.regs->msr |= MSR_VEC; } +#endif /* We may as well turn on VSX too since all the state is restored now */ if (msr & MSR_VSX) new->thread.regs->msr |= MSR_VSX; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 7f7fb7fd991..13f8d168b3f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2832,11 +2832,13 @@ static void unreloc_toc(void) { } #else -static void __reloc_toc(void *tocstart, unsigned long offset, - unsigned long nr_entries) +static void __reloc_toc(unsigned long offset, unsigned long nr_entries) { unsigned long i; - unsigned long *toc_entry = (unsigned long *)tocstart; + unsigned long *toc_entry; + + /* Get the start of the TOC by using r2 directly. */ + asm volatile("addi %0,2,-0x8000" : "=b" (toc_entry)); for (i = 0; i < nr_entries; i++) { *toc_entry = *toc_entry + offset; @@ -2850,8 +2852,7 @@ static void reloc_toc(void) unsigned long nr_entries = (__prom_init_toc_end - __prom_init_toc_start) / sizeof(long); - /* Need to add offset to get at __prom_init_toc_start */ - __reloc_toc(__prom_init_toc_start + offset, offset, nr_entries); + __reloc_toc(offset, nr_entries); mb(); } @@ -2864,8 +2865,7 @@ static void unreloc_toc(void) mb(); - /* __prom_init_toc_start has been relocated, no need to add offset */ - __reloc_toc(__prom_init_toc_start, -offset, nr_entries); + __reloc_toc(-offset, nr_entries); } #endif #endif diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 245c1b6a085..f9b30c68ba4 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1428,6 +1428,7 @@ static long ppc_set_hwdebug(struct task_struct *child, brk.address = bp_info->addr & ~7UL; brk.type = HW_BRK_TYPE_TRANSLATE; + brk.len = 8; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3acb28e245b..95068bf569a 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -866,10 +866,12 @@ static long restore_tm_user_regs(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 995f8543cb5..c1794286098 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -522,10 +522,12 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return err; } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 84dbace657c..2da67e7a16d 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -309,6 +309,7 @@ _GLOBAL(tm_recheckpoint) or r5, r6, r5 /* Set MSR.FP+.VSX/.VEC */ mtmsr r5 +#ifdef CONFIG_ALTIVEC /* FP and VEC registers: These are recheckpointed from thread.fpr[] * and thread.vr[] respectively. The thread.transact_fpr[] version * is more modern, and will be loaded subsequently by any FPUnavailable @@ -323,6 +324,7 @@ _GLOBAL(tm_recheckpoint) REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */ ld r5, THREAD_VRSAVE(r3) mtspr SPRN_VRSAVE, r5 +#endif dont_restore_vec: andi. r0, r4, MSR_FP diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index ead58e31729..5d7d29a313e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -326,8 +326,8 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu) vcpu3s->context_id[0] = err; vcpu3s->proto_vsid_max = ((vcpu3s->context_id[0] + 1) - << USER_ESID_BITS) - 1; - vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS; + << ESID_BITS) - 1; + vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << ESID_BITS; vcpu3s->proto_vsid_next = vcpu3s->proto_vsid_first; kvmppc_mmu_hpte_init(vcpu); diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 41cefd43655..33db48a8ce2 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -26,17 +26,20 @@ #define E500_PID_NUM 3 #define E500_TLB_NUM 2 -#define E500_TLB_VALID 1 -#define E500_TLB_BITMAP 2 +/* entry is mapped somewhere in host TLB */ +#define E500_TLB_VALID (1 << 0) +/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */ +#define E500_TLB_BITMAP (1 << 1) +/* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 2) struct tlbe_ref { - pfn_t pfn; - unsigned int flags; /* E500_TLB_* */ + pfn_t pfn; /* valid only for TLB0, except briefly */ + unsigned int flags; /* E500_TLB_* */ }; struct tlbe_priv { - struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */ + struct tlbe_ref ref; }; #ifdef CONFIG_KVM_E500V2 @@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 { unsigned int gtlb_nv[E500_TLB_NUM]; - /* - * information associated with each host TLB entry -- - * TLB1 only for now. If/when guest TLB1 entries can be - * mapped with host TLB0, this will be used for that too. - * - * We don't want to use this for guest TLB0 because then we'd - * have the overhead of doing the translation again even if - * the entry is still in the guest TLB (e.g. we swapped out - * and back, and our host TLB entries got evicted). - */ - struct tlbe_ref *tlb_refs[E500_TLB_NUM]; unsigned int host_tlb1_nv; u32 svr; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index a222edfb9a9..1c6a9d729df 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) - return; + if (!(ref->flags & E500_TLB_VALID)) { + WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, ref->flags); + WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); + } if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; @@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, pfn_t pfn) { ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + ref->flags |= E500_TLB_VALID; if (tlbe_is_writable(gtlbe)) kvm_set_pfn_dirty(pfn); @@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) { if (ref->flags & E500_TLB_VALID) { + /* FIXME: don't log bogus pfn for TLB1 */ trace_kvm_booke206_ref_release(ref->pfn, ref->flags); ref->flags = 0; } @@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500) static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) { - int tlbsel = 0; - int i; - - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } -} - -static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500) -{ - int stlbsel = 1; + int tlbsel; int i; - kvmppc_e500_tlbil_all(vcpu_e500); - - for (i = 0; i < host_tlb_params[stlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->tlb_refs[stlbsel][i]; - kvmppc_e500_ref_release(ref); + for (tlbsel = 0; tlbsel <= 1; tlbsel++) { + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { + struct tlbe_ref *ref = + &vcpu_e500->gtlb_priv[tlbsel][i].ref; + kvmppc_e500_ref_release(ref); + } } - - clear_tlb_privs(vcpu_e500); } void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - clear_tlb_refs(vcpu_e500); + kvmppc_e500_tlbil_all(vcpu_e500); + clear_tlb_privs(vcpu_e500); clear_tlb1_bitmap(vcpu_e500); } @@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } - /* Drop old ref and setup new one. */ - kvmppc_e500_ref_release(ref); kvmppc_e500_ref_setup(ref, gtlbe, pfn); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, @@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size())) vcpu_e500->host_tlb1_nv = 0; - vcpu_e500->tlb_refs[1][sesel] = *ref; - vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; if (vcpu_e500->h2g_tlb1_rmap[sesel]) { - unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel]; + unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1; vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->h2g_tlb1_rmap[sesel] = esel; + + vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; + vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; + WARN_ON(!(ref->flags & E500_TLB_VALID)); return sesel; } @@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref ref; + struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; int sesel; int r; - ref.flags = 0; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - &ref); + ref); if (r) return r; @@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, case 0: priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; - /* Triggers after clear_tlb_refs or on initial mapping */ + /* Triggers after clear_tlb_privs or on initial mapping */ if (!(priv->ref.flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { @@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500) host_tlb_params[0].entries / host_tlb_params[0].ways; host_tlb_params[1].sets = 1; - vcpu_e500->tlb_refs[0] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[0]) - goto err; - - vcpu_e500->tlb_refs[1] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[1]) - goto err; - vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) * host_tlb_params[1].entries, GFP_KERNEL); if (!vcpu_e500->h2g_tlb1_rmap) - goto err; + return -EINVAL; return 0; - -err: - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); - return -EINVAL; } void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500) { kfree(vcpu_e500->h2g_tlb1_rmap); - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); } diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 1f89d26e65f..2f4baa074b2 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -108,6 +108,8 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { } +static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); + void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -136,8 +138,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GDEAR, vcpu->arch.shared->dar); mtspr(SPRN_GESR, vcpu->arch.shared->esr); - if (vcpu->arch.oldpir != mfspr(SPRN_PIR)) + if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || + __get_cpu_var(last_vcpu_on_cpu) != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); + __get_cpu_var(last_vcpu_on_cpu) = vcpu; + } kvmppc_load_guest_fp(vcpu); } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 1b6e1271719..f410c3e12c1 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -195,6 +195,11 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, unsigned long vpn = hpt_vpn(vaddr, vsid, ssize); unsigned long tprot = prot; + /* + * If we hit a bad address return error. + */ + if (!vsid) + return -1; /* Make kernel text executable */ if (overlaps_kernel_text(vaddr, vaddr + step)) tprot &= ~HPTE_R_N; @@ -759,6 +764,8 @@ void __init early_init_mmu(void) /* Initialize stab / SLB management */ if (mmu_has_feature(MMU_FTR_SLB)) slb_initialize(); + else + stab_initialize(get_paca()->stab_real); } #ifdef CONFIG_SMP @@ -922,11 +929,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n", ea, access, trap); - if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) { - DBG_LOW(" out of pgtable range !\n"); - return 1; - } - /* Get region & vsid */ switch (REGION_ID(ea)) { case USER_REGION_ID: @@ -957,6 +959,11 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) } DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid); + /* Bad address. */ + if (!vsid) { + DBG_LOW("Bad address!