diff options
Diffstat (limited to 'arch/arm/kernel')
| -rw-r--r-- | arch/arm/kernel/Makefile | 1 | ||||
| -rw-r--r-- | arch/arm/kernel/calls.S | 1 | ||||
| -rw-r--r-- | arch/arm/kernel/head.S | 2 | ||||
| -rw-r--r-- | arch/arm/kernel/iwmmxt.S | 8 | ||||
| -rw-r--r-- | arch/arm/kernel/machine_kexec.c | 7 | ||||
| -rw-r--r-- | arch/arm/kernel/pj4-cp0.c | 42 | ||||
| -rw-r--r-- | arch/arm/kernel/sys_oabi-compat.c | 6 | ||||
| -rw-r--r-- | arch/arm/kernel/topology.c | 80 |
8 files changed, 111 insertions, 36 deletions
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index a766bcbaf8ad..040619c32d68 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -79,6 +79,7 @@ obj-$(CONFIG_CPU_XSCALE) += xscale-cp0.o obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o obj-$(CONFIG_CPU_PJ4) += pj4-cp0.o +obj-$(CONFIG_CPU_PJ4B) += pj4-cp0.o obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o perf_event_cpu.o diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index 166e945de832..8f51bdcdacbb 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -391,6 +391,7 @@ CALL(sys_finit_module) /* 380 */ CALL(sys_sched_setattr) CALL(sys_sched_getattr) + CALL(sys_renameat2) #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index f8c08839edf3..591d6e4a6492 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -587,7 +587,7 @@ __fixup_pv_table: add r6, r6, r3 @ adjust __pv_phys_pfn_offset address add r7, r7, r3 @ adjust __pv_offset address mov r0, r8, lsr #12 @ convert to PFN - str r0, [r6, #LOW_OFFSET] @ save computed PHYS_OFFSET to __pv_phys_pfn_offset + str r0, [r6] @ save computed PHYS_OFFSET to __pv_phys_pfn_offset strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits mov r6, r3, lsr #24 @ constant for add/sub instructions teq r3, r6, lsl #24 @ must be 16MiB aligned diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S index a08783823b32..2452dd1bef53 100644 --- a/arch/arm/kernel/iwmmxt.S +++ b/arch/arm/kernel/iwmmxt.S @@ -19,12 +19,16 @@ #include <asm/thread_info.h> #include <asm/asm-offsets.h> -#if defined(CONFIG_CPU_PJ4) +#if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B) #define PJ4(code...) code #define XSC(code...) -#else +#elif defined(CONFIG_CPU_MOHAWK) || \ + defined(CONFIG_CPU_XSC3) || \ + defined(CONFIG_CPU_XSCALE) #define PJ4(code...) #define XSC(code...) code +#else +#error "Unsupported iWMMXt architecture" #endif #define MMX_WR0 (0x00) diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index f0d180d8b29f..8cf0996aa1a8 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -184,3 +184,10 @@ void machine_kexec(struct kimage *image) soft_restart(reboot_entry_phys); } + +void arch_crash_save_vmcoreinfo(void) +{ +#ifdef CONFIG_ARM_LPAE + VMCOREINFO_CONFIG(ARM_LPAE); +#endif +} diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c index fc7208636284..8153e36b2491 100644 --- a/arch/arm/kernel/pj4-cp0.c +++ b/arch/arm/kernel/pj4-cp0.c @@ -45,7 +45,7 @@ static int iwmmxt_do(struct notifier_block *self, unsigned long cmd, void *t) return NOTIFY_DONE; } -static struct notifier_block iwmmxt_notifier_block = { +static struct notifier_block __maybe_unused iwmmxt_notifier_block = { .notifier_call = iwmmxt_do, }; @@ -72,6 +72,33 @@ static void __init pj4_cp_access_write(u32 value) : "=r" (temp) : "r" (value)); } +static int __init pj4_get_iwmmxt_version(void) +{ + u32 cp_access, wcid; + + cp_access = pj4_cp_access_read(); + pj4_cp_access_write(cp_access | 0xf); + + /* check if coprocessor 0 and 1 are available */ + if ((pj4_cp_access_read() & 0xf) != 0xf) { + pj4_cp_access_write(cp_access); + return -ENODEV; + } + + /* read iWMMXt coprocessor id register p1, c0 */ + __asm__ __volatile__ ("mrc p1, 0, %0, c0, c0, 0\n" : "=r" (wcid)); + + pj4_cp_access_write(cp_access); + + /* iWMMXt v1 */ + if ((wcid & 0xffffff00) == 0x56051000) + return 1; + /* iWMMXt v2 */ + if ((wcid & 0xffffff00) == 0x56052000) + return 2; + + return -EINVAL; +} /* * Disable CP0/CP1 on boot, and let call_fpe() and the iWMMXt lazy @@ -79,17 +106,26 @@ static void __init pj4_cp_access_write(u32 value) */ static int __init pj4_cp0_init(void) { - u32 cp_access; + u32 __maybe_unused cp_access; + int vers; if (!cpu_is_pj4()) return 0; + vers = pj4_get_iwmmxt_version(); + if (vers < 0) + return 0; + +#ifndef CONFIG_IWMMXT + pr_info("PJ4 iWMMXt coprocessor detected, but kernel support is missing.\n"); +#else cp_access = pj4_cp_access_read() & ~0xf; pj4_cp_access_write(cp_access); - printk(KERN_INFO "PJ4 iWMMXt coprocessor enabled.\n"); + pr_info("PJ4 iWMMXt v%d coprocessor enabled.