diff options
Diffstat (limited to 'arch/arm64')
73 files changed, 3179 insertions, 545 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 56b3f6d447a..517fd2e8f70 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1,6 +1,8 @@ config ARM64 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE + select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_COMPAT_IPC_PARSE_VERSION select ARCH_WANT_FRAME_POINTERS @@ -9,7 +11,9 @@ config ARM64 select ARM_GIC select CLONE_BACKWARDS select COMMON_CLK + select CPU_PM if (SUSPEND || CPU_IDLE) select GENERIC_CLOCKEVENTS + select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_IOMAP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW @@ -130,6 +134,11 @@ config ARM64_64K_PAGES look-up. AArch32 emulation is not available when this feature is enabled. +config CPU_BIG_ENDIAN + bool "Build big-endian kernel" + help + Say Y if you plan on running a kernel in big-endian mode. + config SMP bool "Symmetric Multi-Processing" select USE_GENERIC_SMP_HELPERS @@ -144,12 +153,139 @@ config SMP If you don't know what to do here, say N. +config ARM_CPU_TOPOLOGY + bool "Support CPU topology definition" + depends on SMP + default y + help + Support CPU topology definition, based on configuration + provided by the firmware. + +config SCHED_MC + bool "Multi-core scheduler support" + depends on ARM_CPU_TOPOLOGY + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + +config SCHED_SMT + bool "SMT scheduler support" + depends on ARM_CPU_TOPOLOGY + help + Improves the CPU scheduler's decision making when dealing with + MultiThreading at a cost of slightly increased overhead in some + places. If unsure say N here. + +config DISABLE_CPU_SCHED_DOMAIN_BALANCE + bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing" + help + Disables scheduler load-balancing at CPU sched domain level. + +config SCHED_HMP + bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling" + depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP + help + Experimental scheduler optimizations for heterogeneous platforms. + Attempts to introspectively select task affinity to optimize power + and performance. Basic support for multiple (>2) cpu types is in place, + but it has only been tested with two types of cpus. + There is currently no support for migration of task groups, hence + !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled + between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE). + +config SCHED_HMP_PRIO_FILTER + bool "(EXPERIMENTAL) Filter HMP migrations by task priority" + depends on SCHED_HMP + help + Enables task priority based HMP migration filter. Any task with + a NICE value above the threshold will always be on low-power cpus + with less compute capacity. + +config SCHED_HMP_PRIO_FILTER_VAL + int "NICE priority threshold" + default 5 + depends on SCHED_HMP_PRIO_FILTER + +config HMP_FAST_CPU_MASK + string "HMP scheduler fast CPU mask" + depends on SCHED_HMP + help + Leave empty to use device tree information. + Specify the cpuids of the fast CPUs in the system as a list string, + e.g. cpuid 0+1 should be specified as 0-1. + +config HMP_SLOW_CPU_MASK + string "HMP scheduler slow CPU mask" + depends on SCHED_HMP + help + Leave empty to use device tree information. + Specify the cpuids of the slow CPUs in the system as a list string, + e.g. cpuid 0+1 should be specified as 0-1. + +config HMP_VARIABLE_SCALE + bool "Allows changing the load tracking scale through sysfs" + depends on SCHED_HMP + help + When turned on, this option exports the thresholds and load average + period value for the load tracking patches through sysfs. + The values can be modified to change the rate of load accumulation + and the thresholds used for HMP migration. + The load_avg_period_ms is the time in ms to reach a load average of + 0.5 for an idle task of 0 load average ratio that start a busy loop. + The up_threshold and down_threshold is the value to go to a faster + CPU or to go back to a slower cpu. + The {up,down}_threshold are devided by 1024 before being compared + to the load average. + For examples, with load_avg_period_ms = 128 and up_threshold = 512, + a running task with a load of 0 will be migrated to a bigger CPU after + 128ms, because after 128ms its load_avg_ratio is 0.5 and the real + up_threshold is 0.5. + This patch has the same behavior as changing the Y of the load + average computation to + (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms) + but it remove intermadiate overflows in computation. + +config HMP_FREQUENCY_INVARIANT_SCALE + bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP" + depends on HMP_VARIABLE_SCALE && CPU_FREQ + help + Scales the current load contribution in line with the frequency + of the CPU that the task was executed on. + In this version, we use a simple linear scale derived from the + maximum frequency reported by CPUFreq. + Restricting tracked load to be scaled by the CPU's frequency + represents the consumption of possible compute capacity + (rather than consumption of actual instantaneous capacity as + normal) and allows the HMP migration's simple threshold + migration strategy to interact more predictably with CPUFreq's + asynchronous compute capacity changes. + +config SCHED_HMP_LITTLE_PACKING + bool "Small task packing for HMP" + depends on SCHED_HMP + default n + help + Allows the HMP Scheduler to pack small tasks into CPUs in the + smallest HMP domain. + Controlled by two sysfs files in sys/kernel/hmp. + packing_enable: 1 to enable, 0 to disable packing. Default 1. + packing_limit: runqueue load ratio where a RQ is considered + to be full. Default is NICE_0_LOAD * 9/8. + config NR_CPUS int "Maximum number of CPUs (2-32)" range 2 32 depends on SMP default "4" +config HOTPLUG_CPU + bool "Support for hot-pluggable CPUs" + depends on SMP + help + Say Y here to experiment with turning CPUs off and on. CPUs + can be controlled through /sys/devices/system/cpu. + source kernel/Kconfig.preempt config HZ @@ -180,8 +316,25 @@ config HW_PERF_EVENTS Enable hardware performance counter support for perf events. If disabled, perf events will use software events only. +config SYS_SUPPORTS_HUGETLBFS + def_bool y + +config ARCH_WANT_GENERAL_HUGETLB + def_bool y + +config ARCH_WANT_HUGE_PMD_SHARE + def_bool y if !ARM64_64K_PAGES + +config HAVE_ARCH_TRANSPARENT_HUGEPAGE + def_bool y + source "mm/Kconfig" +config FORCE_MAX_ZONEORDER + int + default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE) + default "11" + endmenu menu "Boot options" @@ -229,6 +382,25 @@ config SYSVIPC_COMPAT endmenu +menu "Power management options" + +source "kernel/power/Kconfig" + +source "drivers/cpufreq/Kconfig" +config ARCH_SUSPEND_POSSIBLE + def_bool y + +config ARM64_CPU_SUSPEND + def_bool PM_SLEEP + +endmenu + +menu "CPU Power Management" + +source "drivers/cpuidle/Kconfig" + +endmenu + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index c95c5cb212f..3a926eb93c9 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -20,9 +20,15 @@ LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) KBUILD_DEFCONFIG := defconfig KBUILD_CFLAGS += -mgeneral-regs-only +ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) +KBUILD_CPPFLAGS += -mbig-endian +AS += -EB +LD += -EB +else KBUILD_CPPFLAGS += -mlittle-endian AS += -EL LD += -EL +endif comma = , diff --git a/arch/arm64/boot/dts/foundation-v8.dts b/arch/arm64/boot/dts/foundation-v8.dts index 84fcc501828..519c4b2c068 100644 --- a/arch/arm64/boot/dts/foundation-v8.dts +++ b/arch/arm64/boot/dts/foundation-v8.dts @@ -6,6 +6,8 @@ /dts-v1/; +/memreserve/ 0x80000000 0x00010000; + / { model = "Foundation-v8A"; compatible = "arm,foundation-aarch64", "arm,vexpress"; diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 79a642d199f..ae0612c4fa4 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -26,7 +26,6 @@ generic-y += mman.h generic-y += msgbuf.h generic-y += mutex.h generic-y += pci.h -generic-y += percpu.h generic-y += poll.h generic-y += posix_types.h generic-y += resource.h diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index bf6ab242f04..d56ed11ba9a 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -110,16 +110,6 @@ static inline void __cpuinit arch_counter_set_user_access(void) asm volatile("msr cntkctl_el1, %0" : : "r" (cntkctl)); } -static inline u64 arch_counter_get_cntpct(void) -{ - u64 cval; - - isb(); - asm volatile("mrs %0, cntpct_el0" : "=r" (cval)); - - return cval; -} - static inline u64 arch_counter_get_cntvct(void) { u64 cval; diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 5aceb83b3f5..fd3e3924041 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -115,3 +115,34 @@ lr .req x30 // link register .align 7 b \label .endm + +/* + * Select code when configured for BE. + */ +#ifdef CONFIG_CPU_BIG_ENDIAN +#define CPU_BE(code...) code +#else +#define CPU_BE(code...) +#endif + +/* + * Select code when configured for LE. + */ +#ifdef CONFIG_CPU_BIG_ENDIAN +#define CPU_LE(code...) +#else +#define CPU_LE(code...) code +#endif + +/* + * Define a macro that constructs a 64-bit value by concatenating two + * 32-bit registers. Note that on big endian systems the order of the + * registers is swapped. + */ +#ifndef CONFIG_CPU_BIG_ENDIAN + .macro regs_to_64, rd, lbits, hbits +#else + .macro regs_to_64, rd, hbits, lbits +#endif + orr \rd, \lbits, \hbits, lsl #32 + .endm diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 3300cbd18a8..d6ac12e1186 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -85,6 +85,13 @@ static inline void flush_cache_page(struct vm_area_struct *vma, } /* + * Cache maintenance functions used by the DMA API. No to be used directly. + */ +extern void __dma_map_area(const void *, size_t, int); +extern void __dma_unmap_area(const void *, size_t, int); +extern void __dma_flush_range(const void *, const void *); + +/* * Copy user data from/to a page which is mapped into a different * processes address space. Really, we want to allow our "user * space" model to handle this. @@ -116,6 +123,7 @@ extern void flush_dcache_page(struct page *); static inline void __flush_icache_all(void) { asm("ic ialluis"); + dsb(); } #define flush_dcache_mmap_lock(mapping) \ diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 8a8ce0e73a3..68d7c932a9c 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -158,17 +158,23 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old, return ret; } -#define cmpxchg(ptr,o,n) \ - ((__typeof__(*(ptr)))__cmpxchg_mb((ptr), \ - (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) - -#define cmpxchg_local(ptr,o,n) \ - ((__typeof__(*(ptr)))__cmpxchg((ptr), \ - (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) +#define cmpxchg(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __ret = (__typeof__(*(ptr))) \ + __cmpxchg_mb((ptr), (unsigned long)(o), (unsigned long)(n), \ + sizeof(*(ptr))); \ + __ret; \ +}) + +#define cmpxchg_local(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __ret = (__typeof__(*(ptr))) \ + __cmpxchg((ptr), (unsigned long)(o), \ + (unsigned long)(n), sizeof(*(ptr))); \ + __ret; \ +}) #define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n)) #define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n)) diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 899af807ef0..fda2704b3f9 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -26,7 +26,11 @@ #include <linux/ptrace.h> #define COMPAT_USER_HZ 100 +#ifdef __AARCH64EB__ +#define COMPAT_UTS_MACHINE "armv8b\0\0" +#else #define COMPAT_UTS_MACHINE "armv8l\0\0" +#endif typedef u32 compat_size_t; typedef s32 compat_ssize_t; @@ -73,13 +77,23 @@ struct compat_timeval { }; struct compat_stat { +#ifdef __AARCH64EB__ + short st_dev; + short __pad1; +#else compat_dev_t st_dev; +#endif compat_ino_t st_ino; compat_mode_t st_mode; compat_ushort_t st_nlink; __compat_uid16_t st_uid; __compat_gid16_t st_gid; +#ifdef __AARCH64EB__ + short st_rdev; + short __pad2; +#else compat_dev_t st_rdev; +#endif compat_off_t st_size; compat_off_t st_blksize; compat_off_t st_blocks; diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h new file mode 100644 index 00000000000..15241307650 --- /dev/null +++ b/arch/arm64/include/asm/cpu_ops.h @@ -0,0 +1,65 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#ifndef __ASM_CPU_OPS_H +#define __ASM_CPU_OPS_H + +#include <linux/init.h> +#include <linux/threads.h> + +struct device_node; + +/** + * struct cpu_operations - Callback operations for hotplugging CPUs. + * + * @name: Name of the property as appears in a devicetree cpu node's + * enable-method property. + * @cpu_init: Reads any data necessary for a specific enable-method from the + * devicetree, for a given cpu node and proposed logical id. + * @cpu_prepare: Early one-time preparation step for a cpu. If there is a + * mechanism for doing so, tests whether it is possible to boot + * the given CPU. + * @cpu_boot: Boots a cpu into the kernel. + * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary + * synchronisation. Called from the cpu being booted. + * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific + * reason, which will cause the hot unplug to be aborted. Called + * from the cpu to be killed. + * @cpu_die: Makes a cpu leave the kernel. Must not fail. Called from the + * cpu being killed. + * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing + * to wrong parameters or error conditions. Called from the + * CPU being suspended. Must be called with IRQs disabled. + */ +struct cpu_operations { + const char *name; + int (*cpu_init)(struct device_node *, unsigned int); + int (*cpu_prepare)(unsigned int); + int (*cpu_boot)(unsigned int); + void (*cpu_postboot)(void); +#ifdef CONFIG_HOTPLUG_CPU + int (*cpu_disable)(unsigned int cpu); + void (*cpu_die)(unsigned int cpu); +#endif +#ifdef CONFIG_ARM64_CPU_SUSPEND + int (*cpu_suspend)(unsigned long); +#endif +}; + +extern const struct cpu_operations *cpu_ops[NR_CPUS]; +extern int __init cpu_read_ops(struct device_node *dn, int cpu); +extern void __init cpu_read_bootcpu_ops(void); + +#endif /* ifndef __ASM_CPU_OPS_H */ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index cf2749488cd..a8053d89512 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -30,6 +30,16 @@ #define MPIDR_HWID_BITMASK 0xff00ffffff +#define MPIDR_LEVEL_BITS_SHIFT 3 +#define MPIDR_LEVEL_BITS (1 << MPIDR_LEVEL_BITS_SHIFT) +#define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1) + +#define MPIDR_LEVEL_SHIFT(level) \ + (((1 << level) >> 1) << MPIDR_LEVEL_BITS_SHIFT) + +#define MPIDR_AFFINITY_LEVEL(mpidr, level) \ + ((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK) + #define read_cpuid(reg) ({ \ u64 __val; \ asm("mrs %0, " reg : "=r" (__val)); \ diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index 99477689419..00a41aab4a3 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -25,7 +25,10 @@ #define ARCH_HAS_DMA_GET_REQUIRED_MASK +#define DMA_ERROR_CODE (~(dma_addr_t)0) extern struct dma_map_ops *dma_ops; +extern struct dma_map_ops coherent_swiotlb_dma_ops; +extern struct dma_map_ops noncoherent_swiotlb_dma_ops; static inline struct dma_map_ops *get_dma_ops(struct device *dev) { @@ -35,6 +38,11 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) return dev->archdata.dma_ops; } +static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops) +{ + dev->archdata.dma_ops = ops; +} + #include <asm-generic/dma-mapping-common.h> static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) @@ -81,8 +89,12 @@ static inline void dma_mark_clean(void *addr, size_t size) { } -static inline void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flags) +#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL) +#define dma_free_coherent(d, s, h, f) dma_free_attrs(d, s, h, f, NULL) + +static inline void *dma_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) { struct dma_map_ops *ops = get_dma_ops(dev); void *vaddr; @@ -90,13 +102,14 @@ static inline void *dma_alloc_coherent(struct device *dev, size_t size, if (dma_alloc_from_coherent(dev, size, dma_handle, &vaddr)) return vaddr; - vaddr = ops->alloc(dev, size, dma_handle, flags, NULL); + vaddr = ops->alloc(dev, size, dma_handle, flags, attrs); debug_dma_alloc_coherent(dev, size, *dma_handle, vaddr); return vaddr; } -static inline void dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dev_addr) +static inline void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t dev_addr, + struct dma_attrs *attrs) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -104,7 +117,7 @@ static inline void dma_free_coherent(struct device *dev, size_t size, return; debug_dma_free_coherent(dev, size, vaddr, dev_addr); - ops->free(dev, size, vaddr, dev_addr, NULL); + ops->free(dev, size, vaddr, dev_addr, attrs); } /* diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index fe32c0e4ac0..212b0b615b4 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -92,11 +92,24 @@ typedef struct user_fpsimd_state elf_fpregset_t; * These are used to set parameters in the core dumps. */ #define ELF_CLASS ELFCLASS64 +#ifdef __AARCH64EB__ +#define ELF_DATA ELFDATA2MSB +#else #define ELF_DATA ELFDATA2LSB +#endif #define ELF_ARCH EM_AARCH64 +/* + * This yields a string that ld.so will use to load implementation + * specific libraries for optimization. This is more