\n"); + return 1; + } /* Get pgdir */ pgdir = mm->pgd; if (pgdir == NULL) @@ -1126,6 +1133,8 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, /* Get VSID */ ssize = user_segment_size(ea); vsid = get_vsid(mm->context.id, ea, ssize); + if (!vsid) + return; /* Hash doesn't like irqs */ local_irq_save(flags); @@ -1233,6 +1242,9 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize); hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); + /* Don't create HPTE entries for bad address */ + if (!vsid) + return; ret = ppc_md.hpte_insert(hpteg, vpn, __pa(vaddr), mode, HPTE_V_BOLTED, mmu_linear_psize, mmu_kernel_ssize); diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c index 40bc5b0ace5..d1d1b92c5b9 100644 --- a/arch/powerpc/mm/mmu_context_hash64.c +++ b/arch/powerpc/mm/mmu_context_hash64.c @@ -29,15 +29,6 @@ static DEFINE_SPINLOCK(mmu_context_lock); static DEFINE_IDA(mmu_context_ida); -/* - * 256MB segment - * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments - * available for user mappings. Each segment contains 2^28 bytes. Each - * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts - * (19 == 37 + 28 - 46). - */ -#define MAX_CONTEXT ((1UL << CONTEXT_BITS) - 1) - int __init_new_context(void) { int index; @@ -56,7 +47,7 @@ again: else if (err) return err; - if (index > MAX_CONTEXT) { + if (index > MAX_USER_CONTEXT) { spin_lock(&mmu_context_lock); ida_remove(&mmu_context_ida, index); spin_unlock(&mmu_context_lock); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index e212a271c7a..654258f165a 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -61,7 +61,7 @@ #endif #ifdef CONFIG_PPC_STD_MMU_64 -#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT)) +#if TASK_SIZE_USER64 > (1UL << (ESID_BITS + SID_SHIFT)) #error TASK_SIZE_USER64 exceeds user VSID range #endif #endif diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 1a16ca22775..17aa6dfceb3 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -31,10 +31,15 @@ * No other registers are examined or changed. */ _GLOBAL(slb_allocate_realmode) - /* r3 = faulting address */ + /* + * check for bad kernel/user address + * (ea & ~REGION_MASK) >= PGTABLE_RANGE + */ + rldicr. r9,r3,4,(63 - 46 - 4) + bne- 8f srdi r9,r3,60 /* get region */ - srdi r10,r3,28 /* get esid */ + srdi r10,r3,SID_SHIFT /* get esid */ cmpldi cr7,r9,0xc /* cmp PAGE_OFFSET for later use */ /* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */ @@ -56,12 +61,14 @@ _GLOBAL(slb_allocate_realmode) */ _GLOBAL(slb_miss_kernel_load_linear) li r11,0 - li r9,0x1 /* - * for 1T we shift 12 bits more. slb_finish_load_1T will do - * the necessary adjustment + * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * r9 = region id. */ - rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0 + addis r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l + + BEGIN_FTR_SECTION b slb_finish_load END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) @@ -91,24 +98,19 @@ _GLOBAL(slb_miss_kernel_load_vmemmap) _GLOBAL(slb_miss_kernel_load_io) li r11,0 6: - li r9,0x1 /* - * for 1T we shift 12 bits more. slb_finish_load_1T will do - * the necessary adjustment + * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 + * r9 = region id. */ - rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0 + addis r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha + addi r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l + BEGIN_FTR_SECTION b slb_finish_load END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) b slb_finish_load_1T -0: /* user address: proto-VSID = context << 15 | ESID. First check - * if the address is within the boundaries of the user region - */ - srdi. r9,r10,USER_ESID_BITS - bne- 8f /* invalid ea bits set */ - - +0: /* when using slices, we extract the psize off the slice bitmaps * and then we need to get the sllp encoding off the mmu_psize_defs * array. @@ -164,15 +166,13 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) ld r9,PACACONTEXTID(r13) BEGIN_FTR_SECTION cmpldi r10,0x1000 -END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) - rldimi r10,r9,USER_ESID_BITS,0 -BEGIN_FTR_SECTION bge slb_finish_load_1T END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) b slb_finish_load 8: /* invalid EA */ li r10,0 /* BAD_VSID */ + li r9,0 /* BAD_VSID */ li r11,SLB_VSID_USER /* flags don't much matter */ b slb_finish_load @@ -221,8 +221,6 @@ _GLOBAL(slb_allocate_user) /* get context to calculate proto-VSID */ ld r9,PACACONTEXTID(r13) - rldimi r10,r9,USER_ESID_BITS,0 - /* fall through slb_finish_load */ #endif /* __DISABLED__ */ @@ -231,9 +229,10 @@ _GLOBAL(slb_allocate_user) /* * Finish loading of an SLB entry and return * - * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET + * r3 = EA, r9 = context, r10 = ESID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET */ slb_finish_load: + rldimi r10,r9,ESID_BITS,0 ASM_VSID_SCRAMBLE(r10,r9,256M) /* * bits above VSID_BITS_256M need to be ignored from r10 @@ -298,10 +297,11 @@ _GLOBAL(slb_compare_rr_to_size) /* * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return. * - * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9 + * r3 = EA, r9 = context, r10 = ESID(256MB), r11 = flags, clobbers r9 */ slb_finish_load_1T: - srdi r10,r10,40-28 /* get 1T ESID */ + srdi r10,r10,(SID_SHIFT_1T - SID_SHIFT) /* get 1T ESID */ + rldimi r10,r9,ESID_BITS_1T,0 ASM_VSID_SCRAMBLE(r10,r9,1T) /* * bits above VSID_BITS_1T need to be ignored from r10 diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 0d82ef50dc3..023ec8a13f3 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -82,11 +82,11 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, if (!is_kernel_addr(addr)) { ssize = user_segment_size(addr); vsid = get_vsid(mm->context.id, addr, ssize); - WARN_ON(vsid == 0); } else { vsid = get_kernel_vsid(addr, mmu_kernel_ssize); ssize = mmu_kernel_ssize; } + WARN_ON(vsid == 0); vpn = hpt_vpn(addr, vsid, ssize); rpte = __real_pte(__pte(pte), ptep); diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index b554879bd31..3c475d6267c 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -420,7 +420,20 @@ static struct attribute_group power7_pmu_events_group = { .attrs = power7_events_attr, }; +PMU_FORMAT_ATTR(event, "config:0-19"); + +static struct attribute *power7_pmu_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +struct attribute_group power7_pmu_format_group = { + .name = "format", + .attrs = power7_pmu_format_attr, +}; + static const struct attribute_group *power7_pmu_attr_groups[] = { + &power7_pmu_format_group, &power7_pmu_events_group, NULL, }; diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c index 611e92f291c..7179726ba5c 100644 --- a/arch/powerpc/platforms/85xx/sgy_cts1000.c +++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c @@ -69,7 +69,7 @@ static irqreturn_t gpio_halt_irq(int irq, void *__data) return IRQ_HANDLED; }; -static int __devinit gpio_halt_probe(struct platform_device *pdev) +static int gpio_halt_probe(struct platform_device *pdev) { enum of_gpio_flags flags; struct device_node *node = pdev->dev.of_node; @@ -128,7 +128,7 @@ static int __devinit gpio_halt_probe(struct platform_device *pdev) return 0; } -static int __devexit gpio_halt_remove(struct platform_device *pdev) +static int gpio_halt_remove(struct platform_device *pdev) { if (halt_node) { int gpio = of_get_gpio(halt_node, 0); @@ -165,7 +165,7 @@ static struct platform_driver gpio_halt_driver = { .of_match_table = gpio_halt_match, }, .probe = gpio_halt_probe, - .remove = __devexit_p(gpio_halt_remove), + .remove = gpio_halt_remove, }; module_platform_driver(gpio_halt_driver); diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index cea2f09c424..18e3b76c78d 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -124,9 +124,8 @@ config 6xx select PPC_HAVE_PMU_SUPPORT config POWER3 - bool depends on PPC64 && PPC_BOOK3S - default y if !POWER4_ONLY + def_bool y config POWER4 depends on PPC64 && PPC_BOOK3S @@ -145,8 +144,7 @@ config TUNE_CELL but somewhat slower on other machines. This option only changes the scheduling of instructions, not the selection of instructions itself, so the resulting kernel will keep running on all other - machines. When building a kernel that is supposed to run only - on Cell, you should also select the POWER4_ONLY option. + machines. # this is temp to handle compat with arch=ppc config 8xx diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 0da39fed355..299731e9036 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -186,7 +186,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group) (0x1UL << 4), &dummy1, &dummy2); if (lpar_rc == H_SUCCESS) return i; - BUG_ON(lpar_rc != H_NOT_FOUND); + + /* + * The test for adjunct partition is performed before the + * ANDCOND test. H_RESOURCE may be returned, so we need to + * check for that as well. + */ + BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE); slot_offset++; slot_offset &= 0x7; diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h index 8d4847191ec..dc9200ca32e 100644 --- a/arch/s390/include/asm/eadm.h +++ b/arch/s390/include/asm/eadm.h @@ -34,6 +34,8 @@ struct arsb { u32 reserved[4]; } __packed; +#define EQC_WR_PROHIBIT 22 + struct msb { u8 fmt:4; u8 oc:4; @@ -96,11 +98,13 @@ struct scm_device { #define OP_STATE_TEMP_ERR 2 #define OP_STATE_PERM_ERR 3 +enum scm_event {SCM_CHANGE, SCM_AVAIL}; + struct scm_driver { struct device_driver drv; int (*probe) (struct scm_device *scmdev); int (*remove) (struct scm_device *scmdev); - void (*notify) (struct scm_device *scmdev); + void (*notify) (struct scm_device *scmdev, enum scm_event event); void (*handler) (struct scm_device *scmdev, void *data, int error); }; diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 27cb32185ce..379d96e2105 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -50,10 +50,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr); #define ioremap_nocache(addr, size) ioremap(addr, size) #define ioremap_wc ioremap_nocache -/* TODO: s390 cannot support io_remap_pfn_range... */ -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - remap_pfn_range(vma, vaddr, pfn, size, prot) - static inline void __iomem *ioremap(unsigned long offset, unsigned long size) { return (void __iomem *) offset; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 4a2930844d4..3cb47cf0253 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -57,6 +57,10 @@ extern unsigned long zero_page_mask; (((unsigned long)(vaddr)) &zero_page_mask)))) #define __HAVE_COLOR_ZERO_PAGE +/* TODO: s390 cannot support io_remap_pfn_range... */ +#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ + remap_pfn_range(vma, vaddr, pfn, size, prot) + #endif /* !