From d635711daa98be86d4c7fd01499c34f566b54ccb Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Fri, 10 Jun 2016 05:30:17 -0300 Subject: Linux-libre 4.6.2-gnu --- arch/arm64/mm/context.c | 54 +++-- arch/arm64/mm/dump.c | 21 +- arch/arm64/mm/extable.c | 2 +- arch/arm64/mm/fault.c | 86 ++++++- arch/arm64/mm/flush.c | 4 - arch/arm64/mm/hugetlbpage.c | 2 +- arch/arm64/mm/init.c | 162 ++++++++++---- arch/arm64/mm/kasan_init.c | 70 ++++-- arch/arm64/mm/mmu.c | 532 ++++++++++++++++++++++++++++---------------- arch/arm64/mm/pageattr.c | 46 +++- arch/arm64/mm/proc.S | 40 ++++ 11 files changed, 723 insertions(+), 296 deletions(-) (limited to 'arch/arm64/mm') diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index e87f53ff5..c90c3c5f4 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -24,6 +24,7 @@ #include #include +#include #include static u32 asid_bits; @@ -40,6 +41,45 @@ static cpumask_t tlb_flush_pending; #define ASID_FIRST_VERSION (1UL << asid_bits) #define NUM_USER_ASIDS ASID_FIRST_VERSION +/* Get the ASIDBits supported by the current CPU */ +static u32 get_cpu_asid_bits(void) +{ + u32 asid; + int fld = cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64MMFR0_EL1), + ID_AA64MMFR0_ASID_SHIFT); + + switch (fld) { + default: + pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n", + smp_processor_id(), fld); + /* Fallthrough */ + case 0: + asid = 8; + break; + case 2: + asid = 16; + } + + return asid; +} + +/* Check if the current cpu's ASIDBits is compatible with asid_bits */ +void verify_cpu_asid_bits(void) +{ + u32 asid = get_cpu_asid_bits(); + + if (asid < asid_bits) { + /* + * We cannot decrease the ASID size at runtime, so panic if we support + * fewer ASID bits than the boot CPU. + */ + pr_crit("CPU%d: smaller ASID size(%u) than boot CPU (%u)\n", + smp_processor_id(), asid, asid_bits); + update_cpu_boot_status(CPU_PANIC_KERNEL); + cpu_park_loop(); + } +} + static void flush_context(unsigned int cpu) { int i; @@ -187,19 +227,7 @@ switch_mm_fastpath: static int asids_init(void) { - int fld = cpuid_feature_extract_field(read_cpuid(ID_AA64MMFR0_EL1), 4); - - switch (fld) { - default: - pr_warn("Unknown ASID size (%d); assuming 8-bit\n", fld); - /* Fallthrough */ - case 0: - asid_bits = 8; - break; - case 2: - asid_bits = 16; - } - + asid_bits = get_cpu_asid_bits(); /* If we end up with more CPUs than ASIDs, expect things to crash */ WARN_ON(NUM_USER_ASIDS < num_possible_cpus()); atomic64_set(&asid_generation, ASID_FIRST_VERSION); diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 0adbebbc2..f9271cb2f 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -27,15 +27,15 @@ #include #include -#define LOWEST_ADDR (UL(0xffffffffffffffff) << VA_BITS) - struct addr_marker { unsigned long start_address; const char *name; }; enum address_markers_idx { - VMALLOC_START_NR = 0, + MODULES_START_NR = 0, + MODULES_END_NR, + VMALLOC_START_NR, VMALLOC_END_NR, #ifdef CONFIG_SPARSEMEM_VMEMMAP VMEMMAP_START_NR, @@ -45,12 +45,12 @@ enum address_markers_idx { FIXADDR_END_NR, PCI_START_NR, PCI_END_NR, - MODULES_START_NR, - MODULES_END_NR, KERNEL_SPACE_NR, }; static struct addr_marker address_markers[] = { + { MODULES_VADDR, "Modules start" }, + { MODULES_END, "Modules end" }, { VMALLOC_START, "vmalloc() Area" }, { VMALLOC_END, "vmalloc() End" }, #ifdef CONFIG_SPARSEMEM_VMEMMAP @@ -61,9 +61,7 @@ static struct addr_marker address_markers[] = { { FIXADDR_TOP, "Fixmap end" }, { PCI_IO_START, "PCI I/O start" }, { PCI_IO_END, "PCI I/O end" }, - { MODULES_VADDR, "Modules start" }, - { MODULES_END, "Modules end" }, - { PAGE_OFFSET, "Kernel Mapping" }, + { PAGE_OFFSET, "Linear Mapping" }, { -1, NULL }, }; @@ -90,6 +88,11 @@ struct prot_bits { static const struct prot_bits pte_bits[] = { { + .mask = PTE_VALID, + .val = PTE_VALID, + .set = " ", + .clear = "F", + }, { .mask = PTE_USER, .val = PTE_USER, .set = "USR", @@ -316,7 +319,7 @@ static int ptdump_show(struct seq_file *m, void *v) .marker = address_markers, }; - walk_pgd(&st, &init_mm, LOWEST_ADDR); + walk_pgd(&st, &init_mm, VA_START); note_page(&st, 0, 0, 0); return 0; diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c index 79444279b..81acd4706 100644 --- a/arch/arm64/mm/extable.c +++ b/arch/arm64/mm/extable.c @@ -11,7 +11,7 @@ int fixup_exception(struct pt_regs *regs) fixup = search_exception_tables(instruction_pointer(regs)); if (fixup) - regs->pc = fixup->fixup; + regs->pc = (unsigned long)&fixup->fixup + fixup->fixup; return fixup != NULL; } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index abe2a9542..3ae4a28c4 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -81,6 +81,56 @@ void show_pte(struct mm_struct *mm, unsigned long addr) printk("\n"); } +#ifdef CONFIG_ARM64_HW_AFDBM +/* + * This function sets the access flags (dirty, accessed), as well as write + * permission, and only to a more permissive setting. + * + * It needs to cope with hardware update of the accessed/dirty state by other + * agents in the system and can safely skip the __sync_icache_dcache() call as, + * like set_pte_at(), the PTE is never changed from no-exec to exec here. + * + * Returns whether or not the PTE actually changed. + */ +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + pteval_t old_pteval; + unsigned int tmp; + + if (pte_same(*ptep, entry)) + return 0; + + /* only preserve the access flags and write permission */ + pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY; + + /* + * PTE_RDONLY is cleared by default in the asm below, so set it in + * back if necessary (read-only or clean PTE). + */ + if (!pte_write(entry) || !dirty) + pte_val(entry) |= PTE_RDONLY; + + /* + * Setting the flags must be done atomically to avoid racing with the + * hardware update of the access/dirty state. + */ + asm volatile("// ptep_set_access_flags\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " and %0, %0, %3 // clear PTE_RDONLY\n" + " orr %0, %0, %4 // set flags\n" + " stxr %w1, %0, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)) + : "L" (~PTE_RDONLY), "r" (pte_val(entry))); + + flush_tlb_fix_spurious_fault(vma, address); + return 1; +} +#endif + /* * The kernel tried to access some page that wasn't present. */ @@ -192,6 +242,14 @@ out: return fault; } +static inline int permission_fault(unsigned int esr) +{ + unsigned int ec = (esr & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT; + unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE; + + return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM); +} + static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -225,12 +283,13 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, mm_flags |= FAULT_FLAG_WRITE; } - /* - * PAN bit set implies the fault happened in kernel space, but not - * in the arch's user access functions. - */ - if (IS_ENABLED(CONFIG_ARM64_PAN) && (regs->pstate & PSR_PAN_BIT)) - goto no_context; + if (permission_fault(esr) && (addr < USER_DS)) { + if (get_fs() == KERNEL_DS) + die("Accessing user space memory with fs=KERNEL_DS", regs, esr); + + if (!search_exception_tables(regs->pc)) + die("Accessing user space memory outside uaccess.h routines", regs, esr); + } /* * As per x86, we may deadlock here. However, since the kernel only @@ -295,7 +354,7 @@ retry: up_read(&mm->mmap_sem); /* - * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR + * Handle the "normal" case first - VM_FAULT_MAJOR */ if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS)))) @@ -568,3 +627,16 @@ void cpu_enable_pan(void *__unused) config_sctlr_el1(SCTLR_EL1_SPAN, 0); } #endif /* CONFIG_ARM64_PAN */ + +#ifdef CONFIG_ARM64_UAO +/* + * Kernel threads have fs=KERNEL_DS by default, and don't need to call + * set_fs(), devtmpfs in particular relies on this behaviour. + * We need to enable the feature at runtime (instead of adding it to + * PSR_MODE_EL1h) as the feature may not be implemented by the cpu. + */ +void cpu_enable_uao(void *__unused) +{ + asm(SET_PSTATE_UAO(1)); +} +#endif /* CONFIG_ARM64_UAO */ diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 60585bde1..dbd12ea8c 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -58,17 +58,13 @@ static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, * Copy user data from/to a page which is mapped into a different processes * address space. Really, we want to allow our "user space" model to handle * this. - * - * Note that this code needs to run on the current CPU. */ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { - preempt_disable(); memcpy(dst, src, len); flush_ptrace_access(vma, page, uaddr, dst, len); - preempt_enable(); } void __sync_icache_dcache(pte_t pte, unsigned long addr) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index da30529bb..589fd28e1 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -124,7 +124,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, * will be no pte_unmap() to correspond with this * pte_alloc_map(). */ - pte = pte_alloc_map(mm, NULL, pmd, addr); + pte = pte_alloc_map(mm, pmd, addr); } else if (sz == PMD_SIZE) { if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && pud_none(*pud)) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 7802f216a..ea989d83e 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -35,7 +35,10 @@ #include #include +#include #include +#include +#include #include #include #include @@ -45,7 +48,13 @@ #include "mm.h" -phys_addr_t memstart_addr __read_mostly = 0; +/* + * We need to be able to catch inadvertent references to memstart_addr + * that occur (potentially in generic code) before arm64_memblock_init() + * executes, which assigns it its actual value. So use a default value + * that cannot be mistaken for a real physical address. + */ +s64 memstart_addr __read_mostly = -1; phys_addr_t arm64_dma_phys_limit __read_mostly; #ifdef CONFIG_BLK_DEV_INITRD @@ -58,8 +67,8 @@ static int __init early_initrd(char *p) if (*endp == ',') { size = memparse(endp + 1, NULL); - initrd_start = (unsigned long)__va(start); - initrd_end = (unsigned long)__va(start + size); + initrd_start = start; + initrd_end = start + size; } return 0; } @@ -159,7 +168,57 @@ early_param("mem", early_mem); void __init arm64_memblock_init(void) { - memblock_enforce_memory_limit(memory_limit); + const s64 linear_region_size = -(s64)PAGE_OFFSET; + + /* + * Ensure that the linear region takes up exactly half of the kernel + * virtual address space. This way, we can distinguish a linear address + * from a kernel/module/vmalloc address by testing a single bit. + */ + BUILD_BUG_ON(linear_region_size != BIT(VA_BITS - 1)); + + /* + * Select a suitable value for the base of physical memory. + */ + memstart_addr = round_down(memblock_start_of_DRAM(), + ARM64_MEMSTART_ALIGN); + + /* + * Remove the memory that we will not be able to cover with the + * linear mapping. Take care not to clip the kernel which may be + * high in memory. + */ + memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa(_end)), + ULLONG_MAX); + if (memblock_end_of_DRAM() > linear_region_size) + memblock_remove(0, memblock_end_of_DRAM() - linear_region_size); + + /* + * Apply the memory limit if it was set. Since the kernel may be loaded + * high up in memory, add back the kernel region that must be accessible + * via the linear mapping. + */ + if (memory_limit != (phys_addr_t)ULLONG_MAX) { + memblock_enforce_memory_limit(memory_limit); + memblock_add(__pa(_text), (u64)(_end - _text)); + } + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + extern u16 memstart_offset_seed; + u64 range = linear_region_size - + (memblock_end_of_DRAM() - memblock_start_of_DRAM()); + + /* + * If the size of the linear region exceeds, by