diff options
Diffstat (limited to 'arch/powerpc/kernel')
78 files changed, 1970 insertions, 741 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index ce4f7f179117..ee728e433aa2 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -85,6 +85,8 @@ extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds +obj-$(CONFIG_RELOCATABLE_PPC32) += reloc_32.o + obj-$(CONFIG_PPC32) += entry_32.o setup_32.o obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o obj-$(CONFIG_KGDB) += kgdb.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 5f078bc2063e..04caee7d9bc1 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -44,10 +44,14 @@ #include <asm/compat.h> #include <asm/mmu.h> #include <asm/hvcall.h> +#include <asm/xics.h> #endif #ifdef CONFIG_PPC_ISERIES #include <asm/iseries/alpaca.h> #endif +#ifdef CONFIG_PPC_POWERNV +#include <asm/opal.h> +#endif #if defined(CONFIG_KVM) || defined(CONFIG_KVM_GUEST) #include <linux/kvm_host.h> #endif @@ -204,6 +208,7 @@ int main(void) DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time)); DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); + DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost)); #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -449,8 +454,6 @@ int main(void) #ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); - DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip)); - DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr)); DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr)); DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr)); DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr)); @@ -458,14 +461,12 @@ int main(void) DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor)); DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl)); DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr)); - DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem)); - DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); - DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); - DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec)); DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires)); DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions)); + DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded)); + DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded)); DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa)); DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr)); DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc)); @@ -481,6 +482,7 @@ int main(void) DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count)); DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); + DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) - offsetof(struct kvmppc_vcpu_book3s, vcpu)); DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige)); @@ -537,6 +539,8 @@ int main(void) HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); + HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); + HSTATE_FIELD(HSTATE_NAPPING, napping); #ifdef CONFIG_KVM_BOOK3S_64_HV HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu); @@ -549,6 +553,7 @@ int main(void) HSTATE_FIELD(HSTATE_DSCR, host_dscr); HSTATE_FIELD(HSTATE_DABR, dabr); HSTATE_FIELD(HSTATE_DECEXP, dec_expires); + DEFINE(IPI_PRIORITY, IPI_PRIORITY); #endif /* CONFIG_KVM_BOOK3S_64_HV */ #else /* CONFIG_PPC_BOOK3S */ @@ -609,5 +614,12 @@ int main(void) arch.timing_last_enter.tv32.tbl)); #endif +#ifdef CONFIG_PPC_POWERNV + DEFINE(OPAL_MC_GPR3, offsetof(struct opal_machine_check_event, gpr3)); + DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0)); + DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1)); + DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt)); +#endif + return 0; } diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 60b3e377b1e4..ac8f52732fde 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -6,7 +6,7 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/memblock.h> #include <asm/sections.h> diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index a3c684b4c862..92c6b008dd2b 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -451,15 +451,15 @@ out: static struct cache_dir *__cpuinit cacheinfo_create_cache_dir(unsigned int cpu_id) { struct cache_dir *cache_dir; - struct sys_device *sysdev; + struct device *dev; struct kobject *kobj = NULL; - sysdev = get_cpu_sysdev(cpu_id); - WARN_ONCE(!sysdev, "no sysdev for CPU %i\n", cpu_id); - if (!sysdev) + dev = get_cpu_device(cpu_id); + WARN_ONCE(!dev, "no dev for CPU %i\n", cpu_id); + if (!dev) goto err; - kobj = kobject_create_and_add("cache", &sysdev->kobj); + kobj = kobject_create_and_add("cache", &dev->kobj); if (!kobj) goto err; diff --git a/arch/powerpc/kernel/clock.c b/arch/powerpc/kernel/clock.c index ce668f545758..a764b47791e8 100644 --- a/arch/powerpc/kernel/clock.c +++ b/arch/powerpc/kernel/clock.c @@ -6,7 +6,7 @@ #include <linux/clk.h> #include <linux/err.h> #include <linux/errno.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/clk_interface.h> struct clk_interface clk_functions; diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S index 7f818feaa7a5..ebc62f42a237 100644 --- a/arch/powerpc/kernel/cpu_setup_a2.S +++ b/arch/powerpc/kernel/cpu_setup_a2.S @@ -41,11 +41,16 @@ _GLOBAL(__setup_cpu_a2) * core local but doing it always won't hurt */ -#ifdef CONFIG_PPC_WSP_COPRO +#ifdef CONFIG_PPC_ICSWX /* Make sure ACOP starts out as zero */ li r3,0 mtspr SPRN_ACOP,r3 + /* Skip the following if we are in Guest mode */ + mfmsr r3 + andis. r0,r3,MSR_GS@h + bne _icswx_skip_guest + /* Enable icswx instruction */ mfspr r3,SPRN_A2_CCR2 ori r3,r3,A2_CCR2_ENABLE_ICSWX @@ -54,7 +59,8 @@ _GLOBAL(__setup_cpu_a2) /* Unmask all CTs in HACOP */ li r3,-1 mtspr SPRN_HACOP,r3 -#endif /* CONFIG_PPC_WSP_COPRO */ +_icswx_skip_guest: +#endif /* CONFIG_PPC_ICSWX */ /* Enable doorbell */ mfspr r3,SPRN_A2_CCR2 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index fa44ff538861..81db9e2a8a20 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -14,7 +14,7 @@ #include <linux/sched.h> #include <linux/threads.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/oprofile_impl.h> #include <asm/cputable.h> @@ -1505,6 +1505,19 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_4xx, .platform = "ppc405", }, + { /* APM8018X */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x7ff11432, + .cpu_name = "APM8018X", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, { /* default match */ .pvr_mask = 0x00000000, .pvr_value = 0x00000000, @@ -1830,6 +1843,20 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_47x, .platform = "ppc470", }, + { /* 476fpe */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x7ff50000, + .cpu_name = "476fpe", + .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | + MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, { /* 476 iss */ .pvr_mask = 0xffff0000, .pvr_value = 0x00050000, diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index cc6a9d5d69ab..28be3452e67a 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -10,84 +10,85 @@ * */ -#undef DEBUG - #include <linux/kernel.h> #include <linux/smp.h> #include <linux/reboot.h> #include <linux/kexec.h> -#include <linux/bootmem.h> +#include <linux/export.h> #include <linux/crash_dump.h> #include <linux/delay.h> -#include <linux/elf.h> -#include <linux/elfcore.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/types.h> -#include <linux/memblock.h> #include <asm/processor.h> #include <asm/machdep.h> #include <asm/kexec.h> #include <asm/kdump.h> #include <asm/prom.h> -#include <asm/firmware.h> #include <asm/smp.h> #include <asm/system.h> #include <asm/setjmp.h> -#ifdef DEBUG -#include <asm/udbg.h> -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif +/* + * The primary CPU waits a while for all secondary CPUs to enter. This is to + * avoid sending an IPI if the secondary CPUs are entering + * crash_kexec_secondary on their own (eg via a system reset). + * + * The secondary timeout has to be longer than the primary. Both timeouts are + * in milliseconds. + */ +#define PRIMARY_TIMEOUT 500 +#define SECONDARY_TIMEOUT 1000 -/* This keeps a track of which one is crashing cpu. */ +#define IPI_TIMEOUT 10000 +#define REAL_MODE_TIMEOUT 10000 + +/* This keeps a track of which one is the crashing cpu. */ int crashing_cpu = -1; -static cpumask_t cpus_in_crash = CPU_MASK_NONE; -cpumask_t cpus_in_sr = CPU_MASK_NONE; +static atomic_t cpus_in_crash; +static int time_to_dump; #define CRASH_HANDLER_MAX 3 /* NULL terminated list of shutdown handles */ static crash_shutdown_t crash_shutdown_handles[CRASH_HANDLER_MAX+1]; static DEFINE_SPINLOCK(crash_handlers_lock); +static unsigned long crash_shutdown_buf[JMP_BUF_LEN]; +static int crash_shutdown_cpu = -1; + +static int handle_fault(struct pt_regs *regs) +{ + if (crash_shutdown_cpu == smp_processor_id()) + longjmp(crash_shutdown_buf, 1); + return 0; +} + #ifdef CONFIG_SMP -static atomic_t enter_on_soft_reset = ATOMIC_INIT(0); void crash_ipi_callback(struct pt_regs *regs) { + static cpumask_t cpus_state_saved = CPU_MASK_NONE; + int cpu = smp_processor_id(); if (!cpu_online(cpu)) return; hard_irq_disable(); - if (!cpumask_test_cpu(cpu, &cpus_in_crash)) + if (!cpumask_test_cpu(cpu, &cpus_state_saved)) { crash_save_cpu(regs, cpu); - cpumask_set_cpu(cpu, &cpus_in_crash); - - /* - * Entered via soft-reset - could be the kdump - * process is invoked using soft-reset or user activated - * it if some CPU did not respond to an IPI. - * For soft-reset, the secondary CPU can enter this func - * twice. 1 - using IPI, and 2. soft-reset. - * Tell the kexec CPU that entered via soft-reset and ready - * to go down. - */ - if (cpumask_test_cpu(cpu, &cpus_in_sr)) { - cpumask_clear_cpu(cpu, &cpus_in_sr); - atomic_inc(&enter_on_soft_reset); + cpumask_set_cpu(cpu, &cpus_state_saved); } + atomic_inc(&cpus_in_crash); + smp_mb__after_atomic_inc(); + /* * Starting the kdump boot. * This barrier is needed to make sure that all CPUs are stopped. - * If not, soft-reset will be invoked to bring other CPUs. */ - while (!cpumask_test_cpu(crashing_cpu, &cpus_in_crash)) + while (!time_to_dump) cpu_relax(); if (ppc_md.kexec_cpu_down) @@ -102,106 +103,99 @@ void crash_ipi_callback(struct pt_regs *regs) /* NOTREACHED */ } -/* - * Wait until all CPUs are entered via soft-reset. - */ -static void crash_soft_reset_check(int cpu) -{ - unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ - - cpumask_clear_cpu(cpu, &cpus_in_sr); - while (atomic_read(&enter_on_soft_reset) != ncpus) - cpu_relax(); -} - - static void crash_kexec_prepare_cpus(int cpu) { unsigned int msecs; - unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ + int tries = 0; + int (*old_handler)(struct pt_regs *regs); + + printk(KERN_EMERG "Sending IPI to other CPUs\n"); crash_send_ipi(crash_ipi_callback); smp_wmb(); +again: /* * FIXME: Until we will have the way to stop other CPUs reliably, * the crash CPU will send an IPI and wait for other CPUs to * respond. - * Delay of at least 10 seconds. */ - printk(KERN_EMERG "Sending IPI to other cpus...\n"); - msecs = 10000; - while ((cpumask_weight(&cpus_in_crash) < ncpus) && (--msecs > 0)) { - cpu_relax(); + msecs = IPI_TIMEOUT; + while ((atomic_read(&cpus_in_crash) < ncpus) && (--msecs > 0)) mdelay(1); - } /* Would it be better to replace the trap vector here? */ + if (atomic_read(&cpus_in_crash) >= ncpus) { + printk(KERN_EMERG "IPI complete\n"); + return; + } + + printk(KERN_EMERG "ERROR: %d cpu(s) not responding\n", + ncpus - atomic_read(&cpus_in_crash)); + /* - * FIXME: In case if we do not get all CPUs, one possibility: ask the - * user to do soft reset such that we get all. - * Soft-reset will be used until better mechanism is implemented. + * If we have a panic timeout set then we can't wait indefinitely + * for someone to activate system reset. We also give up on the + * second time through if system reset fail to work. */ - if (cpumask_weight(&cpus_in_crash) < ncpus) { - printk(KERN_EMERG "done waiting: %d cpu(s) not responding\n", - ncpus - cpumask_weight(&cpus_in_crash)); - printk(KERN_EMERG "Activate soft-reset to stop other cpu(s)\n"); - cpumask_clear(&cpus_in_sr); - atomic_set(&enter_on_soft_reset, 0); - while (cpumask_weight(&cpus_in_crash) < ncpus) - cpu_relax(); - } + if ((panic_timeout > 0) || (tries > 0)) + return; + /* - * Make sure all CPUs are entered via soft-reset if the kdump is - * invoked using soft-reset. + * A system reset will cause all CPUs to take an 0x100 exception. + * The primary CPU returns here via setjmp, and the secondary + * CPUs reexecute the crash_kexec_secondary path. */ - if (cpumask_test_cpu(cpu, &cpus_in_sr)) - crash_soft_reset_check(cpu); - /* Leave the IPI callback set */ + old_handler = __debugger; + __debugger = handle_fault; + crash_shutdown_cpu = smp_processor_id(); + + if (setjmp(crash_shutdown_buf) == 0) { + printk(KERN_EMERG "Activate system reset (dumprestart) " + "to stop other cpu(s)\n"); + + /* + * A system reset will force all CPUs to execute the + * crash code again. We need to reset cpus_in_crash so we + * wait for everyone to do this. + */ + atomic_set(&cpus_in_crash, 0); + smp_mb(); + + while (atomic_read(&cpus_in_crash) < ncpus) + cpu_relax(); + } + + crash_shutdown_cpu = -1; + __debugger = old_handler; + + tries++; + goto again; } /* - * This function will be called by secondary cpus or by kexec cpu - * if soft-reset is activated to stop some CPUs. + * This function will be called by secondary cpus. */ void crash_kexec_secondary(struct pt_regs *regs) { - int cpu = smp_processor_id(); unsigned long flags; - int msecs = 5; + int msecs = SECONDARY_TIMEOUT; local_irq_save(flags); - /* Wait 5ms if the kexec CPU is not entered yet. */ + + /* Wait for the primary crash CPU to signal its progress */ while (crashing_cpu < 0) { if (--msecs < 0) { - /* - * Either kdump image is not loaded or - * kdump process is not started - Probably xmon - * exited using 'x'(exit and recover) or - * kexec_should_crash() failed for all running tasks. - */ - cpumask_clear_cpu(cpu, &cpus_in_sr); + /* No response, kdump image may not have been loaded */ local_irq_restore(flags); return; } + mdelay(1); - cpu_relax(); - } - if (cpu == crashing_cpu) { - /* - * Panic CPU will enter this func only via soft-reset. - * Wait until all secondary CPUs entered and - * then start kexec boot. - */ - crash_soft_reset_check(cpu); - cpumask_set_cpu(crashing_cpu, &cpus_in_crash); - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(1, 0); - machine_kexec(kexec_crash_image); - /* NOTREACHED */ } + crash_ipi_callback(regs); } @@ -210,7 +204,7 @@ void crash_kexec_secondary(struct pt_regs *regs) static void crash_kexec_prepare_cpus(int cpu) { /* - * move the secondarys to us so that we can copy + * move the secondaries to us so that we can copy * the new kernel 0-0x100 safely * * do this if kexec in setup.c ? @@ -224,7 +218,6 @@ static void crash_kexec_prepare_cpus(int cpu) void crash_kexec_secondary(struct pt_regs *regs) { - cpumask_clear(&cpus_in_sr); } #endif /* CONFIG_SMP */ @@ -235,7 +228,7 @@ static void crash_kexec_wait_realmode(int cpu) unsigned int msecs; int i; - msecs = 10000; + msecs = REAL_MODE_TIMEOUT; for (i=0; i < nr_cpu_ids && msecs > 0; i++) { if (i == cpu) continue; @@ -307,22 +300,11 @@ int crash_shutdown_unregister(crash_shutdown_t handler) } EXPORT_SYMBOL(crash_shutdown_unregister); -static unsigned long crash_shutdown_buf[JMP_BUF_LEN]; -static int crash_shutdown_cpu = -1; - -static int handle_fault(struct pt_regs *regs) -{ - if (crash_shutdown_cpu == smp_processor_id()) - longjmp(crash_shutdown_buf, 1); - return 0; -} - void default_machine_crash_shutdown(struct pt_regs *regs) { unsigned int i; int (*old_handler)(struct pt_regs *regs); - /* * This function is only called after the system * has panicked or is otherwise in a critical state. @@ -340,15 +322,26 @@ void default_machine_crash_shutdown(struct pt_regs *regs) * such that another IPI will not be sent. */ crashing_cpu = smp_processor_id(); - crash_save_cpu(regs, crashing_cpu); + + /* + * If we came in via system reset, wait a while for the secondary + * CPUs to enter. + */ + if (TRAP(regs) == 0x100) + mdelay(PRIMARY_TIMEOUT); + crash_kexec_prepare_cpus(crashing_cpu); - cpumask_set_cpu(crashing_cpu, &cpus_in_crash); + + crash_save_cpu(regs, crashing_cpu); + + time_to_dump = 1; + crash_kexec_wait_realmode(crashing_cpu); machine_kexec_mask_interrupts(); /* - * Call registered shutdown routines savely. Swap out + * Call registered shutdown routines safely. Swap out * __debugger_fault_handler, and replace on exit. */ old_handler = __debugger_fault_handler; diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 424afb6b8fba..b3ba5163eae2 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -28,7 +28,7 @@ #define DBG(fmt...) #endif -#ifndef CONFIG_RELOCATABLE +#ifndef CONFIG_NONSTATIC_KERNEL void __init reserve_kdump_trampoline(void) { memblock_reserve(0, KDUMP_RESERVE_LIMIT); @@ -67,7 +67,7 @@ void __init setup_kdump_trampoline(void) DBG(" <- setup_kdump_trampoline()\n"); } -#endif /* CONFIG_RELOCATABLE */ +#endif /* CONFIG_NONSTATIC_KERNEL */ static int __init parse_savemaxmem(char *p) { diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index e7554154a6de..3f6464b4d970 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -5,6 +5,7 @@ * busses using the iommu infrastructure */ +#include <linux/export.h> #include <asm/iommu.h> /* @@ -90,13 +91,27 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask) return 1; } +static u64 dma_iommu_get_required_mask(struct device *dev) +{ + struct iommu_table *tbl = get_iommu_table_base(dev); + u64 mask; + if (!tbl) + return 0; + + mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1); + mask += mask - 1; + + return mask; +} + struct dma_map_ops dma_iommu_ops = { - .alloc_coherent = dma_iommu_alloc_coherent, - .free_coherent = dma_iommu_free_coherent, - .map_sg = dma_iommu_map_sg, - .unmap_sg = dma_iommu_unmap_sg, - .dma_supported = dma_iommu_dma_supported, - .map_page = dma_iommu_map_page, - .unmap_page = dma_iommu_unmap_page, + .alloc_coherent = dma_iommu_alloc_coherent, + .free_coherent = dma_iommu_free_coherent, + .map_sg = dma_iommu_map_sg, + .unmap_sg = dma_iommu_unmap_sg, + .dma_supported = dma_iommu_dma_supported, + .map_page = dma_iommu_map_page, + .unmap_page = dma_iommu_unmap_page, + .get_required_mask = dma_iommu_get_required_mask, }; EXPORT_SYMBOL(dma_iommu_ops); diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 4295e0b94b2d..1ebc9189aada 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -24,6 +24,21 @@ unsigned int ppc_swiotlb_enable; +static u64 swiotlb_powerpc_get_required(struct device *dev) +{ + u64 end, mask, max_direct_dma_addr = dev->archdata.max_direct_dma_addr; + + end = memblock_end_of_DRAM(); + if (max_direct_dma_addr && end > max_direct_dma_addr) + end = max_direct_dma_addr; + end += get_dma_offset(dev); + + mask = 1ULL << (fls64(end) - 1); + mask += mask - 1; + + return mask; +} + /* * At the moment, all platforms that use this code only require * swiotlb to be used if we're operating on HIGHMEM. Since @@ -44,6 +59,7 @@ struct dma_map_ops swiotlb_dma_ops = { .