__ASSEMBLY__ */ /* @@ -344,6 +348,7 @@ extern unsigned long MODULES_END; #define _REGION3_ENTRY_CO 0x100 /* change-recording override */ /* Bits in the segment table entry */ +#define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ #define _SEGMENT_ENTRY_ORIGIN ~0x7ffUL/* segment table origin */ #define _SEGMENT_ENTRY_RO 0x200 /* page protection bit */ #define _SEGMENT_ENTRY_INV 0x20 /* invalid segment table entry */ @@ -1531,7 +1536,8 @@ extern int s390_enable_sie(void); /* * No page table caches to initialise */ -#define pgtable_cache_init() do { } while (0) +static inline void pgtable_cache_init(void) { } +static inline void check_pgt_cache(void) { } #include <asm-generic/pgtable.h> diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 1d8fe2b17ef..6b32af30878 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -74,8 +74,6 @@ static inline void __tlb_flush_idte(unsigned long asce) static inline void __tlb_flush_mm(struct mm_struct * mm) { - if (unlikely(cpumask_empty(mm_cpumask(mm)))) - return; /* * If the machine has IDTE we prefer to do a per mm flush * on all cpus instead of doing a local flush if the mm diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 55022852326..94feff7d613 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -636,7 +636,8 @@ ENTRY(mcck_int_handler) UPDATE_VTIME %r14,%r15,__LC_MCCK_ENTER_TIMER mcck_skip: SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+32,__LC_PANIC_STACK,PAGE_SHIFT - mvc __PT_R0(64,%r11),__LC_GPREGS_SAVE_AREA + stm %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(32,%r11),__LC_GPREGS_SAVE_AREA+32 stm %r8,%r9,__PT_PSW(%r11) xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) l %r1,BASED(.Ldo_machine_check) diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 9c837c10129..2e6d60c55f9 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -678,8 +678,9 @@ ENTRY(mcck_int_handler) UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER LAST_BREAK %r14 mcck_skip: - lghi %r14,__LC_GPREGS_SAVE_AREA - mvc __PT_R0(128,%r11),0(%r14) + lghi %r14,__LC_GPREGS_SAVE_AREA+64 + stmg %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(64,%r11),0(%r14) stmg %r8,%r9,__PT_PSW(%r11) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index a5360de85ec..29268859d8e 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -571,6 +571,8 @@ static void __init setup_memory_end(void) /* Split remaining virtual space between 1:1 mapping & vmemmap array */ tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page)); + /* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */ + tmp = SECTION_ALIGN_UP(tmp); tmp = VMALLOC_START - tmp * sizeof(struct page); tmp &= ~((vmax >> 11) - 1); /* align to page table level */ tmp = min(tmp, 1UL << MAX_PHYSMEM_BITS); diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index dff631d34b4..466fb338396 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -77,42 +77,69 @@ static size_t copy_in_kernel(size_t count, void __user *to, * >= -4095 (IS_ERR_VALUE(x) returns true), a fault has occured and the address * contains the (negative) exception code. */ -static __always_inline unsigned long follow_table(struct mm_struct *mm, - unsigned long addr, int write) +#ifdef CONFIG_64BIT +static unsigned long follow_table(struct mm_struct *mm, + unsigned long address, int write) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; + unsigned long *table = (unsigned long *)__pa(mm->pgd); + + switch (mm->context.asce_bits & _ASCE_TYPE_MASK) { + case _ASCE_TYPE_REGION1: + table = table + ((address >> 53) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -0x39UL; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + case _ASCE_TYPE_REGION2: + table = table + ((address >> 42) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -0x3aUL; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + case _ASCE_TYPE_REGION3: + table = table + ((address >> 31) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -0x3bUL; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + case _ASCE_TYPE_SEGMENT: + table = table + ((address >> 20) & 0x7ff); + if (unlikely(*table & _SEGMENT_ENTRY_INV)) + return -0x10UL; + if (unlikely(*table & _SEGMENT_ENTRY_LARGE)) { + if (write && (*table & _SEGMENT_ENTRY_RO)) + return -0x04UL; + return (*table & _SEGMENT_ENTRY_ORIGIN_LARGE) + + (address & ~_SEGMENT_ENTRY_ORIGIN_LARGE); + } + table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); + } + table = table + ((address >> 12) & 0xff); + if (unlikely(*table & _PAGE_INVALID)) + return -0x11UL; + if (write && (*table & _PAGE_RO)) + return -0x04UL; + return (*table & PAGE_MASK) + (address & ~PAGE_MASK); +} - pgd = pgd_offset(mm, addr); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return -0x3aUL; +#else /* CONFIG_64BIT */ - pud = pud_offset(pgd, addr); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) - return -0x3bUL; +static unsigned long follow_table(struct mm_struct *mm, + unsigned long address, int write) +{ + unsigned long *table = (unsigned long *)__pa(mm->pgd); - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + table = table + ((address >> 20) & 0x7ff); + if (unlikely(*table & _SEGMENT_ENTRY_INV)) return -0x10UL; - if (pmd_large(*pmd)) { - if (write && (pmd_val(*pmd) & _SEGMENT_ENTRY_RO)) - return -0x04UL; - return (pmd_val(*pmd) & HPAGE_MASK) + (addr & ~HPAGE_MASK); - } - if (unlikely(pmd_bad(*pmd))) - return -0x10UL; - - ptep = pte_offset_map(pmd, addr); - if (!pte_present(*ptep)) + table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); + table = table + ((address >> 12) & 0xff); + if (unlikely(*table & _PAGE_INVALID)) return -0x11UL; - if (write && (!pte_write(*ptep) || !pte_dirty(*ptep))) + if (write && (*table & _PAGE_RO)) return -0x04UL; - - return (pte_val(*ptep) & PAGE_MASK) + (addr & ~PAGE_MASK); + return (*table & PAGE_MASK) + (address & ~PAGE_MASK); } +#endif /* CONFIG_64BIT */ + static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr, size_t n, int write_user) { @@ -197,7 +224,7 @@ size_t copy_to_user_pt(size_t n, void __user *to, const void *from) static size_t clear_user_pt(size_t n, void __user *to) { - void *zpage = &empty_zero_page; + void *zpage = (void *) empty_zero_page; long done, size, ret; done = 0; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 289127d5241..3d361f23630 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -84,12 +84,6 @@ config ARCH_DEFCONFIG default "arch/sparc/configs/sparc32_defconfig" if SPARC32 default "arch/sparc/configs/sparc64_defconfig" if SPARC64 -# CONFIG_BITS can be used at source level to get 32/64 bits -config BITS - int - default 32 if SPARC32 - default 64 if SPARC64 - config IOMMU_HELPER bool default y if SPARC64 @@ -197,7 +191,7 @@ config RWSEM_XCHGADD_ALGORITHM config GENERIC_HWEIGHT bool - default y if !ULTRA_HAS_POPULATION_COUNT + default y config GENERIC_CALIBRATE_DELAY bool diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index e26d430ce2f..ff18e3cfb6b 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -2,11 +2,16 @@ generic-y += clkdev.h +generic-y += cputime.h generic-y += div64.h +generic-y += emergency-restart.h generic-y += exec.h generic-y += local64.h +generic-y += mutex.h generic-y += irq_regs.h generic-y += local.h generic-y += module.h +generic-y += serial.h generic-y += trace_clock.h +generic-y += types.h generic-y += word-at-a-time.h diff --git a/arch/sparc/include/asm/cputime.h b/arch/sparc/include/asm/cputime.h deleted file mode 100644 index 1a642b81e01..00000000000 --- a/arch/sparc/include/asm/cputime.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_CPUTIME_H -#define __SPARC_CPUTIME_H - -#include <asm-generic/cputime.h> - -#endif /* __SPARC_CPUTIME_H */ diff --git a/arch/sparc/include/asm/emergency-restart.h b/arch/sparc/include/asm/emergency-restart.h deleted file mode 100644 index 108d8c48e42..00000000000 --- a/arch/sparc/include/asm/emergency-restart.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_EMERGENCY_RESTART_H -#define _ASM_EMERGENCY_RESTART_H - -#include <asm-generic/emergency-restart.h> - -#endif /* _ASM_EMERGENCY_RESTART_H */ diff --git a/arch/sparc/include/asm/mutex.h b/arch/sparc/include/asm/mutex.h deleted file mode 100644 index 458c1f7fbc1..00000000000 --- a/arch/sparc/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include <asm-generic/mutex-dec.h> diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 08fcce90316..7619f2f792a 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -915,6 +915,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); } +#include <asm/tlbflush.h> #include <asm-generic/pgtable.h> /* We provide our own get_unmapped_area to cope with VA holes and diff --git a/arch/sparc/include/asm/serial.h b/arch/sparc/include/asm/serial.h deleted file mode 100644 index f90d61c2805..00000000000 --- a/arch/sparc/include/asm/serial.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_SERIAL_H -#define __SPARC_SERIAL_H - -#define BASE_BAUD ( 1843200 / 16 ) - -#endif /* __SPARC_SERIAL_H */ diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h index b73da3c5f10..3c8917f054d 100644 --- a/arch/sparc/include/asm/smp_32.h +++ b/arch/sparc/include/asm/smp_32.h @@ -36,7 +36,6 @@ typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); void cpu_panic(void); -extern void smp4m_irq_rotate(int cpu); /* * General functions that each host system must provide. @@ -46,7 +45,6 @@ void sun4m_init_smp(void); void sun4d_init_smp(void); void smp_callin(void); -void smp_boot_cpus(void); void smp_store_cpu_info(int); void smp_resched_interrupt(void); @@ -107,9 +105,6 @@ extern int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) -#define prof_multiplier(__cpu) cpu_data(__cpu).multiplier -#define prof_counter(__cpu) cpu_data(__cpu).counter - void smp_setup_cpu_possible_map(void); #endif /* !(__ASSEMBLY__) */ diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index d06a2660175..6b67e50fb9b 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -45,6 +45,7 @@ #define SUN4V_CHIP_NIAGARA3 0x03 #define SUN4V_CHIP_NIAGARA4 0x04 #define SUN4V_CHIP_NIAGARA5 0x05 +#define SUN4V_CHIP_SPARC64X 0x8a #define SUN4V_CHIP_UNKNOWN 0xff #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h index cad36f56fa0..c7de3323819 100644 --- a/arch/sparc/include/asm/switch_to_64.h +++ b/arch/sparc/include/asm/switch_to_64.h @@ -18,8 +18,7 @@ do { \ * and 2 stores in this critical code path. -DaveM */ #define switch_to(prev, next, last) \ -do { flush_tlb_pending(); \ - save_and_clear_fpu(); \ +do { save_and_clear_fpu(); \ /* If you are tempted to conditionalize the following */ \ /* so that ASI is only written if it changes, think again. */ \ __asm__ __volatile__("wr %%g0, %0, %%asi" \ diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index 2ef46349415..f0d6a9700f4 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -11,24 +11,40 @@ struct tlb_batch { struct mm_struct *mm; unsigned long tlb_nr; + unsigned long active; unsigned long vaddrs[TLB_BATCH_NR]; }; extern void flush_tsb_kernel_range(unsigned long start, unsigned long end); extern void flush_tsb_user(struct tlb_batch *tb); +extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr); /* TLB flush operations. */ -extern void flush_tlb_pending(void); +static inline void flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define flush_tlb_range(vma,start,end) \ - do { (void)(start); flush_tlb_pending(); } while (0) -#define flush_tlb_page(vma,addr) flush_tlb_pending() -#define flush_tlb_mm(mm) flush_tlb_pending() +extern void flush_tlb_pending(void); +extern void arch_enter_lazy_mmu_mode(void); +extern void arch_leave_lazy_mmu_mode(void); +#define arch_flush_lazy_mmu_mode() do {} while (0) /* Local cpu only. */ extern void __flush_tlb_all(void); - +extern void __flush_tlb_page(unsigned long context, unsigned long vaddr); extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifndef CONFIG_SMP @@ -38,15 +54,24 @@ do { flush_tsb_kernel_range(start,end); \ __flush_tlb_kernel_range(start,end); \ } while (0) +static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); +} + #else /* CONFIG_SMP */ extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); #define flush_tlb_kernel_range(start, end) \ do { flush_tsb_kernel_range(start,end); \ smp_flush_tlb_kernel_range(start, end); \ } while (0) +#define global_flush_tlb_page(mm, vaddr) \ + smp_flush_tlb_page(mm, vaddr) + #endif /* ! CONFIG_SMP */ #endif /* _SPARC64_TLBFLUSH_H */ diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index ce175aff71b..b5843ee09fb 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -44,7 +44,6 @@ header-y += swab.h header-y += termbits.h header-y += termios.h header-y += traps.h -header-y += types.h header-y += uctx.h header-y += unistd.h header-y += utrap.h diff --git a/arch/sparc/include/uapi/asm/types.h b/arch/sparc/include/uapi/asm/types.h deleted file mode 100644 index 383d156cde9..00000000000 --- a/arch/sparc/include/uapi/asm/types.