diff options
Diffstat (limited to 'arch/arm64/mm')
| -rw-r--r-- | arch/arm64/mm/Makefile | 2 | ||||
| -rw-r--r-- | arch/arm64/mm/fault.c | 58 | ||||
| -rw-r--r-- | arch/arm64/mm/init.c | 4 | ||||
| -rw-r--r-- | arch/arm64/mm/mmap.c | 15 | ||||
| -rw-r--r-- | arch/arm64/mm/mmu.c | 31 | ||||
| -rw-r--r-- | arch/arm64/mm/numa.c | 464 | ||||
| -rw-r--r-- | arch/arm64/mm/proc.S | 16 | ||||
| -rw-r--r-- | arch/arm64/mm/ptdump.c | 1 | ||||
| -rw-r--r-- | arch/arm64/mm/trans_pgd.c | 324 |
9 files changed, 372 insertions, 543 deletions
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 5ead3c3de3b6..f188c9092696 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -6,7 +6,7 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_PTDUMP_CORE) += ptdump.o obj-$(CONFIG_PTDUMP_DEBUGFS) += ptdump_debugfs.o -obj-$(CONFIG_NUMA) += numa.o +obj-$(CONFIG_TRANS_TABLE) += trans_pgd.o obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_ARM64_MTE) += mteswap.o KASAN_SANITIZE_physaddr.o += n diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 35d75c60e2b8..f37d4e3830b7 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -10,6 +10,7 @@ #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/extable.h> +#include <linux/kfence.h> #include <linux/signal.h> #include <linux/mm.h> #include <linux/hardirq.h> @@ -302,12 +303,24 @@ static void die_kernel_fault(const char *msg, unsigned long addr, static void report_tag_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - bool is_write = ((esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT) != 0; + static bool reported; + bool is_write; + + if (READ_ONCE(reported)) + return; + + /* + * This is used for KASAN tests and assumes that no MTE faults + * happened before running the tests. + */ + if (mte_report_once()) + WRITE_ONCE(reported, true); /* * SAS bits aren't set for all faults reported in EL1, so we can't * find out access size. */ + is_write = !!(esr & ESR_ELx_WNR); kasan_report(addr, 0, is_write, regs->pc); } #else @@ -319,12 +332,8 @@ static inline void report_tag_fault(unsigned long addr, unsigned int esr, static void do_tag_recovery(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - static bool reported; - if (!READ_ONCE(reported)) { - report_tag_fault(addr, esr, regs); - WRITE_ONCE(reported, true); - } + report_tag_fault(addr, esr, regs); /* * Disable MTE Tag Checking on the local CPU for the current EL. @@ -381,6 +390,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { + if (kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) + return; + msg = "paging request"; } @@ -564,7 +576,7 @@ retry: mmap_read_lock(mm); } else { /* - * The above down_read_trylock() might have succeeded in which + * The above mmap_read_trylock() might have succeeded in which * case, we'll have missed the might_sleep() from down_read(). */ might_sleep(); @@ -875,44 +887,12 @@ static void debug_exception_exit(struct pt_regs *regs) } NOKPROBE_SYMBOL(debug_exception_exit); -#ifdef CONFIG_ARM64_ERRATUM_1463225 -DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); - -static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) -{ - if (user_mode(regs)) - return 0; - - if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa)) - return 0; - - /* - * We've taken a dummy step exception from the kernel to ensure - * that interrupts are re-enabled on the syscall path. Return back - * to cortex_a76_erratum_1463225_svc_handler() with debug exceptions - * masked so that we can safely restore the mdscr and get on with - * handling the syscall. - */ - regs->pstate |= PSR_D_BIT; - return 1; -} -#else -static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) -{ - return 0; -} -#endif /* CONFIG_ARM64_ERRATUM_1463225 */ -NOKPROBE_SYMBOL(cortex_a76_erratum_1463225_debug_handler); - void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); - if (cortex_a76_erratum_1463225_debug_handler(regs)) - return; - debug_exception_enter(regs); if (user_mode(regs) && !is_ttbr0_addr(pc)) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 709d98fea90c..0ace5e68efba 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -416,10 +416,10 @@ void __init bootmem_init(void) max_pfn = max_low_pfn = max; min_low_pfn = min; - arm64_numa_init(); + arch_numa_init(); /* - * must be done after arm64_numa_init() which calls numa_init() to + * must be done after arch_numa_init() which calls numa_init() to * initialize node_online_map that gets used in hugetlb_cma_reserve() * while allocating required CMA size across online nodes. */ diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 07937b49cb88..a38f54cd638c 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -5,20 +5,11 @@ * Copyright (C) 2012 ARM Ltd. */ -#include <linux/elf.h> -#include <linux/fs.h> -#include <linux/memblock.h> -#include <linux/mm.h> -#include <linux/mman.h> -#include <linux/export.h> -#include <linux/shm.h> -#include <linux/sched/signal.h> -#include <linux/sched/mm.h> #include <linux/io.h> -#include <linux/personality.h> -#include <linux/random.h> +#include <linux/memblock.h> +#include <linux/types.h> -#include <asm/cputype.h> +#include <asm/page.h> /* * You really shouldn't be using read() or write() on /dev/mem. This might go diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index ae0c3d023824..3802cfbdd20d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -628,7 +628,7 @@ static bool arm64_early_this_cpu_has_bti(void) if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) return false; - pfr1 = read_sysreg_s(SYS_ID_AA64PFR1_EL1); + pfr1 = __read_sysreg_by_encoding(SYS_ID_AA64PFR1_EL1); return cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_BT_SHIFT); } @@ -1094,6 +1094,7 @@ static void free_empty_tables(unsigned long addr, unsigned long end, int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { + WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); return vmemmap_populate_basepages(start, end, node, altmap); } #else /* !ARM64_SWAPPER_USES_SECTION_MAPS */ @@ -1107,6 +1108,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, pud_t *pudp; pmd_t *pmdp; + WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); do { next = pmd_addr_end(addr, end); @@ -1153,7 +1155,7 @@ void vmemmap_free(unsigned long start, unsigned long end, } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -static inline pud_t * fixmap_pud(unsigned long addr) +static inline pud_t *fixmap_pud(unsigned long addr) { pgd_t *pgdp = pgd_offset_k(addr); p4d_t *p4dp = p4d_offset(pgdp, addr); @@ -1164,7 +1166,7 @@ static inline pud_t * fixmap_pud(unsigned long addr) return pud_offset_kimg(p4dp, addr); } -static inline pmd_t * fixmap_pmd(unsigned long addr) +static inline pmd_t *fixmap_pmd(unsigned long addr) { pud_t *pudp = fixmap_pud(addr); pud_t pud = READ_ONCE(*pudp); @@ -1174,7 +1176,7 @@ static inline pmd_t * fixmap_pmd(unsigned long addr) return pmd_offset_kimg(pudp, addr); } -static inline pte_t * fixmap_pte(unsigned long addr) +static inline pte_t *fixmap_pte(unsigned long addr) { return &bm_pte[pte_index(addr)]; } @@ -1442,16 +1444,19 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) free_empty_tables(start, end, PAGE_OFFSET, PAGE_END); } -static bool inside_linear_region(u64 start, u64 size) +struct range arch_get_mappable_range(void) { + struct range mhp_range; + /* * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)] * accommodating both its ends but excluding PAGE_END. Max physical * range which can be mapped inside this linear mapping range, must * also be derived from its end points. */ - return start >= __pa(_PAGE_OFFSET(vabits_actual)) && - (start + size - 1) <= __pa(PAGE_END - 1); + mhp_range.start = __pa(_PAGE_OFFSET(vabits_actual)); + mhp_range.end = __pa(PAGE_END - 1); + return mhp_range; } int arch_add_memory(int nid, u64 start, u64 size, @@ -1459,12 +1464,14 @@ int arch_add_memory(int nid, u64 start, u64 size, { int ret, flags = 0; - if (!inside_linear_region(start, size)) { - pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size); - return -EINVAL; - } + VM_BUG_ON(!mhp_range_allowed(start, size, true)); - if (rodata_full || debug_pagealloc_enabled()) + /* + * KFENCE requires linear map to be mapped at page granularity, so that + * it is possible to protect/unprotect single pages in the KFENCE pool. + */ + if (rodata_full || debug_pagealloc_enabled() || + IS_ENABLED(CONFIG_KFENCE)) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c deleted file mode 100644 