diff options
Diffstat (limited to 'arch/arm64/mm/init.c')
| -rw-r--r-- | arch/arm64/mm/init.c | 404 |
1 files changed, 227 insertions, 177 deletions
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index b9af30be813e..0c8c35dd645e 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -16,6 +16,7 @@ #include <linux/nodemask.h> #include <linux/initrd.h> #include <linux/gfp.h> +#include <linux/math.h> #include <linux/memblock.h> #include <linux/sort.h> #include <linux/of.h> @@ -31,6 +32,7 @@ #include <linux/hugetlb.h> #include <linux/acpi_iort.h> #include <linux/kmemleak.h> +#include <linux/execmem.h> #include <asm/boot.h> #include <asm/fixmap.h> @@ -39,6 +41,7 @@ #include <asm/kvm_host.h> #include <asm/memory.h> #include <asm/numa.h> +#include <asm/rsi.h> #include <asm/sections.h> #include <asm/setup.h> #include <linux/sizes.h> @@ -61,167 +64,81 @@ EXPORT_SYMBOL(memstart_addr); * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, * otherwise it is empty. - * - * Memory reservation for crash kernel either done early or deferred - * depending on DMA memory zones configs (ZONE_DMA) -- - * - * In absence of ZONE_DMA configs arm64_dma_phys_limit initialized - * here instead of max_zone_phys(). This lets early reservation of - * crash kernel memory which has a dependency on arm64_dma_phys_limit. - * Reserving memory early for crash kernel allows linear creation of block - * mappings (greater than page-granularity) for all the memory bank rangs. - * In this scheme a comparatively quicker boot is observed. - * - * If ZONE_DMA configs are defined, crash kernel memory reservation - * is delayed until DMA zone memory range size initialization performed in - * zone_sizes_init(). The defer is necessary to steer clear of DMA zone - * memory range to avoid overlap allocation. So crash kernel memory boundaries - * are not known when mapping all bank memory ranges, which otherwise means - * not possible to exclude crash kernel range from creating block mappings - * so page-granularity mappings are created for the entire memory range. - * Hence a slightly slower boot is observed. - * - * Note: Page-granularity mappings are necessary for crash kernel memory - * range for shrinking its size via /sys/kernel/kexec_crash_size interface. */ -#if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32) phys_addr_t __ro_after_init arm64_dma_phys_limit; + +/* + * To make optimal use of block mappings when laying out the linear + * mapping, round down the base of physical memory to a size that can + * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE + * (64k granule), or a multiple that can be mapped using contiguous bits + * in the page tables: 32 * PMD_SIZE (16k granule) + */ +#if defined(CONFIG_ARM64_4K_PAGES) +#define ARM64_MEMSTART_SHIFT PUD_SHIFT +#elif defined(CONFIG_ARM64_16K_PAGES) +#define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT #else -phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1; +#define ARM64_MEMSTART_SHIFT PMD_SHIFT #endif -/* Current arm64 boot protocol requires 2MB alignment */ -#define CRASH_ALIGN SZ_2M - -#define CRASH_ADDR_LOW_MAX arm64_dma_phys_limit -#define CRASH_ADDR_HIGH_MAX (PHYS_MASK + 1) - -static int __init reserve_crashkernel_low(unsigned long long low_size) -{ - unsigned long long low_base; - - low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX); - if (!low_base) { - pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); - return -ENOMEM; - } - - pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n", - low_base, low_base + low_size, low_size >> 20); - - crashk_low_res.start = low_base; - crashk_low_res.end = low_base + low_size - 1; - insert_resource(&iomem_resource, &crashk_low_res); - - return 0; -} - /* - * reserve_crashkernel() - reserves memory for crash kernel - * - * This function reserves memory area given in "crashkernel=" kernel command - * line parameter. The memory reserved is used by dump capture kernel when - * primary kernel is crashing. + * sparsemem vmemmap imposes an additional requirement on the alignment of + * memstart_addr, due to the fact that the base of the vmemmap region + * has a direct correspondence, and