specific in + * intent than poking at uname or /proc/cpuinfo. + */ #define ELF_PLATFORM_SIZE 16 +#ifdef __AARCH64EB__ +#define ELF_PLATFORM ("aarch64_be") +#else #define ELF_PLATFORM ("aarch64") +#endif /* * This is used to ensure we don't load something for the wrong architecture. @@ -152,7 +165,12 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm); #ifdef CONFIG_COMPAT #define EM_ARM 40 + +#ifdef __AARCH64EB__ +#define COMPAT_ELF_PLATFORM ("v8b") +#else #define COMPAT_ELF_PLATFORM ("v8l") +#endif #define COMPAT_ELF_ET_DYN_BASE (randomize_et_dyn(2 * TASK_SIZE_32 / 3)) diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index 990c051e782..ae4801d7751 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -20,7 +20,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 4 +#define NR_IPI 5 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h new file mode 100644 index 00000000000..5b7ca8ace95 --- /dev/null +++ b/arch/arm64/include/asm/hugetlb.h @@ -0,0 +1,117 @@ +/* + * arch/arm64/include/asm/hugetlb.h + * + * Copyright (C) 2013 Linaro Ltd. + * + * Based on arch/x86/include/asm/hugetlb.h + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __ASM_HUGETLB_H +#define __ASM_HUGETLB_H + +#include <asm-generic/hugetlb.h> +#include <asm/page.h> + +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + return *ptep; +} + +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + set_pte_at(mm, addr, ptep, pte); +} + +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + ptep_clear_flush(vma, addr, ptep); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + ptep_set_wrprotect(mm, addr, ptep); +} + +static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + return ptep_get_and_clear(mm, addr, ptep); +} + +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); +} + +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, + unsigned long ceiling) +{ + free_pgd_range(tlb, addr, end, floor, ceiling); +} + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} + +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) +{ + struct hstate *h = hstate_file(file); + if (len & ~huge_page_mask(h)) + return -EINVAL; + if (addr & ~huge_page_mask(h)) + return -EINVAL; + return 0; +} + +static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) +{ +} + +static inline int huge_pte_none(pte_t pte) +{ + return pte_none(pte); +} + +static inline pte_t huge_pte_wrprotect(pte_t pte) +{ + return pte_wrprotect(pte); +} + +static inline int arch_prepare_hugepage(struct page *page) +{ + return 0; +} + +static inline void arch_release_hugepage(struct page *page) +{ +} + +static inline void arch_clear_hugepage_flags(struct page *page) +{ + clear_bit(PG_dcache_clean, &page->flags); +} + +#endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index 0332fc077f6..e1f7ecdde11 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -4,6 +4,7 @@ #include <asm-generic/irq.h> extern void (*handle_arch_irq)(struct pt_regs *); +extern void migrate_irqs(void); extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); #endif diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h new file mode 100644 index 00000000000..13fb0b3efc5 --- /dev/null +++ b/arch/arm64/include/asm/percpu.h @@ -0,0 +1,41 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#ifndef __ASM_PERCPU_H +#define __ASM_PERCPU_H + +static inline void set_my_cpu_offset(unsigned long off) +{ + asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory"); +} + +static inline unsigned long __my_cpu_offset(void) +{ + unsigned long off; + register unsigned long *sp asm ("sp"); + + /* + * We want to allow caching the value, so avoid using volatile and + * instead use a fake stack read to hazard against barrier(). + */ + asm("mrs %0, tpidr_el1" : "=r" (off) : "Q" (*sp)); + + return off; +} +#define __my_cpu_offset __my_cpu_offset() + +#include <asm-generic/percpu.h> + +#endif /* __ASM_PERCPU_H */ diff --git a/arch/arm64/include/asm/pgtable-3level-types.h b/arch/arm64/include/asm/pgtable-3level-types.h index 4489615f14a..4e94424938a 100644 --- a/arch/arm64/include/asm/pgtable-3level-types.h +++ b/arch/arm64/include/asm/pgtable-3level-types.h @@ -16,6 +16,8 @@ #ifndef __ASM_PGTABLE_3LEVEL_TYPES_H #define __ASM_PGTABLE_3LEVEL_TYPES_H +#include <asm/types.h> + typedef u64 pteval_t; typedef u64 pmdval_t; typedef u64 pgdval_t; diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 75fd13d289b..d2599174765 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -25,16 +25,27 @@ /* * Hardware page table definitions. * + * Level 1 descriptor (PUD). + */ + +#define PUD_TABLE_BIT (_AT(pgdval_t, 1) << 1) + +/* * Level 2 descriptor (PMD). */ #define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0) #define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) #define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0) #define PMD_TYPE_SECT (_AT(pmdval_t, 1) << 0) +#define PMD_TABLE_BIT (_AT(pmdval_t, 1) << 1) /* * Section */ +#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) +#define PMD_SECT_PROT_NONE (_AT(pmdval_t, 1) << 58) +#define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */ +#define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */ #define PMD_SECT_S (_AT(pmdval_t, 3) << 8) #define PMD_SECT_AF (_AT(pmdval_t, 1) << 10) #define PMD_SECT_NG (_AT(pmdval_t, 1) << 11) @@ -53,6 +64,7 @@ #define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0) #define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0) #define PTE_TYPE_PAGE (_AT(pteval_t, 3) << 0) +#define PTE_TABLE_BIT (_AT(pteval_t, 1) << 1) #define PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */ #define PTE_RDONLY (_AT(pteval_t, 1) << 7) /* AP[2] */ #define PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */ @@ -92,5 +104,6 @@ #define TCR_TG1_64K (UL(1) << 30) #define TCR_IPS_40BIT (UL(2) << 32) #define TCR_ASID16 (UL(1) << 36) +#define TCR_TBI0 (UL(1) << 37) #endif diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index e333a243bfc..b4d6eae1aef 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -25,10 +25,11 @@ * Software defined PTE bits definition. */ #define PTE_VALID (_AT(pteval_t, 1) << 0) -#define PTE_PROT_NONE (_AT(pteval_t, 1) << 1) /* only when !PTE_VALID */ #define PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !pte_present() */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) +#define PTE_WRITE (_AT(pteval_t, 1) << 57) +#define PTE_PROT_NONE (_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. @@ -66,23 +67,23 @@ extern pgprot_t pgprot_default; #define _MOD_PROT(p, b) __pgprot_modify(p, 0, b) -#define PAGE_NONE __pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE) -#define PAGE_SHARED _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_SHARED_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN) -#define PAGE_COPY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY) -#define PAGE_COPY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY) -#define PAGE_READONLY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY) -#define PAGE_READONLY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY) -#define PAGE_KERNEL _MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY) -#define PAGE_KERNEL_EXEC _MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY) - -#define __PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE) -#define __PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) -#define __PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) -#define __PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY) -#define __PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY) -#define __PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY) -#define __PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY) +#define PAGE_NONE __pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE | PTE_PXN | PTE_UXN) +#define PAGE_SHARED _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define PAGE_SHARED_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +#define PAGE_COPY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) +#define PAGE_COPY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN) +#define PAGE_READONLY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) +#define PAGE_READONLY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN) +#define PAGE_KERNEL _MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) +#define PAGE_KERNEL_EXEC _MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY | PTE_WRITE) + +#define __PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) +#define __PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define __PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +#define __PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) +#define __PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) +#define __PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) +#define __PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN) #endif /* __ASSEMBLY__ */ @@ -129,26 +130,57 @@ extern struct page *empty_zero_page; /* * The following only work if pte_present(). Undefined behaviour otherwise. */ -#define pte_present(pte) (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) -#define pte_dirty(pte) (pte_val(pte) & PTE_DIRTY) -#define pte_young(pte) (pte_val(pte) & PTE_AF) -#define pte_special(pte) (pte_val(pte) & PTE_SPECIAL) -#define pte_write(pte) (!(pte_val(pte) & PTE_RDONLY)) +#define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))) +#define pte_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) +#define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) +#define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) +#define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) -#define PTE_BIT_FUNC(fn,op) \ -static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + pte_val(pte) &= ~PTE_WRITE; + return pte; +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + pte_val(pte) |= PTE_WRITE; + return pte; +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + pte_val(pte) &= ~PTE_DIRTY; + return pte; +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + pte_val(pte) |= PTE_DIRTY; + return pte; +} -PTE_BIT_FUNC(wrprotect, |= PTE_RDONLY); -PTE_BIT_FUNC(mkwrite, &= ~PTE_RDONLY); -PTE_BIT_FUNC(mkclean, &= ~PTE_DIRTY); -PTE_BIT_FUNC(mkdirty, |= PTE_DIRTY); -PTE_BIT_FUNC(mkold, &= ~PTE_AF); -PTE_BIT_FUNC(mkyoung, |= PTE_AF); -PTE_BIT_FUNC(mkspecial, |= PTE_SPECIAL); +static inline pte_t pte_mkold(pte_t pte) +{ + pte_val(pte) &= ~PTE_AF; + return pte; +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + pte_val(pte) |= PTE_AF; + return pte; +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + pte_val(pte) |= PTE_SPECIAL; + return pte; +} static inline void set_pte(pte_t *ptep, pte_t pte) { @@ -163,8 +195,10 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, if (pte_valid_user(pte)) { if (pte_exec(pte)) __sync_icache_dcache(pte, addr); - if (!pte_dirty(pte)) - pte = pte_wrprotect(pte); + if (pte_dirty(pte) && pte_write(pte)) + pte_val(pte) &= ~PTE_RDONLY; + else + pte_val(pte) |= PTE_RDONLY; } set_pte(ptep, pte); @@ -173,18 +207,82 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, /* * Huge pte definitions. */ -#define pte_huge(pte) ((pte_val(pte) & PTE_TYPE_MASK) == PTE_TYPE_HUGEPAGE) -#define pte_mkhuge(pte) (__pte((pte_val(pte) & ~PTE_TYPE_MASK) | PTE_TYPE_HUGEPAGE)) +#define pte_huge(pte) (!(pte_val(pte) & PTE_TABLE_BIT)) +#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) + +/* + * Hugetlb definitions. + */ +#define HUGE_MAX_HSTATE 2 +#define HPAGE_SHIFT PMD_SHIFT +#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) #define __HAVE_ARCH_PTE_SPECIAL /* + * Software PMD bits for THP + */ + +#define PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55) +#define PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 57) + +/* + * THP definitions. + */ +#define pmd_young(pmd) (pmd_val(pmd) & PMD_SECT_AF) + +#define __HAVE_ARCH_PMD_WRITE +#define pmd_write(pmd) (!(pmd_val(pmd) & PMD_SECT_RDONLY)) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT)) +#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING) +#endif + +#define PMD_BIT_FUNC(fn,op) \ +static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; } + +PMD_BIT_FUNC(wrprotect, |= PMD_SECT_RDONLY); +PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF); +PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING); +PMD_BIT_FUNC(mkwrite, &= ~PMD_SECT_RDONLY); +PMD_BIT_FUNC(mkdirty, |= PMD_SECT_DIRTY); +PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); +PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK); + +#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) + +#define pmd_pfn(pmd) (((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT) +#define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) +#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) + +#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) + +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + const pmdval_t mask = PMD_SECT_USER | PMD_SECT_PXN | PMD_SECT_UXN | + PMD_SECT_RDONLY | PMD_SECT_PROT_NONE | + PMD_SECT_VALID; + pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask); + return pmd; +} + +#define set_pmd_at(mm, addr, pmdp, pmd) set_pmd(pmdp, pmd) + +static inline int has_transparent_hugepage(void) +{ + return 1; +} + +/* * Mark the prot value as uncacheable and unbufferable. */ #define pgprot_noncached(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define pgprot_writecombine(prot) \ - __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_GRE)) + __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC)) #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC)) #define __HAVE_PHYS_MEM_ACCESS_PROT @@ -268,7 +366,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_VALID; + PTE_PROT_NONE | PTE_VALID | PTE_WRITE; pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); return pte; } @@ -284,15 +382,17 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; * bits 0-1: present (must be zero) * bit 2: PTE_FILE * bits 3-8: swap type - * bits 9-63: swap offset + * bits 9-57: swap offset */ #define __SWP_TYPE_SHIFT 3 #define __SWP_TYPE_BITS 6 +#define __SWP_OFFSET_BITS 49 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) +#define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) -#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT) +#define __swp_offset(x) (((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK) #define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) @@ -308,13 +408,13 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; * Encode and decode a file entry: * bits 0-1: present (must be zero) * bit 2: PTE_FILE - * bits 3-63: file offset / PAGE_SIZE + * bits 3-57: file offset / PAGE_SIZE */ #define pte_file(pte) (pte_val(pte) & PTE_FILE) #define pte_to_pgoff(x) (pte_val(x) >> 3) #define pgoff_to_pte(x) __pte(((x) << 3) | PTE_FILE) -#define PTE_FILE_MAX_BITS 61 +#define PTE_FILE_MAX_BITS 55 extern int kern_addr_valid(unsigned long addr); diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h index 7cdf466fd0c..0c657bb5459 100644 --- a/arch/arm64/include/asm/proc-fns.h +++ b/arch/arm64/include/asm/proc-fns.h @@ -26,11 +26,14 @@ #include <asm/page.h> struct mm_struct; +struct cpu_suspend_ctx; extern void cpu_cache_off(void); extern void cpu_do_idle(void); extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm); extern void cpu_reset(unsigned long addr) __attribute__((noreturn)); +extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr); +extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr); #include <asm/memory.h> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index ab239b2c456..45b20cd6cbc 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -107,6 +107,11 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, regs->pstate = COMPAT_PSR_MODE_USR; if (pc & 1) regs->pstate |= COMPAT_PSR_T_BIT; + +#ifdef __AARCH64EB__ + regs->pstate |= COMPAT_PSR_E_BIT; +#endif + regs->compat_sp = sp; } #endif diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h index 0604237ecd9..e5312ea0ec1 100644 --- a/arch/arm64/include/asm/psci.h +++ b/arch/arm64/include/asm/psci.h @@ -14,25 +14,6 @@ #ifndef __ASM_PSCI_H #define __ASM_PSCI_H -#define PSCI_POWER_STATE_TYPE_STANDBY 0 -#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 - -struct psci_power_state { - u16 id; - u8 type; - u8 affinity_level; -}; - -struct psci_operations { - int (*cpu_suspend)(struct psci_power_state state, - unsigned long entry_point); - int (*cpu_off)(struct psci_power_state state); - int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); - int (*migrate)(unsigned long cpuid); -}; - -extern struct psci_operations psci_ops; - int psci_init(void); #endif /* __ASM_PSCI_H */ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 41a71ee4c3d..491bea413fb 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -42,6 +42,7 @@ #define COMPAT_PSR_MODE_UND 0x0000001b #define COMPAT_PSR_MODE_SYS 0x0000001f #define COMPAT_PSR_T_BIT 0x00000020 +#define COMPAT_PSR_E_BIT 0x00000200 #define COMPAT_PSR_F_BIT 0x00000040 #define COMPAT_PSR_I_BIT 0x00000080 #define COMPAT_PSR_A_BIT 0x00000100 diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 4b8023c5d14..a498f2cd2c2 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -60,21 +60,14 @@ struct