diff options
Diffstat (limited to 'arch/powerpc/kernel/setup_64.c')
| -rw-r--r-- | arch/powerpc/kernel/setup_64.c | 256 |
1 files changed, 206 insertions, 50 deletions
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2a178b0ebcd..ee082d77117 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -10,9 +10,9 @@ * 2 of the License, or (at your option) any later version. */ -#undef DEBUG +#define DEBUG -#include <linux/module.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/init.h> @@ -35,6 +35,9 @@ #include <linux/pci.h> #include <linux/lockdep.h> #include <linux/memblock.h> +#include <linux/hugetlb.h> +#include <linux/memory.h> + #include <asm/io.h> #include <asm/kdump.h> #include <asm/prom.h> @@ -50,7 +53,6 @@ #include <asm/btext.h> #include <asm/nvram.h> #include <asm/setup.h> -#include <asm/system.h> #include <asm/rtas.h> #include <asm/iommu.h> #include <asm/serial.h> @@ -62,8 +64,10 @@ #include <asm/udbg.h> #include <asm/kexec.h> #include <asm/mmu_context.h> - -#include "setup.h" +#include <asm/code-patching.h> +#include <asm/kvm_ppc.h> +#include <asm/hugetlb.h> +#include <asm/epapr_hcalls.h> #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) @@ -71,7 +75,7 @@ #define DBG(fmt...) #endif -int boot_cpuid = 0; +int spinning_secondaries; u64 ppc64_pft_size; /* Pick defaults since we might want to patch instructions @@ -93,6 +97,38 @@ int dcache_bsize; int icache_bsize; int ucache_bsize; +#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) +static void setup_tlb_core_data(void) +{ + int cpu; + + BUILD_BUG_ON(offsetof(struct tlb_core_data, lock) != 0); + + for_each_possible_cpu(cpu) { + int first = cpu_first_thread_sibling(cpu); + + paca[cpu].tcd_ptr = &paca[first].tcd; + + /* + * If we have threads, we need either tlbsrx. + * or e6500 tablewalk mode, or else TLB handlers + * will be racy and could produce duplicate entries. + */ + if (smt_enabled_at_boot >= 2 && + !mmu_has_feature(MMU_FTR_USE_TLBRSRV) && + book3e_htw_mode != PPC_HTW_E6500) { + /* Should we panic instead? */ + WARN_ONCE("%s: unsupported MMU configuration -- expect problems\n", + __func__); + } + } +} +#else +static void setup_tlb_core_data(void) +{ +} +#endif + #ifdef CONFIG_SMP static char *smt_enabled_cmdline; @@ -151,6 +187,28 @@ early_param("smt-enabled", early_smt_enabled); #define check_smt_enabled() #endif /* CONFIG_SMP */ +/** Fix up paca fields required for the boot cpu */ +static void fixup_boot_paca(void) +{ + /* The boot cpu is started */ + get_paca()->cpu_start = 1; + /* Allow percpu accesses to work until we setup percpu data */ + get_paca()->data_offset = 0; +} + +static void cpu_ready_for_interrupts(void) +{ + /* Set IR and DR in PACA MSR */ + get_paca()->kernel_msr = MSR_KERNEL; + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_ARCH_207S)) { + unsigned long lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); + } +} + /* * Early initialization entry point. This is called by head.S * with MMU translation disabled. We rely on the "feature" of @@ -172,6 +230,8 @@ early_param("smt-enabled", early_smt_enabled); void __init early_setup(unsigned long dt_ptr) { + static __initdata struct paca_struct boot_paca; + /* -------- printk is _NOT_ safe to use here ! ------- */ /* Identify CPU type */ @@ -180,6 +240,7 @@ void __init early_setup(unsigned long dt_ptr) /* Assume we're on cpu 0 for now. Don't write to the paca yet! */ initialise_paca(&boot_paca, 0); setup_paca(&boot_paca); + fixup_boot_paca(); /* Initialize lockdep early or else spinlocks will blow */ lockdep_init(); @@ -198,11 +259,11 @@ void __init early_setup(unsigned long dt_ptr) */ early_init_devtree(__va(dt_ptr)); + epapr_paravirt_early_init(); + /* Now we know the logical id of our boot cpu, setup the paca. */ setup_paca(&paca[boot_cpuid]); - - /* Fix up paca fields required for the boot cpu */ - get_paca()->cpu_start = 1; + fixup_boot_paca(); /* Probe the machine type */ probe_machine(); @@ -214,7 +275,36 @@ void __init early_setup(unsigned long dt_ptr) /* Initialize the hash table or TLB handling */ early_init_mmu(); + /* + * At this point, we can let interrupts switch to virtual mode + * (the MMU has been setup), so adjust the MSR in the PACA to + * have IR and DR set and enable AIL if it exists + */ + cpu_ready_for_interrupts(); + + /* Reserve large chunks of memory for use by CMA for KVM */ + kvm_cma_reserve(); + + /* + * 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"); + +#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX + /* + * This needs to be done *last* (after the above DBG() even) + * + * Right after we return from this function, we turn on the MMU + * which means the real-mode access trick that btext does will + * no longer work, it needs to switch to using a real MMU + * mapping. This call will ensure that it does + */ + btext_map(); +#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */ } #ifdef CONFIG_SMP @@ -225,6 +315,13 @@ void early_setup_secondary(void) /* Initialize the hash table or TLB handling */ early_init_mmu_secondary(); + + /* + * At this point, we can let interrupts switch to virtual mode + * (the MMU has been setup), so adjust the MSR in the PACA to + * have IR and DR set. + */ + cpu_ready_for_interrupts(); } #endif /* CONFIG_SMP */ @@ -233,6 +330,7 @@ void early_setup_secondary(void) void smp_release_cpus(void) { unsigned long *ptr; + int i; DBG(" -> smp_release_cpus()\n"); @@ -244,8 +342,17 @@ void smp_release_cpus(void) ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop - PHYSICAL_START); - *ptr = __pa(generic_secondary_smp_init); - mb(); + *ptr = ppc_function_entry(generic_secondary_smp_init); + + /* And wait a bit for them to catch up */ + for (i = 0; i < 100000; i++) { + mb(); + HMT_low(); + if (spinning_secondaries == 0) + break; + udelay(1); + } + DBG("spinning_secondaries = %d\n", spinning_secondaries); DBG(" <- smp_release_cpus()\n"); } @@ -265,29 +372,32 @@ 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 ) { - const u32 *sizep, *lsizep; + if (num_cpus == 1) { + const __be32 *sizep, *lsizep; u32 size, lsize; size = 0; lsize = cur_cpu_spec->dcache_bsize; sizep = of_get_property(np, "d-cache-size", NULL); if (sizep != NULL) - size = *sizep; - lsizep = of_get_property(np, "d-cache-block-size", NULL); + size = be32_to_cpu(*sizep); + 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) + lsize = be32_to_cpu(*lsizep); + if (sizep == NULL || lsizep == NULL) DBG("Argh, can't find dcache properties ! " "sizep: %p, lsizep: %p\n", sizep, lsizep); @@ -300,13 +410,16 @@ static void __init initialize_cache_info(void) lsize = cur_cpu_spec->icache_bsize; sizep = of_get_property(np, "i-cache-size", NULL); if (sizep != NULL) - size = *sizep; - lsizep = of_get_property(np, "i-cache-block-size", NULL); + size = be32_to_cpu(*sizep); + 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) + lsize = be32_to_cpu(*lsizep); + if (sizep == NULL || lsizep == NULL) DBG("Argh, can't find icache properties ! " "sizep: %p, lsizep: %p\n", sizep, lsizep); @@ -340,6 +453,7 @@ 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 @@ -391,6 +505,7 @@ void __init setup_system(void) smp_setup_cpu_maps(); check_smt_enabled(); + setup_tlb_core_data(); #ifdef CONFIG_SMP /* Release secondary cpus out of their spinloops at 0x60 now that @@ -423,22 +538,35 @@ void __init setup_system(void) DBG(" <- setup_system()\n"); } -static u64 slb0_limit(void) +/* This returns the limit below which memory accesses to the linear + * mapping are guarnateed not to cause a TLB or SLB miss. This is + * used to allocate interrupt or emergency stacks for which our + * exception entry path doesn't deal with being interrupted. + */ +static u64 safe_stack_limit(void) { - if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) { +#ifdef CONFIG_PPC_BOOK3E + /* Freescale BookE bolts the entire linear mapping */ + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) + return linear_map_top; + /* Other BookE, we assume the first GB is bolted */ + return 1ul << 30; +#else + /* BookS, the first segment is bolted */ + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) return 