index a8303bc6b62a..000000000000 --- a/arch/arm64/mm/numa.c +++ /dev/null @@ -1,464 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * NUMA support, based on the x86 implementation. - * - * Copyright (C) 2015 Cavium Inc. - * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com> - */ - -#define pr_fmt(fmt) "NUMA: " fmt - -#include <linux/acpi.h> -#include <linux/memblock.h> -#include <linux/module.h> -#include <linux/of.h> - -#include <asm/acpi.h> -#include <asm/sections.h> - -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); -nodemask_t numa_nodes_parsed __initdata; -static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE }; - -static int numa_distance_cnt; -static u8 *numa_distance; -bool numa_off; - -static __init int numa_parse_early_param(char *opt) -{ - if (!opt) - return -EINVAL; - if (str_has_prefix(opt, "off")) - numa_off = true; - - return 0; -} -early_param("numa", numa_parse_early_param); - -cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; -EXPORT_SYMBOL(node_to_cpumask_map); - -#ifdef CONFIG_DEBUG_PER_CPU_MAPS - -/* - * Returns a pointer to the bitmask of CPUs on Node 'node'. - */ -const struct cpumask *cpumask_of_node(int node) -{ - - if (node == NUMA_NO_NODE) - return cpu_all_mask; - - if (WARN_ON(node < 0 || node >= nr_node_ids)) - return cpu_none_mask; - - if (WARN_ON(node_to_cpumask_map[node] == NULL)) - return cpu_online_mask; - - return node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(cpumask_of_node); - -#endif - -static void numa_update_cpu(unsigned int cpu, bool remove) -{ - int nid = cpu_to_node(cpu); - - if (nid == NUMA_NO_NODE) - return; - - if (remove) - cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]); - else - cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); -} - -void numa_add_cpu(unsigned int cpu) -{ - numa_update_cpu(cpu, false); -} - -void numa_remove_cpu(unsigned int cpu) -{ - numa_update_cpu(cpu, true); -} - -void numa_clear_node(unsigned int cpu) -{ - numa_remove_cpu(cpu); - set_cpu_numa_node(cpu, NUMA_NO_NODE); -} - -/* - * Allocate node_to_cpumask_map based on number of available nodes - * Requires node_possible_map to be valid. - * - * Note: cpumask_of_node() is not valid until after this is done. - * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) - */ -static void __init setup_node_to_cpumask_map(void) -{ - int node; - - /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) - setup_nr_node_ids(); - - /* allocate and clear the mapping */ - for (node = 0; node < nr_node_ids; node++) { - alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); - cpumask_clear(node_to_cpumask_map[node]); - } - - /* cpumask_of_node() will now work */ - pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); -} - -/* - * Set the cpu to node and mem mapping - */ -void numa_store_cpu_info(unsigned int cpu) -{ - set_cpu_numa_node(cpu, cpu_to_node_map[cpu]); -} - -void __init early_map_cpu_to_node(unsigned int cpu, int nid) -{ - /* fallback to node 0 */ - if (nid < 0 || nid >= MAX_NUMNODES || numa_off) - nid = 0; - - cpu_to_node_map[cpu] = nid; - - /* - * We should set the numa node of cpu0 as soon as possible, because it - * has already been set up online before. cpu_to_node(0) will soon be - * called. - */ - if (!cpu) - set_cpu_numa_node(cpu, nid); -} - -#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(__per_cpu_offset); - -static int __init early_cpu_to_node(int cpu) -{ - return cpu_to_node_map[cpu]; -} - -static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) -{ - return node_distance(early_cpu_to_node(from), early_cpu_to_node(to)); -} - -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, - size_t align) -{ - int nid = early_cpu_to_node(cpu); - - return memblock_alloc_try_nid(size, align, - __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); -} - -static void __init pcpu_fc_free(void *ptr, size_t size) -{ - memblock_free_early(__pa(ptr), size); -} - -void __init setup_per_cpu_areas(void) -{ - unsigned long delta; - unsigned int cpu; - int rc; - - /* - * Always reserve area for module percpu variables. That's - * what the legacy allocator did. - */ - rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, - PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, - pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); - if (rc < 0) - panic("Failed to initialize percpu areas."); - - delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; - for_each_possible_cpu(cpu) - __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; -} -#endif - -/** - * numa_add_memblk() - Set node id to memblk - * @nid: NUMA node ID of the new memblk - * @start: Start address of the new memblk - * @end: End address of the new memblk - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_add_memblk(int nid, u64 start, u64 end) -{ - int ret; - - ret = memblock_set_node(start, (end - start), &memblock.memory, nid); - if (ret < 0) { - pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n", - start, (end - 1), nid); - return ret; - } - - node_set(nid, numa_nodes_parsed); - return ret; -} - -/* - * Initialize NODE_DATA for a node on the local memory - */ -static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) -{ - const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); - u64 nd_pa; - void *nd; - int tnid; - - if (start_pfn >= end_pfn) - pr_info("Initmem setup node %d [<memory-less node>]\n", nid); - - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) - panic("Cannot allocate %zu bytes for node %d data\n", - nd_size, nid); - - nd = __va(nd_pa); - - /* report and initialize */ - pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n", - nd_pa, nd_pa + nd_size - 1); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != nid) - pr_info("NODE_DATA(%d) on node %d\n", nid, tnid); - - node_data[nid] = nd; - memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); - NODE_DATA(nid)->node_id = nid; - NODE_DATA(nid)->node_start_pfn = start_pfn; - NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; -} - -/* - * numa_free_distance - * - * The current table is freed. - */ -void __init numa_free_distance(void) -{ - size_t size; - - if (!numa_distance) - return; - - size = numa_distance_cnt * numa_distance_cnt * - sizeof(numa_distance[0]); - - memblock_free(__pa(numa_distance), size); - numa_distance_cnt = 0; - numa_distance = NULL; -} - -/* - * Create a new NUMA distance table. - */ -static int __init numa_alloc_distance(void) -{ - size_t size; - u64 phys; - int i, j; - - size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]); - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn), - size, PAGE_SIZE); - if (WARN_ON(!phys)) - return -ENOMEM; - - memblock_reserve(phys, size); - - numa_distance = __va(phys); - numa_distance_cnt = nr_node_ids; - - /* fill with the default distances */ - for (i = 0; i < numa_distance_cnt; i++) - for (j = 0; j < numa_distance_cnt; j++) - numa_distance[i * numa_distance_cnt + j] = i == j ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - - pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt); - - return 0; -} - -/** - * numa_set_distance() - Set inter node NUMA distance from node to node. - * @from: the 'from' node to set distance - * @to: the 'to' node to set distance - * @distance: NUMA distance - * - * Set the distance from node @from to @to to @distance. - * If distance table doesn't exist, a warning is printed. - * - * If @from or @to is higher than the highest known node or lower than zero - * or @distance doesn't make sense, the call is ignored. - */ -void __init numa_set_distance(int from, int to, int distance) -{ - if (!numa_distance) { - pr_warn_once("Warning: distance table not allocated yet\n"); - return; - } - - if (from >= numa_distance_cnt || to >= numa_distance_cnt || - from < 0 || to < 0) { - pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - if ((u8)distance != distance || - (from == to && distance != LOCAL_DISTANCE)) { - pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - numa_distance[from * numa_distance_cnt + to] = distance; -} - -/* - * Return NUMA distance @from to @to - */ -int __node_distance(int from, int to) -{ - if (from >= numa_distance_cnt || to >= numa_distance_cnt) - return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; - return numa_distance[from * numa_distance_cnt + to]; -} -EXPORT_SYMBOL(__node_distance); - -static int __init numa_register_nodes(void) -{ - int nid; - struct