a sufficient + * margin, the size of the region that the available physical + * memory spans, randomize the linear region as well. + */ + if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) { + range = range / ARM64_MEMSTART_ALIGN + 1; + memstart_addr -= ARM64_MEMSTART_ALIGN * + ((range * memstart_offset_seed) >> 16); + } + } /* * Register the kernel text, kernel data, initrd, and initial @@ -167,8 +226,13 @@ void __init arm64_memblock_init(void) */ memblock_reserve(__pa(_text), _end - _text); #ifdef CONFIG_BLK_DEV_INITRD - if (initrd_start) - memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start); + if (initrd_start) { + memblock_reserve(initrd_start, initrd_end - initrd_start); + + /* the generic initrd code expects virtual addresses */ + initrd_start = __phys_to_virt(initrd_start); + initrd_end = __phys_to_virt(initrd_end); + } #endif early_init_fdt_scan_reserved_mem(); @@ -298,39 +362,38 @@ void __init mem_init(void) #define MLG(b, t) b, t, ((t) - (b)) >> 30 #define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K) - pr_notice("Virtual kernel memory layout:\n" -#ifdef CONFIG_KASAN - " kasan : 0x%16lx - 0x%16lx (%6ld GB)\n" -#endif - " vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n" -#ifdef CONFIG_SPARSEMEM_VMEMMAP - " vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n" - " 0x%16lx - 0x%16lx (%6ld MB actual)\n" -#endif - " fixed : 0x%16lx - 0x%16lx (%6ld KB)\n" - " PCI I/O : 0x%16lx - 0x%16lx (%6ld MB)\n" - " modules : 0x%16lx - 0x%16lx (%6ld MB)\n" - " memory : 0x%16lx - 0x%16lx (%6ld MB)\n" - " .init : 0x%p" " - 0x%p" " (%6ld KB)\n" - " .text : 0x%p" " - 0x%p" " (%6ld KB)\n" - " .data : 0x%p" " - 0x%p" " (%6ld KB)\n", + pr_notice("Virtual kernel memory layout:\n"); #ifdef CONFIG_KASAN - MLG(KASAN_SHADOW_START, KASAN_SHADOW_END), + pr_cont(" kasan : 0x%16lx - 0x%16lx (%6ld GB)\n", + MLG(KASAN_SHADOW_START, KASAN_SHADOW_END)); #endif - MLG(VMALLOC_START, VMALLOC_END), + pr_cont(" modules : 0x%16lx - 0x%16lx (%6ld MB)\n", + MLM(MODULES_VADDR, MODULES_END)); + pr_cont(" vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n", + MLG(VMALLOC_START, VMALLOC_END)); + pr_cont(" .text : 0x%p" " - 0x%p" " (%6ld KB)\n" + " .rodata : 0x%p" " - 0x%p" " (%6ld KB)\n" + " .init : 0x%p" " - 0x%p" " (%6ld KB)\n" + " .data : 0x%p" " - 0x%p" " (%6ld KB)\n", + MLK_ROUNDUP(_text, __start_rodata), + MLK_ROUNDUP(__start_rodata, _etext), + MLK_ROUNDUP(__init_begin, __init_end), + MLK_ROUNDUP(_sdata, _edata)); #ifdef CONFIG_SPARSEMEM_VMEMMAP - MLG(VMEMMAP_START, - VMEMMAP_START + VMEMMAP_SIZE), - MLM((unsigned long)virt_to_page(PAGE_OFFSET), - (unsigned long)virt_to_page(high_memory)), + pr_cont(" vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n" + " 0x%16lx - 0x%16lx (%6ld MB actual)\n", + MLG(VMEMMAP_START, + VMEMMAP_START + VMEMMAP_SIZE), + MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()), + (unsigned long)virt_to_page(high_memory))); #endif - MLK(FIXADDR_START, FIXADDR_TOP), - MLM(PCI_IO_START, PCI_IO_END), - MLM(MODULES_VADDR, MODULES_END), - MLM(PAGE_OFFSET, (unsigned long)high_memory), - MLK_ROUNDUP(__init_begin, __init_end), - MLK_ROUNDUP(_text, _etext), - MLK_ROUNDUP(_sdata, _edata)); + pr_cont(" fixed : 0x%16lx - 0x%16lx (%6ld KB)\n", + MLK(FIXADDR_START, FIXADDR_TOP)); + pr_cont(" PCI I/O : 0x%16lx - 0x%16lx (%6ld MB)\n", + MLM(PCI_IO_START, PCI_IO_END)); + pr_cont(" memory : 0x%16lx - 0x%16lx (%6ld MB)\n", + MLM(__phys_to_virt(memblock_start_of_DRAM()), + (unsigned long)high_memory)); #undef MLK #undef MLM @@ -343,8 +406,6 @@ void __init mem_init(void) #ifdef CONFIG_COMPAT BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); #endif - BUILD_BUG_ON(TASK_SIZE_64 > MODULES_VADDR); - BUG_ON(TASK_SIZE_64 > MODULES_VADDR); if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; @@ -358,8 +419,8 @@ void __init mem_init(void) void free_initmem(void) { - fixup_init(); free_initmem_default(0); + fixup_init(); } #ifdef CONFIG_BLK_DEV_INITRD @@ -380,3 +441,28 @@ static int __init keepinitrd_setup(char *__unused) __setup("keepinitrd", keepinitrd_setup); #endif + +/* + * Dump out memory limit information on panic. + */ +static int dump_mem_limit(struct notifier_block *self, unsigned long v, void *p) +{ + if (memory_limit != (phys_addr_t)ULLONG_MAX) { + pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20); + } else { + pr_emerg("Memory Limit: none\n"); + } + return 0; +} + +static struct notifier_block mem_limit_notifier = { + .notifier_call = dump_mem_limit, +}; + +static int __init register_mem_limit_dumper(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, + &mem_limit_notifier); + return 0; +} +__initcall(register_mem_limit_dumper); diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index cab7a5be4..757009daa 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -16,9 +16,12 @@ #include #include +#include +#include #include #include #include +#include #include static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); @@ -32,7 +35,7 @@ static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr, if (pmd_none(*pmd)) pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte); - pte = pte_offset_kernel(pmd, addr); + pte = pte_offset_kimg(pmd, addr); do { next = addr + PAGE_SIZE; set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page), @@ -50,7 +53,7 @@ static void __init kasan_early_pmd_populate(pud_t *pud, if (pud_none(*pud)) pud_populate(&init_mm, pud, kasan_zero_pmd); - pmd = pmd_offset(pud, addr); + pmd = pmd_offset_kimg(pud, addr); do { next = pmd_addr_end(addr, end); kasan_early_pte_populate(pmd, addr, next); @@ -67,7 +70,7 @@ static void __init kasan_early_pud_populate(pgd_t *pgd, if (pgd_none(*pgd)) pgd_populate(&init_mm, pgd, kasan_zero_pud); - pud = pud_offset(pgd, addr); + pud = pud_offset_kimg(pgd, addr); do { next = pud_addr_end(addr, end); kasan_early_pmd_populate(pud, addr, next); @@ -96,6 +99,21 @@ asmlinkage void __init kasan_early_init(void) kasan_map_early_shadow(); } +/* + * Copy the current shadow region into a new pgdir. + */ +void __init kasan_copy_shadow(pgd_t *pgdir) +{ + pgd_t *pgd, *pgd_new, *pgd_end; + + pgd = pgd_offset_k(KASAN_SHADOW_START); + pgd_end = pgd_offset_k(KASAN_SHADOW_END); + pgd_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); + do { + set_pgd(pgd_new, *pgd); + } while (pgd++, pgd_new++, pgd != pgd_end); +} + static void __init clear_pgds(unsigned long start, unsigned long end) { @@ -108,20 +126,19 @@ static void __init clear_pgds(unsigned long start, set_pgd(pgd_offset_k(start), __pgd(0)); } -static void __init cpu_set_ttbr1(unsigned long ttbr1) -{ - asm( - " msr ttbr1_el1, %0\n" - " isb" - : - : "r" (ttbr1)); -} - void __init kasan_init(void) { + u64 kimg_shadow_start, kimg_shadow_end; + u64 mod_shadow_start, mod_shadow_end; struct memblock_region *reg; int i; + kimg_shadow_start = (u64)kasan_mem_to_shadow(_text); + kimg_shadow_end = (u64)kasan_mem_to_shadow(_end); + + mod_shadow_start = (u64)kasan_mem_to_shadow((void *)MODULES_VADDR); + mod_shadow_end = (u64)kasan_mem_to_shadow((void *)MODULES_END); + /* * We are going to perform proper setup of shadow memory. * At first we should unmap early shadow (clear_pgds() call bellow). @@ -130,13 +147,33 @@ void __init kasan_init(void) * setup will be finished. */ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir)); - cpu_set_ttbr1(__pa(tmp_pg_dir)); - flush_tlb_all(); + dsb(ishst); + cpu_replace_ttbr1(tmp_pg_dir); clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + vmemmap_populate(kimg_shadow_start, kimg_shadow_end, + pfn_to_nid(virt_to_pfn(_text))); + + /* + * vmemmap_populate() has populated the shadow region that covers the + * kernel image with SWAPPER_BLOCK_SIZE mappings, so we have to round + * the start and end addresses to SWAPPER_BLOCK_SIZE as well, to prevent + * kasan_populate_zero_shadow() from replacing the page table entries + * (PMD or PTE) at the edges of the shadow region for the kernel + * image. + */ + kimg_shadow_start = round_down(kimg_shadow_start, SWAPPER_BLOCK_SIZE); + kimg_shadow_end = round_up(kimg_shadow_end, SWAPPER_BLOCK_SIZE); + kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, - kasan_mem_to_shadow((void *)MODULES_VADDR)); + (void *)mod_shadow_start); + kasan_populate_zero_shadow((void *)kimg_shadow_end, + kasan_mem_to_shadow((void *)PAGE_OFFSET)); + + if (kimg_shadow_start > mod_shadow_end) + kasan_populate_zero_shadow((void *)mod_shadow_end, + (void *)kimg_shadow_start); for_each_memblock(memory, reg) { void *start = (void *)__phys_to_virt(reg->base); @@ -165,8 +202,7 @@ void __init kasan_init(void) pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO)); memset(kasan_zero_page, 0, PAGE_SIZE); - cpu_set_ttbr1(__pa(swapper_pg_dir)); - flush_tlb_all(); + cpu_replace_ttbr1(swapper_pg_dir); /* At this point kasan is fully initialized. Enable error messages */ init_task.kasan_depth = 0; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 58faeaa7f..f3e5c7423 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -30,8 +30,10 @@ #include #include +#include #include #include +#include #include #include #include @@ -44,13 +46,20 @@ u64 idmap_t0sz = TCR_T0SZ(VA_BITS); +u64 kimage_voffset __read_mostly; +EXPORT_SYMBOL(kimage_voffset); + /* * Empty_zero_page is a special page that is used for zero-initialized data * and COW. */ -struct page *empty_zero_page; +unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); +static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; +static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused; +static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused; + pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { @@ -62,16 +71,30 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, } EXPORT_SYMBOL(phys_mem_access_prot); -static void __init *early_alloc(unsigned long sz) +static phys_addr_t __init early_pgtable_alloc(void) { phys_addr_t phys; void *ptr; - phys = memblock_alloc(sz, sz); + phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE); BUG_ON(!phys); - ptr = __va(phys); - memset(ptr, 0, sz); - return ptr; + + /* + * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE + * slot will be free, so we can (ab)use the FIX_PTE slot to initialise + * any level of table. + */ + ptr = pte_set_fixmap(phys); + + memset(ptr, 0, PAGE_SIZE); + + /* + * Implicit barriers also ensure the zeroed page is visible to the page + * table walker + */ + pte_clear_fixmap(); + + return phys; } /* @@ -95,24 +118,30 @@ static void split_pmd(pmd_t *pmd, pte_t *pte) static void alloc_init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot, - void *(*alloc)(unsigned long size)) + phys_addr_t (*pgtable_alloc)(void)) { pte_t *pte; if (pmd_none(*pmd) || pmd_sect(*pmd)) { - pte = alloc(PTRS_PER_PTE * sizeof(pte_t)); + phys_addr_t pte_phys; + BUG_ON(!pgtable_alloc); + pte_phys = pgtable_alloc(); + pte = pte_set_fixmap(pte_phys); if (pmd_sect(*pmd)) split_pmd(pmd, pte); - __pmd_populate(pmd, __pa(pte), PMD_TYPE_TABLE); + __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); flush_tlb_all(); + pte_clear_fixmap(); } BUG_ON(pmd_bad(*pmd)); - pte = pte_offset_kernel(pmd, addr); + pte = pte_set_fixmap_offset(pmd, addr); do { set_pte(pte, pfn_pte(pfn, prot)); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); + + pte_clear_fixmap(); } static void split_pud(pud_t *old_pud, pmd_t *pmd) @@ -127,10 +156,29 @@ static void split_pud(pud_t *old_pud, pmd_t *pmd) } while (pmd++, i++, i < PTRS_PER_PMD); } -static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, - unsigned long addr, unsigned long end, +#ifdef CONFIG_DEBUG_PAGEALLOC +static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) +{ + + /* + * If debug_page_alloc is enabled we must map the linear map + * using pages. However, other mappings created by + * create_mapping_noalloc must use sections in some cases. Allow + * sections to be used in those cases, where no pgtable_alloc + * function is provided. + */ + return !pgtable_alloc || !debug_pagealloc_enabled(); +} +#else +static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) +{ + return true; +} +#endif + +static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - void *(*alloc)(unsigned long size)) + phys_addr_t (*pgtable_alloc)(void)) { pmd_t *pmd; unsigned long next; @@ -139,7 +187,10 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, * Check for initial section mappings in the pgd/pud and remove them. */ if (pud_none(*pud) || pud_sect(*pud)) { - pmd = alloc(PTRS_PER_PMD * sizeof(pmd_t)); + phys_addr_t pmd_phys; + BUG_ON(!pgtable_alloc); + pmd_phys = pgtable_alloc(); + pmd = pmd_set_fixmap(pmd_phys); if (pud_sect(*pud)) { /* * need to have the 1G of mappings continue to be @@ -147,19 +198,20 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, */ split_pud(pud, pmd); } - pud_populate(mm, pud, pmd); + __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE); flush_tlb_all(); + pmd_clear_fixmap(); } BUG_ON(pud_bad(*pud)); - pmd = pmd_offset(pud, addr); + pmd = pmd_set_fixmap_offset(pud, addr); do { next = pmd_addr_end(addr, end); /* try section mapping first */ - if (((addr | next | phys) & ~SECTION_MASK) == 0) { + if (((addr | next | phys) & ~SECTION_MASK) == 0 && + block_mappings_allowed(pgtable_alloc)) { pmd_t old_pmd =*pmd; - set_pmd(pmd, __pmd(phys | - pgprot_val(mk_sect_prot(prot)))); + pmd_set_huge(pmd, phys, prot); /* * Check for previous table entries created during * boot (__create_page_tables) and flush them. @@ -167,17 +219,19 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, if (!pmd_none(old_pmd)) { flush_tlb_all(); if (pmd_table(old_pmd)) { - phys_addr_t table = __pa(pte_offset_map(&old_pmd, 0)); + phys_addr_t table = pmd_page_paddr(old_pmd); if (!WARN_ON_ONCE(slab_is_available())) memblock_free(table, PAGE_SIZE); } } } else { alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys), - prot, alloc); + prot, pgtable_alloc); } phys += next - addr; } while (pmd++, addr = next, addr != end); + + pmd_clear_fixmap(); } static inline bool use_1G_block(unsigned long addr, unsigned long next, @@ -192,31 +246,32 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, return true; } -static void alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, - unsigned long addr, unsigned long end, +static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - void *(*alloc)(unsigned long size)) + phys_addr_t (*pgtable_alloc)(void)) { pud_t *pud; unsigned long next; if (pgd_none(*pgd)) { - pud = alloc(PTRS_PER_PUD * sizeof(pud_t)); - pgd_populate(mm, pgd, pud); + phys_addr_t pud_phys; + BUG_ON(!pgtable_alloc); + pud_phys = pgtable_alloc(); + __pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE); } BUG_ON(pgd_bad(*pgd)); - pud = pud_offset(pgd, addr); + pud = pud_set_fixmap_offset(pgd, addr); do { next = pud_addr_end(addr, end); /* * For 4K granule only, attempt to put down a 1GB block */ - if (use_1G_block(addr, next, phys)) { + if (use_1G_block(addr, next, phys) && + block_mappings_allowed(pgtable_alloc)) { pud_t old_pud = *pud; - set_pud(pud, __pud(phys | - pgprot_val(mk_sect_prot(prot)))); + pud_set_huge(pud, phys, prot); /* * If we have an old value for a pud, it will @@ -228,26 +283,28 @@ static void alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, if (!pud_none(old_pud)) { flush_tlb_all(); if (pud_table(old_pud)) { - phys_addr_t table = __pa(pmd_offset(&old_pud, 0)); + phys_addr_t table = pud_page_paddr(old_pud); if (!WARN_ON_ONCE(slab_is_available())) memblock_free(table, PAGE_SIZE); } } } else { - alloc_init_pmd(mm, pud, addr, next, phys, prot, alloc); + alloc_init_pmd(pud, addr, next, phys, prot, + pgtable_alloc); } phys += next - addr; } while (pud++, addr = next, addr != end); + + pud_clear_fixmap(); } /* * Create the page directory entries and any necessary page tables for the * mapping specified by 'md'. */ -static void __create_mapping(struct mm_struct *mm, pgd_t *pgd, - phys_addr_t phys, unsigned long virt, +static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, - void *(*alloc)(unsigned long size)) + phys_addr_t (*pgtable_alloc)(void)) { unsigned long addr, length, end, next; @@ -265,22 +322,35 @@ static void __create_mapping(struct mm_struct *mm, pgd_t *pgd, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(mm, pgd, addr, next, phys, prot, alloc); + alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc); phys += next - addr; } while (pgd++, addr = next, addr != end); } -static void *late_alloc(unsigned long size) +static phys_addr_t late_pgtable_alloc(void) { - void *ptr; - - BUG_ON(size > PAGE_SIZE); - ptr = (void *)__get_free_page(PGALLOC_GFP); + void *ptr = (void *)__get_free_page(PGALLOC_GFP); BUG_ON(!ptr); - return ptr; + + /* Ensure the zeroed page is visible to the page table walker */ + dsb(ishst); + return __pa(ptr); } -static void __init create_mapping(phys_addr_t phys, unsigned long virt, +static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*alloc)(void)) +{ + init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc); +} + +/* + * This function can only be used to modify existing table entries, + * without allocating new levels of table. Note that this permits the + * creation of new section or page entries. + */ +static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { if (virt < VMALLOC_START) { @@ -288,16 +358,16 