needs to appear sufficiently aligned + * in the virtual address space. */ -static void __init reserve_crashkernel(void) +#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS +#define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) +#else +#define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) +#endif + +static void __init arch_reserve_crashkernel(void) { + unsigned long long low_size = 0; unsigned long long crash_base, crash_size; - unsigned long long crash_low_size = 0; - unsigned long long crash_max = CRASH_ADDR_LOW_MAX; - char *cmdline = boot_command_line; + bool high = false; int ret; - if (!IS_ENABLED(CONFIG_KEXEC_CORE)) - return; - - /* crashkernel=X[@offset] */ - ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), - &crash_size, &crash_base); - if (ret == -ENOENT) { - ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base); - if (ret || !crash_size) - return; - - /* - * crashkernel=Y,low can be specified or not, but invalid value - * is not allowed. - */ - ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base); - if (ret && (ret != -ENOENT)) - return; - - crash_max = CRASH_ADDR_HIGH_MAX; - } else if (ret || !crash_size) { - /* The specified value is invalid */ + if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; - } - - crash_size = PAGE_ALIGN(crash_size); - - /* User specifies base address explicitly. */ - if (crash_base) - crash_max = crash_base + crash_size; - - crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, - crash_base, crash_max); - if (!crash_base) { - pr_warn("cannot allocate crashkernel (size:0x%llx)\n", - crash_size); - return; - } - if ((crash_base >= CRASH_ADDR_LOW_MAX) && - crash_low_size && reserve_crashkernel_low(crash_low_size)) { - memblock_phys_free(crash_base, crash_size); + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + &crash_size, &crash_base, + &low_size, &high); + if (ret) return; - } - - pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", - crash_base, crash_base + crash_size, crash_size >> 20); - /* - * The crashkernel memory will be removed from the kernel linear - * map. Inform kmemleak so that it won't try to access it. - */ - kmemleak_ignore_phys(crash_base); - if (crashk_low_res.end) - kmemleak_ignore_phys(crashk_low_res.start); - - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; - insert_resource(&iomem_resource, &crashk_res); + reserve_crashkernel_generic(crash_size, crash_base, low_size, high); } -/* - * Return the maximum physical address for a zone accessible by the given bits - * limit. If DRAM starts above 32-bit, expand the zone to the maximum - * available memory, otherwise cap it at 32-bit. - */ -static phys_addr_t __init max_zone_phys(unsigned int zone_bits) +static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit) { - phys_addr_t zone_mask = DMA_BIT_MASK(zone_bits); - phys_addr_t phys_start = memblock_start_of_DRAM(); - - if (phys_start > U32_MAX) - zone_mask = PHYS_ADDR_MAX; - else if (phys_start > zone_mask) - zone_mask = U32_MAX; - - return min(zone_mask, memblock_end_of_DRAM() - 1) + 1; + return min(zone_limit, memblock_end_of_DRAM() - 1) + 1; } static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; - unsigned int __maybe_unused acpi_zone_dma_bits; - unsigned int __maybe_unused dt_zone_dma_bits; - phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32); + phys_addr_t __maybe_unused acpi_zone_dma_limit; + phys_addr_t __maybe_unused dt_zone_dma_limit; + phys_addr_t __maybe_unused dma32_phys_limit = + max_zone_phys(DMA_BIT_MASK(32)); #ifdef CONFIG_ZONE_DMA - acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); - dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL)); - zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits); - arm64_dma_phys_limit = max_zone_phys(zone_dma_bits); + acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address(); + dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL); + zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit); + /* + * Information we get from firmware (e.g. DT dma-ranges) describe DMA + * bus constraints. Devices using DMA might have their own