1UL << SID_SHIFT_1T; - } return 1UL << SID_SHIFT; +#endif } static void __init irqstack_early_init(void) { - u64 limit = slb0_limit(); + u64 limit = safe_stack_limit(); unsigned int i; /* - * interrupt stacks must be under 256MB, we cannot afford to take - * SLB misses on them. + * Interrupt stacks must be in the first segment since we + * cannot afford to take SLB misses on them. */ for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) @@ -454,15 +582,24 @@ static void __init irqstack_early_init(void) static void __init exc_lvl_early_init(void) { unsigned int i; + unsigned long sp; for_each_possible_cpu(i) { - critirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); - dbgirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); - mcheckirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); + critirq_ctx[i] = (struct thread_info *)__va(sp); + paca[i].crit_kstack = __va(sp + THREAD_SIZE); + + sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); + dbgirq_ctx[i] = (struct thread_info *)__va(sp); + paca[i].dbg_kstack = __va(sp + THREAD_SIZE); + + sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); + mcheckirq_ctx[i] = (struct thread_info *)__va(sp); + paca[i].mc_kstack = __va(sp + THREAD_SIZE); } + + if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) + patch_exception(0x040, exc_debug_debug_book3e); } #else #define exc_lvl_early_init() @@ -470,7 +607,8 @@ static void __init exc_lvl_early_init(void) /* * Stack space used when we detect a bad kernel stack pointer, and - * early in SMP boots before relocation is enabled. + * early in SMP boots before relocation is enabled. Exclusive emergency + * stack for machine checks. */ static void __init emergency_stack_init(void) { @@ -486,20 +624,26 @@ static void __init emergency_stack_init(void) * bringup, we need to get at them in real mode. This means they * must also be within the RMO region. */ - limit = min(slb0_limit(), ppc64_rma_size); + limit = min(safe_stack_limit(), ppc64_rma_size); for_each_possible_cpu(i) { unsigned long sp; sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); sp += THREAD_SIZE; paca[i].emergency_sp = __va(sp); + +#ifdef CONFIG_PPC_BOOK3S_64 + /* emergency stack for machine check exception handling. */ + sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); + sp += THREAD_SIZE; + paca[i].mc_emergency_sp = __va(sp); +#endif } } /* - * Called into from start_kernel, after lock_kernel has been called. - * Initializes bootmem, which is unsed to manage page allocation until - * mem_init is called. + * Called into from start_kernel this initializes bootmem, which is used + * to manage page allocation until mem_init is called. */ void __init setup_arch(char **cmdline_p) { @@ -515,9 +659,6 @@ void __init setup_arch(char **cmdline_p) dcache_bsize = ppc64_caches.dline_size; icache_bsize = ppc64_caches.iline_size; - /* reboot on panic */ - panic_timeout = 180; - if (ppc_md.panic) setup_panic(); @@ -525,7 +666,9 @@ void __init setup_arch(char **cmdline_p) init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; init_mm.brk = klimit; - +#ifdef CONFIG_PPC_64K_PAGES + init_mm.context.pte_frag = NULL; +#endif irqstack_early_init(); exc_lvl_early_init(); emergency_stack_init(); @@ -549,6 +692,11 @@ void __init setup_arch(char **cmdline_p) /* Initialize the MMU context management stuff */ mmu_context_init(); + /* Interrupt code needs to be 64K-aligned */ + if ((unsigned long)_stext & 0xffff) + panic("Kernelbase not 64K-aligned (0x%lx)!\n", + (unsigned long)_stext); + ppc64_boot_msg(0x15, "Setup Done"); } @@ -633,9 +781,17 @@ void __init setup_per_cpu_areas(void) } #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +unsigned long memory_block_size_bytes(void) +{ + if (ppc_md.memory_block_size) + return ppc_md.memory_block_size(); + + return MIN_MEMORY_BLOCK_SIZE; +} +#endif -#ifdef CONFIG_PPC_INDIRECT_IO +#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO) struct ppc_pci_io ppc_pci_io; EXPORT_SYMBOL(ppc_pci_io); -#endif /* CONFIG_PPC_INDIRECT_IO */ - +#endif |