memblock_region *mblk; - - /* Check that valid nid is set to memblks */ - for_each_mem_region(mblk) { - int mblk_nid = memblock_get_region_node(mblk); - - if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) { - pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", - mblk_nid, mblk->base, - mblk->base + mblk->size - 1); - return -EINVAL; - } - } - - /* Finally register nodes. */ - for_each_node_mask(nid, numa_nodes_parsed) { - unsigned long start_pfn, end_pfn; - - get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); - setup_node_data(nid, start_pfn, end_pfn); - node_set_online(nid); - } - - /* Setup online nodes to actual nodes*/ - node_possible_map = numa_nodes_parsed; - - return 0; -} - -static int __init numa_init(int (*init_func)(void)) -{ - int ret; - - nodes_clear(numa_nodes_parsed); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - - ret = numa_alloc_distance(); - if (ret < 0) - return ret; - - ret = init_func(); - if (ret < 0) - goto out_free_distance; - - if (nodes_empty(numa_nodes_parsed)) { - pr_info("No NUMA configuration found\n"); - ret = -EINVAL; - goto out_free_distance; - } - - ret = numa_register_nodes(); - if (ret < 0) - goto out_free_distance; - - setup_node_to_cpumask_map(); - - return 0; -out_free_distance: - numa_free_distance(); - return ret; -} - -/** - * dummy_numa_init() - Fallback dummy NUMA init - * - * Used if there's no underlying NUMA architecture, NUMA initialization - * fails, or NUMA is disabled on the command line. - * - * Must online at least one node (node 0) and add memory blocks that cover all - * allowed memory. It is unlikely that this function fails. - * - * Return: 0 on success, -errno on failure. - */ -static int __init dummy_numa_init(void) -{ - phys_addr_t start = memblock_start_of_DRAM(); - phys_addr_t end = memblock_end_of_DRAM(); - int ret; - - if (numa_off) - pr_info("NUMA disabled\n"); /* Forced off on command line. */ - pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", start, end - 1); - - ret = numa_add_memblk(0, start, end); - if (ret) { - pr_err("NUMA init failed\n"); - return ret; - } - - numa_off = true; - return 0; -} - -/** - * arm64_numa_init() - Initialize NUMA - * - * Try each configured NUMA initialization method until one succeeds. The - * last fallback is dummy single node config encompassing whole memory. - */ -void __init arm64_numa_init(void) -{ - if (!numa_off) { - if (!acpi_disabled && !numa_init(arm64_acpi_numa_init)) - return; - if (acpi_disabled && !numa_init(of_numa_init)) - return; - } - - numa_init(dummy_numa_init); -} diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 1f7ee8c8b7b8..c967bfd30d2b 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -291,17 +291,7 @@ skip_pgd: /* We're done: fire up the MMU again */ mrs x17, sctlr_el1 orr x17, x17, #SCTLR_ELx_M - msr sctlr_el1, x17 - isb - - /* - * Invalidate the local I-cache so that any instructions fetched - * speculatively from the PoC are discarded, since they may have - * been dynamically patched at the PoU. - */ - ic iallu - dsb nsh - isb + set_sctlr_el1 x17 /* Set the flag to zero to indicate that we're all done */ str wzr, [flag_ptr] @@ -464,8 +454,8 @@ SYM_FUNC_START(__cpu_setup) #endif msr mair_el1, x5 /* - * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for - * both user and kernel. + * Set/prepare TCR and TTBR. TCR_EL1.T1SZ gets further + * adjusted if the kernel is compiled with 52bit VA support. */ mov_q x10, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index 04137a8f3d2d..0e050d76b83a 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -324,6 +324,7 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info) st = (struct pg_state){ .seq = s, .marker = info->markers, + .level = -1, .ptdump = { .note_page = note_page, .range = (struct ptdump_range[]){ diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c new file mode 100644 index 000000000000..527f0a39c3da --- /dev/null +++ b/arch/arm64/mm/trans_pgd.