limitations. + * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM + * DMA zone on platforms that have RAM there. + */ + if (memblock_start_of_DRAM() < U32_MAX) + zone_dma_limit = min(zone_dma_limit, U32_MAX); + arm64_dma_phys_limit = max_zone_phys(zone_dma_limit); max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 @@ -229,6 +146,8 @@ static void __init zone_sizes_init(void) if (!arm64_dma_phys_limit) arm64_dma_phys_limit = dma32_phys_limit; #endif + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max_pfn; free_area_init(max_zone_pfns); @@ -315,7 +234,7 @@ void __init arm64_memblock_init(void) * physical address of PAGE_OFFSET, we have to *subtract* from it. */ if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) - memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52); + memstart_addr -= _PAGE_OFFSET(vabits_actual) - _PAGE_OFFSET(52); /* * Apply the memory limit if it was set. Since the kernel may be loaded @@ -356,26 +275,6 @@ void __init arm64_memblock_init(void) } } - if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { - extern u16 memstart_offset_seed; - u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); - int parange = cpuid_feature_extract_unsigned_field( - mmfr0, ID_AA64MMFR0_PARANGE_SHIFT); - s64 range = linear_region_size - - BIT(id_aa64mmfr0_parange_to_phys_shift(parange)); - - /* - * If the size of the linear region exceeds, by a sufficient - * margin, the size of the region that the physical memory can - * span, randomize the linear region as well. - */ - if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) { - range /= ARM64_MEMSTART_ALIGN; - memstart_addr -= ARM64_MEMSTART_ALIGN * - ((range * memstart_offset_seed) >> 16); - } - } - /* * Register the kernel text, kernel data, initrd, and initial * pagetables with memblock. @@ -388,11 +287,6 @@ void __init arm64_memblock_init(void) } early_init_fdt_scan_reserved_mem(); - - if (!defer_reserve_crashkernel()) - reserve_crashkernel(); - - high_memory = __va(memblock_end_of_DRAM() - 1) + 1; } void __init bootmem_init(void) @@ -418,8 +312,6 @@ void __init bootmem_init(void) arm64_hugetlb_cma_reserve(); #endif - dma_pernuma_cma_reserve(); - kvm_hyp_reserve(); /* @@ -438,23 +330,34 @@ void __init bootmem_init(void) * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ - if (defer_reserve_crashkernel()) - reserve_crashkernel(); + arch_reserve_crashkernel(); memblock_dump_all(); } -/* - * mem_init() marks the free areas in the mem_map and tells us how much memory - * is free. This is done after various parts of the system have claimed their - * memory after the kernel image. - */ -void __init mem_init(void) +void __init arch_mm_preinit(void) { - swiotlb_init(max_pfn > PFN_DOWN(arm64_dma_phys_limit), SWIOTLB_VERBOSE); + unsigned int flags = SWIOTLB_VERBOSE; + bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit); + + if (is_realm_world()) { + swiotlb = true; + flags |= SWIOTLB_FORCE; + } + + if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) { + /* + * If no bouncing needed for ZONE_DMA, reduce the swiotlb + * buffer for kmalloc() bouncing to 1MB per 1GB of RAM. + */ + unsigned long size = + DIV_ROUND_UP(memblock_phys_mem_size(), 1024); + swiotlb_adjust_size(min(swiotlb_size_or_default(), size)); + swiotlb = true; + } - /* this will put all unused low memory onto the freelists */ - memblock_free_all(); + swiotlb_init(swiotlb, flags); + swiotlb_update_mem_attributes(); /* * Check boundaries twice: Some fundamental inconsistencies can be @@ -483,8 +386,16 @@ void __init mem_init(void) void free_initmem(void) { - free_reserved_area(lm_alias(__init_begin), - lm_alias(__init_end), + void *lm_init_begin = lm_alias(__init_begin); + void *lm_init_end = lm_alias(__init_end); + + WARN_ON(!IS_ALIGNED((unsigned long)lm_init_begin, PAGE_SIZE)); + WARN_ON(!IS_ALIGNED((unsigned long)lm_init_end, PAGE_SIZE)); + + /* Delete __init region from memblock.reserved. */ + memblock_free(lm_init_begin, lm_init_end - lm_init_begin); + + free_reserved_area(lm_init_begin, lm_init_end, POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This @@ -502,3 +413,142 @@ void dump_mem_limit(void) pr_emerg("Memory Limit: none\n"); } } + +#ifdef