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, .mapping_error = swiotlb_dma_mapping_error, + .get_required_mask = swiotlb_powerpc_get_required, }; void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev) diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 4f0959fbfbee..7d0233c12ee3 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -10,6 +10,7 @@ #include <linux/dma-debug.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/export.h> #include <asm/bug.h> #include <asm/abs_addr.h> #include <asm/machdep.h> @@ -96,6 +97,18 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask) #endif } +static u64 dma_direct_get_required_mask(struct device *dev) +{ + u64 end, mask; + + end = memblock_end_of_DRAM() + get_dma_offset(dev); + + mask = 1ULL << (fls64(end) - 1); + mask += mask - 1; + + return mask; +} + static inline dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, @@ -137,13 +150,14 @@ static inline void dma_direct_sync_single(struct device *dev, #endif struct dma_map_ops dma_direct_ops = { - .alloc_coherent = dma_direct_alloc_coherent, - .free_coherent = dma_direct_free_coherent, - .map_sg = dma_direct_map_sg, - .unmap_sg = dma_direct_unmap_sg, - .dma_supported = dma_direct_dma_supported, - .map_page = dma_direct_map_page, - .unmap_page = dma_direct_unmap_page, + .alloc_coherent = dma_direct_alloc_coherent, + .free_coherent = dma_direct_free_coherent, + .map_sg = dma_direct_map_sg, + .unmap_sg = dma_direct_unmap_sg, + .dma_supported = dma_direct_dma_supported, + .map_page = dma_direct_map_page, + .unmap_page = dma_direct_unmap_page, + .get_required_mask = dma_direct_get_required_mask, #ifdef CONFIG_NOT_COHERENT_CACHE .sync_single_for_cpu = dma_direct_sync_single, .sync_single_for_device = dma_direct_sync_single, @@ -170,6 +184,23 @@ int dma_set_mask(struct device *dev, u64 dma_mask) } EXPORT_SYMBOL(dma_set_mask); +u64 dma_get_required_mask(struct device *dev) +{ + struct dma_map_ops *dma_ops = get_dma_ops(dev); + + if (ppc_md.dma_get_required_mask) + return ppc_md.dma_get_required_mask(dev); + + if (unlikely(dma_ops == NULL)) + return 0; + + if (dma_ops->get_required_mask) + return dma_ops->get_required_mask(dev); + + return DMA_BIT_MASK(8 * sizeof(dma_addr_t)); +} +EXPORT_SYMBOL_GPL(dma_get_required_mask); + static int __init dma_init(void) { dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 56212bc0ab08..4f80cf1ce77b 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -215,7 +215,22 @@ reenable_mmu: /* re-enable mmu so we can */ stw r9,8(r1) stw r11,12(r1) stw r3,ORIG_GPR3(r1) + /* + * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1. + * If from user mode there is only one stack frame on the stack, and + * accessing CALLER_ADDR1 will cause oops. So we need create a dummy + * stack frame to make trace_hardirqs_off happy. + */ + andi. r12,r12,MSR_PR + beq 11f + stwu r1,-16(r1) + bl trace_hardirqs_off + addi r1,r1,16 + b 12f + +11: bl trace_hardirqs_off +12: lwz r0,GPR0(r1) lwz r3,ORIG_GPR3(r1) lwz r4,GPR4(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 41b02c792aa3..d4be7bb3dbdf 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -65,7 +65,7 @@ BEGIN_FTR_SECTION lbz r0,PACAPROCSTART(r13) cmpwi r0,0x80 bne 1f - li r0,0 + li r0,1 stb r0,PACAPROCSTART(r13) b kvm_start_guest 1: @@ -267,7 +267,7 @@ vsx_unavailable_pSeries_1: #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error) - KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1202) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202) #endif /* CONFIG_CBE_RAS */ STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint) @@ -275,7 +275,7 @@ vsx_unavailable_pSeries_1: #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance) - KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1602) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602) #endif /* CONFIG_CBE_RAS */ STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist) @@ -283,7 +283,7 @@ vsx_unavailable_pSeries_1: #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal) - KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1802) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802) #endif /* CONFIG_CBE_RAS */ . = 0x3000 @@ -427,16 +427,6 @@ slb_miss_user_pseries: b . /* prevent spec. execution */ #endif /* __DISABLED__ */ -/* KVM's trampoline code needs to be close to the interrupt handlers */ - -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#ifdef CONFIG_KVM_BOOK3S_PR -#include "../kvm/book3s_rmhandlers.S" -#else -#include "../kvm/book3s_hv_rmhandlers.S" -#endif -#endif - .align 7 .globl __end_interrupts __end_interrupts: @@ -1143,7 +1133,7 @@ _GLOBAL(do_stab_bolted) rfid b . /* prevent speculative execution */ -#ifdef CONFIG_PPC_PSERIES +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * Data area reserved for FWNMI option. * This address (0x7000) is fixed by the RPA. @@ -1151,7 +1141,7 @@ _GLOBAL(do_stab_bolted) .= 0x7000 .globl fwnmi_data_area fwnmi_data_area: -#endif /* CONFIG_PPC_PSERIES */ +#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */ /* iSeries does not use the FWNMI stuff, so it is safe to put * this here, even if we later allow kernels that will boot on @@ -1176,9 +1166,12 @@ xLparMap: #endif /* CONFIG_PPC_ISERIES */ -#ifdef CONFIG_PPC_PSERIES +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) + /* pseries and powernv need to keep the whole page from + * 0x7000 to 0x8000 free for use by the firmware + */ . = 0x8000 -#endif /* CONFIG_PPC_PSERIES */ +#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */ /* * Space for CPU0's segment table. @@ -1193,3 +1186,19 @@ xLparMap: .globl initial_stab initial_stab: .space 4096 +#ifdef CONFIG_PPC_POWERNV +_GLOBAL(opal_mc_secondary_handler) + HMT_MEDIUM + SET_SCRATCH0(r13) + GET_PACA(r13) + clrldi r3,r3,2 + tovirt(r3,r3) + std r3,PACA_OPAL_MC_EVT(r13) + ld r13,OPAL_MC_SRR0(r3) + mtspr SPRN_SRR0,r13 + ld r13,OPAL_MC_SRR1(r3) + mtspr SPRN_SRR1,r13 + ld r3,OPAL_MC_GPR3(r3) + GET_SCRATCH0(r13) + b machine_check_pSeries +#endif /* CONFIG_PPC_POWERNV */ diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c index 6b1f4271eb53..2eae4478f7a1 100644 --- a/arch/powerpc/kernel/firmware.c +++ b/arch/powerpc/kernel/firmware.c @@ -13,7 +13,8 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/module.h> +#include <linux/export.h> +#include <linux/cache.h> #include <asm/firmware.h> diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index ba250d505e07..0654dba2c1f1 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -139,8 +139,7 @@ __start: trap #endif /* CONFIG_PPC_PMAC */ -1: mr r31,r3 /* save parameters */ - mr r30,r4 +1: mr r31,r3 /* save device tree ptr */ li r24,0 /* cpu # */ /* @@ -964,8 +963,8 @@ start_here: * Do early platform-specific initialization, * and set up the MMU. */ - mr r3,r31 - mr r4,r30 + li r3,0 + mr r4,r31 bl machine_init bl __save_cpu_setup bl MMU_init diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index a91626d87fc9..872a6af83bad 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -58,13 +58,7 @@ _ENTRY(_stext); _ENTRY(_start); - /* Save parameters we are passed. - */ - mr r31,r3 - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 + mr r31,r3 /* save device tree ptr */ /* We have to turn on the MMU right away so we get cache modes * set correctly. @@ -849,11 +843,8 @@ start_here: /* * Decide what sort of machine this is and initialize the MMU. */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 + li r3,0 + mr r4,r31 bl machine_init bl MMU_init diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index f8e971ba94f5..7dd2981bcc50 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -61,15 +61,37 @@ _ENTRY(_start); * of abatron_pteptrs */ nop + mr r31,r3 /* save device tree ptr */ + li r24,0 /* CPU number */ + +#ifdef CONFIG_RELOCATABLE /* - * Save parameters we are passed + * Relocate ourselves to the current runtime address. + * This is called only by the Boot CPU. + * "relocate" is called with our current runtime virutal + * address. + * r21 will be loaded with the physical runtime address of _stext */ - mr r31,r3 - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 - li r24,0 /* CPU number */ + bl 0f /* Get our runtime address */ +0: mflr r21 /* Make it accessible */ + addis r21,r21,(_stext - 0b)@ha + addi r21,r21,(_stext - 0b)@l /* Get our current runtime base */ + + /* + * We have the runtime (virutal) address of our base. + * We calculate our shift of offset from a 256M page. + * We could map the 256M page we belong to at PAGE_OFFSET and + * get going from there. + */ + lis r4,KERNELBASE@h + ori r4,r4,KERNELBASE@l + rlwinm r6,r21,0,4,31 /* r6 = PHYS_START % 256M */ + rlwinm r5,r4,0,4,31 /* r5 = KERNELBASE % 256M */ + subf r3,r5,r6 /* r3 = r6 - r5 */ + add r3,r4,r3 /* Required Virutal Address */ + + bl relocate +#endif bl init_cpu_state @@ -95,6 +117,65 @@ _ENTRY(_start); #ifdef CONFIG_RELOCATABLE /* + * Relocatable kernel support based on processing of dynamic + * relocation entries. + * + * r25 will contain RPN/ERPN for the start address of memory + * r21 will contain the current offset of _stext + */ + lis r3,kernstart_addr@ha + la r3,kernstart_addr@l(r3) + + /* + * Compute the kernstart_addr. + * kernstart_addr => (r6,r8) + * kernstart_addr & ~0xfffffff => (r6,r7) + */ + rlwinm r6,r25,0,28,31 /* ERPN. Bits 32-35 of Address */ + rlwinm r7,r25,0,0,3 /* RPN - assuming 256 MB page size */ + rlwinm r8,r21,0,4,31 /* r8 = (_stext & 0xfffffff) */ + or r8,r7,r8 /* Compute the lower 32bit of kernstart_addr */ + + /* Store kernstart_addr */ + stw r6,0(r3) /* higher 32bit */ + stw r8,4(r3) /* lower 32bit */ + + /* + * Compute the virt_phys_offset : + * virt_phys_offset = stext.run - kernstart_addr + * + * stext.run = (KERNELBASE & ~0xfffffff) + (kernstart_addr & 0xfffffff) + * When we relocate, we have : + * + * (kernstart_addr & 0xfffffff) = (stext.run & 0xfffffff) + * + * hence: + * virt_phys_offset = (KERNELBASE & ~0xfffffff) - (kernstart_addr & ~0xfffffff) + * + */ + + /* KERNELBASE&~0xfffffff => (r4,r5) */ + li r4, 0 /* higer 32bit */ + lis r5,KERNELBASE@h + rlwinm r5,r5,0,0,3 /* Align to 256M, lower 32bit */ + + /* + * 64bit subtraction. + */ + subfc r5,r7,r5 + subfe r4,r6,r4 + + /* Store virt_phys_offset */ + lis r3,virt_phys_offset@ha + la r3,virt_phys_offset@l(r3) + + stw r4,0(r3) + stw r5,4(r3) + +#elif defined(CONFIG_DYNAMIC_MEMSTART) + /* + * Mapping based, page aligned dynamic kernel loading. + * * r25 will contain RPN/ERPN for the start address of memory * * Add the difference between KERNELBASE and PAGE_OFFSET to the @@ -120,11 +201,8 @@ _ENTRY(_start); /* * Decide what sort of machine this is and initialize the MMU. */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 + li r3,0 + mr r4,r31 bl machine_init bl MMU_init @@ -742,6 +820,8 @@ _GLOBAL(init_cpu_state) /* We use the PVR to differenciate 44x cores from 476 */ mfspr r3,SPRN_PVR srwi r3,r3,16 + cmplwi cr0,r3,PVR_476FPE@h + beq head_start_47x cmplwi cr0,r3,PVR_476@h beq head_start_47x cmplwi cr0,r3,PVR_476_ISS@h @@ -810,12 +890,29 @@ skpinv: addi r4,r4,1 /* Increment */ /* * Configure and load pinned entry into TLB slot 63. */ +#ifdef CONFIG_NONSTATIC_KERNEL + /* + * In case of a NONSTATIC_KERNEL we reuse the TLB XLAT + * entries of the initial mapping set by the boot loader. + * The XLAT entry is stored in r25 + */ + + /* Read the XLAT entry for our current mapping */ + tlbre r25,r23,PPC44x_TLB_XLAT + + lis r3,KERNELBASE@h + ori r3,r3,KERNELBASE@l + + /* Use our current RPN entry */ + mr r4,r25 +#else lis r3,PAGE_OFFSET@h ori r3,r3,PAGE_OFFSET@l /* Kernel is at the base of RAM */ li r4, 0 /* Load the kernel physical address */ +#endif /* Load the kernel PID = 0 */ li r0,0 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 3564c49c683e..06c7251c1bf7 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -51,6 +51,11 @@ * For pSeries or server processors: * 1. The MMU is off & open firmware is running in real mode. * 2. The kernel is entered at __start + * -or- For OPAL entry: + * 1. The MMU is off, processor in HV mode, primary CPU enters at 0 + * with device-tree in gpr3. We also get OPAL base in r8 and + * entry in r9 for debugging purposes + * 2. Secondary processors enter at 0x60 with PIR in gpr3 * * For iSeries: * 1. The MMU is on (as it always is for iSeries) @@ -331,6 +336,11 @@ _GLOBAL(__start_initialization_multiplatform) /* Save parameters */ mr r31,r3 mr r30,r4 +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL + /* Save OPAL entry */ + mr r28,r8 + mr r29,r9 +#endif #ifdef CONFIG_PPC_BOOK3E bl .start_initialization_book3e @@ -674,9 +684,9 @@ _GLOBAL(enable_64b_mode) _GLOBAL(relative_toc) mflr r0 bcl 20,31,$+4 -0: mflr r9 - ld r2,(p_toc - 0b)(r9) - add r2,r2,r9 +0: mflr r11 + ld r2,(p_toc - 0b)(r11) + add r2,r2,r11 mtlr r0 blr @@ -707,6 +717,12 @@ _INIT_STATIC(start_here_multiplatform) bdnz 3b 4: +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL + /* Setup OPAL entry */ + std r28,0(r11); + std r29,8(r11); +#endif + #ifndef CONFIG_PPC_BOOK3E mfmsr r6 ori r6,r6,MSR_RI diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 1cbf64e6b416..b68cb173ba2c 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -76,11 +76,7 @@ _ENTRY(_start); */ .globl __start __start: - mr r31,r3 /* save parameters */ - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 + mr r31,r3 /* save device tree ptr */ /* We have to turn on the MMU right away so we get cache modes * set correctly. @@ -723,11 +719,8 @@ start_here: /* * Decide what sort of machine this is and initialize the MMU. */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 + li r3,0 + mr r4,r31 bl machine_init bl MMU_init diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 50845924b7d9..d5d78c4ceef6 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -63,17 +63,30 @@ _ENTRY(_start); * of abatron_pteptrs */ nop -/* - * Save parameters we are passed - */ - mr r31,r3 - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 - li r25,0 /* phys kernel start (low) */ - li r24,0 /* CPU number */ - li r23,0 /* phys kernel start (high) */ + + /* Translate device tree address to physical, save in r30/r31 */ + mfmsr r16 + mfspr r17,SPRN_PID + rlwinm r17,r17,16,0x3fff0000 /* turn PID into MAS6[SPID] */ + rlwimi r17,r16,28,0x00000001 /* turn MSR[DS] into MAS6[SAS] */ + mtspr SPRN_MAS6,r17 + + tlbsx 0,r3 /* must succeed */ + + mfspr r16,SPRN_MAS1 + mfspr r20,SPRN_MAS3 + rlwinm r17,r16,25,0x1f /* r17 = log2(page size) */ + li r18,1024 + slw r18,r18,r17 /* r18 = page size */ + addi r18,r18,-1 + and r19,r3,r18 /* r19 = page offset */ + andc r31,r20,r18 /* r31 = page base */ + or r31,r31,r19 /* r31 = devtree phys addr */ + mfspr r30,SPRN_MAS7 + + li r25,0 /* phys kernel start (low) */ + li r24,0 /* CPU number */ + li r23,0 /* phys kernel start (high) */ /* We try to not make any assumptions about how the boot loader * setup or used the TLBs. We invalidate all mappings from the @@ -184,7 +197,7 @@ _ENTRY(__early_start) bl early_init -#ifdef CONFIG_RELOCATABLE +#ifdef CONFIG_DYNAMIC_MEMSTART lis r3,kernstart_addr@ha la r3,kernstart_addr@l(r3) #ifdef CONFIG_PHYS_64BIT @@ -198,11 +211,8 @@ _ENTRY(__early_start) /* * Decide what sort of machine this is and initialize the MMU. */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 + mr r3,r30 + mr r4,r31 bl machine_init bl MMU_init @@ -236,8 +246,24 @@ _ENTRY(__early_start) * if we find the pte (fall through): * r11 is low pte word * r12 is pointer to the pte + * r10 is the pshift from the PGD, if we're a hugepage */ #ifdef CONFIG_PTE_64BIT +#ifdef CONFIG_HUGETLB_PAGE +#define FIND_PTE \ + rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \ + lwzx r11, r12, r11; /* Get pgd/pmd entry */ \ + rlwinm. r12, r11, 0, 0, 20; /* Extract pt base address */ \ + blt 1000f; /* Normal non-huge page */ \ + beq 2f; /* Bail if no table */ \ + oris r11, r11, PD_HUGE@h; /* Put back address bit */ \ + andi. r10, r11, HUGEPD_SHIFT_MASK@l; /* extract size field */ \ + xor r12, r10, r11; /* drop size bits from pointer */ \ + b 1001f; \ +1000: rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \ + li r10, 0; /* clear r10 */ \ +1001: lwz r11, 4(r12); /* Get pte entry */ +#else #define FIND_PTE \ rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \ lwzx r11, r12, r11; /* Get pgd/pmd entry */ \ @@ -245,7 +271,8 @@ _ENTRY(__early_start) beq 2f; /* Bail if no table */ \ rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \ lwz r11, 4(r12); /* Get pte entry */ -#else +#endif /* HUGEPAGE */ +#else /* !PTE_64BIT */ #define FIND_PTE \ rlwimi r11, r10, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \ lwz r11, 0(r11); /* Get L1 entry */ \ @@ -402,8 +429,8 @@ interrupt_base: #ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP - subf r10,r11,r12 /* create false data dep */ - lwzx r13,r11,r10 /* Get upper pte bits */ + subf r13,r11,r12 /* create false data dep */ + lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ #endif @@ -483,8 +510,8 @@ interrupt_base: #ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP - subf