secondary_data { void *stack; }; extern struct secondary_data secondary_data; -extern void secondary_holding_pen(void); -extern volatile unsigned long secondary_holding_pen_release; +extern void secondary_entry(void); extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); -struct device_node; +extern int __cpu_disable(void); -struct smp_enable_ops { - const char *name; - int (*init_cpu)(struct device_node *, int); - int (*prepare_cpu)(int); -}; - -extern const struct smp_enable_ops smp_spin_table_ops; -extern const struct smp_enable_ops smp_psci_ops; +extern void __cpu_die(unsigned int cpu); +extern void cpu_die(void); #endif /* ifndef __ASM_SMP_H */ diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h index ed43a0d2b1b..59e282311b5 100644 --- a/arch/arm64/include/asm/smp_plat.h +++ b/arch/arm64/include/asm/smp_plat.h @@ -21,6 +21,19 @@ #include <asm/types.h> +struct mpidr_hash { + u64 mask; + u32 shift_aff[4]; + u32 bits; +}; + +extern struct mpidr_hash mpidr_hash; + +static inline u32 mpidr_hash_size(void) +{ + return 1 << mpidr_hash.bits; +} + /* * Logical CPU mapping. */ diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index 7065e920149..0defa0728a9 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -59,9 +59,10 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) unsigned int tmp; asm volatile( - " ldaxr %w0, %1\n" + "2: ldaxr %w0, %1\n" " cbnz %w0, 1f\n" " stxr %w0, %w2, %1\n" + " cbnz %w0, 2b\n" "1:\n" : "=&r" (tmp), "+Q" (lock->lock) : "r" (1) diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h new file mode 100644 index 00000000000..e9c149c042e --- /dev/null +++ b/arch/arm64/include/asm/suspend.h @@ -0,0 +1,27 @@ +#ifndef __ASM_SUSPEND_H +#define __ASM_SUSPEND_H + +#define NR_CTX_REGS 11 + +/* + * struct cpu_suspend_ctx must be 16-byte aligned since it is allocated on + * the stack, which must be 16-byte aligned on v8 + */ +struct cpu_suspend_ctx { + /* + * This struct must be kept in sync with + * cpu_do_{suspend/resume} in mm/proc.S + */ + u64 ctx_regs[NR_CTX_REGS]; + u64 sp; +} __aligned(16); + +struct sleep_save_sp { + phys_addr_t *save_ptr_stash; + phys_addr_t save_ptr_stash_phys; +}; + +extern void cpu_resume(void); +extern int cpu_suspend(unsigned long); + +#endif diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 89c047f9a97..70ba9d4ee97 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -59,6 +59,9 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned int i, unsigned int n, unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i; unsigned int n_bad = n + i - SYSCALL_MAX_ARGS; @@ -82,6 +85,9 @@ static inline void syscall_set_arguments(struct task_struct *task, unsigned int i, unsigned int n, const unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { pr_warning("%s called with max args %d, handling only %d\n", __func__, i + n, SYSCALL_MAX_ARGS); diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 3659e460071..23a3c4791d8 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -24,10 +24,10 @@ #include <linux/compiler.h> #ifndef CONFIG_ARM64_64K_PAGES -#define THREAD_SIZE_ORDER 1 +#define THREAD_SIZE_ORDER 2 #endif -#define THREAD_SIZE 8192 +#define THREAD_SIZE 16384 #define THREAD_START_SP (THREAD_SIZE - 16) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 654f0968030..717031a762c 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -35,6 +35,7 @@ struct mmu_gather { struct mm_struct *mm; unsigned int fullmm; struct vm_area_struct *vma; + unsigned long start, end; unsigned long range_start; unsigned long range_end; unsigned int nr; @@ -97,10 +98,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb) } static inline void -tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm) +tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) { tlb->mm = mm; - tlb->fullmm = fullmm; + tlb->fullmm = !(start | (end+1)); + tlb->start = start; + tlb->end = end; tlb->vma = NULL; tlb->max = ARRAY_SIZE(tlb->local); tlb->pages = tlb->local; @@ -187,4 +190,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, #define tlb_migrate_finish(mm) do { } while (0) +static inline void +tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) +{ + tlb_add_flush(tlb, addr); +} + #endif diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 122d6320f74..8b482035cfc 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -117,6 +117,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, dsb(); } +#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) + #endif #endif diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h new file mode 100644 index 00000000000..5692ba11322 --- /dev/null +++ b/arch/arm64/include/asm/topology.h @@ -0,0 +1,70 @@ +#ifndef _ASM_ARM_TOPOLOGY_H +#define _ASM_ARM_TOPOLOGY_H + +#ifdef CONFIG_ARM_CPU_TOPOLOGY + +#include <linux/cpumask.h> + +struct cputopo_arm { + int thread_id; + int core_id; + int socket_id; + cpumask_t thread_sibling; + cpumask_t core_sibling; +}; + +extern struct cputopo_arm cpu_topology[NR_CPUS]; + +#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) +#define topology_core_id(cpu) (cpu_topology[cpu].core_id) +#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) +#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) + +#define mc_capable() (cpu_topology[0].socket_id != -1) +#define smt_capable() (cpu_topology[0].thread_id != -1) + +void init_cpu_topology(void); +void store_cpu_topology(unsigned int cpuid); +const struct cpumask *cpu_coregroup_mask(int cpu); + +#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) { } + +#endif + +#include <asm-generic/topology.h> + +#endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 439827271e3..130e2be952c 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -18,9 +18,11 @@ #ifndef __ASM__VIRT_H #define __ASM__VIRT_H -#define BOOT_CPU_MODE_EL2 (0x0e12b007) +#define BOOT_CPU_MODE_EL1 (0xe11) +#define BOOT_CPU_MODE_EL2 (0xe12) #ifndef __ASSEMBLY__ +#include <asm/cacheflush.h> /* * __boot_cpu_mode records what mode CPUs were booted in. @@ -36,9 +38,20 @@ extern u32 __boot_cpu_mode[2]; void __hyp_set_vectors(phys_addr_t phys_vector_base); phys_addr_t __hyp_get_vectors(void); +static inline void sync_boot_mode(void) +{ + /* + * As secondaries write to __boot_cpu_mode with caches disabled, we + * must flush the corresponding cache entries to ensure the visibility + * of their writes. + */ + __flush_dcache_area(__boot_cpu_mode, sizeof(__boot_cpu_mode)); +} + /* Reports the availability of HYP mode */ static inline bool is_hyp_mode_available(void) { + sync_boot_mode(); return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 && __boot_cpu_mode[1] == BOOT_CPU_MODE_EL2); } @@ -46,6 +59,7 @@ static inline bool is_hyp_mode_available(void) /* Check if the bootloader has booted CPUs in different modes */ static inline bool is_hyp_mode_mismatched(void) { + sync_boot_mode(); return __boot_cpu_mode[0] != __boot_cpu_mode[1]; } diff --git a/arch/arm64/include/uapi/asm/byteorder.h b/arch/arm64/include/uapi/asm/byteorder.h index 2b92046aafc..dc19e9537f0 100644 --- a/arch/arm64/include/uapi/asm/byteorder.h +++ b/arch/arm64/include/uapi/asm/byteorder.h @@ -16,6 +16,10 @@ #ifndef __ASM_BYTEORDER_H #define __ASM_BYTEORDER_H +#ifdef __AARCH64EB__ +#include <linux/byteorder/big_endian.h> +#else #include <linux/byteorder/little_endian.h> +#endif #endif /* __ASM_BYTEORDER_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 7b4b564961d..c6172392b20 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -9,15 +9,17 @@ AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) arm64-obj-y := cputable.o debug-monitors.o entry.o irq.o fpsimd.o \ entry-fpsimd.o process.o ptrace.o setup.o signal.o \ sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o + hyp-stub.o psci.o cpu_ops.o arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ sys_compat.o arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o -arm64-obj-$(CONFIG_SMP) += smp.o smp_spin_table.o smp_psci.o +arm64-obj-$(CONFIG_SMP) += smp.o smp_spin_table.o arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o arm64-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +arm64-obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o +arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND) += sleep.o suspend.o obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index a2a4d810bea..c481a119b98 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -24,6 +24,8 @@ #include <asm/thread_info.h> #include <asm/memory.h> #include <asm/cputable.h> +#include <asm/smp_plat.h> +#include <asm/suspend.h> #include <asm/vdso_datapage.h> #include <linux/kbuild.h> @@ -104,5 +106,47 @@ int main(void) BLANK(); DEFINE(TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); + BLANK(); +#ifdef CONFIG_KVM_ARM_HOST + DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); + DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); + DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs)); + DEFINE(CPU_FP_REGS, offsetof(struct kvm_regs, fp_regs)); + DEFINE(CPU_SP_EL1, offsetof(struct kvm_regs, sp_el1)); + DEFINE(CPU_ELR_EL1, offsetof(struct kvm_regs, elr_el1)); + DEFINE(CPU_SPSR, offsetof(struct kvm_regs, spsr)); + DEFINE(CPU_SYSREGS, offsetof(struct kvm_cpu_context, sys_regs)); + DEFINE(VCPU_ESR_EL2, offsetof(struct kvm_vcpu, arch.fault.esr_el2)); + DEFINE(VCPU_FAR_EL2, offsetof(struct kvm_vcpu, arch.fault.far_el2)); + DEFINE(VCPU_HPFAR_EL2, offsetof(struct kvm_vcpu, arch.fault.hpfar_el2)); + DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2)); + DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines)); + DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context)); + DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl)); + DEFINE(VCPU_TIMER_CNTV_CVAL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval)); + DEFINE(KVM_TIMER_CNTVOFF, offsetof(struct kvm, arch.timer.cntvoff)); + DEFINE(KVM_TIMER_ENABLED, offsetof(struct kvm, arch.timer.enabled)); + DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); + DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); + DEFINE(VGIC_CPU_HCR, offsetof(struct vgic_cpu, vgic_hcr)); + DEFINE(VGIC_CPU_VMCR, offsetof(struct vgic_cpu, vgic_vmcr)); + DEFINE(VGIC_CPU_MISR, offsetof(struct vgic_cpu, vgic_misr)); + DEFINE(VGIC_CPU_EISR, offsetof(struct vgic_cpu, vgic_eisr)); + DEFINE(VGIC_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_elrsr)); + DEFINE(VGIC_CPU_APR, offsetof(struct vgic_cpu, vgic_apr)); + DEFINE(VGIC_CPU_LR, offsetof(struct vgic_cpu, vgic_lr)); + DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr)); + DEFINE(KVM_VTTBR, offsetof(struct kvm, arch.vttbr)); + DEFINE(KVM_VGIC_VCTRL, offsetof(struct kvm, arch.vgic.vctrl_base)); +#endif +#ifdef CONFIG_ARM64_CPU_SUSPEND + DEFINE(CPU_SUSPEND_SZ, sizeof(struct cpu_suspend_ctx)); + DEFINE(CPU_CTX_SP, offsetof(struct cpu_suspend_ctx, sp)); + DEFINE(MPIDR_HASH_MASK, offsetof(struct mpidr_hash, mask)); + DEFINE(MPIDR_HASH_SHIFTS, offsetof(struct mpidr_hash, shift_aff)); + DEFINE(SLEEP_SAVE_SP_SZ, sizeof(struct sleep_save_sp)); + DEFINE(SLEEP_SAVE_SP_PHYS, offsetof(struct sleep_save_sp, save_ptr_stash_phys)); + DEFINE(SLEEP_SAVE_SP_VIRT, offsetof(struct sleep_save_sp, save_ptr_stash)); +#endif return 0; } diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c new file mode 100644 index 00000000000..04efea8fe4b --- /dev/null +++ b/arch/arm64/kernel/cpu_ops.c @@ -0,0 +1,99 @@ +/* + * CPU kernel entry/exit control + * + * Copyright (C) 2013 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <asm/cpu_ops.h> +#include <asm/smp_plat.h> +#include <linux/errno.h> +#include <linux/of.h> +#include <linux/string.h> + +extern const struct cpu_operations smp_spin_table_ops; +extern const struct cpu_operations cpu_psci_ops; + +const struct cpu_operations *cpu_ops[NR_CPUS]; + +static const struct cpu_operations *supported_cpu_ops[] __initconst = { +#ifdef CONFIG_SMP + &smp_spin_table_ops, + &cpu_psci_ops, +#endif + NULL, +}; + +static const struct cpu_operations * __init cpu_get_ops(const char *name) +{ + const struct cpu_operations **ops = supported_cpu_ops; + + while (*ops) { + if (!strcmp(name, (*ops)->name)) + return *ops; + + ops++; + } + + return NULL; +} + +/* + * Read a cpu's enable method from the device tree and record it in cpu_ops. + */ +int __init cpu_read_ops(struct device_node *dn, int cpu) +{ + const char *enable_method = of_get_property(dn, "enable-method", NULL); + if (!enable_method) { + /* + * The boot CPU may not have an enable method (e.g. when + * spin-table is used for secondaries). Don't warn spuriously. + */ + if (cpu != 0) + pr_err("%s: missing enable-method property\n", + dn->full_name); + return -ENOENT; + } + + cpu_ops[cpu] = cpu_get_ops(enable_method); + if (!cpu_ops[cpu]) { + pr_warn("%s: unsupported enable-method property: %s\n", + dn->full_name, enable_method); + return -EOPNOTSUPP; + } + + return 0; +} + +void __init cpu_read_bootcpu_ops(void) +{ + struct device_node *dn = NULL; + u64 mpidr = cpu_logical_map(0); + + while ((dn = of_find_node_by_type(dn, "cpu"))) { + u64 hwid; + const __be32 *prop; + + prop = of_get_property(dn, "reg", NULL); + if (!prop) + continue; + + hwid = of_read_number(prop, of_n_addr_cells(dn)); + if (hwid == mpidr) { + cpu_read_ops(dn, 0); + of_node_put(dn); + return; + } + } +} diff --git a/arch/arm64/kernel/cputable.c b/arch/arm64/kernel/cputable.c index 63cfc4a43f4..fd3993cb060 100644 --- a/arch/arm64/kernel/cputable.c +++ b/arch/arm64/kernel/cputable.c @@ -22,7 +22,7 @@ extern unsigned long __cpu_setup(void); -struct cpu_info __initdata cpu_table[] = { +struct cpu_info cpu_table[] = { { .cpu_id_val = 0x000f0000, .cpu_id_mask = 0x000f0000, diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 1d1314280a0..93f96098ae4 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -121,7 +121,7 @@ .macro get_thread_info, rd mov \rd, sp - and \rd, \rd, #~((1 << 13) - 1) // top of 8K stack + and \rd, \rd, #~(THREAD_SIZE - 1) // top of stack .endm /* @@ -423,6 +423,7 @@ el0_da: * Data abort handling */ mrs x0, far_el1 + bic x0, x0, #(0xff << 56) disable_step x1 isb enable_dbg diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index e8b8357aedb..522df9c7f3a 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -17,6 +17,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/cpu_pm.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/sched.h> @@ -79,10 +80,72 @@ void fpsimd_thread_switch(struct task_struct *next) void fpsimd_flush_thread(void) { + preempt_disable(); memset(¤t->thread.fpsimd_state, 0, sizeof(struct fpsimd_state)); fpsimd_load_state(¤t->thread.fpsimd_state); + preempt_enable(); } +#ifdef CONFIG_KERNEL_MODE_NEON + +/* + * Kernel-side NEON support functions + */ +void kernel_neon_begin(void) +{ + /* Avoid using the NEON in interrupt context */ + BUG_ON(in_interrupt()); + preempt_disable(); + + if (current->mm) + fpsimd_save_state(¤t->thread.fpsimd_state); +} +EXPORT_SYMBOL(kernel_neon_begin); + +void kernel_neon_end(void) +{ + if (current->mm) + fpsimd_load_state(¤t->thread.fpsimd_state); + + preempt_enable(); +} +EXPORT_SYMBOL(kernel_neon_end); + +#endif /* CONFIG_KERNEL_MODE_NEON */ + +#ifdef CONFIG_CPU_PM +static int fpsimd_cpu_pm_notifier(struct notifier_block *self, + unsigned long cmd, void *v) +{ + switch (cmd) { + case CPU_PM_ENTER: + if (current->mm) + fpsimd_save_state(¤t->thread.fpsimd_state); + break; + case CPU_PM_EXIT: + if (current->mm) + fpsimd_load_state(¤t->thread.fpsimd_state); + break; + case CPU_PM_ENTER_FAILED: + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static struct notifier_block fpsimd_cpu_pm_notifier_block = { + .notifier_call = fpsimd_cpu_pm_notifier, +}; + +static void fpsimd_pm_init(void) +{ + cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block); +} + +#else +static inline void fpsimd_pm_init(void) { } +#endif /* CONFIG_CPU_PM */ + /* * FP/SIMD support code initialisation. */ @@ -101,6 +164,8 @@ static int __init fpsimd_init(void) else elf_hwcap |= HWCAP_ASIMD; + fpsimd_pm_init(); + return 0; } late_initcall(fpsimd_init); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 53dcae49e72..999504b50c3 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -115,8 +115,9 @@ ENTRY(stext) mov x21, x0 // x21=FDT + bl el2_setup // Drop to EL1, w20=cpu_boot_mode bl __calc_phys_offset // x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET - bl el2_setup // Drop to EL1 + bl set_cpu_boot_mode_flag mrs x22, midr_el1 // x22=cpuid mov x0, x22 bl lookup_processor_type @@ -142,21 +143,30 @@ ENDPROC(stext) /* * If we're fortunate enough to boot at EL2, ensure that the world is * sane before dropping to EL1. + * + * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if + * booted in EL1 or EL2 respectively. */ ENTRY(el2_setup) mrs x0, CurrentEL cmp x0, #PSR_MODE_EL2t ccmp x0, #PSR_MODE_EL2h, #0x4, ne - ldr x0, =__boot_cpu_mode // Compute __boot_cpu_mode - add x0, x0, x28 - b.eq 1f - str wzr, [x0] // Remember we don't have EL2... + b.ne 1f + mrs x0, sctlr_el2 +CPU_BE( orr x0, x0, #(1 << 25) ) // Set the EE bit for EL2 +CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2 + msr sctlr_el2, x0 + b 2f +1: mrs x0, sctlr_el1 +CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1 +CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1 + msr sctlr_el1, x0 + mov w20, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1 + isb ret /* Hyp configuration. */ -1: ldr w1, =BOOT_CPU_MODE_EL2 - str w1, [x0, #4] // This CPU has EL2 - mov x0, #(1 << 31) // 64-bit EL1 +2: mov x0, #(1 << 31) // 64-bit EL1 msr hcr_el2, x0 /* Generic timers. */ @@ -173,7 +183,8 @@ ENTRY(el2_setup) /* sctlr_el1 */ mov x0, #0x0800 // Set/clear RES{1,0} bits - movk x0, #0x30d0, lsl #16 +CPU_BE( movk x0, #0x33d0, lsl #16 ) // Set EE and E0E on BE systems +CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems msr sctlr_el1, x0 /* Coprocessor traps. */ @@ -196,10 +207,25 @@ ENTRY(el2_setup) PSR_MODE_EL1h) msr spsr_el2, x0 msr elr_el2, lr + mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 eret ENDPROC(el2_setup) /* + * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed + * in x20. See arch/arm64/include/asm/virt.h for more info. + */ +ENTRY(set_cpu_boot_mode_flag) + ldr x1, =__boot_cpu_mode // Compute __boot_cpu_mode + add x1, x1, x28 + cmp w20, #BOOT_CPU_MODE_EL2 + b.ne 1f + add x1, x1, #4 +1: str w20, [x1] // This CPU has booted in EL1 + ret +ENDPROC(set_cpu_boot_mode_flag) + +/* * We need to find out the CPU boot mode long after boot, so we need to * store it in a writable variable. * @@ -217,7 +243,6 @@ ENTRY(__boot_cpu_mode) .quad PAGE_OFFSET #ifdef CONFIG_SMP - .pushsection .smp.pen.text, "ax" .align 3 1: .quad . .quad secondary_holding_pen_release @@ -227,8 +252,9 @@ ENTRY(__boot_cpu_mode) * cores are held until we're ready for them to initialise. */ ENTRY(secondary_holding_pen) - bl __calc_phys_offset // x24=phys offset - bl el2_setup // Drop to EL1 + bl el2_setup // Drop to EL1, w20=cpu_boot_mode + bl __calc_phys_offset // x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET + bl set_cpu_boot_mode_flag mrs x0, mpidr_el1 ldr x1, =MPIDR_HWID_BITMASK and x0, x0, x1 @@ -242,7 +268,16 @@ pen: ldr x4, [x3] wfe b pen ENDPROC(secondary_holding_pen) - .popsection + + /* + * Secondary entry point that jumps straight into the kernel. Only to + * be used where CPUs are brought online dynamically by the kernel. + */ +ENTRY(secondary_entry) + bl __calc_phys_offset // x2=phys offset + bl el2_setup // Drop to EL1 + b secondary_startup +ENDPROC(secondary_entry) ENTRY(secondary_startup) /* diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 5ab825c59db..b989233a9d3 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -20,6 +20,7 @@ #define pr_fmt(fmt) "hw-breakpoint: " fmt +#include <linux/cpu_pm.h> #include <linux/errno.h> #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> @@ -169,15 +170,68 @@ static enum debug_el debug_exception_level(int privilege) } } -/* - * Install a perf counter breakpoint. +enum hw_breakpoint_ops { + HW_BREAKPOINT_INSTALL, + HW_BREAKPOINT_UNINSTALL, + HW_BREAKPOINT_RESTORE +}; + +/** + * hw_breakpoint_slot_setup - Find and setup a perf slot according to + * operations + * + * @slots: pointer to array of slots + * @max_slots: max number of slots + * @bp: perf_event to setup + * @ops: operation to be carried out on the slot + * + * Return: + * slot index on success + * -ENOSPC if no slot is available/matches + * -EINVAL on wrong operations parameter */ -int arch_install_hw_breakpoint(struct perf_event *bp) +static int hw_breakpoint_slot_setup(struct perf_event **slots, int max_slots, + struct perf_event *bp, + enum hw_breakpoint_ops ops) +{ + int i; + struct perf_event **slot; + + for (i = 0; i < max_slots; ++i) { + slot = &slots[i]; + switch (ops) { + case HW_BREAKPOINT_INSTALL: + if (!*slot) { + *slot = bp; + return i; + } + break; + case HW_BREAKPOINT_UNINSTALL: + if (*slot == bp) { + *slot = NULL; + return i; + } + break; + case HW_BREAKPOINT_RESTORE: + if (*slot == bp) + return i; + break; + default: + pr_warn_once("Unhandled hw breakpoint ops %d\n", ops); + return -EINVAL; + } + } + return -ENOSPC; +} + +static int hw_breakpoint_control(struct perf_event *bp, + enum hw_breakpoint_ops ops) { struct arch_hw_breakpoint *info = counter_arch_bp(bp); - struct perf_event **slot, **slots; + struct perf_event **slots; struct debug_info *debug_info = ¤t->thread.debug; int i, max_slots, ctrl_reg, val_reg, reg_enable; + enum debug_el dbg_el = debug_exception_level(info->ctrl.privilege); u32 ctrl; if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { @@ -196,67 +250,54 @@ int arch_install_hw_breakpoint(struct perf_event *bp) reg_enable = !debug_info->wps_disabled; } - for (i = 0; i < max_slots; ++i) { - slot = &slots[i]; - - if (!*slot) { - *slot = bp; - break; - } - } - - if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot")) - return -ENOSPC; + i = hw_breakpoint_slot_setup(slots, max_slots, bp, ops); - /* Ensure debug monitors are enabled at the correct exception level. */ - enable_debug_monitors(debug_exception_level(info->ctrl.privilege)); + if (WARN_ONCE(i < 0, "Can't find any breakpoint slot")) + return i; - /* Setup the address register. */ - write_wb_reg(val_reg, i, info->address); + switch (ops) { + case HW_BREAKPOINT_INSTALL: + /* + * Ensure debug monitors are enabled at the correct exception + * level. + */ + enable_debug_monitors(dbg_el); + /* Fall through */ + case HW_BREAKPOINT_RESTORE: + /* Setup the address register. */ + write_wb_reg(val_reg, i, info->address); + + /* Setup the control register. */ + ctrl = encode_ctrl_reg(info->ctrl); + write_wb_reg(ctrl_reg, i, + reg_enable ? ctrl | 0x1 : ctrl & ~0x1); + break; + case HW_BREAKPOINT_UNINSTALL: + /* Reset the control register. */ + write_wb_reg(ctrl_reg, i, 0); - /* Setup the control register. */ - ctrl = encode_ctrl_reg(info->ctrl); - write_wb_reg(ctrl_reg, i, reg_enable ? ctrl | 0x1 : ctrl & ~0x1); + /* + * Release the debug monitors for the correct exception + * level. + */ + disable_debug_monitors(dbg_el); + break; + } return 0; } -void arch_uninstall_hw_breakpoint(struct perf_event *bp) +/* + * Install a perf counter breakpoint. + */ +int arch_install_hw_breakpoint(struct perf_event *bp) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - struct perf_event **slot, **slots; - int i, max_slots, base; - - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { - /* Breakpoint */ - base = AARCH64_DBG_REG_BCR; - slots = __get_cpu_var(bp_on_reg); - max_slots = core_num_brps; - } else { - /* Watchpoint */ - base = AARCH64_DBG_REG_WCR; - slots = __get_cpu_var(wp_on_reg); - max_slots = core_num_wrps; - } - - /* Remove the breakpoint. */ - for (i = 0; i < max_slots; ++i) { - slot = &slots[i]; - - if (*slot == bp) { - *slot = NULL; - break; - } - } - - if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot")) - return; - - /* Reset the control register. */ - write_wb_reg(base, i, 0); + return hw_breakpoint_control(bp, HW_BREAKPOINT_INSTALL); +} - /* Release the debug monitors for the correct exception level. */ - disable_debug_monitors(debug_exception_level(info->ctrl.privilege)); +void arch_uninstall_hw_breakpoint(struct perf_event *bp) +{ + hw_breakpoint_control(bp, HW_BREAKPOINT_UNINSTALL); } static int get_hbp_len(u8 hbp_len) @@ -806,18 +847,36 @@ void hw_breakpoint_thread_switch(struct task_struct *next) /* * CPU initialisation. */ -static void reset_ctrl_regs(void *unused) +static void hw_breakpoint_reset(void *unused) { int i; - - for (i = 0; i < core_num_brps; ++i) { - write_wb_reg(AARCH64_DBG_REG_BCR, i, 0UL); - write_wb_reg(AARCH64_DBG_REG_BVR, i, 0UL); + struct perf_event **slots; + /* + * When a CPU goes through cold-boot, it does not have any installed + * slot, so it is safe to share the same function for restoring and + * resetting breakpoints; when a CPU is hotplugged in, it goes + * through the slots, which are all empty, hence it just resets control + * and value for debug registers. + * When this function is triggered on warm-boot through a CPU PM + * notifier some slots might be initialized; if so they are + * reprogrammed according to the debug slots content. + */ + for (slots = __get_cpu_var(bp_on_reg), i = 0; i < core_num_brps; ++i) { + if (slots[i]) { + hw_breakpoint_control(slots[i], HW_BREAKPOINT_RESTORE); + } else { + write_wb_reg(AARCH64_DBG_REG_BCR, i, 0UL); + write_wb_reg(AARCH64_DBG_REG_BVR, i, 0UL); + } } - for (i = 0; i < core_num_wrps; ++i) { - write_wb_reg(AARCH64_DBG_REG_WCR, i, 0UL); - write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL); + for (slots = __get_cpu_var(wp_on_reg), i = 0; i < core_num_wrps; ++i) { + if (slots[i]) { + hw_breakpoint_control(slots[i], HW_BREAKPOINT_RESTORE); + } else { + write_wb_reg(AARCH64_DBG_REG_WCR, i, 0UL); + write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL); + } } } @@ -827,7 +886,7 @@ static int __cpuinit hw_breakpoint_reset_notify(struct notifier_block *self, { int cpu = (long)hcpu; if (action == CPU_ONLINE) - smp_call_function_single(cpu, reset_ctrl_regs, NULL, 1); + smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1); return NOTIFY_OK; } @@ -835,6 +894,14 @@ static struct notifier_block __cpuinitdata hw_breakpoint_reset_nb = { .notifier_call = hw_breakpoint_reset_notify, }; +#ifdef CONFIG_ARM64_CPU_SUSPEND +extern void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)); +#else +static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) +{ +} +#endif + /* * One-time initialisation. */ @@ -850,8 +917,8 @@ static int __init arch_hw_breakpoint_init(void) * Reset the breakpoint resources. We assume that a halting * debugger will leave the world in a nice state for us. */ - smp_call_function(reset_ctrl_regs, NULL, 1); - reset_ctrl_regs(NULL); + smp_call_function(hw_breakpoint_reset, NULL, 1); + hw_breakpoint_reset(NULL); /* Register debug fault handlers. */ hook_debug_fault_code(DBG_ESR_EVT_HWBP, breakpoint_handler, SIGTRAP, @@ -861,6 +928,8 @@ static int __init arch_hw_breakpoint_init(void) /* Register hotplug notifier. */ register_cpu_notifier(&hw_breakpoint_reset_nb); + /* Register cpu_suspend hw breakpoint restore hook */ + cpu_suspend_set_dbg_restorer(hw_breakpoint_reset); return 0; } diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index ecb3354292e..473e5dbf8f3 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -81,3 +81,64 @@ void __init init_IRQ(void) if (!handle_arch_irq) panic("No interrupt controller found."); } + +#ifdef CONFIG_HOTPLUG_CPU +static bool migrate_one_irq(struct irq_desc *desc) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + const struct cpumask *affinity = d->affinity; + struct irq_chip *c; + bool ret = false; + + /* + * If this is a per-CPU interrupt, or the affinity does not + * include this CPU, then we have nothing to do. + */ + if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity)) + return false; + + if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + affinity = cpu_online_mask; + ret = true; + } + + c = irq_data_get_irq_chip(d); + if (!c->irq_set_affinity) + pr_debug("IRQ%u: unable to set affinity\n", d->irq); + else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + cpumask_copy(d->affinity, affinity); + + return ret; +} + +/* + * The current CPU has been marked offline. Migrate IRQs off this CPU. + * If the affinity settings do not allow other CPUs, force them onto any + * available CPU. + * + * Note: we must iterate over all IRQs, whether they have an attached + * action structure or not, as we need to get chained interrupts too. + */ +void migrate_irqs(void) +{ + unsigned int i; + struct irq_desc *desc; + unsigned long flags; + + local_irq_save(flags); + + for_each_irq_desc(i, desc) { + bool affinity_broken; + + raw_spin_lock(&desc->lock); + affinity_broken = migrate_one_irq(desc); + raw_spin_unlock(&desc->lock); + + if (affinity_broken) + pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n", + i, smp_processor_id()); + } + + local_irq_restore(flags); +} +#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S index 8b69ecb1d8b..1e4905d52d3 100644 --- a/arch/arm64/kernel/kuser32.S +++ b/arch/arm64/kernel/kuser32.S @@ -27,6 +27,9 @@ * * See Documentation/arm/kernel_user_helpers.txt for formal definitions. */ + +#include <asm/unistd32.h> + .align 5 .globl __kuser_helper_start __kuser_helper_start: @@ -75,3 +78,42 @@ __kuser_helper_version: // 0xffff0ffc .word ((__kuser_helper_end - __kuser_helper_start) >> 5) .globl __kuser_helper_end __kuser_helper_end: + +/* + * AArch32 sigreturn code + * + * For ARM syscalls, the syscall number has to be loaded into r7. + * We do not support an OABI userspace. + * + * For Thumb syscalls, we also pass the syscall number via r7. We therefore + * need two 16-bit instructions. + */ + .globl __aarch32_sigret_code_start +__aarch32_sigret_code_start: + + /* + * ARM Code + */ + .byte __NR_compat_sigreturn, 0x70, 0xa0, 0xe3 // mov r7, #__NR_compat_sigreturn + .byte __NR_compat_sigreturn, 0x00, 0x00, 0xef // svc #__NR_compat_sigreturn + + /* + * Thumb code + */ + .byte __NR_compat_sigreturn, 0x27 // svc #__NR_compat_sigreturn + .byte __NR_compat_sigreturn, 0xdf // mov r7, #__NR_compat_sigreturn + + /* + * ARM code + */ + .byte __NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3 // mov r7, #__NR_compat_rt_sigreturn + .byte __NR_compat_rt_sigreturn, 0x00, 0x00, 0xef // svc #__NR_compat_rt_sigreturn + + /* + * Thumb code + */ + .byte __NR_compat_rt_sigreturn, 0x27 // svc #__NR_compat_rt_sigreturn + .byte __NR_compat_rt_sigreturn, 0xdf // mov r7, #__NR_compat_rt_sigreturn + + .globl __aarch32_sigret_code_end +__aarch32_sigret_code_end: diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index ca0e3d55da9..2c28a6cf93e 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -111,6 +111,9 @@ static u32 encode_insn_immediate(enum aarch64_imm_type type, u32 insn, u64 imm) u32 immlo, immhi, lomask, himask, mask; int shift; + /* The instruction stream is always little endian. */ + insn = le32_to_cpu(insn); + switch (type) { case INSN_IMM_MOVNZ: /* @@ -179,7 +182,7 @@ static u32 encode_insn_immediate(enum aarch64_imm_type type, u32 insn, u64 imm) insn &= ~(mask << shift); insn |= (imm & mask) << shift; - return insn; + return cpu_to_le32(insn); } static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 9ba33c40cdf..cea1594ff93 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -107,7 +107,12 @@ armpmu_map_cache_event(const unsigned (*cache_map) static int armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config) { - int mapping = (*event_map)[config]; + int mapping; + + if (config >= PERF_COUNT_HW_MAX) + return -EINVAL; + + mapping = (*event_map)[config]; return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping; } @@ -317,7 +322,13 @@ validate_event(struct pmu_hw_events *hw_events, struct hw_perf_event fake_event = event->hw; struct pmu *leader_pmu = event->group_leader->pmu; - if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) + if (is_software_event(event)) + return 1; + + 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, &fake_event) >= 0; @@ -773,7 +784,7 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] /* * PMXEVTYPER: Event selection reg */ -#define ARMV8_EVTYPE_MASK 0xc00000ff /* Mask for writable bits */ +#define ARMV8_EVTYPE_MASK 0xc80000ff /* Mask for writable bits */ #define ARMV8_EVTYPE_EVENT 0xff /* Mask for EVENT bits */ /* diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 46f02c3b501..8254875b67a 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -33,6 +33,7 @@ #include <linux/kallsyms.h> #include <linux/init.h> #include <linux/cpu.h> +#include <linux/cpuidle.h> #include <linux/elfcore.h> #include <linux/pm.h> #include <linux/tick.h> @@ -98,10 +99,19 @@ void arch_cpu_idle(void) * This should do all the clock switching and wait for interrupt * tricks */ - cpu_do_idle(); - local_irq_enable(); + if (cpuidle_idle_call()) { + cpu_do_idle(); + local_irq_enable(); + } } +#ifdef CONFIG_HOTPLUG_CPU +void arch_cpu_idle_dead(void) +{ + cpu_die(); +} +#endif + void machine_shutdown(void) { #ifdef CONFIG_SMP diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 14f73c445ff..4f97db3d736 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -17,12 +17,32 @@ #include <linux/init.h> #include <linux/of.h> +#include <linux/smp.h> #include <asm/compiler.h> +#include <asm/cpu_ops.h> #include <asm/errno.h> #include <asm/psci.h> +#include <asm/smp_plat.h> -struct psci_operations psci_ops; +#define PSCI_POWER_STATE_TYPE_STANDBY 0 +#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 + +struct psci_power_state { + u16 id; + u8 type; + u8 affinity_level; +}; + +struct psci_operations { + int (*cpu_suspend)(struct psci_power_state state, + unsigned long entry_point); + int (*cpu_off)(struct psci_power_state state); + int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); + int (*migrate)(unsigned long cpuid); +}; + +static struct psci_operations psci_ops; static int (*invoke_psci_fn)(u64, u64, u64, u64); @@ -209,3 +229,68 @@ out_put_node: of_node_put(np); return err; } + +#ifdef CONFIG_SMP + +static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu) +{ + return 0; +} + +static int __init cpu_psci_cpu_prepare(unsigned int cpu) +{ + if (!psci_ops.cpu_on) { + pr_err("no cpu_on method, not booting CPU%d\n", cpu); + return -ENODEV; + } + + return 0; +} + +static int cpu_psci_cpu_boot(unsigned int cpu) +{ + int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry)); + if (err) + pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err); + + return err; +} + +#ifdef CONFIG_HOTPLUG_CPU +static int cpu_psci_cpu_disable(unsigned int cpu) +{ + /* Fail early if we don't have CPU_OFF support */ + if (!psci_ops.cpu_off) + return -EOPNOTSUPP; + return 0; +} + +static void cpu_psci_cpu_die(unsigned int cpu) +{ + int ret; + /* + * There are no known implementations of PSCI actually using the + * power state field, pass a sensible default for now. + */ + struct psci_power_state state = { + .type = PSCI_POWER_STATE_TYPE_POWER_DOWN, + }; + + ret = psci_ops.cpu_off(state); + + pr_crit("psci: unable to power off CPU%u (%d)\n", cpu, ret); +} +#endif + +const struct cpu_operations cpu_psci_ops = { + .name = "psci", + .cpu_init = cpu_psci_cpu_init, + .cpu_prepare = cpu_psci_cpu_prepare, + .cpu_boot = cpu_psci_cpu_boot, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = cpu_psci_cpu_disable, + .cpu_die = cpu_psci_cpu_die, +#endif +}; + +#endif diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 6e1e77f1831..7041be26d4a 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -236,31 +236,29 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, { int err, len, type, disabled = !ctrl.enabled; - if (disabled) { - len = 0; - type = HW_BREAKPOINT_EMPTY; - } else { - err = arch_bp_generic_fields(ctrl, &len, &type); - if (err) - return err; - - switch (note_type) { - case NT_ARM_HW_BREAK: - if ((type & HW_BREAKPOINT_X) != type) - return -EINVAL; - break; - case NT_ARM_HW_WATCH: - if ((type & HW_BREAKPOINT_RW) != type) - return -EINVAL; - break; - default: + attr->disabled = disabled; + if (disabled) + return 0; + + err = arch_bp_generic_fields(ctrl, &len, &type); + if (err) + return err; + + switch (note_type) { + case NT_ARM_HW_BREAK: + if ((type & HW_BREAKPOINT_X) != type) return -EINVAL; - } + break; + case NT_ARM_HW_WATCH: + if ((type & HW_BREAKPOINT_RW) != type) + return -EINVAL; + break; + default: + return -EINVAL; } attr->bp_len = len; attr->bp_type = type; - attr->disabled = disabled; return 0; } @@ -658,28 +656,27 @@ static int compat_gpr_get(struct task_struct *target, for (i = 0; i < num_regs; ++i) { unsigned int idx = start + i; - void *reg; + compat_ulong_t reg; switch (idx) { case 15: - reg = (void *)&task_pt_regs(target)->pc; + reg = task_pt_regs(target)->pc; break; case 16: - reg = (void *)&task_pt_regs(target)->pstate; + reg = task_pt_regs(target)->pstate; break; case 17: - reg = (void *)&task_pt_regs(target)->orig_x0; + reg = task_pt_regs(target)->orig_x0; break; default: - reg = (void *)&task_pt_regs(target)->regs[idx]; + reg = task_pt_regs(target)->regs[idx]; } - ret = copy_to_user(ubuf, reg, sizeof(compat_ulong_t)); - + ret = copy_to_user(ubuf, ®, sizeof(reg)); if (ret) break; - else - ubuf += sizeof(compat_ulong_t); + + ubuf += sizeof(reg); } return ret; @@ -707,28 +704,28 @@ static int compat_gpr_set(struct task_struct *target, for (i = 0; i < num_regs; ++i) { unsigned int idx = start + i; - void *reg; + compat_ulong_t reg; + + ret = copy_from_user(®, ubuf, sizeof(reg)); + if (ret) + return ret; + + ubuf += sizeof(reg); switch (idx) { case 15: - reg = (void *)&newregs.pc; + newregs.pc = reg; break; case 16: - reg = (void *)&newregs.pstate; + newregs.pstate = reg; break; case 17: - reg = (void *)&newregs.orig_x0; + newregs.orig_x0 = reg; break; default: - reg = (void *)&newregs.regs[idx]; + newregs.regs[idx] = reg; } - ret = copy_from_user(reg, ubuf, sizeof(compat_ulong_t)); - - if (ret) - goto out; - else - ubuf += sizeof(compat_ulong_t); } if (valid_user_regs(&newregs.user_regs)) @@ -736,7 +733,6 @@ static int compat_gpr_set(struct task_struct *target, else ret = -EINVAL; -out: return ret; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index add6ea61684..26b7c299edc 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -45,6 +45,7 @@ #include <asm/cputype.h> #include <asm/elf.h> #include <asm/cputable.h> +#include <asm/cpu_ops.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/smp_plat.h> @@ -97,6 +98,90 @@ void __init early_print(const char *str, ...) printk("%s", buf); } +void __init smp_setup_processor_id(void) +{ + /* + * clear __my_cpu_offset on boot CPU to avoid hang caused by + * using percpu variable early, for example, lockdep will + * access percpu variable inside lock_release + */ + set_my_cpu_offset(0); +} + +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpu_logical_map(cpu); +} + +struct mpidr_hash mpidr_hash; +#ifdef CONFIG_SMP +/** + * smp_build_mpidr_hash - Pre-compute shifts required at each affinity + * level in order to build a linear index from an + * MPIDR value. Resulting algorithm is a collision + * free hash carried out through shifting and ORing + */ +static void __init smp_build_mpidr_hash(void) +{ + u32 i, affinity, fs[4], bits[4], ls; + u64 mask = 0; + /* + * Pre-scan the list of MPIDRS and filter out bits that do + * not contribute to affinity levels, ie they never toggle. + */ + for_each_possible_cpu(i) + mask |= (cpu_logical_map(i) ^ cpu_logical_map(0)); + pr_debug("mask of set bits %#llx\n", mask); + /* + * Find and stash the last and first bit set at all affinity levels to + * check how many bits are required to represent them. + */ + for (i = 0; i < 4; i++) { + affinity = MPIDR_AFFINITY_LEVEL(mask, i); + /* + * Find the MSB bit and LSB bits position + * to determine how many bits are required + * to express the affinity level. + */ + ls = fls(affinity); + fs[i] = affinity ? ffs(affinity) - 1 : 0; + bits[i] = ls - fs[i]; + } + /* + * An index can be created from the MPIDR_EL1 by isolating the + * significant bits at each affinity level and by shifting + * them in order to compress the 32 bits values space to a + * compressed set of values. This is equivalent to hashing + * the MPIDR_EL1 through shifting and ORing. It is a collision free + * hash though not minimal since some levels might contain a number + * of CPUs that is not an exact power of 2 and their bit + * representation might contain holes, eg MPIDR_EL1[7:0] = {0x2, 0x80}. + */ + mpidr_hash.shift_aff[0] = MPIDR_LEVEL_SHIFT(0) + fs[0]; + mpidr_hash.shift_aff[1] = MPIDR_LEVEL_SHIFT(1) + fs[1] - bits[0]; + mpidr_hash.shift_aff[2] = MPIDR_LEVEL_SHIFT(2) + fs[2] - + (bits[1] + bits[0]); + mpidr_hash.shift_aff[3] = MPIDR_LEVEL_SHIFT(3) + + fs[3] - (bits[2] + bits[1] + bits[0]); + mpidr_hash.mask = mask; + mpidr_hash.bits = bits[3] + bits[2] + bits[1] + bits[0]; + pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] aff3[%u] mask[%#llx] bits[%u]\n", + mpidr_hash.shift_aff[0], + mpidr_hash.shift_aff[1], + mpidr_hash.shift_aff[2], + mpidr_hash.shift_aff[3], + mpidr_hash.mask, + mpidr_hash.bits); + /* + * 4x is an arbitrary value used to warn on a hash table much bigger + * than expected on most systems. + */ + if (mpidr_hash_size() > 4 * num_possible_cpus()) + pr_warn("Large number of MPIDR hash buckets detected\n"); + __flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash)); +} +#endif + static void __init setup_processor(void) { struct cpu_info *cpu_info; @@ -118,7 +203,7 @@ static void __init setup_processor(void) printk("CPU: %s [%08x] revision %d\n", cpu_name, read_cpuid_id(), read_cpuid_id() & 15); - sprintf(init_utsname()->machine, "aarch64"); + sprintf(init_utsname()->machine, ELF_PLATFORM); elf_hwcap = 0; } @@ -269,8 +354,10 @@ void __init setup_arch(char **cmdline_p) psci_init(); cpu_logical_map(0) = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; + cpu_read_bootcpu_ops(); #ifdef CONFIG_SMP smp_init_cpus(); + smp_build_mpidr_hash(); #endif #ifdef CONFIG_VT diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index e393174fe85..e8772c07cf5 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -100,34 +100,6 @@ struct compat_rt_sigframe { #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) -/* - * For ARM syscalls, the syscall number has to be loaded into r7. - * We do not support an OABI userspace. - */ -#define MOV_R7_NR_SIGRETURN (0xe3a07000 | __NR_compat_sigreturn) -#define SVC_SYS_SIGRETURN (0xef000000 | __NR_compat_sigreturn) -#define MOV_R7_NR_RT_SIGRETURN (0xe3a07000 | __NR_compat_rt_sigreturn) -#define SVC_SYS_RT_SIGRETURN (0xef000000 | __NR_compat_rt_sigreturn) - -/* - * For Thumb syscalls, we also pass the syscall number via r7. We therefore - * need two 16-bit instructions. - */ -#define SVC_THUMB_SIGRETURN (((0xdf00 | __NR_compat_sigreturn) << 16) | \ - 0x2700 | __NR_compat_sigreturn) -#define SVC_THUMB_RT_SIGRETURN (((0xdf00 | __NR_compat_rt_sigreturn) << 16) | \ - 0x2700 | __NR_compat_rt_sigreturn) - -const compat_ulong_t aarch32_sigret_code[6] = { - /* - * AArch32 sigreturn code. - * We don't construct an OABI SWI - instead we just set the imm24 field - * to the EABI syscall number so that we create a sane disassembly. - */ - MOV_R7_NR_SIGRETURN, SVC_SYS_SIGRETURN, SVC_THUMB_SIGRETURN, - MOV_R7_NR_RT_SIGRETURN, SVC_SYS_RT_SIGRETURN, SVC_THUMB_RT_SIGRETURN, -}; - static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set) { compat_sigset_t cset; diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S new file mode 100644 index 00000000000..b1925729c69 --- /dev/null +++ b/arch/arm64/kernel/sleep.S @@ -0,0 +1,184 @@ +#include <linux/errno.h> +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/assembler.h> + + .text +/* + * Implementation of MPIDR_EL1 hash algorithm through shifting + * and OR'ing. + * + * @dst: register containing hash result + * @rs0: register containing affinity level 0 bit shift + * @rs1: register containing affinity level 1 bit shift + * @rs2: register containing affinity level 2 bit shift + * @rs3: register containing affinity level 3 bit shift + * @mpidr: register containing MPIDR_EL1 value + * @mask: register containing MPIDR mask + * + * Pseudo C-code: + * + *u32 dst; + * + *compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 rs3, u64 mpidr, u64 mask) { + * u32 aff0, aff1, aff2, aff3; + * u64 mpidr_masked = mpidr & mask; + * aff0 = mpidr_masked & 0xff; + * aff1 = mpidr_masked & 0xff00; + * aff2 = mpidr_masked & 0xff0000; + * aff2 = mpidr_masked & 0xff00000000; + * dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2 | aff3 >> rs3); + *} + * Input registers: rs0, rs1, rs2, rs3, mpidr, mask + * Output register: dst + * Note: input and output registers must be disjoint register sets + (eg: a macro instance with mpidr = x1 and dst = x1 is invalid) + */ + .macro compute_mpidr_hash dst, rs0, rs1, rs2, rs3, mpidr, mask + and \mpidr, \mpidr, \mask // mask out MPIDR bits + and \dst, \mpidr, #0xff // mask=aff0 + lsr \dst ,\dst, \rs0 // dst=aff0>>rs0 + and \mask, \mpidr, #0xff00 // mask = aff1 + lsr \mask ,\mask, \rs1 + orr \dst, \dst, \mask // dst|=(aff1>>rs1) + and \mask, \mpidr, #0xff0000 // mask = aff2 + lsr \mask ,\mask, \rs2 + orr \dst, \dst, \mask // dst|=(aff2>>rs2) + and \mask, \mpidr, #0xff00000000 // mask = aff3 + lsr \mask ,\mask, \rs3 + orr \dst, \dst, \mask // dst|=(aff3>>rs3) + .endm +/* + * Save CPU state for a suspend. This saves callee registers, and allocates + * space on the kernel stack to save the CPU specific registers + some + * other data for resume. + * + * x0 = suspend finisher argument + */ +ENTRY(__cpu_suspend) + stp x29, lr, [sp, #-96]! + stp x19, x20, [sp,#16] + stp x21, x22, [sp,#32] + stp x23, x24, [sp,#48] + stp x25, x26, [sp,#64] + stp x27, x28, [sp,#80] + mov x2, sp + sub sp, sp, #CPU_SUSPEND_SZ // allocate cpu_suspend_ctx + mov x1, sp + /* + * x1 now points to struct cpu_suspend_ctx allocated on the stack + */ + str x2, [x1, #CPU_CTX_SP] + ldr x2, =sleep_save_sp + ldr x2, [x2, #SLEEP_SAVE_SP_VIRT] +#ifdef CONFIG_SMP + mrs x7, mpidr_el1 + ldr x9, =mpidr_hash + ldr x10, [x9, #MPIDR_HASH_MASK] + /* + * Following code relies on the struct mpidr_hash + * members size. + */ + ldp w3, w4, [x9, #MPIDR_HASH_SHIFTS] + ldp w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)] + compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10 + add x2, x2, x8, lsl #3 +#endif + bl __cpu_suspend_finisher + /* + * Never gets here, unless suspend fails. + * Successful cpu_suspend should return from cpu_resume, returning + * through this code path is considered an error + * If the return value is set to 0 force x0 = -EOPNOTSUPP + * to make sure a proper error condition is propagated + */ + cmp x0, #0 + mov x3, #-EOPNOTSUPP + csel x0, x3, x0, eq + add sp, sp, #CPU_SUSPEND_SZ // rewind stack pointer + ldp x19, x20, [sp, #16] + ldp x21, x22, [sp, #32] + ldp x23, x24, [sp, #48] + ldp x25, x26, [sp, #64] + ldp x27, x28, [sp, #80] + ldp x29, lr, [sp], #96 + ret +ENDPROC(__cpu_suspend) + .ltorg + +/* + * x0 must contain the sctlr value retrieved from restored context + */ +ENTRY(cpu_resume_mmu) + ldr x3, =cpu_resume_after_mmu + msr sctlr_el1, x0 // restore sctlr_el1 + isb + br x3 // global jump to virtual address +ENDPROC(cpu_resume_mmu) +cpu_resume_after_mmu: + mov x0, #0 // return zero on success + ldp x19, x20, [sp, #16] + ldp x21, x22, [sp, #32] + ldp x23, x24, [sp, #48] + ldp x25, x26, [sp, #64] + ldp x27, x28, [sp, #80] + ldp x29, lr, [sp], #96 + ret +ENDPROC(cpu_resume_after_mmu) + + .data +ENTRY(cpu_resume) + bl el2_setup // if in EL2 drop to EL1 cleanly +#ifdef CONFIG_SMP + mrs x1, mpidr_el1 + adr x4, mpidr_hash_ptr + ldr x5, [x4] + add x8, x4, x5 // x8 = struct mpidr_hash phys address + /* retrieve mpidr_hash members to compute the hash */ + ldr x2, [x8, #MPIDR_HASH_MASK] + ldp w3, w4, [x8, #MPIDR_HASH_SHIFTS] + ldp w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)] + compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2 + /* x7 contains hash index, let's use it to grab context pointer */ +#else + mov x7, xzr +#endif + adr x0, sleep_save_sp + ldr x0, [x0, #SLEEP_SAVE_SP_PHYS] + ldr x0, [x0, x7, lsl #3] + /* load sp from context */ + ldr x2, [x0, #CPU_CTX_SP] + adr x1, sleep_idmap_phys + /* load physical address of identity map page table in x1 */ + ldr x1, [x1] + mov sp, x2 + /* + * cpu_do_resume expects x0 to contain context physical address + * pointer and x1 to contain physical address of 1:1 page tables + */ + bl cpu_do_resume // PC relative jump, MMU off + b cpu_resume_mmu // Resume MMU, never returns +ENDPROC(cpu_resume) + + .align 3 +mpidr_hash_ptr: + /* + * offset of mpidr_hash symbol from current location + * used to obtain run-time mpidr_hash address with MMU off + */ + .quad mpidr_hash - . +/* + * physical address of identity mapped page tables + */ + .type sleep_idmap_phys, #object +ENTRY(sleep_idmap_phys) + .quad 0 +/* + * struct sleep_save_sp { + * phys_addr_t *save_ptr_stash; + * phys_addr_t save_ptr_stash_phys; + * }; + */ + .type sleep_save_sp, #object +ENTRY(sleep_save_sp) + .space SLEEP_SAVE_SP_SZ // struct sleep_save_sp diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 5d54e3717bf..bd68d67d7da 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -39,6 +39,7 @@ #include <asm/atomic.h> #include <asm/cacheflush.h> #include <asm/cputype.h> +#include <asm/cpu_ops.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -48,76 +49,34 @@ #include <asm/tlbflush.h> #include <asm/ptrace.h> +#define CREATE_TRACE_POINTS +#include <trace/events/arm-ipi.h> + /* * as from 2.5, kernels no longer have an init_tasks structure * so we need some other way of telling a new secondary core * where to place its SVC stack */ struct secondary_data secondary_data; -volatile unsigned long secondary_holding_pen_release = INVALID_HWID; enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, + IPI_TIMER, }; -static DEFINE_RAW_SPINLOCK(boot_lock); - -/* - * Write secondary_holding_pen_release in a way that is guaranteed to be - * visible to all observers, irrespective of whether they're taking part - * in coherency or not. This is necessary for the hotplug code to work - * reliably. - */ -static void __cpuinit write_pen_release(u64 val) -{ - void *start = (void *)&secondary_holding_pen_release; - unsigned long size = sizeof(secondary_holding_pen_release); - - secondary_holding_pen_release = val; - __flush_dcache_area(start, size); -} - /* * Boot a secondary CPU, and assign it the specified idle task. * This also gives us the initial stack to use for this CPU. */ static int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) { - unsigned long timeout; - - /* - * Set synchronisation state between this boot processor - * and the secondary one - */ - raw_spin_lock(&boot_lock); - - /* - * Update the pen release flag. - */ - write_pen_release(cpu_logical_map(cpu)); + if (cpu_ops[cpu]->cpu_boot) + return cpu_ops[cpu]->cpu_boot(cpu); - /* - * Send an event, causing the secondaries to read pen_release. - */ - sev(); - - timeout = jiffies + (1 * HZ); - while (time_before(jiffies, timeout)) { - if (secondary_holding_pen_release == INVALID_HWID) - break; - udelay(10); - } - - /* - * Now the secondary core is starting up let it run its - * calibrations, then wait for it to finish - */ - raw_spin_unlock(&boot_lock); - - return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0; + return -EOPNOTSUPP; } static DECLARE_COMPLETION(cpu_running); @@ -158,6 +117,11 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle) return ret; } +static void __cpuinit smp_store_cpu_info(unsigned int cpuid) +{ + store_cpu_topology(cpuid); +} + /* * This is the secondary CPU boot entry. We're using this CPUs * idle thread stack, but a set of temporary page tables. @@ -167,8 +131,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void) struct mm_struct *mm = &init_mm; unsigned int cpu = smp_processor_id(); - printk("CPU%u: Booted secondary processor\n", cpu); - /* * All kernel threads share the same mm context; grab a * reference and switch to it. @@ -177,6 +139,9 @@ asmlinkage void __cpuinit secondary_start_kernel(void) current->active_mm = mm; cpumask_set_cpu(cpu, mm_cpumask(mm)); + set_my_cpu_offset(per_cpu_offset(smp_processor_id())); + printk("CPU%u: Booted secondary processor\n", cpu); + /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. @@ -187,24 +152,15 @@ asmlinkage void __cpuinit secondary_start_kernel(void) preempt_disable(); trace_hardirqs_off(); - /* - * Let the primary processor know we're out of the - * pen, then head off into the C entry point - */ - write_pen_release(INVALID_HWID); + if (cpu_ops[cpu]->cpu_postboot) + cpu_ops[cpu]->cpu_postboot(); - /* - * Synchronise with the boot thread. - */ - raw_spin_lock(&boot_lock); - raw_spin_unlock(&boot_lock); + smp_store_cpu_info(cpu); /* - * Enable local interrupts. + * Enable GIC and timers. */ notify_cpu_starting(cpu); - local_irq_enable(); - local_fiq_enable(); /* * OK, now it's safe to let the boot CPU continue. Wait for @@ -214,48 +170,126 @@ asmlinkage void __cpuinit secondary_start_kernel(void) set_cpu_online(cpu, true); complete(&cpu_running); + local_irq_enable(); + local_fiq_enable(); + /* * OK, it's off to the idle thread for us */ cpu_startup_entry(CPUHP_ONLINE); } -void __init smp_cpus_done(unsigned int max_cpus) +#ifdef CONFIG_HOTPLUG_CPU +static int op_cpu_disable(unsigned int cpu) { - unsigned long bogosum = loops_per_jiffy * num_online_cpus(); + /* + * If we don't have a cpu_die method, abort before we reach the point + * of no return. CPU0 may not have an cpu_ops, so test for it. + */ + if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die) + return -EOPNOTSUPP; - pr_info("SMP: Total of %d processors activated (%lu.