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _SPARC_TYPES_H -#define _SPARC_TYPES_H -/* - * This file is never included by application software unless - * explicitly requested (e.g., via linux/types.h) in which case the - * application is Linux specific so (user-) name space pollution is - * not a major issue. However, for interoperability, libraries still - * need to be careful to avoid a name clashes. - */ - -#if defined(__sparc__) - -#include <asm-generic/int-ll64.h> - -#endif /* defined(__sparc__) */ - -#endif /* defined(_SPARC_TYPES_H) */ diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index a6c94a2bf9d..5c5125895db 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -493,6 +493,12 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "niagara5"; break; + case SUN4V_CHIP_SPARC64X: + sparc_cpu_type = "SPARC64-X"; + sparc_fpu_type = "SPARC64-X integrated FPU"; + sparc_pmu_type = "sparc64-x"; + break; + default: printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n", prom_cpu_compatible); diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 2feb15c35d9..26b706a1867 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -134,6 +134,8 @@ prom_niagara_prefix: .asciz "SUNW,UltraSPARC-T" prom_sparc_prefix: .asciz "SPARC-" +prom_sparc64x_prefix: + .asciz "SPARC64-X" .align 4 prom_root_compatible: .skip 64 @@ -412,7 +414,7 @@ sun4v_chip_type: cmp %g2, 'T' be,pt %xcc, 70f cmp %g2, 'M' - bne,pn %xcc, 4f + bne,pn %xcc, 49f nop 70: ldub [%g1 + 7], %g2 @@ -425,7 +427,7 @@ sun4v_chip_type: cmp %g2, '5' be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA5, %g4 - ba,pt %xcc, 4f + ba,pt %xcc, 49f nop 91: sethi %hi(prom_cpu_compatible), %g1 @@ -439,6 +441,25 @@ sun4v_chip_type: mov SUN4V_CHIP_NIAGARA2, %g4 4: + /* Athena */ + sethi %hi(prom_cpu_compatible), %g1 + or %g1, %lo(prom_cpu_compatible), %g1 + sethi %hi(prom_sparc64x_prefix), %g7 + or %g7, %lo(prom_sparc64x_prefix), %g7 + mov 9, %g3 +41: ldub [%g7], %g2 + ldub [%g1], %g4 + cmp %g2, %g4 + bne,pn %icc, 49f + add %g7, 1, %g7 + subcc %g3, 1, %g3 + bne,pt %xcc, 41b + add %g1, 1, %g1 + mov SUN4V_CHIP_SPARC64X, %g4 + ba,pt %xcc, 5f + nop + +49: mov SUN4V_CHIP_UNKNOWN, %g4 5: sethi %hi(sun4v_chip_type), %g2 or %g2, %lo(sun4v_chip_type), %g2 diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index fc4320886a3..4d1487138d2 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -186,6 +186,8 @@ struct grpci2_cap_first { #define CAP9_IOMAP_OFS 0x20 #define CAP9_BARSIZE_OFS 0x24 +#define TGT 256 + struct grpci2_priv { struct leon_pci_info info; /* must be on top of this structure */ struct grpci2_regs *regs; @@ -237,8 +239,12 @@ static int grpci2_cfg_r32(struct grpci2_priv *priv, unsigned int bus, if (where & 0x3) return -EINVAL; - if (bus == 0 && PCI_SLOT(devfn) != 0) - devfn += (0x8 * 6); + if (bus == 0) { + devfn += (0x8 * 6); /* start at AD16=Device0 */ + } else if (bus == TGT) { + bus = 0; + devfn = 0; /* special case: bridge controller itself */ + } /* Select bus */ spin_lock_irqsave(&grpci2_dev_lock, flags); @@ -303,8 +309,12 @@ static int grpci2_cfg_w32(struct grpci2_priv *priv, unsigned int bus, if (where & 0x3) return -EINVAL; - if (bus == 0 && PCI_SLOT(devfn) != 0) - devfn += (0x8 * 6); + if (bus == 0) { + devfn += (0x8 * 6); /* start at AD16=Device0 */ + } else if (bus == TGT) { + bus = 0; + devfn = 0; /* special case: bridge controller itself */ + } /* Select bus */ spin_lock_irqsave(&grpci2_dev_lock, flags); @@ -368,7 +378,7 @@ static int grpci2_read_config(struct pci_bus *bus, unsigned int devfn, unsigned int busno = bus->number; int ret; - if (PCI_SLOT(devfn) > 15 || (PCI_SLOT(devfn) == 0 && busno == 0)) { + if (PCI_SLOT(devfn) > 15 || busno > 255) { *val = ~0; return 0; } @@ -406,7 +416,7 @@ static int grpci2_write_config(struct pci_bus *bus, unsigned int devfn, struct grpci2_priv *priv = grpci2priv; unsigned int busno = bus->number; - if (PCI_SLOT(devfn) > 15 || (PCI_SLOT(devfn) == 0 && busno == 0)) + if (PCI_SLOT(devfn) > 15 || busno > 255) return 0; #ifdef GRPCI2_DEBUG_CFGACCESS @@ -578,15 +588,15 @@ void grpci2_hw_init(struct grpci2_priv *priv) REGSTORE(regs->ahbmst_map[i], priv->pci_area); /* Get the GRPCI2 Host PCI ID */ - grpci2_cfg_r32(priv, 0, 0, PCI_VENDOR_ID, &priv->pciid); + grpci2_cfg_r32(priv, TGT, 0, PCI_VENDOR_ID, &priv->pciid); /* Get address to first (always defined) capability structure */ - grpci2_cfg_r8(priv, 0, 0, PCI_CAPABILITY_LIST, &capptr); + grpci2_cfg_r8(priv, TGT, 0, PCI_CAPABILITY_LIST, &capptr); /* Enable/Disable Byte twisting */ - grpci2_cfg_r32(priv, 0, 0, capptr+CAP9_IOMAP_OFS, &io_map); + grpci2_cfg_r32(priv, TGT, 0, capptr+CAP9_IOMAP_OFS, &io_map); io_map = (io_map & ~0x1) | (priv->bt_enabled ? 1 : 0); - grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_IOMAP_OFS, io_map); + grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_IOMAP_OFS, io_map); /* Setup the Host's PCI Target BARs for other peripherals to access, * and do DMA to the host's memory. The target BARs can be sized and @@ -617,17 +627,18 @@ void grpci2_hw_init(struct grpci2_priv *priv) pciadr = 0; } } - grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_BARSIZE_OFS+i*4, bar_sz); - grpci2_cfg_w32(priv, 0, 0, PCI_BASE_ADDRESS_0+i*4, pciadr); - grpci2_cfg_w32(priv, 0, 0, capptr+CAP9_BAR_OFS+i*4, ahbadr); + grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_BARSIZE_OFS+i*4, + bar_sz); + grpci2_cfg_w32(priv, TGT, 0, PCI_BASE_ADDRESS_0+i*4, pciadr); + grpci2_cfg_w32(priv, TGT, 0, capptr+CAP9_BAR_OFS+i*4, ahbadr); printk(KERN_INFO " TGT BAR[%d]: 0x%08x (PCI)-> 0x%08x\n", i, pciadr, ahbadr); } /* set as bus master and enable pci memory responses */ - grpci2_cfg_r32(priv, 0, 0, PCI_COMMAND, &data); + grpci2_cfg_r32(priv, TGT, 0, PCI_COMMAND, &data); data |= (PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); - grpci2_cfg_w32(priv, 0, 0, PCI_COMMAND, data); + grpci2_cfg_w32(priv, TGT, 0, PCI_COMMAND, data); /* Enable Error respone (CPU-TRAP) on illegal memory access. */ REGSTORE(regs->ctrl, CTRL_ER | CTRL_PE); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 537eb66abd0..ca64d2a86ec 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -849,7 +849,7 @@ void smp_tsb_sync(struct mm_struct *mm) } extern unsigned long xcall_flush_tlb_mm; -extern unsigned long xcall_flush_tlb_pending; +extern unsigned long xcall_flush_tlb_page; extern unsigned long xcall_flush_tlb_kernel_range; extern unsigned long xcall_fetch_glob_regs; extern unsigned long xcall_fetch_glob_pmu; @@ -1074,23 +1074,56 @@ local_flush_and_out: put_cpu(); } +struct tlb_pending_info { + unsigned long ctx; + unsigned long nr; + unsigned long *vaddrs; +}; + +static void tlb_pending_func(void *info) +{ + struct tlb_pending_info *t = info; + + __flush_tlb_pending(t->ctx, t->nr, t->vaddrs); +} + void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs) { u32 ctx = CTX_HWBITS(mm->context); + struct tlb_pending_info info; int cpu = get_cpu(); + info.ctx = ctx; + info.nr = nr; + info.vaddrs = vaddrs; + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); else - smp_cross_call_masked(&xcall_flush_tlb_pending, - ctx, nr, (unsigned long) vaddrs, - mm_cpumask(mm)); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); put_cpu(); } +void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long context = CTX_HWBITS(mm->context); + int cpu = get_cpu(); + + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) + cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); + else + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); + + put_cpu(); +} + void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end) { start &= PAGE_MASK; diff --git a/arch/sparc/lib/bitext.c b/arch/sparc/lib/bitext.c index 48d00e72ce1..8ec4e9c0251 100644 --- a/arch/sparc/lib/bitext.c +++ b/arch/sparc/lib/bitext.c @@ -119,11 +119,7 @@ void bit_map_clear(struct bit_map *t, int offset, int len) void bit_map_init(struct bit_map *t, unsigned long *map, int size) { - - if ((size & 07) != 0) - BUG(); - memset(map, 0, size>>3); - + bitmap_zero(map, size); memset(t, 0, sizeof *t); spin_lock_init(&t->lock); t->map = map; diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 0f4f7191fbb..28f96f27c76 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -34,7 +34,7 @@ #define IOMMU_RNGE IOMMU_RNGE_256MB #define IOMMU_START 0xF0000000 #define IOMMU_WINSIZE (256*1024*1024U) -#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 265KB */ +#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 256KB */ #define IOMMU_ORDER 6 /* 4096 * (1<<6) */ /* srmmu.c */ diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index c38bb72e3e8..036c2797dec 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -280,7 +280,9 @@ static void __init srmmu_nocache_init(void) SRMMU_NOCACHE_ALIGN_MAX, 0UL); memset(srmmu_nocache_pool, 0, srmmu_nocache_size); - srmmu_nocache_bitmap = __alloc_bootmem(bitmap_bits >> 3, SMP_CACHE_BYTES, 0UL); + srmmu_nocache_bitmap = + __alloc_bootmem(BITS_TO_LONGS(bitmap_bits) * sizeof(long), + SMP_CACHE_BYTES, 0UL); bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits); srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE); diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index ba6ae7ffdc2..83d89bcb44a 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch); void flush_tlb_pending(void) { struct tlb_batch *tb = &get_cpu_var(tlb_batch); + struct mm_struct *mm = tb->mm; - if (tb->tlb_nr) { - flush_tsb_user(tb); + if (!tb->tlb_nr) + goto out; - if (CTX_VALID(tb->mm->context)) { + flush_tsb_user(tb); + + if (CTX_VALID(mm->context)) { + if (tb->tlb_nr == 1) { + global_flush_tlb_page(mm, tb->vaddrs[0]); + } else { #ifdef CONFIG_SMP smp_flush_tlb_pending(tb->mm, tb->tlb_nr, &tb->vaddrs[0]); @@ -37,12 +43,30 @@ void flush_tlb_pending(void) tb->tlb_nr, &tb->vaddrs[0]); #endif } - tb->tlb_nr = 0; } + tb->tlb_nr = 0; + +out: put_cpu_var(tlb_batch); } +void arch_enter_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + tb->active = 1; +} + +void