\n", vers); elf_hwcap |= HWCAP_IWMMXT; thread_register_notifier(&iwmmxt_notifier_block); +#endif return 0; } diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 702bd329d9d0..e90a3148f385 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -203,9 +203,9 @@ asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, int ret; switch (cmd) { - case F_GETLKP: - case F_SETLKP: - case F_SETLKPW: + case F_OFD_GETLK: + case F_OFD_SETLK: + case F_OFD_SETLKW: case F_GETLK64: case F_SETLK64: case F_SETLKW64: diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 0bc94b1fd1ae..d42a7db22236 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -26,30 +26,30 @@ #include <asm/topology.h> /* - * cpu power scale management + * cpu capacity scale management */ /* - * cpu power table + * cpu capacity 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. + * and we reflect that difference in the cpu_capacity 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_capacity 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_capacity 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) +unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) { return per_cpu(cpu_scale, cpu); } -static void set_power_scale(unsigned int cpu, unsigned long power) +static void set_capacity_scale(unsigned int cpu, unsigned long capacity) { - per_cpu(cpu_scale, cpu) = power; + per_cpu(cpu_scale, cpu) = capacity; } #ifdef CONFIG_OF @@ -62,11 +62,11 @@ struct cpu_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 + * 0 < cpu_scale < 3*SCHED_CAPACITY_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. + * use the default SCHED_CAPACITY_SCALE value for cpu_scale. */ static const struct cpu_efficiency table_efficiency[] = { {"arm,cortex-a15", 3891}, @@ -83,9 +83,9 @@ static unsigned long middle_capacity = 1; * 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(). + * This is later used to scale the cpu_capacity field such that an + * 'average' CPU is of middle capacity. Also see the comments near + * table_efficiency[] and update_cpu_capacity(). */ static void __init parse_dt_topology(void) { @@ -141,15 +141,15 @@ static void __init parse_dt_topology(void) * 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 + * SCHED_CAPACITY_SCALE, which is the default value, but with the * constraint explained near table_efficiency[]. */ if (4*max_capacity < (3*(max_capacity + min_capacity))) middle_capacity = (min_capacity + max_capacity) - >> (SCHED_POWER_SHIFT+1); + >> (SCHED_CAPACITY_SHIFT+1); else middle_capacity = ((max_capacity / 3) - >> (SCHED_POWER_SHIFT-1)) + 1; + >> (SCHED_CAPACITY_SHIFT-1)) + 1; } @@ -158,20 +158,20 @@ static void __init parse_dt_topology(void) * 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) +static void update_cpu_capacity(unsigned int cpu) { if (!cpu_capacity(cpu)) return; - set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity); + set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity); - printk(KERN_INFO "CPU%u: update cpu_power %lu\n", - cpu, arch_scale_freq_power(NULL, cpu)); + printk(KERN_INFO "CPU%u: update cpu_capacity %lu\n", + cpu, arch_scale_freq_capacity(NULL, cpu)); } #else static inline void parse_dt_topology(void) {} -static inline void update_cpu_power(unsigned int cpuid) {} +static inline void update_cpu_capacity(unsigned int cpuid) {} #endif /* @@ -185,6 +185,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return &cpu_topology[cpu].core_sibling; } +/* + * The current assumption is that we can power gate each core independently. + * This will be superseded by DT binding once available. + */ +const struct cpumask *cpu_corepower_mask(int cpu) +{ + return &cpu_topology[cpu].thread_sibling; +} + static void update_siblings_masks(unsigned int cpuid) { struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; @@ -258,7 +267,7 @@ void store_cpu_topology(unsigned int cpuid) update_siblings_masks(cpuid); - update_cpu_power(cpuid); + update_cpu_capacity(cpuid); printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, @@ -266,6 +275,20 @@ void store_cpu_topology(unsigned int cpuid) cpu_topology[cpuid].socket_id, mpidr); } +static inline const int cpu_corepower_flags(void) +{ + return SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN; +} + +static struct sched_domain_topology_level arm_topology[] = { +#ifdef CONFIG_SCHED_MC + { cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) }, + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + /* * init_cpu_topology is called at boot when only one cpu is running * which prevent simultaneous write access to cpu_topology array @@ -274,7 +297,7 @@ void __init init_cpu_topology(void) { unsigned int cpu; - /* init core mask and power*/ + /* init core mask and capacity */ for_each_possible_cpu(cpu) { struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); @@ -284,9 +307,12 @@ void __init init_cpu_topology(void) cpumask_clear(&cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); - set_power_scale(cpu, SCHED_POWER_SCALE); + set_capacity_scale(cpu, SCHED_CAPACITY_SCALE); } smp_wmb(); parse_dt_topology(); + + /* Set scheduler topology descriptor */ + set_sched_topology(arm_topology); } |