diff options
Diffstat (limited to 'arch/powerpc/mm/mem.c')
| -rw-r--r-- | arch/powerpc/mm/mem.c | 682 |
1 files changed, 294 insertions, 388 deletions
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 7f4bea162026..3ddbfdbfa941 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * PowerPC version * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) @@ -9,251 +10,218 @@ * * Derived from "arch/i386/mm/init.c" * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds - * - * 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 <linux/export.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/string.h> -#include <linux/gfp.h> -#include <linux/types.h> -#include <linux/mm.h> -#include <linux/stddef.h> -#include <linux/init.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/highmem.h> -#include <linux/initrd.h> -#include <linux/pagemap.h> #include <linux/suspend.h> -#include <linux/memblock.h> -#include <linux/hugetlb.h> -#include <linux/slab.h> - -#include <asm/pgalloc.h> -#include <asm/prom.h> -#include <asm/io.h> -#include <asm/mmu_context.h> -#include <asm/pgtable.h> -#include <asm/mmu.h> -#include <asm/smp.h> -#include <asm/machdep.h> -#include <asm/btext.h> -#include <asm/tlb.h> -#include <asm/sections.h> -#include <asm/sparsemem.h> -#include <asm/vdso.h> -#include <asm/fixmap.h> +#include <linux/dma-direct.h> +#include <linux/execmem.h> +#include <linux/vmalloc.h> + #include <asm/swiotlb.h> +#include <asm/machdep.h> #include <asm/rtas.h> +#include <asm/kasan.h> +#include <asm/svm.h> +#include <asm/mmzone.h> +#include <asm/ftrace.h> +#include <asm/text-patching.h> +#include <asm/setup.h> +#include <asm/fixmap.h> -#include "mmu_decl.h" - -#ifndef CPU_FTR_COHERENT_ICACHE -#define CPU_FTR_COHERENT_ICACHE 0 /* XXX for now */ -#define CPU_FTR_NOEXECUTE 0 -#endif - -int init_bootmem_done; -int mem_init_done; -unsigned long long memory_limit; - -#ifdef CONFIG_HIGHMEM -pte_t *kmap_pte; -EXPORT_SYMBOL(kmap_pte); -pgprot_t kmap_prot; -EXPORT_SYMBOL(kmap_prot); - -static inline pte_t *virt_to_kpte(unsigned long vaddr) -{ - return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), - vaddr), vaddr), vaddr); -} -#endif +#include <mm/mmu_decl.h> -int page_is_ram(unsigned long pfn) -{ -#ifndef CONFIG_PPC64 /* XXX for now */ - return pfn < max_pfn; -#else - unsigned long paddr = (pfn << PAGE_SHIFT); - struct memblock_region *reg; +unsigned long long memory_limit __initdata; - for_each_memblock(memory, reg) - if (paddr >= reg->base && paddr < (reg->base + reg->size)) - return 1; - return 0; -#endif -} +unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; +EXPORT_SYMBOL(empty_zero_page); -pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot) +pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size, + pgprot_t vma_prot) { if (ppc_md.phys_mem_access_prot) - return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot); + return ppc_md.phys_mem_access_prot(pfn, size, vma_prot); if (!page_is_ram(pfn)) vma_prot = pgprot_noncached(vma_prot); return vma_prot; } -EXPORT_SYMBOL(phys_mem_access_prot); +EXPORT_SYMBOL(__phys_mem_access_prot); #ifdef CONFIG_MEMORY_HOTPLUG +static DEFINE_MUTEX(linear_mapping_mutex); #ifdef CONFIG_NUMA int memory_add_physaddr_to_nid(u64 start) { return hot_add_scn_to_nid(start); } +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif -int arch_add_memory(int nid, u64 start, u64 size) +int __weak create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot) { - struct pglist_data *pgdata; - struct zone *zone; - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long nr_pages = size >> PAGE_SHIFT; - - pgdata = NODE_DATA(nid); + return -ENODEV; +} - start = (unsigned long)__va(start); - if (create_section_mapping(start, start + size)) - return -EINVAL; +int __weak