r10,r11,r12 /* create false data dep */ - lwzx r13,r11,r10 /* Get upper pte bits */ + subf r13,r11,r12 /* create false data dep */ + lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ #endif @@ -548,7 +575,7 @@ interrupt_base: /* * Both the instruction and data TLB miss get to this * point to load the TLB. - * r10 - available to use + * r10 - tsize encoding (if HUGETLB_PAGE) or available to use * r11 - TLB (info from Linux PTE) * r12 - available to use * r13 - upper bits of PTE (if PTE_64BIT) or available to use @@ -558,21 +585,73 @@ interrupt_base: * Upon exit, we reload everything and RFI. */ finish_tlb_load: +#ifdef CONFIG_HUGETLB_PAGE + cmpwi 6, r10, 0 /* check for huge page */ + beq 6, finish_tlb_load_cont /* !huge */ + + /* Alas, we need more scratch registers for hugepages */ + mfspr r12, SPRN_SPRG_THREAD + stw r14, THREAD_NORMSAVE(4)(r12) + stw r15, THREAD_NORMSAVE(5)(r12) + stw r16, THREAD_NORMSAVE(6)(r12) + stw r17, THREAD_NORMSAVE(7)(r12) + + /* Get the next_tlbcam_idx percpu var */ +#ifdef CONFIG_SMP + lwz r12, THREAD_INFO-THREAD(r12) + lwz r15, TI_CPU(r12) + lis r14, __per_cpu_offset@h + ori r14, r14, __per_cpu_offset@l + rlwinm r15, r15, 2, 0, 29 + lwzx r16, r14, r15 +#else + li r16, 0 +#endif + lis r17, next_tlbcam_idx@h + ori r17, r17, next_tlbcam_idx@l + add r17, r17, r16 /* r17 = *next_tlbcam_idx */ + lwz r15, 0(r17) /* r15 = next_tlbcam_idx */ + + lis r14, MAS0_TLBSEL(1)@h /* select TLB1 (TLBCAM) */ + rlwimi r14, r15, 16, 4, 15 /* next_tlbcam_idx entry */ + mtspr SPRN_MAS0, r14 + + /* Extract TLB1CFG(NENTRY) */ + mfspr r16, SPRN_TLB1CFG + andi. r16, r16, 0xfff + + /* Update next_tlbcam_idx, wrapping when necessary */ + addi r15, r15, 1 + cmpw r15, r16 + blt 100f + lis r14, tlbcam_index@h + ori r14, r14, tlbcam_index@l + lwz r15, 0(r14) +100: stw r15, 0(r17) + + /* + * Calc MAS1_TSIZE from r10 (which has pshift encoded) + * tlb_enc = (pshift - 10). + */ + subi r15, r10, 10 + mfspr r16, SPRN_MAS1 + rlwimi r16, r15, 7, 20, 24 + mtspr SPRN_MAS1, r16 + + /* copy the pshift for use later */ + mr r14, r10 + + /* fall through */ + +#endif /* CONFIG_HUGETLB_PAGE */ + /* * We set execute, because we don't have the granularity to * properly set this at the page level (Linux problem). * Many of these bits are software only. Bits we don't set * here we (properly should) assume have the appropriate value. */ - - mfspr r12, SPRN_MAS2 -#ifdef CONFIG_PTE_64BIT - rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */ -#else - rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ -#endif - mtspr SPRN_MAS2, r12 - +finish_tlb_load_cont: #ifdef CONFIG_PTE_64BIT rlwinm r12, r11, 32-2, 26, 31 /* Move in perm bits */ andi. r10, r11, _PAGE_DIRTY @@ -581,22 +660,40 @@ finish_tlb_load: andc r12, r12, r10 1: rlwimi r12, r13, 20, 0, 11 /* grab RPN[32:43] */ rlwimi r12, r11, 20, 12, 19 /* grab RPN[44:51] */ - mtspr SPRN_MAS3, r12 +2: mtspr SPRN_MAS3, r12 BEGIN_MMU_FTR_SECTION srwi r10, r13, 12 /* grab RPN[12:31] */ mtspr SPRN_MAS7, r10 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) #else li r10, (_PAGE_EXEC | _PAGE_PRESENT) + mr r13, r11 rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */ and r12, r11, r10 andi. r10, r11, _PAGE_USER /* Test for _PAGE_USER */ slwi r10, r12, 1 or r10, r10, r12 iseleq r12, r12, r10 - rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */ - mtspr SPRN_MAS3, r11 + rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */ + mtspr SPRN_MAS3, r13 #endif + + mfspr r12, SPRN_MAS2 +#ifdef CONFIG_PTE_64BIT + rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */ +#else + rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ +#endif +#ifdef CONFIG_HUGETLB_PAGE + beq 6, 3f /* don't mask if page isn't huge */ + li r13, 1 + slw r13, r13, r14 + subi r13, r13, 1 + rlwinm r13, r13, 0, 0, 19 /* bottom bits used for WIMGE/etc */ + andc r12, r12, r13 /* mask off ea bits within the page */ +#endif +3: mtspr SPRN_MAS2, r12 + #ifdef CONFIG_E200 /* Round robin TLB1 entries assignment */ mfspr r12, SPRN_MAS0 @@ -622,11 +719,19 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) mtspr SPRN_MAS0,r12 #endif /* CONFIG_E200 */ +tlb_write_entry: tlbwe /* Done...restore registers and get out of here. */ mfspr r10, SPRN_SPRG_THREAD - lwz r11, THREAD_NORMSAVE(3)(r10) +#ifdef CONFIG_HUGETLB_PAGE + beq 6, 8f /* skip restore for 4k page faults */ + lwz r14, THREAD_NORMSAVE(4)(r10) + lwz r15, THREAD_NORMSAVE(5)(r10) + lwz r16, THREAD_NORMSAVE(6)(r10) + lwz r17, THREAD_NORMSAVE(7)(r10) +#endif +8: lwz r11, THREAD_NORMSAVE(3)(r10) mtcr r11 lwz r13, THREAD_NORMSAVE(2)(r10) lwz r12, THREAD_NORMSAVE(1)(r10) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 5ecd0401cdb1..2bc0584be81c 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -27,7 +27,6 @@ #include <linux/kprobes.h> #include <linux/percpu.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/smp.h> diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 28581f1ad2c0..d39ae606ff8d 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -37,12 +37,14 @@ */ #include <linux/init.h> +#include <linux/export.h> #include <linux/console.h> #include <linux/kobject.h> #include <linux/dma-mapping.h> #include <linux/interrupt.h> #include <linux/of.h> #include <linux/slab.h> +#include <linux/stat.h> #include <linux/of_platform.h> #include <asm/ibmebus.h> #include <asm/abs_addr.h> @@ -125,17 +127,23 @@ static void ibmebus_unmap_sg(struct device *dev, static int ibmebus_dma_supported(struct device *dev, u64 mask) { - return 1; + return mask == DMA_BIT_MASK(64); +} + +static u64 ibmebus_dma_get_required_mask(struct device *dev) +{ + return DMA_BIT_MASK(64); } static struct dma_map_ops ibmebus_dma_ops = { - .alloc_coherent = ibmebus_alloc_coherent, - .free_coherent = ibmebus_free_coherent, - .map_sg = ibmebus_map_sg, - .unmap_sg = ibmebus_unmap_sg, - .dma_supported = ibmebus_dma_supported, - .map_page = ibmebus_map_page, - .unmap_page = ibmebus_unmap_page, + .alloc_coherent = ibmebus_alloc_coherent, + .free_coherent = ibmebus_free_coherent, + .map_sg = ibmebus_map_sg, + .unmap_sg = ibmebus_unmap_sg, + .dma_supported = ibmebus_dma_supported, + .get_required_mask = ibmebus_dma_get_required_mask, + .map_page = ibmebus_map_page, + .unmap_page = ibmebus_unmap_page, }; static int ibmebus_match_path(struct device *dev, void *data) diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 39a2baa6ad58..7c66ce13da89 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -39,13 +39,23 @@ #define cpu_should_die() 0 #endif +unsigned long cpuidle_disable = IDLE_NO_OVERRIDE; +EXPORT_SYMBOL(cpuidle_disable); + static int __init powersave_off(char *arg) { ppc_md.power_save = NULL; + cpuidle_disable = IDLE_POWERSAVE_OFF; return 0; } __setup("powersave=off", powersave_off); +#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_TRACEPOINTS) +static const bool idle_uses_rcu = 1; +#else +static const bool idle_uses_rcu; +#endif + /* * The body of the idle task. */ @@ -56,7 +66,10 @@ void cpu_idle(void) set_thread_flag(TIF_POLLING_NRFLAG); while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + if (!idle_uses_rcu) + rcu_idle_enter(); + while (!need_resched() && !cpu_should_die()) { ppc64_runlatch_off(); @@ -93,7 +106,9 @@ void cpu_idle(void) HMT_medium(); ppc64_runlatch_on(); - tick_nohz_restart_sched_tick(); + if (!idle_uses_rcu) + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); if (cpu_should_die()) cpu_die(); @@ -102,6 +117,29 @@ void cpu_idle(void) } } + +/* + * cpu_idle_wait - Used to ensure that all the CPUs come out of the old + * idle loop and start using the new idle loop. + * Required while changing idle handler on SMP systems. + * Caller must have changed idle handler to the new value before the call. + * This window may be larger on shared systems. + */ +void cpu_idle_wait(void) +{ + int cpu; + smp_mb(); + + /* kick all the CPUs so that they exit out of old idle routine */ + get_online_cpus(); + for_each_online_cpu(cpu) { + if (cpu != smp_processor_id()) + smp_send_reschedule(cpu); + } + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(cpu_idle_wait); + int powersave_nap; #ifdef CONFIG_SYSCTL diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S index 3e2b95c6ae67..4f0ab85f3788 100644 --- a/arch/powerpc/kernel/idle_e500.S +++ b/arch/powerpc/kernel/idle_e500.S @@ -26,7 +26,7 @@ _GLOBAL(e500_idle) ori r4,r4,_TLF_NAPPING /* so when we take an exception */ stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */ -#ifdef CONFIG_E500MC +#ifdef CONFIG_PPC_E500MC wrteei 1 1: wait diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 3a70845a51c7..fcdff198da4b 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -54,6 +54,7 @@ _GLOBAL(power7_idle) li r0,0 stb r0,PACASOFTIRQEN(r13) /* we'll hard-enable shortly */ stb r0,PACAHARDIRQEN(r13) + stb r0,PACA_NAPSTATELOST(r13) /* Continue saving state */ SAVE_GPR(2, r1) @@ -86,6 +87,9 @@ _GLOBAL(power7_wakeup_loss) rfid _GLOBAL(power7_wakeup_noloss) + lbz r0,PACA_NAPSTATELOST(r13) + cmpwi r0,0 + bne .power7_wakeup_loss ld r1,PACAR1(r13) ld r4,_MSR(r1) ld r5,_NIP(r1) diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c index 2375b7eb1c76..d076d465dbd1 100644 --- a/arch/powerpc/kernel/init_task.c +++ b/arch/powerpc/kernel/init_task.c @@ -1,5 +1,5 @@ #include <linux/mm.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/init_task.h> diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c index ffafaea3d261..12d329bcbb98 100644 --- a/arch/powerpc/kernel/io-workarounds.c +++ b/arch/powerpc/kernel/io-workarounds.c @@ -12,6 +12,7 @@ #undef DEBUG #include <linux/kernel.h> +#include <linux/sched.h> /* for init_mm */ #include <asm/io.h> #include <asm/machdep.h> diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c index 8dc7547c2377..886381f32c3d 100644 --- a/arch/powerpc/kernel/io.c +++ b/arch/powerpc/kernel/io.c @@ -19,7 +19,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/compiler.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/io.h> #include <asm/firmware.h> diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index b25f6325fc70..262791807397 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -6,6 +6,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/mm.h> +#include <linux/export.h> #include <asm/io.h> #include <asm/pci-bridge.h> diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 961bb03413f3..0cfcf98aafca 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -501,6 +501,14 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) tbl->it_map = page_address(page); memset(tbl->it_map, 0, sz); + /* + * Reserve page 0 so it will not be used for any mappings. + * This avoids buggy drivers that consider page 0 to be invalid + * to crash the machine or even lose data. + */ + if (tbl->it_offset == 0) + set_bit(0, tbl->it_map); + tbl->it_hint = 0; tbl->it_largehint = tbl->it_halfpoint; spin_lock_init(&tbl->it_lock); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index d281fb6f12f3..701d4aceb4f4 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -30,7 +30,7 @@ #undef DEBUG -#include <linux/module.h> +#include <linux/export.h> #include <linux/threads.h> #include <linux/kernel_stat.h> #include <linux/signal.h> @@ -115,6 +115,15 @@ static inline notrace void set_soft_enabled(unsigned long enable) : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled))); } +static inline notrace void decrementer_check_overflow(void) +{ + u64 now = get_tb_or_rtc(); + u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + + if (now >= *next_tb) + set_dec(1); +} + notrace void arch_local_irq_restore(unsigned long en) { /* @@ -164,24 +173,21 @@ notrace void arch_local_irq_restore(unsigned long en) */ local_paca->hard_enabled = en; -#ifndef CONFIG_BOOKE - /* On server, re-trigger the decrementer if it went negative since - * some processors only trigger on edge transitions of the sign bit. - * - * BookE has a level sensitive decrementer (latches in TSR) so we - * don't need that + /* + * Trigger the decrementer if we have a pending event. Some processors + * only trigger on edge transitions of the sign bit. We might also + * have disabled interrupts long enough that the decrementer wrapped + * to positive. */ - if ((int)mfspr(SPRN_DEC) < 0) - mtspr(SPRN_DEC, 1); -#endif /* CONFIG_BOOKE */ + decrementer_check_overflow(); /* * Force the delivery of pending soft-disabled interrupts on PS3. * Any HV call will have this side effect. */ if (firmware_has_feature(FW_FEATURE_PS3_LV1)) { - u64 tmp; - lv1_get_version_info(&tmp); + u64 tmp, tmp2; + lv1_get_version_info(&tmp, &tmp2); } __hard_irq_enable(); diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 4d5731b2429a..479752901ec6 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -18,6 +18,7 @@ #include <linux/kernel.h> #include <linux/pci.h> #include <linux/string.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/notifier.h> diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c index 368d158d665d..a1ed8a8c7cb4 100644 --- a/arch/powerpc/kernel/jump_label.c +++ b/arch/powerpc/kernel/jump_label.c @@ -11,6 +11,7 @@ #include <linux/jump_label.h> #include <asm/code-patching.h> +#ifdef HAVE_JUMP_LABEL void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { @@ -21,3 +22,4 @@ void arch_jump_label_transform(struct jump_entry *entry, else patch_instruction(addr, PPC_INST_NOP); } +#endif diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index b06bdae04064..2985338d0e10 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -20,6 +20,7 @@ #include <linux/kvm_host.h> #include <linux/init.h> +#include <linux/export.h> #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> @@ -131,7 +132,6 @@ static void kvm_patch_ins_b(u32 *inst, int addr) /* On relocatable kernels interrupts handlers and our code can be in different regions, so we don't patch them */ - extern u32 __end_interrupts; if ((ulong)inst < (ulong)&__end_interrupts) return; #endif diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 2b97b80d6d7d..3fea3689527e 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -6,6 +6,7 @@ #include <linux/pci.h> #include <linux/of_address.h> #include <linux/of_device.h> +#include <linux/serial_reg.h> #include <asm/io.h> #include <asm/mmu.h> #include <asm/prom.h> @@ -47,6 +48,24 @@ static struct __initdata of_device_id legacy_serial_parents[] = { static unsigned int legacy_serial_count; static int legacy_serial_console = -1; +static unsigned int tsi_serial_in(struct uart_port *p, int offset) +{ + unsigned int tmp; + offset = offset << p->regshift; + if (offset == UART_IIR) { + tmp = readl(p->membase + (UART_IIR & ~3)); + return (tmp >> 16) & 0xff; /* UART_IIR % 4 == 2 */ + } else + return readb(p->membase + offset); +} + +static void tsi_serial_out(struct uart_port *p, int offset, int value) +{ + offset = offset << p->regshift; + if (!((offset == UART_IER) && (value & UART_IER_UUE))) + writeb(value, p->membase + offset); +} + static int __init add_legacy_port(struct device_node *np, int want_index, int iotype, phys_addr_t base, phys_addr_t taddr, unsigned long irq, @@ -102,6 +121,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_ports[index].iobase = base; else legacy_serial_ports[index].mapbase = base; + legacy_serial_ports[index].iotype = iotype; legacy_serial_ports[index].uartclk = clock; legacy_serial_ports[index].irq = irq; @@ -112,6 +132,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_infos[index].speed = spd ? be32_to_cpup(spd) : 0; legacy_serial_infos[index].irq_check_parent = irq_check_parent; + if (iotype == UPIO_TSI) { + legacy_serial_ports[index].serial_in = tsi_serial_in; + legacy_serial_ports[index].serial_out = tsi_serial_out; + } + printk(KERN_DEBUG "Found legacy serial port %d for %s\n", index, np->full_name); printk(KERN_DEBUG " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n", @@ -416,6 +441,9 @@ static void __init fixup_port_irq(int index, return; port->irq = virq; + + if (of_device_is_compatible(np, "fsl,ns16550")) + port->handle_irq = fsl8250_handle_irq; } static void __init fixup_port_pio(int index, diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 84daabe2fcba..578f35f18723 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -783,7 +783,7 @@ static const struct file_operations lparcfg_fops = { static int __init lparcfg_init(void) { struct proc_dir_entry *ent; - mode_t mode = S_IRUSR | S_IRGRP | S_IROTH; + umode_t mode = S_IRUSR | S_IRGRP | S_IROTH; /* Allow writing if we have FW_FEATURE_SPLPAR */ if (firmware_has_feature(FW_FEATURE_SPLPAR) && diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 9ce1672afb59..c957b1202bdc 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -107,9 +107,6 @@ void __init reserve_crashkernel(void) unsigned long long crash_size, crash_base; int ret; - /* this is necessary because of memblock_phys_mem_size() */ - memblock_analyze(); - /* use common parsing */ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base); @@ -128,7 +125,7 @@ void __init reserve_crashkernel(void) crash_size = resource_size(&crashk_res); -#ifndef CONFIG_RELOCATABLE +#ifndef CONFIG_NONSTATIC_KERNEL if (crashk_res.start != KDUMP_KERNELBASE) printk("Crash kernel location must be 0x%x\n", KDUMP_KERNELBASE); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 583af70c4b14..26ccbf77dd41 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -74,8 +74,7 @@ int default_machine_kexec_prepare(struct kimage *image) } /* We also should not overwrite the tce tables */ - for (node = of_find_node_by_type(NULL, "pci"); node != NULL; - node = of_find_node_by_type(node, "pci")) { + for_each_node_by_type(node, "pci") { basep = of_get_property(node, "linux,tce-base", NULL); sizep = of_get_property(node, "linux,tce-size", NULL); if (basep == NULL || sizep == NULL) diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 998a10028608..7cd07b42ca1a 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -8,6 +8,8 @@ * kexec bits: * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com> * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz + * PPC44x port. Copyright (C) 2011, IBM Corporation + * Author: Suzuki Poulose <suzuki@in.ibm.