diff options
Diffstat (limited to 'arch/arm/kernel')
-rw-r--r-- | arch/arm/kernel/entry-armv.S | 1 | ||||
-rw-r--r-- | arch/arm/kernel/kprobes-test-arm.c | 4 | ||||
-rw-r--r-- | arch/arm/kernel/kprobes-thumb.c | 2 | ||||
-rw-r--r-- | arch/arm/kernel/perf_event.c | 2 | ||||
-rw-r--r-- | arch/arm/kernel/ptrace.c | 3 | ||||
-rw-r--r-- | arch/arm/kernel/signal.c | 46 | ||||
-rw-r--r-- | arch/arm/kernel/signal.h | 2 | ||||
-rw-r--r-- | arch/arm/kernel/topology.c | 278 | ||||
-rw-r--r-- | arch/arm/kernel/traps.c | 2 | ||||
-rw-r--r-- | arch/arm/kernel/vmlinux.lds.S | 2 |
10 files changed, 307 insertions, 35 deletions
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 437f0c42651..0d1851ca6eb 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -495,6 +495,7 @@ ENDPROC(__und_usr) * The out of line fixup for the ldrt above. */ .pushsection .fixup, "ax" + .align 2 4: mov pc, r9 .popsection .pushsection __ex_table,"a" diff --git a/arch/arm/kernel/kprobes-test-arm.c b/arch/arm/kernel/kprobes-test-arm.c index ba32b393b3f..38c1a3b103a 100644 --- a/arch/arm/kernel/kprobes-test-arm.c +++ b/arch/arm/kernel/kprobes-test-arm.c @@ -187,8 +187,8 @@ void kprobe_arm_test_cases(void) TEST_BF_R ("mov pc, r",0,2f,"") TEST_BF_RR("mov pc, r",0,2f,", asl r",1,0,"") TEST_BB( "sub pc, pc, #1b-2b+8") -#if __LINUX_ARM_ARCH__ >= 6 - TEST_BB( "sub pc, pc, #1b-2b+8-2") /* UNPREDICTABLE before ARMv6 */ +#if __LINUX_ARM_ARCH__ == 6 && !defined(CONFIG_CPU_V7) + TEST_BB( "sub pc, pc, #1b-2b+8-2") /* UNPREDICTABLE before and after ARMv6 */ #endif TEST_BB_R( "sub pc, pc, r",14, 1f-2f+8,"") TEST_BB_R( "rsb pc, r",14,1f-2f+8,", pc") diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 8f96ec778e8..6123daf397a 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -660,7 +660,7 @@ static const union decode_item t32_table_1111_100x[] = { /* LDRSB (literal) 1111 1001 x001 1111 xxxx xxxx xxxx xxxx */ /* LDRH (literal) 1111 1000 x011 1111 xxxx xxxx xxxx xxxx */ /* LDRSH (literal) 1111 1001 x011 1111 xxxx xxxx xxxx xxxx */ - DECODE_EMULATEX (0xfe5f0000, 0xf81f0000, t32_simulate_ldr_literal, + DECODE_SIMULATEX(0xfe5f0000, 0xf81f0000, t32_simulate_ldr_literal, REGS(PC, NOSPPCX, 0, 0, 0)), /* STRB (immediate) 1111 1000 0000 xxxx xxxx 1xxx xxxx xxxx */ diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 186c8cb982c..a02eada3aa5 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -503,7 +503,7 @@ __hw_perf_event_init(struct perf_event *event) event_requires_mode_exclusion(&event->attr)) { pr_debug("ARM performance counters do not support " "mode exclusion\n"); - return -EPERM; + return -EOPNOTSUPP; } /* diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 5700a7ae7f0..14e38261cd3 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -25,7 +25,6 @@ #include <linux/regset.h> #include <linux/audit.h> #include <linux/tracehook.h> -#include <linux/unistd.h> #include <asm/pgtable.h> #include <asm/traps.h> @@ -918,8 +917,6 @@ asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno) audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0, regs->ARM_r1, regs->ARM_r2, regs->ARM_r3); - if (why == 0 && test_and_clear_thread_flag(TIF_SYSCALL_RESTARTSYS)) - scno = __NR_restart_syscall - __NR_SYSCALL_BASE; if (!test_thread_flag(TIF_SYSCALL_TRACE)) return scno; diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index fd2392a17ac..536c5d6b340 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -27,6 +27,7 @@ */ #define SWI_SYS_SIGRETURN (0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)) #define SWI_SYS_RT_SIGRETURN (0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)) +#define SWI_SYS_RESTART (0xef000000|__NR_restart_syscall|__NR_OABI_SYSCALL_BASE) /* * With EABI, the syscall number has to be loaded into r7. @@ -47,6 +48,18 @@ const unsigned long sigreturn_codes[7] = { }; /* + * Either we support OABI only, or we have EABI with the OABI + * compat layer enabled. In the later case we don't know if + * user space is EABI or not, and if not we must not clobber r7. + * Always using the OABI syscall solves that issue and works for + * all those cases. + */ +const unsigned long syscall_restart_code[2] = { + SWI_SYS_RESTART, /* swi __NR_restart_syscall */ + 0xe49df004, /* ldr pc, [sp], #4 */ +}; + +/* * atomically swap in the new signal mask, and wait for a signal. */ asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask) @@ -592,10 +605,12 @@ static void do_signal(struct pt_regs *regs, int syscall) case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: - case -ERESTART_RESTARTBLOCK: regs->ARM_r0 = regs->ARM_ORIG_r0; regs->ARM_pc = restart_addr; break; + case -ERESTART_RESTARTBLOCK: + regs->ARM_r0 = -EINTR; + break; } } @@ -611,14 +626,12 @@ static void do_signal(struct pt_regs *regs, int syscall) * debugger has chosen to restart at a different PC. */ if (regs->ARM_pc == restart_addr) { - if (retval == -ERESTARTNOHAND || - retval == -ERESTART_RESTARTBLOCK + if (retval == -ERESTARTNOHAND || (retval == -ERESTARTSYS && !(ka.sa.sa_flags & SA_RESTART))) { regs->ARM_r0 = -EINTR; regs->ARM_pc = continue_addr; } - clear_thread_flag(TIF_SYSCALL_RESTARTSYS); } handle_signal(signr, &ka, &info, regs); @@ -632,8 +645,29 @@ static void do_signal(struct pt_regs *regs, int syscall) * ignore the restart. */ if (retval == -ERESTART_RESTARTBLOCK - && regs->ARM_pc == restart_addr) - set_thread_flag(TIF_SYSCALL_RESTARTSYS); + && regs->ARM_pc == continue_addr) { + if (thumb_mode(regs)) { + regs->ARM_r7 = __NR_restart_syscall - __NR_SYSCALL_BASE; + regs->ARM_pc -= 2; + } else { +#if defined(CONFIG_AEABI) && !defined(CONFIG_OABI_COMPAT) + regs->ARM_r7 = __NR_restart_syscall; + regs->ARM_pc -= 4; +#else + u32 __user *usp; + + regs->ARM_sp -= 4; + usp = (u32 __user *)regs->ARM_sp; + + if (put_user(regs->ARM_pc, usp) == 0) { + regs->ARM_pc = KERN_RESTART_CODE; + } else { + regs->ARM_sp += 4; + force_sigsegv(0, current); + } +#endif + } + } } restore_saved_sigmask(); diff --git a/arch/arm/kernel/signal.h b/arch/arm/kernel/signal.h index 5ff067b7c75..6fcfe8398aa 100644 --- a/arch/arm/kernel/signal.h +++ b/arch/arm/kernel/signal.h @@ -8,5 +8,7 @@ * published by the Free Software Foundation. */ #define KERN_SIGRETURN_CODE (CONFIG_VECTORS_BASE + 0x00000500) +#define KERN_RESTART_CODE (KERN_SIGRETURN_CODE + sizeof(sigreturn_codes)) extern const unsigned long sigreturn_codes[7]; +extern const unsigned long syscall_restart_code[2]; diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 8200deaa14f..61302df56ef 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -17,11 +17,160 @@ #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/cputype.h> #include <asm/topology.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. The final + * cpu_scale value must be in the range + * 0 < cpu_scale < 2*SCHED_POWER_SCALE. + * Processors that are not defined in the table, + * use the default SCHED_POWER_SCALE value for cpu_scale. + */ +struct cpu_efficiency table_efficiency[] = { + {"arm,cortex-a15", 3891}, + {"arm,cortex-a7", 2048}, + {NULL, }, +}; + +struct cpu_capacity { + unsigned long hwid; + unsigned long capacity; +}; + +struct cpu_capacity *cpu_capacity; + +unsigned long middle_capacity = 1; + +static void __init parse_dt_topology(void) +{ + 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 = 0; + + alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity); + cpu_capacity = (struct cpu_capacity *)kzalloc(alloc_size, GFP_NOWAIT); + + while ((cn = of_find_node_by_type(cn, "cpu"))) { + const u32 *rate, *reg; + int len; + + if (cpu >= num_possible_cpus()) + break; + + 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) + 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; + } + + reg = of_get_property(cn, "reg", &len); + if (!reg || len != 4) { + pr_err("%s missing reg 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 = capacity; + cpu_capacity[cpu++].hwid = be32_to_cpup(reg); + } + + if (cpu < num_possible_cpus()) + cpu_capacity[cpu].hwid = (unsigned long)(-1); + + middle_capacity = (min_capacity + max_capacity) >> 11; +} + +void update_cpu_power(unsigned int cpu, unsigned long hwid) +{ + unsigned int idx = 0; + + /* look for the cpu's hwid in the cpu capacity table */ + for (idx = 0; idx < num_possible_cpus(); idx++) { + if (cpu_capacity[idx].hwid == hwid) + break; + + if (cpu_capacity[idx].hwid == -1) + return; + } + + if (idx == num_possible_cpus()) + return; + + set_power_scale(cpu, cpu_capacity[idx].capacity / middle_capacity); + + printk(KERN_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, unsigned int mpidr) {} +#endif + + +/* + * cpu topology management + */ + #define MPIDR_SMP_BITMASK (0x3 << 30) #define MPIDR_SMP_VALUE (0x2 << 30) @@ -31,6 +180,7 @@ * These masks reflect the current use of the affinity levels. * The affinity level can be up to 16 bits according to ARM ARM */ +#define MPIDR_HWID_BITMASK 0xFFFFFF #define MPIDR_LEVEL0_MASK 0x3 #define MPIDR_LEVEL0_SHIFT 0 @@ -41,6 +191,9 @@ #define MPIDR_LEVEL2_MASK 0xFF #define MPIDR_LEVEL2_SHIFT 16 +/* + * cpu topology table + */ struct cputopo_arm cpu_topology[NR_CPUS]; const struct cpumask *cpu_coregroup_mask(int cpu) @@ -48,6 +201,32 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return &cpu_topology[cpu].core_sibling; } +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(); +} + /* * store_cpu_topology is called at boot when only one cpu is running * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, @@ -57,7 +236,6 @@ void store_cpu_topology(unsigned int cpuid) { struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; unsigned int mpidr; - unsigned int cpu; /* If the cpu topology has been already set, just return */ if (cpuid_topo->core_id != -1) @@ -99,26 +277,9 @@ void store_cpu_topology(unsigned int cpuid) cpuid_topo->socket_id = -1; } - /* update core and thread sibling masks */ - for_each_possible_cpu(cpu) { - struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; - - if (cpuid_topo->socket_id == cpu_topo->socket_id) { - 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) { - cpumask_set_cpu(cpuid, - &cpu_topo->thread_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, - &cpuid_topo->thread_sibling); - } - } - } - smp_wmb(); + update_siblings_masks(cpuid); + + update_cpu_power(cpuid, mpidr & MPIDR_HWID_BITMASK); printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, @@ -126,6 +287,75 @@ void store_cpu_topology(unsigned int cpuid) cpu_topology[cpuid].socket_id, mpidr); } + +#ifdef CONFIG_SCHED_HMP + +static const char * const little_cores[] = { + "arm,cortex-a7", + NULL, +}; + +static bool is_little_cpu(struct device_node *cn) +{ + const char * const *lc; + for (lc = little_cores; *lc; lc++) + if (of_device_is_compatible(cn, *lc)) + return true; + return false; +} + +void __init arch_get_fast_and_slow_cpus(struct cpumask *fast, + struct cpumask *slow) +{ + struct device_node *cn = NULL; + int cpu = 0; + + 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"))) { + + if (cpu >= num_possible_cpus()) + break; + + if (is_little_cpu(cn)) + cpumask_set_cpu(cpu, slow); + else + cpumask_set_cpu(cpu, fast); + + cpu++; + } + + 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); +} + +#endif /* CONFIG_SCHED_HMP */ + + /* * init_cpu_topology is called at boot when only one cpu is running * which prevent simultaneous write access to cpu_topology array @@ -134,7 +364,7 @@ void init_cpu_topology(void) { unsigned int cpu; - /* init core mask */ + /* init core mask and power*/ for_each_possible_cpu(cpu) { struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); @@ -143,6 +373,10 @@ void init_cpu_topology(void) 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(); } diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 4928d89758f..3647170e9a1 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -820,6 +820,8 @@ void __init early_trap_init(void *vectors_base) */ memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE), sigreturn_codes, sizeof(sigreturn_codes)); + memcpy((void *)(vectors + KERN_RESTART_CODE - CONFIG_VECTORS_BASE), + syscall_restart_code, sizeof(syscall_restart_code)); flush_icache_range(vectors, vectors + PAGE_SIZE); modify_domain(DOMAIN_USER, DOMAIN_CLIENT); diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 43a31fb0631..36ff15bbfdd 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -183,7 +183,9 @@ SECTIONS } #endif +#ifdef CONFIG_SMP PERCPU_SECTION(L1_CACHE_BYTES) +#endif #ifdef CONFIG_XIP_KERNEL __data_loc = ALIGN(4); /* location in binary */ |