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Transitional page tables for kexec and hibernate + * + * This file derived from: arch/arm64/kernel/hibernate.c + * + * Copyright (c) 2020, Microsoft Corporation. + * Pavel Tatashin <pasha.tatashin@soleen.com> + * + */ + +/* + * Transitional tables are used during system transferring from one world to + * another: such as during hibernate restore, and kexec reboots. During these + * phases one cannot rely on page table not being overwritten. This is because + * hibernate and kexec can overwrite the current page tables during transition. + */ + +#include <asm/trans_pgd.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <linux/suspend.h> +#include <linux/bug.h> +#include <linux/mm.h> +#include <linux/mmzone.h> + +static void *trans_alloc(struct trans_pgd_info *info) +{ + return info->trans_alloc_page(info->trans_alloc_arg); +} + +static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr) +{ + pte_t pte = READ_ONCE(*src_ptep); + + if (pte_valid(pte)) { + /* + * Resume will overwrite areas that may be marked + * read only (code, rodata). Clear the RDONLY bit from + * the temporary mappings we use during restore. + */ + set_pte(dst_ptep, pte_mkwrite(pte)); + } else if (debug_pagealloc_enabled() && !pte_none(pte)) { + /* + * debug_pagealloc will removed the PTE_VALID bit if + * the page isn't in use by the resume kernel. It may have + * been in use by the original kernel, in which case we need + * to put it back in our copy to do the restore. + * + * Before marking this entry valid, check the pfn should + * be mapped. + */ + BUG_ON(!pfn_valid(pte_pfn(pte))); + + set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte))); + } +} + +static int copy_pte(struct trans_pgd_info *info, pmd_t *dst_pmdp, + pmd_t *src_pmdp, unsigned long start, unsigned long end) +{ + pte_t *src_ptep; + pte_t *dst_ptep; + unsigned long addr = start; + + dst_ptep = trans_alloc(info); + if (!dst_ptep) + return -ENOMEM; + pmd_populate_kernel(NULL, dst_pmdp, dst_ptep); + dst_ptep = pte_offset_kernel(dst_pmdp, start); + + src_ptep = pte_offset_kernel(src_pmdp, start); + do { + _copy_pte(dst_ptep, src_ptep, addr); + } while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end); + + return 0; +} + +static int copy_pmd(struct trans_pgd_info *info, pud_t *dst_pudp, + pud_t *src_pudp, unsigned long start, unsigned long end) +{ + pmd_t *src_pmdp; + pmd_t *dst_pmdp; + unsigned long next; + unsigned long addr = start; + + if (pud_none(READ_ONCE(*dst_pudp))) { + dst_pmdp = trans_alloc(info); + if (!dst_pmdp) + return -ENOMEM; + pud_populate(NULL, dst_pudp, dst_pmdp); + } + dst_pmdp = pmd_offset(dst_pudp, start); + + src_pmdp = pmd_offset(src_pudp, start); + do { + pmd_t pmd = READ_ONCE(*src_pmdp); + + next = pmd_addr_end(addr, end); + if (pmd_none(pmd)) + continue; + if (pmd_table(pmd)) { + if (copy_pte(info, dst_pmdp, src_pmdp, addr, next)) + return -ENOMEM; + } else { + set_pmd(dst_pmdp, + __pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY)); + } + } while (dst_pmdp++, src_pmdp++, addr = next, addr != end); + + return 0; +} + +static int copy_pud(struct trans_pgd_info *info, p4d_t *dst_p4dp, + p4d_t *src_p4dp, unsigned long start, + unsigned long end) +{ + pud_t *dst_pudp; + pud_t *src_pudp; + unsigned long next; + unsigned long addr = start; + + if (p4d_none(READ_ONCE(*dst_p4dp))) { + dst_pudp = trans_alloc(info); + if (!dst_pudp) + return -ENOMEM; + p4d_populate(NULL, dst_p4dp, dst_pudp); + } + dst_pudp = pud_offset(dst_p4dp, start); + + src_pudp = pud_offset(src_p4dp, start); + do { + pud_t pud = READ_ONCE(*src_pudp); + + next = pud_addr_end(addr, end); + if (pud_none(pud)) + continue; + if (pud_table(pud)) { + if (copy_pmd(info, dst_pudp, src_pudp, addr, next)) + return -ENOMEM; + } else { + set_pud(dst_pudp, + __pud(pud_val(pud) & ~PUD_SECT_RDONLY)); + } + } while (dst_pudp++, src_pudp++, addr = next, addr != end); + + return 0; +} + +static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp, + pgd_t *src_pgdp, unsigned long start, + unsigned long end) +{ + p4d_t *dst_p4dp; + p4d_t *src_p4dp; + unsigned long next; + unsigned long addr = start; + + dst_p4dp = p4d_offset(dst_pgdp, start); + src_p4dp = p4d_offset(src_pgdp, start); + do { + next = p4d_addr_end(addr, end); + if (p4d_none(READ_ONCE(*src_p4dp))) + continue; + if (copy_pud(info, dst_p4dp, src_p4dp, addr, next)) + return -ENOMEM; + } while (dst_p4dp++, src_p4dp++, addr = next, addr != end); + + return 0; +} + +static int copy_page_tables(struct trans_pgd_info *info, pgd_t *dst_pgdp, + unsigned long start, unsigned long end) +{ + unsigned long next; + unsigned long addr = start; + pgd_t *src_pgdp = pgd_offset_k(start); + + dst_pgdp = pgd_offset_pgd(dst_pgdp, start); + do { + next = pgd_addr_end(addr, end); + if (pgd_none(READ_ONCE(*src_pgdp))) + continue; + if (copy_p4d(info, dst_pgdp, src_pgdp, addr, next)) + return -ENOMEM; + } while (dst_pgdp++, src_pgdp++, addr = next, addr != end); + + return 0; +} + +/* + * Create trans_pgd and copy linear map. + * info: contains allocator and its argument + * dst_pgdp: new page table that is created, and to which map is copied. + * start: Start of the interval (inclusive). + * end: End of the interval (exclusive). + * + * Returns 0 on success, and -ENOMEM on failure. + */ +int trans_pgd_create_copy(struct trans_pgd_info *info, pgd_t **dst_pgdp, + unsigned long start, unsigned long end) +{ + int rc; + pgd_t *trans_pgd = trans_alloc(info); + + if (!trans_pgd) { + pr_err("Failed to allocate memory for temporary page tables.\n"); + return -ENOMEM; + } + + rc = copy_page_tables(info, trans_pgd, start, end); + if (!rc) + *dst_pgdp = trans_pgd; + + return rc; +} + +/* + * Add map entry to trans_pgd for a base-size page at PTE level. + * info: contains allocator and its argument + * trans_pgd: page table in which new map is added. + * page: page to be mapped. + * dst_addr: new VA address for the page + * pgprot: protection for the page. + * + * Returns 0 on success, and -ENOMEM on failure. + */ +int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd, + void *page, unsigned long dst_addr, pgprot_t pgprot) +{ + pgd_t *pgdp; + p4d_t *p4dp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + + pgdp = pgd_offset_pgd(trans_pgd, dst_addr); + if (pgd_none(READ_ONCE(*pgdp))) { + p4dp = trans_alloc(info); + if (!pgdp) + return -ENOMEM; + pgd_populate(NULL, pgdp, p4dp); + } + + p4dp = p4d_offset(pgdp, dst_addr); + if (p4d_none(READ_ONCE(*p4dp))) { + pudp = trans_alloc(info); + if (!pudp) + return -ENOMEM; + p4d_populate(NULL, p4dp, pudp); + } + + pudp = pud_offset(p4dp, dst_addr); + if (pud_none(READ_ONCE(*pudp))) { + pmdp = trans_alloc(info); + if (!pmdp) + return -ENOMEM; + pud_populate(NULL, pudp, pmdp); + } + + pmdp = pmd_offset(pudp, dst_addr); + if (pmd_none(READ_ONCE(*pmdp))) { + ptep = trans_alloc(info); + if (!ptep) + return -ENOMEM; + pmd_populate_kernel(NULL, pmdp, ptep); + } + + ptep = pte_offset_kernel(pmdp, dst_addr); + set_pte(ptep, pfn_pte(virt_to_pfn(page), pgprot)); + + return 0; +} + +/* + * The page we want to idmap may be outside the range covered by VA_BITS that + * can be built using the kernel's p?d_populate() helpers. As a one off, for a + * single page, we build these page tables bottom up and just assume that will + * need the maximum T0SZ. + * + * Returns 0 on success, and -ENOMEM on failure. + * On success trans_ttbr0 contains page table with idmapped page, t0sz is set to + * maximum T0SZ for this page. + */ +int trans_pgd_idmap_page(struct trans_pgd_info *info, phys_addr_t *trans_ttbr0, + unsigned long *t0sz, void *page) +{ + phys_addr_t dst_addr = virt_to_phys(page); + unsigned long pfn = __phys_to_pfn(dst_addr); + int max_msb = (dst_addr & GENMASK(52, 48)) ? 51 : 47; + int bits_mapped = PAGE_SHIFT - 4; + unsigned long level_mask, prev_level_entry, *levels[4]; + int this_level, index, level_lsb, level_msb; + + dst_addr &= PAGE_MASK; + prev_level_entry = pte_val(pfn_pte(pfn, PAGE_KERNEL_EXEC)); + + for (this_level = 3; this_level >= 0; this_level--) { + levels[this_level] = trans_alloc(info); + if (!levels[this_level]) + return -ENOMEM; + + level_lsb = ARM64_HW_PGTABLE_LEVEL_SHIFT(this_level); + level_msb = min(level_lsb + bits_mapped, max_msb); + level_mask = GENMASK_ULL(level_msb, level_lsb); + + index = (dst_addr & level_mask) >> level_lsb; + *(levels[this_level] + index) = prev_level_entry; + + pfn = virt_to_pfn(levels[this_level]); + prev_level_entry = pte_val(pfn_pte(pfn, + __pgprot(PMD_TYPE_TABLE))); + + if (level_msb == max_msb) + break; + } + + *trans_ttbr0 = phys_to_ttbr(__pfn_to_phys(pfn)); + *t0sz = TCR_T0SZ(max_msb + 1); + + return 0; +} |