CONFIG_EXECMEM +static u64 module_direct_base __ro_after_init = 0; +static u64 module_plt_base __ro_after_init = 0; + +/* + * Choose a random page-aligned base address for a window of 'size' bytes which + * entirely contains the interval [start, end - 1]. + */ +static u64 __init random_bounding_box(u64 size, u64 start, u64 end) +{ + u64 max_pgoff, pgoff; + + if ((end - start) >= size) + return 0; + + max_pgoff = (size - (end - start)) / PAGE_SIZE; + pgoff = get_random_u32_inclusive(0, max_pgoff); + + return start - pgoff * PAGE_SIZE; +} + +/* + * Modules may directly reference data and text anywhere within the kernel + * image and other modules. References using PREL32 relocations have a +/-2G + * range, and so we need to ensure that the entire kernel image and all modules + * fall within a 2G window such that these are always within range. + * + * Modules may directly branch to functions and code within the kernel text, + * and to functions and code within other modules. These branches will use + * CALL26/JUMP26 relocations with a +/-128M range. Without PLTs, we must ensure + * that the entire kernel text and all module text falls within a 128M window + * such that these are always within range. With PLTs, we can expand this to a + * 2G window. + * + * We chose the 128M region to surround the entire kernel image (rather than + * just the text) as using the same bounds for the 128M and 2G regions ensures + * by construction that we never select a 128M region that is not a subset of + * the 2G region. For very large and unusual kernel configurations this means + * we may fall back to PLTs where they could have been avoided, but this keeps + * the logic significantly simpler. + */ +static int __init module_init_limits(void) +{ + u64 kernel_end = (u64)_end; + u64 kernel_start = (u64)_text; + u64 kernel_size = kernel_end - kernel_start; + + /* + * The default modules region is placed immediately below the kernel + * image, and is large enough to use the full 2G relocation range. + */ + BUILD_BUG_ON(KIMAGE_VADDR != MODULES_END); + BUILD_BUG_ON(MODULES_VSIZE < SZ_2G); + + if (!kaslr_enabled()) { + if (kernel_size < SZ_128M) + module_direct_base = kernel_end - SZ_128M; + if (kernel_size < SZ_2G) + module_plt_base = kernel_end - SZ_2G; + } else { + u64 min = kernel_start; + u64 max = kernel_end; + + if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { + pr_info("2G module region forced by RANDOMIZE_MODULE_REGION_FULL\n"); + } else { + module_direct_base = random_bounding_box(SZ_128M, min, max); + if (module_direct_base) { + min = module_direct_base; + max = module_direct_base + SZ_128M; + } + } + + module_plt_base = random_bounding_box(SZ_2G, min, max); + } + + pr_info("%llu pages in range for non-PLT usage", + module_direct_base ? (SZ_128M - kernel_size) / PAGE_SIZE : 0); + pr_info("%llu pages in range for PLT usage", + module_plt_base ? (SZ_2G - kernel_size) / PAGE_SIZE : 0); + + return 0; +} + +static struct execmem_info execmem_info __ro_after_init; + +struct execmem_info __init *execmem_arch_setup(void) +{ + unsigned long fallback_start = 0, fallback_end = 0; + unsigned long start = 0, end = 0; + + module_init_limits(); + + /* + * Where possible, prefer to allocate within direct branch range of the + * kernel such that no PLTs are necessary. + */ + if (module_direct_base) { + start = module_direct_base; + end = module_direct_base + SZ_128M; + + if (module_plt_base) { + fallback_start = module_plt_base; + fallback_end = module_plt_base + SZ_2G; + } + } else if (module_plt_base) { + start = module_plt_base; + end = module_plt_base + SZ_2G; + } + + execmem_info = (struct execmem_info){ + .ranges = { + [EXECMEM_DEFAULT] = { + .start = start, + .end = end, + .pgprot = PAGE_KERNEL, + .alignment = 1, + .fallback_start = fallback_start, + .fallback_end = fallback_end, + }, + [EXECMEM_KPROBES] = { + .start = VMALLOC_START, + .end = VMALLOC_END, + .pgprot = PAGE_KERNEL_ROX, + .alignment = 1, + }, + [EXECMEM_BPF] = { + .start = VMALLOC_START, + .end = VMALLOC_END, + .pgprot = PAGE_KERNEL, + .alignment = 1, + }, + }, + }; + + return &execmem_info; +} +#endif /* CONFIG_EXECMEM */ |