%02lu BogoMIPS).\n", - num_online_cpus(), bogosum / (500000/HZ), - (bogosum / (5000/HZ)) % 100); + /* + * We may need to abort a hot unplug for some other mechanism-specific + * reason. + */ + if (cpu_ops[cpu]->cpu_disable) + return cpu_ops[cpu]->cpu_disable(cpu); + + return 0; } -void __init smp_prepare_boot_cpu(void) +/* + * __cpu_disable runs on the processor to be shutdown. + */ +int __cpu_disable(void) { -} + unsigned int cpu = smp_processor_id(); + int ret; -static void (*smp_cross_call)(const struct cpumask *, unsigned int); + ret = op_cpu_disable(cpu); + if (ret) + return ret; -static const struct smp_enable_ops *enable_ops[] __initconst = { - &smp_spin_table_ops, - &smp_psci_ops, - NULL, -}; + /* + * Take this CPU offline. Once we clear this, we can't return, + * and we must not schedule until we're ready to give up the cpu. + */ + set_cpu_online(cpu, false); -static const struct smp_enable_ops *smp_enable_ops[NR_CPUS]; + /* + * OK - migrate IRQs away from this CPU + */ + migrate_irqs(); -static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name) -{ - const struct smp_enable_ops **ops = enable_ops; + /* + * Remove this CPU from the vm mask set of all processes. + */ + clear_tasks_mm_cpumask(cpu); - while (*ops) { - if (!strcmp(name, (*ops)->name)) - return *ops; + return 0; +} - ops++; +static DECLARE_COMPLETION(cpu_died); + +/* + * called on the thread which is asking for a CPU to be shutdown - + * waits until shutdown has completed, or it is timed out. + */ +void __cpu_die(unsigned int cpu) +{ + if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) { + pr_crit("CPU%u: cpu didn't die\n", cpu); + return; } + pr_notice("CPU%u: shutdown\n", cpu); +} + +/* + * Called from the idle thread for the CPU which has been shutdown. + * + * Note that we disable IRQs here, but do not re-enable them + * before returning to the caller. This is also the behaviour + * of the other hotplug-cpu capable cores, so presumably coming + * out of idle fixes this. + */ +void cpu_die(void) +{ + unsigned int cpu = smp_processor_id(); + + idle_task_exit(); + + local_irq_disable(); - return NULL; + /* Tell __cpu_die() that this CPU is now safe to dispose of */ + complete(&cpu_died); + + /* + * Actually shutdown the CPU. This must never fail. The specific hotplug + * mechanism must perform all required cache maintenance to ensure that + * no dirty lines are lost in the process of shutting down the CPU. + */ + cpu_ops[cpu]->cpu_die(cpu); + + BUG(); } +#endif + +void __init smp_cpus_done(unsigned int max_cpus) +{ + unsigned long bogosum = loops_per_jiffy * num_online_cpus(); + + pr_info("SMP: Total of %d processors activated (%lu.%02lu BogoMIPS).\n", + num_online_cpus(), bogosum / (500000/HZ), + (bogosum / (5000/HZ)) % 100); +} + +void __init smp_prepare_boot_cpu(void) +{ + set_my_cpu_offset(per_cpu_offset(smp_processor_id())); +} + +static void (*smp_cross_call)(const struct cpumask *, unsigned int); /* * Enumerate the possible CPU set from the device tree and build the @@ -264,9 +298,8 @@ static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name) */ void __init smp_init_cpus(void) { - const char *enable_method; struct device_node *dn = NULL; - int i, cpu = 1; + unsigned int i, cpu = 1; bool bootcpu_valid = false; while ((dn = of_find_node_by_type(dn, "cpu"))) { @@ -335,25 +368,10 @@ void __init smp_init_cpus(void) if (cpu >= NR_CPUS) goto next; - /* - * We currently support only the "spin-table" enable-method. - */ - enable_method = of_get_property(dn, "enable-method", NULL); - if (!enable_method) { - pr_err("%s: missing enable-method property\n", - dn->full_name); + if (cpu_read_ops(dn, cpu) != 0) goto next; - } - smp_enable_ops[cpu] = smp_get_enable_ops(enable_method); - - if (!smp_enable_ops[cpu]) { - pr_err("%s: invalid enable-method property: %s\n", - dn->full_name, enable_method); - goto next; - } - - if (smp_enable_ops[cpu]->init_cpu(dn, cpu)) + if (cpu_ops[cpu]->cpu_init(dn, cpu)) goto next; pr_debug("cpu logical map 0x%llx\n", hwid); @@ -383,8 +401,13 @@ next: void __init smp_prepare_cpus(unsigned int max_cpus) { - int cpu, err; - unsigned int ncores = num_possible_cpus(); + int err; + unsigned int cpu, ncores = num_possible_cpus(); + + init_cpu_topology(); + + smp_store_cpu_info(smp_processor_id()); + /* * are we trying to boot more cores than exist? @@ -411,10 +434,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus) if (cpu == smp_processor_id()) continue; - if (!smp_enable_ops[cpu]) + if (!cpu_ops[cpu]) continue; - err = smp_enable_ops[cpu]->prepare_cpu(cpu); + err = cpu_ops[cpu]->cpu_prepare(cpu); if (err) continue; @@ -445,6 +468,7 @@ static const char *ipi_types[NR_IPI] = { S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_TIMER, "Timer broadcast interrupts"), }; void show_ipi_list(struct seq_file *p, int prec) @@ -530,6 +554,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + case IPI_TIMER: + irq_enter(); + tick_receive_broadcast(); + irq_exit(); + break; +#endif + default: pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); break; @@ -542,6 +574,13 @@ void smp_send_reschedule(int cpu) smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE); } +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +void tick_broadcast(const struct cpumask *mask) +{ + smp_cross_call(mask, IPI_TIMER); +} +#endif + void smp_send_stop(void) { unsigned long timeout; diff --git a/arch/arm64/kernel/smp_psci.c b/arch/arm64/kernel/smp_psci.c deleted file mode 100644 index 0c533301be7..00000000000 --- a/arch/arm64/kernel/smp_psci.c +++ /dev/null @@ -1,53 +0,0 @@ -/* - * PSCI SMP initialisation - * - * Copyright (C) 2013 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/init.h> -#include <linux/of.h> -#include <linux/smp.h> - -#include <asm/psci.h> -#include <asm/smp_plat.h> - -static int __init smp_psci_init_cpu(struct device_node *dn, int cpu) -{ - return 0; -} - -static int __init smp_psci_prepare_cpu(int cpu) -{ - int err; - - if (!psci_ops.cpu_on) { - pr_err("psci: no cpu_on method, not booting CPU%d\n", cpu); - return -ENODEV; - } - - err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_holding_pen)); - if (err) { - pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err); - return err; - } - - return 0; -} - -const struct smp_enable_ops smp_psci_ops __initconst = { - .name = "psci", - .init_cpu = smp_psci_init_cpu, - .prepare_cpu = smp_psci_prepare_cpu, -}; diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c index 7c35fa682f7..44c22805d2e 100644 --- a/arch/arm64/kernel/smp_spin_table.c +++ b/arch/arm64/kernel/smp_spin_table.c @@ -16,15 +16,39 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/delay.h> #include <linux/init.h> #include <linux/of.h> #include <linux/smp.h> #include <asm/cacheflush.h> +#include <asm/cpu_ops.h> +#include <asm/cputype.h> +#include <asm/smp_plat.h> + +extern void secondary_holding_pen(void); +volatile unsigned long secondary_holding_pen_release = INVALID_HWID; static phys_addr_t cpu_release_addr[NR_CPUS]; +static DEFINE_RAW_SPINLOCK(boot_lock); + +/* + * Write secondary_holding_pen_release in a way that is guaranteed to be + * visible to all observers, irrespective of whether they're taking part + * in coherency or not. This is necessary for the hotplug code to work + * reliably. + */ +static void write_pen_release(u64 val) +{ + void *start = (void *)&secondary_holding_pen_release; + unsigned long size = sizeof(secondary_holding_pen_release); -static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu) + secondary_holding_pen_release = val; + __flush_dcache_area(start, size); +} + + +static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu) { /* * Determine the address from which the CPU is polling. @@ -40,7 +64,7 @@ static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu) return 0; } -static int __init smp_spin_table_prepare_cpu(int cpu) +static int smp_spin_table_cpu_prepare(unsigned int cpu) { void **release_addr; @@ -48,7 +72,16 @@ static int __init smp_spin_table_prepare_cpu(int cpu) return -ENODEV; release_addr = __va(cpu_release_addr[cpu]); - release_addr[0] = (void *)__pa(secondary_holding_pen); + + /* + * We write the release address as LE regardless of the native + * endianess of the kernel. Therefore, any boot-loaders that + * read this address need to convert this address to the + * boot-loader's endianess before jumping. This is mandated by + * the boot protocol. + */ + release_addr[0] = (void *) cpu_to_le64(__pa(secondary_holding_pen)); + __flush_dcache_area(release_addr, sizeof(release_addr[0])); /* @@ -59,8 +92,60 @@ static int __init smp_spin_table_prepare_cpu(int cpu) return 0; } -const struct smp_enable_ops smp_spin_table_ops __initconst = { +static int smp_spin_table_cpu_boot(unsigned int cpu) +{ + unsigned long timeout; + + /* + * Set synchronisation state between this boot processor + * and the secondary one + */ + raw_spin_lock(&boot_lock); + + /* + * Update the pen release flag. + */ + write_pen_release(cpu_logical_map(cpu)); + + /* + * Send an event, causing the secondaries to read pen_release. + */ + sev(); + + timeout = jiffies + (1 * HZ); + while (time_before(jiffies, timeout)) { + if (secondary_holding_pen_release == INVALID_HWID) + break; + udelay(10); + } + + /* + * Now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ + raw_spin_unlock(&boot_lock); + + return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0; +} + +void smp_spin_table_cpu_postboot(void) +{ + /* + * Let the primary processor know we're out of the pen. + */ + write_pen_release(INVALID_HWID); + + /* + * Synchronise with the boot thread. + */ + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); +} + +const struct cpu_operations smp_spin_table_ops = { .name = "spin-table", - .init_cpu = smp_spin_table_init_cpu, - .prepare_cpu = smp_spin_table_prepare_cpu, + .cpu_init = smp_spin_table_cpu_init, + .cpu_prepare = smp_spin_table_cpu_prepare, + .cpu_boot = smp_spin_table_cpu_boot, + .cpu_postboot = smp_spin_table_cpu_postboot, }; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index d25459ff57f..048334bb265 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -48,7 +48,11 @@ int unwind_frame(struct stackframe *frame) frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); - frame->pc = *(unsigned long *)(fp + 8); + /* + * -4 here because we care about the PC at time of bl, + * not where the return will go. + */ + frame->pc = *(unsigned long *)(fp + 8) - 4; return 0; } diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c new file mode 100644 index 00000000000..1fa9ce4afd8 --- /dev/null +++ b/arch/arm64/kernel/suspend.c @@ -0,0 +1,140 @@ +#include <linux/percpu.h> +#include <linux/slab.h> +#include <asm/cacheflush.h> +#include <asm/cpu_ops.h> +#include <asm/debug-monitors.h> +#include <asm/pgtable.h> +#include <asm/memory.h> +#include <asm/smp_plat.h> +#include <asm/suspend.h> +#include <asm/tlbflush.h> + +extern int __cpu_suspend(unsigned long); +/* + * This is called by __cpu_suspend() to save the state, and do whatever + * flushing is required to ensure that when the CPU goes to sleep we have + * the necessary data available when the caches are not searched. + * + * @arg: Argument to pass to suspend operations + * @ptr: CPU context virtual address + * @save_ptr: address of the location where the context physical address + * must be saved + */ +int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr, + phys_addr_t *save_ptr) +{ + int cpu = smp_processor_id(); + + *save_ptr = virt_to_phys(ptr); + + cpu_do_suspend(ptr); + /* + * Only flush the context that must be retrieved with the MMU + * off. VA primitives ensure the flush is applied to all + * cache levels so context is pushed to DRAM. + */ + __flush_dcache_area(ptr, sizeof(*ptr)); + __flush_dcache_area(save_ptr, sizeof(*save_ptr)); + + return cpu_ops[cpu]->cpu_suspend(arg); +} + +/* + * This hook is provided so that cpu_suspend code can restore HW + * breakpoints as early as possible in the resume path, before reenabling + * debug exceptions. Code cannot be run from a CPU PM notifier since by the + * time the notifier runs debug exceptions might have been enabled already, + * with HW breakpoints registers content still in an unknown state. + */ +void (*hw_breakpoint_restore)(void *); +void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) +{ + /* Prevent multiple restore hook initializations */ + if (WARN_ON(hw_breakpoint_restore)) + return; + hw_breakpoint_restore = hw_bp_restore; +} + +/** + * cpu_suspend + * + * @arg: argument to pass to the finisher function + */ +int cpu_suspend(unsigned long arg) +{ + struct mm_struct *mm = current->active_mm; + int ret, cpu = smp_processor_id(); + unsigned long flags; + + /* + * If cpu_ops have not been registered or suspend + * has not been initialized, cpu_suspend call fails early. + */ + if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend) + return -EOPNOTSUPP; + + /* + * From this point debug exceptions are disabled to prevent + * updates to mdscr register (saved and restored along with + * general purpose registers) from kernel debuggers. + */ + local_dbg_save(flags); + + /* + * mm context saved on the stack, it will be restored when + * the cpu comes out of reset through the identity mapped + * page tables, so that the thread address space is properly + * set-up on function return. + */ + ret = __cpu_suspend(arg); + if (ret == 0) { + cpu_switch_mm(mm->pgd, mm); + flush_tlb_all(); + + /* + * Restore per-cpu offset before any kernel + * subsystem relying on it has a chance to run. + */ + set_my_cpu_offset(per_cpu_offset(cpu)); + + /* + * Restore HW breakpoint registers to sane values + * before debug exceptions are possibly reenabled + * through local_dbg_restore. + */ + if (hw_breakpoint_restore) + hw_breakpoint_restore(NULL); + } + + /* + * Restore pstate flags. OS lock and mdscr have been already + * restored, so from this point onwards, debugging is fully + * renabled if it was enabled when core started shutdown. + */ + local_dbg_restore(flags); + + return ret; +} + +extern struct sleep_save_sp sleep_save_sp; +extern phys_addr_t sleep_idmap_phys; + +static int cpu_suspend_init(void) +{ + void *ctx_ptr; + + /* ctx_ptr is an array of physical addresses */ + ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(phys_addr_t), GFP_KERNEL); + + if (WARN_ON(!ctx_ptr)) + return -ENOMEM; + + sleep_save_sp.save_ptr_stash = ctx_ptr; + sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr); + sleep_idmap_phys = virt_to_phys(idmap_pg_dir); + __flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp)); + __flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys)); + + return 0; +} +early_initcall(cpu_suspend_init); diff --git a/arch/arm64/kernel/sys32.S b/arch/arm64/kernel/sys32.S index a1b19ed7467..423a5b3fc2b 100644 --- a/arch/arm64/kernel/sys32.S +++ b/arch/arm64/kernel/sys32.S @@ -59,48 +59,48 @@ ENDPROC(compat_sys_fstatfs64_wrapper) * extension. */ compat_sys_pread64_wrapper: - orr x3, x4, x5, lsl #32 + regs_to_64 x3, x4, x5 b sys_pread64 ENDPROC(compat_sys_pread64_wrapper) compat_sys_pwrite64_wrapper: - orr x3, x4, x5, lsl #32 + regs_to_64 x3, x4, x5 b sys_pwrite64 ENDPROC(compat_sys_pwrite64_wrapper) compat_sys_truncate64_wrapper: - orr x1, x2, x3, lsl #32 + regs_to_64 x1, x2, x3 b sys_truncate ENDPROC(compat_sys_truncate64_wrapper) compat_sys_ftruncate64_wrapper: - orr x1, x2, x3, lsl #32 + regs_to_64 x1, x2, x3 b sys_ftruncate