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -736,6 +738,175 @@ relocate_new_kernel: mr r5, r31 li r0, 0 +#elif defined(CONFIG_44x) && !defined(CONFIG_PPC_47x) + +/* + * Code for setting up 1:1 mapping for PPC440x for KEXEC + * + * We cannot switch off the MMU on PPC44x. + * So we: + * 1) Invalidate all the mappings except the one we are running from. + * 2) Create a tmp mapping for our code in the other address space(TS) and + * jump to it. Invalidate the entry we started in. + * 3) Create a 1:1 mapping for 0-2GiB in chunks of 256M in original TS. + * 4) Jump to the 1:1 mapping in original TS. + * 5) Invalidate the tmp mapping. + * + * - Based on the kexec support code for FSL BookE + * - Doesn't support 47x yet. + * + */ + /* Save our parameters */ + mr r29, r3 + mr r30, r4 + mr r31, r5 + + /* Load our MSR_IS and TID to MMUCR for TLB search */ + mfspr r3,SPRN_PID + mfmsr r4 + andi. r4,r4,MSR_IS@l + beq wmmucr + oris r3,r3,PPC44x_MMUCR_STS@h +wmmucr: + mtspr SPRN_MMUCR,r3 + sync + + /* + * Invalidate all the TLB entries except the current entry + * where we are running from + */ + bl 0f /* Find our address */ +0: mflr r5 /* Make it accessible */ + tlbsx r23,0,r5 /* Find entry we are in */ + li r4,0 /* Start at TLB entry 0 */ + li r3,0 /* Set PAGEID inval value */ +1: cmpw r23,r4 /* Is this our entry? */ + beq skip /* If so, skip the inval */ + tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */ +skip: + addi r4,r4,1 /* Increment */ + cmpwi r4,64 /* Are we done? */ + bne 1b /* If not, repeat */ + isync + + /* Create a temp mapping and jump to it */ + andi. r6, r23, 1 /* Find the index to use */ + addi r24, r6, 1 /* r24 will contain 1 or 2 */ + + mfmsr r9 /* get the MSR */ + rlwinm r5, r9, 27, 31, 31 /* Extract the MSR[IS] */ + xori r7, r5, 1 /* Use the other address space */ + + /* Read the current mapping entries */ + tlbre r3, r23, PPC44x_TLB_PAGEID + tlbre r4, r23, PPC44x_TLB_XLAT + tlbre r5, r23, PPC44x_TLB_ATTRIB + + /* Save our current XLAT entry */ + mr r25, r4 + + /* Extract the TLB PageSize */ + li r10, 1 /* r10 will hold PageSize */ + rlwinm r11, r3, 0, 24, 27 /* bits 24-27 */ + + /* XXX: As of now we use 256M, 4K pages */ + cmpwi r11, PPC44x_TLB_256M + bne tlb_4k + rotlwi r10, r10, 28 /* r10 = 256M */ + b write_out +tlb_4k: + cmpwi r11, PPC44x_TLB_4K + bne default + rotlwi r10, r10, 12 /* r10 = 4K */ + b write_out +default: + rotlwi r10, r10, 10 /* r10 = 1K */ + +write_out: + /* + * Write out the tmp 1:1 mapping for this code in other address space + * Fixup EPN = RPN , TS=other address space + */ + insrwi r3, r7, 1, 23 /* Bit 23 is TS for PAGEID field */ + + /* Write out the tmp mapping entries */ + tlbwe r3, r24, PPC44x_TLB_PAGEID + tlbwe r4, r24, PPC44x_TLB_XLAT + tlbwe r5, r24, PPC44x_TLB_ATTRIB + + subi r11, r10, 1 /* PageOffset Mask = PageSize - 1 */ + not r10, r11 /* Mask for PageNum */ + + /* Switch to other address space in MSR */ + insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ + + bl 1f +1: mflr r8 + addi r8, r8, (2f-1b) /* Find the target offset */ + + /* Jump to the tmp mapping */ + mtspr SPRN_SRR0, r8 + mtspr SPRN_SRR1, r9 + rfi + +2: + /* Invalidate the entry we were executing from */ + li r3, 0 + tlbwe r3, r23, PPC44x_TLB_PAGEID + + /* attribute fields. rwx for SUPERVISOR mode */ + li r5, 0 + ori r5, r5, (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G) + + /* Create 1:1 mapping in 256M pages */ + xori r7, r7, 1 /* Revert back to Original TS */ + + li r8, 0 /* PageNumber */ + li r6, 3 /* TLB Index, start at 3 */ + +next_tlb: + rotlwi r3, r8, 28 /* Create EPN (bits 0-3) */ + mr r4, r3 /* RPN = EPN */ + ori r3, r3, (PPC44x_TLB_VALID | PPC44x_TLB_256M) /* SIZE = 256M, Valid */ + insrwi r3, r7, 1, 23 /* Set TS from r7 */ + + tlbwe r3, r6, PPC44x_TLB_PAGEID /* PageID field : EPN, V, SIZE */ + tlbwe r4, r6, PPC44x_TLB_XLAT /* Address translation : RPN */ + tlbwe r5, r6, PPC44x_TLB_ATTRIB /* Attributes */ + + addi r8, r8, 1 /* Increment PN */ + addi r6, r6, 1 /* Increment TLB Index */ + cmpwi r8, 8 /* Are we done ? */ + bne next_tlb + isync + + /* Jump to the new mapping 1:1 */ + li r9,0 + insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ + + bl 1f +1: mflr r8 + and r8, r8, r11 /* Get our offset within page */ + addi r8, r8, (2f-1b) + + and r5, r25, r10 /* Get our target PageNum */ + or r8, r8, r5 /* Target jump address */ + + mtspr SPRN_SRR0, r8 + mtspr SPRN_SRR1, r9 + rfi +2: + /* Invalidate the tmp entry we used */ + li r3, 0 + tlbwe r3, r24, PPC44x_TLB_PAGEID + sync + + /* Restore the parameters */ + mr r3, r29 + mr r4, r30 + mr r5, r31 + + li r0, 0 #else li r0, 0 diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index a1cd701b5753..2d275707f419 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -16,7 +16,6 @@ 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/module.h> #include <linux/elf.h> #include <linux/moduleloader.h> #include <linux/err.h> diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index 59dbf6abaaf3..e1612dfb4a93 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -15,7 +15,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mod_devicetable.h> #include <linux/pci.h> #include <linux/of.h> diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0a5a899846bb..41456ff55e14 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -8,7 +8,7 @@ */ #include <linux/smp.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/memblock.h> #include <asm/firmware.h> diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 32656f105250..fa4a573d6716 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/export.h> #include <linux/of_address.h> #include <linux/of_pci.h> #include <linux/mm.h> @@ -213,7 +214,7 @@ char __devinit *pcibios_setup(char *str) * If the interrupt is used, then gets the interrupt line from the * openfirmware and sets it in the pci_dev and pci_config line. */ -int pci_read_irq_line(struct pci_dev *pci_dev) +static int pci_read_irq_line(struct pci_dev *pci_dev) { struct of_irq oirq; unsigned int virq; @@ -282,7 +283,6 @@ int pci_read_irq_line(struct pci_dev *pci_dev) return 0; } -EXPORT_SYMBOL(pci_read_irq_line); /* * Platform support for /proc/bus/pci/X/Y mmap()s, @@ -920,18 +920,22 @@ static void __devinit pcibios_fixup_resources(struct pci_dev *dev) struct resource *res = dev->resource + i; if (!res->flags) continue; - /* On platforms that have PCI_PROBE_ONLY set, we don't - * consider 0 as an unassigned BAR value. It's technically - * a valid value, but linux doesn't like it... so when we can - * re-assign things, we do so, but if we can't, we keep it - * around and hope for the best... + + /* If we're going to re-assign everything, we mark all resources + * as unset (and 0-base them). In addition, we mark BARs starting + * at 0 as unset as well, except if PCI_PROBE_ONLY is also set + * since in that case, we don't want to re-assign anything */ - if (res->start == 0 && !pci_has_flag(PCI_PROBE_ONLY)) { - pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] is unassigned\n", - pci_name(dev), i, - (unsigned long long)res->start, - (unsigned long long)res->end, - (unsigned int)res->flags); + if (pci_has_flag(PCI_REASSIGN_ALL_RSRC) || + (res->start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) { + /* Only print message if not re-assigning */ + if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC)) + pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] " + "is unassigned\n", + pci_name(dev), i, + (unsigned long long)res->start, + (unsigned long long)res->end, + (unsigned int)res->flags); res->end -= res->start; res->start = 0; res->flags |= IORESOURCE_UNSET; @@ -1041,6 +1045,16 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus) if (i >= 3 && bus->self->transparent) continue; + /* If we are going to re-assign everything, mark the resource + * as unset and move it down to 0 + */ + if (pci_has_flag(PCI_REASSIGN_ALL_RSRC)) { + res->flags |= IORESOURCE_UNSET; + res->end -= res->start; + res->start = 0; + continue; + } + pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x] fixup...\n", pci_name(dev), i, (unsigned long long)res->start,\ @@ -1261,18 +1275,15 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus) pci_bus_for_each_resource(bus, res, i) { if (!res || !res->flags || res->start > res->end || res->parent) continue; + + /* If the resource was left unset at this point, we clear it */ + if (res->flags & IORESOURCE_UNSET) + goto clear_resource; + if (bus->parent == NULL) pr = (res->flags & IORESOURCE_IO) ? &ioport_resource : &iomem_resource; else { - /* Don't bother with non-root busses when - * re-assigning all resources. We clear the - * resource flags as if they were colliding - * and as such ensure proper re-allocation - * later. - */ - if (pci_has_flag(PCI_REASSIGN_ALL_RSRC)) - goto clear_resource; pr = pci_find_parent_resource(bus->self, res); if (pr == res) { /* this happens when the generic PCI @@ -1303,9 +1314,9 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus) if (reparent_resources(pr, res) == 0) continue; } - printk(KERN_WARNING "PCI: Cannot allocate resource region " - "%d of PCI bridge %d, will remap\n", i, bus->number); -clear_resource: + pr_warning("PCI: Cannot allocate resource region " + "%d of PCI bridge %d, will remap\n", i, bus->number); + clear_resource: res->start = res->end = 0; res->flags = 0; } @@ -1450,16 +1461,11 @@ void __init pcibios_resource_survey(void) { struct pci_bus *b; - /* Allocate and assign resources. If we re-assign everything, then - * we skip the allocate phase - */ + /* Allocate and assign resources */ list_for_each_entry(b, &pci_root_buses, node) pcibios_allocate_bus_resources(b); - - if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC)) { - pcibios_allocate_resources(0); - pcibios_allocate_resources(1); - } + pcibios_allocate_resources(0); + pcibios_allocate_resources(1); /* Before we start assigning unassigned resource, we try to reserve * the low IO area and the VGA memory area if they intersect the @@ -1730,15 +1736,35 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) if (mode == PCI_PROBE_NORMAL) hose->last_busno = bus->subordinate = pci_scan_child_bus(bus); + + /* Platform gets a chance to do some global fixups before + * we proceed to resource allocation + */ + if (ppc_md.pcibios_fixup_phb) + ppc_md.pcibios_fixup_phb(hose); + + /* Configure PCI Express settings */ + if (bus && !pci_has_flag(PCI_PROBE_ONLY)) { + struct pci_bus *child; + list_for_each_entry(child, &bus->children, node) { + struct pci_dev *self = child->self; + if (!self) + continue; + pcie_bus_configure_settings(child, self->pcie_mpss); + } + } } static void fixup_hide_host_resource_fsl(struct pci_dev *dev) { int i, class = dev->class >> 8; + /* When configured as agent, programing interface = 1 */ + int prog_if = dev->class & 0xf; if ((class == PCI_CLASS_PROCESSOR_POWERPC || class == PCI_CLASS_BRIDGE_OTHER) && (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) && + (prog_if == 0) && (dev->bus->parent == NULL)) { for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { dev->resource[i].start = 0; diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index bb154511db5e..fdd1a3d951dc 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -15,6 +15,7 @@ #include <linux/list.h> #include <linux/of.h> #include <linux/slab.h> +#include <linux/export.h> #include <asm/processor.h> #include <asm/io.h> diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index ab34046752bf..bcf4bf9e72d9 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -18,6 +18,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/list.h> #include <linux/syscalls.h> diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 478f8d78716b..dd9e4a04bf79 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -22,6 +22,7 @@ #include <linux/kernel.h> #include <linux/pci.h> #include <linux/string.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/gfp.h> @@ -49,6 +50,9 @@ void * __devinit update_dn_pci_info(struct device_node *dn, void *data) dn->data = pdn; pdn->node = dn; pdn->phb = phb; +#ifdef CONFIG_PPC_POWERNV + pdn->pe_number = IODA_INVALID_PE; +#endif regs = of_get_property(dn, "reg", NULL); if (regs) { /* First register entry is addr (00BBSS00) */ diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index fe0a5ad6f73e..b37d0b5a796e 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -15,6 +15,7 @@ */ #include <linux/pci.h> +#include <linux/export.h> #include <asm/pci-bridge.h> #include <asm/prom.h> diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c index 461499b43cff..a841a9d136a2 100644 --- a/arch/powerpc/kernel/pmc.c +++ b/arch/powerpc/kernel/pmc.c @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/spinlock.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/processor.h> #include <asm/cputable.h> diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index 03b95e2c6d65..0bbc901e7efc 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -487,8 +487,8 @@ static int power6_generic_events[] = { */ static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ - [C(OP_READ)] = { 0x80082, 0x80080 }, - [C(OP_WRITE)] = { 0x80086, 0x80088 }, + [C(OP_READ)] = { 0x280030, 0x80080 }, + [C(OP_WRITE)] = { 0x180032, 0x80088 }, [C(OP_PREFETCH)] = { 0x810a4, 0 }, }, [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index de83d6060dda..1251e4d7e262 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -297,6 +297,8 @@ static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[]) static int power7_generic_events[] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x1e, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x100f8, /* GCT_NOSLOT_CYC */ + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x4000a, /* CMPLU_STALL */ [PERF_COUNT_HW_INSTRUCTIONS] = 2, [PERF_COUNT_HW_CACHE_REFERENCES] = 0xc880, /* LD_REF_L1_LSU*/ [PERF_COUNT_HW_CACHE_MISSES] = 0x400f0, /* LD_MISS_L1 */ diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index f5ae872a2ef0..d3114a71dd32 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -1,4 +1,4 @@ -#include <linux/module.h> +#include <linux/export.h> #include <linux/threads.h> #include <linux/smp.h> #include <linux/sched.h> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 8f53954e75a3..ebe5766781aa 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -28,7 +28,7 @@ #include <linux/init.h> #include <linux/prctl.h> #include <linux/init_task.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kallsyms.h> #include <linux/mqueue.h> #include <linux/hardirq.h> @@ -486,28 +486,6 @@ struct task_struct *__switch_to(struct task_struct *prev, new_thread = &new->thread; old_thread = ¤t->thread; -#if defined(CONFIG_PPC_BOOK3E_64) - /* XXX Current Book3E code doesn't deal with kernel side DBCR0, - * we always hold the user values, so we set it now. - * - * However, we ensure the kernel MSR:DE is appropriately cleared too - * to avoid spurrious single step exceptions in the kernel. - * - * This will have to change to merge with the ppc32 code at some point, - * but I don't like much what ppc32 is doing today so there's some - * thinking needed there - */ - if ((new_thread->dbcr0 | old_thread->dbcr0) & DBCR0_IDM) { - u32 dbcr0; - - mtmsr(mfmsr() & ~MSR_DE); - isync(); - dbcr0 = mfspr(SPRN_DBCR0); - dbcr0 = (dbcr0 & DBCR0_EDM) | new_thread->dbcr0; - mtspr(SPRN_DBCR0, dbcr0); - } -#endif /* CONFIG_PPC64_BOOK3E */ - #ifdef CONFIG_PPC64 /* * Collect processor utilization data per process @@ -606,16 +584,32 @@ static struct regbit { unsigned long bit; const char *name; } msr_bits[] = { +#if defined(CONFIG_PPC64) && !defined(CONFIG_BOOKE) + {MSR_SF, "SF"}, + {MSR_HV, "HV"}, +#endif + {MSR_VEC, "VEC"}, + {MSR_VSX, "VSX"}, +#ifdef CONFIG_BOOKE + {MSR_CE, "CE"}, +#endif {MSR_EE, "EE"}, {MSR_PR, "PR"}, {MSR_FP, "FP"}, - {MSR_VEC, "VEC"}, - {MSR_VSX, "VSX"}, {MSR_ME, "ME"}, - {MSR_CE, "CE"}, +#ifdef CONFIG_BOOKE {MSR_DE, "DE"}, +#else + {MSR_SE, "SE"}, + {MSR_BE, "BE"}, +#endif {MSR_IR, "IR"}, {MSR_DR, "DR"}, + {MSR_PMM, "PMM"}, +#ifndef CONFIG_BOOKE + {MSR_RI, "RI"}, + {MSR_LE, "LE"}, +#endif {0, NULL} }; @@ -657,7 +651,7 @@ void show_regs(struct pt_regs * regs) if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) printk("CFAR: "REG"\n", regs->orig_gpr3); if (trap == 0x300 || trap == 0x600) -#ifdef CONFIG_PPC_ADV_DEBUG_REGS +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr); #else printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 174e1e96175e..abe405dab34d 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -27,7 +27,7 @@ #include <linux/delay.h> #include <linux/initrd.h> #include <linux/bitops.