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_mapping(&init_mm, pgd_offset_k(virt), phys, virt, - size, prot, early_alloc); + __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, + NULL); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - __create_mapping(mm, pgd_offset(mm, virt), phys, virt, size, prot, - late_alloc); + __create_pgd_mapping(mm->pgd, phys, virt, size, prot, + late_pgtable_alloc); } static void create_mapping_late(phys_addr_t phys, unsigned long virt, @@ -309,69 +379,57 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt, return; } - return __create_mapping(&init_mm, pgd_offset_k(virt), - phys, virt, size, prot, late_alloc); + __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, + late_pgtable_alloc); } -#ifdef CONFIG_DEBUG_RODATA -static void __init __map_memblock(phys_addr_t start, phys_addr_t end) +static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end) { + unsigned long kernel_start = __pa(_stext); + unsigned long kernel_end = __pa(_etext); + /* - * Set up the executable regions using the existing section mappings - * for now. This will get more fine grained later once all memory - * is mapped + * Take care not to create a writable alias for the + * read-only text and rodata sections of the kernel image. */ - unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE); - unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE); - - if (end < kernel_x_start) { - create_mapping(start, __phys_to_virt(start), - end - start, PAGE_KERNEL); - } else if (start >= kernel_x_end) { - create_mapping(start, __phys_to_virt(start), - end - start, PAGE_KERNEL); - } else { - if (start < kernel_x_start) - create_mapping(start, __phys_to_virt(start), - kernel_x_start - start, - PAGE_KERNEL); - create_mapping(kernel_x_start, - __phys_to_virt(kernel_x_start), - kernel_x_end - kernel_x_start, - PAGE_KERNEL_EXEC); - if (kernel_x_end < end) - create_mapping(kernel_x_end, - __phys_to_virt(kernel_x_end), - end - kernel_x_end, - PAGE_KERNEL); + + /* No overlap with the kernel text */ + if (end < kernel_start || start >= kernel_end) { + __create_pgd_mapping(pgd, start, __phys_to_virt(start), + end - start, PAGE_KERNEL, + early_pgtable_alloc); + return; } + /* + * This block overlaps the kernel text mapping. + * Map the portion(s) which don't overlap. + */ + if (start < kernel_start) + __create_pgd_mapping(pgd, start, + __phys_to_virt(start), + kernel_start - start, PAGE_KERNEL, + early_pgtable_alloc); + if (kernel_end < end) + __create_pgd_mapping(pgd, kernel_end, + __phys_to_virt(kernel_end), + end - kernel_end, PAGE_KERNEL, + early_pgtable_alloc); + + /* + * Map the linear alias of the [_stext, _etext) interval as + * read-only/non-executable. This makes the contents of the + * region accessible to subsystems such as hibernate, but + * protects it from inadvertent modification or execution. + */ + __create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start), + kernel_end - kernel_start, PAGE_KERNEL_RO, + early_pgtable_alloc); } -#else -static void __init __map_memblock(phys_addr_t start, phys_addr_t end) -{ - create_mapping(start, __phys_to_virt(start), end - start, - PAGE_KERNEL_EXEC); -} -#endif -static void __init map_mem(void) +static void __init map_mem(pgd_t *pgd) { struct memblock_region *reg; - phys_addr_t limit; - - /* - * Temporarily limit the memblock range. We need to do this as - * create_mapping requires puds, pmds and ptes to be allocated from - * memory addressable from the initial direct kernel mapping. - * - * The initial direct kernel mapping, located at swapper_pg_dir, gives - * us PUD_SIZE (with SECTION maps) or PMD_SIZE (without SECTION maps, - * memory starting from PHYS_OFFSET (which must be aligned to 2MB as - * per Documentation/arm64/booting.txt). - */ - limit = PHYS_OFFSET + SWAPPER_INIT_MAP_SIZE; - memblock_set_current_limit(limit); /* map all the memory banks */ for_each_memblock(memory, reg) { @@ -383,69 +441,94 @@ static void __init map_mem(void) if (memblock_is_nomap(reg)) continue; - if (ARM64_SWAPPER_USES_SECTION_MAPS) { - /* - * For the first memory bank align the start address and - * current memblock limit to prevent create_mapping() from - * allocating pte page tables from unmapped memory. With - * the section maps, if the first block doesn't end on section - * size boundary, create_mapping() will try to allocate a pte - * page, which may be returned from an unmapped area. - * When section maps are not used, the pte page table for the - * current limit is already present in swapper_pg_dir. - */ - if (start < limit) - start = ALIGN(start, SECTION_SIZE); - if (end < limit) { - limit = end & SECTION_MASK; - memblock_set_current_limit(limit); - } - } - __map_memblock(start, end); + __map_memblock(pgd, start, end); } - - /* Limit no longer required. */ - memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); } -static void __init fixup_executable(void) +void mark_rodata_ro(void) { -#ifdef CONFIG_DEBUG_RODATA - /* now that we are actually fully mapped, make the start/end more fine grained */ - if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) { - unsigned long aligned_start = round_down(__pa(_stext), - SWAPPER_BLOCK_SIZE); + unsigned long section_size; - create_mapping(aligned_start, __phys_to_virt(aligned_start), - __pa(_stext) - aligned_start, - PAGE_KERNEL); - } + section_size = (unsigned long)__start_rodata - (unsigned long)_stext; + create_mapping_late(__pa(_stext), (unsigned long)_stext, + section_size, PAGE_KERNEL_ROX); + /* + * mark .rodata as read only. Use _etext rather than __end_rodata to + * cover NOTES and EXCEPTION_TABLE. + */ + section_size = (unsigned long)_etext - (unsigned long)__start_rodata; + create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata, + section_size, PAGE_KERNEL_RO); +} - if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) { - unsigned long aligned_end = round_up(__pa(__init_end), - SWAPPER_BLOCK_SIZE); - create_mapping(__pa(__init_end), (unsigned