arch_leave_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + if (tb->tlb_nr) + flush_tlb_pending(); + tb->active = 0; +} + static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, bool exec) { @@ -60,6 +84,12 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, nr = 0; } + if (!tb->active) { + global_flush_tlb_page(mm, vaddr); + flush_tsb_user_page(mm, vaddr); + goto out; + } + if (nr == 0) tb->mm = mm; @@ -68,6 +98,7 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, if (nr >= TLB_BATCH_NR) flush_tlb_pending(); +out: put_cpu_var(tlb_batch); } diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 428982b9bec..2cc3bce5ee9 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -7,11 +7,10 @@ #include <linux/preempt.h> #include <linux/slab.h> #include <asm/page.h> -#include <asm/tlbflush.h> -#include <asm/tlb.h> -#include <asm/mmu_context.h> #include <asm/pgtable.h> +#include <asm/mmu_context.h> #include <asm/tsb.h> +#include <asm/tlb.h> #include <asm/oplib.h> extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; @@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end) } } -static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, - unsigned long tsb, unsigned long nentries) +static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v, + unsigned long hash_shift, + unsigned long nentries) { - unsigned long i; + unsigned long tag, ent, hash; - for (i = 0; i < tb->tlb_nr; i++) { - unsigned long v = tb->vaddrs[i]; - unsigned long tag, ent, hash; + v &= ~0x1UL; + hash = tsb_hash(v, hash_shift, nentries); + ent = tsb + (hash * sizeof(struct tsb)); + tag = (v >> 22UL); - v &= ~0x1UL; + tsb_flush(ent, tag); +} - hash = tsb_hash(v, hash_shift, nentries); - ent = tsb + (hash * sizeof(struct tsb)); - tag = (v >> 22UL); +static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, + unsigned long tsb, unsigned long nentries) +{ + unsigned long i; - tsb_flush(ent, tag); - } + for (i = 0; i < tb->tlb_nr; i++) + __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries); } void flush_tsb_user(struct tlb_batch *tb) @@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb) spin_unlock_irqrestore(&mm->context.lock, flags); } +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long nentries, base, flags; + + spin_lock_irqsave(&mm->context.lock, flags); + + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); + +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) + if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; + nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries); + } +#endif + spin_unlock_irqrestore(&mm->context.lock, flags); +} + #define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_8K #define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_8K diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index f8e13d421fc..432aa0cb1b3 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -53,6 +53,33 @@ __flush_tlb_mm: /* 18 insns */ nop .align 32 + .globl __flush_tlb_page +__flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, %pstate + mov SECONDARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + andn %o1, 1, %o3 + be,pn %icc, 1f + or %o3, 0x10, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + retl + wrpr %g7, 0x0, %pstate + nop + nop + nop + nop + + .align 32 .globl __flush_tlb_pending __flush_tlb_pending: /* 26 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ @@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */ retl wrpr %g7, 0x0, %pstate +__cheetah_flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, 0x0, %pstate + wrpr %g0, 1, %tl + mov PRIMARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o3 + sllx %o3, CTX_PGSZ1_NUC_SHIFT, %o3 + or %o0, %o3, %o0 /* Preserve nucleus page size fields */ + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + be,pn %icc, 1f + andn %o1, 1, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + wrpr %g0, 0, %tl + retl + wrpr %g7, 0x0, %pstate + __cheetah_flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ rdpr %pstate, %g7 @@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */ retl nop +__hypervisor_flush_tlb_page: /* 11 insns */ + /* %o0 = context, %o1 = vaddr */ + mov %o0, %g2 + mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */ + mov %g2, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + srlx %o0, PAGE_SHIFT, %o0 + sllx %o0, PAGE_SHIFT, %o0 + ta HV_MMU_UNMAP_ADDR_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_MMU_UNMAP_ADDR_TRAP, %o1 + retl + nop + __hypervisor_flush_tlb_pending: /* 16 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ sllx %o1, 3, %g1 @@ -339,6 +405,13 @@ cheetah_patch_cachetlbops: call tlb_patch_one mov 19, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__cheetah_flush_tlb_page), %o1 + or %o1, %lo(__cheetah_flush_tlb_page), %o1 + call tlb_patch_one + mov 22, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__cheetah_flush_tlb_pending), %o1 @@ -397,10 +470,9 @@ xcall_flush_tlb_mm: /* 21 insns */ nop nop - .globl xcall_flush_tlb_pending -xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=context, %g1=nr, %g7=vaddrs[] */ - sllx %g1, 3, %g1 + .globl xcall_flush_tlb_page +xcall_flush_tlb_page: /* 17 insns */ + /* %g5=context, %g1=vaddr */ mov PRIMARY_CONTEXT, %g4 ldxa [%g4] ASI_DMMU, %g2 srlx %g2, CTX_PGSZ1_NUC_SHIFT, %g4 @@ -408,20 +480,16 @@ xcall_flush_tlb_pending: /* 21 insns */ or %g5, %g4, %g5 mov PRIMARY_CONTEXT, %g4 stxa %g5, [%g4] ASI_DMMU -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %g5 - andcc %g5, 0x1, %g0 + andcc %g1, 0x1, %g0 be,pn %icc, 2f - - andn %g5, 0x1, %g5 + andn %g1, 0x1, %g5 stxa %g0, [%g5] ASI_IMMU_DEMAP 2: stxa %g0, [%g5] ASI_DMMU_DEMAP membar #Sync - brnz,pt %g1, 1b - nop stxa %g2, [%g4] ASI_DMMU retry nop + nop .globl xcall_flush_tlb_kernel_range xcall_flush_tlb_kernel_range: /* 25 insns */ @@ -656,15 +724,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ membar #Sync retry - .globl __hypervisor_xcall_flush_tlb_pending -__hypervisor_xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */ - sllx %g1, 3, %g1 + .globl __hypervisor_xcall_flush_tlb_page +__hypervisor_xcall_flush_tlb_page: /* 17 insns */ + /* %g5=ctx, %g1=vaddr */ mov %o0, %g2 mov %o1, %g3 mov %o2, %g4 -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %o0 /* ARG0: virtual address */ + mov %g1, %o0 /* ARG0: virtual address */ mov %g5, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ srlx %o0, PAGE_SHIFT, %o0 @@ -673,8 +739,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */ mov HV_MMU_UNMAP_ADDR_TRAP, %g6 brnz,a,pn %o0, __hypervisor_tlb_xcall_error mov %o0, %g5 - brnz,pt %g1, 1b - nop mov %g2, %o0 mov %g3, %o1 mov %g4, %o2 @@ -757,6 +821,13 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 10, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__hypervisor_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_flush_tlb_page), %o1 + call tlb_patch_one + mov 11, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__hypervisor_flush_tlb_pending), %o1 @@ -788,12 +859,12 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 21, %o2 - sethi %hi(xcall_flush_tlb_pending), %o0 - or %o0, %lo(xcall_flush_tlb_pending), %o0 - sethi %hi(__hypervisor_xcall_flush_tlb_pending), %o1 - or %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1 + sethi %hi(xcall_flush_tlb_page), %o0 + or %o0, %lo(xcall_flush_tlb_page), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1 call tlb_patch_one - mov 21, %o2 + mov 17, %o2 sethi %hi(xcall_flush_tlb_kernel_range), %o0 or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index 8c5eff6d6df..47684815e5c 100644 --- a/arch/tile/configs/tilegx_defconfig +++ b/arch/tile/configs/tilegx_defconfig @@ -330,7 +330,6 @@ CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m -CONFIG_MULTICORE_RAID456=y CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_DEBUG=y diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig index e7a3dfcbcda..dd2b8f0c631 100644 --- a/arch/tile/configs/tilepro_defconfig +++ b/arch/tile/configs/tilepro_defconfig @@ -324,7 +324,6 @@ CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m -CONFIG_MULTICORE_RAID456=y CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_DEBUG=y diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h index 241c0bb60b1..c96f9bbb760 100644 --- a/arch/tile/include/asm/irqflags.h +++ b/arch/tile/include/asm/irqflags.h @@ -40,7 +40,15 @@ #include <asm/percpu.h> #include <arch/spr_def.h> -/* Set and clear kernel interrupt masks. */ +/* + * Set and clear kernel interrupt masks. + * + * NOTE: __insn_mtspr() is a compiler builtin marked as a memory + * clobber. We rely on it being equivalent to a compiler barrier in + * this code since arch_local_irq_save() and friends must act as + * compiler barriers. This compiler semantic is baked into enough + * places that the compiler will maintain it going forward. + */ #if CHIP_HAS_SPLIT_INTR_MASK() #if INT_PERF_COUNT < 32 || INT_AUX_PERF_COUNT < 32 || INT_MEM_ERROR >= 32 # error Fix assumptions about which word various interrupts are in diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index d1e15f7b59c..7a5aa1a7864 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -1004,15 +1004,8 @@ void __cpuinit setup_cpu(int boot) #ifdef CONFIG_BLK_DEV_INITRD -/* - * Note that the kernel can potentially support other compression - * techniques than gz, though we don't do so by default. If we ever - * decide to do so we can either look for other filename extensions, - * or just allow a file with this name to be compressed with an - * arbitrary compressor (somewhat counterintuitively). - */ static int __initdata set_initramfs_file; -static char __initdata initramfs_file[128] = "initramfs.cpio.gz"; +static char __initdata initramfs_file[128] = "initramfs"; static int __init setup_initramfs_file(char *str) { @@ -1026,9 +1019,9 @@ static int __init setup_initramfs_file(char *str) early_param("initramfs_file", setup_initramfs_file); /* - * We look for an "initramfs.cpio.gz" file in the hvfs. - * If there is one, we allocate some memory for it and it will be - * unpacked to the initramfs. + * We look for a file called "initramfs" in the hvfs. If there is one, we + * allocate some memory for it and it will be unpacked to the initramfs. + * If it's compressed, the initd code will uncompress it first. */ static void __init load_hv_initrd(void) { @@ -1038,10 +1031,16 @@ static void __init load_hv_initrd(void) fd = hv_fs_findfile((HV_VirtAddr) initramfs_file); if (fd == HV_ENOENT) { - if (set_initramfs_file) + if (set_initramfs_file) { pr_warning("No such hvfs initramfs file '%s'\n", initramfs_file); - return; + return; + } else { + /* Try old backwards-compatible name. */ + fd = hv_fs_findfile((HV_VirtAddr)"initramfs.cpio.gz"); + if (fd == HV_ENOENT) + return; + } } BUG_ON(fd < 0); stat = hv_fs_fstat(fd); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 70c0f3da047..15b5cef4aa3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1549,6 +1549,7 @@ config X86_SMAP config EFI bool "EFI