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kexec.h> #include <linux/debugfs.h> #include <linux/irq.h> @@ -54,6 +54,8 @@ #include <asm/pci-bridge.h> #include <asm/phyp_dump.h> #include <asm/kexec.h> +#include <asm/opal.h> + #include <mm/mmu_decl.h> #ifdef DEBUG @@ -707,11 +709,23 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_rtas, NULL); #endif +#ifdef CONFIG_PPC_POWERNV + /* Some machines might need OPAL info for debugging, grab it now. */ + of_scan_flat_dt(early_init_dt_scan_opal, NULL); +#endif + #ifdef CONFIG_PHYP_DUMP /* scan tree to see if dump occurred during last boot */ of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL); #endif + /* Pre-initialize the cmd_line with the content of boot_commmand_line, + * which will be empty except when the content of the variable has + * been overriden by a bootloading mechanism. This happens typically + * with HAL takeover + */ + strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE); + /* Retrieve various informations from the /chosen node of the * device-tree, including the platform type, initrd location and * size, TCE reserve, and more ... @@ -719,16 +733,17 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_chosen_ppc, cmd_line); /* Scan memory nodes and rebuild MEMBLOCKs */ - memblock_init(); - of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); - setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Save command line for /proc/cmdline and then parse parameters */ strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); parse_early_param(); + /* make sure we've parsed cmdline for mem= before this */ + if (memory_limit) + first_memblock_size = min(first_memblock_size, memory_limit); + setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */ memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); /* If relocatable, reserve first 32k for interrupt vectors etc. */ @@ -739,20 +754,14 @@ void __init early_init_devtree(void *params) early_reserve_mem(); phyp_dump_reserve_mem(); - limit = memory_limit; - if (! limit) { - phys_addr_t memsize; - - /* Ensure that total memory size is page-aligned, because - * otherwise mark_bootmem() gets upset. */ - memblock_analyze(); - memsize = memblock_phys_mem_size(); - if ((memsize & PAGE_MASK) != memsize) - limit = memsize & PAGE_MASK; - } + /* + * Ensure that total memory size is page-aligned, because otherwise + * mark_bootmem() gets upset. + */ + limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); memblock_enforce_memory_limit(limit); - memblock_analyze(); + memblock_allow_resize(); memblock_dump_all(); DBG("Phys. mem: %llx\n", memblock_phys_mem_size()); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a909f4e9343b..eca626ea3f23 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -43,6 +43,7 @@ #include <asm/btext.h> #include <asm/sections.h> #include <asm/machdep.h> +#include <asm/opal.h> #include <linux/linux_logo.h> @@ -139,7 +140,9 @@ struct mem_map_entry { typedef u32 cell_t; -extern void __start(unsigned long r3, unsigned long r4, unsigned long r5); +extern void __start(unsigned long r3, unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, unsigned long r8, + unsigned long r9); #ifdef CONFIG_PPC64 extern int enter_prom(struct prom_args *args, unsigned long entry); @@ -185,6 +188,7 @@ static unsigned long __initdata prom_tce_alloc_end; #define PLATFORM_LPAR 0x0001 #define PLATFORM_POWERMAC 0x0400 #define PLATFORM_GENERIC 0x0500 +#define PLATFORM_OPAL 0x0600 static int __initdata of_platform; @@ -644,7 +648,7 @@ static void __init early_cmdline_parse(void) } } -#ifdef CONFIG_PPC_PSERIES +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * There are two methods for telling firmware what our capabilities are. * Newer machines have an "ibm,client-architecture-support" method on the @@ -738,7 +742,7 @@ static unsigned char ibm_architecture_vec[] = { W(0xffffffff), /* virt_base */ W(0xffffffff), /* virt_size */ W(0xffffffff), /* load_base */ - W(64), /* 64MB min RMA */ + W(256), /* 256MB min RMA */ W(0xffffffff), /* full client load */ 0, /* min RMA percentage of total RAM */ 48, /* max log_2(hash table size) */ @@ -1220,14 +1224,6 @@ static void __init prom_init_mem(void) RELOC(alloc_bottom) = PAGE_ALIGN((unsigned long)&RELOC(_end) + 0x4000); - /* Check if we have an initrd after the kernel, if we do move our bottom - * point to after it - */ - if (RELOC(prom_initrd_start)) { - if (RELOC(prom_initrd_end) > RELOC(alloc_bottom)) - RELOC(alloc_bottom) = PAGE_ALIGN(RELOC(prom_initrd_end)); - } - /* * If prom_memory_limit is set we reduce the upper limits *except* for * alloc_top_high. This must be the real top of RAM so we can put @@ -1265,6 +1261,15 @@ static void __init prom_init_mem(void) RELOC(alloc_top) = RELOC(rmo_top); RELOC(alloc_top_high) = RELOC(ram_top); + /* + * Check if we have an initrd after the kernel but still inside + * the RMO. If we do move our bottom point to after it. + */ + if (RELOC(prom_initrd_start) && + RELOC(prom_initrd_start) < RELOC(rmo_top) && + RELOC(prom_initrd_end) > RELOC(alloc_bottom)) + RELOC(alloc_bottom) = PAGE_ALIGN(RELOC(prom_initrd_end)); + prom_printf("memory layout at init:\n"); prom_printf(" memory_limit : %x (16 MB aligned)\n", RELOC(prom_memory_limit)); prom_printf(" alloc_bottom : %x\n", RELOC(alloc_bottom)); @@ -1274,6 +1279,284 @@ static void __init prom_init_mem(void) prom_printf(" ram_top : %x\n", RELOC(ram_top)); } +static void __init prom_close_stdin(void) +{ + struct prom_t *_prom = &RELOC(prom); + ihandle val; + + if (prom_getprop(_prom->chosen, "stdin", &val, sizeof(val)) > 0) + call_prom("close", 1, 0, val); +} + +#ifdef CONFIG_PPC_POWERNV + +static u64 __initdata prom_opal_size; +static u64 __initdata prom_opal_align; +static int __initdata prom_rtas_start_cpu; +static u64 __initdata prom_rtas_data; +static u64 __initdata prom_rtas_entry; + +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL +static u64 __initdata prom_opal_base; +static u64 __initdata prom_opal_entry; +#endif + +/* XXX Don't change this structure without updating opal-takeover.S */ +static struct opal_secondary_data { + s64 ack; /* 0 */ + u64 go; /* 8 */ + struct opal_takeover_args args; /* 16 */ +} opal_secondary_data; + +extern char opal_secondary_entry; + +static void prom_query_opal(void) +{ + long rc; + + /* We must not query for OPAL presence on a machine that + * supports TNK takeover (970 blades), as this uses the same + * h-call with different arguments and will crash + */ + if (PHANDLE_VALID(call_prom("finddevice", 1, 1, + ADDR("/tnk-memory-map")))) { + prom_printf("TNK takeover detected, skipping OPAL check\n"); + return; + } + + prom_printf("Querying for OPAL presence... "); + rc = opal_query_takeover(&RELOC(prom_opal_size), + &RELOC(prom_opal_align)); + prom_debug("(rc = %ld) ", rc); + if (rc != 0) { + prom_printf("not there.\n"); + return; + } + RELOC(of_platform) = PLATFORM_OPAL; + prom_printf(" there !\n"); + prom_debug(" opal_size = 0x%lx\n", RELOC(prom_opal_size)); + prom_debug(" opal_align = 0x%lx\n", RELOC(prom_opal_align)); + if (RELOC(prom_opal_align) < 0x10000) + RELOC(prom_opal_align) = 0x10000; +} + +static int prom_rtas_call(int token, int nargs, int nret, int *outputs, ...) +{ + struct rtas_args rtas_args; + va_list list; + int i; + + rtas_args.token = token; + rtas_args.nargs = nargs; + rtas_args.nret = nret; + rtas_args.rets = (rtas_arg_t *)&(rtas_args.args[nargs]); + va_start(list, outputs); + for (i = 0; i < nargs; ++i) + rtas_args.args[i] = va_arg(list, rtas_arg_t); + va_end(list); + + for (i = 0; i < nret; ++i) + rtas_args.rets[i] = 0; + + opal_enter_rtas(&rtas_args, RELOC(prom_rtas_data), + RELOC(prom_rtas_entry)); + + if (nret > 1 && outputs != NULL) + for (i = 0; i < nret-1; ++i) + outputs[i] = rtas_args.rets[i+1]; + return (nret > 0)? rtas_args.rets[0]: 0; +} + +static void __init prom_opal_hold_cpus(void) +{ + int i, cnt, cpu, rc; + long j; + phandle node; + char type[64]; + u32 servers[8]; + struct prom_t *_prom = &RELOC(prom); + void *entry = (unsigned long *)&RELOC(opal_secondary_entry); + struct opal_secondary_data *data = &RELOC(opal_secondary_data); + + prom_debug("prom_opal_hold_cpus: start...\n"); + prom_debug(" - entry = 0x%x\n", entry); + prom_debug(" - data = 0x%x\n", data); + + data->ack = -1; + data->go = 0; + + /* look for cpus */ + for (node = 0; prom_next_node(&node); ) { + type[0] = 0; + prom_getprop(node, "device_type", type, sizeof(type)); + if (strcmp(type, RELOC("cpu")) != 0) + continue; + + /* Skip non-configured cpus. */ + if (prom_getprop(node, "status", type, sizeof(type)) > 0) + if (strcmp(type, RELOC("okay")) != 0) + continue; + + cnt = prom_getprop(node, "ibm,ppc-interrupt-server#s", servers, + sizeof(servers)); + if (cnt == PROM_ERROR) + break; + cnt >>= 2; + for (i = 0; i < cnt; i++) { + cpu = servers[i]; + prom_debug("CPU %d ... ", cpu); + if (cpu == _prom->cpu) { + prom_debug("booted !\n"); + continue; + } + prom_debug("starting ... "); + + /* Init the acknowledge var which will be reset by + * the secondary cpu when it awakens from its OF + * spinloop. + */ + data->ack = -1; + rc = prom_rtas_call(RELOC(prom_rtas_start_cpu), 3, 1, + NULL, cpu, entry, data); + prom_debug("rtas rc=%d ...", rc); + + for (j = 0; j < 100000000 && data->ack == -1; j++) { + HMT_low(); + mb(); + } + HMT_medium(); + if (data->ack != -1) + prom_debug("done, PIR=0x%x\n", data->ack); + else + prom_debug("timeout !\n"); + } + } + prom_debug("prom_opal_hold_cpus: end...\n"); +} + +static void prom_opal_takeover(void) +{ + struct opal_secondary_data *data = &RELOC(opal_secondary_data); + struct opal_takeover_args *args = &data->args; + u64 align = RELOC(prom_opal_align); + u64 top_addr, opal_addr; + + args->k_image = (u64)RELOC(_stext); + args->k_size = _end - _stext; + args->k_entry = 0; + args->k_entry2 = 0x60; + + top_addr = _ALIGN_UP(args->k_size, align); + + if (RELOC(prom_initrd_start) != 0) { + args->rd_image = RELOC(prom_initrd_start); + args->rd_size = RELOC(prom_initrd_end) - args->rd_image; + args->rd_loc = top_addr; + top_addr = _ALIGN_UP(args->rd_loc + args->rd_size, align); + } + + /* Pickup an address for the HAL. We want to go really high + * up to avoid problem with future kexecs. On the other hand + * we don't want to be all over the TCEs on P5IOC2 machines + * which are going to be up there too. We assume the machine + * has plenty of memory, and we ask for the HAL for now to + * be just below the 1G point, or above the initrd + */ + opal_addr = _ALIGN_DOWN(0x40000000 - RELOC(prom_opal_size), align); + if (opal_addr < top_addr) + opal_addr = top_addr; + args->hal_addr = opal_addr; + + /* Copy the command line to the kernel image */ + strlcpy(RELOC(boot_command_line), RELOC(prom_cmd_line), + COMMAND_LINE_SIZE); + + prom_debug(" k_image = 0x%lx\n", args->k_image); + prom_debug(" k_size = 0x%lx\n", args->k_size); + prom_debug(" k_entry = 0x%lx\n", args->k_entry); + prom_debug(" k_entry2 = 0x%lx\n", args->k_entry2); + prom_debug(" hal_addr = 0x%lx\n", args->hal_addr); + prom_debug(" rd_image = 0x%lx\n", args->rd_image); + prom_debug(" rd_size = 0x%lx\n", args->rd_size); + prom_debug(" rd_loc = 0x%lx\n", args->rd_loc); + prom_printf("Performing OPAL takeover,this can take a few minutes..\n"); + prom_close_stdin(); + mb(); + data->go = 1; + for (;;) + opal_do_takeover(args); +} + +/* + * Allocate room for and instantiate OPAL + */ +static void __init prom_instantiate_opal(void) +{ + phandle opal_node; + ihandle opal_inst; + u64 base, entry; + u64 size = 0, align = 0x10000; + u32 rets[2]; + + prom_debug("prom_instantiate_opal: start...\n"); + + opal_node = call_prom("finddevice", 1, 1, ADDR("/ibm,opal")); + prom_debug("opal_node: %x\n", opal_node); + if (!PHANDLE_VALID(opal_node)) + return; + + prom_getprop(opal_node, "opal-runtime-size", &size, sizeof(size)); + if (size == 0) + return; + prom_getprop(opal_node, "opal-runtime-alignment", &align, + sizeof(align)); + + base = alloc_down(size, align, 0); + if (base == 0) { + prom_printf("OPAL allocation failed !\n"); + return; + } + + opal_inst = call_prom("open", 1, 1, ADDR("/ibm,opal")); + if (!IHANDLE_VALID(opal_inst)) { + prom_printf("opening opal package failed (%x)\n", opal_inst); + return; + } + + prom_printf("instantiating opal at 0x%x...", base); + + if (call_prom_ret("call-method", 4, 3, rets, + ADDR("load-opal-runtime"), + opal_inst, + base >> 32, base & 0xffffffff) != 0 + || (rets[0] == 0 && rets[1] == 0)) { + prom_printf(" failed\n"); + return; + } + entry = (((u64)rets[0]) << 32) | rets[1]; + + prom_printf(" done\n"); + + reserve_mem(base, size); + + prom_debug("opal base = 0x%x\n", base); + prom_debug("opal align = 0x%x\n", align); + prom_debug("opal entry = 0x%x\n", entry); + prom_debug("opal size = 0x%x\n", (long)size); + + prom_setprop(opal_node, "/ibm,opal", "opal-base-address", + &base, sizeof(base)); + prom_setprop(opal_node, "/ibm,opal", "opal-entry-address", + &entry, sizeof(entry)); + +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL + RELOC(prom_opal_base) = base; + RELOC(prom_opal_entry) = entry; +#endif + prom_debug("prom_instantiate_opal: end...\n"); +} + +#endif /* CONFIG_PPC_POWERNV */ /* * Allocate room for and instantiate RTAS @@ -1297,10 +1580,8 @@ static void __init prom_instantiate_rtas(void) return; base = alloc_down(size, PAGE_SIZE, 0); - if (base == 0) { - prom_printf("RTAS allocation failed !\n"); - return; - } + if (base == 0) + prom_panic("Could not allocate memory for RTAS\n"); rtas_inst = call_prom("open", 1, 1, ADDR("/rtas")); if (!IHANDLE_VALID(rtas_inst)) { @@ -1326,6 +1607,12 @@ static void __init prom_instantiate_rtas(void) prom_setprop(rtas_node, "/rtas", "linux,rtas-entry", &entry, sizeof(entry)); +#ifdef CONFIG_PPC_POWERNV + /* PowerVN takeover hack */ + RELOC(prom_rtas_data) = base; + RELOC(prom_rtas_entry) = entry; + prom_getprop(rtas_node, "start-cpu", &RELOC(prom_rtas_start_cpu), 4); +#endif prom_debug("rtas base = 0x%x\n", base); prom_debug("rtas entry = 0x%x\n", entry); prom_debug("rtas size = 0x%x\n", (long)size); @@ -1543,7 +1830,7 @@ static void __init prom_hold_cpus(void) *acknowledge = (unsigned long)-1; if (reg != _prom->cpu) { - /* Primary Thread of non-boot cpu */ + /* Primary Thread of non-boot cpu or any thread */ prom_printf("starting cpu hw idx %lu... ", reg); call_prom("start-cpu", 3, 0, node, secondary_hold, reg); @@ -1652,15 +1939,6 @@ static void __init prom_init_stdout(void) prom_setprop(val, path, "linux,boot-display", NULL, 0); } -static void __init prom_close_stdin(void) -{ - struct prom_t *_prom = &RELOC(prom); - ihandle val; - - if (prom_getprop(_prom->chosen, "stdin", &val, sizeof(val)) > 0) - call_prom("close", 1, 0, val); -} - static int __init prom_find_machine_type(void) { struct prom_t *_prom = &RELOC(prom); @@ -1671,7 +1949,7 @@ static int __init prom_find_machine_type(void) int x; #endif - /* Look for a PowerMac */ + /* Look for a PowerMac or a Cell */ len = prom_getprop(_prom->root, "compatible", compat, sizeof(compat)-1); if (len > 0) { @@ -1697,7 +1975,11 @@ static int __init prom_find_machine_type(void) } } #ifdef CONFIG_PPC64 - /* If not a mac, try to figure out if it's an IBM pSeries or any other + /* Try to detect OPAL */ + if (PHANDLE_VALID(call_prom("finddevice", 1, 1, ADDR("/ibm,opal")))) + return PLATFORM_OPAL; + + /* Try to figure out if it's an IBM pSeries or any other * PAPR compliant platform. We assume it is if : * - /device_type is "chrp" (please, do NOT use that for future * non-IBM designs ! @@ -1798,7 +2080,7 @@ static void __init prom_check_displays(void) /* Setup a usable color table when the appropriate * method is available. Should update this to set-colors */ clut = RELOC(default_colors); - for (i = 0; i < 32; i++, clut += 3) + for (i = 0; i < 16; i++, clut += 3) if (prom_set_color(ih, i, clut[0], clut[1], clut[2]) != 0) break; @@ -1924,7 +2206,7 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start, unsigned long soff; unsigned char *valp; static char pname[MAX_PROPERTY_NAME]; - int l, room; + int l, room, has_phandle = 0; dt_push_token(OF_DT_BEGIN_NODE, mem_start, mem_end); @@ -2008,19 +2290,26 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start, valp = make_room(mem_start, mem_end, l, 4); call_prom("getprop", 4, 1, node, RELOC(pname), valp, l); *mem_start = _ALIGN(*mem_start, 4); + + if (!strcmp(RELOC(pname), RELOC("phandle"))) + has_phandle = 1; } - /* Add a "linux,phandle" property. */ - soff = dt_find_string(RELOC("linux,phandle")); - if (soff == 0) - prom_printf("WARNING: Can't find string index for" - " <linux-phandle> node %s\n", path); - else { - dt_push_token(OF_DT_PROP, mem_start, mem_end); - dt_push_token(4, mem_start, mem_end); - dt_push_token(soff, mem_start, mem_end); - valp = make_room(mem_start, mem_end, 4, 4); - *(u32 *)valp = node; + /* Add a "linux,phandle" property if no "phandle" property already + * existed (can happen with OPAL) + */ + if (!has_phandle) { + soff = dt_find_string(RELOC("linux,phandle")); + if (soff == 0) + prom_printf("WARNING: Can't find string index for" + " <linux-phandle> node %s\n", path); + else { + dt_push_token(OF_DT_PROP, mem_start, mem_end); + dt_push_token(4, mem_start, mem_end); + dt_push_token(soff, mem_start, mem_end); + valp = make_room(mem_start, mem_end, 4, 4); + *(u32 *)valp = node; + } } /* do all our children */ @@ -2504,6 +2793,7 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4) #endif /* CONFIG_BLK_DEV_INITRD */ } + /* * We enter here early on, when the Open Firmware prom is still * handling exceptions and the MMU hash table for us. @@ -2553,8 +2843,9 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, * between pSeries SMP and pSeries LPAR */ RELOC(of_platform) = prom_find_machine_type(); + prom_printf("Detected machine type: %x\n", RELOC(of_platform)); -#ifndef CONFIG_RELOCATABLE +#ifndef CONFIG_NONSTATIC_KERNEL /* Bail if this is a kdump kernel. */ if (PHYSICAL_START > 0) prom_panic("Error: You can't boot a kdump kernel from OF!