ENDPROC(compat_sys_ftruncate64_wrapper) compat_sys_readahead_wrapper: - orr x1, x2, x3, lsl #32 + regs_to_64 x1, x2, x3 mov w2, w4 b sys_readahead ENDPROC(compat_sys_readahead_wrapper) compat_sys_fadvise64_64_wrapper: mov w6, w1 - orr x1, x2, x3, lsl #32 - orr x2, x4, x5, lsl #32 + regs_to_64 x1, x2, x3 + regs_to_64 x2, x4, x5 mov w3, w6 b sys_fadvise64_64 ENDPROC(compat_sys_fadvise64_64_wrapper) compat_sys_sync_file_range2_wrapper: - orr x2, x2, x3, lsl #32 - orr x3, x4, x5, lsl #32 + regs_to_64 x2, x2, x3 + regs_to_64 x3, x4, x5 b sys_sync_file_range2 ENDPROC(compat_sys_sync_file_range2_wrapper) compat_sys_fallocate_wrapper: - orr x2, x2, x3, lsl #32 - orr x3, x4, x5, lsl #32 + regs_to_64 x2, x2, x3 + regs_to_64 x3, x4, x5 b sys_fallocate ENDPROC(compat_sys_fallocate_wrapper) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c new file mode 100644 index 00000000000..0460ba0573f --- /dev/null +++ b/arch/arm64/kernel/topology.c @@ -0,0 +1,554 @@ +/* + * arch/arm64/kernel/topology.c + * + * Copyright (C) 2011,2013 Linaro Limited. + * + * Based on the arm32 version written by Vincent Guittot in turn based on + * arch/sh/kernel/topology.c + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/node.h> +#include <linux/nodemask.h> +#include <linux/of.h> +#include <linux/sched.h> +#include <linux/slab.h> + +#include <asm/topology.h> +#include <asm/cputype.h> +#include <asm/smp_plat.h> + + +/* + * cpu power scale management + */ + +/* + * cpu power table + * This per cpu data structure describes the relative capacity of each core. + * On a heteregenous system, cores don't have the same computation capacity + * and we reflect that difference in the cpu_power field so the scheduler can + * take this difference into account during load balance. A per cpu structure + * is preferred because each CPU updates its own cpu_power field during the + * load balance except for idle cores. One idle core is selected to run the + * rebalance_domains for all idle cores and the cpu_power can be updated + * during this sequence. + */ +static DEFINE_PER_CPU(unsigned long, cpu_scale); + +unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return per_cpu(cpu_scale, cpu); +} + +static void set_power_scale(unsigned int cpu, unsigned long power) +{ + per_cpu(cpu_scale, cpu) = power; +} + +#ifdef CONFIG_OF +struct cpu_efficiency { + const char *compatible; + unsigned long efficiency; +}; + +/* + * Table of relative efficiency of each processors + * The efficiency value must fit in 20bit and the final + * cpu_scale value must be in the range + * 0 < cpu_scale < 3*SCHED_POWER_SCALE/2 + * in order to return at most 1 when DIV_ROUND_CLOSEST + * is used to compute the capacity of a CPU. + * Processors that are not defined in the table, + * use the default SCHED_POWER_SCALE value for cpu_scale. + */ +static const struct cpu_efficiency table_efficiency[] = { + { "arm,cortex-a57", 3891 }, + { "arm,cortex-a53", 2048 }, + { NULL, }, +}; + +static unsigned long *__cpu_capacity; +#define cpu_capacity(cpu) __cpu_capacity[cpu] + +static unsigned long middle_capacity = 1; +static int cluster_id; + +static int __init get_cpu_for_node(struct device_node *node) +{ + struct device_node *cpu_node; + int cpu; + + cpu_node = of_parse_phandle(node, "cpu", 0); + if (!cpu_node) { + pr_crit("%s: Unable to parse CPU phandle\n", node->full_name); + return -1; + } + + for_each_possible_cpu(cpu) { + if (of_get_cpu_node(cpu, NULL) == cpu_node) + return cpu; + } + + pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name); + return -1; +} + +static void __init parse_core(struct device_node *core, int core_id) +{ + char name[10]; + bool leaf = true; + int i, cpu; + struct device_node *t; + + i = 0; + do { + snprintf(name, sizeof(name), "thread%d", i); + t = of_get_child_by_name(core, name); + if (t) { + leaf = false; + cpu = get_cpu_for_node(t); + if (cpu >= 0) { + pr_info("CPU%d: socket %d core %d thread %d\n", + cpu, cluster_id, core_id, i); + cpu_topology[cpu].socket_id = cluster_id; + cpu_topology[cpu].core_id = core_id; + cpu_topology[cpu].thread_id = i; + } else { + pr_err("%s: Can't get CPU for thread\n", + t->full_name); + } + } + i++; + } while (t); + + cpu = get_cpu_for_node(core); + if (cpu >= 0) { + if (!leaf) { + pr_err("%s: Core has both threads and CPU\n", + core->full_name); + return; + } + + pr_info("CPU%d: socket %d core %d\n", + cpu, cluster_id, core_id); + cpu_topology[cpu].socket_id = cluster_id; + cpu_topology[cpu].core_id = core_id; + } else if (leaf) { + pr_err("%s: Can't get CPU for leaf core\n", core->full_name); + } +} + +static void __init parse_cluster(struct device_node *cluster, int depth) +{ + char name[10]; + bool leaf = true; + bool has_cores = false; + struct device_node *c; + int core_id = 0; + int i; + + /* + * First check for child clusters; we currently ignore any + * information about the nesting of clusters and present the + * scheduler with a flat list of them. + */ + i = 0; + do { + snprintf(name, sizeof(name), "cluster%d", i); + c = of_get_child_by_name(cluster, name); + if (c) { + parse_cluster(c, depth + 1); + leaf = false; + } + i++; + } while (c); + + /* Now check for cores */ + i = 0; + do { + snprintf(name, sizeof(name), "core%d", i); + c = of_get_child_by_name(cluster, name); + if (c) { + has_cores = true; + + if (depth == 0) + pr_err("%s: cpu-map children should be clusters\n", + c->full_name); + + if (leaf) + parse_core(c, core_id++); + else + pr_err("%s: Non-leaf cluster with core %s\n", + cluster->full_name, name); + } + i++; + } while (c); + + if (leaf && !has_cores) + pr_warn("%s: empty cluster\n", cluster->full_name); + + if (leaf) + cluster_id++; +} + +/* + * Iterate all CPUs' descriptor in DT and compute the efficiency + * (as per table_efficiency). Also calculate a middle efficiency + * as close as possible to (max{eff_i} - min{eff_i}) / 2 + * This is later used to scale the cpu_power field such that an + * 'average' CPU is of middle power. Also see the comments near + * table_efficiency[] and update_cpu_power(). + */ +static void __init parse_dt_topology(void) +{ + const struct cpu_efficiency *cpu_eff; + struct device_node *cn = NULL; + unsigned long min_capacity = (unsigned long)(-1); + unsigned long max_capacity = 0; + unsigned long capacity = 0; + int alloc_size, cpu; + + alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity); + __cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT); + + cn = of_find_node_by_path("/cpus"); + if (!cn) { + pr_err("No CPU information found in DT\n"); + return; + } + + /* + * If topology is provided as a cpu-map it is essentially a + * root cluster. + */ + cn = of_find_node_by_name(cn, "cpu-map"); + if (!cn) + return; + parse_cluster(cn, 0); + + for_each_possible_cpu(cpu) { + const u32 *rate; + int len; + + /* Too early to use cpu->of_node */ + cn = of_get_cpu_node(cpu, NULL); + if (!cn) { + pr_err("Missing device node for CPU %d\n", cpu); + continue; + } + + /* check if the cpu is marked as "disabled", if so ignore */ + if (!of_device_is_available(cn)) + continue; + + for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++) + if (of_device_is_compatible(cn, cpu_eff->compatible)) + break; + + if (cpu_eff->compatible == NULL) { + pr_warn("%s: Unknown CPU type\n", cn->full_name); + continue; + } + + rate = of_get_property(cn, "clock-frequency", &len); + if (!rate || len != 4) { + pr_err("%s: Missing clock-frequency property\n", + cn->full_name); + continue; + } + + capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency; + + /* Save min capacity of the system */ + if (capacity < min_capacity) + min_capacity = capacity; + + /* Save max capacity of the system */ + if (capacity > max_capacity) + max_capacity = capacity; + + cpu_capacity(cpu) = capacity; + } + + /* If min and max capacities are equal we bypass the update of the + * cpu_scale because all CPUs have the same capacity. Otherwise, we + * compute a middle_capacity factor that will ensure that the capacity + * of an 'average' CPU of the system will be as close as possible to + * SCHED_POWER_SCALE, which is the default value, but with the + * constraint explained near table_efficiency[]. + */ + if (min_capacity == max_capacity) + return; + else if (4 * max_capacity < (3 * (max_capacity + min_capacity))) + middle_capacity = (min_capacity + max_capacity) + >> (SCHED_POWER_SHIFT+1); + else + middle_capacity = ((max_capacity / 3) + >> (SCHED_POWER_SHIFT-1)) + 1; + +} + +/* + * Look for a customed capacity of a CPU in the cpu_topo_data table during the + * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the + * function returns directly for SMP system. + */ +static void update_cpu_power(unsigned int cpu) +{ + if (!cpu_capacity(cpu)) + return; + + set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity); + + pr_info("CPU%u: update cpu_power %lu\n", + cpu, arch_scale_freq_power(NULL, cpu)); +} + +#else +static inline void parse_dt_topology(void) {} +static inline void update_cpu_power(unsigned int cpuid) {} +#endif + +/* + * cpu topology table + */ +struct cputopo_arm cpu_topology[NR_CPUS]; +EXPORT_SYMBOL_GPL(cpu_topology); + +const struct cpumask *cpu_coregroup_mask(int cpu) +{ + return &cpu_topology[cpu].core_sibling; +} + +static void update_siblings_masks(unsigned int cpuid) +{ + struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int cpu; + + /* update core and thread sibling masks */ + for_each_possible_cpu(cpu) { + cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->socket_id != cpu_topo->socket_id) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id != cpu_topo->core_id) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); + } + smp_wmb(); +} + +void store_cpu_topology(unsigned int cpuid) +{ + struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + + /* Something should have picked a topology by the time we get here */ + if (cpuid_topo->core_id == -1) + pr_warn("CPU%u: No topology information configured\n", cpuid); + else + update_siblings_masks(cpuid); + + update_cpu_power(cpuid); +} + +#ifdef CONFIG_SCHED_HMP + +/* + * Retrieve logical cpu index corresponding to a given MPIDR[23:0] + * - mpidr: MPIDR[23:0] to be used for the look-up + * + * Returns the cpu logical index or -EINVAL on look-up error + */ +static inline int get_logical_index(u32 mpidr) +{ + int cpu; + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + if (cpu_logical_map(cpu) == mpidr) + return cpu; + return -EINVAL; +} + +static const char * const little_cores[] = { + "arm,cortex-a53", + 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 != 8) { + pr_err("%s missing reg property\n", cn->full_name); + continue; + } + + cpu = get_logical_index(be32_to_cpup(mpidr+1)); + if (cpu == -EINVAL) { + pr_err("couldn't get logical index for mpidr %x\n", + be32_to_cpup(mpidr+1)); + break; + } + + if (is_little_cpu(cn)) + cpumask_set_cpu(cpu, slow); + else + cpumask_set_cpu(cpu, fast); + } + + if (!cpumask_empty(fast) && !cpumask_empty(slow)) + return; + + /* + * We didn't find both big and little cores so let's call all cores + * fast as this will keep the system running, with all cores being + * treated equal. + */ + cpumask_setall(fast); + cpumask_clear(slow); +} + +struct cpumask hmp_slow_cpu_mask; + +void __init arch_get_hmp_domains(struct list_head *hmp_domains_list) +{ + struct cpumask hmp_fast_cpu_mask; + struct hmp_domain *domain; + + arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask); + + /* + * Initialize hmp_domains + * Must be ordered with respect to compute capacity. + * Fastest domain at head of list. + */ + if(!cpumask_empty(&hmp_slow_cpu_mask)) { + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask); + cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus); + list_add(&domain->hmp_domains, hmp_domains_list); + } + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask); + cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus); + list_add(&domain->hmp_domains, hmp_domains_list); +} +#endif /* CONFIG_SCHED_HMP */ + +/* + * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster + * @socket_id: cluster HW identifier + * @cluster_mask: the cpumask location to be initialized, modified by the + * function only if return value == 0 + * + * Return: + * + * 0 on success + * -EINVAL if cluster_mask is NULL or there is no record matching socket_id + */ +int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask) +{ + int cpu; + + if (!cluster_mask) + return -EINVAL; + + for_each_online_cpu(cpu) { + if (socket_id == topology_physical_package_id(cpu)) { + cpumask_copy(cluster_mask, topology_core_cpumask(cpu)); + return 0; + } + } + + return -EINVAL; +} + +/* + * init_cpu_topology is called at boot when only one cpu is running + * which prevent simultaneous write access to cpu_topology array + */ +void __init init_cpu_topology(void) +{ + unsigned int cpu; + + /* init core mask and power*/ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); + + cpu_topo->thread_id = -1; + cpu_topo->core_id = -1; + cpu_topo->socket_id = -1; + cpumask_clear(&cpu_topo->core_sibling); + cpumask_clear(&cpu_topo->thread_sibling); + + set_power_scale(cpu, SCHED_POWER_SCALE); + } + smp_wmb(); + + parse_dt_topology(); + + /* + * Assign all remaining CPUs to a cluster so the scheduler + * doesn't get confused. + */ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; + + if (cpu_topo->socket_id == -1) { + cpu_topo->socket_id = INT_MAX; + cpu_topo->core_id = cpu; + } + } +} diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 6a389dc1bd4..a7149cae161 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -58,7 +58,10 @@ static struct page *vectors_page[1]; static int alloc_vectors_page(void) { extern char __kuser_helper_start[], __kuser_helper_end[]; + extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; + int kuser_sz = __kuser_helper_end - __kuser_helper_start; + int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start; unsigned long vpage; vpage = get_zeroed_page(GFP_ATOMIC); @@ -72,7 +75,7 @@ static int alloc_vectors_page(void) /* sigreturn code */ memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET, - aarch32_sigret_code, sizeof(aarch32_sigret_code)); + __aarch32_sigret_code_start, sigret_sz); flush_icache_range(vpage, vpage + PAGE_SIZE); vectors_page[0] = virt_to_page(vpage); @@ -235,6 +238,8 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->use_syscall = use_syscall; vdso_data->xtime_coarse_sec = xtime_coarse.tv_sec; vdso_data->xtime_coarse_nsec = xtime_coarse.tv_nsec; + vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec; + vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { vdso_data->cs_cycle_last = tk->clock->cycle_last; @@ -242,8 +247,6 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->xtime_clock_nsec = tk->xtime_nsec; vdso_data->cs_mult = tk->mult; vdso_data->cs_shift = tk->shift; - vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec; - vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; } smp_wmb(); diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index d8064af42e6..6d20b7d162d 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -48,7 +48,7 @@ $(obj-vdso): %.o: %.S # Actual build commands quiet_cmd_vdsold = VDSOL $@ - cmd_vdsold = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@ quiet_cmd_vdsoas = VDSOA $@ cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index f0a6d10b521..fe652ffd34c 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -103,6 +103,8 @@ ENTRY(__kernel_clock_gettime) bl __do_get_tspec seqcnt_check w9, 1b + mov x30, x2 + cmp w0, #CLOCK_MONOTONIC b.ne 6f @@ -118,6 +120,9 @@ ENTRY(__kernel_clock_gettime) ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne b.ne 8f + /* xtime_coarse_nsec is already right-shifted */ + mov x12, #0 + /* Get coarse timespec. */ adr vdso_data, _vdso_data 3: seqcnt_acquire @@ -156,7 +161,7 @@ ENTRY(__kernel_clock_gettime) lsr x11, x11, x12 stp x10, x11, [x1, #TSPEC_TV_SEC] mov x0, xzr - ret x2 + ret 7: mov x30, x2 8: /* Syscall fallback. */ diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 3fae2be8b01..2c8a95b539c 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -41,7 +41,6 @@ SECTIONS } .text : { /* Real text segment */ _stext = .; /* Text and read-only data */ - *(.smp.pen.text) __exception_text_start = .; *(.exception.text) __exception_text_end = .; diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 3140a2abcdc..b51d36401d8 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -2,3 +2,4 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ cache.o copypage.o flush.o \ ioremap.o mmap.o pgd.o mmu.o \ context.o tlb.o proc.o +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 48a386094fa..4726b8209d3 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -166,3 +166,81 @@ ENTRY(__flush_dcache_area) dsb sy ret ENDPROC(__flush_dcache_area) + +/* + * __dma_inv_range(start, end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +__dma_inv_range: + dcache_line_size x2, x3 + sub x3, x2, #1 + bic x0, x0, x3 + bic x1, x1, x3 +1: dc ivac, x0 // invalidate D / U line + add x0, x0, x2 + cmp x0, x1 + b.lo 1b + dsb sy + ret +ENDPROC(__dma_inv_range) + +/* + * __dma_clean_range(start, end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +__dma_clean_range: + dcache_line_size x2, x3 + sub x3, x2, #1 + bic x0, x0, x3 +1: dc cvac, x0 // clean D / U line + add x0, x0, x2 + cmp x0, x1 + b.lo 1b + dsb sy + ret +ENDPROC(__dma_clean_range) + +/* + * __dma_flush_range(start, end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(__dma_flush_range) + dcache_line_size x2, x3 + sub x3, x2, #1 + bic x0, x0, x3 +1: dc civac, x0 // clean & invalidate D / U line + add x0, x0, x2 + cmp x0, x1 + b.lo 1b + dsb sy + ret +ENDPROC(__dma_flush_range) + +/* + * __dma_map_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(__dma_map_area) + add x1, x1, x0 + cmp w2, #DMA_FROM_DEVICE + b.eq __dma_inv_range + b __dma_clean_range +ENDPROC(__dma_map_area) + +/* + * __dma_unmap_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(__dma_unmap_area) + add x1, x1, x0 + cmp w2, #DMA_TO_DEVICE + b.ne __dma_inv_range + ret +ENDPROC(__dma_unmap_area) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 4bd7579ec9e..ba0ff75666e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -29,9 +29,9 @@ struct dma_map_ops *dma_ops; EXPORT_SYMBOL(dma_ops); -static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) +static void *__dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) { if (IS_ENABLED(CONFIG_ZONE_DMA32) && dev->coherent_dma_mask <= DMA_BIT_MASK(32)) @@ -39,16 +39,175 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size, return swiotlb_alloc_coherent(dev, size, dma_handle, flags); } -static void arm64_swiotlb_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) +static void __dma_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) { swiotlb_free_coherent(dev, size, vaddr, dma_handle); } -static struct dma_map_ops arm64_swiotlb_dma_ops = { - .alloc = arm64_swiotlb_alloc_coherent, - .free = arm64_swiotlb_free_coherent, +static void *__dma_alloc_noncoherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) +{ + struct page *page, **map; + void *ptr, *coherent_ptr; + int order, i; + + size = PAGE_ALIGN(size); + order = get_order(size); + + ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs); + if (!ptr) + goto no_mem; + map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA); + if (!map) + goto no_map; + + /* remove any dirty cache lines on the kernel alias */ + __dma_flush_range(ptr, ptr + size); + + /* create a coherent mapping */ + page = virt_to_page(ptr); + for (i = 0; i < (size >> PAGE_SHIFT); i++) + map[i] = page + i; + coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP, + pgprot_dmacoherent(pgprot_default)); + kfree(map); + if (!coherent_ptr) + goto no_map; + + return coherent_ptr; + +no_map: + __dma_free_coherent(dev, size, ptr, *dma_handle, attrs); +no_mem: + *dma_handle = ~0; + return NULL; +} + +static void __dma_free_noncoherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle)); + + vunmap(vaddr); + __dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs); +} + +static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + dma_addr_t dev_addr; + + dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs); + __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); + + return dev_addr; +} + + +static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); + swiotlb_unmap_page(dev, dev_addr, size, dir, attrs); +} + +static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct scatterlist *sg; + int i, ret; + + ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs); + for_each_sg(sgl, sg, ret, i) + __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), + sg->length, dir); + + return ret; +} + +static void __swiotlb_unmap_sg_attrs(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nelems, i) + __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), + sg->length, dir); + swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs); +} + +static void __swiotlb_sync_single_for_cpu(struct device *dev, + dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir) +{ + __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); + swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir); +} + +static void __swiotlb_sync_single_for_device(struct device *dev, + dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir) +{ + swiotlb_sync_single_for_device(dev, dev_addr, size, dir); + __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); +} + +static void __swiotlb_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nelems, i) + __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), + sg->length, dir); + swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir); +} + +static void __swiotlb_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + swiotlb_sync_sg_for_device(dev, sgl, nelems, dir); + for_each_sg(sgl, sg, nelems, i) + __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), + sg->length, dir); +} + +struct dma_map_ops noncoherent_swiotlb_dma_ops = { + .alloc = __dma_alloc_noncoherent, + .free = __dma_free_noncoherent, + .map_page = __swiotlb_map_page, + .unmap_page = __swiotlb_unmap_page, + .map_sg = __swiotlb_map_sg_attrs, + .unmap_sg = __swiotlb_unmap_sg_attrs, + .sync_single_for_cpu = __swiotlb_sync_single_for_cpu, + .sync_single_for_device = __swiotlb_sync_single_for_device, + .sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu, + .sync_sg_for_device = __swiotlb_sync_sg_for_device, + .dma_supported = swiotlb_dma_supported, + .mapping_error = swiotlb_dma_mapping_error, +}; +EXPORT_SYMBOL(noncoherent_swiotlb_dma_ops); + +struct dma_map_ops coherent_swiotlb_dma_ops = { + .alloc = __dma_alloc_coherent, + .free = __dma_free_coherent, .map_page = swiotlb_map_page, .unmap_page = swiotlb_unmap_page, .map_sg = swiotlb_map_sg_attrs, @@ -60,10 +219,11 @@ static struct dma_map_ops arm64_swiotlb_dma_ops = { .dma_supported = swiotlb_dma_supported, .mapping_error = swiotlb_dma_mapping_error, }; +EXPORT_SYMBOL(coherent_swiotlb_dma_ops); void __init arm64_swiotlb_init(void) { - dma_ops = &arm64_swiotlb_dma_ops; + dma_ops = &coherent_swiotlb_dma_ops; swiotlb_init(1); } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 1426468b77f..6c8ba25bf6b 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -152,25 +152,8 @@ void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs) #define ESR_CM (1 << 8) #define ESR_LNX_EXEC (1 << 24) -/* - * Check that the permissions on the VMA allow for the fault which occurred. - * If we encountered a write fault, we must have write permission, otherwise - * we allow any permission. - */ -static inline bool access_error(unsigned int esr, struct vm_area_struct *vma) -{ - unsigned int mask = VM_READ | VM_WRITE | VM_EXEC; - - if (esr & ESR_WRITE) - mask = VM_WRITE; - if (esr & ESR_LNX_EXEC) - mask = VM_EXEC; - - return vma->vm_flags & mask ? false : true; -} - static int __do_page_fault(struct mm_struct *mm, unsigned long addr, - unsigned int esr, unsigned int flags, + unsigned int mm_flags, unsigned long vm_flags, struct task_struct *tsk) { struct vm_area_struct *vma; @@ -188,12 +171,17 @@ static int __do_page_fault(struct mm_struct *mm, unsigned long addr, * it. */ good_area: - if (access_error(esr, vma)) { + /* + * Check that the permissions on the VMA allow for the fault which + * occurred. If we encountered a write or exec fault, we must have + * appropriate permissions, otherwise we allow any permission. + */ + if (!(vma->vm_flags & vm_flags)) { fault = VM_FAULT_BADACCESS; goto out; } - return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags); + return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags); check_stack: if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr)) @@ -208,9 +196,15 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, struct task_struct *tsk; struct mm_struct *mm; int fault, sig, code; - bool write = (esr & ESR_WRITE) && !(esr & ESR_CM); - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0); + unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; + unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + + if (esr & ESR_LNX_EXEC) { + vm_flags = VM_EXEC; + } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) { + vm_flags = VM_WRITE; + mm_flags |= FAULT_FLAG_WRITE; + } tsk = current; mm = tsk->mm; @@ -248,7 +242,7 @@ retry: #endif } - fault = __do_page_fault(mm, addr, esr, flags, tsk); + fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk); /* * If we need to retry but a fatal signal is pending, handle the @@ -265,7 +259,7 @@ retry: */ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); - if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (mm_flags & FAULT_FLAG_ALLOW_RETRY) { if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, @@ -280,7 +274,7 @@ retry: * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of * starvation. */ - flags &= ~FAULT_FLAG_ALLOW_RETRY; + mm_flags &= ~FAULT_FLAG_ALLOW_RETRY; goto retry; } } @@ -365,17 +359,6 @@ static int __kprobes do_translation_fault(unsigned long addr, } /* - * Some section permission faults need to be handled gracefully. They can - * happen due to a __{get,put}_user during an oops. - */ -static int do_sect_fault(unsigned long addr, unsigned int esr, - struct pt_regs *regs) -{ - do_bad_area(addr, esr, regs); - return 0; -} - -/* * This abort handler always returns "fault". */ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs) @@ -398,12 +381,12 @@ static struct fault_info { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_bad, SIGBUS, 0, "reserved access flag fault" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, { do_bad, SIGBUS, 0, "reserved permission fault" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_bad, SIGBUS, 0, "synchronous external abort" }, { do_bad, SIGBUS, 0, "asynchronous external abort" }, diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 88611c3a421..7c716634a67 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -77,14 +77,12 @@ void __flush_dcache_page(struct page *page) void __sync_icache_dcache(pte_t pte, unsigned long addr) { - unsigned long pfn; - struct page *page; + struct page *page = pte_page(pte); - pfn = pte_pfn(pte); - if (!pfn_valid(pfn)) + /* no flushing needed for anonymous pages */ + if (!page_mapping(page)) return; - page = pfn_to_page(pfn); if (!test_and_set_bit(PG_dcache_clean, &page->flags)) { __flush_dcache_page(page); __flush_icache_all(); @@ -94,28 +92,14 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr) } /* - * Ensure cache coherency between kernel mapping and userspace mapping of this - * page. + * This function is called when a page has been modified by the kernel. Mark + * it as dirty for later flushing when mapped in user space (if executable, + * see __sync_icache_dcache). */ void flush_dcache_page(struct page *page) { - struct address_space *mapping; - - /* - * The zero page is never written to, so never has any dirty cache - * lines, and therefore never needs to be flushed. - */ - if (page == ZERO_PAGE(0)) - return; - - mapping = page_mapping(page); - if (mapping && mapping_mapped(mapping)) { - __flush_dcache_page(page); - __flush_icache_all(); - set_bit(PG_dcache_clean, &page->flags); - } else { + if (test_bit(PG_dcache_clean, &page->flags)) clear_bit(PG_dcache_clean, &page->flags); - } } EXPORT_SYMBOL(flush_dcache_page); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c new file mode 100644 index 00000000000..2fc8258bab2 --- /dev/null +++ b/arch/arm64/mm/hugetlbpage.c @@ -0,0 +1,70 @@ +/* + * arch/arm64/mm/hugetlbpage.c + * + * Copyright (C) 2013 Linaro Ltd. + * + * Based on arch/x86/mm/hugetlbpage.c. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/init.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/pagemap.h> +#include <linux/err.h> +#include <linux/sysctl.h> +#include <asm/mman.h> +#include <asm/tlb.h> +#include <asm/tlbflush.h> +#include <asm/pgalloc.h> + +#ifndef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + return 0; +} +#endif + +struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, + int write) +{ + return ERR_PTR(-EINVAL); +} + +int pmd_huge(pmd_t pmd) +{ + return !(pmd_val(pmd) & PMD_TABLE_BIT); +} + +int pud_huge(pud_t pud) +{ + return !(pud_val(pud) & PUD_TABLE_BIT); +} + +static __init int setup_hugepagesz(char *opt) +{ + unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { + hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); + } else if (ps == PUD_SIZE) { + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else { + pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20); + return 0; + } + return 1; +} +__setup("hugepagesz=", setup_hugepagesz); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index eeecc9c8ed6..49961d1fa03 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -203,10 +203,18 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, do { next = pmd_addr_end(addr, end); /* try section mapping first */ - if (((addr | next | phys) & ~SECTION_MASK) == 0) + if (((addr | next | phys) & ~SECTION_MASK) == 0) { + pmd_t old_pmd =*pmd; set_pmd(pmd, __pmd(phys | prot_sect_kernel)); - else + /* + * Check for previous table entries created during + * boot (__create_page_tables) and flush them. + */ + if (!pmd_none(old_pmd)) + flush_tlb_all(); + } else { alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys)); + } phys += next - addr; } while (pmd++, addr = next, addr != end); } @@ -297,6 +305,16 @@ static void __init map_mem(void) { struct memblock_region *reg; + /* + * Temporarily limit the memblock range. We need to do this as + * create_mapping requires puds, pmds and ptes to be allocated from + * memory addressable from the initial direct kernel mapping. + * + * The initial direct kernel mapping, located at swapper_pg_dir, + * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (aligned). + */ + memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE); + /* map all the memory banks */ for_each_memblock(memory, reg) { phys_addr_t start = reg->base; @@ -307,6 +325,9 @@ static void __init map_mem(void) create_mapping(start, __phys_to_virt(start), end - start); } + + /* Limit no longer required. */ + memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); } /* @@ -317,12 +338,6 @@ void __init paging_init(void) { void *zero_page; - /* - * Maximum PGDIR_SIZE addressable via the initial direct kernel - * mapping in swapper_pg_dir. - */ - memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE); - init_mem_pgprot(); map_mem(); @@ -339,7 +354,6 @@ void __init paging_init(void) bootmem_init(); empty_zero_page = virt_to_page(zero_page); - __flush_dcache_page(empty_zero_page); /* * TTBR0 is only used for the identity mapping at this stage. Make it diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index a82ae886807..ef9104692d8 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -80,6 +80,75 @@ ENTRY(cpu_do_idle) ret ENDPROC(cpu_do_idle) +#ifdef CONFIG_ARM64_CPU_SUSPEND +/** + * cpu_do_suspend - save CPU registers context + * + * x0: virtual address of context pointer + */ +ENTRY(cpu_do_suspend) + mrs x2, tpidr_el0 + mrs x3, tpidrro_el0 + mrs x4, contextidr_el1 + mrs x5, mair_el1 + mrs x6, cpacr_el1 + mrs x7, ttbr1_el1 + mrs x8, tcr_el1 + mrs x9, vbar_el1 + mrs x10, mdscr_el1 + mrs x11, oslsr_el1 + mrs x12, sctlr_el1 + stp x2, x3, [x0] + stp x4, x5, [x0, #16] + stp x6, x7, [x0, #32] + stp x8, x9, [x0, #48] + stp x10, x11, [x0, #64] + str x12, [x0, #80] + ret +ENDPROC(cpu_do_suspend) + +/** + * cpu_do_resume - restore CPU register context + * + * x0: Physical address of context pointer + * x1: ttbr0_el1 to be restored + * + * Returns: + * sctlr_el1 value in x0 + */ +ENTRY(cpu_do_resume) + /* + * Invalidate local tlb entries before turning on MMU + */ + tlbi vmalle1 + ldp x2, x3, [x0] + ldp x4, x5, [x0, #16] + ldp x6, x7, [x0, #32] + ldp x8, x9, [x0, #48] + ldp x10, x11, [x0, #64] + ldr x12, [x0, #80] + msr tpidr_el0, x2 + msr tpidrro_el0, x3 + msr contextidr_el1, x4 + msr mair_el1, x5 + msr cpacr_el1, x6 + msr ttbr0_el1, x1 + msr ttbr1_el1, x7 + msr tcr_el1, x8 + msr vbar_el1, x9 + msr mdscr_el1, x10 + /* + * Restore oslsr_el1 by writing oslar_el1 + */ + ubfx x11, x11, #1, #1 + msr oslar_el1, x11 + mov x0, x12 + dsb nsh // Make sure local tlb invalidation completed + isb + ret +ENDPROC(cpu_do_resume) +#endif + /* * cpu_switch_mm(pgd_phys, tsk) * @@ -95,10 +164,6 @@ ENTRY(cpu_do_switch_mm) ret ENDPROC(cpu_do_switch_mm) -cpu_name: - .ascii "AArch64 Processor" - .align - .section ".text.init", #alloc, #execinstr /* @@ -151,7 +216,7 @@ ENTRY(__cpu_setup) * both user and kernel. */ ldr x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | TCR_IPS_40BIT | \ - TCR_ASID16 | (1 << 31) + TCR_ASID16 | TCR_TBI0 | (1 << 31) #ifdef CONFIG_ARM64_64K_PAGES orr x10, x10, TCR_TG0_64K orr x10, x10, TCR_TG1_64K @@ -166,9 +231,9 @@ ENDPROC(__cpu_setup) * CE0 XWHW CZ ME TEEA S * .... .IEE .... NEAI TE.I ..AD DEN0 ACAM * 0011 0... 1101 ..0. ..0. 10.. .... .... < hardware reserved - * .... .100 .... 01.1 11.1 ..01 0001 1101 < software settings + * .... .1.. .... 01.1 11.1 ..01 0001 1101 < software settings */ .type crval, #object crval: - .word 0x030802e2 // clear + .word 0x000802e2 // clear .word 0x0405d11d // set diff --git a/arch/arm64/mm/tlb.S b/arch/arm64/mm/tlb.S index 8ae80a18e8e..19da91e0cd2 100644 --- a/arch/arm64/mm/tlb.S +++ b/arch/arm64/mm/tlb.S @@ -35,7 +35,7 @@ */ ENTRY(__cpu_flush_user_tlb_range) vma_vm_mm x3, x2 // get vma->vm_mm - mmid x3, x3 // get vm_mm->context.id + mmid w3, x3 // get vm_mm->context.id dsb sy lsr x0, x0, #12 // align address lsr x1, x1, #12 |