runtime service support" depends on ACPI + select UCS2_STRING ---help--- This enables the kernel to use EFI runtime services that are available (such as the EFI variable services). diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 8a84501acb1..5ef205c5f37 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,7 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o +targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -29,7 +29,6 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ $(obj)/piggy.o $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone -$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone ifeq ($(CONFIG_EFI_STUB), y) VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o @@ -43,7 +42,7 @@ OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) -targets += vmlinux.bin.all vmlinux.relocs +targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs CMD_RELOCS = arch/x86/tools/relocs quiet_cmd_relocs = RELOCS $@ diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index c205035a6b9..35ee62fccf9 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -251,6 +251,51 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size) *size = len; } +static efi_status_t setup_efi_vars(struct boot_params *params) +{ + struct setup_data *data; + struct efi_var_bootdata *efidata; + u64 store_size, remaining_size, var_size; + efi_status_t status; + + if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + status = efi_call_phys4((void *)sys_table->runtime->query_variable_info, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, &store_size, + &remaining_size, &var_size); + + if (status != EFI_SUCCESS) + return status; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, sizeof(*efidata), &efidata); + + if (status != EFI_SUCCESS) + return status; + + efidata->data.type = SETUP_EFI_VARS; + efidata->data.len = sizeof(struct efi_var_bootdata) - + sizeof(struct setup_data); + efidata->data.next = 0; + efidata->store_size = store_size; + efidata->remaining_size = remaining_size; + efidata->max_var_size = var_size; + + if (data) + data->next = (unsigned long)efidata; + else + params->hdr.setup_data = (unsigned long)efidata; + +} + static efi_status_t setup_efi_pci(struct boot_params *params) { efi_pci_io_protocol *pci; @@ -1157,6 +1202,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, setup_graphics(boot_params); + setup_efi_vars(boot_params); + setup_efi_pci(boot_params); status = efi_call_phys3(sys_table->boottime->allocate_pool, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 60c89f30c72..2fb5d5884e2 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -102,6 +102,13 @@ extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); +struct efi_var_bootdata { + struct setup_data data; + u64 store_size; + u64 remaining_size; + u64 max_var_size; +}; + #ifdef CONFIG_EFI static inline bool efi_is_native(void) diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index d3ddd17405d..5a6d2873f80 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -77,6 +77,7 @@ struct arch_specific_insn { * a post_handler or break_handler). */ int boostable; + bool if_modifier; }; struct arch_optimized_insn { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 635a74d2240..4979778cc7f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -414,8 +414,8 @@ struct kvm_vcpu_arch { gpa_t time; struct pvclock_vcpu_time_info hv_clock; unsigned int hw_tsc_khz; - unsigned int time_offset; - struct page *time_page; + struct gfn_to_hva_cache pv_time; + bool pv_time_enabled; /* set guest stopped flag in pvclock flags field */ bool pvclock_set_guest_stopped_request; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 5edd1742cfd..7361e47db79 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -703,7 +703,10 @@ static inline void arch_leave_lazy_mmu_mode(void) PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave); } -void arch_flush_lazy_mmu_mode(void); +static inline void arch_flush_lazy_mmu_mode(void) +{ + PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush); +} static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 142236ed83a..b3b0ec1dac8 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -91,6 +91,7 @@ struct pv_lazy_ops { /* Set deferred update mode, used for batching operations. */ void (*enter)(void); void (*leave)(void); + void (*flush)(void); }; struct pv_time_ops { @@ -679,6 +680,7 @@ void paravirt_end_context_switch(struct task_struct *next); void paravirt_enter_lazy_mmu(void); void paravirt_leave_lazy_mmu(void); +void paravirt_flush_lazy_mmu(void); void _paravirt_nop(void); u32 _paravirt_ident_32(u32); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 1ace47b6259..2e188d68397 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -29,13 +29,13 @@ extern const unsigned long sys_call_table[]; */ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return regs->orig_ax & __SYSCALL_MASK; + return regs->orig_ax; } static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { - regs->ax = regs->orig_ax & __SYSCALL_MASK; + regs->ax = regs->orig_ax; } static inline long syscall_get_error(struct task_struct *task, diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 4fef20773b8..c7797307fc2 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -7,7 +7,7 @@ #define tlb_flush(tlb) \ { \ - if (tlb->fullmm == 0) \ + if (!tlb->fullmm && !tlb->need_flush_all) \ flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \ else \ flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL); \ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index c20d1ce62dc..e709884d0ef 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -382,14 +382,14 @@ HYPERVISOR_console_io(int cmd, int count, char *str) return _hypercall3(int, console_io, cmd, count, str); } -extern int __must_check HYPERVISOR_physdev_op_compat(int, void *); +extern int __must_check xen_physdev_op_compat(int, void *); static inline int HYPERVISOR_physdev_op(int cmd, void *arg) { int rc = _hypercall2(int, physdev_op, cmd, arg); if (unlikely(rc == -ENOSYS)) - rc = HYPERVISOR_physdev_op_compat(cmd, arg); + rc = xen_physdev_op_compat(cmd, arg); return rc; } diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index c15ddaf9071..08744242b8d 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -6,6 +6,7 @@ #define SETUP_E820_EXT 1 #define SETUP_DTB 2 #define SETUP_PCI 3 +#define SETUP_EFI_VARS 4 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 892ce40a747..7a060f4b411 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -44,6 +44,7 @@ #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) +#define MSR_PLATFORM_INFO 0x000000ce #define MSR_MTRRcap 0x000000fe #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index a7d26d83fb7..8f4be53ea04 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return false; - /* - * Xen emulates Hyper-V to support enlightened Windows. - * Check to see first if we are on a Xen Hypervisor. - */ - if (xen_cpuid_base()) - return false; - cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); @@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); -#if IS_ENABLED(CONFIG_HYPERV) - /* - * Setup the IDT for hypervisor callback. - */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); -#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr; void hv_register_vmbus_handler(int irq, irq_handler_t handler) { + /* + * Setup the IDT for hypervisor callback. + */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + vmbus_irq = irq; vmbus_isr = handler; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 529c8931fc0..cc45deb791b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -101,6 +101,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ + INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ @@ -149,8 +153,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = }; static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), + EVENT_EXTRA_END +}; + +static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), EVENT_EXTRA_END }; @@ -2093,7 +2103,10 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 45) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; @@ -2119,7 +2132,10 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 62) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index b05a575d56f..26830f3af0d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -314,10 +314,11 @@ int intel_pmu_drain_bts_buffer(void) if (top <= at) return 0; + memset(®s, 0, sizeof(regs)); + ds->bts_index = ds->bts_buffer_base; perf_sample_data_init(&data, 0, event->hw.last_period); - regs.ip = 0; /* * Prepare a generic sample, i.e. fill in the invariant fields. diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 3f06e614998..7bfe318d3d8 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -375,6 +375,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p) else p->ainsn.boostable = -1; + /* Check whether the instruction modifies Interrupt Flag or not */ + p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn); + /* Also, displacement change doesn't affect the first byte */ p->opcode = p->ainsn.insn[0]; } @@ -434,7 +437,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, __this_cpu_write(current_kprobe, p); kcb->kprobe_saved_flags = kcb->kprobe_old_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); - if (is_IF_modifier(p->ainsn.insn)) + if (p->ainsn.if_modifier) kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF; } diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c index 577db8417d1..833d51d6ee0 100644 --- a/arch/x86/kernel/microcode_core_early.c +++ b/arch/x86/kernel/microcode_core_early.c @@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void) u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; - if (!have_cpuid_p()) - return X86_VENDOR_UNKNOWN; - native_cpuid(&eax, &ebx, &ecx, &edx); if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) @@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void) return X86_VENDOR_UNKNOWN; } +static int __cpuinit x86_family(void) +{ + u32 eax = 0x00000001; + u32 ebx, ecx = 0, edx; + int x86; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + x86 = (eax >> 8) & 0xf; + if (x86 == 15) + x86 += (eax >> 20) & 0xff; + + return x86; +} + void __init load_ucode_bsp(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; - if (vendor == X86_VENDOR_INTEL) + vendor = x86_vendor(); + x86 = x86_family(); + + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_bsp(); } void __cpuinit load_ucode_ap(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + x86 = x86_family(); - if (vendor == X86_VENDOR_INTEL) + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_ap(); } diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c index 7890bc83895..d893e8ed8ac 100644 --- a/arch/x86/kernel/microcode_intel_early.c +++ b/arch/x86/kernel/microcode_intel_early.c @@ -90,13 +90,13 @@ microcode_phys(struct microcode_intel **mc_saved_tmp, struct microcode_intel ***mc_saved; mc_saved = (struct microcode_intel ***) - __pa_symbol(&mc_saved_data->mc_saved); + __pa_nodebug(&mc_saved_data->mc_saved); for (i = 0; i < mc_saved_data->mc_saved_count; i++) { struct microcode_intel *p; p = *(struct microcode_intel **) - __pa(mc_saved_data->mc_saved + i); - mc_saved_tmp[i] = (struct microcode_intel *)__pa(p); + __pa_nodebug(mc_saved_data->mc_saved + i); + mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p); } } #endif @@ -562,7 +562,7 @@ scan_microcode(unsigned long start, unsigned long end, struct cpio_data cd; long offset = 0; #ifdef CONFIG_X86_32 - char *p = (char *)__pa_symbol(ucode_name); + char *p = (char *)__pa_nodebug(ucode_name); #else char *p = ucode_name; #endif @@ -630,8 +630,8 @@ static void __cpuinit print_ucode(struct ucode_cpu_info *uci) if (mc_intel == NULL) return; - delay_ucode_info_p = (int *)__pa_symbol(&delay_ucode_info); - current_mc_date_p = (int *)__pa_symbol(¤t_mc_date); + delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); + current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); *delay_ucode_info_p = 1; *current_mc_date_p = mc_intel->hdr.date; @@ -659,8 +659,8 @@ static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci) } #endif -static int apply_microcode_early(struct mc_saved_data *mc_saved_data, - struct ucode_cpu_info *uci) +static int __cpuinit apply_microcode_early(struct mc_saved_data *mc_saved_data, + struct ucode_cpu_info *uci) { struct microcode_intel *mc_intel; unsigned int val[2]; @@ -741,15 +741,15 @@ load_ucode_intel_bsp(void) #ifdef CONFIG_X86_32 struct boot_params *boot_params_p; - boot_params_p = (struct boot_params *)__pa_symbol(&boot_params); + boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params); ramdisk_image = boot_params_p->hdr.ramdisk_image; ramdisk_size = boot_params_p->hdr.ramdisk_size; initrd_start_early = ramdisk_image; initrd_end_early = initrd_start_early + ramdisk_size; _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_symbol(&mc_saved_data), - (unsigned long *)__pa_symbol(&mc_saved_in_initrd), + (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), initrd_start_early, initrd_end_early, &uci); #else ramdisk_image = boot_params.hdr.ramdisk_image; @@ -772,10 +772,10 @@ void __cpuinit load_ucode_intel_ap(void) unsigned long *initrd_start_p; mc_saved_in_initrd_p = - (unsigned long *)__pa_symbol(mc_saved_in_initrd); - mc_saved_data_p = (struct mc_saved_data *)__pa_symbol(&mc_saved_data); - initrd_start_p = (unsigned long *)__pa_symbol(&initrd_start); - initrd_start_addr = (unsigned long)__pa_symbol(*initrd_start_p); + (unsigned long *)__pa_nodebug(mc_saved_in_initrd); + mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); + initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); + initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); #else mc_saved_data_p = &mc_saved_data; mc_saved_in_initrd_p = mc_saved_in_initrd; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 17fff18a103..8bfb335f74b 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void) leave_lazy(PARAVIRT_LAZY_MMU); } +void paravirt_flush_lazy_mmu(void) +{ + preempt_disable(); + + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + arch_enter_lazy_mmu_mode(); + } + + preempt_enable(); +} + void paravirt_start_context_switch(struct task_struct *prev) { BUG_ON(preemptible()); @@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) return this_cpu_read(paravirt_lazy_mode); } -void arch_flush_lazy_mmu_mode(void) -{ - preempt_disable(); - - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { - arch_leave_lazy_mmu_mode(); - arch_enter_lazy_mmu_mode(); - } - - preempt_enable(); -} - struct pv_info pv_info = { .name = "bare hardware", .paravirt_enabled = 0, @@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = { .lazy_mode = { .enter = paravirt_nop, .leave = paravirt_nop, + .flush = paravirt_nop, }, .set_fixmap = native_set_fixmap, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90d8cc930f5..fae9134a2de 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -507,11 +507,14 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64bit, old kexec-tools need to under 896MiB. */ #ifdef CONFIG_X86_32 -# define CRASH_KERNEL_ADDR_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_MAX MAXMEM +# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) +# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM #endif static void __init reserve_crashkernel_low(void) @@ -521,19 +524,35 @@ static void __init reserve_crashkernel_low(void) unsigned long long low_base = 0, low_size = 0; unsigned long total_low_mem; unsigned long long base; + bool auto_set = false; int ret; total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + /* crashkernel=Y,low */ ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); - if (ret != 0 || low_size <= 0) - return; + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel=0,low ? */ + if (!low_size) + return; + } low_base = memblock_find_in_range(low_size, (1ULL<<32), low_size, alignment); if (!low_base) { - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); return; } @@ -554,14 +573,22 @@ static void __init reserve_crashkernel(void) const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long total_mem; unsigned long long crash_size, crash_base; + bool high = false; int ret; total_mem = memblock_phys_mem_size(); + /* crashkernel=XM */ ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) - return; + if (ret != 0 || crash_size <= 0) { + /* crashkernel=X,high */ + ret = parse_crashkernel_high(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret != 0 || crash_size <= 0) + return; + high = true; + } /* 0 means: find the address automatically */ if (crash_base <= 0) { @@ -569,7 +596,9 @@ static void __init reserve_crashkernel(void) * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ crash_base = memblock_find_in_range(alignment, - CRASH_KERNEL_ADDR_MAX, crash_size, alignment); + high ? CRASH_KERNEL_ADDR_HIGH_MAX : + CRASH_KERNEL_ADDR_LOW_MAX, + crash_size, alignment); if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 02b51dd4e4a..f77df1c5de6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1857,7 +1857,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) if (!pv_eoi_enabled(vcpu)) return 0; return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data, - addr); + addr, sizeof(u8)); } void kvm_lapic_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f71500af1f8..e1721324c27 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1406,25 +1406,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) unsigned long flags, this_tsc_khz; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; - void *shared_kaddr; s64 kernel_ns, max_kernel_ns; u64 tsc_timestamp, host_tsc; - struct pvclock_vcpu_time_info *guest_hv_clock; + struct pvclock_vcpu_time_info guest_hv_clock; u8 pvclock_flags; bool use_master_clock; kernel_ns = 0; host_tsc = 0; - /* Keep irq disabled to prevent changes to the clock */ - local_irq_save(flags); - this_tsc_khz = __get_cpu_var(cpu_tsc_khz); - if (unlikely(this_tsc_khz == 0)) { - local_irq_restore(flags); - kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); - return 1; - } - /* * If the host uses TSC clock, then passthrough TSC as stable * to the guest. @@ -1436,6 +1426,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) kernel_ns = ka->master_kernel_ns; } spin_unlock(&ka->pvclock_gtod_sync_lock); + + /* Keep irq disabled to prevent changes to the clock */ + local_irq_save(flags); + this_tsc_khz = __get_cpu_var(cpu_tsc_khz); + if (unlikely(this_tsc_khz == 0)) { + local_irq_restore(flags); + kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); + return 1; + } if (!use_master_clock) { host_tsc = native_read_tsc(); kernel_ns = get_kernel_ns(); @@ -1463,7 +1462,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) local_irq_restore(flags); - if (!vcpu->time_page) + if (!vcpu->pv_time_enabled) return 0; /* @@ -1525,12 +1524,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) */ vcpu->hv_clock.version += 2; - shared_kaddr = kmap_atomic(vcpu->time_page); - - guest_hv_clock = shared_kaddr + vcpu->time_offset; + if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, + &guest_hv_clock, sizeof(guest_hv_clock)))) + return 0; /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ - pvclock_flags = (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED); + pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); if (vcpu->pvclock_set_guest_stopped_request) { pvclock_flags |= PVCLOCK_GUEST_STOPPED; @@ -1543,12 +1542,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; - memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); - - kunmap_atomic(shared_kaddr); - - mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT); + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); return 0; } @@ -1827,7 +1823,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 0; } - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa)) + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + sizeof(u32))) return 1; vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); @@ -1837,10 +1834,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { - if (vcpu->arch.time_page) { - kvm_release_page_dirty(vcpu->arch.time_page); - vcpu->arch.time_page = NULL; - } + vcpu->arch.pv_time_enabled = false; } static void accumulate_steal_time(struct kvm_vcpu *vcpu) @@ -1947,6 +1941,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_KVM_SYSTEM_TIME_NEW: case MSR_KVM_SYSTEM_TIME: { + u64 gpa_offset; kvmclock_reset(vcpu); vcpu->arch.time = data; @@ -1956,14 +1951,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & 1)) break; - /* ...but clean it before doing the actual write */ - vcpu->arch.time_offset = data & ~(PAGE_MASK | 1); - - vcpu->arch.time_page = - gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT); + gpa_offset = data & ~(PAGE_MASK | 1); - if (is_error_page(vcpu->arch.time_page)) - vcpu->arch.time_page = NULL; + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.pv_time, data & ~1ULL, + sizeof(struct pvclock_vcpu_time_info))) + vcpu->arch.pv_time_enabled = false; + else + vcpu->arch.pv_time_enabled = true; break; } @@ -1980,7 +1975,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS)) + data & KVM_STEAL_VALID_BITS, + sizeof(struct kvm_steal_time))) return 1; vcpu->arch.st.msr_val = data; @@ -2967,7 +2963,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, */ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) { - if (!vcpu->arch.time_page) + if (!vcpu->arch.pv_time_enabled) return -EINVAL; vcpu->arch.pvclock_set_guest_stopped_request = true; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -6718,6 +6714,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_wbinvd_dirty_mask; vcpu->arch.ia32_tsc_adjust_msr = 0x0; + vcpu->arch.pv_time_enabled = false; kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 1cbd89ca556..7114c63f047 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1334,6 +1334,7 @@ __init void lguest_init(void) pv_mmu_ops.read_cr3 = lguest_read_cr3; pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; + pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; pv_mmu_ops.pte_update = lguest_pte_update; pv_mmu_ops.pte_update_defer = lguest_pte_update; diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 05928aae911..906fea31579 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -74,10 +74,10 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest) char c; unsigned zero_len; - for (; len; --len) { + for (; len; --len, to++) { if (__get_user_nocheck(c, from++, sizeof(char))) break; - if (__put_user_nocheck(c, to++, sizeof(char))) + if (__put_user_nocheck(c, to, sizeof(char))) break; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2b97525246d..0e883364abb 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -378,10 +378,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) if (pgd_none(*pgd_ref)) return -1; - if (pgd_none(*pgd)) + if (pgd_none(*pgd)) { set_pgd(pgd, *pgd_ref); - else + arch_flush_lazy_mmu_mode(); + } else { BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + } /* * Below here mismatches are bugs because these lower tables diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index b0086567271..0e38951e65e 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -68,7 +68,7 @@ static int print_split(struct split_state *s) s->gpg++; i += GPS/PAGE_SIZE; } else if (level == PG_LEVEL_2M) { - if (!