remove_section_mapping(unsigned long start, unsigned long end) +{ + return -ENODEV; +} - /* this should work for most non-highmem platforms */ - zone = pgdata->node_zones; +int __ref arch_create_linear_mapping(int nid, u64 start, u64 size, + struct mhp_params *params) +{ + int rc; - return __add_pages(nid, zone, start_pfn, nr_pages); + start = (unsigned long)__va(start); + mutex_lock(&linear_mapping_mutex); + rc = create_section_mapping(start, start + size, nid, + params->pgprot); + mutex_unlock(&linear_mapping_mutex); + if (rc) { + pr_warn("Unable to create linear mapping for 0x%llx..0x%llx: %d\n", + start, start + size, rc); + return -EFAULT; + } + return 0; } -#ifdef CONFIG_MEMORY_HOTREMOVE -int arch_remove_memory(u64 start, u64 size) +void __ref arch_remove_linear_mapping(u64 start, u64 size) { - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; + int ret; - zone = page_zone(pfn_to_page(start_pfn)); - return __remove_pages(zone, start_pfn, nr_pages); + /* Remove htab bolted mappings for this section of memory */ + start = (unsigned long)__va(start); + + mutex_lock(&linear_mapping_mutex); + ret = remove_section_mapping(start, start + size); + mutex_unlock(&linear_mapping_mutex); + if (ret) + pr_warn("Unable to remove linear mapping for 0x%llx..0x%llx: %d\n", + start, start + size, ret); + + /* Ensure all vmalloc mappings are flushed in case they also + * hit that section of memory + */ + vm_unmap_aliases(); } -#endif -#endif /* CONFIG_MEMORY_HOTPLUG */ /* - * walk_memory_resource() needs to make sure there is no holes in a given - * memory range. PPC64 does not maintain the memory layout in /proc/iomem. - * Instead it maintains it in memblock.memory structures. Walk through the - * memory regions, find holes and callback for contiguous regions. + * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need + * updating. */ -int -walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, - void *arg, int (*func)(unsigned long, unsigned long, void *)) +static void update_end_of_memory_vars(u64 start, u64 size) { - struct memblock_region *reg; - unsigned long end_pfn = start_pfn + nr_pages; - unsigned long tstart, tend; - int ret = -1; - - for_each_memblock(memory, reg) { - tstart = max(start_pfn, memblock_region_memory_base_pfn(reg)); - tend = min(end_pfn, memblock_region_memory_end_pfn(reg)); - if (tstart >= tend) - continue; - ret = (*func)(tstart, tend - tstart, arg); - if (ret) - break; + unsigned long end_pfn = PFN_UP(start + size); + + if (end_pfn > max_pfn) { + max_pfn = end_pfn; + max_low_pfn = end_pfn; + high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; } +} + +int __ref add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, + struct mhp_params *params) +{ + int ret; + + ret = __add_pages(nid, start_pfn, nr_pages, params); + if (ret) + return ret; + + /* update max_pfn, max_low_pfn and high_memory */ + update_end_of_memory_vars(start_pfn << PAGE_SHIFT, + nr_pages << PAGE_SHIFT); + return ret; } -EXPORT_SYMBOL_GPL(walk_system_ram_range); -/* - * Initialize the bootmem system and give it all the memory we - * have available. If we are using highmem, we only put the - * lowmem into the bootmem system. - */ -#ifndef CONFIG_NEED_MULTIPLE_NODES -void __init do_init_bootmem(void) +int __ref arch_add_memory(int nid, u64 start, u64 size, + struct mhp_params *params) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + int rc; + + rc = arch_create_linear_mapping(nid, start, size, params); + if (rc) + return rc; + rc = add_pages(nid, start_pfn, nr_pages, params); + if (rc) + arch_remove_linear_mapping(start, size); + return rc; +} + +void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { - unsigned long start, bootmap_pages; - unsigned long total_pages; - struct memblock_region *reg; - int boot_mapsize; + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + + __remove_pages(start_pfn, nr_pages, altmap); + arch_remove_linear_mapping(start, size); +} +#endif +#ifndef CONFIG_NUMA +void __init mem_topology_setup(void) +{ max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; - total_pages = (memblock_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT; + min_low_pfn = MEMORY_START >> PAGE_SHIFT; #ifdef CONFIG_HIGHMEM - total_pages = total_lowmem >> PAGE_SHIFT; max_low_pfn = lowmem_end_addr >> PAGE_SHIFT; #endif - /* - * Find an area to use for the bootmem bitmap. Calculate the size of - * bitmap required as (Total Memory) / PAGE_SIZE / BITS_PER_BYTE. - * Add 1 additional page in case the address isn't page-aligned. - */ - bootmap_pages = bootmem_bootmap_pages(total_pages); - - start = memblock_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE); - - min_low_pfn = MEMORY_START >> PAGE_SHIFT; - boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn); - /* Place all memblock_regions in the same node and merge contiguous * memblock_regions */ - memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); - - /* Add all physical memory to the bootmem map, mark each area - * present. - */ -#ifdef CONFIG_HIGHMEM - free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT); - - /* reserve the sections we're already using */ - for_each_memblock(reserved, reg) { - unsigned long top = reg->base + reg->size - 1; - if (top < lowmem_end_addr) - reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT); - else if (reg->base < lowmem_end_addr) { - unsigned long trunc_size = lowmem_end_addr - reg->base; - reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT); - } - } -#else - free_bootmem_with_active_regions(0, max_pfn); - - /* reserve the sections we're already using */ - for_each_memblock(reserved, reg) - reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT); -#endif - /* XXX need to clip this if using highmem? */ - sparse_memory_present_with_active_regions(0); + memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); +} - init_bootmem_done = 1; +void __init initmem_init(void) +{ + sparse_init(); } /* mark pages that don't exist as nosave */ static int __init mark_nonram_nosave(void) { - struct memblock_region *reg, *prev = NULL; - - for_each_memblock(memory, reg) { - if (prev && - memblock_region_memory_end_pfn(prev) < memblock_region_memory_base_pfn(reg)) - register_nosave_region(memblock_region_memory_end_pfn(prev), - memblock_region_memory_base_pfn(reg)); - prev = reg; + unsigned long spfn, epfn, prev = 0; + int i; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &spfn, &epfn, NULL) { + if (prev && prev < spfn) + register_nosave_region(prev, spfn); + + prev = epfn; } + return 0; } +#else /* CONFIG_NUMA */ +static int __init mark_nonram_nosave(void) +{ + return 0; +} +#endif + +/* + * Zones usage: + * + * We setup ZONE_DMA to be 31-bits on all platforms and ZONE_NORMAL to be + * everything else. GFP_DMA32 page allocations automatically fall back to + * ZONE_DMA. + * + * By using 31-bit unconditionally, we can exploit zone_dma_limit to inform the + * generic DMA mapping code. 32-bit only devices (if not handled by an IOMMU + * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by + * ZONE_DMA. + */ +static unsigned long max_zone_pfns[MAX_NR_ZONES]; /* * paging_init() sets up the page tables - in fact we've already done this. @@ -262,66 +230,72 @@ void __init paging_init(void) { unsigned long long total_ram = memblock_phys_mem_size(); phys_addr_t top_of_ram = memblock_end_of_DRAM(); - unsigned long max_zone_pfns[MAX_NR_ZONES]; + int zone_dma_bits; -#ifdef CONFIG_PPC32 - unsigned long v = __fix_to_virt(__end_of_fixed_addresses - 1); - unsigned long end = __fix_to_virt(FIX_HOLE); +#ifdef CONFIG_HIGHMEM + unsigned long v = __fix_to_virt(FIX_KMAP_END); + unsigned long end = __fix_to_virt(FIX_KMAP_BEGIN); for (; v < end; v += PAGE_SIZE) - map_page(v, 0, 0); /* XXX gross */ -#endif + map_kernel_page(v, 0, __pgprot(0)); /* XXX gross */ -#ifdef CONFIG_HIGHMEM - map_page(PKMAP_BASE, 0, 0); /* XXX gross */ + map_kernel_page(PKMAP_BASE, 0, __pgprot(0)); /* XXX gross */ pkmap_page_table = virt_to_kpte(PKMAP_BASE); - - kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN)); - kmap_prot = PAGE_KERNEL; #endif /* CONFIG_HIGHMEM */ printk(KERN_DEBUG "Top of RAM: 0x%llx, Total RAM: 0x%llx\n", (unsigned long long)top_of_ram, total_ram); printk(KERN_DEBUG "Memory hole size: %ldMB\n", (long int)((top_of_ram - total_ram) >> 20)); - memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + + /* + * Allow 30-bit DMA for very limited Broadcom wifi chips on many + * powerbooks. + */ + if (IS_ENABLED(CONFIG_PPC32)) + zone_dma_bits = 30; + else + zone_dma_bits = 31; + + zone_dma_limit = DMA_BIT_MASK(zone_dma_bits); + +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = min(max_low_pfn, + 1UL << (zone_dma_bits - PAGE_SHIFT)); +#endif + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM - max_zone_pfns[ZONE_DMA] = lowmem_end_addr >> PAGE_SHIFT; - max_zone_pfns[ZONE_HIGHMEM] = top_of_ram >> PAGE_SHIFT; -#else - max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT; + max_zone_pfns[ZONE_HIGHMEM] = max_pfn; #endif - free_area_init_nodes(max_zone_pfns); + + free_area_init(max_zone_pfns); mark_nonram_nosave(); } -#endif /* ! CONFIG_NEED_MULTIPLE_NODES */ -void __init mem_init(void) +void __init arch_mm_preinit(void) { + /* + * book3s is limited to 16 page sizes due to encoding this in + * a 4-bit field for slices. + */ + BUILD_BUG_ON(MMU_PAGE_COUNT > 16); + #ifdef CONFIG_SWIOTLB - swiotlb_init(0); + /* + * Some platforms (e.g. 85xx) limit DMA-able memory way below + * 4G. We force memblock to bottom-up mode to ensure that the + * memory allocated in swiotlb_init() is DMA-able. + * As it's the last memblock allocation, no need to reset it + * back to to-down. + */ + memblock_set_bottom_up(true); + swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags); #endif - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_pfn); - free_all_bootmem(); - -#ifdef CONFIG_HIGHMEM - { - unsigned long pfn, highmem_mapnr; - - highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT; - for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) { - phys_addr_t paddr = (phys_addr_t)pfn << PAGE_SHIFT; - struct page *page = pfn_to_page(pfn); - if (!memblock_is_reserved(paddr)) - free_highmem_page(page); - } - } -#endif /* CONFIG_HIGHMEM */ + kasan_late_init(); -#if defined(CONFIG_PPC_FSL_BOOK3E) && !defined(CONFIG_SMP) +#if defined(CONFIG_PPC_E500) && !defined(CONFIG_SMP) /* * If smp is enabled, next_tlbcam_idx is initialized in the cpu up * functions.... do it here for the non-smp case. @@ -329,193 +303,42 @@ void __init mem_init(void) per_cpu(next_tlbcam_idx, smp_processor_id()) = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1; #endif - - mem_init_print_info(NULL); -#ifdef CONFIG_PPC32 - pr_info("Kernel virtual memory layout:\n"); - pr_info(" * 0x%08lx..0x%08lx : fixmap\n", FIXADDR_START, FIXADDR_TOP); -#ifdef CONFIG_HIGHMEM - pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n", - PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP)); -#endif /* CONFIG_HIGHMEM */ -#ifdef CONFIG_NOT_COHERENT_CACHE - pr_info(" * 0x%08lx..0x%08lx : consistent mem\n", - IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE); -#endif /* CONFIG_NOT_COHERENT_CACHE */ - pr_info(" * 0x%08lx..0x%08lx : early ioremap\n", - ioremap_bot, IOREMAP_TOP); - pr_info(" * 0x%08lx..0x%08lx : vmalloc & ioremap\n", - VMALLOC_START, VMALLOC_END); -#endif /* CONFIG_PPC32 */ - - mem_init_done = 1; } void free_initmem(void) { ppc_md.progress = ppc_printk_progress; + mark_initmem_nx(); free_initmem_default(POISON_FREE_INITMEM); -} - -#ifdef CONFIG_BLK_DEV_INITRD -void __init free_initrd_mem(unsigned long start, unsigned long end) -{ - free_reserved_area((void *)start, (void *)end, -1, "initrd"); -} -#endif - -/* - * This is called when a page has been modified by the kernel. - * It just marks the page as not i-cache clean. We do the i-cache - * flush later when the page is given to a user process, if necessary. - */ -void flush_dcache_page(struct page *page) -{ - if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) - return; - /* avoid an atomic op if possible */ - if (test_bit(PG_arch_1, &page->flags)) - clear_bit(PG_arch_1, &page->flags); -} -EXPORT_SYMBOL(flush_dcache_page); - -void flush_dcache_icache_page(struct page *page) -{ -#ifdef CONFIG_HUGETLB_PAGE - if (PageCompound(page)) { - flush_dcache_icache_hugepage(page); - return; - } -#endif -#ifdef CONFIG_BOOKE - { - void *start = kmap_atomic(page); - __flush_dcache_icache(start); - kunmap_atomic(start); - } -#elif defined(CONFIG_8xx) || defined(CONFIG_PPC64) - /* On 8xx there is no need to kmap since highmem is not supported */ - __flush_dcache_icache(page_address(page)); -#else - __flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT); -#endif -} -EXPORT_SYMBOL(flush_dcache_icache_page); - -void clear_user_page(void *page, unsigned long vaddr, struct page *pg) -{ - clear_page(page); - - /* - * We shouldn't have to do this, but some versions of glibc - * require it (ld.so assumes zero filled pages are icache clean) - * - Anton - */ - flush_dcache_page(pg); -} -EXPORT_SYMBOL(clear_user_page); - -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg) -{ - copy_page(vto, vfrom); - - /* - * We should be able to use the following optimisation, however - * there are two problems. - * Firstly a bug in some versions of binutils meant PLT sections - * were not marked executable. - * Secondly the first word in the GOT section is blrl, used - * to establish the GOT address. Until recently the GOT was - * not marked executable. - * - Anton - */ -#if 0 - if (!vma->vm_file && ((vma->vm_flags & VM_EXEC) == 0)) - return; -#endif - - flush_dcache_page(pg); -} - -void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, - unsigned long addr, int len) -{ - unsigned long maddr; - - maddr = (unsigned long) kmap(page) + (addr & ~PAGE_MASK); - flush_icache_range(maddr, maddr + len); - kunmap(page); -} -EXPORT_SYMBOL(flush_icache_user_range); - -/* - * This is called at the end of handling a user page fault, when the - * fault has been handled by updating a PTE in the linux page tables. - * We use it to preload an HPTE into the hash table corresponding to - * the updated linux PTE. - * - * This must always be called with the pte lock held. - */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep) -{ -#ifdef CONFIG_PPC_STD_MMU - /* - * We don't need to worry about _PAGE_PRESENT here because we are - * called with either mm->page_table_lock held or ptl lock held - */ - unsigned long access = 0, trap; - - /* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */ - if (!pte_young(*ptep) || address >= TASK_SIZE) - return; - - /* We try to figure out if we are coming from an instruction - * access fault and pass that down to __hash_page so we avoid - * double-faulting on execution of fresh text. We have to test - * for regs NULL since init will get here first thing at boot - * - * We also avoid filling the hash if not coming from a fault - */ - if (current->thread.regs == NULL) - return; - trap = TRAP(current->thread.regs); - if (trap == 0x400) - access |= _PAGE_EXEC; - else if (trap != 0x300) - return; - hash_preload(vma->vm_mm, address, access, trap); -#endif /* CONFIG_PPC_STD_MMU */ -#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \ - && defined(CONFIG_HUGETLB_PAGE) - if (is_vm_hugetlb_page(vma)) - book3e_hugetlb_preload(vma, address, *ptep); -#endif + ftrace_free_init_tramp(); } /* * System memory should not be in /proc/iomem but various tools expect it * (eg kdump). */ -static int add_system_ram_resources(void) +static int __init add_system_ram_resources(void) { - struct memblock_region *reg; + phys_addr_t start, end; + u64 i; - for_each_memblock(memory, reg) { + for_each_mem_range(i, &start, &end) { struct resource *res; - unsigned long base = reg->base; - unsigned long size = reg->size; res = kzalloc(sizeof(struct resource), GFP_KERNEL); WARN_ON(!res); if (res) { res->name = "System RAM"; - res->start = base; - res->end = base + size - 1; - res->flags = IORESOURCE_MEM; - WARN_ON(request_resource(&iomem_resource, res) < 0); + res->start = start; + /* + * In memblock, end points to the first byte after + * the range while in resourses, end points to the + * last byte in the range. + */ + res->end = end - 1; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + WARN_ON(insert_resource(&iomem_resource, res) < 0); } } @@ -533,12 +356,95 @@ subsys_initcall(add_system_ram_resources); */ int devmem_is_allowed(unsigned long pfn) { - if (iomem_is_exclusive(pfn << PAGE_SHIFT)) + if (page_is_rtas_user_buf(pfn)) + return 1; + if (iomem_is_exclusive(PFN_PHYS(pfn))) return 0; if (!page_is_ram(pfn)) return 1; - if (page_is_rtas_user_buf(pfn)) - return 1; return 0; } #endif /* CONFIG_STRICT_DEVMEM */ + +/* + * This is defined in kernel/resource.c but only powerpc needs to export it, for + * the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed. + */ +EXPORT_SYMBOL_GPL(walk_system_ram_range); + +#ifdef CONFIG_EXECMEM +static struct execmem_info execmem_info __ro_after_init; + +#if defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_BOOK3S_603) +static void prealloc_execmem_pgtable(void) +{ + unsigned long va; + + for (va = ALIGN_DOWN(MODULES_VADDR, PGDIR_SIZE); va < MODULES_END; va += PGDIR_SIZE) + pte_alloc_kernel(pmd_off_k(va), va); +} +#else +static void prealloc_execmem_pgtable(void) { } +#endif + +struct execmem_info __init *execmem_arch_setup(void) +{ + pgprot_t kprobes_prot = strict_module_rwx_enabled() ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC; + pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC; + unsigned long fallback_start = 0, fallback_end = 0; + unsigned long start, end; + + /* + * BOOK3S_32 and 8xx define MODULES_VADDR for text allocations and + * allow allocating data in the entire vmalloc space + */ +#ifdef MODULES_VADDR + unsigned long limit = (unsigned long)_etext - SZ_32M; + + BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR); + + /* First try within 32M limit from _etext to avoid branch trampolines */ + if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit) { + start = limit; + fallback_start = MODULES_VADDR; + fallback_end = MODULES_END; + } else { + start = MODULES_VADDR; + } + + end = MODULES_END; +#else + start = VMALLOC_START; + end = VMALLOC_END; +#endif + + prealloc_execmem_pgtable(); + + execmem_info = (struct execmem_info){ + .ranges = { + [EXECMEM_DEFAULT] = { + .start = start, + .end = end, + .pgprot = prot, + .alignment = 1, + .fallback_start = fallback_start, + .fallback_end = fallback_end, + }, + [EXECMEM_KPROBES] = { + .start = VMALLOC_START, + .end = VMALLOC_END, + .pgprot = kprobes_prot, + .alignment = 1, + }, + [EXECMEM_MODULE_DATA] = { + .start = VMALLOC_START, + .end = VMALLOC_END, + .pgprot = PAGE_KERNEL, + .alignment = 1, + }, + }, + }; + + return &execmem_info; +} +#endif /* CONFIG_EXECMEM */ |