\n"); @@ -2565,7 +2856,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, */ prom_check_initrd(r3, r4); -#ifdef CONFIG_PPC_PSERIES +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * On pSeries, inform the firmware about our capabilities */ @@ -2611,14 +2902,33 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, #endif /* - * On non-powermacs, try to instantiate RTAS and puts all CPUs - * in spin-loops. PowerMacs don't have a working RTAS and use - * a different way to spin CPUs + * On non-powermacs, try to instantiate RTAS. PowerMacs don't + * have a usable RTAS implementation. */ - if (RELOC(of_platform) != PLATFORM_POWERMAC) { + if (RELOC(of_platform) != PLATFORM_POWERMAC && + RELOC(of_platform) != PLATFORM_OPAL) prom_instantiate_rtas(); + +#ifdef CONFIG_PPC_POWERNV + /* Detect HAL and try instanciating it & doing takeover */ + if (RELOC(of_platform) == PLATFORM_PSERIES_LPAR) { + prom_query_opal(); + if (RELOC(of_platform) == PLATFORM_OPAL) { + prom_opal_hold_cpus(); + prom_opal_takeover(); + } + } else if (RELOC(of_platform) == PLATFORM_OPAL) + prom_instantiate_opal(); +#endif + + /* + * On non-powermacs, put all CPUs in spin-loops. + * + * PowerMacs use a different mechanism to spin CPUs + */ + if (RELOC(of_platform) != PLATFORM_POWERMAC && + RELOC(of_platform) != PLATFORM_OPAL) prom_hold_cpus(); - } /* * Fill in some infos for use by the kernel later on @@ -2660,9 +2970,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* * in case stdin is USB and still active on IBM machines... * Unfortunately quiesce crashes on some powermacs if we have - * closed stdin already (in particular the powerbook 101). + * closed stdin already (in particular the powerbook 101). It + * appears that the OPAL version of OFW doesn't like it either. */ - if (RELOC(of_platform) != PLATFORM_POWERMAC) + if (RELOC(of_platform) != PLATFORM_POWERMAC && + RELOC(of_platform) != PLATFORM_OPAL) prom_close_stdin(); /* @@ -2678,14 +2990,24 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, * is common to us and kexec */ hdr = RELOC(dt_header_start); - prom_printf("returning from prom_init\n"); - prom_debug("->dt_header_start=0x%x\n", hdr); + + /* Don't print anything after quiesce under OPAL, it crashes OFW */ + if (RELOC(of_platform) != PLATFORM_OPAL) { + prom_printf("returning from prom_init\n"); + prom_debug("->dt_header_start=0x%x\n", hdr); + } #ifdef CONFIG_PPC32 reloc_got2(-offset); #endif - __start(hdr, kbase, 0); +#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL + /* OPAL early debug gets the OPAL base & entry in r8 and r9 */ + __start(hdr, kbase, 0, 0, 0, + RELOC(prom_opal_base), RELOC(prom_opal_entry)); +#else + __start(hdr, kbase, 0, 0, 0, 0, 0); +#endif return 0; } diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 9f82f4937892..70f4286eaa7a 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -20,7 +20,9 @@ WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush _end enter_prom memcpy memset reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224 -reloc_got2 kernstart_addr memstart_addr linux_banner" +reloc_got2 kernstart_addr memstart_addr linux_banner _stext +opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry +boot_command_line" NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index 47187cc2cf00..4e1331b8eb33 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -2,7 +2,6 @@ #include <linux/kernel.h> #include <linux/string.h> -#include <linux/module.h> #include <linux/ioport.h> #include <linux/etherdevice.h> #include <linux/of_address.h> diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 05b7dd217f60..5de73dbd15c7 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -30,9 +30,6 @@ #include <linux/seccomp.h> #include <linux/audit.h> #include <trace/syscall.h> -#ifdef CONFIG_PPC32 -#include <linux/module.h> -#endif #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> @@ -1497,9 +1494,14 @@ long arch_ptrace(struct task_struct *child, long request, if (index < PT_FPR0) { tmp = ptrace_get_reg(child, (int) index); } else { + unsigned int fpidx = index - PT_FPR0; + flush_fp_to_thread(child); - tmp = ((unsigned long *)child->thread.fpr) - [TS_FPRWIDTH * (index - PT_FPR0)]; + if (fpidx < (PT_FPSCR - PT_FPR0)) + tmp = ((unsigned long *)child->thread.fpr) + [fpidx * TS_FPRWIDTH]; + else + tmp = child->thread.fpscr.val; } ret = put_user(tmp, datalp); break; @@ -1525,9 +1527,14 @@ long arch_ptrace(struct task_struct *child, long request, if (index < PT_FPR0) { ret = ptrace_put_reg(child, index, data); } else { + unsigned int fpidx = index - PT_FPR0; + flush_fp_to_thread(child); - ((unsigned long *)child->thread.fpr) - [TS_FPRWIDTH * (index - PT_FPR0)] = data; + if (fpidx < (PT_FPSCR - PT_FPR0)) + ((unsigned long *)child->thread.fpr) + [fpidx * TS_FPRWIDTH] = data; + else + child->thread.fpscr.val = data; ret = 0; } break; diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S new file mode 100644 index 000000000000..ef46ba6e094f --- /dev/null +++ b/arch/powerpc/kernel/reloc_32.S @@ -0,0 +1,208 @@ +/* + * Code to process dynamic relocations for PPC32. + * + * Copyrights (C) IBM Corporation, 2011. + * Author: Suzuki Poulose <suzuki@in.ibm.com> + * + * - Based on ppc64 code - reloc_64.S + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <asm/ppc_asm.h> + +/* Dynamic section table entry tags */ +DT_RELA = 7 /* Tag for Elf32_Rela section */ +DT_RELASZ = 8 /* Size of the Rela relocs */ +DT_RELAENT = 9 /* Size of one Rela reloc entry */ + +STN_UNDEF = 0 /* Undefined symbol index */ +STB_LOCAL = 0 /* Local binding for the symbol */ + +R_PPC_ADDR16_LO = 4 /* Lower half of (S+A) */ +R_PPC_ADDR16_HI = 5 /* Upper half of (S+A) */ +R_PPC_ADDR16_HA = 6 /* High Adjusted (S+A) */ +R_PPC_RELATIVE = 22 + +/* + * r3 = desired final address + */ + +_GLOBAL(relocate) + + mflr r0 /* Save our LR */ + bl 0f /* Find our current runtime address */ +0: mflr r12 /* Make it accessible */ + mtlr r0 + + lwz r11, (p_dyn - 0b)(r12) + add r11, r11, r12 /* runtime address of .dynamic section */ + lwz r9, (p_rela - 0b)(r12) + add r9, r9, r12 /* runtime address of .rela.dyn section */ + lwz r10, (p_st - 0b)(r12) + add r10, r10, r12 /* runtime address of _stext section */ + lwz r13, (p_sym - 0b)(r12) + add r13, r13, r12 /* runtime address of .dynsym section */ + + /* + * Scan the dynamic section for RELA, RELASZ entries + */ + li r6, 0 + li r7, 0 + li r8, 0 +1: lwz r5, 0(r11) /* ELF_Dyn.d_tag */ + cmpwi r5, 0 /* End of ELF_Dyn[] */ + beq eodyn + cmpwi r5, DT_RELA + bne relasz + lwz r7, 4(r11) /* r7 = rela.link */ + b skip +relasz: + cmpwi r5, DT_RELASZ + bne relaent + lwz r8, 4(r11) /* r8 = Total Rela relocs size */ + b skip +relaent: + cmpwi r5, DT_RELAENT + bne skip + lwz r6, 4(r11) /* r6 = Size of one Rela reloc */ +skip: + addi r11, r11, 8 + b 1b +eodyn: /* End of Dyn Table scan */ + + /* Check if we have found all the entries */ + cmpwi r7, 0 + beq done + cmpwi r8, 0 + beq done + cmpwi r6, 0 + beq done + + + /* + * Work out the current offset from the link time address of .rela + * section. + * cur_offset[r7] = rela.run[r9] - rela.link [r7] + * _stext.link[r12] = _stext.run[r10] - cur_offset[r7] + * final_offset[r3] = _stext.final[r3] - _stext.link[r12] + */ + subf r7, r7, r9 /* cur_offset */ + subf r12, r7, r10 + subf r3, r12, r3 /* final_offset */ + + subf r8, r6, r8 /* relaz -= relaent */ + /* + * Scan through the .rela table and process each entry + * r9 - points to the current .rela table entry + * r13 - points to the symbol table + */ + + /* + * Check if we have a relocation based on symbol + * r5 will hold the value of the symbol. + */ +applyrela: + lwz r4, 4(r9) /* r4 = rela.r_info */ + srwi r5, r4, 8 /* ELF32_R_SYM(r_info) */ + cmpwi r5, STN_UNDEF /* sym == STN_UNDEF ? */ + beq get_type /* value = 0 */ + /* Find the value of the symbol at index(r5) */ + slwi r5, r5, 4 /* r5 = r5 * sizeof(Elf32_Sym) */ + add r12, r13, r5 /* r12 = &__dyn_sym[Index] */ + + /* + * GNU ld has a bug, where dynamic relocs based on + * STB_LOCAL symbols, the value should be assumed + * to be zero. - Alan Modra + */ + /* XXX: Do we need to check if we are using GNU ld ? */ + lbz r5, 12(r12) /* r5 = dyn_sym[Index].st_info */ + extrwi r5, r5, 4, 24 /* r5 = ELF32_ST_BIND(r5) */ + cmpwi r5, STB_LOCAL /* st_value = 0, ld bug */ + beq get_type /* We have r5 = 0 */ + lwz r5, 4(r12) /* r5 = __dyn_sym[Index].st_value */ + +get_type: + /* Load the relocation type to r4 */ + extrwi r4, r4, 8, 24 /* r4 = ELF32_R_TYPE(r_info) = ((char*)r4)[3] */ + + /* R_PPC_RELATIVE */ + cmpwi r4, R_PPC_RELATIVE + bne hi16 + lwz r4, 0(r9) /* r_offset */ + lwz r0, 8(r9) /* r_addend */ + add r0, r0, r3 /* final addend */ + stwx r0, r4, r7 /* memory[r4+r7]) = (u32)r0 */ + b nxtrela /* continue */ + + /* R_PPC_ADDR16_HI */ +hi16: + cmpwi r4, R_PPC_ADDR16_HI + bne ha16 + lwz r4, 0(r9) /* r_offset */ + lwz r0, 8(r9) /* r_addend */ + add r0, r0, r3 + add r0, r0, r5 /* r0 = (S+A+Offset) */ + extrwi r0, r0, 16, 0 /* r0 = (r0 >> 16) */ + b store_half + + /* R_PPC_ADDR16_HA */ +ha16: + cmpwi r4, R_PPC_ADDR16_HA + bne lo16 + lwz r4, 0(r9) /* r_offset */ + lwz r0, 8(r9) /* r_addend */ + add r0, r0, r3 + add r0, r0, r5 /* r0 = (S+A+Offset) */ + extrwi r5, r0, 1, 16 /* Extract bit 16 */ + extrwi r0, r0, 16, 0 /* r0 = (r0 >> 16) */ + add r0, r0, r5 /* Add it to r0 */ + b store_half + + /* R_PPC_ADDR16_LO */ +lo16: + cmpwi r4, R_PPC_ADDR16_LO + bne nxtrela + lwz r4, 0(r9) /* r_offset */ + lwz r0, 8(r9) /* r_addend */ + add r0, r0, r3 + add r0, r0, r5 /* r0 = (S+A+Offset) */ + extrwi r0, r0, 16, 16 /* r0 &= 0xffff */ + /* Fall through to */ + + /* Store half word */ +store_half: + sthx r0, r4, r7 /* memory[r4+r7] = (u16)r0 */ + +nxtrela: + /* + * We have to flush the modified instructions to the + * main storage from the d-cache. And also, invalidate the + * cached instructions in i-cache which has been modified. + * + * We delay the sync / isync operation till the end, since + * we won't be executing the modified instructions until + * we return from here. + */ + dcbst r4,r7 + sync /* Ensure the data is flushed before icbi */ + icbi r4,r7 + cmpwi r8, 0 /* relasz = 0 ? */ + ble done + add r9, r9, r6 /* move to next entry in the .rela table */ + subf r8, r6, r8 /* relasz -= relaent */ + b applyrela + +done: + sync /* Wait for the flush to finish */ + isync /* Discard prefetched instructions */ + blr + +p_dyn: .long __dynamic_start - 0b +p_rela: .long __rela_dyn_start - 0b +p_sym: .long __dynamic_symtab - 0b +p_st: .long _stext - 0b diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index d5ca8236315c..517b1d8f455b 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -15,7 +15,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/spinlock.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/capability.h> #include <linux/delay.h> diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index e037c7494fd8..4174b4b23246 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -568,6 +568,12 @@ static void rtas_flash_firmware(int reboot_type) } /* + * Just before starting the firmware flash, cancel the event scan work + * to avoid any soft lockup issues. + */ + rtas_cancel_event_scan(); + + /* * NOTE: the "first" block must be under 4GB, so we create * an entry with no data blocks in the reserved buffer in * the kernel data segment. diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 481ef064c8f1..1045ff49cc6d 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -472,6 +472,13 @@ static void start_event_scan(void) &event_scan_work, event_scan_delay); } +/* Cancel the rtas event scan work */ +void rtas_cancel_event_scan(void) +{ + cancel_delayed_work_sync(&event_scan_work); +} +EXPORT_SYMBOL_GPL(rtas_cancel_event_scan); + static int __init rtas_init(void) { struct proc_dir_entry *entry; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b1d738d12890..77bb77da05c1 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -12,7 +12,7 @@ #undef DEBUG -#include <linux/module.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/init.h> diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 209135af0a40..ac7610815113 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -107,6 +107,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) PTRRELOC(&__start___lwsync_fixup), PTRRELOC(&__stop___lwsync_fixup)); + do_final_fixups(); + return KERNELBASE + offset; } @@ -117,7 +119,7 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * This is called very early on the boot process, after a minimal * MMU environment has been set up but before MMU_init is called. */ -notrace void __init machine_init(unsigned long dt_ptr) +notrace void __init machine_init(u64 dt_ptr) { lockdep_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index aebef1320ed7..4cb8f1e9d044 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -12,7 +12,7 @@ #undef DEBUG -#include <linux/module.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/init.h> @@ -35,6 +35,8 @@ #include <linux/pci.h> #include <linux/lockdep.h> #include <linux/memblock.h> +#include <linux/hugetlb.h> + #include <asm/io.h> #include <asm/kdump.h> #include <asm/prom.h> @@ -64,6 +66,7 @@ #include <asm/mmu_context.h> #include <asm/code-patching.h> #include <asm/kvm_ppc.h> +#include <asm/hugetlb.h> #include "setup.h" @@ -217,6 +220,13 @@ void __init early_setup(unsigned long dt_ptr) /* Initialize the hash table or TLB handling */ early_init_mmu(); + /* + * Reserve any gigantic pages requested on the command line. + * memblock needs to have been initialized by the time this is + * called since this will reserve memory. + */ + reserve_hugetlb_gpages(); + DBG(" <- early_setup()\n"); } @@ -278,14 +288,14 @@ static void __init initialize_cache_info(void) DBG(" -> initialize_cache_info()\n"); - for (np = NULL; (np = of_find_node_by_type(np, "cpu"));) { + for_each_node_by_type(np, "cpu") { num_cpus += 1; - /* We're assuming *all* of the CPUs have the same + /* + * We're assuming *all* of the CPUs have the same * d-cache and i-cache sizes... -Peter */ - - if ( num_cpus == 1 ) { + if (num_cpus == 1) { const u32 *sizep, *lsizep; u32 size, lsize; @@ -294,10 +304,13 @@ static void __init initialize_cache_info(void) sizep = of_get_property(np, "d-cache-size", NULL); if (sizep != NULL) size = *sizep; - lsizep = of_get_property(np, "d-cache-block-size", NULL); + lsizep = of_get_property(np, "d-cache-block-size", + NULL); /* fallback if block size missing */ if (lsizep == NULL) - lsizep = of_get_property(np, "d-cache-line-size", NULL); + lsizep = of_get_property(np, + "d-cache-line-size", + NULL); if (lsizep != NULL) lsize = *lsizep; if (sizep == 0 || lsizep == 0) @@ -314,9 +327,12 @@ static void __init initialize_cache_info(void) sizep = of_get_property(np, "i-cache-size", NULL); if (sizep != NULL) size = *sizep; - lsizep = of_get_property(np, "i-cache-block-size", NULL); + lsizep = of_get_property(np, "i-cache-block-size", + NULL); if (lsizep == NULL) - lsizep = of_get_property(np, "i-cache-line-size", NULL); + lsizep = of_get_property(np, + "i-cache-line-size", + NULL); if (lsizep != NULL) lsize = *lsizep; if (sizep == 0 || lsizep == 0) @@ -353,6 +369,7 @@ void __init setup_system(void) &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); do_lwsync_fixups(cur_cpu_spec->cpu_features, &__start___lwsync_fixup, &__stop___lwsync_fixup); + do_final_fixups(); /* * Unflatten the device-tree passed by prom_init or kexec diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 78b76dc54dfb..836a5a19eb2c 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -97,7 +97,7 @@ static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set) compat_sigset_t cset; switch (_NSIG_WORDS) { - case 4: cset.sig[5] = set->sig[3] & 0xffffffffull; + case 4: cset.sig[6] = set->sig[3] & 0xffffffffull; cset.sig[7] = set->sig[3] >> 32; case 3: cset.sig[4] = set->sig[2] & 0xffffffffull; cset.sig[5] = set->sig[2] >> 32; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index e91c736cc842..a50b5ec281dc 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -23,7 +23,6 @@ #include <linux/stddef.h> #include <linux/elf.h> #include <linux/ptrace.h> -#include <linux/module.h> #include <linux/ratelimit.h> #include <asm/sigcontext.h> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 7bf2187dfd99..46695febc09f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -18,7 +18,7 @@ #undef DEBUG #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/smp.h> #include <linux/interrupt.h> @@ -27,7 +27,7 @@ #include <linux/spinlock.h> #include <linux/cache.h> #include <linux/err.h> -#include <linux/sysdev.h> +#include <linux/device.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/topology.h> @@ -70,6 +70,10 @@ static DEFINE_PER_CPU(struct task_struct *, idle_thread_array); #define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x)) #define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p)) + +/* State of each CPU during hotplug phases */ +static DEFINE_PER_CPU(int, cpu_state) = { 0 }; + #else static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ; #define get_idle_for_cpu(x) (idle_thread_array[(x)]) @@ -104,12 +108,25 @@ int __devinit smp_generic_kick_cpu(int nr) * cpu_start field to become non-zero After we set cpu_start, * the processor will continue on to secondary_start */ - paca[nr].cpu_start = 1; - smp_mb(); + if (!paca[nr].cpu_start) { + paca[nr].cpu_start = 1; + smp_mb(); + return 0; + } + +#ifdef CONFIG_HOTPLUG_CPU + /* + * Ok it's not there, so it might be soft-unplugged, let's + * try to bring it back + */ + per_cpu(cpu_state, nr) = CPU_UP_PREPARE; + smp_wmb(); + smp_send_reschedule(nr); +#endif /* CONFIG_HOTPLUG_CPU */ return 0; } -#endif +#endif /* CONFIG_PPC64 */ static irqreturn_t call_function_action(int irq, void *data) { @@ -170,7 +187,8 @@ int smp_request_message_ipi(int virq, int msg) return 1; } #endif - err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU, + err = request_irq(virq, smp_ipi_action[msg], + IRQF_PERCPU | IRQF_NO_THREAD, smp_ipi_name[msg], 0); WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n", virq, smp_ipi_name[msg], err); @@ -357,8 +375,6 @@ void __devinit smp_prepare_boot_cpu(void) } #ifdef CONFIG_HOTPLUG_CPU -/* State of each CPU during hotplug phases */ -static DEFINE_PER_CPU(int, cpu_state) = { 0 }; int generic_cpu_disable(void) { @@ -406,6 +422,11 @@ void generic_set_cpu_dead(unsigned int cpu) { per_cpu(cpu_state, cpu) = CPU_DEAD; } + +int generic_check_cpu_restart(unsigned int cpu) +{ + return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE; +} #endif struct create_idle { diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index b0dbb1daa4df..3d30ef1038e5 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -10,7 +10,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/stacktrace.h> #include <asm/ptrace.h> diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c index aa17b76dd427..641f9adc6205 100644 --- a/arch/powerpc/kernel/swsusp.c +++ b/arch/powerpc/kernel/swsusp.c @@ -33,6 +33,6 @@ void save_processor_state(void) void restore_processor_state(void) { #ifdef CONFIG_PPC32 - switch_mmu_context(NULL, current->active_mm); + switch_mmu_context(current->active_mm, current->active_mm); #endif } diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c index 6f3f0697274e..168e88480223 100644 --- a/arch/powerpc/kernel/swsusp_64.c +++ b/arch/powerpc/kernel/swsusp_64.c @@ -9,6 +9,7 @@ #include <asm/system.h> #include <asm/iommu.h> #include <linux/irq.h> +#include <linux/sched.h> #include <linux/interrupt.h> void do_after_copyback(void) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index f0f2199e64e1..883e74c0d1b3 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -1,10 +1,10 @@ -#include <linux/sysdev.h> +#include <linux/device.h> #include <linux/cpu.h> #include <linux/smp.