(pte_val(*pte) & _PAGE_PSE)) { + if ((pte_val(*pte) & _PAGE_PRESENT) && !(pte_val(*pte) & _PAGE_PSE)) { printk(KERN_ERR "%lx level %d but not PSE %Lx\n", addr, level, (u64)pte_val(*pte)); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 091934e1d0d..fb4e73ec24d 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -467,7 +467,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * We are safe now. Check whether the new pgprot is the same: */ old_pte = *kpte; - old_prot = new_prot = req_prot = pte_pgprot(old_pte); + old_prot = req_prot = pte_pgprot(old_pte); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); @@ -478,12 +478,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL * for the ancient hardware that doesn't support it. */ - if (pgprot_val(new_prot) & _PAGE_PRESENT) - pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL; + if (pgprot_val(req_prot) & _PAGE_PRESENT) + pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL; else - pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); + pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); - new_prot = canon_pgprot(new_prot); + req_prot = canon_pgprot(req_prot); /* * old_pte points to the large page base address. So we need @@ -1413,6 +1413,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable) * but that can deadlock->flush only current cpu: */ __flush_tlb_all(); + + arch_flush_lazy_mmu_mode(); } #ifdef CONFIG_HIBERNATION diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 193350b51f9..17fda6a8b3c 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -58,6 +58,13 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); + /* + * NOTE! For PAE, any changes to the top page-directory-pointer-table + * entries need a full cr3 reload to flush. + */ +#ifdef CONFIG_X86_PAE + tlb->need_flush_all = 1; +#endif tlb_remove_page(tlb, virt_to_page(pmd)); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 5f2ecaf3f9d..e4a86a677ce 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -41,6 +41,7 @@ #include <linux/io.h> #include <linux/reboot.h> #include <linux/bcd.h> +#include <linux/ucs2_string.h> #include <asm/setup.h> #include <asm/efi.h> @@ -51,6 +52,13 @@ #define EFI_DEBUG 1 +/* + * There's some additional metadata associated with each + * variable. Intel's reference implementation is 60 bytes - bump that + * to account for potential alignment constraints + */ +#define VAR_METADATA_SIZE 64 + struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, .acpi = EFI_INVALID_TABLE_ADDR, @@ -69,6 +77,13 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; +static u64 efi_var_store_size; +static u64 efi_var_remaining_size; +static u64 efi_var_max_var_size; +static u64 boot_used_size; +static u64 boot_var_size; +static u64 active_size; + unsigned long x86_efi_facility; /* @@ -98,6 +113,15 @@ static int __init setup_add_efi_memmap(char *arg) } early_param("add_efi_memmap", setup_add_efi_memmap); +static bool efi_no_storage_paranoia; + +static int __init setup_storage_paranoia(char *arg) +{ + efi_no_storage_paranoia = true; + return 0; +} +early_param("efi_no_storage_paranoia", setup_storage_paranoia); + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { @@ -162,8 +186,53 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - return efi_call_virt3(get_next_variable, - name_size, name, vendor); + efi_status_t status; + static bool finished = false; + static u64 var_size; + + status = efi_call_virt3(get_next_variable, + name_size, name, vendor); + + if (status == EFI_NOT_FOUND) { + finished = true; + if (var_size < boot_used_size) { + boot_var_size = boot_used_size - var_size; + active_size += boot_var_size; + } else { + printk(KERN_WARNING FW_BUG "efi: Inconsistent initial sizes\n"); + } + } + + if (boot_used_size && !finished) { + unsigned long size; + u32 attr; + efi_status_t s; + void *tmp; + + s = virt_efi_get_variable(name, vendor, &attr, &size, NULL); + + if (s != EFI_BUFFER_TOO_SMALL || !size) + return status; + + tmp = kmalloc(size, GFP_ATOMIC); + + if (!tmp) + return status; + + s = virt_efi_get_variable(name, vendor, &attr, &size, tmp); + + if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) { + var_size += size; + var_size += ucs2_strsize(name, 1024); + active_size += size; + active_size += VAR_METADATA_SIZE; + active_size += ucs2_strsize(name, 1024); + } + + kfree(tmp); + } + + return status; } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -172,9 +241,34 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - return efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); + efi_status_t status; + u32 orig_attr = 0; + unsigned long orig_size = 0; + + status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size, + NULL); + + if (status != EFI_BUFFER_TOO_SMALL) + orig_size = 0; + + status = efi_call_virt5(set_variable, + name, vendor, attr, + data_size, data); + + if (status == EFI_SUCCESS) { + if (orig_size) { + active_size -= orig_size; + active_size -= ucs2_strsize(name, 1024); + active_size -= VAR_METADATA_SIZE; + } + if (data_size) { + active_size += data_size; + active_size += ucs2_strsize(name, 1024); + active_size += VAR_METADATA_SIZE; + } + } + + return status; } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -682,6 +776,9 @@ void __init efi_init(void) char vendor[100] = "unknown"; int i = 0; void *tmp; + struct setup_data *data; + struct efi_var_bootdata *efi_var_data; + u64 pa_data; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -699,6 +796,22 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = early_ioremap(pa_data, sizeof(*efi_var_data)); + if (data->type == SETUP_EFI_VARS) { + efi_var_data = (struct efi_var_bootdata *)data; + + efi_var_store_size = efi_var_data->store_size; + efi_var_remaining_size = efi_var_data->remaining_size; + efi_var_max_var_size = efi_var_data->max_var_size; + } + pa_data = data->next; + early_iounmap(data, sizeof(*efi_var_data)); + } + + boot_used_size = efi_var_store_size - efi_var_remaining_size; + set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); /* @@ -999,3 +1112,48 @@ u64 efi_mem_attributes(unsigned long phys_addr) } return 0; } + +/* + * Some firmware has serious problems when using more than 50% of the EFI + * variable store, i.e. it triggers bugs that can brick machines. Ensure that + * we never use more than this safe limit. + * + * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable + * store. + */ +efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + efi_status_t status; + u64 storage_size, remaining_size, max_size; + + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); + if (status != EFI_SUCCESS) + return status; + + if (!max_size && remaining_size > size) + printk_once(KERN_ERR FW_BUG "Broken EFI implementation" + " is returning MaxVariableSize=0\n"); + /* + * Some firmware implementations refuse to boot if there's insufficient + * space in the variable store. We account for that by refusing the + * write if permitting it would reduce the available space to under + * 50%. However, some firmware won't reclaim variable space until + * after the used (not merely the actively used) space drops below + * a threshold. We can approximate that case with the value calculated + * above. If both the firmware and our calculations indicate that the + * available space would drop below 50%, refuse the write. + */ + + if (!storage_size || size > remaining_size || + (max_size && size > max_size)) + return EFI_OUT_OF_RESOURCES; + + if (!efi_no_storage_paranoia && + ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) && + (remaining_size - size < storage_size / 2))) + return EFI_OUT_OF_RESOURCES; + + return EFI_SUCCESS; +} +EXPORT_SYMBOL_GPL(efi_query_variable_store); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index e8e34938c57..e006c18d288 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1467,8 +1467,6 @@ static void __init xen_write_cr3_init(unsigned long cr3) __xen_write_cr3(true, cr3); xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ - - pv_mmu_ops.write_cr3 = &xen_write_cr3; } #endif @@ -1750,14 +1748,18 @@ static void *m2v(phys_addr_t maddr) } /* Set the page permissions on an identity-mapped pages */ -static void set_page_prot(void *addr, pgprot_t prot) +static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags) { unsigned long pfn = __pa(addr) >> PAGE_SHIFT; pte_t pte = pfn_pte(pfn, prot); - if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0)) + if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags)) BUG(); } +static void set_page_prot(void *addr, pgprot_t prot) +{ + return set_page_prot_flags(addr, prot, UVMF_NONE); +} #ifdef CONFIG_X86_32 static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) { @@ -1841,12 +1843,12 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, unsigned long addr) { if (*pt_base == PFN_DOWN(__pa(addr))) { - set_page_prot((void *)addr, PAGE_KERNEL); + set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG); clear_page((void *)addr); (*pt_base)++; } if (*pt_end == PFN_DOWN(__pa(addr))) { - set_page_prot((void *)addr, PAGE_KERNEL); + set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG); clear_page((void *)addr); (*pt_end)--; } @@ -2122,6 +2124,7 @@ static void __init xen_post_allocator_init(void) #endif #ifdef CONFIG_X86_64 + pv_mmu_ops.write_cr3 = &xen_write_cr3; SetPagePinned(virt_to_page(level3_user_vsyscall)); #endif xen_mark_init_mm_pinned(); @@ -2197,6 +2200,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .lazy_mode = { .enter = paravirt_enter_lazy_mmu, .leave = xen_leave_lazy_mmu, + .flush = paravirt_flush_lazy_mmu, }, .set_fixmap = xen_set_fixmap, |