long)__init_end, - aligned_end - __pa(__init_end), - PAGE_KERNEL); - } -#endif +void fixup_init(void) +{ + /* + * Unmap the __init region but leave the VM area in place. This + * prevents the region from being reused for kernel modules, which + * is not supported by kallsyms. + */ + unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); } -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void) +static void __init map_kernel_chunk(pgd_t *pgd, void *va_start, void *va_end, + pgprot_t prot, struct vm_struct *vma) { - create_mapping_late(__pa(_stext), (unsigned long)_stext, - (unsigned long)_etext - (unsigned long)_stext, - PAGE_KERNEL_ROX); + phys_addr_t pa_start = __pa(va_start); + unsigned long size = va_end - va_start; + + BUG_ON(!PAGE_ALIGNED(pa_start)); + BUG_ON(!PAGE_ALIGNED(size)); + + __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, + early_pgtable_alloc); + + vma->addr = va_start; + vma->phys_addr = pa_start; + vma->size = size; + vma->flags = VM_MAP; + vma->caller = __builtin_return_address(0); + vm_area_add_early(vma); } -#endif -void fixup_init(void) +/* + * Create fine-grained mappings for the kernel. + */ +static void __init map_kernel(pgd_t *pgd) { - create_mapping_late(__pa(__init_begin), (unsigned long)__init_begin, - (unsigned long)__init_end - (unsigned long)__init_begin, - PAGE_KERNEL); + static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_init, vmlinux_data; + + map_kernel_chunk(pgd, _stext, __start_rodata, PAGE_KERNEL_EXEC, &vmlinux_text); + map_kernel_chunk(pgd, __start_rodata, _etext, PAGE_KERNEL, &vmlinux_rodata); + map_kernel_chunk(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC, + &vmlinux_init); + map_kernel_chunk(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data); + + if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) { + /* + * The fixmap falls in a separate pgd to the kernel, and doesn't + * live in the carveout for the swapper_pg_dir. We can simply + * re-use the existing dir for the fixmap. + */ + set_pgd(pgd_offset_raw(pgd, FIXADDR_START), + *pgd_offset_k(FIXADDR_START)); + } else if (CONFIG_PGTABLE_LEVELS > 3) { + /* + * The fixmap shares its top level pgd entry with the kernel + * mapping. This can really only occur when we are running + * with 16k/4 levels, so we can simply reuse the pud level + * entry instead. + */ + BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); + set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START), + __pud(__pa(bm_pmd) | PUD_TYPE_TABLE)); + pud_clear_fixmap(); + } else { + BUG(); + } + + kasan_copy_shadow(pgd); } /* @@ -454,28 +537,35 @@ void fixup_init(void) */ void __init paging_init(void) { - void *zero_page; + phys_addr_t pgd_phys = early_pgtable_alloc(); + pgd_t *pgd = pgd_set_fixmap(pgd_phys); - map_mem(); - fixup_executable(); + map_kernel(pgd); + map_mem(pgd); - /* allocate the zero page. */ - zero_page = early_alloc(PAGE_SIZE); - - bootmem_init(); - - empty_zero_page = virt_to_page(zero_page); + /* + * We want to reuse the original swapper_pg_dir so we don't have to + * communicate the new address to non-coherent secondaries in + * secondary_entry, and so cpu_switch_mm can generate the address with + * adrp+add rather than a load from some global variable. + * + * To do this we need to go via a temporary pgd. + */ + cpu_replace_ttbr1(__va(pgd_phys)); + memcpy(swapper_pg_dir, pgd, PAGE_SIZE); + cpu_replace_ttbr1(swapper_pg_dir); - /* Ensure the zero page is visible to the page table walker */ - dsb(ishst); + pgd_clear_fixmap(); + memblock_free(pgd_phys, PAGE_SIZE); /* - * TTBR0 is only used for the identity mapping at this stage. Make it - * point to zero page to avoid speculatively fetching new entries. + * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd + * allocated with it. */ - cpu_set_reserved_ttbr0(); - local_flush_tlb_all(); - cpu_set_default_tcr_t0sz(); + memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE, + SWAPPER_DIR_SIZE - PAGE_SIZE); + + bootmem_init(); } /* @@ -562,21 +652,13 @@ void vmemmap_free(unsigned long start, unsigned long end) } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; -#if CONFIG_PGTABLE_LEVELS > 2 -static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss; -#endif -#if CONFIG_PGTABLE_LEVELS > 3 -static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss; -#endif - static inline pud_t * fixmap_pud(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); - return pud_offset(pgd, addr); + return pud_offset_kimg(pgd, addr); } static inline pmd_t * fixmap_pmd(unsigned long addr) @@ -585,16 +667,12 @@ static inline pmd_t * fixmap_pmd(unsigned long addr) BUG_ON(pud_none(*pud) || pud_bad(*pud)); - return pmd_offset(pud, addr); + return pmd_offset_kimg(pud, addr); } static inline pte_t * fixmap_pte(unsigned long addr) { - pmd_t *pmd = fixmap_pmd(addr); - - BUG_ON(pmd_none(*pmd) || pmd_bad(*pmd)); - - return pte_offset_kernel(pmd, addr); + return &bm_pte[pte_index(addr)]; } void __init early_fixmap_init(void) @@ -605,15 +683,26 @@ void __init early_fixmap_init(void) unsigned long addr = FIXADDR_START; pgd = pgd_offset_k(addr); - pgd_populate(&init_mm, pgd, bm_pud); - pud = pud_offset(pgd, addr); + if (CONFIG_PGTABLE_LEVELS > 3 && + !