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/sched.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/nodemask.h> #include <linux/cpumask.h> #include <linux/notifier.h> @@ -18,6 +18,7 @@ #include <asm/machdep.h> #include <asm/smp.h> #include <asm/pmc.h> +#include <asm/system.h> #include "cacheinfo.h" @@ -37,12 +38,12 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); /* Time in microseconds we delay before sleeping in the idle loop */ DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; -static ssize_t store_smt_snooze_delay(struct sys_device *dev, - struct sysdev_attribute *attr, +static ssize_t store_smt_snooze_delay(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { - struct cpu *cpu = container_of(dev, struct cpu, sysdev); + struct cpu *cpu = container_of(dev, struct cpu, dev); ssize_t ret; long snooze; @@ -50,21 +51,22 @@ static ssize_t store_smt_snooze_delay(struct sys_device *dev, if (ret != 1) return -EINVAL; - per_cpu(smt_snooze_delay, cpu->sysdev.id) = snooze; + per_cpu(smt_snooze_delay, cpu->dev.id) = snooze; + update_smt_snooze_delay(snooze); return count; } -static ssize_t show_smt_snooze_delay(struct sys_device *dev, - struct sysdev_attribute *attr, +static ssize_t show_smt_snooze_delay(struct device *dev, + struct device_attribute *attr, char *buf) { - struct cpu *cpu = container_of(dev, struct cpu, sysdev); + struct cpu *cpu = container_of(dev, struct cpu, dev); - return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->sysdev.id)); + return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->dev.id)); } -static SYSDEV_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, +static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, store_smt_snooze_delay); static int __init setup_smt_snooze_delay(char *str) @@ -117,25 +119,25 @@ static void write_##NAME(void *val) \ ppc_enable_pmcs(); \ mtspr(ADDRESS, *(unsigned long *)val); \ } \ -static ssize_t show_##NAME(struct sys_device *dev, \ - struct sysdev_attribute *attr, \ +static ssize_t show_##NAME(struct device *dev, \ + struct device_attribute *attr, \ char *buf) \ { \ - struct cpu *cpu = container_of(dev, struct cpu, sysdev); \ + struct cpu *cpu = container_of(dev, struct cpu, dev); \ unsigned long val; \ - smp_call_function_single(cpu->sysdev.id, read_##NAME, &val, 1); \ + smp_call_function_single(cpu->dev.id, read_##NAME, &val, 1); \ return sprintf(buf, "%lx\n", val); \ } \ static ssize_t __used \ - store_##NAME(struct sys_device *dev, struct sysdev_attribute *attr, \ + store_##NAME(struct device *dev, struct device_attribute *attr, \ const char *buf, size_t count) \ { \ - struct cpu *cpu = container_of(dev, struct cpu, sysdev); \ + struct cpu *cpu = container_of(dev, struct cpu, dev); \ unsigned long val; \ int ret = sscanf(buf, "%lx", &val); \ if (ret != 1) \ return -EINVAL; \ - smp_call_function_single(cpu->sysdev.id, write_##NAME, &val, 1); \ + smp_call_function_single(cpu->dev.id, write_##NAME, &val, 1); \ return count; \ } @@ -177,23 +179,25 @@ SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); SYSFS_PMCSETUP(purr, SPRN_PURR); SYSFS_PMCSETUP(spurr, SPRN_SPURR); SYSFS_PMCSETUP(dscr, SPRN_DSCR); +SYSFS_PMCSETUP(pir, SPRN_PIR); -static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra); -static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL); -static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr); -static SYSDEV_ATTR(purr, 0600, show_purr, store_purr); +static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra); +static DEVICE_ATTR(spurr, 0600, show_spurr, NULL); +static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr); +static DEVICE_ATTR(purr, 0600, show_purr, store_purr); +static DEVICE_ATTR(pir, 0400, show_pir, NULL); unsigned long dscr_default = 0; EXPORT_SYMBOL(dscr_default); -static ssize_t show_dscr_default(struct sysdev_class *class, - struct sysdev_class_attribute *attr, char *buf) +static ssize_t show_dscr_default(struct device *dev, + struct device_attribute *attr, char *buf) { return sprintf(buf, "%lx\n", dscr_default); } -static ssize_t __used store_dscr_default(struct sysdev_class *class, - struct sysdev_class_attribute *attr, const char *buf, +static ssize_t __used store_dscr_default(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { unsigned long val; @@ -207,15 +211,14 @@ static ssize_t __used store_dscr_default(struct sysdev_class *class, return count; } -static SYSDEV_CLASS_ATTR(dscr_default, 0600, +static DEVICE_ATTR(dscr_default, 0600, show_dscr_default, store_dscr_default); static void sysfs_create_dscr_default(void) { int err = 0; if (cpu_has_feature(CPU_FTR_DSCR)) - err = sysfs_create_file(&cpu_sysdev_class.kset.kobj, - &attr_dscr_default.attr); + err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default); } #endif /* CONFIG_PPC64 */ @@ -259,72 +262,72 @@ SYSFS_PMCSETUP(tsr3, SPRN_PA6T_TSR3); #endif /* HAS_PPC_PMC_PA6T */ #ifdef HAS_PPC_PMC_IBM -static struct sysdev_attribute ibm_common_attrs[] = { - _SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), - _SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), +static struct device_attribute ibm_common_attrs[] = { + __ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), + __ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), }; #endif /* HAS_PPC_PMC_G4 */ #ifdef HAS_PPC_PMC_G4 -static struct sysdev_attribute g4_common_attrs[] = { - _SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), - _SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), - _SYSDEV_ATTR(mmcr2, 0600, show_mmcr2, store_mmcr2), +static struct device_attribute g4_common_attrs[] = { + __ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), + __ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), + __ATTR(mmcr2, 0600, show_mmcr2, store_mmcr2), }; #endif /* HAS_PPC_PMC_G4 */ -static struct sysdev_attribute classic_pmc_attrs[] = { - _SYSDEV_ATTR(pmc1, 0600, show_pmc1, store_pmc1), - _SYSDEV_ATTR(pmc2, 0600, show_pmc2, store_pmc2), - _SYSDEV_ATTR(pmc3, 0600, show_pmc3, store_pmc3), - _SYSDEV_ATTR(pmc4, 0600, show_pmc4, store_pmc4), - _SYSDEV_ATTR(pmc5, 0600, show_pmc5, store_pmc5), - _SYSDEV_ATTR(pmc6, 0600, show_pmc6, store_pmc6), +static struct device_attribute classic_pmc_attrs[] = { + __ATTR(pmc1, 0600, show_pmc1, store_pmc1), + __ATTR(pmc2, 0600, show_pmc2, store_pmc2), + __ATTR(pmc3, 0600, show_pmc3, store_pmc3), + __ATTR(pmc4, 0600, show_pmc4, store_pmc4), + __ATTR(pmc5, 0600, show_pmc5, store_pmc5), + __ATTR(pmc6, 0600, show_pmc6, store_pmc6), #ifdef CONFIG_PPC64 - _SYSDEV_ATTR(pmc7, 0600, show_pmc7, store_pmc7), - _SYSDEV_ATTR(pmc8, 0600, show_pmc8, store_pmc8), + __ATTR(pmc7, 0600, show_pmc7, store_pmc7), + __ATTR(pmc8, 0600, show_pmc8, store_pmc8), #endif }; #ifdef HAS_PPC_PMC_PA6T -static struct sysdev_attribute pa6t_attrs[] = { - _SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), - _SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), - _SYSDEV_ATTR(pmc0, 0600, show_pa6t_pmc0, store_pa6t_pmc0), - _SYSDEV_ATTR(pmc1, 0600, show_pa6t_pmc1, store_pa6t_pmc1), - _SYSDEV_ATTR(pmc2, 0600, show_pa6t_pmc2, store_pa6t_pmc2), - _SYSDEV_ATTR(pmc3, 0600, show_pa6t_pmc3, store_pa6t_pmc3), - _SYSDEV_ATTR(pmc4, 0600, show_pa6t_pmc4, store_pa6t_pmc4), - _SYSDEV_ATTR(pmc5, 0600, show_pa6t_pmc5, store_pa6t_pmc5), +static struct device_attribute pa6t_attrs[] = { + __ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0), + __ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1), + __ATTR(pmc0, 0600, show_pa6t_pmc0, store_pa6t_pmc0), + __ATTR(pmc1, 0600, show_pa6t_pmc1, store_pa6t_pmc1), + __ATTR(pmc2, 0600, show_pa6t_pmc2, store_pa6t_pmc2), + __ATTR(pmc3, 0600, show_pa6t_pmc3, store_pa6t_pmc3), + __ATTR(pmc4, 0600, show_pa6t_pmc4, store_pa6t_pmc4), + __ATTR(pmc5, 0600, show_pa6t_pmc5, store_pa6t_pmc5), #ifdef CONFIG_DEBUG_KERNEL - _SYSDEV_ATTR(hid0, 0600, show_hid0, store_hid0), - _SYSDEV_ATTR(hid1, 0600, show_hid1, store_hid1), - _SYSDEV_ATTR(hid4, 0600, show_hid4, store_hid4), - _SYSDEV_ATTR(hid5, 0600, show_hid5, store_hid5), - _SYSDEV_ATTR(ima0, 0600, show_ima0, store_ima0), - _SYSDEV_ATTR(ima1, 0600, show_ima1, store_ima1), - _SYSDEV_ATTR(ima2, 0600, show_ima2, store_ima2), - _SYSDEV_ATTR(ima3, 0600, show_ima3, store_ima3), - _SYSDEV_ATTR(ima4, 0600, show_ima4, store_ima4), - _SYSDEV_ATTR(ima5, 0600, show_ima5, store_ima5), - _SYSDEV_ATTR(ima6, 0600, show_ima6, store_ima6), - _SYSDEV_ATTR(ima7, 0600, show_ima7, store_ima7), - _SYSDEV_ATTR(ima8, 0600, show_ima8, store_ima8), - _SYSDEV_ATTR(ima9, 0600, show_ima9, store_ima9), - _SYSDEV_ATTR(imaat, 0600, show_imaat, store_imaat), - _SYSDEV_ATTR(btcr, 0600, show_btcr, store_btcr), - _SYSDEV_ATTR(pccr, 0600, show_pccr, store_pccr), - _SYSDEV_ATTR(rpccr, 0600, show_rpccr, store_rpccr), - _SYSDEV_ATTR(der, 0600, show_der, store_der), - _SYSDEV_ATTR(mer, 0600, show_mer, store_mer), - _SYSDEV_ATTR(ber, 0600, show_ber, store_ber), - _SYSDEV_ATTR(ier, 0600, show_ier, store_ier), - _SYSDEV_ATTR(sier, 0600, show_sier, store_sier), - _SYSDEV_ATTR(siar, 0600, show_siar, store_siar), - _SYSDEV_ATTR(tsr0, 0600, show_tsr0, store_tsr0), - _SYSDEV_ATTR(tsr1, 0600, show_tsr1, store_tsr1), - _SYSDEV_ATTR(tsr2, 0600, show_tsr2, store_tsr2), - _SYSDEV_ATTR(tsr3, 0600, show_tsr3, store_tsr3), + __ATTR(hid0, 0600, show_hid0, store_hid0), + __ATTR(hid1, 0600, show_hid1, store_hid1), + __ATTR(hid4, 0600, show_hid4, store_hid4), + __ATTR(hid5, 0600, show_hid5, store_hid5), + __ATTR(ima0, 0600, show_ima0, store_ima0), + __ATTR(ima1, 0600, show_ima1, store_ima1), + __ATTR(ima2, 0600, show_ima2, store_ima2), + __ATTR(ima3, 0600, show_ima3, store_ima3), + __ATTR(ima4, 0600, show_ima4, store_ima4), + __ATTR(ima5, 0600, show_ima5, store_ima5), + __ATTR(ima6, 0600, show_ima6, store_ima6), + __ATTR(ima7, 0600, show_ima7, store_ima7), + __ATTR(ima8, 0600, show_ima8, store_ima8), + __ATTR(ima9, 0600, show_ima9, store_ima9), + __ATTR(imaat, 0600, show_imaat, store_imaat), + __ATTR(btcr, 0600, show_btcr, store_btcr), + __ATTR(pccr, 0600, show_pccr, store_pccr), + __ATTR(rpccr, 0600, show_rpccr, store_rpccr), + __ATTR(der, 0600, show_der, store_der), + __ATTR(mer, 0600, show_mer, store_mer), + __ATTR(ber, 0600, show_ber, store_ber), + __ATTR(ier, 0600, show_ier, store_ier), + __ATTR(sier, 0600, show_sier, store_sier), + __ATTR(siar, 0600, show_siar, store_siar), + __ATTR(tsr0, 0600, show_tsr0, store_tsr0), + __ATTR(tsr1, 0600, show_tsr1, store_tsr1), + __ATTR(tsr2, 0600, show_tsr2, store_tsr2), + __ATTR(tsr3, 0600, show_tsr3, store_tsr3), #endif /* CONFIG_DEBUG_KERNEL */ }; #endif /* HAS_PPC_PMC_PA6T */ @@ -333,14 +336,14 @@ static struct sysdev_attribute pa6t_attrs[] = { static void __cpuinit register_cpu_online(unsigned int cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); - struct sys_device *s = &c->sysdev; - struct sysdev_attribute *attrs, *pmc_attrs; + struct device *s = &c->dev; + struct device_attribute *attrs, *pmc_attrs; int i, nattrs; #ifdef CONFIG_PPC64 if (!firmware_has_feature(FW_FEATURE_ISERIES) && cpu_has_feature(CPU_FTR_SMT)) - sysdev_create_file(s, &attr_smt_snooze_delay); + device_create_file(s, &dev_attr_smt_snooze_delay); #endif /* PMC stuff */ @@ -348,14 +351,14 @@ static void __cpuinit register_cpu_online(unsigned int cpu) #ifdef HAS_PPC_PMC_IBM case PPC_PMC_IBM: attrs = ibm_common_attrs; - nattrs = sizeof(ibm_common_attrs) / sizeof(struct sysdev_attribute); + nattrs = sizeof(ibm_common_attrs) / sizeof(struct device_attribute); pmc_attrs = classic_pmc_attrs; break; #endif /* HAS_PPC_PMC_IBM */ #ifdef HAS_PPC_PMC_G4 case PPC_PMC_G4: attrs = g4_common_attrs; - nattrs = sizeof(g4_common_attrs) / sizeof(struct sysdev_attribute); + nattrs = sizeof(g4_common_attrs) / sizeof(struct device_attribute); pmc_attrs = classic_pmc_attrs; break; #endif /* HAS_PPC_PMC_G4 */ @@ -363,7 +366,7 @@ static void __cpuinit register_cpu_online(unsigned int cpu) case PPC_PMC_PA6T: /* PA Semi starts counting at PMC0 */ attrs = pa6t_attrs; - nattrs = sizeof(pa6t_attrs) / sizeof(struct sysdev_attribute); + nattrs = sizeof(pa6t_attrs) / sizeof(struct device_attribute); pmc_attrs = NULL; break; #endif /* HAS_PPC_PMC_PA6T */ @@ -374,24 +377,27 @@ static void __cpuinit register_cpu_online(unsigned int cpu) } for (i = 0; i < nattrs; i++) - sysdev_create_file(s, &attrs[i]); + device_create_file(s, &attrs[i]); if (pmc_attrs) for (i = 0; i < cur_cpu_spec->num_pmcs; i++) - sysdev_create_file(s, &pmc_attrs[i]); + device_create_file(s, &pmc_attrs[i]); #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_MMCRA)) - sysdev_create_file(s, &attr_mmcra); + device_create_file(s, &dev_attr_mmcra); if (cpu_has_feature(CPU_FTR_PURR)) - sysdev_create_file(s, &attr_purr); + device_create_file(s, &dev_attr_purr); if (cpu_has_feature(CPU_FTR_SPURR)) - sysdev_create_file(s, &attr_spurr); + device_create_file(s, &dev_attr_spurr); if (cpu_has_feature(CPU_FTR_DSCR)) - sysdev_create_file(s, &attr_dscr); + device_create_file(s, &dev_attr_dscr); + + if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) + device_create_file(s, &dev_attr_pir); #endif /* CONFIG_PPC64 */ cacheinfo_cpu_online(cpu); @@ -401,8 +407,8 @@ static void __cpuinit register_cpu_online(unsigned int cpu) static void unregister_cpu_online(unsigned int cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); - struct sys_device *s = &c->sysdev; - struct sysdev_attribute *attrs, *pmc_attrs; + struct device *s = &c->dev; + struct device_attribute *attrs, *pmc_attrs; int i, nattrs; BUG_ON(!c->hotpluggable); @@ -410,7 +416,7 @@ static void unregister_cpu_online(unsigned int cpu) #ifdef CONFIG_PPC64 if (!firmware_has_feature(FW_FEATURE_ISERIES) && cpu_has_feature(CPU_FTR_SMT)) - sysdev_remove_file(s, &attr_smt_snooze_delay); + device_remove_file(s, &dev_attr_smt_snooze_delay); #endif /* PMC stuff */ @@ -418,14 +424,14 @@ static void unregister_cpu_online(unsigned int cpu) #ifdef HAS_PPC_PMC_IBM case PPC_PMC_IBM: attrs = ibm_common_attrs; - nattrs = sizeof(ibm_common_attrs) / sizeof(struct sysdev_attribute); + nattrs = sizeof(ibm_common_attrs) / sizeof(struct device_attribute); pmc_attrs = classic_pmc_attrs; break; #endif /* HAS_PPC_PMC_IBM */ #ifdef HAS_PPC_PMC_G4 case PPC_PMC_G4: attrs = g4_common_attrs; - nattrs = sizeof(g4_common_attrs) / sizeof(struct sysdev_attribute); + nattrs = sizeof(g4_common_attrs) / sizeof(struct device_attribute); pmc_attrs = classic_pmc_attrs; break; #endif /* HAS_PPC_PMC_G4 */ @@ -433,7 +439,7 @@ static void unregister_cpu_online(unsigned int cpu) case PPC_PMC_PA6T: /* PA Semi starts counting at PMC0 */ attrs = pa6t_attrs; - nattrs = sizeof(pa6t_attrs) / sizeof(struct sysdev_attribute); + nattrs = sizeof(pa6t_attrs) / sizeof(struct device_attribute); pmc_attrs = NULL; break; #endif /* HAS_PPC_PMC_PA6T */ @@ -444,24 +450,27 @@ static void unregister_cpu_online(unsigned int cpu) } for (i = 0; i < nattrs; i++) - sysdev_remove_file(s, &attrs[i]); + device_remove_file(s, &attrs[i]); if (pmc_attrs) for (i = 0; i < cur_cpu_spec->num_pmcs; i++) - sysdev_remove_file(s, &pmc_attrs[i]); + device_remove_file(s, &pmc_attrs[i]); #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_MMCRA)) - sysdev_remove_file(s, &attr_mmcra); + device_remove_file(s, &dev_attr_mmcra); if (cpu_has_feature(CPU_FTR_PURR)) - sysdev_remove_file(s, &attr_purr); + device_remove_file(s, &dev_attr_purr); if (cpu_has_feature(CPU_FTR_SPURR)) - sysdev_remove_file(s, &attr_spurr); + device_remove_file(s, &dev_attr_spurr); if (cpu_has_feature(CPU_FTR_DSCR)) - sysdev_remove_file(s, &attr_dscr); + device_remove_file(s, &dev_attr_dscr); + + if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) + device_remove_file(s, &dev_attr_pir); #endif /* CONFIG_PPC64 */ cacheinfo_cpu_offline(cpu); @@ -513,70 +522,70 @@ static struct notifier_block __cpuinitdata sysfs_cpu_nb = { static DEFINE_MUTEX(cpu_mutex); -int cpu_add_sysdev_attr(struct sysdev_attribute *attr) +int cpu_add_dev_attr(struct device_attribute *attr) { int cpu; mutex_lock(&cpu_mutex); for_each_possible_cpu(cpu) { - sysdev_create_file(get_cpu_sysdev(cpu), attr); + device_create_file(get_cpu_device(cpu), attr); } mutex_unlock(&cpu_mutex); return 0; } -EXPORT_SYMBOL_GPL(cpu_add_sysdev_attr); +EXPORT_SYMBOL_GPL(cpu_add_dev_attr); -int cpu_add_sysdev_attr_group(struct attribute_group *attrs) +int cpu_add_dev_attr_group(struct attribute_group *attrs) { int cpu; - struct sys_device *sysdev; + struct device *dev; int ret; mutex_lock(&cpu_mutex); for_each_possible_cpu(cpu) { - sysdev = get_cpu_sysdev(cpu); - ret = sysfs_create_group(&sysdev->kobj, attrs); + dev = get_cpu_device(cpu); + ret = sysfs_create_group(&dev->kobj, attrs); WARN_ON(ret != 0); } mutex_unlock(&cpu_mutex); return 0; } -EXPORT_SYMBOL_GPL(cpu_add_sysdev_attr_group); +EXPORT_SYMBOL_GPL(cpu_add_dev_attr_group); -void cpu_remove_sysdev_attr(struct sysdev_attribute *attr) +void cpu_remove_dev_attr(struct device_attribute *attr) { int cpu; mutex_lock(&cpu_mutex); for_each_possible_cpu(cpu) { - sysdev_remove_file(get_cpu_sysdev(cpu), attr); + device_remove_file(get_cpu_device(cpu), attr); } mutex_unlock(&cpu_mutex); } -EXPORT_SYMBOL_GPL(cpu_remove_sysdev_attr); +EXPORT_SYMBOL_GPL(cpu_remove_dev_attr); -void cpu_remove_sysdev_attr_group(struct attribute_group *attrs) +void cpu_remove_dev_attr_group(struct attribute_group *attrs) { int cpu; - struct sys_device *sysdev; + struct device *dev; mutex_lock(&cpu_mutex); for_each_possible_cpu(cpu) { - sysdev = get_cpu_sysdev(cpu); - sysfs_remove_group(&sysdev->kobj, attrs); + dev = get_cpu_device(cpu); + sysfs_remove_group(&dev->kobj, attrs); } mutex_unlock(&cpu_mutex); } -EXPORT_SYMBOL_GPL(cpu_remove_sysdev_attr_group); +EXPORT_SYMBOL_GPL(cpu_remove_dev_attr_group); /* NUMA stuff */ @@ -590,18 +599,18 @@ static void register_nodes(void) register_one_node(i); } -int sysfs_add_device_to_node(struct sys_device *dev, int nid) +int sysfs_add_device_to_node(struct device *dev, int nid) { struct node *node = &node_devices[nid]; - return sysfs_create_link(&node->sysdev.kobj, &dev->kobj, + return sysfs_create_link(&node->dev.kobj, &dev->kobj, kobject_name(&dev->kobj)); } EXPORT_SYMBOL_GPL(sysfs_add_device_to_node); -void sysfs_remove_device_from_node(struct sys_device *dev, int nid) +void sysfs_remove_device_from_node(struct device *dev, int nid) { struct node *node = &node_devices[nid]; - sysfs_remove_link(&node->sysdev.kobj, kobject_name(&dev->kobj)); + sysfs_remove_link(&node->dev.kobj, kobject_name(&dev->kobj)); } EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node); @@ -614,14 +623,14 @@ static void register_nodes(void) #endif /* Only valid if CPU is present. */ -static ssize_t show_physical_id(struct sys_device *dev, - struct sysdev_attribute *attr, char *buf) +static ssize_t show_physical_id(struct device *dev, + struct device_attribute *attr, char *buf) { - struct cpu *cpu = container_of(dev, struct cpu, sysdev); + struct cpu *cpu = container_of(dev, struct cpu, dev); - return sprintf(buf, "%d\n", get_hard_smp_processor_id(cpu->sysdev.id)); + return sprintf(buf, "%d\n", get_hard_smp_processor_id(cpu->dev.id)); } -static SYSDEV_ATTR(physical_id, 0444, show_physical_id, NULL); +static DEVICE_ATTR(physical_id, 0444, show_physical_id, NULL); static int __init topology_init(void) { @@ -646,7 +655,7 @@ static int __init topology_init(void) if (cpu_online(cpu) || c->hotpluggable) { register_cpu(c, cpu); - sysdev_create_file(&c->sysdev, &attr_physical_id); + device_create_file(&c->dev, &dev_attr_physical_id); } if (cpu_online(cpu)) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 03b29a6759ab..567dd7c3ac2a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -33,7 +33,7 @@ */ #include <linux/errno.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/param.h> @@ -86,8 +86,6 @@ static struct clocksource clocksource_rtc = { .rating = 400, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .mask = CLOCKSOURCE_MASK(64), - .shift = 22, - .mult = 0, /* To be filled in */ .read = rtc_read, }; @@ -97,8 +95,6 @@ static struct clocksource clocksource_timebase = { .rating = 400, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .mask = CLOCKSOURCE_MASK(64), - .shift = 22, - .mult = 0, /* To be filled in */ .read = timebase_read, }; @@ -110,22 +106,16 @@ static void decrementer_set_mode(enum clock_event_mode mode, struct clock_event_device *dev); static struct clock_event_device decrementer_clockevent = { - .name = "decrementer", - .rating = 200, - .shift = 0, /* To be filled in */ - .mult = 0, /* To be filled in */ - .irq = 0, - .set_next_event = decrementer_set_next_event, - .set_mode = decrementer_set_mode, - .features = CLOCK_EVT_FEAT_ONESHOT, + .name = "decrementer", + .rating = 200, + .irq = 0, + .set_next_event = decrementer_set_next_event, + .set_mode = decrementer_set_mode, + .features = CLOCK_EVT_FEAT_ONESHOT, }; -struct decrementer_clock { - struct clock_event_device event; - u64 next_tb; -}; - -static DEFINE_PER_CPU(struct decrementer_clock, decrementers); +DEFINE_PER_CPU(u64, decrementers_next_tb); +static DEFINE_PER_CPU(struct clock_event_device, decrementers); #ifdef CONFIG_PPC_ISERIES static unsigned long __initdata iSeries_recal_titan; @@ -168,13 +158,13 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* * Factors for converting from cputime_t (timebase ticks) to - * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds). + * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds). * These are all stored as 0.64 fixed-point binary fractions. */ u64 __cputime_jiffies_factor; EXPORT_SYMBOL(__cputime_jiffies_factor); -u64 __cputime_msec_factor; -EXPORT_SYMBOL(__cputime_msec_factor); +u64 __cputime_usec_factor; +EXPORT_SYMBOL(__cputime_usec_factor); u64 __cputime_sec_factor; EXPORT_SYMBOL(__cputime_sec_factor); u64 __cputime_clockt_factor; @@ -192,8 +182,8 @@ static void calc_cputime_factors(void) div128_by_32(HZ, 0, tb_ticks_per_sec, &res); __cputime_jiffies_factor = res.result_low; - div128_by_32(1000, 0, tb_ticks_per_sec, &res); - __cputime_msec_factor = res.result_low; + div128_by_32(1000000, 0, tb_ticks_per_sec, &res); + __cputime_usec_factor = res.result_low; div128_by_32(1, 0, tb_ticks_per_sec, &res); __cputime_sec_factor = res.result_low; div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res); @@ -441,7 +431,7 @@ EXPORT_SYMBOL(profile_pc); /* * This function recalibrates the timebase based on the 49-bit time-of-day * value in the Titan chip. The Titan is much more accurate than the value - * returned by the service processor for the timebase frequency. + * returned by the service processor for the timebase frequency. */ static int __init iSeries_tb_recal(void) @@ -576,9 +566,8 @@ void arch_irq_work_raise(void) void timer_interrupt(struct pt_regs * regs) { struct pt_regs *old_regs; - struct decrementer_clock *decrementer = &__get_cpu_var(decrementers); - struct clock_event_device *evt = &decrementer->event; - u64 now; + u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + struct clock_event_device *evt = &__get_cpu_var(decrementers); /* Ensure a positive value is written to the decrementer, or else * some CPUs will continue to take decrementer exceptions. @@ -613,16 +602,9 @@ void timer_interrupt(struct pt_regs * regs) get_lppaca()->int_dword.fields.decr_int = 0; #endif - now = get_tb_or_rtc(); - if (now >= decrementer->next_tb) { - decrementer->next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); - } else { - now = decrementer->next_tb - now; - if (now <= DECREMENTER_MAX) - set_dec((int)now); - } + *next_tb = ~(u64)0; + if (evt->event_handler) + evt->event_handler(evt); #ifdef CONFIG_PPC_ISERIES if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending()) @@ -650,9 +632,9 @@ static void generic_suspend_disable_irqs(void) * with suspending. */ - set_dec(0x7fffffff); + set_dec(DECREMENTER_MAX); local_irq_disable(); - set_dec(0x7fffffff); + set_dec(DECREMENTER_MAX); } static void generic_suspend_enable_irqs(void) @@ -824,9 +806,8 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, ++vdso_data->tb_update_count; smp_mb(); - /* XXX this assumes clock->shift == 22 */ - /* 4611686018 ~= 2^(20+64-22) / 1e9 */ - new_tb_to_xs = (u64) mult * 4611686018ULL; + /* 19342813113834067 ~= 2^(20+64) / 1e9 */ + new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift); new_stamp_xsec = (u64) wall_time->tv_nsec * XSEC_PER_SEC; do_div(new_stamp_xsec, 1000000000); new_stamp_xsec += (u64) wall_time->tv_sec * XSEC_PER_SEC; @@ -877,9 +858,7 @@ static void __init clocksource_init(void) else clock = &clocksource_timebase; - clock->mult = clocksource_hz2mult(tb_ticks_per_sec, clock->shift); - - if (clocksource_register(clock)) { + if (clocksource_register_hz(clock, tb_ticks_per_sec)) { printk(KERN_ERR "clocksource: %s is already registered\n", clock->name); return; @@ -892,7 +871,7 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { - __get_cpu_var(decrementers).next_tb = get_tb_or_rtc() + evt; + __get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt; set_dec(evt); return 0; } @@ -904,34 +883,9 @@ static void decrementer_set_mode(enum clock_event_mode mode, decrementer_set_next_event(DECREMENTER_MAX, dev); } -static inline uint64_t div_sc64(unsigned long ticks, unsigned long nsec, - int shift) -{ - uint64_t tmp = ((uint64_t)ticks) << shift; - - do_div(tmp, nsec); - return tmp; -} - -static void __init setup_clockevent_multiplier(unsigned long hz) -{ - u64 mult, shift = 32; - - while (1) { - mult = div_sc64(hz, NSEC_PER_SEC, shift); - if (mult && (mult >> 32UL) == 0UL) - break; - - shift--; - } - - decrementer_clockevent.shift = shift; - decrementer_clockevent.mult = mult; -} - static void register_decrementer_clockevent(int cpu) { - struct clock_event_device *dec = &per_cpu(decrementers, cpu).event; + struct clock_event_device *dec = &per_cpu(decrementers, cpu); *dec = decrementer_clockevent; dec->cpumask = cpumask_of(cpu); @@ -946,7 +900,8 @@ static void __init init_decrementer_clockevent(void) { int cpu = smp_processor_id(); - setup_clockevent_multiplier(ppc_tb_freq); + clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4); + decrementer_clockevent.max_delta_ns = clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent); decrementer_clockevent.min_delta_ns = @@ -1014,10 +969,10 @@ void __init time_init(void) boot_tb = get_tb_or_rtc(); /* If platform provided a timezone (pmac), we correct the time */ - if (timezone_offset) { + if (timezone_offset) { sys_tz.tz_minuteswest = -timezone_offset / 60; sys_tz.tz_dsttime = 0; - } + } vdso_data->tb_update_count = 0; vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index f19d9777d3c1..c091527efd89 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -98,18 +98,14 @@ static void pmac_backlight_unblank(void) static inline void pmac_backlight_unblank(void) { } #endif -int die(const char *str, struct pt_regs *regs, long err) +static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; +static int die_owner = -1; +static unsigned int die_nest_count; +static int die_counter; + +static unsigned __kprobes long oops_begin(struct pt_regs *regs) { - static struct { - raw_spinlock_t lock; - u32 lock_owner; - int lock_owner_depth; - } die = { - .lock = __RAW_SPIN_LOCK_UNLOCKED(die.lock), - .lock_owner = -1, - .lock_owner_depth = 0 - }; - static int die_counter; + int cpu; unsigned long flags; if (debugger(regs)) @@ -117,66 +113,109 @@ int die(const char *str, struct pt_regs *regs, long err) oops_enter(); - if (die.lock_owner != raw_smp_processor_id()) { - console_verbose(); - raw_spin_lock_irqsave(&die.lock, flags); - die.lock_owner = smp_processor_id(); - die.lock_owner_depth = 0; - bust_spinlocks(1); - if (machine_is(powermac)) - pmac_backlight_unblank(); - } else { - local_save_flags(flags); + /* racy, but better than risking deadlock. */ + raw_local_irq_save(flags); + cpu = smp_processor_id(); + if (!arch_spin_trylock(&die_lock)) { + if (cpu == die_owner) + /* nested oops. should stop eventually */; + else + arch_spin_lock(&die_lock); } + die_nest_count++; + die_owner = cpu; + console_verbose(); + bust_spinlocks(1); + if (machine_is(powermac)) + pmac_backlight_unblank(); + return flags; +} - if (++die.lock_owner_depth < 3) { - printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP NR_CPUS=%d ", NR_CPUS); -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC "); -#endif -#ifdef CONFIG_NUMA - printk("NUMA "); -#endif - printk("%s\n", ppc_md.name ? ppc_md.name : ""); +static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, + int signr) +{ + bust_spinlocks(0); + die_owner = -1; + add_taint(TAINT_DIE); + die_nest_count--; + oops_exit(); + printk("\n"); + if (!die_nest_count) + /* Nest count reaches zero, release the lock. */ + arch_spin_unlock(&die_lock); + raw_local_irq_restore(flags); - if (notify_die(DIE_OOPS, str, regs, err, 255, - SIGSEGV) == NOTIFY_STOP) - return 1; + /* + * A system reset (0x100) is a request to dump, so we always send + * it through the crashdump code. + */ + if (kexec_should_crash(current) || (TRAP(regs) == 0x100)) { + crash_kexec(regs); - print_modules(); - show_regs(regs); - } else { - printk("Recursive die() failure, output suppressed\n"); + /* + * We aren't the primary crash CPU. We need to send it + * to a holding pattern to avoid it ending up in the panic + * code. + */ + crash_kexec_secondary(regs); } - bust_spinlocks(0); - die.lock_owner = -1; - add_taint(TAINT_DIE); - raw_spin_unlock_irqrestore(&die.lock, flags); + if (!signr) + return; - if (kexec_should_crash(current) || - kexec_sr_activated(smp_processor_id())) - crash_kexec(regs); - crash_kexec_secondary(regs); + /* + * While our oops output is serialised by a spinlock, output + * from panic() called below can race and corrupt it. If we + * know we are going to panic, delay for 1 second so we have a + * chance to get clean backtraces from all CPUs that are oopsing. + */ + if (in_interrupt() || panic_on_oops || !current->pid || + is_global_init(current)) { + mdelay(MSEC_PER_SEC); + } if (in_interrupt()) panic("Fatal exception in interrupt"); - if (panic_on_oops) panic("Fatal exception"); + do_exit(signr); +} - oops_exit(); - do_exit(err); +static int __kprobes __die(const char *str, struct pt_regs *regs, long err) +{ + printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); +#endif +#ifdef CONFIG_SMP + printk("SMP NR_CPUS=%d ", NR_CPUS); +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC "); +#endif +#ifdef CONFIG_NUMA + printk("NUMA "); +#endif + printk("%s\n", ppc_md.name ? ppc_md.name : ""); + + if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP) + return 1; + + print_modules(); + show_regs(regs); return 0; } +void die(const char *str, struct pt_regs *regs, long err) +{ + unsigned long flags = oops_begin(regs); + + if (__die(str, regs, err)) + err = 0; + oops_end(flags, regs, err); +} + void user_single_step_siginfo(struct task_struct *tsk, struct pt_regs *regs, siginfo_t *info) { @@ -195,10 +234,11 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) "at %016lx nip %016lx lr %016lx code %x\n"; if (!user_mode(regs)) { - if (die("Exception in kernel mode", regs, signr)) - return; - } else if (show_unhandled_signals && - unhandled_signal(current, signr)) { + die("Exception in kernel mode", regs, signr); + return; + } + + if (show_unhandled_signals && unhandled_signal(current, signr)) { printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, current->comm, current->pid, signr, addr, regs->nip, regs->link, code); @@ -220,25 +260,8 @@ void system_reset_exception(struct pt_regs *regs) return; } -#ifdef CONFIG_KEXEC - cpumask_set_cpu(smp_processor_id(), &cpus_in_sr); -#endif - die("System Reset", regs, SIGABRT); - /* - * Some CPUs when released from the debugger will execute this path. - * These CPUs entered the debugger via a soft-reset. If the CPU was - * hung before entering the debugger it will return to the hung - * state when exiting this function. This causes a problem in - * kdump since the hung CPU(s) will not respond to the IPI sent - * from kdump. To prevent the problem we call crash_kexec_secondary() - * here. If a kdump had not been initiated or we exit the debugger - * with the "exit and recover" command (x) crash_kexec_secondary() - * will return after 5ms and the CPU returns to its previous state. - */ - crash_kexec_secondary(regs); - /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) panic("Unrecoverable System Reset"); @@ -457,7 +480,14 @@ int machine_check_e500mc(struct pt_regs *regs) if (reason & MCSR_DCPERR_MC) { printk("Data Cache Parity Error\n"); - recoverable = 0; + + /* + * In write shadow mode we auto-recover from the error, but it + * may still get logged and cause a machine check. We should + * only treat the non-write shadow case as non-recoverable. + */ + if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS)) + recoverable = 0; } if (reason & MCSR_L2MMU_MHIT) { @@ -1291,14 +1321,12 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) if (user_mode(regs)) { current->thread.dbcr0 &= ~DBCR0_IC; -#ifdef CONFIG_PPC_ADV_DEBUG_REGS if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0, current->thread.dbcr1)) regs->msr |= MSR_DE; else /* Make sure the IDM bit is off */ current->thread.dbcr0 &= ~DBCR0_IDM; -#endif } _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index faa82c1f3f68..57fa2c0a531c 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -67,6 +67,14 @@ void __init udbg_early_init(void) udbg_init_usbgecko(); #elif defined(CONFIG_PPC_EARLY_DEBUG_WSP) udbg_init_wsp(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC) + udbg_init_ehv_bc(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC) + udbg_init_ps3gelic(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_RAW) + udbg_init_debug_opal_raw(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_HVSI) + udbg_init_debug_opal_hvsi(); #endif #ifdef CONFIG_PPC_EARLY_DEBUG diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 142ab1008c3b..7d14bb697d40 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -9,7 +9,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/module.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/kernel.h> diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 1b695fdc362b..8b086299ba25 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -15,11 +15,12 @@ */ #include <linux/types.h> +#include <linux/stat.h> #include <linux/device.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/console.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/dma-mapping.h> #include <linux/kobject.h> @@ -605,15 +606,20 @@ static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask) return dma_iommu_ops.dma_supported(dev, mask); } -struct dma_map_ops vio_dma_mapping_ops = { - .alloc_coherent = vio_dma_iommu_alloc_coherent, - .free_coherent = vio_dma_iommu_free_coherent, - .map_sg = vio_dma_iommu_map_sg, - .unmap_sg = vio_dma_iommu_unmap_sg, - .map_page = vio_dma_iommu_map_page, - .unmap_page = vio_dma_iommu_unmap_page, - .dma_supported = vio_dma_iommu_dma_supported, +static u64 vio_dma_get_required_mask(struct device *dev) +{ + return dma_iommu_ops.get_required_mask(dev); +} +struct dma_map_ops vio_dma_mapping_ops = { + .alloc_coherent = vio_dma_iommu_alloc_coherent, + .free_coherent = vio_dma_iommu_free_coherent, + .map_sg = vio_dma_iommu_map_sg, + .unmap_sg = vio_dma_iommu_unmap_sg, + .map_page = vio_dma_iommu_map_page, + .unmap_page = vio_dma_iommu_unmap_page, + .dma_supported = vio_dma_iommu_dma_supported, + .get_required_mask = vio_dma_get_required_mask, }; /** @@ -1400,7 +1406,6 @@ static struct bus_type vio_bus_type = { .match = vio_bus_match, .probe = vio_bus_probe, .remove = vio_bus_remove, - .pm = GENERIC_SUBSYS_PM_OPS, }; /** diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 920276c0f6a1..710a54005dfb 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -170,7 +170,13 @@ SECTIONS } #ifdef CONFIG_RELOCATABLE . = ALIGN(8); - .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { *(.dynsym) } + .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) + { +#ifdef CONFIG_RELOCATABLE_PPC32 + __dynamic_symtab = .; +#endif + *(.dynsym) + } .dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) } .dynamic : AT(ADDR(.dynamic) - LOAD_OFFSET) { |