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa(bm_pud))) { + /* + * We only end up here if the kernel mapping and the fixmap + * share the top level pgd entry, which should only happen on + * 16k/4 levels configurations. + */ + BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); + pud = pud_offset_kimg(pgd, addr); + } else { + pgd_populate(&init_mm, pgd, bm_pud); + pud = fixmap_pud(addr); + } pud_populate(&init_mm, pud, bm_pmd); - pmd = pmd_offset(pud, addr); + pmd = fixmap_pmd(addr); pmd_populate_kernel(&init_mm, pmd, bm_pte); /* * The boot-ioremap range spans multiple pmds, for which - * we are not preparted: + * we are not prepared: */ BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); @@ -652,11 +741,10 @@ void __set_fixmap(enum fixed_addresses idx, } } -void *__init fixmap_remap_fdt(phys_addr_t dt_phys) +void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); - pgprot_t prot = PAGE_KERNEL_RO; - int size, offset; + int offset; void *dt_virt; /* @@ -673,7 +761,7 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) /* * Make sure that the FDT region can be mapped without the need to * allocate additional translation table pages, so that it is safe - * to call create_mapping() this early. + * to call create_mapping_noalloc() this early. * * On 64k pages, the FDT will be mapped using PTEs, so we need to * be in the same PMD as the rest of the fixmap. @@ -689,21 +777,73 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) dt_virt = (void *)dt_virt_base + offset; /* map the first chunk so we can read the size from the header */ - create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, - SWAPPER_BLOCK_SIZE, prot); + create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), + dt_virt_base, SWAPPER_BLOCK_SIZE, prot); if (fdt_check_header(dt_virt) != 0) return NULL; - size = fdt_totalsize(dt_virt); - if (size > MAX_FDT_SIZE) + *size = fdt_totalsize(dt_virt); + if (*size > MAX_FDT_SIZE) return NULL; - if (offset + size > SWAPPER_BLOCK_SIZE) - create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, - round_up(offset + size, SWAPPER_BLOCK_SIZE), prot); + if (offset + *size > SWAPPER_BLOCK_SIZE) + create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, + round_up(offset + *size, SWAPPER_BLOCK_SIZE), prot); - memblock_reserve(dt_phys, size); + return dt_virt; +} + +void *__init fixmap_remap_fdt(phys_addr_t dt_phys) +{ + void *dt_virt; + int size; + + dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); + if (!dt_virt) + return NULL; + memblock_reserve(dt_phys, size); return dt_virt; } + +int __init arch_ioremap_pud_supported(void) +{ + /* only 4k granule supports level 1 block mappings */ + return IS_ENABLED(CONFIG_ARM64_4K_PAGES); +} + +int __init arch_ioremap_pmd_supported(void) +{ + return 1; +} + +int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) +{ + BUG_ON(phys & ~PUD_MASK); + set_pud(pud, __pud(phys | PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot)))); + return 1; +} + +int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) +{ + BUG_ON(phys & ~PMD_MASK); + set_pmd(pmd, __pmd(phys | PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot)))); + return 1; +} + +int pud_clear_huge(pud_t *pud) +{ + if (!pud_sect(*pud)) + return 0; + pud_clear(pud); + return 1; +} + +int pmd_clear_huge(pmd_t *pmd) +{ + if (!pmd_sect(*pmd)) + return 0; + pmd_clear(pmd); + return 1; +} diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 0795c3a36..ca6d268e3 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -37,14 +37,31 @@ static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, return 0; } +/* + * This function assumes that the range is mapped with PAGE_SIZE pages. + */ +static int __change_memory_common(unsigned long start, unsigned long size, + pgprot_t set_mask, pgprot_t clear_mask) +{ + struct page_change_data data; + int ret; + + data.set_mask = set_mask; + data.clear_mask = clear_mask; + + ret = apply_to_page_range(&init_mm, start, size, change_page_range, + &data); + + flush_tlb_kernel_range(start, start + size); + return ret; +} + static int change_memory_common(unsigned long addr, int numpages, pgprot_t set_mask, pgprot_t clear_mask) { unsigned long start = addr; unsigned long size = PAGE_SIZE*numpages; unsigned long end = start + size; - int ret; - struct page_change_data data; struct vm_struct *area; if (!PAGE_ALIGNED(addr)) { @@ -75,14 +92,7 @@ static int change_memory_common(unsigned long addr, int numpages, if (!numpages) return 0; - data.set_mask = set_mask; - data.clear_mask = clear_mask; - - ret = apply_to_page_range(&init_mm, start, size, change_page_range, - &data); - - flush_tlb_kernel_range(start, end); - return ret; + return __change_memory_common(start, size, set_mask, clear_mask); } int set_memory_ro(unsigned long addr, int numpages) @@ -114,3 +124,19 @@ int set_memory_x(unsigned long addr, int numpages) __pgprot(PTE_PXN)); } EXPORT_SYMBOL_GPL(set_memory_x); + +#ifdef CONFIG_DEBUG_PAGEALLOC +void __kernel_map_pages(struct page *page, int numpages, int enable) +{ + unsigned long addr = (unsigned long) page_address(page); + + if (enable) + __change_memory_common(addr, PAGE_SIZE * numpages, + __pgprot(PTE_VALID), + __pgprot(0)); + else + __change_memory_common(addr, PAGE_SIZE * numpages, + __pgprot(0), + __pgprot(PTE_VALID)); +} +#endif diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index c164d2cb3..543f51980 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -25,6 +25,8 @@ #include #include #include +#include +#include #include "proc-macros.S" @@ -137,9 +139,47 @@ ENTRY(cpu_do_switch_mm) bfi x0, x1, #48, #16 // set the ASID msr ttbr0_el1, x0 // set TTBR0 isb +alternative_if_not ARM64_WORKAROUND_CAVIUM_27456 ret + nop + nop + nop +alternative_else + ic iallu + dsb nsh + isb + ret +alternative_endif ENDPROC(cpu_do_switch_mm) + .pushsection ".idmap.text", "ax" +/* + * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd) + * + * This is the low-level counterpart to cpu_replace_ttbr1, and should not be + * called by anything else. It can only be executed from a TTBR0 mapping. + */ +ENTRY(idmap_cpu_replace_ttbr1) + mrs x2, daif + msr daifset, #0xf + + adrp x1, empty_zero_page + msr ttbr1_el1, x1 + isb + + tlbi vmalle1 + dsb nsh + isb + + msr ttbr1_el1, x0 + isb + + msr daif, x2 + + ret +ENDPROC(idmap_cpu_replace_ttbr1) + .popsection + /* * __cpu_setup * -- cgit v1.2.3-54-g00ecf